arXiv AI
DrugHarness: An Evolvable Agent Harness for Computational Drug Discovery
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jun 18
TxBench-PP: Analyzing AI Agent Performance on Small-Molecule Preclinical Pharmacology
arXiv:2606. 19245v1 Announce Type: new Abstract: Artificial intelligence (AI) agents promise to accelerate drug discovery by compressing interpretation and decision-making loops, but practical deployment requires trusted evaluation on realistic program decisions.
arXiv AI
Jun 2
Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
arXiv:2606. 00555v1 Announce Type: new Abstract: Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two often-conflicting objectives -- binding affinity and druggability -- which single optimization steps rarely improve together.
arXiv AI
Aug 10
CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows
arXiv:2608. 06961v1 Announce Type: new Abstract: Early-stage molecular design is an iterative process, not just a task of generating molecules.
arXiv Machine Learning
5d ago
PMO-Dock: Benchmarking Docking, Specificity, and Generalization in Molecular Optimization
PMO-Dock introduces a standardized benchmark for docking‑based molecular optimization, comprising 25 tasks that span hit generation, lead optimization, and a specificity task that rewards strong on‑target binding while penalizing off‑target interactions. The protocol separates model development from final evaluation, using validation tasks for hyperparameter tuning and held‑out test tasks evaluated under a strict oracle budget to mimic realistic drug‑discovery constraints. Four diverse methods—Saturn, GenMol, Genetic‑guided GFlowNet, and ChemLlama—were benchmarked, revealing no single method dominates across all tasks and highlighting limited hyperparameter transferability, which underscores the need for method‑dependent selection strategies.
arXiv AI
Jul 10
DrugGen 2: A disease-aware language model for enhancing drug discovery
arXiv:2607. 08404v1 Announce Type: cross Abstract: Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properties, often neglecting the influence of disease context on target behavior and therapeutic outcomes.
arXiv AI
Oct 12
From Benchmark to Bench: Can Agents Survive Real-World Drug Discovery?
The paper introduces MAGI, an open modular agent that orchestrates molecular‑design tools by setting objectives, launching optimization, interpreting structure–activity relationships, and adjusting strategy. In nine retrospective lead‑optimization campaigns from three pharmaceutical companies, MAGI produced valid molecules via either direct LLM generation or delegation to REINVENT 4; LLM proposals stayed closer to local chemistry and achieved comparable or higher activity with fewer operations, while REINVENT explored broader chemical space. The success of a campaign depended on the accuracy of predictive models rather than the generation route, and a blinded evaluation showed chemists could not distinguish MAGI’s outputs from expert‑generated compounds, though the SAR reasoning was deemed plausible yet incomplete. The study positions MAGI as a coordination layer that can be plugged into existing workflows, but notes that the current ceiling for real projects is set by scorer applicability rather than tool orchestration.