Inflammasomes meet organoids and artificial intelligence: unraveling the complexity of gynecological inflammation

Abstract

Gynecological diseases represent a persistent global health burden. According to a WHO report, the global incidence of gynecological diseases exceeds 65%. Furthermore, over 90% of women suffer from gynecological issues to varying degrees. They account for about 4.5% of the global disease burden. This share is higher than that of other major global health problems. For example, malaria accounts for about 1.04%. Tuberculosis accounts for about 1.9%. Ischemic heart disease accounts for about 2.2%. Mounting evidence suggests that inflammasomes act as master regulators linking chronic inflammation with the onset and progression of gynecological disorders including endometriosis, ovarian cancer, and polycystic ovary syndrome. Yet, traditional two-dimensional cultures and animal models fail to reproduce the intricate immune–endocrine microenvironment of the human reproductive system, impeding translational progress. This review provides an integrated perspective that unites inflammasome biology, organoid technology, and artificial intelligence (AI) into a new research paradigm for precision immunology. We comprehensively summarize the molecular mechanisms of inflammasome activation—particularly NLRP3, AIM2, and IFI16—and their dual roles in inflammatory injury and immune regulation across gynecological diseases. We further highlight advances in organoid-based models that reconstruct the three-dimensional architecture and immune context of reproductive tissues, offering a physiologically relevant platform for mechanistic exploration. In parallel, AI-driven multi-omics analytics and image-based deep learning are shown to accelerate data interpretation, reveal inflammasome-related regulatory networks, and optimize experimental design. By bridging immunopathology, bioengineering, and computational intelligence, this review establishes a conceptual and methodological framework for studying inflammasome-mediated pathogenesis in gynecological diseases. It highlights the transformative capabilities of AI-assisted organoid systems in identifying biomarkers, predicting therapeutic responses, and enabling individualized immunomodulatory strategies—laying a foundation for next-generation translational research in reproductive immunology. To provide a comprehensive overview of recent advances in this field, we conducted a literature search primarily using the PubMed database, with keywords including “inflammasome,” “artificial intelligence,” “organoid,” and “gynecological inflammation,” as well as related terms. The review mainly focuses on experimental and methodological studies published within the past five years, aiming to reflect the most current developments in this rapidly evolving area.

1 Introduction

Gynecological diseases constitute a major and widespread risk to global public health; their aggregate burden is reported to surpass that of malaria and tuberculosis (1). Despite advances in medical studies, several obstacles persist in clinical care. Endometriosis is frequently diagnosed after prolonged delay, and there is an absence of reliable diagnostic biomarkers (2, 3). Treatment of ovarian cancer is often complicated by recurrences and drug resistance, and there is insufficient research on the immune environment of ovarian cancer (4, 5). Accordingly, further elucidation of the complex pathogenesis of gynecological diseases is crucial for optimizing treatment strategies. Inflammasomes are key multiprotein complexes of innate immunity that activate caspase-1 to induce pyroptosis by recognizing pathogen-associated molecular patterns (PAMPs) as well as damage-associated molecular patterns (DAMPs) (6, 7). Inflammasomes directly drive inflammation, encompassing both infectious and sterile inflammatory responses, thereby contributing to classic gynecological inflammatory diseases such as reproductive tract inflammation, endometritis, and oophoritis. Furthermore, alterations in the inflammatory microenvironment caused by inflammasome-driven inflammation can lead to pregnancy-related complications, including recurrent implantation failure, miscarriage, and preeclampsia. In the pathogenesis of these pregnancy-associated disorders, inflammasome-mediated disruption of inflammatory homeostasis lies at the core of the disease mechanism (8–11). As a central regulatory hub of innate immunity, the inflammasome is central to understanding these pathologies. Nevertheless, conventional models remain poorly suited to resolve the mechanisms governing its activation. Two-dimensional cell culture systems cannot reconstruct the complex cell interactions and signaling networks found in the three-dimensional microenvironment in vivo. Due to species differences, animal models also have limitations in accurately simulating the characteristics of human gynecological diseases, particularly in the regulation of estrogen-dependent inflammation. These issues pose significant challenges to the clinical translation of inflammasome-targeted drugs, creating what is known as the “translational bottleneck” (12–14).

Organoids, 3D cell clusters formed through the differentiation and self-organization of stem cells, could highly recapitulate the heterogeneity, structure, and physiological functions of their source tissues, providing an unprecedented “in vitro window” for studying gynecological diseases (15). The conversion of two-dimensional cell models into three-dimensional organoids is a process in which a three-dimensional microenvironment is constructed and developmental signals are regulated to enable the self-organization of monolayer cells. Seed cells are first expanded in a two-dimensional system and then embedded in a matrix scaffold to simulate the physical and chemical microenvironment in vivo (16); with the aid of growth factors and other means to precisely regulate signaling pathways, cells are driven to aggregate, establish polarity, and differentiate into multiple cell types; ultimately, they spontaneously form three-dimensional organoids with organ-like structures and functions (17). As three-dimensional cell aggregates, the construction of organoids mainly depends, in addition to cells, on customized culture media, specific growth factors and inhibitors, three-dimensional culture modes, and artificial scaffold materials. By adding key factors such as estrogen to regulate cells (18); by using Matrigel embedding, air-liquid interface, or suspension culture to construct a three-dimensional microenvironment; and by using materials such as Matrigel and synthetic hydrogels to provide physical support, cells ultimately self-assemble into functional organoid structures (19, 20). Compared with the in vitro culture of human tissues, organoids have broad sources, can be stably passaged and cultured for a long time, have a short construction cycle, and offer strong controllability; whereas human tissues, although closer to the real in vivo state, suffer from scarce sample sources, strong individual heterogeneity, short in vitro survival time, and ethical restrictions. Therefore, the construction of organoids is more suitable for standardized and high-throughput operations, providing ideas for AI-assisted research.

Organoid in vitro models and animal experiments can complement and cross-validate one another. However, organoid culture systems are inherently simplified, lacking, for example, a complete vascular network, an immune microenvironment, and systemic metabolic regulation (21). Conversely, animal models are subject to species differences and cannot achieve complete accuracy when simulating human gynecological diseases (22, 23). Both approaches have their own limitations. Therefore, organoids can be used independently for preliminary mechanistic exploration and drug screening, with key research findings subsequently validated through animal experiments, thereby more accurately reflecting human pathophysiological processes.

Artificial intelligence (AI) tools offer the necessary capabilities to process and analyze the massive, high-dimensional data generated by such high-fidelity models. Currently, AI is being used for the standardization and high-throughput construction of organoids (24), dynamic monitoring of inflammasome activation (25), and multi-omics integration to uncover the regulatory networks of inflammasomes in tumor microenvironments (26, 27).

The integration of inflammasome mechanism analysis, organoid model construction, and AI technology is rapidly becoming a new trend in precision research for gynecological diseases. AI has been used to conduct deep learning to target key genes in the NLRP3 pathway by profiling the transcriptome of endometrioid organoids (28) and track immune-tumor cell interactions in ovarian cancer organoids using microfluidic technology (29). This review systematically examines the pathogenic mechanisms of inflammasomes in gynecological diseases, the methods and technical bottlenecks of organoid model construction, and the enabling role of AI technology in the study of inflammasomes through multi-omics integration, image analysis, and experimental optimization. The review also looks forward to the future prospects of integrating these three approaches to the precise diagnosis and treatments of gynecological diseases. It aims to provide theoretical support and practical paths for related fields.

2 Inflammasomes

2.1 Overview of inflammasomes

The inflammasome is a multiprotein complex that detects pathogen-associated molecular patterns (PAMPs) and damage-associated molecular patterns (DAMPs) via pattern recognition receptors (PRRs), thereby modulating the activation of caspase-1.It also facilitates the maturation and secretion of pro-IL-1β and pro-IL-18, thereby contributing to the innate immune defense response (30, 31). It controls caspase-1-dependent programmed cell death. Under pathological conditions like inflammation and stress, this process induces cell death and drives inflammatory response activation (32). All in all, inflammasomes promote the release and maturation of various pro-inflammatory factors, thus contributing to inflammation and pyroptosis.It is worth distinguishing that pyroptosis is a caspase-dependent programmed cell death mode, characterized by the activation of inflammatory factors and the formation of cell membrane pores (33). On the other hand, extracellular vesicles (EVs) are phospholipid bilayer structures secreted by cells, which can transfer active substances and important mediators in the body and act as messengers for intercellular communication (34).

2.2 Structure and function of inflammasomes

The inflammasome comprises three components: sensor proteins, adaptor proteins, and effector proteases. Sensor proteins are the primary basis for the classification of inflammasome subtypes and can be divided into the PYHIN and NLR families (11, 35). These proteins detect and transmit signals induced by self or non-self stimuli. PYHIN inflammasomes primarily detect double-stranded DNA. Their function is critical in viral infection-related gynecological diseases. IFI16 is a PYHIN protein. It increases PD-L1 expression via the STING-TBK1-NF-κB pathway, thereby accelerating the progression of cervical cancer (36). Members of the NLR family are stimulated by pathogen proteins and metabolites, contributing to the development of gynecological inflammatory diseases (37). Exploring the targets of sensor proteins in both families may aid in developing targeted therapies for cervical cancer.

The adaptor protein ASC, an apoptosis-associated speck-like protein containing caspase activation and recruitment domains, serves as a molecular bridge connecting sensor proteins with effector proteases. Upon receiving signals from sensor proteins, ASC activates effector proteases.

Effector proteases are the final components of the inflammasome and are responsible for promoting the maturation of IL-1β and IL-18 precursors. Additionally, effector proteases cleave PRO-GSDMD to form GSDMD. GSDMD can oligomerize to form perforations in the target cell membrane, promoting the active efflux of IL-1β and IL-18 from the target cells, thereby initiating inflammation (38).

2.3 The role of inflammasomes in gynecological diseases

Inflammasomes can either directly or indirectly help to release many pro-inflammatory chemicals, trigger something called pyroptosis, and recruit immune cells. They play a really important role in the start and development of gynaecological disorders, like endometriosis, ovarian cancer, polycystic ovary syndrome and miscarriage (11, 32).

2.3.1 Inflammasomes and endometriosis

Endometriosis is a chronic gynecological condition affecting approximately 5–10% of women of reproductive age worldwide, characterized by the ectopic implantation and growth of endometrial tissue outside the uterine cavity (39, 40). While endometriosis is considered a benign gynecological disease, it significantly impacts patients’ lives. The severity of endometriosis correlates with the viability index and migration activity of ectopic human endometrial stromal cells (hESC). Elevated expression of the NLRP3 inflammasome enhances the viability and migration of human endometrial stromal cells (hESCs) via the NLRP3/caspase-1/IL-1β signaling pathway, thereby driving disease progression (41, 42).

Endometriosis is estrogen-dependent. Elevated levels of estrogen receptor β (ER-β) in pathological tissues lead to excessive activation of the NLRP3 inflammasome. This inflammasome activation increases the production of IL-18 and IL-1β, which promote cell adhesion and proliferation (43). Symptoms of endometriosis often correlate with the menstrual cycle. During menstruation, NF-κB activation significantly increases NLRP3 and ASC levels, triggering an inflammatory response similar to that seen in menstrual endometrium (44). Inhibiting the ROS/NLRP3 inflammasome signaling pathway alleviated endometrial fibrosis (45). While targeting inflammasomes can induce pyroptosis in ectopic endometrial cells, excessive inflammasome activation may also cause tissue damage (46) (Figure 1A).

Figure 1

2.3.2 Inflammasomes and ovarian cancer

In ovarian cancer, increased NLRP3 inflammasome levels promote the expression of immune checkpoints such as PD-1, PD-L1, and LAG3 in cancer cells, facilitating immune escape. As a result, high NLRP3 levels are often associated with poor prognosis in ovarian cancer (47). Activation of inflammasomes induces the production of IL-18 and IL-1β, promoting chronic inflammation, inhibiting NK and T-cell surveillance, and facilitating cancer progression (48). However, some evidence suggests that inflammasomes may inhibit cancer development. For instance, nobiletin induces ROS release, activating inflammasomes and promoting pyroptosis in ovarian cancer cells (49, 50). In mouse models, depletion of NLRP3 inflammasomes in macrophages significantly increased cancer cell growth and metastasis, possibly due to reduced macrophage phagocytosis and fewer cytotoxic CD8+ T cells (51). Inflammasome-mediated pyroptosis can cause cell membrane perforation, leading to cell swelling and inhibition of ovarian cancer development (52). Cisplatin resistance in ovarian cancer cells may be associated with the suppression of NLRP3 activation by estrogen-related receptor α (ERRα), which consequently inhibits pyroptosis (53). However, the role of inflammasomes in ovarian cancer remains controversial, and further studies are needed (54) (Figure 1B).

2.3.3 Inflammasomes and pregnancy-related diseases

Pregnancy is a intricate and lengthy process, encompassing stages from fertilization to embryo development and birth. Pregnancy is maintained by a unique immune state. Its success depends on a stable inflammatory environment regulated by inflammasomes. Under pathological inflammatory conditions, however, excessive or insufficient inflammasome activity disrupts this immune equilibrium. This disruption leads to adverse pregnancy outcomes and complications, such as recurrent implantation failure (RIF), spontaneous miscarriage, preterm birth, and preeclampsia. Consequently, these pregnancy-related disorders form an essential part of any discussion on inflammasome-associated gynecological inflammation. They demonstrate how dysregulation of inflammasome-mediated inflammation drives pregnancy complications and adverse outcomes. NLRP3 is abundantly expressed in the human endometrium during the mid-proliferative and mid-secretory phases, promoting the transcriptional upregulation of NLRP3 inflammasome-related genes by binding to ER-β. Moreover, NLRP3 facilitates embryo implantation through inflammasome-dependent and independent pathways, enhancing EMT in Ishikawa (IK) cells, thus making the endometrium more receptive to embryo adhesion and implantation (55).

However, dysregulated activation of the inflammasome can impair embryo implantation, resulting in recurrent implantation failure and spontaneous miscarriage (56). During pregnancy, cholesterol crystals can accumulate in the decidua, activating the NLRP3 inflammasome and leading to decidual inflammation, which increases the risk of miscarriage (57).

In the case of recurrent miscarriage, intestinal leakage and lipopolysaccharide (LPS) may enter the bloodstream, causing excessive activation of the NLRP3 inflammasome in the endometrium (56). Additionally, during spontaneous abortion, NLRP3 inflammasome activation adversely affects endometrial receptivity by promoting inflammatory responses in the placenta and accelerating placental aging (58, 59). The NLRP7 inflammasome, a member of the NLR family, is also a cause of recurrent complete hydatidiform mole. NLRP7 inflammasomes promote the transformation of recurrent complete hydatidiform mole into gestational choriocarcinoma by enhancing the proliferation and three-dimensional structure construction of gestational choriocarcinoma cells in an inflammasome-independent manner, while simultaneously inhibiting the maternal immune response and accelerating carcinogenesis (60). Additionally, the NLRC4 inflammasome has been shown to contribute to term premature rupture of membranes (TPROM) (61), and may also be associated with NLRP3 inflammasome overactivation in preterm membrane rupture (PROM) (62). NLRP3 inactivation in the human uterus contributes to its resting state, and promoting its activation can trigger parturition (63, 64) (Figure 1C).

2.3.4 Inflammasomes and vaginitis

Vaginitis is a common gynecological disease with a variety of causes. In persistent fungal vaginitis caused by Candida albicans, activation of the NLRP3 inflammasome and lack of AIM2 inflammasomes can lead to excessive neutrophil aggregation and pyroptosis of vaginal epithelial cells, resulting in damage to the vaginal epithelial mucosa and prolonging the disease (65, 66). Activation of the NLRP3 inflammasome also serves as a pivotal driver of mucosal inflammatory responses, predominantly involving neutrophils, in recurrent vaginal Candida infection (67). Furthermore, inflammasome signaling can have a protective effect against Candida albicansinfections by mediating the cleavage of gasdermin D (GSDMD), a key mediator in the inflammasome pathway (68). It has also been shown that Gardnerella vaginalis can induce bacterial vaginitis by activating NLRP3 inflammasomes and triggering pyroptosis (69) (Figure 1D).

