Drug discovery is increasingly driven by computational innovation, transforming how we identify targets, discover hits, optimize leads, and repurpose approved molecules. Advances across structural bioinformatics, cheminformatics, and machine learning now enable high-throughput hypothesis generation, mechanism-aware modeling, and data-centric decision-making at unprecedented scale. From AI-enabled generative design to multi-scale systems modeling and physiologically based PK/PD, informatics has become integral to improving efficiency, reproducibility, and translational impact throughout the R&D pipeline.

Within this landscape, progress hinges on robust methods, interoperable tools, and validated algorithms that integrate heterogeneous data—structural, chemical, omics, phenotypic, clinical—under rigorous standards of benchmarking, uncertainty quantification, and FAIR principles. Modern CADD spans protein–ligand and protein–protein docking, binding free energy estimation, QSAR/QSPR, and large-scale virtual screening, increasingly accelerated by GPUs, distributed computing, and cloud-native workflows. Parallel advances in data engineering—knowledge graphs, ontologies, and provenance-aware pipelines—support trustworthy aggregation and retrieval across public and proprietary resources.

Equally vital are methodologies for ADME/Tox prediction and translational PK/PD, which bridge in silico findings to safety and efficacy. In biologics and immunoinformatics, sequence- and structure-based analytics are reshaping antibody design, epitope discovery, and vaccine development. Structural bioinformatics underpins target assessment, cryptic pocket detection, conformational ensemble analysis, and complex modeling, including challenging systems such as membrane proteins and IDPs. Systems biology and phenomenological modeling enable mechanism discovery, target prioritization, and synthetic lethality mapping.

Despite these advances, the field needs authoritative syntheses that clarify best practices, standardize evaluation, and highlight reproducible, open workflows with demonstrated utility in real-world pipelines. This Research Topic addresses that need by consolidating critical knowledge across methods, tools, and algorithms with clear relevance to drug discovery and development. Submissions solely focused on genetic screening without a direct drug discovery link, or lacking a clear bioinformatics application to pharmaceutical development, are out of scope.

To curate definitive, practice-oriented reviews that distill state-of-the-art methods, tools, and algorithms in drug discovery bioinformatics, emphasizing rigor, benchmarking, reproducibility, and translational relevance across the pipeline from target identification to optimization and repurposing—thereby accelerating computation-enabled therapeutic discovery and decision-making.

We invite Mini Reviews, Systematic Reviews, and Full Reviews that provide comprehensive, critical, and tutorial value across:

- AI/ML for Drug Discovery

- Foundation and generative models, GNNs, multimodal learning; interpretability, causality, active learning, domain adaptation; data-centric AI and uncertainty.

- CADD and Cheminformatics

- Protein–ligand/protein–protein docking and scoring; pose refinement; free energy methods; QSAR/QSPR; hybrid physics–ML; ultra-large virtual screening (HPC/cloud).

- ADME, PK/PD, and Toxicity

- Mechanistic and data-driven prediction; PBPK, translational frameworks; predictive toxicology and safety margins; validation strategies and XAI for safety.

- Data, Standards, and Visualization

- Databases, knowledge graphs, ontologies, FAIR/PROV; dataset curation, bias mitigation; interactive visualization and XR (VR/AR/MR) for design and decisions.

- Structure prediction and refinement; complex/membrane/IDP modeling; binding site detection and cryptic pocket discovery; conformational ensembles.

- Systems Biology and Phenomenological Modeling

- Network/ODE/agent-based models; pathway inference; target prioritization and synthetic lethality.

- Biologics and Immunoinformatics

- Antibody/peptide design; developability; epitope/neoepitope prediction; TCR/BCR analytics; vaccine design.

- Software, Algorithms, and Reproducibility

- Benchmarking protocols; open-source tools; containers, workflows, and MLOps; GPU/distributed computing; scalability and cost-performance.

Reviews must demonstrate clear application to drug discovery and development. Genetic screening is in scope only when directly enabling target discovery/validation or therapeutic hypothesis generation.

Are you interested in contributing a manuscript to this Research Topic?

Methods, Tools and Algorithms in Drug Discovery Bioinformatics