Accelerating drug discovery with Artificial: a whole-lab orchestration and scheduling system for self-driving labs

TL;DR

The paper confronts the challenge of coordinating AI-guided experimentation in self-driving labs for drug discovery, highlighting data silos and integration barriers. It introduces Artificial, a modular orchestration and scheduling platform that unifies lab operations, AI-driven decision-making, and data management, featuring a digital twin, Lab Gateway, and cloud/on-prem deployment capabilities. A key contribution is a proof-of-concept integrating NVIDIA BioNeMo NIMs into a self-driving virtual screening workflow, demonstrating iterative optimization and seamless data exchange. The work argues that this approach enhances reproducibility, shortens discovery timelines, and provides a scalable framework for both dry and wet lab environments in AI-enabled drug discovery.

Abstract

Self-driving labs are transforming drug discovery by enabling automated, AI-guided experimentation, but they face challenges in orchestrating complex workflows, integrating diverse instruments and AI models, and managing data efficiently. Artificial addresses these issues with a comprehensive orchestration and scheduling system that unifies lab operations, automates workflows, and integrates AI-driven decision-making. By incorporating AI/ML models like NVIDIA BioNeMo - which facilitates molecular interaction prediction and biomolecular analysis - Artificial enhances drug discovery and accelerates data-driven research. Through real-time coordination of instruments, robots, and personnel, the platform streamlines experiments, enhances reproducibility, and advances drug discovery.

Figures (5)

• Figure 1: The Artificial stack.
• Figure 2: The self-driving cycle.
• Figure 3: A proof of concept use case for self-driving virtual screening with NVIDIA BioNeMo models.
• Figure 4: The self-driving iterations during the virtual screening proof of concept.
• Figure 5: Artificial architecture for NVIDIA BioNeMo model integration.