2.3.5 Inflammasomes and polycystic ovary syndrome

Polycystic ovary syndrome (PCOS) is a multifactorial endocrine and metabolic disorder affecting nearly 15% of women of reproductive age worldwide, imposing a substantial economic and health burden on affected individuals (70–73). The clinical features of PCOS encompass hyperandrogenism, elevated testosterone levels, hirsutism, insulin resistance, and infertility (73). In PCOS, ovarian granulosa cells (GC) surround oocytes to form follicles, providing a suitable environment for follicle maturation. However, elevated levels of NLRP3 inflammasomes induce granulosa cell pyroptosis, accelerating the onset and progression of the disease (74). Chronic ovarian inflammation, driven by IL-18 and IL-1β released upon inflammasome activation, also promotes ovarian fibrosis and follicular dysfunction, further exacerbating the disease (75). This effect is particularly pronounced in obese patients (75, 76). Reducing inflammasome expression can alleviate heart and kidney diseases associated with PCOS (77). Notably, plumbagin, a therapeutic compound, can inhibit inflammasome-dependent granulosa cell pyroptosis, thus providing a potential treatment for PCOS (78). Moreover, metformin and pioglitazone complex preparations have been shown to alleviate psychological distress in patients with PCOS through the suppression of NLRP3 inflammasome activation (79), whereas acetate has been reported to alleviate PCOS-related complications by reducing androgen excess and attenuating NF-κB/NLRP3 immunoreactivity (80) (Figure 1E).

2.3.6 Inflammasomes and premature ovarian failure

Premature ovarian failure (POI) is a major cause of female infertility and endocrine dysfunction, leading to early menopause and reduced fertility (81). The clinical symptoms of POI include impaired ovarian function, decreased fertility, and premature menopause (82). Premature depletion of ovarian follicles is a major cause of POI, and the inflammatory microenvironment accelerates follicular apoptosis (83). Increased expression of inflammatory markers, including NLRP3 inflammasome, caspase-1, and IL-1β, is observed in the granulosa cells of POI patients. In a POI mouse model, inhibition of NLRP3 expression alleviated follicular apoptosis and ovarian aging, thereby improving ovarian function (84). Traditional Chinese medicine treatments, such as moxibustion, have been demonstrated to downregulate the expression of NLRP3 and ASC, alleviate granulosa cell apoptosis, and improve the ovarian microenvironment, thus promoting follicle growth and delaying follicle depletion (85). Furthermore, the transplantation of placental mesenchymal stem cells (PMSCs) improved ovarian function in POI rats by inhibiting NLRP3 inflammasome activation (86) (Figure 1F).

2.3.7 Inflammasomes and cervical cancer

Cervical cancer continues to pose a significant global health burden for women, with high morbidity and mortality rates due to inadequate screening programs (87). The primary etiological factor of cervical cancer is persistent infection with high-risk human papillomavirus (HPV) types, particularly HPV-16 and HPV-18 (88). HPV-16 not only activates AIM2 and IFI16 inflammasomes through its own DNA (89), but also indirectly activates NLRP3 through HPV oncoproteins E6 and E7 (90–92). Both of these mechanisms promote pyroptosis. However, HPV E7 can suppress pyroptosis and evade immune surveillance by recruiting the E3 ubiquitin ligase TRIM21 to mediate the ubiquitination and degradation of the IFI16 inflammasome (93). Reduced levels of IL-1β and IL-18 mRNA in cervical tissue have been identified as risk factors for the progression of CIN to cancer, suggesting that these cytokines could serve as potential biomarkers for risk stratification (94). Additionally, single nucleotide polymorphisms (SNPs) in the NLRP3 gene, particularly rs10754558, have been identified as significant risk factors for cervical cancer (95).

2.3.8 Inflammasomes and pelvic inflammatory disease

Pelvic inflammatory disease (PID) is an infectious inflammation of the female upper reproductive tract, most commonly induced by sexually transmitted pathogens such as Neisseria gonorrhoeae and Chlamydia trachomatis, as well as by microorganisms associated with bacterial vaginosis (96). Studies have shown that Chlamydia trachomatis can effectively activate the NLRP3/caspase-1/IL-1β pathway upon infecting cervical epithelial cells (97). Caspase-1 causes the fragmentation of the host cell Golgi, which provides lipids for Chlamydia replication, leading to prolonged infection (98). Chronic release of downstream cytokines like IL-1β and IL-18 recruits immune cells, aggravating local tissue damage, causing tubal edema, fibrosis, and adhesion, and ultimately leading to severe sequelae (99) (Tables 1, 2).

3 Establishment of organoids and their application in gynecological diseases

3.1 Overview of organoids

The theory of evolutionary conservation of biological principles has made animal models the primary approach to studying the basic mechanisms of development and disease, but even basic biological processes may differ significantly across species (14). However, human-specific processes such as brain development, metabolism, and drug efficacy testing cannot be effectively modeled in animals (13). Organoids, which mimic the physiological and pathological environment of organs, offer a promising platform for such research (12, 123).

Organoids refer to miniature, three-dimensional (3D) cell clusters formed from induced pluripotent stem cells (iPSCs), adult stem cells (ASCs), or patient-derived cells. Self-organising and differentiating into functional cell types, these organoids closely resemble the structure and function of the organs they represent (15, 124). Organoids have vast potential in regenerative medicine, precision medicine and drug research (124). They are being increasingly used in various disease modeling studies (125–127).

3.2 Construction of organoids for gynecological diseases

3.2.1 Establishment of tumor immune microenvironment

The tumor microenvironment (TME) is defined as the complex and diverse environment surrounding tumor cells, comprising various immune cells, tissue cells, adipocytes, and extracellular matrix components. It serves a crucial role by supporting tumor growth and survival (128–130). The immune-related components within TME are collectively termed the tumor immune microenvironment (TIME), which focuses on the immune regulation mechanisms that affect tumor progression (131–133).

Studies have shown that complex interactions between tumour cells, immune cells and local stroma are associated with lymphatic metastasis in cervical cancer (134). For example, tumor-associated macrophage M2 (TAM) in the TME promote the expression of PD-L1 in cervical cancer cells through the PI3K/AKT pathway, enhancing their metastatic and invasive abilities, which affects tumor progression (135). Similarly, metastasis in ovarian cancer is linked to FOXP3+ regulatory T cells, which suppress the growth of effector T cells by producing the immune checkpoint molecule PD-1. This activation of the PD-1/PD-L1 pathway has an immunosuppressive effect on the tumour microenvironment, promoting immune evasion and metastasis (136–138).

Constructing an accurate TIME model is crucial for gynecological disease research, and two main methods are employed: reconstruction models and non-reconstruction models (139). In the reconstructed model, pure tumour cell organoids are co-cultured with exogenous immune cells to mimic the morphological and genetic characteristics of tumours, though these organoids lack endogenous immune infiltration. In the non-reconstructed model, it can preserve tumor cells and their endogenous immune cells, primarily cultivated through two methods:air-liquid interface (ALI) culture and 3D microfluidic culture systems (PDOTS/MDOTS).

ALI culture involves physically dividing patient-derived tumor tissue into small fragments and culturing them in a chamber where one side is exposed to air while the other is immersed in liquid culture medium (29, 125, 140). This method preserves the TME structures, including functional tumor-infiltrating lymphocytes (TILs), and is particularly useful for modeling TIME in vitro.

PDOTS/MDOTS involves embedding tumor spheres from patient-derived tissues in a 3D microfluidic device with collagen for co-culture (29, 140). This approach also preserves multiple functional immune cell populations and enables more precise control of the microenvironment (29, 141). Vikram et al. investigated the influence of neutrophils on the initiation of collective 3D invasion by ovarian tumor cells by designing a novel, microfluidically integrated 3D-TIME-on-chip device. They demonstrated that neutrophil extracellular traps play a crucial role in mediating collective invasion of human ovarian cancer cells from a clustered state (142).

3.2.2 Initial cell population for organoid construction in gynecological diseases

Organoid cultures can be generated from induced pluripotent stem cells (iPSCs), adult stem cells (ASCs), or patient-derived cells (143, 144). Naive cells can self-organize and form tissue-specific organoids when provided with appropriate 3D substrates and specific signaling instructions (144–147). Different cell types follow distinct developmental pathways (127, 144). Organoids derived from iPSCs resemble fetal tissues and are primarily used to understand diseases associated with developmental defects. Organoids derived from ASCs highly recapitulate the homeostasis and regenerative capacity of their source tissues, making them widely employed for disease modeling (148–150).

3.2.2.1 Induced pluripotent stem cells

iPSCs are one of the primary sources for organoid formation, characterized by their self-renewal capacity and ability to differentiate into specialized cell types derived from the three germ layers: ectoderm, endoderm, and mesoderm (151, 152). Gynecological target cells can be obtained by reprogramming patient-derived somatic cells into iPSCs, followed by expansion and differentiation. These somatic cells carry disease-causing mutations or genetic risk factors, and the resulting iPSCs possess a disease-associated genetic background (103, 153). iPSCs derived from BRCA1 mutation patients can differentiate into fallopian tube organoids, which can be modeled to simulate high-grade serous ovarian cancer (154, 155). iPSC-derived organoids can provide insights into early organogenesis and diseases related to developmental defects (12, 148) (Figure 2A).

Figure 2

3.2.2.2 Adult stem cells

ASCs are undifferentiated cells present in specific differentiated tissues that possess high proliferative potential as well as the ability to differentiate into various cell types. Organoids derived from ASCs closely r esemble the tissue of origin and retain its characteristics (156–158). In cancer research, ASCs-derived organoids maintain the genomic integrity and TME of the original tumor (158). Moreover, AdSCs can be directly obtained from regenerating human adult tissues, with their derived organoids mature more closely to adult tissues compared to iPSC-derived organoids, enabling quicker establishment of tumor organoids that accurately simulate original tissues (12, 151) (Figure 2B).

3.2.2.3 Patient-derived cells

Patient-derived cells primarily refer to primary tumor cells obtained directly from the patient’s tumor tissue. Culturing organoids from these cells requires no reprogramming, and the resulting organoids highly preserve heterogeneity while maintaining the key phenotypic and genetic characteristics of the source tumor (159). Patient-derived tumor organoids serve as a vital preclinical model for drug sensitivity prediction and cancer progression research (151, 160) (Figure 2C).

3.2.3 Application of organoid construction in gynecological diseases

Although organoid technology is still in its early phases, it holds tremendous potential in regenerative medicine, drug research, and precision medicine (124). Several gynecological disease organoid models, such as those for ovarian cancer and cervical cancer, have already been established for studying the pathogenesis of gynecological diseases (161).

3.2.3.1 Ovarian cancer

Ovarian cancer (OC) is the deadliest malignant gynecological tumor, ranking eighth in cancer incidence and mortality among women worldwide (162). It is highly heterogeneous, with different subtypes exhibiting distinct clinical and molecular characteristics (163, 164). Organoids derived from ovarian cancer tissues, such as fallopian tube epithelium, ovarian cancer in situ, and ascitic ovarian cancer tissues, have been successfully constructed for disease modeling (164). The collected samples are mechanically and enzymatically digested to form a cell suspension, then plated using basement membrane extract, and supported with a medium supplemented with additives specifically for culturing ovarian cancer cells (165, 166).

Ovarian cancer (OC) organoids, as an emerging preclinical in vitro tool, are crucial for studying pathogenesis (167). The majority of OC cases currently exhibit an epithelial phenotype, known as epithelial ovarian cancer (EOC) (168). It has been reported that organoids derived from EOC can recapitulate the disease and the original tumor phenotype, replicate the genomic and mutational profile of the primary tumor, and have been successfully engineered, providing a foundation for mechanistic studies (169). Additionally, compared to animal models, ovarian cancer organoids possess advantages such as clonality, the potential for high-throughput screening, and lower costs, which simplifies the complex processes in the preclinical drug development phase, making them suitable for drug screening and development (167, 170).

3.2.3.2 Endometriosis

Endometriosis is an estrogen-dependent chronic gynecological condition characterized by the growth of endometrial-like tissue outside the uterus. The resulting chronic pelvic pain and infertility severely impact the well-being of women of reproductive age (3). Meanwhile, it also significantly raises the incidence of OC (171). The application of organoids in modeling this disease has garnered significant interest. For instance, placental protein(Gda) is a glycoprotein produced by the endometrium that mediates several biological processes involved in human reproduction and maternal-fetal immunity. Its gene expression and modification varying throughout the menstrual cycle (172). At the same time, Gda also changes significantly during the menstrual cycle of female patients with Ems (173). Alice et al. found that endometrioid ovarian cancer organoids (EndORG) were able to generalize this specific expression pattern (174). Jiang Research also found that human endometrial organoids (hEO) can summarize the human menstrual cycle dynamics and respond to estrogen treatment (100). Both endometriotic tissue and normal endometrial tissue undergo cyclical changes in response to hormonal fluctuations, but the former exhibits invasive and metastatic properties, whereas the latter does not. Researchers have successfully established endometrial epithelial organoids and endometriotic epithelial organoids. They found that, compared to in situ endometrial epithelial organoids, most endometriotic epithelial organoids took longer to establish, grew more slowly, and had a slightly lower success rate. This may be because fibrosis of the endometrioma wall reduces the proportion of glandular epithelial cells in the ectopic tissue, thereby increasing the difficulty of establishing ectopic endometrial epithelial organoids (175), whereas an appropriate level of estrogen helps promote the establishment of ovarian endometriosis (OE) organoids (101). It can be concluded that the in vitro modeling of Ems by organoids can well summarize the disease, including the original in vivo characteristics. It also provides an excellent experimental model for drug intervention and mechanism research.

3.2.3.3 Cervical cancer

Cervical cancer represents one of the most prevalent malignant tumors among women worldwide (176). It includes several histological types, such as squamous cell carcinoma (SCC), cervical adenocarcinoma (CA), and adenosquamous carcinoma (177). Due to the low detection rate of early-stage CA, its invasiveness, high recurrence rate, and mortality rate pose significant clinical challenges (177). Moreover, the current research on CA lacks sufficient preclinical models, while organoids have the ability to mimic the structure and function of patient tumour tissue, providing accurate and individualised in vitro platforms for disease modeling (177). CA organoids are typically established by taking biopsy tissue, dissociating and separating the cells with collagenase, embedding them in Matrigel matrix, and culturing them in organoid medium (178). These organoids retain host genetic and genomic heterogeneity (117). The development of cervical cancer is significantly influenced by HPV infection. It primarily infects the stratified squamous epithelial cells of the mucosa, where it replicates and proliferates. Epithelial cells with glandular components in the cervix may provide a microenvironment conducive to HPV replication (177). Therefore, CA organoids can be used to simulate the process of HPV-induced tumors. In reality, however, the successful establishment of CA organoids is rare, which may be a finding for future research (117, 177).

3.2.3.4 Polycystic ovary syndrome

PCOS is a complex disorder of the endocrine and metabolic systems. Its primary clinical features include elevated levels of androgens, polycystic ovaries, and impaired ovulation, leading to reproductive dysfunction, chronic low-grade inflammation, and abnormal metabolism like insulin resistance (179). Teerawat et al. investigated the influence of increased androgen concentrations on the endometrium in PCOS patients by establishing scaffold-free multicellular endometrial organoids. They found that excess androgens directly affect endometrial cells (180). Lu et al. also observed the same adverse effects in human trophoblast organoids as those seen in animal models treated with androgen stimulation. Furthermore, these adverse effects could be prevented by blocking androgen receptors (181). A recent study, using endometrial organoids (EEO), identified for the first time a clear link between the GPX4-TGF-β1/Smad2/3 signaling pathway and fibrosis in the endometrial epithelial cells of PCOS, providing a direction for therapeutic strategies to improve PCOS-related endometrial function (114). Thus, the establishment of PCOS organoids not only facilitates the exploration of its pathogenesis but also provides a foundation for therapeutic strategies that reduce the impact of this disease on pregnancy, as well as on women’s overall health (182).

