Editorial: Computational Genomics and Precision Medicine

Zeeshan Ahmed^1,2*Ramkumar Thirunavukarasu³Atlas Khan⁴

• ¹Institute for Health, Health Care Policy and Aging Research, Rutgers, The State University of New Jersey, New Brunswick, New Jersey, United States
• ²Department of Medicine, Robert Wood Johnson Medical School, Rutgers, The State University of New Jersey, New Brunswick, New Jersey, United States
• ³VIT University, Vellore, Tamil Nadu, India
• ⁴Columbia University Irving Medical Center, Columbia University, New York, New York, United States

Misdiagnosis has been reported among the leading causes of death, along with cancer, heart disease, and respiratory diseases [1]. A fair amount of literature has been published in impactful peerreviewed journals, which discuss medication error and delayed treatment, and is accessible through authentic resources (e.g., PubMed) [2]). One of the most trending subjects in life sciences, which addresses these issues and contributes to providing personalized treatment to patients, is genomic and precision medicine [3]. It involves patient engagement, analyzing medical records to examine provided diagnoses and treatment outcomes, and investigating the genomic profile to understand disease mechanisms and propose better treatments [4]. Furthermore, it promotes integrating and analyzing different kinds of patient data (e.g., clinical, sociodemographic, behavioral, biomedical image, and multi-omics) to form multimodal data to discover important risk factors and biomarkers, which could be used to prevent and predict diseases [5]. This research topic focuses on gathering the most up-to-date knowledge on recent advances in analytical approaches, including deep and machine learning models for identifying disease-associated genes and rare variants, and predicting the best treatment outcomes for genomic and precision medicine. Successfully achieving the goals of this research topic, we were able to publish five interesting peer-reviewed articles.In, "SAFE-MIL: a statistically interpretable framework for screening potential targeted therapy patients based on risk estimation", Guan et al. set out to construct a generalizable framework for risk assessment of treatment failure for Non-Small Cell Lung Cancer (NSCLC) patients receiving epidermal growth factor receptor tyrosine kinase inhibitor-based treatment. Currently, patients with NSCLC who have the same target gene mutation experience vastly different treatment outcomes, largely due to varying mutation abundance levels and drug sensitivity that existing models don't account for, leading to black boxes and misalignment with Food and Drug Administration (FDA) standards, weakening the clinical applicability of machine learning (ML)driven drug prediction models. This study utilized three independent patient cohorts, implementing We are grateful to the Frontiers, Frontiers in Genetics, and editorial staff for their endless support in 104 the preparation, study collection, peer-review processes, editing, press, and publication process 105 involved in this research topic. We thank the honorable reviewers for their time and constructive 106 suggestions to the authors for the possible quality and scientific improvements to their studies. 107The authors declare that the research was conducted without any commercial or financial 109 relationships that could potentially create a conflict of interest. 110