Perspectives for building a computational drug discovery program in resource-limited settings

Computational drug discovery is increasingly transforming the way therapeutic candidates are identified, prioritized, and optimized, with advances in artificial intelligence (AI), machine learning, molecular modelling, cheminformatics, and data-driven approaches expanding the possibilities for early-stage drug discovery. The growing availability of open-source software, public chemical and biological databases, cloud and high-performance computing, and increasingly accessible AI technologies presents an important opportunity for researchers and institutions in resource-limited settings to participate more actively in global drug discovery. Nevertheless, translating these technological opportunities into sustainable research capacity remains challenging, particularly in low- and middle-income countries, where limitations in infrastructure, funding, skilled personnel, multidisciplinary integration, and access to appropriate technologies can constrain program development. In this Perspective, we reflect on practical approaches to building computational drug discovery programs that are scientifically focused, locally embedded, collaborative, reproducible, and sustainable. Drawing on experiences spanning computational chemistry, natural product drug discovery, AI-driven research, capacity development, and international collaboration, we propose ten guiding principles covering scientific focus, human and computational infrastructure, open-source tools and data, reproducible workflows, equitable partnerships, responsible AI adoption, open science, funding diversification, research culture, and long-term institutional sustainability. We argue that meaningful participation in computational drug discovery does not necessarily require immediate access to extensive or expensive infrastructure, but rather strategic investment in people, fit-for-purpose technologies, open resources, and durable research ecosystems. These perspectives are intended to stimulate discussion and provide a practical framework for emerging research groups seeking to harness computational approaches to address diseases of regional and global importance.