4 Artificial intelligence

4.1 Current status of artificial intelligence in modern medicine

Artificial Intelligence (AI) can be defined as the use of computer systems to imitate intelligent behaviour with minimal human assistance (104). With continuous improvements in algorithmic performance and the rapid accumulation of biomedical data, AI has progressively expanded from predominantly macroscopic applications in clinical imaging–based diagnosis to data interpretation at the cellular and molecular scales, and its potential value in mechanistic research has become increasingly evident. In medical research, AI was initially applied to imaging data analysis; deep learning–based models have demonstrated strong performance in automatically identifying abnormal structures in CT, MRI, and histopathological sections (105, 183–188). These advances have also opened new avenues for applications in gynecological diseases (115, 118, 189–196). However, in recent years, the focus of AI applications has gradually shifted from macroscopic imaging diagnosis toward microscopy-scale biological research.

In high-content imaging (HCI)–based analyses, AI enables automated identification, classification, and quantification of large numbers of cellular and subcellular structures, thereby supporting systematic profiling of complex cellular phenotypes. Using deep learning models, AI can detect subtle morphological differences, changes in intracellular protein distributions, and spatial patterns of subcellular structures. This allows researchers to extract high-dimensional features from large-scale image datasets and to further analyze dynamic cellular responses under different experimental conditions (197, 198). At single-cell resolution, deep learning–assisted microscopic image analysis can capture heterogeneous features within cell populations. This is particularly important for investigating biological events such as dynamic inflammatory responses, immune cell activation, and signal transduction processes, because heterogeneity at the single-cell level is often masked by population-averaged data (199, 200). For example, in inflammasome research, ASC speck formation is a morphological hallmark of activation and can be detected by fluorescence microscopy, flow cytometry, or HCI. AI can not only accurately count these specks but also analyze their spatial distribution and temporal dynamics, enabling quantitative determination of inflammasome activation states (201, 202).

Meanwhile, AI integrates multi-omics data to identify individualized disease risks, pathogenesis, and therapeutic targets (203, 204). High-throughput screening of potential biomarkers through multi-omics integration (116, 205). AI-driven virtual screening, big data mining, and molecular generation algorithms have significantly shortened the development cycle and reduced costs in drug research (206–208). Furthermore, AI-assisted surgical systems, capable of achieving millimeter-level precision in complex surgeries, are becoming increasingly common, significantly enhancing the safety and efficiency of gynecological procedures (209–213). AI also assists novice doctors in performing professional examinations with the accuracy of experienced specialists (214). In addition, AI can integrate multi-source data—such as electronic medical records, pathology reports, and laboratory testing results—to support molecular characterization and longitudinal monitoring of gynecologic diseases (215–218).

Overall, the application of AI in medicine has evolved from macroscopic imaging analysis toward microscopic structural recognition, single-cell phenotypic profiling, and molecular-level data integration. This transition has positioned AI not only as a clinical decision-support tool but also as an increasingly important research approach for interrogating inflammation-related molecular pathways during tumor initiation and progression, thereby providing a technical foundation for systematic investigation of key mechanisms—such as inflammasomes—in organoid models.

4.2 Challenges and application scenarios of AI-assisted organoid research

Traditional organoid culture systems require the precise simulation of the in vivo microenvironment, involving media, extracellular matrix, growth factors, and other components. However, the culture conditions for different types of organs vary greatly, making it challenging to standardize (13, 219, 220). Additionally, traditional culture methods make high-throughput screening difficult, limiting the scale of sample research and drug development (13, 221). Organoid culture thus often relies on trial-and-error methods and expert knowledge, which can be inefficient and inconsistent, despite significant successes in growing organoids.While traditional animal models can fully replicate systemic physiological processes in vivo and support long-term in vivo observation and studies of overall mechanisms, they lack sufficient accuracy in simulating complex conditions such as human gynecological diseases due to species differences. Additionally, they suffer from drawbacks such as long study durations, high costs, strict ethical constraints, and poor experimental reproducibility (222, 223). In contrast, AI-assisted organoid culture can optimize construction strategies by accurately screening matrix materials, optimizing cell culture conditions, and dynamically monitoring culture conditions, cell behavior, and organoid development in real-time (24, 25, 224). It can efficiently process multi-scale images and multi-omics data, enhancing disease modeling, drug screening, immune checkpoint blockade simulations, and other applications, thus accelerating organoid research development (25, 221, 225–227). AI algorithms can analyse data from multiple sources to predict how stem cells will differentiate into specific cell types. This promotes the generation of more complex and precise organoids. This technology has shown potential not only in kidney, retina, and other organoid models (228–230), but also in gynecological-related organoid studies. For example, AI technology can integrate multi-platform metabolomics data to accurately detect intrauterine growth restriction (231, 232). By combining with natural language processing (NLP), AI can further explore and understand the function and regulatory mechanisms of endometriosis-related genes (231, 233). Additionally, AI can be employed to model placental development and assess placental susceptibility to emerging pathogens (234). Although AI-assisted organoid research holds significant value, its in vitro culture systems lack a complete in vivo microenvironment, making it difficult to simulate complex pathophysiological processes. Furthermore, since culture protocols have not yet been fully standardized and AI models rely on in vitro data, this can easily lead to discrepancies between predictive results and actual in vivo conditions (235). Therefore, by utilizing animal models to provide in vivo physiological references and validate the authenticity of organoid functions, AI models can be trained and validated against benchmarks that more closely resemble human diseases, thereby effectively enhancing the reliability of predictions and their clinical translation value.

Additionally, AI has a significant impact on drug research and prediction using organoids. AI technology can assist organ-on-a-chip (OoC) models in simulating the physiological activities and functions of human organs, thereby avoiding the ethical concerns of animal welfare and other drawbacks associated with traditional drug development models (236). In organoid research, AI can also analyze multi-omics data to deeply explore disease mechanisms and drug responses; by analyzing time-series data from organoids, AI can simulate organoid development in both normal and diseased states (237), revealing organoid-specific developmental functions and pathways (238). Furthermore, AI can be used to understand different immune cell phenotypes within the breast tumor microenvironment, offering a better understanding of cancer progression and immune therapy responses (239). In addition, breakthroughs in AI-driven therapeutic target exploration support drug discovery and development, further advancing the field (240, 241).

Nevertheless, several key challenges remain for AI applications in organoid research. First, sample sizes are often limited, particularly in high-throughput single-cell or multi-omics experiments. Insufficient data may lead to inadequate coverage for model training, making it difficult to capture features of rare cell types or complex cellular states and thereby reducing predictive accuracy and generalizability (242–244). Second, batch effects across culture batches, imaging conditions, or experimental platforms can introduce systematic biases that obscure true biological signals and compromise the accurate identification of cellular phenotypes, molecular features, or dynamic responses. Accordingly, algorithmic correction and/or standardized workflows are required to mitigate these confounders (245, 246). Finally, obtaining reliable ground-truth labels in three-dimensional organoid systems remains challenging. Owing to tissue thickness and optical constraints, fluorescent labeling or sectioning may not fully capture internal spatial architecture, leading to missing information in training datasets and increasing the complexity of model validation and interpretation. In addition, limitations in 3D live imaging and labeling technologies restrict the ability of AI models to precisely simulate organoid development and intercellular interactions (247).

Despite these challenges, AI shows great potential in image analysis and dynamic monitoring of organoids. It can precisely diagnose diseases by analyzing large volumes of images, providing technical support for organoid image analysis (248–250). Deep learning (DL) technologies further enhance image analysis. Timothy Kassis’ team created and publicly released a unique dataset that allows AI to fully automate the analysis of thousands of images for human intestinal organoid localization and quantification (251). The following year, Rutger N U Kok’s team developed a semi-automated cell tracker, making it possible to track cells within organoids and directly observe patterns of cell division and differentiation (252). Various machine learning algorithms and deep learning architectures could be used for compound screening and toxicity testing. This would enhance the effectiveness and precision of research, as well as introducing new approaches to drug discovery (26). In organoid immuno-microenvironment studies, AI can assist with single-cell gene expression and immune repertoire analysis (25). Furthermore, DL has a positive impact on improving gynecological cancer screening and diagnosis under resource-limited conditions (253). Additionally, the combination of MRI with advanced automated image analysis tools supports long-term monitoring, analysis, and clinical applications of brain organoids (254). Based on these advancements, we can reasonably infer that AI holds potential in assisting gynecological inflammation-related organoid research, offering new paths for research and treatment in this field (158). In the future, efforts should be made to promote the deep integration of organoids and AI, with animal models serving as auxiliaries, to construct standardized, vascularized, and immune co-cultured multi-organ interaction models, addressing their systemic limitations. At the same time, a unified quality control and regulatory system should be established to promote the complementary advantages of organoids, AI, and animal models, providing an efficient, ethical, and translatable new generation of research paradigms for precision medicine and new drug development.

4.3 AI-assisted study of inflammasomes in organoids

Inflammasomes are critical multi-protein complexes involved in innate immunity. They recognize intracellular pathogen-associated molecular patterns (PAMPs) and damage-associated molecular patterns (DAMPs), promoting the maturation and release of inflammatory factors such as IL-1β and IL-18 by activating caspase-1. Inflammasomes also induce pyroptosis, which plays a key role in the body’s defense mechanisms (6, 7). In recent years, studies have demonstrated that inflammasomes play a significant role in a variety of pathological conditions, including infectious diseases, metabolic disorders, autoimmune diseases, tumors, and chronic inflammation (255–257). In gynecology, inflammasomes contribute to multiple inflammatory conditions. NLRP3 and IFI16 show connections to pelvic inflammatory disease, endometriosis, cervicitis, and HPV-associated cervical cancer (84, 93, 258–260).

But traditional two-dimensional cell models can’t really copy the complexity of the inflammatory microenvironment seen in gynaecological diseases. These models don’t have a true three-dimensional structure and can’t show the relationship between cells and the stuff around them accurately. They don’t show how all the different cells in the inflamed area are interacting with each other (261–263). Organoid models better mimic the female reproductive system. They are well-suited for inflammasome research in gynecological diseases (169, 263). For example, in a co-culture model of endometriotic cells with other cell types, organoids have been used to study the early stages of endometriosis, including initial adhesion, invasion, and angiogenesis (43). A mouse organoid study showed how AIM2 and NLRP3 inflammasomes drive inflammation through IL-1β. This process actively promoted angiogenesis, cell adhesion, and tissue growth. blocking IL-1β effectively suppressed these effects, leading to improved vascular outcomes (264). A novel, laboratory-developed, mouse-human endometrial organoid model demonstrated the physiological responses of the endometrial epithelium to estrogen and progesterone, including increased cell proliferation in response to estrogen and maturation in response to progesterone, which lasted for more than 14 days (265). These models help to investigate how oestrogen influences NLRP3 inflammasome levels. They offer a more accurate representation of the human inflammatory environment, allowing researchers to study cell interactions influenced by inflammasomes in co-culture models (266). Thus, AI plays a vital role in the analysis of inflammasomes in these organoid models, enabling deeper insights into their regulation mechanisms and their association with the progression of gynecological diseases (218, 267–269).

4.3.1 Integration with transcriptomics

Transcriptomics is the study of all RNA molecules in cells, tissues, or organisms (270, 271). RNAsequencing (RNA-seq) has become the field’s principal workhorse, enabling rapid, comprehensive measurement of transcript identity and abundance in a given specimen (272). When paired with AI-guided analytics, researchers can better understand the mechanistic details of inflammasome activation through transcriptomic analysis (28, 106, 273, 274).

AI algorithms excel at extracting biologically meaningful features from high-dimensional data generated by RNA-seq (107, 273, 275–277). ML can identify differentially expressed genes (DEGs), such as PYCARD (ASC), IL1B, and IL18, which are linked to key inflammasome pathways in gynecological inflammation, such as NLRP3 and AIM2. On this basis, by further constructing predictive models for gynecological organoids, it is possible to determine whether cells or tissues are in a state of inflammasome activation (278–280). DL, coupled with RNA-seq, supports representation learning and pattern discovery in organoid transcriptomes, providing dual support for pathway mechanism analysis (281, 282). NLP can further quantify cell states and gene functions by constructing embedding vectors, making it a valuable tool for studying inflammasome activation in organoids (107). Combining AI with RNA-seq enables accurate and efficient computational frameworks for identifying the mechanisms of inflammasome activation in gynecological diseases.

4.3.2 Binding to the proteome

The integration of AI technology can break through the limitations of traditional proteomics analysis, providing a powerful tool for the precise analysis of inflammasomes in organoids. Traditional proteomics techniques, such as liquid chromatography-tandem mass spectrometry (LC-MS/MS) and two-dimensional polyacrylamide gel electrophoresis (2D-PAGE), enable protein identification and quantification (283–285).

However, such techniques have problems such as complex data processing, difficult to detect low-abundance proteins, and low efficiency of post-translational modification capture. Moreover, the experimental process is time-consuming and the interpretation of results is highly dependent on manual work, which limits their application efficiency in fine mechanism research (286–288).

AI-assisted proteomics significantly optimizes data processing and analysis, improving the research efficiency and accuracy of results. For instance, DISCO-MS, which combines tissue transparency, deep learning-based image analysis, automated tissue extraction, and mass spectrometry (289), offers an unbiased path for analyzing inflammasomes such as NLRP1, NLRP3, NLRC4, and AIM2. Additionally, AI tools like π-HuB (Human proteomics Navigator) use high-resolution proteomics to analyze the human proteome, offering powerful insights into inflammasome research in organoid models (290).

4.3.3 Integration with the metabolome

Inflammasomes play a critical role in gynecological inflammation, which can be triggered by microbial infections, leading to inflammatory responses that regulate immune responses. The interaction between inflammasomes and microbial metabolites influences the development of gynecological diseases (291).

With the continuous advancement of medical research, new technologies and methods provide novel approaches for precise diagnosis and treatment of diseases. In the study of bacterial vaginosis (BV), machine learning-based diagnostic models can address limitations such as subjectivity in diagnosis, technical constraints, and the inability to comprehensively reflect the vaginal microecological status. In recent years, the combination of multi-omics and machine learning (ML) has also provided strong support for the screening and validation of BV-related biomarkers (111). The advancement of high-throughput sequencing technologies has opened new avenues for exploring the microbiome and inflammasomes (292–294). Among them, the unsupervised learning framework NMFGOT can effectively integrate microbiome and metabolome data, handle complex nonlinear relationships, and facilitate downstream biological analysis (27). In other areas of medical research, such as analyzing the urinary metabolomic changes in pregnant women to predict gestational age (GA) and delivery time, or exploring the interactions between gut microbiota and metabolites, various statistical and ML methods are commonly employed. These are often combined with 16S rRNA gene sequencing and LC-MS/MS metabolomics, complemented by network module analysis to uncover potential associations and construct clinical prediction models (295, 296). The DeepMSProfiler method based on deep learning (DL) can effectively address challenges such as complex data processing, batch-to-batch variation, and unknown metabolites, thus improving the accuracy and reliability of the output results (297). To gain a deeper understanding of the microbial ecosystem in complex gynecological organoids, ecology-based computational methods such as GutCP can predict untested cross-feeding interactions within the microbiome (298). These AI-based metabolomics analysis strategies provide valuable approaches for elucidating the interaction mechanisms between inflammasomes and microbial metabolites in gynecological inflammation (Figure 3).

Figure 3

5 Conclusion and discussion

The inflammasome serves as a pivotal regulatory hub for immune activation and inflammatory cell death within the female reproductive system, linking diverse stimuli such as infection, metabolic stress, and hormonal imbalance to disease progression. In conditions including endometriosis, ovarian cancer, polycystic ovary syndrome (PCOS), and premature ovarian insufficiency, aberrant inflammasome activation drives persistent inflammation, fibrosis, and immune evasion, thereby propelling pathological processes. These findings establish inflammasomes as pivotal molecular players in chronic reproductive inflammation. However, translating these mechanistic discoveries into effective clinical interventions remains profoundly challenging, fundamentally due to the inability of traditional two-dimensional culture systems and animal models to authentically replicate the intricate immunological and endocrine interactions within human reproductive tissues.

