About this Research Topic
The impact of Artificial Intelligence on traditional drug discovery is in its early stages. Over the past decade, the development of oncogene/pathway-directed targeted therapies made huge progress in complex disease treatment. However, hundreds of drugs failed in clinical trials, likely due to misclassified responders in the cohorts or weak treatment efficacy of predictive biomarkers. Even when there is an initial treatment response, durable drug responses are rare, as cells acquire drug resistance. To achieve sustainable clinical responses, AI can deliver value in small-molecule drug discovery by multi-Omics data integration, novel chemistry discovery with structural and clinical outcome prediction, identification of cohorts with responders, and quicker and cheaper discovery processes. With the upcoming opportunities in single-cell omics, CRISPR genome-editing screens, drug-like chemical space, and advanced network biology analysis, AI-enabled capabilities highlight lessons derived from the development of novel drugs and propose new horizons for the clinical development of personalized medicine in understanding and differentiating the use cases.
This Research Topic aims to bring together a collection of papers that individually and collectively use AI-enhanced drug discovery and personalized medicine. We aim to highlight that AI facilitates drug discovery and reveals molecular insights with an in-depth understanding of biology. AI algorithms can potentially transform most discovery tasks, such as drug design and adverse reaction prediction, so physical experiments are conducted only when required to validate results. For example, AI-driven personalized medicine revolutionizes potential treatment globally by providing sustainable clinical responses and avoiding side effects by integrating multi-Omics, molecular structural, imaging, and clinical data. To reveal appropriate intervention “agents” and strategies for treating an individual with a disease, AI can infer the potential IC50 of drugs in developing personalized medicines. Then, the pharmaceutical company can benefit from AI-driven personalized therapy and perform clinical trials for phenotypic monitoring and drug monitoring. We strive to gather research papers from many domains where AI can play such a role and highlight AI’s ability in advanced personalized medicine with in-depth learning from data.
The Research Topic will focus on late-breaking research, including but not limited to the following topics:
1) AI-enabled multi-Omics data integration and explainable discovery.
2) AI-based insights into drug-target characterization and prediction.
3) AI-enhanced cohort stratification.
4) AI-enhanced network medicine.
5) AI-enhanced systematic complex disease therapy.
6) AI-based drug-drug adverse reaction.
7) AI-based analysis in single-cell data.
8) AI-based analysis of medical imaging data.
9) AI & ML methods for personalized drug repurposing.
10) Supervised, Unsupervised, self-supervised, and semi-supervised ML methods for personalized drug discovery processes.
This Research Topic aims to bring together a collection of papers that individually and collectively use AI-enhanced drug discovery and personalized medicine. We aim to highlight that AI facilitates drug discovery and reveals molecular insights with an in-depth understanding of biology. AI algorithms can potentially transform most discovery tasks, such as drug design and adverse reaction prediction, so physical experiments are conducted only when required to validate results. For example, AI-driven personalized medicine revolutionizes potential treatment globally by providing sustainable clinical responses and avoiding side effects by integrating multi-Omics, molecular structural, imaging, and clinical data. To reveal appropriate intervention “agents” and strategies for treating an individual with a disease, AI can infer the potential IC50 of drugs in developing personalized medicines. Then, the pharmaceutical company can benefit from AI-driven personalized therapy and perform clinical trials for phenotypic monitoring and drug monitoring. We strive to gather research papers from many domains where AI can play such a role and highlight AI’s ability in advanced personalized medicine with in-depth learning from data.
The Research Topic will focus on late-breaking research, including but not limited to the following topics:
1) AI-enabled multi-Omics data integration and explainable discovery.
2) AI-based insights into drug-target characterization and prediction.
3) AI-enhanced cohort stratification.
4) AI-enhanced network medicine.
5) AI-enhanced systematic complex disease therapy.
6) AI-based drug-drug adverse reaction.
7) AI-based analysis in single-cell data.
8) AI-based analysis of medical imaging data.
9) AI & ML methods for personalized drug repurposing.
10) Supervised, Unsupervised, self-supervised, and semi-supervised ML methods for personalized drug discovery processes.
Keywords: Artificial Intelligence, Drug Discovery, drug repurposing, personalized medicine, drug combination
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
