Volume II: Methods, Tools and Algorithms in Drug Discovery Bioinformatics

Computational bioinformatics has become the cornerstone of modern drug discovery, enabling deeper insights into target identification, lead optimization, and therapeutic repurposing. Rapid progress across fields such as structural bioinformatics, cheminformatics, machine learning, and systems biology has transformed data-driven hypothesis formulation and mechanism modeling. These interdisciplinary advances have led to scalable and interpretable frameworks that connect molecular, cellular, and clinical data streams, reinforcing the pivotal role of informatics in translational pharmaceutical research. Yet, challenges remain in ensuring methodological rigor, transparency, and reproducibility across complex, multi-modal datasets, reinforcing the need for integrative benchmarking, uncertainty quantification, and open, interoperable ecosystems. Recent developments have demonstrated the potential of deep learning architectures—such as foundation and generative models, graph neural networks, and multimodal transformers—to enhance molecular representation learning and de novo molecule design. Similarly, progress in structural biology and computational chemistry has refined protein–ligand interaction prediction, ultra-large virtual screening, and free energy estimation at scale. In parallel, biologics and immunoinformatics approaches are advancing antibody and vaccine design, while computational PK/PD and toxicology models are bridging in silico predictions with human pharmacology. Despite these strides, many workflows still face barriers to validation and standardization, underscoring the need for comprehensive frameworks that connect robust algorithms with real-world applications.This Research Topic aims to curate authoritative perspectives on emerging methods, tools, and algorithms in drug discovery bioinformatics, emphasizing rigor, benchmarking, and translational relevance. We seek contributions that unify computational innovation with reproducibility and open science principles, enhancing predictive performance, generalizability, and impact across the discovery–development continuum. By consolidating rigorous syntheses, this collection will foster shared standards and reproducible practices that drive data-centric decision making in modern R&D pipelines.To gather further insights into computational bioinformatics frameworks for drug discovery, we welcome submissions addressing, but not limited to, the following themes:o AI and machine learning for molecular design, prediction, and interpretabilityo Structure-based modeling, docking, and free energy calculation methodso Integrative CADD and cheminformatics workflows at scale (HPC, cloud)o Knowledge graphs, ontologies, and FAIR-compliant data infrastructureso Computational ADME, PK/PD, and predictive toxicology frameworkso Structural bioinformatics for complex systems and cryptic pocket discoveryo Systems biology and network-based mechanistic modelingo Biologics and immunoinformatics for antibody and vaccine discoveryo Computational benchmarking, reproducibility, and open-source tool developmento AI and machine learning in tool development Topic editors: Pranab Kishor Mohapatra, Cristiano Valim Bizarro Source: https://www.frontiersin.org/research-topics/83822/volume-ii-methods-tools-and-algorithms-in-drug-discovery-bioinformatics