To overcome this obstacle, we have proposed a new approach that integrates the analysis of inflammasome mechanisms, the construction of organoid models, and artificial intelligence (AI) technology. Firstly, organoids derived from patients’ endometrium, ovaries, and cervix can reconstruct the three-dimensional structure and multi-cellular complexity of tissues, simulate hormone responses and inflammatory signaling pathways, providing a physiologically relevant platform for mechanism research and drug screening. At the same time, this process generates massive, high-dimensional, and multi-modal data. Subsequently, the introduction of computational tools such as AI can efficiently process and analyze the complex datasets generated by organoid research. This is because AI can utilize deep learning, computer vision, and multi-omics integration to quantify the dynamic changes in inflammasome activation, identify potential biomarkers, and predict treatment responses in different disease states.

This three-in-one integrated approach has been demonstrated in various studies. Dana El Soufi El Sabbagh et al. aimed to further clarify whether bipolar disorder (BD) is accompanied by mitochondrial dysfunction and enhanced inflammatory reactivity. They used iPSC-derived brain organoids (CO) from BD patients to simulate more physiologically relevant disease-specific metabolic and inflammatory dysfunctions and proved the increased sensitivity of NLRP3 inflammasome activation through metabolomics and other methods. Shashi Kant Tiwari et al. constructed iPSC-derived lung organoids (LORGs) as an in vitro model system to study the pathogenesis of the novel coronavirus SARS-CoV-2. By examining host response genes, they found that key genes in the inflammasome pathway, such as NLRP3, were upregulated, indicating that SARS-CoV-2 infection of LORGs activated genes involved in the inflammasome pathway (NLRP3, etc.). Thus, this three-in-one integrated approach is feasible, and its application in the precise diagnosis and treatment of gynecological diseases also holds promise.

It is worth noting that although the interdisciplinary research progress of this method is rapid, it is still in its early stages and faces several key limitations.Current inflammasome research in gynaecological diseases predominantly focuses on fundamental mechanisms, with differences between disease subtypes and their dynamic associations with the hormonal cycle is still lacking. While organoid models effectively reproduce tissue architecture and certain immune features, they lack complete immune cell populations and the humoral environment, hindering precise simulation of the complex regulation of chronic inflammation and immune tolerance. AI−driven analyses, despite clear promise for multi−omics integration and disease prediction, are frequently hampered by small cohort sizes, marked inter−dataset heterogeneity, and restricted interpretability. These limitations impact the clinical reliability and generalisability of models.

Looking ahead, future research should further advance interdisciplinary integration by establishing high-fidelity gynaecological organoid systems incorporating immune, endocrine, and metabolic components. This should be combined with integrated analyses using large-scale patient-derived samples and longitudinal clinical data. Concurrently, developing interpretable AI algorithms is essential to achieve dynamic visualisation and causal inference within inflammasome regulatory networks. From a clinical perspective, urgent, multicentre validation is essential to confirm the safe and effective use of inflammasome-targeting therapeutics and AI predictive models in the management of gynaecological diseases. Collectively, synergistic research integrating inflammasomes, organoids, and artificial intelligence is charting novel pathways in female reproductive immunology. As model precision and algorithmic transparency advance, this field holds promise for genuine translation from mechanism discovery to clinical application, laying a robust foundation for precision diagnosis and personalised treatment of gynaecological disorders.

References

• 1

  CaoYGuoYLongZWuYPeiBYeJet al. The global burden of gynecological diseases from 1990 to 2019. Am J Prev Med. (2024) 67:698–704. doi: 10.1016/j.amepre.2024.06.022. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 2

  RižnerTL. Noninvasive biomarkers of endometriosis: myth or reality? Expert Rev Mol Diagn. (2014) 14:365–85. doi: 10.1586/14737159.2014.899905

  • CrossRef
  • Google Scholar

• 3

  ZondervanKTBeckerCMMissmerSA. Endometriosis. N Engl J Med. (2020) 382:1244–56. doi: 10.1016/j.ejogrb.2022.02.059. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 4

  YangCXiaBRZhangZCZhangYJLouGJinWL. Immunotherapy for ovarian cancer: adjuvant, combination, and neoadjuvant. Front Immunol. (2020) 11:577869. doi: 10.3389/fimmu.2020.577869. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 5

  MorandSDevanaboyinaMStaatsHStanberyLNemunaitisJ. Ovarian cancer immunotherapy and personalized medicine. Int J Mol Sci. (2021) 22:6532. doi: 10.3390/ijms22126532. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 6

  PaerewijckOLamkanfiM. The human inflammasomes. Mol Aspects Med. (2022) 88:101100. doi: 10.1016/j.mam.2022.101100. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 7

  DengZLuLLiBShiXJinHHuW. The roles of inflammasomes in cancer. Front Immunol. (2023) 14:1195572. doi: 10.3389/fimmu.2023.1195572. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 8

  GuoBChenJHZhangJHFangYLiuXJZhangJet al. Pattern-recognition receptors in endometriosis: a narrative review. Front Immunol. (2023) 14:1161606. doi: 10.3389/fimmu.2023.1161606. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 9

  MoustakliEStavrosSKatopodisPSkentouCPotirisAPanagopoulosPet al. Oxidative stress and the NLRP3 inflammasome: focus on female fertility and reproductive health. Cells. (2025) 14:36. doi: 10.3390/cells14010036. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 10

  SochaMWMalinowskiBPukODubielMWicińskiM. The NLRP3 inflammasome role in the pathogenesis of pregnancy induced hypertension and preeclampsia. Cells. (2020) 9:1642. doi: 10.3390/cells9071642. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 11

  ZhengXZhaoDJinYLiuYLiuD. Role of the NLRP3 inflammasome in gynecological disease. Biomedicine Pharmacotherapy. (2023) 166:115393. doi: 10.1016/j.biopha.2023.115393. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 12

  TangXYWuSWangDChuCHongYTaoMet al. Human organoids in basic research and clinical applications. Signal Transduct Target Ther. (2022) 7:168. doi: 10.1038/s41392-022-01024-9. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 13

  KimJKooBKKnoblichJA. Human organoids: model systems for human biology and medicine. Nat Rev Mol Cell Biol. (2020) 21:571–84. doi: 10.1038/s41580-020-0259-3. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 14

  CorsiniNSKnoblichJA. Human organoids: new strategies and methods for analyzing human development and disease. Cell. (2022) 185:2756–69. doi: 10.1016/j.cell.2022.06.051. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 15

  LewisAKesharaRKimYHGrapin-BottonA. Self-organization of organoids from endoderm-derived cells. J Mol Med (Berl). (2021) 99:449–62. doi: 10.1007/s00109-020-02010-w. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 16

  ShangYWangGZhenYLiuNNieFZhaoZet al. Application of decellularization-recellularization technique in plastic and reconstructive surgery. Chin Med J (Engl). (2023) 136:2017–27. doi: 10.1097/cm9.0000000000002085. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 17

  LiuSZhangYLuoYLiuJ. Traditional and emerging strategies using hepatocytes for pancreatic regenerative medicine. J Diabetes. (2024) 16:e13545. doi: 10.1111/1753-0407.13545. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 18

  Garcia GarciaJMVannuzziVDonatiCBernacchioniCBruniPPetragliaF. Endometriosis: cellular and molecular mechanisms leading to fibrosis. Reprod Sci. (2023) 30:1453–61. doi: 10.1007/s43032-022-01083-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 19

  LacoFKunMWeberHJRamakrishnaSChanCK. The dose effect of human bone marrow-derived mesenchymal stem cells on epidermal development in organotypic co-culture. J Dermatol Sci. (2009) 55:150–60. doi: 10.1016/j.jdermsci.2009.05.009. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 20

  NguyenDTFamigliettiJESmolchekRADupeeZDiodatiNPedroDIet al. 3D in vitro platform for cell and explant culture in liquid-like solids. Cells. (2022) 11:967. doi: 10.3390/cells11060967. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 21

  QiGXZhaoRXGaoCMaZYWangSXuJ. Recent advances and challenges in colorectal cancer: from molecular research to treatment.World J Gastroenterol. (2025) 31:106964. doi: 10.3748/wjg.v31.i21.106964. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 22

  Francés-HerreroEJuárez-BarberECampoHLópez-MartínezSde Miguel-GómezLFausAet al. Improved models of human endometrial organoids based on hydrogels from decellularized endometrium. J Pers Med. (2021) 11:504. doi: 10.3390/jpm11060504. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 23

  AshoubMHRazaviRHeydaryanKSalavati-NiasariMAmiriM. Targeting ferroptosis for leukemia therapy: exploring novel strategies from its mechanisms and role in leukemia based on nanotechnology. Eur J Med Res. (2024) 29:224. doi: 10.1186/s40001-024-01822-7. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 24

  KandaGNTsuzukiTTeradaMSakaiNMotozawaNMasudaTet al. Robotic search for optimal cell culture in regenerative medicine. Elife. (2022) 11:e77007. doi: 10.7554/elife.77007. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 25

  NealJTLiXZhuJGiangarraVGrzeskowiakCLJuJet al. Organoid modeling of the tumor immune microenvironment. Cell. (2018) 175:1972–1988.e16. doi: 10.1016/j.cell.2018.11.021. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 26

  TranTTVSurya WibowoATayaraHChongKT. Artificial intelligence in drug toxicity prediction: recent advances, challenges, and future perspectives. J Chem Inf Model. (2023) 63:2628–43. doi: 10.1021/acs.jcim.3c00200. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 27

  MaYLiuL. NMFGOT: a multi-view learning framework for the microbiome and metabolome integrative analysis with optimal transport plan. NPJ Biofilms Microbiomes. (2024) 10:135. doi: 10.1038/s41522-024-00612-7. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 28

  RezapourMWalkerSJOrnellesDANiaziMKKMcNuttPMAtalaAet al. Exploring the host response in infected lung organoids using NanoString technology: a statistical analysis of gene expression data. PloS One. (2024) 19:e0308849. doi: 10.1371/journal.pone.0308849. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 29

  DaoVYukiKLoYHNakanoMKuoCJ. Immune organoids: from tumor modeling to precision oncology. Trends Cancer. (2022) 8:870–80. doi: 10.1016/j.trecan.2022.06.001. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 30

  XuZKombe KombeAJDengSZhangHWuSRuanJet al. NLRP inflammasomes in health and disease. Mol BioMed. (2024) 5:14. doi: 10.1186/s43556-024-00179-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 31

  SundaramBTweedellREPrasanth KumarSKannegantiTD. The NLR family of innate immune and cell death sensors. Immunity. (2024) 57:674–99. doi: 10.1016/j.immuni.2024.03.012. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 32

  YaoJSterlingKWangZZhangYSongW. The role of inflammasomes in human diseases and their potential as therapeutic targets. Signal Transduct Target Ther. (2024) 9:10. doi: 10.1038/s41392-023-01687-y. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 33

  LiJMaCMDiDL. A narrative review of pyrolysis and its role in ulcerative colitis. Eur Rev Med Pharmacol Sci. (2022) 26:1156–63. doi: 10.26355/eurrev_202202_28107

  • CrossRef
  • Google Scholar

• 34

  TangDCaoFYanCFangKMaJGaoLet al. Extracellular vesicle/macrophage axis: potential targets for inflammatory disease intervention. Front Immunol. (2022) 13:705472. doi: 10.3389/fimmu.2022.705472. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 35

  WeiXXieFZhouXWuYYanHLiuTet al. Role of pyroptosis in inflammation and cancer. Cell Mol Immunol. (2022) 19:971–92. doi: 10.1038/s41423-022-00905-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 36

  FanXJiaoLJinT. Activation and immune regulation mechanisms of PYHIN family during microbial infection. Front Microbiol. (2021) 12:809412. doi: 10.3389/fmicb.2021.809412. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 37

  FangXWangYZhangYLiYKwak-KimJWuL. NLRP3 inflammasome and its critical role in gynecological disorders and obstetrical complications. Front Immunol. (2020) 11:555826. doi: 10.3389/fimmu.2020.555826. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 38

  Ketelut-CarneiroNFitzgeraldKA. Inflammasomes. Curr Biol. (2020) 30:R689–94. doi: 10.1016/j.cub.2020.04.065. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 39

  DuXYangHKangXFuCYangT. Blocking GATA6 alleviates pyroptosis and inhibits abdominal wall endometriosis lesion growth through inactivating the PI3K/AKT pathway. Cell Biochem Biophys. (2025) 83:1757–70. doi: 10.1007/s12013-024-01583-4. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 40

  TaylorHSKotlyarAMFloresVA. Endometriosis is a chronic systemic disease: clinical challenges and novel innovations. Lancet. (2021) 397:839–52. doi: 10.1016/s0140-6736(21)00389-5. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 41

  ZhouFZhaoFHuangQLinXZhangSDaiY. NLRP3 activated macrophages promote endometrial stromal cells migration in endometriosis. J Reprod Immunol. (2022) 152:103649. doi: 10.1016/j.jri.2022.103649. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 42

  HangYTanLChenQLiuQJinY. E3 ubiquitin ligase TRIM24 deficiency promotes NLRP3/caspase-1/IL-1β-mediated pyroptosis in endometriosis. Cell Biol Int. (2021) 45:1561–70. doi: 10.1002/cbin.11592. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 43

  Di NicuoloFCastellaniRDe Cicco NardoneABarbaroGPaciulloCPontecorviAet al. Alpha-lipoic acid plays a role in endometriosis: new evidence on inflammasome-mediated interleukin production, cellular adhesion and invasion. Molecules. (2021) 26:288. doi: 10.3390/molecules26020288. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 44

  AzlanASalamonsenLAHutchisonJEvansJ. Endometrial inflammasome activation accompanies menstruation and may have implications for systemic inflammatory events of the menstrual cycle. Hum Reprod. (2020) 35:1363–76. doi: 10.1093/humrep/deaa065. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 45

  SongLWangLLiXXiaoL. Ginsenoside Rg1 alleviates lipopolysaccharide-induced fibrosis of endometrial epithelial cells in dairy cows by inhibiting reactive oxygen species-activated NLRP3. Anim (Basel). (2023) 13:3723. doi: 10.3390/ani13233723. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 46

  YuSYLiXL. Pyroptosis and inflammasomes in obstetrical and gynecological diseases. Gynecol Endocrinol. (2021) 37:385–91. doi: 10.1080/09513590.2021.1871893. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 47

  DingYYanYDongYXuJSuWShiWet al. NLRP3 promotes immune escape by regulating immune checkpoints: a pan-cancer analysis. Int Immunopharmacol. (2022) 104:108512. doi: 10.1016/j.intimp.2021.108512. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 48

  SharmaBRKannegantiTD. NLRP3 inflammasome in cancer and metabolic diseases. Nat Immunol. (2021) 22:550–9. doi: 10.1038/s41590-021-00886-5. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 49

  HuangYLiRYangY. Role of pyroptosis in gynecological oncology and its therapeutic regulation. Biomolecules. (2022) 12:924. doi: 10.3390/biom12070924. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 50

  ZhangRChenJMaoLGuoYHaoYDengYet al. Nobiletin triggers reactive oxygen species-mediated pyroptosis through regulating autophagy in ovarian cancer cells. J Agric Food Chem. (2020) 68:1326–36. doi: 10.1021/acs.jafc.9b07908. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 51

  ZijlstraFFiorettiPRoelandtJR. Echocardiographic demonstration of free wall vegetative endocarditis complicated by a pulmonary embolism in a patient with ventricular septal defect. Br Heart J. (1986) 55:497–9. doi: 10.1136/hrt.55.5.497. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 52

