AI in Drug Discovery, Genomics & Precision Medicine

Session Overview

The application of artificial intelligence to drug discovery and genomic medicine represents one of the most consequential scientific convergences of our era. From the in silico design of novel therapeutic molecules to the integration of multi-omics data in precision treatment planning, AI is fundamentally reshaping the pipeline that connects molecular biology with clinical medicine. This session brings together computational biologists, medicinal chemists, genomicists, pharmacologists, and translational researchers to explore how machine learning, deep learning, and data-driven approaches are accelerating every stage of the drug discovery and precision medicine continuum.

This session features a keynote lecture, four oral presentations, and a poster presentation segment spanning the breadth of AI applications in molecular design, genomics, systems biology, and individualized therapeutic strategies.

Why This Session Matters Now

The traditional drug discovery pipeline — characterized by high attrition rates, decade-long timelines, and billions in development costs — is under profound pressure to transform. AI-driven approaches are demonstrating the capacity to compress early-stage discovery timelines, identify previously intractable targets, and generate novel chemical entities with predicted efficacy and safety profiles. Simultaneously, the maturation of single-cell sequencing, spatial transcriptomics, and multi-omics integration platforms is generating biological datasets of unprecedented resolution, demanding AI methodologies capable of extracting actionable insight at scale. In precision medicine, the convergence of genomic profiling, pharmacogenomics, and AI-driven stratification is moving individualized therapy from oncology into a broad range of complex and rare diseases. The 2027 landscape will be defined by the translation of these computational advances into validated clinical applications.

Key Scientific & Technical Themes

AI in Molecular Design, Target Identification & In Silico Drug Screening

Generative AI architectures — including variational autoencoders, graph neural networks, and large language models trained on chemical space — are enabling the de novo design of drug-like molecules with specified biological activity profiles. AI-driven virtual screening and molecular docking are replacing or augmenting high-throughput experimental approaches, enabling the rapid prioritization of candidate compounds from vast chemical libraries. Target identification and validation using AI-based analysis of multi-omic, structural, and literature data is uncovering novel druggable proteins and pathway vulnerabilities across disease areas. This theme examines the computational methodologies, benchmarking standards, and experimental validation strategies that define the current frontier of AI-assisted molecular drug design and in silico screening.

Genomics, Multi-Omics Integration & Biomarker Discovery

The proliferation of high-throughput sequencing technologies has generated genomic, transcriptomic, proteomic, and metabolomic datasets that far exceed the analytical capacity of traditional bioinformatics approaches. Machine learning methods — from ensemble models for variant interpretation to deep learning architectures for non-coding regulatory element analysis — are enabling the extraction of biologically and clinically meaningful signals from these complex, high-dimensional data landscapes. Single-cell omics analysis is resolving cellular heterogeneity at unprecedented resolution, revealing disease-relevant subpopulations and trajectory dynamics that bulk sequencing obscures. Spatial transcriptomics is adding a further dimension by mapping gene expression within tissue architecture. This theme addresses the AI methodologies underpinning multi-omics integration, biomarker discovery and validation, and the translation of genomic signals into actionable clinical information.

Systems Biology, Network Medicine & Digital Twins

Understanding disease as a systems-level phenomenon — involving complex interactions between genes, proteins, metabolites, and environmental factors — requires analytical frameworks that can capture and model biological complexity at multiple scales. AI-driven systems biology and network medicine approaches are constructing and interrogating disease-relevant molecular interaction networks, identifying key regulatory nodes, and predicting the systemic consequences of therapeutic intervention. Pathway analysis and network biology are revealing mechanistic connections between molecular alterations and phenotypic outcomes that reductionist approaches miss. Digital twin modeling — the construction of computational representations of biological systems parameterized with patient-specific data — is emerging as a powerful framework for simulating disease progression and predicting individualized treatment responses. This theme explores the computational architectures, data requirements, and validation frameworks for AI in systems-level biological modeling.

