Artificial Intelligence-Driven Drug Design (AIDD) in Cancer Therapeutics

Cancer continues to be a substantial global health issue. By customizing prevention, diagnosis, and treatment plans depending on individual patient genetic makeup, environment, and lifestyle, precision medicine presents a hopeful path. PM allows tailored treatment plans meant to increase patient outcomes by combining multi-omics and multi-modal data. In this field artificial intelligence (AI), especially machine learning (ML) and deep learning, has become a rather effective instrument. By using big data and artificial intelligence, complex datasets including genomics, transcriptomics, proteomics, radiomics, and digital pathology can have meaningful insights extracted and hidden trends can be found. These technologies support the identification of new biomarkers for cancer screening, diagnosis, therapy choice, and prognosis prediction as well as help doctors to have a complete knowledge of tumors. Combining artificial intelligence with PM has great potential to improve clinical decision-making and provide customized treatment that raises cancer patient outcomes.Recent research shows how ML might support clinical decision-making, improve tumor classification, and predict therapy response. Moreover, quantitative structure-activity relationship (QSAR) modelling provides a useful instrument for drug development since it allows one to predict compound efficacy depending on molecular structure. QSAR and ML taken together enable effective virtual screening and personalized therapy development.Standardized, interpretable, and clinically validated models remain few even with these developments. This work intends to investigate and create AI- and QSAR-driven approaches, combining imaging data and multi-omics for complete tumor profiling. The objective is to find new biomarkers, enhance diagnosis, direct therapy decisions, and forecast results—ultimately with the aim of improving the application of precision medicine in oncology and providing individualized treatment that raises patient survival and quality of life.With a focus toward integrating multi-omics and imaging data to progress precision medicine, this Research Topic seeks to investigate creative uses of artificial intelligence (AI), and machine learning (ML) in cancer research. We welcome contributions using AI-driven approaches addressing tumor classification, biomarker discovery, treatment optimization, prognosis prediction, and drug development. Deep learning for radiomics and pathology, ML-based multi-omics integration, interpretable artificial intelligence models, QSAR in personalized drug design, and real-world clinical applications of artificial intelligence in oncology are among the specific themes, though not limited to anyone.Please note: Manuscripts consisting solely of bioinformatics, computational analysis, or predictions of public databases which are not accompanied by validation (independent clinical or patient cohort, or biological validation in vitro or in vivo, which are not based on public databases) are not suitable for publication in this journal. Topic editors: Shashanka Prasad, Liang Cheng, Benedito Carneiro Source: https://www.frontiersin.org/research-topics/72735/artificial-intelligence-driven-drug-design-aidd-in-cancer-therapeutics