  LiJYangCLiYChenALiLYouZ. LncRNA GAS5 suppresses ovarian cancer by inducing inflammasome formation. Biosci Rep. (2018) 38:BSR20171150. doi: 10.1042/bsr20171150. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 53

  HsuPCChaoTKChouYCYuMHWangYCLinYHet al. AIM2 inflammasome in tumor cells as a biomarker for predicting the treatment response to antiangiogenic therapy in epithelial ovarian cancer patients. J Clin Med. (2021) 10:4529. doi: 10.3390/jcm10194529. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 54

  IbruliORoseFBeleggiaFSchmittACartolanoMFernandezLTet al. A novel mouse model recapitulating the MMR-defective SCLC subtype uncovers an actionable sensitivity to immune checkpoint blockade. J Cancer Res Clin Oncol. (2024) 150:496. doi: 10.1007/s00432-024-05942-9. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 55

  SasagawaTNagamatsuTYanagisawaMFujiiTShibuyaM. Hypoxia-inducible factor-1β is essential for upregulation of the hypoxia-induced FLT1 gene in placental trophoblasts. Mol Hum Reprod. (2021) 27:gaab065. doi: 10.1093/molehr/gaab065. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 56

  TersigniCBarbaroGCastellaniROnoriMGranieriCScambiaGet al. Oral administration of Bifidobacterium longum ES1 reduces endometrial inflammation in women with recurrent pregnancy loss. Am J Reprod Immunol. (2024) 91:e13804. doi: 10.1111/aji.13804. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 57

  SilvaGBGiermanLMRaknerJJStødleGSMundalSBThaningAJet al. Cholesterol crystals and NLRP3 mediated inflammation in the uterine wall decidua in normal and preeclamptic pregnancies. Front Immunol. (2020) 11:564712. doi: 10.3389/fimmu.2020.564712. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 58

  OmeljaniukWJGarleyMPryczyniczAMotykaJCharkiewiczAEMilewskaEet al. NLRP3 inflammasome in the pathogenesis of miscarriages. Int J Mol Sci. (2024) 25:10513. doi: 10.3390/ijms251910513. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 59

  WuHMLoTCTsaiCLChenLHHuangHYWangHSet al. Extracellular vesicle-associated microRNA-138-5p regulates embryo implantation and early pregnancy by adjusting GPR124. Pharmaceutics. (2022) 14:1172. doi: 10.3390/pharmaceutics14061172. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 60

  ReynaudDAbi NahedRLemaitreNBolzePATraboulsiWSergentFet al. NLRP7 promotes choriocarcinoma growth and progression through the establishment of an immunosuppressive microenvironment. Cancers (Basel). (2021) 13:2999. doi: 10.3390/cancers13122999. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 61

  ZhuJMaCZhuLLiJPengFHuangLet al. A role for the NLRC4 inflammasome in premature rupture of membrane. PloS One. (2020) 15:e0237847. doi: 10.1371/journal.pone.0237847. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 62

  XueFWangYTaoXQSuW. A study on the level of NLRP3 inflammasome in patients with premature rupture of membranes. Immun Inflammation Dis. (2023) 11:e1018. doi: 10.1002/iid3.1018. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 63

  ChenZZhangMZhaoYXuWXiangFLiXet al. Hydrogen sulfide contributes to uterine quiescence through inhibition of NLRP3 inflammasome activation by suppressing the TLR4/NF-κB signalling pathway. J Inflammation Res. (2021) 14:2753–68. doi: 10.2147/jir.s308558. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 64

  ChenZShanYYouXGuHXuCLongJet al. NLRP3 inflammasome is involved in uterine activation for labor at term and preterm. Reproduction. (2021) 162:449–60. doi: 10.1530/rep-21-0047. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 65

  LiuWSongYWangRWanZLiRWangX. Card9 deficiency exacerbates vulvovaginal candidiasis by impairing the IL-17 production and vaginal epithelial barrier. Med Mycol. (2025) 63:myaf026. doi: 10.1093/mmy/myaf026. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 66

  PengYXuYLiSShaoMShenZQiW. Mechanism of vaginal epithelial cell pyroptosis induced by the NLRP3 inflammasome in vulvovaginal candidiasis. Am J Reprod Immunol. (2024) 92:e13893. doi: 10.1111/aji.13893. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 67

  HeXTangQZhanFMaoYYeFWengZet al. Inflammatory invasion on human vaginal mucosa correlated with combined drug treatment and recurrence in recurrent vulvovaginal candidiasis. J Obstet Gynaecol Res. (2023) 49:1443–51. doi: 10.1111/jog.15577. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 68

  DingXKambaraHGuoRKannegantiAAcosta-ZaldívarMLiJet al. Inflammasome-mediated GSDMD activation facilitates escape of Candida albicans from macrophages. Nat Commun. (2021) 12:6699. doi: 10.1038/s41467-021-27034-9. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 69

  XiangNYinTChenT. Gardnerella vaginalis induces NLRP3 inflammasome-mediated pyroptosis in macrophages and THP-1 monocytes. Exp Ther Med. (2021) 22:1174. doi: 10.3892/etm.2021.10609. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 70

  KumariyaSUbbaVJhaRKGayenJR. Autophagy in ovary and polycystic ovary syndrome: role, dispute and future perspective. Autophagy. (2021) 17:2706–33. doi: 10.1080/15548627.2021.1938914. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 71

  Sanchez-GarridoMATena-SempereM. Metabolic dysfunction in polycystic ovary syndrome: pathogenic role of androgen excess and potential therapeutic strategies. Mol Metab. (2020) 35:100937. doi: 10.1016/j.molmet.2020.01.001. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 72

  Stener-VictorinETeedeHNormanRJLegroRGoodarziMODokrasAet al. Polycystic ovary syndrome. Nat Rev Dis Primers. (2024) 10:27. doi: 10.1126/science.adq0328. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 73

  Stener-VictorinEDengQ. Epigenetic inheritance of polycystic ovary syndrome - challenges and opportunities for treatment. Nat Rev Endocrinol. (2021) 17:521–33. doi: 10.1038/s41574-021-00517-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 74

  BerkelC. Inducers and inhibitors of pyroptotic death of granulosa cells in models of premature ovarian insufficiency and polycystic ovary syndrome. Reprod Sci. (2024) 31:2972–92. doi: 10.1007/s43032-024-01643-3. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 75

  ChamanaraSHozouriVIrandoostE. Inhibition of NLRP3 inflammasome-A potential mechanistic therapeutic for treatment of polycystic ovary syndrome? J Biochem Mol Toxicol. (2024) 38:e23592. doi: 10.1002/jbt.23592. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 76

  AleneziSAKhanRSnellLAboeldalylSAmerS. The role of NLRP3 inflammasome in obesity and PCOS-A systematic review and meta-analysis. Int J Mol Sci. (2023) 24:10976. doi: 10.3390/ijms241310976. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 77

  PeterMUAreloegbeSEAkintayoCOOniyideAAAturamuAOlaniyiKS. Low-dose spironolactone abates cardio-renal disorder by reduction of BAX/inflammasome expression in experimentally induced polycystic ovarian syndrome rat model. Can J Physiol Pharmacol. (2022) 100:890–902. doi: 10.1139/cjpp-2022-0176. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 78

  CaiZHeSLiuRZhouLZhaoL. Plumbagin rescues the granulosa cell’s pyroptosis by reducing WTAP-mediated N6-methylation in polycystic ovary syndrome. J Ovarian Res. (2022) 15:126. doi: 10.21203/rs.3.rs-1816507/v1. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 79

  GuoQJShanJXuYFHuYYHuoCLSongJYet al. Pioglitazone metformin complex improves polycystic ovary syndrome comorbid psychological distress via inhibiting NLRP3 inflammasome activation: a prospective clinical study. Mediators Inflammation. (2020) 2020:3050487. doi: 10.1155/2020/3050487. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 80

  OlaniyiKSAreloegbeSE. Alleviation of adipose-hepatic glycolipid dysregulation by acetate in experimental PCOS model is associated with NF-κB/NLRP3 repression. Can J Physiol Pharmacol. (2023) 101:630–41. doi: 10.1139/cjpp-2023-0169. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 81

  BakhshH. Committee opinion no. 605: primary ovarian insufficiency in adolescents and young women. Obstet Gynecol. (2014) 124:193–7. doi: 10.1097/01.aog.0000451757.51964.98. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 82

  TourainePChabbert-BuffetNPlu-BureauGDuranteauLSinclairAHTuckerEJ. Premature ovarian insufficiency. Nat Rev Dis Primers. (2024) 10:63. doi: 10.1038/s41572-024-00547-5. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 83

  FeutzSA. When individual rights conflict, who prevails? J Nurs Adm. (1987) 17:5–7.

  • Google Scholar

• 84

  Navarro-PandoJMAlcocer-GómezECastejón-VegaBNavarro-VillaránECondés-HervásMMundi-RoldanMet al. Inhibition of the NLRP3 inflammasome prevents ovarian aging. Sci Adv. (2021) 7:eabc7409. doi: 10.1126/sciadv.abc7409. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 85

  MiaoCZhaoYChenYWangRRenNChenBet al. Investigation of He’s Yang Chao recipe against oxidative stress-related mitophagy and pyroptosis to improve ovarian function. Front Endocrinol (Lausanne). (2023) 14:1077315. doi: 10.3389/fendo.2023.1077315. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 86

  ChenDHuNXingSYangLZhangFGuoSet al. Placental mesenchymal stem cells ameliorate NLRP3 inflammasome-induced ovarian insufficiency by modulating macrophage M2 polarization. J Ovarian Res. (2023) 16:58. doi: 10.1186/s13048-023-01136-y. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 87

  GeorgescuSRMitranCIMitranMICaruntuCSarbuMIMateiCet al. New insights in the pathogenesis of HPV infection and the associated carcinogenic processes: the role of chronic inflammation and oxidative stress. J Immunol Res. (2018) 2018:5315816. doi: 10.1155/2018/5315816. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 88

  OjhaPSMasteMMTubachiSPatilVS. Human papillomavirus and cervical cancer: an insight highlighting pathogenesis and targeting strategies. Virusdisease. (2022) 33:132–54. doi: 10.1007/s13337-022-00768-w. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 89

  ReinholzMKawakamiYSalzerSKreuterADombrowskiYKoglinSet al. HPV16 activates the AIM2 inflammasome in keratinocytes. Arch Dermatol Res. (2013) 305:723–32. doi: 10.1007/s00403-013-1375-0. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 90

  HuCLiuTHanCXuanYJiangDSunYet al. HPV E6/E7 promotes aerobic glycolysis in cervical cancer by regulating IGF2BP2 to stabilize m6A-MYC expression. Int J Biol Sci. (2022) 18:507–21. doi: 10.7150/ijbs.67770. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 91

  MarulloRWernerEZhangHChenGZShinDMDoetschPW. HPV16 E6 and E7 proteins induce a chronic oxidative stress response via NOX2 that causes genomic instability and increased susceptibility to DNA damage in head and neck cancer cells. Carcinogenesis. (2015) 36:1397–406. doi: 10.1093/carcin/bgv126. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 92

  YimEKParkJS. The role of HPV E6 and E7 oncoproteins in HPV-associated cervical carcinogenesis. Cancer Res Treat. (2005) 37:319–24. doi: 10.4143/crt.2005.37.6.319. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 93

  SongYWuXXuYZhuJLiJZouZet al. HPV E7 inhibits cell pyroptosis by promoting TRIM21-mediated degradation and ubiquitination of the IFI16 inflammasome. Int J Biol Sci. (2020) 16:2924–37. doi: 10.7150/ijbs.50074. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 94

  MatamorosJAda SilvaMIFde MouraPMMFLeitãoMCCoimbraEC. Reduced expression of IL-1β and IL-18 proinflammatory interleukins increases the risk of developing cervical cancer. Asian Pac J Cancer Prev. (2019) 20:2715–21. doi: 10.31557/apjcp.2019.20.9.2715. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 95

  LuQLaoXGanJDuPZhouYNongWet al. Impact of NLRP3 gene polymorphisms (rs10754558 and rs10733113) on HPV infection and cervical cancer in southern Chinese population. Infect Agent Cancer. (2023) 18:64. doi: 10.1186/s13027-023-00529-4. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 96

  BrunhamRCGottliebSLPaavonenJ. Pelvic inflammatory disease. N Engl J Med. (2015) 372:2039–48. doi: 10.1056/nejmra1411426. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 97

  Abdul-SaterAAKooEHäckerGOjciusDM. Inflammasome-dependent caspase-1 activation in cervical epithelial cells stimulates growth of the intracellular pathogen Chlamydia trachomatis. J Biol Chem. (2009) 284:26789–96. doi: 10.1074/jbc.m109.026823. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 98

  WaltonEL. The inflammasome: friend or foe in Chlamydia infection? BioMed J. (2016) 39:299–303. doi: 10.1016/j.bj.2016.10.003. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 99

  JenkinsSMVadakekutES. Pelvic Inflammatory Disease. [Updated 2025 Jun 2]. In: StatPearls [Internet]. Treasure Island (FL): StatPearls Publishing. (2026). Available online at: http://www.ncbi.nlm.nih.gov/books/NBK499959/ (Accessed April 10, 2026).

  • Google Scholar

• 100

  JiangYPalomaresARMunozPNalvarteIAcharyaGInzunzaJet al. Proof-of-concept for long-term human endometrial epithelial organoids in modeling menstrual cycle responses. Cells. (2024) 13:1811. doi: 10.3390/cells13211811. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 101

  ZhangRYangYLiRMaYMaSChenXet al. Construction organoid model of ovarian endometriosis and the function of estrogen and progesterone in the model. Sci Rep. (2025) 15:6636. doi: 10.1038/s41598-025-90329-0. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 102

  LuddiAPavoneVSempliciBGoverniniLCriscuoliMPaccagniniEet al. Organoids of human endometrium: a powerful in vitro model for the endometrium-embryo cross-talk at the implantation site. Cells. (2020) 9:1121. doi: 10.3390/cells9051121. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 103

  CerneckisJCaiHShiY. Induced pluripotent stem cells (iPSCs): molecular mechanisms of induction and applications. Signal Transduct Target Ther. (2024) 9:112. doi: 10.1038/s41392-024-01809-0. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 104

  BadrouchiSBachaMMAhmedABen AbdallahTAbderrahimE. Predicting long-term outcomes of kidney transplantation in the era of artificial intelligence. Sci Rep. (2023) 13:21273. doi: 10.1038/s41598-023-48645-w. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 105

  RaffyPPambrunJFKumarADuboisDPattiJWCairnsRAet al. Deep learning body region classification of MRI and CT examinations. J Digit Imaging. (2023) 36:1291–301. doi: 10.1007/s10278-022-00767-9. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 106

  SinhaSCastilloVEspinozaCRTindleCFonsecaAGDanJMet al. COVID-19 lung disease shares driver AT2 cytopathic features with idiopathic pulmonary fibrosis. EBioMedicine. (2022) 82:104185. doi: 10.1016/j.ebiom.2022.104185. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 107

  WeiSLuYWangPLiQShuaiJZhaoQet al. Investigation of cell development and tissue structure network based on natural language processing of scRNA-seq data. J Transl Med. (2025) 23:264. doi: 10.1186/s12967-025-06263-2. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 108

  LiSYDeMayoFJ. Revolutionizing implantation studies: uterine-specific models and advanced technologies. Biomolecules. (2025) 15:450. doi: 10.3390/biom15030450. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 109

  ZhuSHuangZChenXJiangWZhouYZhengBet al. Construction and evaluation of machine learning-based prediction model for live birth following fresh embryo transfer in IVF/ICSI patients with polycystic ovary syndrome. J Ovarian Res. (2025) 18:70. doi: 10.1186/s13048-025-01654-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 110

  ZhuCHuPWangXZengXShiL. A real-time computer-aided diagnosis method for hydatidiform mole recognition using deep neural network. Comput Methods Programs BioMed. (2023) 234:107510. doi: 10.1016/j.cmpb.2023.107510. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 111