Pharmacogenomics, Precision Therapeutics & Rare Disease

The promise of delivering the right treatment to the right patient at the right dose is increasingly being realized through the integration of pharmacogenomic profiling with AI-driven clinical decision support. Genetic variants affecting drug metabolism, efficacy, and toxicity are being systematically characterized and incorporated into AI models that guide prescribing decisions across therapeutic areas. In oncology and beyond, AI-driven patient stratification based on genomic, proteomic, and clinical features is enabling the design and execution of biomarker-selected clinical trials that maximize the probability of therapeutic success. Rare disease research represents a domain where AI is particularly impactful — enabling the identification of causal variants, the prioritization of therapeutic targets, and the design of gene therapy and RNA-based interventions in conditions where patient populations are too small for conventional approaches. This theme covers the breadth of AI applications in pharmacogenomics, precision prescribing, and rare disease drug development.

Vaccine Design, Immunoinformatics & CRISPR-Based Approaches

The rapid development of effective vaccines during global health emergencies demonstrated the potential of AI-accelerated immunoinformatics to compress timelines that previously spanned years into weeks. Computational approaches to antigen design, epitope prediction, and immunogenicity modeling are becoming central tools in both prophylactic and therapeutic vaccine development across infectious disease and oncology. CRISPR-based genome editing, guided by AI-assisted design of guide RNAs and prediction of off-target effects, is advancing the development of gene correction strategies for monogenic diseases and next-generation cell therapies. This theme examines the computational frameworks, experimental validation strategies, and translational pathways that are defining AI-driven vaccine and gene-based therapeutic development.

Research Landscape & Data Trends

AI in drug discovery and genomics is among the most rapidly expanding areas of biomedical research, driven by the simultaneous maturation of deep learning methodology and the explosive growth of biological data generation. The literature is characterized by an accelerating cycle of computational innovation — new model architectures, training strategies, and benchmark datasets — followed by experimental validation and translational application. Multi-omics integration and foundation models trained on biological sequences are emerging as dominant paradigms, with significant activity around protein structure prediction, molecular generation, and genomic variant interpretation. The precision medicine literature is increasingly focused on prospective clinical validation of AI-driven stratification and treatment selection, with regulatory agencies developing guidance frameworks for AI-based companion diagnostics and therapeutic selection tools. By 2027, digital twin modeling and spatially resolved omics analysis are expected to represent the defining frontier of the field.

Who Should Attend

  • Computational biologists and bioinformaticians developing AI methods for genomic and multi-omics data analysis
  • Medicinal chemists and structural biologists working on AI-assisted molecular design and drug screening
  • Pharmacologists and drug development scientists integrating AI into preclinical and translational pipelines
  • Genomic medicine specialists applying precision approaches in clinical practice
  • Oncologists and precision medicine clinicians using genomic profiling to guide treatment decisions
  • Systems biologists and network medicine researchers modeling disease at a pathway and network level
  • Rare disease researchers and geneticists developing AI-driven diagnostic and therapeutic strategies
  • Pharmacogenomics researchers and clinical pharmacologists studying drug-genome interactions
  • Immunologists and vaccinologists applying computational approaches to antigen and vaccine design
  • Regulatory scientists and translational researchers navigating AI-based diagnostic and therapeutic approval pathways

Session Perspective

Artificial intelligence is not replacing the scientist in drug discovery and genomic medicine — it is fundamentally augmenting the capacity to navigate biological complexity at a scale and speed that was previously inconceivable. The session reflects the conviction that the most important advances at this frontier will emerge from deep collaboration between computational and experimental disciplines, and between academic discovery and clinical translation. Researchers and innovators who are building the next generation of AI-driven therapeutic and genomic tools are invited to share their work, challenge existing paradigms, and engage with a community committed to transforming biological insight into patient benefit.

If your research aligns with this session, we invite you to submit an abstract for consideration.

Submit Your Abstract