7The Batch (DeepLearning.AI)·
FutureHouse's Robin agent autonomously proposes drug repurposing candidates, validated in human cell experiments
FutureHouse, University of Oxford, and Fordham University released Robin, an open-source AI agent that autonomously identifies existing drugs that could treat a given disease by iteratively hypothesizing mechanisms, designing experiments, and ranking drug candidates using literature-search sub-agents. In a demonstration targeting dry age-related macular degeneration, Robin identified two drugs (Y-27632 and Ripasudil) that produced roughly 1.75–2x increases in RPE phagocytosis in human cell experiments. The pipeline uses GPT o4-mini for most language tasks and Claude 3.7 Sonnet for pairwise ranking, with human involvement limited to naming the disease and running lab experiments. The work represents a concrete, experimentally validated instance of agentic AI accelerating drug repurposing research.
Related guides (3)
Related events (8)
Uncovering repurposed medicines to fight liver fibrosis using Co-Scientist
A Stanford geneticist used Google DeepMind's Co-Scientist AI system to identify potential drug repurposing candidates for chronic liver disease and liver fibrosis. The work represents a real-world application of AI-assisted scientific discovery in a clinical domain. Co-Scientist is DeepMind's AI research assistant designed to accelerate hypothesis generation and experimental planning for scientists.
TxBench-PP: New benchmark reveals AI agents struggle with preclinical pharmacology decisions
Researchers introduce TxBench-PP (TherapeuticsBench Preclinical Pharmacology), a 100-evaluation benchmark testing AI agents on realistic small-molecule drug discovery tasks including mechanism-of-action reasoning, compound-target engagement, and translational efficacy. Agents receive real workflow snapshots and are graded deterministically on structured answers. Across 16 model-harness configurations and 4,800 trajectories, no system reliably succeeded; the best performer, Claude Opus 4.8 with the Pi harness, passed only 59.3% of endpoint attempts. The results suggest current frontier models are not yet deployment-ready for autonomous preclinical pharmacology decision-making.
OpenAI and Molecule.one demonstrate near-autonomous AI chemist using GPT-5.4 for medicinal chemistry
OpenAI and Molecule.one have demonstrated a near-autonomous AI chemist system built on GPT-5.4 that improved a challenging reaction in medicinal chemistry. The system represents a deployment of frontier AI in scientific research workflows, specifically drug synthesis optimization. This is notable as a concrete capability demonstration of agentic AI applied to chemistry R&D.
Fast-tracking genetic leads to reverse cellular aging with Co-Scientist
DeepMind's Co-Scientist AI system was used by biologists to identify novel genetic factors capable of rejuvenating human cells, advancing cellular aging reversal research. The work demonstrates Co-Scientist's utility as a scientific discovery tool in a high-stakes biological domain. This represents a concrete application of AI-assisted hypothesis generation and experimental prioritization in longevity biology.
Microsoft RD-Agent: automated AI-driven R&D for data and model development
Microsoft has released RD-Agent, an open-source Python framework aimed at automating high-value R&D processes in AI, with a focus on data and model development. The project positions AI as the driver of data-driven AI workflows, targeting industrial productivity use cases. With 13,500 GitHub stars, it has attracted meaningful community interest, and a technical report is available.
Anthropic launches AI for Science rare disease research grants with up to $50K in Claude credits
Anthropic is opening applications for a focused grant program within its AI for Science initiative, targeting rare genetic disease research with up to $50,000 in Claude API credits per recipient over six months. The program has two tracks: one for basic science researchers and one for early-stage biotechs accelerating drug development. Anthropic is partnering with the Monarch Initiative, an international rare disease consortium, and highlights use cases including mechanistic disease classification, regulatory documentation drafting, and therapeutic target analysis. The initiative reflects Anthropic's strategy of directing frontier model access toward high-impact scientific domains.
Accelerating discovery of liver disease mechanisms with Co-Scientist
DeepMind's Co-Scientist AI system is being used by researcher Filippo Menolascina to identify new treatment mechanisms for liver disease and explain differential drug response across patients. The application demonstrates Co-Scientist's utility in biomedical hypothesis generation and drug discovery workflows. This represents a concrete scientific use case for AI-assisted research in a clinical domain.
Anthropic Partners with Allen Institute and HHMI to Deploy Claude in Frontier Life Sciences Research
Anthropic has announced flagship partnerships with the Allen Institute and Howard Hughes Medical Institute (HHMI) to embed Claude into active scientific workflows at both institutions. HHMI's collaboration, anchored at Janelia Research Campus, focuses on developing specialized AI agents integrated with scientific instruments and analysis pipelines. The Allen Institute partnership targets multi-agent systems for multi-modal biological data analysis, including multi-omic integration, knowledge graph management, and experimental design coordination. Both partnerships emphasize interpretability, researcher autonomy, and transparency, with the stated goal of compressing months of manual analysis while keeping human scientists in control of scientific direction.