  ChallaAMarasJSNagpalSTripathiGTanejaBKachhawaGet al. Multi-omics analysis identifies potential microbial and metabolite diagnostic biomarkers of bacterial vaginosis. J Eur Acad Dermatol Venereol. (2024) 38:1152–65. doi: 10.1111/jdv.19805. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 112

  RamprashadJCLinYBeuraLK. Protocol for the coculture of murine vaginal epithelial organoids and T cells to induce resident memory CD8 T cell differentiation. STAR Protoc. (2025) 6:104054. doi: 10.1016/j.xpro.2025.104054. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 113

  WangZWangRGuoHZhaoQRenHNiuJet al. AI-assisted diagnosis of vulvovaginal candidiasis using cascaded neural networks. Microbiol Spectr. (2025) 13:e0169124. doi: 10.1128/spectrum.01691-24. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 114

  LuyckxLWeiMSaarelaUMyllykangasMKinnunenJArffmanRet al. PCOS endometrium-derived epithelial organoids as a novel model to study endometrial dysfunction. Hum Reprod. (2025) 40:1535–49. doi: 10.1093/humrep/deaf113. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 115

  ZhaoBWenLHuangYFuYZhouSLiuJet al. A deep learning-based automatic recognition model for polycystic ovary ultrasound images. Balkan Med J. (2025) 42:419–28. doi: 10.4274/balkanmedj.galenos.2025.2025-5-114. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 116

  ChenWMiaoJChenJChenJ. Development of machine learning models for diagnostic biomarker identification and immune cell infiltration analysis in PCOS. J Ovarian Res. (2025) 18:1. doi: 10.1186/s13048-024-01583-1. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 117

  YeHSongLLiQShenCHeYLiL. Organoid technology in cervical cancer research. Am J Cancer Res. (2025) 15:1988–2003. doi: 10.62347/fntd1712. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 118

  YanBCLiYMaFHZhangGFFengFSunMHet al. Radiologists with MRI-based radiomics aids to predict the pelvic lymph node metastasis in endometrial cancer: a multicenter study. Eur Radiol. (2021) 31:411–22. doi: 10.1007/s00330-020-07099-8. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 119

  XinWRixinSLinruiLZhihuiQLongLYuZ. Machine learning-based radiomics for predicting outcomes in cervical cancer patients undergoing concurrent chemoradiotherapy. Comput Biol Med. (2024) 177:108593. doi: 10.1016/j.compbiomed.2024.108593. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 120

  TitizMLandiniLSouza Monteiro de AraujoDMariniMSeravalliVChiecaMet al. Schwann cell C5aR1 co-opts inflammasome NLRP1 to sustain pain in a mouse model of endometriosis. Nat Commun. (2024) 15:10142. doi: 10.1038/s41467-024-54486-6. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 121

  ChenYLiT. Unveiling the mechanisms of pain in endometriosis: comprehensive analysis of inflammatory sensitization and therapeutic potential. Int J Mol Sci. (2025) 26:1770. doi: 10.3390/ijms26041770. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 122

  HuKJiangXZhangJXiaDWuDShaoJet al. Effect of Pulsatilla decoction on vulvovaginal candidiasis in mice. Evidences for its mechanisms of action. Phytomedicine. (2024) 128:155515. doi: 10.1016/j.phymed.2024.155515. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 123

  YuanJLiXYuS. Cancer organoid co-culture model system: novel approach to guide precision medicine. Front Immunol. (2022) 13:1061388. doi: 10.3389/fimmu.2022.1061388. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 124

  CorròCNovellasdemuntLLiVSW. A brief history of organoids. Am J Physiol Cell Physiol. (2020) 319:C151–165. doi: 10.1152/ajpcell.00120.2020

  • CrossRef
  • Google Scholar

• 125

  XuHJiaoDLiuAWuK. Tumor organoids: applications in cancer modeling and potentials in precision medicine. J Hematol Oncol. (2022) 15:58. doi: 10.1186/s13045-022-01278-4. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 126

  MusahSBhattacharyaRHimmelfarbJ. Kidney disease modeling with organoids and organs-on-chips. Annu Rev BioMed Eng. (2024) 26:383–414. doi: 10.1146/annurev-bioeng-072623-044010. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 127

  Vazquez-ArmendarizAITataPR. Recent advances in lung organoid development and applications in disease modeling. J Clin Invest. (2023) 133:e170500. doi: 10.1172/jci170500. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 128

  WangLYiSTengYLiWCaiJ. Role of the tumor microenvironment in the lymphatic metastasis of cervical cancer (Review). Exp Ther Med. (2023) 26:486. doi: 10.3892/etm.2023.12185. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 129

  JiangXWangJDengXXiongFZhangSGongZet al. The role of microenvironment in tumor angiogenesis. J Exp Clin Cancer Res. (2020) 39:204. doi: 10.1186/s13046-020-01709-5. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 130

  NiuTZhouF. Inflammation and tumor microenvironment. Zhong Nan Da Xue Xue Bao Yi Xue Ban. (2023) 48:1899–913. doi: 10.11817/j.issn.1672-7347.2023.230231

  • CrossRef
  • Google Scholar

• 131

  FuTDaiLJWuSYXiaoYMaDJiangYZet al. Spatial architecture of the immune microenvironment orchestrates tumor immunity and therapeutic response. J Hematol Oncol. (2021) 14:98. doi: 10.1186/s13045-021-01103-4. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 132

  LvBWangYMaDChengWLiuJYongTet al. Immunotherapy: Reshape the tumor immune microenvironment. Front Immunol. (2022) 13:844142. doi: 10.3389/fimmu.2022.844142. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 133

  MaoXXuJWangWLiangCHuaJLiuJet al. Crosstalk between cancer-associated fibroblasts and immune cells in the tumor microenvironment: new findings and future perspectives. Mol Cancer. (2021) 20:131. doi: 10.1186/s12943-021-01428-1. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 134

  LiYGaoXHuangYZhuXChenYXueLet al. Tumor microenvironment promotes lymphatic metastasis of cervical cancer: its mechanisms and clinical implications. Front Oncol. (2023) 13:1114042. doi: 10.3389/fonc.2023.1114042. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 135

  GuoFKongWLiDZhaoGAnwarMXiaFet al. M2-type tumor-associated macrophages upregulated PD-L1 expression in cervical cancer via the PI3K/AKT pathway. Eur J Med Res. (2024) 29:357. doi: 10.1186/s40001-024-01897-2. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 136

  LinXKangKChenPZengZLiGXiongWet al. Regulatory mechanisms of PD-1/PD-L1 in cancers. Mol Cancer. (2024) 23:108. doi: 10.1186/s12943-024-02023-w. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 137

  Blanc-DurandFClemence Wei XianLTanDSP. Targeting the immune microenvironment for ovarian cancer therapy. Front Immunol. (2023) 14:1328651. doi: 10.3389/fimmu.2023.1328651. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 138

  KryczekIWeiSZhuGMyersLMottramPChengPet al. Relationship between B7-H4, regulatory T cells, and patient outcome in human ovarian carcinoma. Cancer Res. (2007) 67:8900–5. doi: 10.1158/0008-5472.can-07-1866. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 139

  YukiKChengNNakanoMKuoCJ. Organoid models of tumor immunology. Trends Immunol. (2020) 41:652–64. doi: 10.1016/j.it.2020.06.010. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 140

  YangYCuiJKongYHouYMaC. Organoids: new frontiers in tumor immune microenvironment research. Front Immunol. (2024) 15:1422031. doi: 10.3389/fimmu.2024.1422031. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 141

  OngLJYZhuLTanGJSTohYC. Quantitative image-based cell viability (QuantICV) assay for microfluidic 3D tissue culture applications. Micromachines (Basel). (2020) 11:669. doi: 10.3390/mi11070669. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 142

  SurendranVRutledgeDColmonRChandrasekaranA. A novel tumor-immune microenvironment (TIME)-on-chip mimics three dimensional neutrophil-tumor dynamics and neutrophil extracellular traps (NETs)-mediated collective tumor invasion. Biofabrication. (2021) 13:035029. doi: 10.1088/1758-5090/abe1cf. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 143

  ChenDSuXChenHChenSZhaoYWeiW. Human organoids as a promising platform for fighting COVID-19. Int J Biol Sci. (2022) 18:901–10. doi: 10.7150/ijbs.64993. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 144

  RauthSKarmakarSBatraSKPonnusamyMP. Recent advances in organoid development and applications in disease modeling. Biochim Biophys Acta Rev Cancer. (2021) 1875:188527. doi: 10.1016/j.bbcan.2021.188527. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 145

  RezakhaniSGjorevskiNLutolfMP. Extracellular matrix requirements for gastrointestinal organoid cultures. Biomaterials. (2021) 276:121020. doi: 10.1016/j.biomaterials.2021.121020. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 146

  LancasterMAKnoblichJA. Organogenesis in a dish: modeling development and disease using organoid technologies. Science. (2014) 345:1247125. doi: 10.1126/science.1247125. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 147

  KretzschmarKCleversH. Organoids: modeling development and the stem cell niche in a dish. Dev Cell. (2016) 38:590–600. doi: 10.1016/j.devcel.2016.08.014. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 148

  CleversH. Modeling development and disease with organoids. Cell. (2016) 165:1586–97. doi: 10.1016/j.cell.2016.05.082. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 149

  CampJGBadshaFFlorioMKantonSGerberTWilsch-BräuningerMet al. Human cerebral organoids recapitulate gene expression programs of fetal neocortex development. Proc Natl Acad Sci USA. (2015) 112:15672–7. doi: 10.1073/pnas.1520760112. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 150

  KaushikGPonnusamyMPBatraSK. Concise review: current status of three-dimensional organoids as preclinical models. Stem Cells. (2018) 36:1329–40. doi: 10.1002/stem.2852. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 151

  AzarJBahmadHFDaherDMoubarakMMHadadehOMonzerAet al. The use of stem cell-derived organoids in disease modeling: an update. Int J Mol Sci. (2021) 22:7667. doi: 10.3390/ijms22147667. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 152

  ChenQSunXLiYYangXYangXXuHet al. The potential of organoids in renal cell carcinoma research. BMC Urol. (2024) 24:120. doi: 10.1186/s12894-024-01511-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 153

  Yousef YengejFAJansenJRookmaakerMBVerhaarMCCleversH. Kidney organoids and tubuloids. Cells. (2020) 9:1326. doi: 10.3390/cells9061326. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 154

  YucerNAhdootRWorkmanMJLaperleAHRecouvreuxMSKurowskiKet al. Human iPSC-derived fallopian tube organoids with BRCA1 mutation recapitulate early-stage carcinogenesis. Cell Rep. (2021) 37:110146. doi: 10.1016/j.celrep.2021.110146. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 155

  Van LentJBaggioliniA. Harmony in chaos: understanding cancer through the lenses of developmental biology. Mol Oncol. (2024) 18:793–6. doi: 10.1002/1878-0261.13594. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 156

  HuchMKooBK. Modeling mouse and human development using organoid cultures. Development. (2015) 142:3113–25. doi: 10.1242/dev.118570. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 157

  CableJFuchsEWeissmanIJasperHGlassDRandoTAet al. Adult stem cells and regenerative medicine-a symposium report. Ann N Y Acad Sci. (2020) 1462:27–36. doi: 10.1111/nyas.14243. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 158

  LiYQinMLiuNZhangC. Organoid development and applications in gynecological cancers: the new stage of tumor treatment. J Nanobiotechnology. (2025) 23:20. doi: 10.1186/s12951-024-03086-z. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 159

  GrönholmMFeodoroffMAntignaniGMartinsBHamdanFCerulloV. Patient-derived organoids for precision cancer immunotherapy. Cancer Res. (2021) 81:3149–57. doi: 10.1158/0008-5472.CAN-20-4026

  • CrossRef
  • Google Scholar

• 160

  VlachogiannisGHedayatSVatsiouAJaminYFernández-MateosJKhanKet al. Patient-derived organoids model treatment response of metastatic gastrointestinal cancers. Science. (2018) 359:920–6. doi: 10.1126/science.aao2774. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 161

  MebarkiMBennaceurABonhomme-FaivreL. Human-cell-derived organoids as a new ex vivo model for drug assays in oncology. Drug Discov Today. (2018) 23:857–63. doi: 10.1016/j.drudis.2018.02.003. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 162

  SungHFerlayJSiegelRLLaversanneMSoerjomataramIJemalAet al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. (2021) 71:209–49. doi: 10.3322/caac.21660. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 163

  ChoKRShihIM. Ovarian cancer. Annu Rev Pathol. (2009) 4:287–313. doi: 10.1146/annurev.pathol.4.110807.092246. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 164

  LiSLeiNChenMGuoRHanLQiuLet al. Exploration of organoids in ovarian cancer: from basic research to clinical translation. Transl Oncol. (2024) 50:102130. doi: 10.1016/j.tranon.2024.102130. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 165

  GrahamORodriguezJvan BiljonLFashemiBGrahamEFuhKet al. Generation and culturing of high-grade serous ovarian cancer patient-derived organoids. J Vis Exp. (2023) 191:64878. doi: 10.3791/64878. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 166

  MaenhoudtNDefrayeCBorettoMJanZHeremansRBoeckxBet al. Developing organoids from ovarian cancer as experimental and preclinical models. Stem Cell Rep. (2020) 14:717–29. doi: 10.1016/j.stemcr.2020.03.004. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 167

  DumontSJanZHeremansRVan GorpTVergoteITimmermanD. Organoids of epithelial ovarian cancer as an emerging preclinical in vitro tool: a review. J Ovarian Res. (2019) 12:105. doi: 10.1186/s13048-019-0577-2. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 168

  JelovacDArmstrongDK. Recent progress in the diagnosis and treatment of ovarian cancer. CA Cancer J Clin. (2011) 61:183–203. doi: 10.3322/caac.20113. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 169

  MaenhoudtNDefrayeCBorettoMJanZHeremansRBoeckxBet al. 29428171. Stem Cell Rep. (2020) 14:717–29. doi: 10.1016/j.stemcr.2020.03.004

  • CrossRef
  • Google Scholar

• 170

  MebarkiMBennaceurABonhomme-FaivreL. 31703723. Drug Discov Today. (2018) 23:857–63. doi: 10.1016/j.drudis.2018.02.003

  • CrossRef
  • Google Scholar

• 171

  SomiglianaEVigano’PParazziniFStoppelliSGiambattistaEVercelliniP. Association between endometriosis and cancer: a comprehensive review and a critical analysis of clinical and epidemiological evidence. Gynecol Oncol. (2006) 101:331–41. doi: 10.1016/j.ygyno.2005.11.033. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 172

  MylonasIJeschkeUKunert-KeilCShabaniNDianDBauerfeindIet al. Glycodelin A is expressed differentially in normal human endometrial tissue throughout the menstrual cycle as assessed by immunohistochemistry and in situ hybridization. Fertil Steril. (2006) 86:1488–97. doi: 10.1016/j.fertnstert.2006.03.062. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 173

  FocarelliRLuddiADe LeoVCapaldoAStendardiAPavoneVet al. Dysregulation of GdA expression in endometrium of women with endometriosis: implication for endometrial receptivity. Reprod Sci. (2018) 25:579–86. doi: 10.1177/1933719117718276. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 174

  LuddiAPavoneVSempliciBGoverniniLCriscuoliMPaccagniniEet al. Organoids of human endometrium: a powerful in vitromodel for the endometrium-embryo cross-talk at the implantation site. Cells. (2020) 9:1121. doi: 10.3390/cells9051121. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 175

  Garcia GarciaJMVannuzziVDonatiCBernacchioniCBruniPPetragliaF. Endometriosis: cellular and molecular mechanisms leading tofibrosis. Reprod Sci. (2023) 30:1453–61. doi: 10.1007/s43032-022-01083-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 176

  KutleIPoltenRHachenbergJKlapdorRMorganMSchambachA. Tumor organoid and spheroid models for cervical cancer. Cancers (Basel). (2023) 15:2518. doi: 10.3390/cancers15092518. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 177

