Autonomous and Automated Laboratories for Closed-Loop Drug Discovery

Autonomous and automated laboratory systems are rapidly transforming the landscape of drug discovery by combining robotics, advanced sensing, and intelligent software to drive efficiency and reproducibility. Traditional drug discovery workflows, often plagued by low throughput, high variability, and limited reproducibility, have constrained the pace of innovation despite promising scientific advances. The emergence of “self-driving labs” (i.e., integrated platforms that enable robotic execution, real-time data capture, and closed-loop optimization) has begun to overcome these obstacles. Pioneering studies have established proof-of-concept systems capable of executing complex experimental routines, leveraging AI-driven strategies to guide experimentation, and generating high-quality, standardized datasets. While these advances signal exciting progress, significant challenges remain in assembling robust, generalized workflows: integrating diverse hardware, developing adaptive experimental designs, and deploying scalable, user-friendly solutions in both academic and industrial contexts.This Research Topic aims to advance the state of the art in autonomous and automated laboratory systems dedicated to drug discovery. Our objective is to foster and showcase innovations in technologies, methods, and strategies that enable closed-loop experimentation spanning robotic sample handling, automated measurement, data-driven decision-making, and workflow orchestration. Emphasis is placed on rigorous experimental validation and demonstrable translational impact, with a particular interest in approaches that enhance assay reproducibility, optimize screening processes, accelerate the move from hits to leads, or improve overall data quality. Submissions addressing the integration of automation with active learning, adaptive control, and practical solutions for instrument interfacing, imaging, and error handling are especially encouraged, as is work tackling persistent barriers such as assay drift, calibration, and interoperability of diverse laboratory systems.- Automation strategies for assays, analytical chemistry, and screening workflows- Robotic manipulation and logistics for laboratory operations- Vision-guided control, calibration, error recovery, and reliability engineering in lab robotics- Closed-loop experiment design (including active learning, Bayesian optimization, and adaptive protocols)- Integration with lab-on-chip and microfluidic technologies- Workflow orchestration, metadata management, and cross-platform reproducibility in both academic and industry settings- Case studies demonstrating full closed-loop experimentation cycles Topic editors: Naresh Marturi, Gurvinder Singh, Vikas Kumar Source: https://www.frontiersin.org/research-topics/79036/autonomous-and-automated-laboratories-for-closed-loop-drug-discovery