Automation and Acceleration of Translational Drug Design, Discovery and Development in the Era of Artificial Intelligence

The convergence of artificial intelligence (AI), machine learning (ML), and modern biological research is fundamentally reshaping our ability to understand, engineer, and manipulate biological systems at the molecular scale. Recent advances in AI-driven technologies, particularly those capable of predicting protein structures, modelling biological pathways, identifying drug targets, and designing novel therapeutics, are transforming the landscape of translational drug discovery and development. Processes that previously required many years of iterative experimentation may now, in some cases, be accelerated to months or even weeks.These developments offer unprecedented opportunities to address some of the most urgent biomedical challenges of our time, including antimicrobial resistance (AMR), multidrug-resistant bacterial infections, emerging pathogens, and other complex diseases that continue to evade conventional therapeutic strategies. The integration of AI/ML approaches with molecular biology, structural biology, medicinal chemistry, systems biology, and translational medicine is creating new paradigms for diagnostic design, therapeutic innovation and precision intervention.Transformative technologies such as AlphaFold and emerging generative protein-design platforms are redefining how researchers conceptualise, design, and prototype biomolecules and therapeutic candidates. However, alongside these remarkable advances come significant scientific, translational, and ethical challenges. AI/ML systems may exhibit model hallucinations, overconfidence, embedded data biases, limited interpretability, and difficulties in accurately predicting complex biological behaviour in vivo. Importantly, computational predictions must still undergo rigorous experimental and clinical validation before translation into safe and effective therapeutic applications.At the same time, certain forms of AI-generated “hallucination” may also provide unexpected opportunities for scientific creativity by enabling the exploration of previously unrecognised protein folds, unconventional drug scaffolds, and novel therapeutic hypotheses beyond traditional human intuition. Understanding how to distinguish productive computational innovation from misleading artefacts is becoming an increasingly important scientific and translational competency.This Research Topic aims to bring together leading scientists, clinicians, computational biologists, bioengineers, translational researchers, industry innovators, regulators, and policymakers to explore both the transformative opportunities and emerging limitations of AI-driven drug discovery and development. We welcome submissions of Original Research, Review articles, Mini Reviews, Perspectives, Methods, and Opinion articles addressing the rapidly evolving interface between AI/ML technologies and translational biomedical science.Potential themes include, but are not limited to:1. AI/ML-guided antimicrobial and anti-infective drug design 2. Protein structure prediction and generative protein engineering3. AI-enabled hit to lead identification and optimisation4. Computational medicinal chemistry and molecular optimisation5. Integration of AI with experimental and translational validation pipelines6. AI applications in AMR research and multidrug-resistant infections7. Hallucination, bias, explainability, and reproducibility in biological AI models8. Regulatory and ethical frameworks for AI-generated therapeutics9. AI-driven biomarker discovery and precision medicine10. High-risk, high-reward translational innovation models in biotechnology11. Public trust, governance, equity, and responsible innovation in AI-enabled healthcare12. Use of AI in clinical trial design, simulation, analysis, and managementParticular attention will be given to emerging translational innovation initiatives internationally that seek to accelerate disruptive biomedical breakthroughs while addressing issues of safety, governance, accessibility, equity, and public trust in AI/ML in understanding AMR mechanisms and new antibiotic design, discovery and development.This Research Topic will also attract submissions focused on the use of AI in clinical trial design, simulation, analysis, and management, thereby broadening its translational relevance beyond early-stage drug discovery. In particular, it will encourage publications on AI-enabled clinical trial simulation, synthetic control arms, digital twins, adaptive trial designs, patient stratification, recruitment prediction, endpoint optimisation, and real-time safety monitoring. For antibiotic development and AMR research, these approaches could help overcome major trial challenges such as small or heterogeneous patient populations, changing resistance patterns, complex microbiological endpoints, and urgent timelines for evaluating new therapies. By including this theme, the Research Topic will provide a platform for researchers, clinicians, industry partners, and regulators to discuss how AI can responsibly accelerate clinical evaluation while maintaining scientific rigour, ethical governance, patient safety, and public trust.As we enter this new era of AI-augmented biology, the key challenge is no longer whether AI will reshape drug discovery, but rather how this transformation can be guided responsibly, ethically, creatively, and inclusively. This Research Topic, therefore, promotes a position of informed and grounded optimism: AI is neither a replacement for scientific judgment nor a technology to be feared. Rather, it is a powerful enabling framework that offers immense opportunities alongside genuine risks. Through rigorous interdisciplinary collaboration, critical evaluation, and responsible innovation, AI-driven approachs have the potential to transform the future of global medicine, infectious disease research, and translational biotechnology. Topic editors: Taane Gregory Clark, Sundeep Chaitanya Vedithi, Marlon Henrique Cardoso, Sanjib Bhakta, Stephen Henry Gillespie Source: https://www.frontiersin.org/research-topics/83893/automation-and-acceleration-of-translational-drug-design-discovery-and-development-in-the-era-of-artificial-intelligence