  LiSLiuCWengL. Exploring cervical adenocarcinoma: epidemiological insights, diagnostic and therapeutic challenges, and pathogenetic mechanisms. Cancer Med. (2025) 14:e70620. doi: 10.1002/cam4.70620. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 178

  SeolHSOhJHChoiEKimSKimHNamEJ. Preclinical investigation of patient-derived cervical cancer organoids for precision medicine. J Gynecol Oncol. (2023) 34:e35. doi: 10.3802/jgo.2023.34.e35. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 179

  SuPChenCSunY. Physiopathology of polycystic ovary syndrome in endocrinology, metabolism and inflammation. J Ovarian Res. (2025) 18:34. doi: 10.1186/s13048-025-01621-6. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 180

  WiwatpanitTMurphyARLuZUrbanekMBurdetteJEWoodruffTKet al. Scaffold-free endometrial organoids respond to excess androgens associated with polycystic ovarian syndrome. J Clin Endocrinol Metab. (2020) 105:769–80. doi: 10.1210/clinem/dgz100. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 181

  LuHJiangHLiCDerisoudEZhaoAErikssonGet al. Dissecting the impact of maternal androgen exposure on developmental programming through targeting the androgen receptor. Adv Sci (Weinh). (2024) 11:e2309429. doi: 10.1002/advs.202309429. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 182

  YeZChengMLianWLengYQinXWangYet al. GPX4 deficiency-induced ferroptosis drives endometrial epithelial fibrosis in polycystic ovary syndrome. Redox Biol. (2025) 83:103615. doi: 10.1016/j.redox.2025.103615. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 183

  MahmutogluMAPreethaCJMeredigHTonnJCWellerMWickWet al. Deep learning-based identification of brain MRI sequences using a model trained on large multicentric study cohorts. Radiol Artif Intell. (2024) 6:e230095. doi: 10.1148/ryai.230095. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 184

  BouslimiRTrabelsiHKaraaWBAHedhliH. AI-driven radiology report generation for traumatic brain injuries. J Imaging Inform Med. (2025) 38(5):2630–45. doi: 10.1007/s10278-025-01411-y. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 185

  LadefogedCNAnderbergLMadsenKHenriksenOMHasselbalchSGAndersenFLet al. Estimation of brain amyloid accumulation using deep learning in clinical [11C]PiB PET imaging. EJNMMI Phys. (2023) 10:44. doi: 10.1186/s40658-023-00562-7. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 186

  LewCOCalabreseEChenJVTangFChaudhariGLeeAet al. Artificial intelligence outcome prediction in neonates with encephalopathy (AI-OPiNE). Radiol Artif Intell. (2024) 6:e240076. doi: 10.1148/ryai.240076. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 187

  FeleflyTFrancisZRoukozCFaresGAchkarSYazbeckSet al. A 3D convolutional neural network based on non-enhanced brain CT to identify patients with brain metastases. J Imaging Inform Med. (2025) 38:858–64. doi: 10.1007/s10278-024-01240-5. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 188

  ZhangKLiuXShenJLiZSangYWuXet al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell. (2020) 181:1423–1433.e11. doi: 10.1016/j.cell.2020.04.045. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 189

  JacobHDybvikJAYtre-HaugeSFasmerKEHoivikEATrovikJet al. An MRI-based radiomic prognostic index predicts poor outcome and specific genetic alterations in endometrial cancer. J Clin Med. (2021) 10:538. doi: 10.3390/jcm10030538. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 190

  Bereby-KahaneMDautryRMatzner-LoberECornelisFSebbag-SfezDPlaceVet al. Prediction of tumor grade and lymphovascular space invasion in endometrial adenocarcinoma with MR imaging-based radiomic analysis. Diagn Interv Imaging. (2020) 101:401–11. doi: 10.1016/j.diii.2020.01.003. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 191

  CrandallJPFraumTJLeeMJiangLGrigsbyPWahlRL. Repeatability of 18F-FDG PET radiomic features in cervical cancer. J Nucl Med. (2021) 62:707–15. doi: 10.2967/jnumed.120.247999. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 192

  LiXRJinJJYuYWangXHGuoYSunHZ. PET-CT radiomics by integrating primary tumor and peritumoral areas predicts E-cadherin expression and correlates with pelvic lymph node metastasis in early-stage cervical cancer. Eur Radiol. (2021) 31:5967–79. doi: 10.1007/s00330-021-07690-7. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 193

  ParkSHLimHBaeBKHahmMHChongGOJeongSYet al. Robustness of magnetic resonance radiomic features to pixel size resampling and interpolation in patients with cervical cancer. Cancer Imaging. (2021) 21:19. doi: 10.1186/s40644-021-00388-5. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 194

  AmidiEMostafaANandySYangGMiddletonWSiegelCet al. Classification of human ovarian cancer using functional, spectral, and imaging features obtained from in vivo photoacoustic imaging. BioMed Opt Express. (2019) 10:2303–17. doi: 10.1364/boe.10.002303. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 195

  AmidiEYangGUddinKMSLuoHMiddletonWPowellMet al. Role of blood oxygenation saturation in ovarian cancer diagnosis using multi-spectral photoacoustic tomography. J Biophotonics. (2021) 14:e202000368. doi: 10.1002/jbio.202000368. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 196

  MirinezhadMRAghasizadehMGhazizadehHHemmatpurAMashhadiMRFKhedmatgozarHet al. Hematological indices and genetic variants of premature ovarian insufficiency: machine learning approaches. Cardiovasc Hematol Disord Drug Targets. (2024) 24:98–109. doi: 10.2174/011871529x297081240613075328. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 197

  MorelliFMKimVHeckerFGeibelSMarín ZapataPA. uniDINO: assay-independent feature extraction for fluorescence microscopy images. Comput Struct Biotechnol J. (2025) 27:928–36. doi: 10.1016/j.csbj.2025.02.020. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 198

  MaesMDysonZASmithSEGouldingDALuddenCBakerSet al. A novel therapeutic antibody screening method using bacterial high-content imaging reveals functional antibody binding phenotypes of Escherichia coli ST131. Sci Rep. (2020) 10:12414. doi: 10.1038/s41598-020-69300-8. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 199

  TyagiTJainKGuSXQiuMGuVWMelchingerHet al. A guide to molecular and functional investigations of platelets to bridge basic and clinical sciences. Nat Cardiovasc Res. (2022) 1:223–37. doi: 10.1038/s44161-022-00021-z. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 200

  LaChanceJSuhKClausenJCohenDJ. Learning the rules of collective cell migration using deep attention networks. PloS Comput Biol. (2022) 18:e1009293. doi: 10.1371/journal.pcbi.1009293. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 201

  NagarADeMarcoRAHartonJA. Inflammasome and caspase-1 activity characterization and evaluation: an imaging flow cytometer-based detection and assessment of inflammasome specks and caspase-1 activation. J Immunol. (2019) 202:1003–15. doi: 10.4049/jimmunol.1800973. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 202

  BeilharzMDe NardoDLatzEFranklinBS. Measuring NLR oligomerization II: detection of ASC speck formation by confocal microscopy and immunofluorescence. Methods Mol Biol. (2016) 1417:145–58. doi: 10.1007/978-1-4939-3566-6_9. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 203

  HeXLiuXZuoFShiHJingJ. Artificial intelligence-based multi-omics analysis fuels cancer precision medicine. Semin Cancer Biol. (2023) 88:187–200. doi: 10.1016/j.semcancer.2022.12.009. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 204

  ChenRJLuMYWilliamsonDFKChenTYLipkovaJNoorZet al. Pan-cancer integrative histology-genomic analysis via multimodal deep learning. Cancer Cell. (2022) 40:865–878.e6. doi: 10.1016/j.ccell.2022.07.004. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 205

  NongWWeiHDouSHeLLinLLuDet al. The NLRP3 activation-related signature predicts the diagnosis and indicates immune characteristics in endometriosis. J Reprod Immunol. (2025) 168:104443. doi: 10.1016/j.jri.2025.104443. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 206

  LaneTRUrbinaFRankLGerlachJRiabovaOLepioshkinAet al. Machine learning models for Mycobacterium tuberculosisin vitro activity: prediction and target visualization. Mol Pharm. (2022) 19:674–89. doi: 10.1021/acs.molpharmaceut.1c00791

  • CrossRef
  • Google Scholar

• 207

  XiongZChengZLinXXuCLiuXWangDet al. Facing small and biased data dilemma in drug discovery with enhanced federated learning approaches. Sci China Life Sci. (2022) 65:529–39. doi: 10.1007/s11427-021-1946-0. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 208

  GaoYXieJTangRYangKZhangYChenLet al. Identification of a pyrimidinetrione derivative as the potent DprE1 inhibitor by structure-based virtual ligand screening. Bioorg Chem. (2019) 85:168–78. doi: 10.1016/j.bioorg.2018.12.018. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 209

  GundavdaKKPatkarSVartyGPShahNVelmuruganKGoelM. Liver resection for hepatocellular carcinoma: recent advances. J Clin Exp Hepatol. (2025) 15:102401. doi: 10.1016/j.jceh.2024.102401. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 210

  IacovacciVTamadonIKauffmannEFPaneSSimoniVMarzialeLet al. A fully implantable device for intraperitoneal drug delivery refilled by ingestible capsules. Sci Robot. (2021) 6:eabh3328. doi: 10.1126/scirobotics.abh3328. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 211

  WangXZhuJWangYWangCChenPLyuPet al. A respiratory signal monitoring method based on dual-pathway deep learning networks in image-guided robotic-assisted intervention system. Int J Med Robot. (2024) 20:e70017. doi: 10.1002/rcs.70017. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 212

  VakitbilirNIslamAGomezASteinKYFroeseLBergmannTet al. Multivariate modelling and prediction of high-frequency sensor-based cerebral physiologic signals: narrative review of machine learning methodologies. Sensors (Basel). (2024) 24:8148. doi: 10.3390/s24248148. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 213

  SchmittMMeyer-ZedlerTGuntinas-LichiusOPoppJ. Multimodal spectroscopic imaging: a new, powerful tool for intraoperative tumor diagnostics. Chirurgie (Heidelb). (2022) 93:948–55. doi: 10.1007/s00104-022-01663-2

  • CrossRef
  • Google Scholar

• 214

  ZhangJLiuLXiangPFangQNieXMaHet al. AI co-pilot bronchoscope robot. Nat Commun. (2024) 15:241. doi: 10.1038/s41467-023-44385-7. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 215

  LeeMCKnappG. Transfer RNA splicing in Saccharomyces cerevisiae. Secondary and tertiary structures of the substrates. J Biol Chem. (1985) 260:3108–15. doi: 10.1016/s0021-9258(18)89479-0

  • CrossRef
  • Google Scholar

• 216

  KlineAWangHLiYDennisSHutchMXuZet al. Multimodal machine learning in precision health: A scoping review. NPJ Digit Med. (2022) 5:171. doi: 10.1038/s41746-022-00712-8. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 217

  LuanYZhongGLiSWuWLiuXZhuDet al. A panel of seven protein tumour markers for effective and affordable multi-cancer early detection by artificial intelligence: A large-scale and multicentre case-control study. EClinicalMedicine. (2023) 61:102041. doi: 10.1016/j.eclinm.2023.102041. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 218

  MikdadiDO’ConnellKAMeachamPJDuganMAOjiereMOCarlsonTBet al. Applications of artificial intelligence (AI) in ovarian cancer, pancreatic cancer, and image biomarker discovery. Cancer biomark. (2022) 33:173–84. doi: 10.3233/cbm-210301. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 219

  HuHGehartHArtegianiBLópez-IglesiasCDekkersFBasakOet al. Long-term expansion of functional mouse and human hepatocytes as 3D organoids. Cell. (2018) 175:1591–1606.e19. doi: 10.1016/j.cell.2018.11.013. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 220

  YiSAZhangYRathnamCPongkulapaTLeeKB. Bioengineering approaches for the advanced organoid research. Adv Mater. (2021) 33:e2007949. doi: 10.1002/adma.202007949. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 221

  BaiLWuYLiGZhangWZhangHSuJ. AI-enabled organoids: Construction, analysis, and application. Bioact Mater. (2024) 31:525–48. doi: 10.1016/j.bioactmat.2023.09.005. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 222

  BakhtSMPardoAGomez-FloritMCaballeroDKunduSCReisRLet al. Human tendon-on-chip: Unveiling the effect of core compartment-T cell spatiotemporal crosstalk at the onset of tendon inflammation. Adv Sci (Weinh). (2024) 11:e2401170. doi: 10.1002/advs.202401170. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 223

  AbrhaleyAGidayMHailuA. Challenges and opportunities of translating animal research into human trials in Ethiopia. BMC Med Res Methodol. (2024) 24:211. doi: 10.1186/s12874-024-02338-8. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 224

  LiFHanJCaoTLamWFanBTangWet al. Design of self-assembly dipeptide hydrogels and machine learning via their chemical features. Proc Natl Acad Sci USA. (2019) 116:11259–64. doi: 10.1073/pnas.1903376116. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 225

  LeeBYoonSLeeJWKimYChangJYunJet al. Statistical characterization of the morphologies of nanoparticles through machine learning based electron microscopy image analysis. ACS Nano. (2020) 14:17125–33. doi: 10.1021/acsnano.0c06809. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 226

  TangXZhangJHeYZhangXLinZPartarrieuSet al. Explainable multi-task learning for multi-modality biological data analysis. Nat Commun. (2023) 14:2546. doi: 10.1038/s41467-023-37477-x. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 227

  MonzelASHemmerKKaomaTSmitsLMBologninSLucarelliPet al. Machine learning-assisted neurotoxicity prediction in human midbrain organoids. Parkinsonism Relat Disord. (2020) 75:105–9. doi: 10.1016/j.parkreldis.2020.05.011. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 228

  CunhaABHouJSchuelkeC. Machine learning for stem cell differentiation and proliferation classification on electrical impedance spectroscopy. J Electr Bioimpedance. (2019) 10:124–32. doi: 10.2478/joeb-2019-0018. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 229

  KegelesENaumovAKarpulevichEAVolchkovPBaranovP. Convolutional neural networks can predict retinal differentiation in retinal organoids. Front Cell Neurosci. (2020) 14:171. doi: 10.3389/fncel.2020.00171. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 230

  ParkKLeeJYLeeSYJeongIParkSYKimJWet al. Deep learning predicts the differentiation of kidney organoids derived from human induced pluripotent stem cells. Kidney Res Clin Pract. (2023) 42:75–85. doi: 10.23876/j.krcp.22.017. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 231

  BouazizJMashiachRCohenSKedemABaronAZajicekMet al. How artificial intelligence can improve our understanding of the genes associated with endometriosis: Natural language processing of the PubMed database. BioMed Res Int. (2018) 2018:6217812. doi: 10.1155/2018/6217812. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 232

  Bahado-SinghROYilmazABisginHTurkogluOKumarPShermanEet al. Artificial intelligence and the analysis of multi-platform metabolomics data for the detection of intrauterine growth restriction. PloS One. (2019) 14:e0214121. doi: 10.1371/journal.pone.0214121. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 233

  KarvasRMKhanSAVermaSYinYKulkarniDDongCet al. Stem-cell-derived trophoblast organoids model human placental development and susceptibility to emerging pathogens. Cell Stem Cell. (2022) 29:810–825.e8. doi: 10.1016/j.stem.2022.04.004. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 234

  GurumurthyRKKosterSKumarNMeyerTFChumduriC. Patient-derived and mouse endo-ectocervical organoid generation, genetic manipulation and applications to model infection. Nat Protoc. (2022) 17:1658–90. doi: 10.1038/s41596-022-00695-6. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 235

  QiGXZhaoRXGaoCMaZYWangSXuJ. Recent advances and challenges in colorectal cancer: From molecular research to treatment. World J Gastroenterol. (2025) 31:106964. doi: 10.3748/wjg.v31.i21.106964. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 236

  DengSLiCCaoJCuiZDuJFuZet al. Organ-on-a-chip meets artificial intelligence in drug evaluation. Theranostics. (2023) 13:4526–58. doi: 10.7150/thno.87266. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 237

  FengWSchrieverHJiangSBaisAWuHKostkaDet al. Computational profiling of hiPSC-derived heart organoids reveals chamber defects associated with NKX2–5 deficiency. Commun Biol. (2022) 5:399. doi: 10.1038/s42003-022-03346-4. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 238

  HeCKalafutNCSandovalSORisgaardRSiroisCLYangCet al. BOMA, a machine-learning framework for comparative gene expression analysis across brains and organoids. Cell Rep Methods. (2023) 3:100409. doi: 10.1016/j.crmeth.2023.100409. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 239

  AziziECarrAJPlitasGCornishAEKonopackiCPrabhakaranSet al. Single-cell map of diverse immune phenotypes in the breast tumor microenvironment. Cell. (2018) 174:1293–1308.e36. doi: 10.1016/j.cell.2018.05.060. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 240

  ChengFWangFTangJZhouYFuZZhangPet al. Artificial intelligence and open science in discovery of disease-modifying medicines for Alzheimer’s disease. Cell Rep Med. (2024) 5:101379. doi: 10.1016/j.xcrm.2023.101379. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 241

  PunFWOzerovIVZhavoronkovA. AI-powered therapeutic target discovery. Trends Pharmacol Sci. (2023) 44:561–72. doi: 10.1016/j.tips.2023.06.010. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 242

  RileyRDEnsorJSnellKIEArcherLWhittleRDhimanPet al. Importance of sample size on the quality and utility of AI-based prediction models for healthcare. Lancet Digit Health. (2025) 7:100857. doi: 10.1016/j.landig.2025.01.013. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 243

  TsegayeBSnellKIEArcherLKirtleySRileyRDSperrinMet al. Larger sample sizes are needed when developing a clinical prediction model using machine learning in oncology: Methodological systematic review. J Clin Epidemiol. (2025) 180:111675. doi: 10.1016/j.jclinepi.2025.111675. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 244

  VabalasAGowenEPoliakoffECassonAJ. Machine learning algorithm validation with a limited sample size. PloS One. (2019) 14:e0224365. doi: 10.1371/journal.pone.0224365. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 245

  YuYMaiYZhengYShiL. Assessing and mitigating batch effects in large-scale omics studies. Genome Biol. (2024) 25:254. doi: 10.1186/s13059-024-03401-9. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 246

  YangYLiGQianHWilhelmsenKCShenYLiY. SMNN: Batch effect correction for single-cell RNA-seq data via supervised mutual nearest neighbor detection. Brief Bioinform. (2021) 22:bbaa097. doi: 10.1093/bib/bbaa097. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 247

  MaharjanSMaCSinghBKangHOriveGYaoJet al. Advanced 3D imaging and organoid bioprinting for biomedical research and therapeutic applications. Adv Drug Delivery Rev. (2024) 208:115237. doi: 10.1016/j.addr.2024.115237. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 248

  GulshanVPengLCoramMStumpeMCWuDNarayanaswamyAet al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. (2016) 316:2402–10. doi: 10.1001/jama.2016.17216. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 249

  EstevaAKuprelBNovoaRAKoJSwetterSMBlauHMet al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. (2017) 542:115–8. doi: 10.1038/nature21056. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 250

  ChilamkurthySGhoshRTanamalaSBivijiMCampeauNGVenugopalVKet al. Deep learning algorithms for detection of critical findings in head CT scans: A retrospective study. Lancet. (2018) 392:2388–96. doi: 10.1016/s0140-6736(18)31645-3. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 251

  KassisTHernandez-GordilloVLangerRGriffithLG. OrgaQuant: Human intestinal organoid localization and quantification using deep convolutional neural networks. Sci Rep. (2019) 9:12479. doi: 10.1038/s41598-019-48874-y. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 252

  KokRNUHebertLHuelsz-PrinceGGoosYJZhengXBozekKet al. OrganoidTracker: Efficient cell tracking using machine learning and manual error correction. PloS One. (2020) 15:e0240802. doi: 10.1371/journal.pone.0240802. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 253

  TaddeseAATilahunBCAwokeTAtnafuAMamuyeAMengisteSA. Deep-learning models for image-based gynecological cancer diagnosis: A systematic review and meta-analysis. Front Oncol. (2023) 13:1216326. doi: 10.3389/fonc.2023.1216326. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 254

  DeiningerLJung-KlawitterSMikutRRichterPFischerMKarimian-JaziKet al. An AI-based segmentation and analysis pipeline for high-field MR monitoring of cerebral organoids. Sci Rep. (2023) 13:21231. doi: 10.1038/s41598-023-48343-7. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 255

  ShawPJMcDermottMFKannegantiTD. Inflammasomes and autoimmunity. Trends Mol Med. (2011) 17:57–64. doi: 10.1016/j.molmed.2010.11.001. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 256

  WenHGrisDLeiYJhaSZhangLHuangMTHet al. Fatty acid-induced NLRP3-ASC inflammasome activation interferes with insulin signaling. Nat Immunol. (2011) 12:408–15. doi: 10.1038/ni.2022. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 257

  KannegantiTDOzörenNBody-MalapelMAmerAParkJHFranchiLet al. Bacterial RNA and small antiviral compounds activate caspase-1 through cryopyrin/Nalp3. Nature. (2006) 440:233–6. doi: 10.1038/nature04517. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 258

  MenkhorstESantosLLZhouWYangGWinshipALRainczukKEet al. IL11 activates the placental inflammasome to drive preeclampsia. Front Immunol. (2023) 14:1175926. doi: 10.3389/fimmu.2023.1175926. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 259

  GuoXXuXLiTYuQWangJChenYet al. NLRP3 inflammasome activation of mast cells by estrogen via the nuclear-initiated signaling pathway contributes to the development of endometriosis. Front Immunol. (2021) 12:749979. doi: 10.3389/fimmu.2021.749979. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 260

  ZhouFLiCZhangSY. NLRP3 inflammasome: A new therapeutic target for high-risk reproductive disorders? Chin Med J (Engl). (2020) 134:20–7. doi: 10.1097/cm9.0000000000001214. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 261

  ParkYJungJGYuZCAsakaRShenWWangYet al. A novel human endometrial epithelial cell line for modeling gynecological diseases and for drug screening. Lab Invest. (2021) 101:1505–12. doi: 10.1038/s41374-021-00624-3. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 262

  PampaloniFReynaudEGStelzerEHK. The third dimension bridges the gap between cell culture and live tissue. Nat Rev Mol Cell Biol. (2007) 8:839–45. doi: 10.1038/nrm2236. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 263

  WhiteEAKennyHALengyelE. Three-dimensional modeling of ovarian cancer. Adv Drug Delivery Rev. (2014) 79–80:184–92. doi: 10.1016/j.addr.2014.07.003. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 264

  LiuXZhouQMengJZuoHLiRZhangRet al. Autophagy-mediated activation of the AIM2 inflammasome enhances M1 polarization of microglia and exacerbates retinal neovascularization. MedComm (2020). (2024) 5:e668. doi: 10.1002/mco2.668. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 265

  BorettoMCoxBNobenMHendriksNFassbenderARooseHet al. Development of organoids from mouse and human endometrium showing endometrial epithelium physiology and long-term expandability. Development. (2017) 144:1775–86. doi: 10.1242/dev.148478. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 266

  MurphyARCampoHKimJJ. Strategies for modelling endometrial diseases. Nat Rev Endocrinol. (2022) 18:727–43. doi: 10.1038/s41574-022-00725-z. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 267

  YangZGuanFBronkLZhaoL. Multi-omics approaches for biomarker discovery in predicting the response of esophageal cancer to neoadjuvant therapy: a multidimensional perspective. Pharmacol Ther. (2024) 254:108591. doi: 10.1016/j.pharmthera.2024.108591. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 268

  ZhouXJZhongXHDuanLX. Integration of artificial intelligence and multi-omics in kidney diseases. Fundam Res. (2023) 3:126–48. doi: 10.1016/j.fmre.2022.01.037. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 269

  WalshLAQuailDF. Decoding the tumor microenvironment with spatial technologies. Nat Immunol. (2023) 24:1982–93. doi: 10.1038/s41590-023-01678-9. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 270

  MahoneySADeyAKBasistyNHermanAB. Identification and functional analysis of senescent cells in the cardiovascular system using omics approaches. Am J Physiol Heart Circ Physiol. (2023) 325:H1039–58. doi: 10.1152/ajpheart.00352.2023. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 271

  XieJYangMRHuXHongZSBaiYYShengJet al. Moringa oleifera Lam. isothiocyanate quinazolinone derivatives inhibit U251 glioma cell proliferation through cell cycle regulation and apoptosis induction. Int J Mol Sci. (2023) 24:11376. doi: 10.3390/ijms241411376. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 272

  TangYFAnPGGuBXYiSHuXWuWJet al. Transcriptomic insights into adenoid cystic carcinoma via RNA sequencing. Front Genet. (2023) 14:1144945. doi: 10.3389/fgene.2023.1144945. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 273

  WuYLiuJXiaoYZhangSLiL. CoupleVAE: coupled variational autoencoders for predicting perturbational single-cell RNA sequencing data. Brief Bioinform. (2025) 26:bbaf126. doi: 10.1093/bib/bbaf126. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 274

  LiuQLiuZLiWSongX. Comparative transcriptome analysis indicates conversion of stamens into pistil-like structures in male sterile wheat (Triticum aestivum L.) with Aegilops crassa cytoplasm. BMC Genomics. (2020) 21:124. doi: 10.1186/s12864-020-6450-2. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 275

  ZouGShenQLiLZhangS. stAI: a deep learning-based model for missing gene imputation and cell-type annotation of spatial transcriptomics. Nucleic Acids Res. (2025) 53:gkaf158. doi: 10.1093/nar/gkaf158. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 276

  ChenLDautleMGaoRZhangSChenY. Inferring gene regulatory networks from time-series scRNA-seq data via GRANGER causal recurrent autoencoders. Brief Bioinform. (2025) 26:bbaf089. doi: 10.1093/bib/bbaf089. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 277

  PuZWangTBLuYWuZChenYLuoZet al. Deciphering the role of metal ion transport-related genes in T2D pathogenesis and immune cell infiltration via scRNA-seq and machine learning. Front Immunol. (2024) 15:1479166. doi: 10.3389/fimmu.2024.1479166. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 278

  ShaoWDingHWangYShiZZhangHMengFet al. Key genes and immune pathways in T-cell mediated rejection post-liver transplantation identified via integrated RNA-seq and machine learning. Sci Rep. (2024) 14:24315. doi: 10.1038/s41598-024-74874-8. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 279

  ZhangLLiJZhangQGaoJZhaoKAsaiYet al. An integrative analysis of single-cell RNA-seq, transcriptome and Mendelian randomization for the identification and validation of NAD+ metabolism-related biomarkers in ulcerative colitis. Int Immunopharmacol. (2025) 145:113765. doi: 10.1016/j.intimp.2024.113765. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 280

  MoXJiFChenJYiCWangF. Impact of mitophagy-related genes on the diagnosis and development of esophageal squamous cell carcinoma via single-cell RNA-seq analysis and machine learning algorithms. J Microbiol Biotechnol. (2024) 34:2362–75. doi: 10.4014/jmb.2407.07052. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 281

  DepuydtMACPrangeKHMSlendersLÖrdTElbersenDBoltjesAet al. Microanatomy of the human atherosclerotic plaque by single-cell transcriptomics. Circ Res. (2020) 127:1437–55. doi: 10.1161/circresaha.120.316770. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 282

  FloresMLiuZZhangTHasibMMChiuYCYeZet al. Deep learning tackles single-cell analysis-a survey of deep learning for scRNA-seq analysis. Brief Bioinform. (2022) 23:bbab531. doi: 10.1016/b978-0-443-29058-9.00009-4. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 283

  JiLJayachandranGRothJA. High throughput profiling of serum phosphoproteins/peptides using the SELDI-TOF-MS platform. Methods Mol Biol. (2012) 818:199–216. doi: 10.1007/978-1-61779-418-6_14. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 284

  WangMChenLLiJYouYQianZLiuJet al. An omics review and perspective of researches on intrahepatic cholestasis of pregnancy. Front Endocrinol (Lausanne). (2023) 14:1267195. doi: 10.3389/fendo.2023.1267195. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 285

  BennikeTBCarlsenTGEllingsenTBonderupOKGlerupHBøgstedMet al. Neutrophil extracellular traps in ulcerative colitis: a proteome analysis of intestinal biopsies. Inflammation Bowel Dis. (2015) 21:2052–67. doi: 10.1097/mib.0000000000000460. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 286

  ShenCLiLChenJY. Discover true association rates in multi-protein complex proteomics data sets. Proc IEEE Comput Syst Bioinform Conf. (2005), 167–74. doi: 10.1109/csb.2005.29. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 287

  MulveyCThurBCrawfordMGodovac-ZimmermannJ. How many proteins are missed in quantitative proteomics based on MS/MS sequencing methods? Proteomics Insights. (2010) 3:61–6. doi: 10.4137/pri.s5882. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 288

  LinTTZhangTKitataRBLiuTSmithRDQianWJet al. Mass spectrometry-based targeted proteomics for analysis of protein mutations. Mass Spectrom Rev. (2023) 42:796–821. doi: 10.1002/mas.21741. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 289

  BhatiaHSBrunnerADÖztürkFKapoorSRongZMaiHet al. Spatial proteomics in three-dimensional intact specimens. Cell. (2022) 185:5040–5058.e19. doi: 10.1016/j.cell.2022.11.021. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 290

  HeFAebersoldRBakerMSBianXBoXChanDWet al. π-HuB: the proteomic navigator of the human body. Nature. (2024) 636:322–31. doi: 10.1038/s41586-024-08280-5. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 291

  YiJLinPLiQZhangAKongX. A new strategy for treating colorectal cancer: regulating the influence of intestinal flora and oncolytic virus on interferon. Mol Ther Oncolytics. (2023) 30:254–74. doi: 10.1016/j.omto.2023.08.010. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 292

  HanMWangNHanWBanMSunTXuJ. Vaginal and tumor microbiomes in gynecological cancer (review). Oncol Lett. (2023) 25:153. doi: 10.3892/ol.2023.13739. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 293

  KangWTXuHLiaoYGuoQHuangQXuYet al. Qualitative and quantitative detection of multiple sexually transmitted infection pathogens reveals distinct associations with cervicitis and vaginitis. Microbiol Spectr. (2022) 10:e0196622. doi: 10.1128/spectrum.01966-22. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 294

  LiHZangYWangCLiHFanAHanCet al. The interaction between microorganisms, metabolites, and immune system in the female genital tract microenvironment. Front Cell Infect Microbiol. (2020) 10:609488. doi: 10.3389/fcimb.2020.609488. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 295

  ChenWZhangPZhangXXiaoTZengJGuoKet al. Machine learning-causal inference based on multi-omics data reveals the association of altered gut bacteria and bile acid metabolism with neonatal jaundice. Gut Microbes. (2024) 16:2388805. doi: 10.1080/19490976.2024.2388805. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 296

  ShenXChenSLiangLAvinaMZackriahHJelliffe-PawlowskiLet al. Longitudinal urine metabolic profiling and gestational age prediction in human pregnancy. Brief Bioinform. (2024) 26:bbaf059. doi: 10.1093/bib/bbaf059. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 297

  DengYYaoYWangYYuTCaiWZhouDet al. An end-to-end deep learning method for mass spectrometry data analysis to reveal disease-specific metabolic profiles. Nat Commun. (2024) 15:7136. doi: 10.1038/s41467-024-51433-3. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar

• 298

  GoyalAWangTDubinkinaVMaslovS. Ecology-guided prediction of cross-feeding interactions in the human gut microbiome. Nat Commun. (2021) 12:1335. doi: 10.1038/s41467-021-21586-6. PMID:

  • Pubmed Abstract
  • CrossRef
  • Google Scholar