Intology launches automated research system Locus, surpassing GPT-6 Astra and Claude… in molecular prediction
Intology releases the automated research system Locus, which can autonomously propose experiments, run multiple batches of experiments in parallel on GPUs, and retain effective results for iteration; it has been used in drug and antibody design. In molecular property prediction, fine-tuning Boltz-2 to predict small-molecule potency, and antibody design pipelines based on BoltzGen, Boltz-2, ESMC, and ESMFold2, Locus outperforms SOTA baselines and LLM agents, and generalizes better, has higher sample efficiency, and explores a more diverse solution space when data is limited. Rohan Paul says Locus beat GPT-6 Astra and Claude Opus 5.5 agents on molecular prediction.
Why read this
AI score 67
Intology's Locus links experiment proposal, parallel training, and screening into an automated research loop, and outperforms expert solutions and LLM agents on molecular prediction tasks.
Topics
View original postLocus sets the frontier for automating molecular design Our automated research system Locus develops scientific AI models that outperform SOTA expert solutions Unlocking the potential of scientific AI requires leveraging proprietary data. Locus achieves this autonomously 🧵👇 -- We test Locus across a number of tasks related to molecular scoring and design: training molecular property prediction models for a proprietary task, fine-tuning Boltz-2 to predict small-molecule potency, and building antibody design workflows around BoltzGen, Boltz-2, ESMC, and ESMFold2. Each of these settings are real-world AI for science use cases, where tasks are often out-of-distribution for existing foundation models and limited in data, while featuring expensive and noisy evaluators. Compared to state-of-the-art baselines and LLM agents set to optimize these tasks, Locus achieves higher performance. Additionally, Locus generalizes better despite limited data, finds more sample efficient solutions, and explores a higher diversity of solutions.
View original
Locus sets the frontier for automating molecular design Our automated research system Locus develops scientific AI models that outperform SOTA expert solutions Unlocking the potential of scientific AI requires leveraging proprietary data. Locus achieves this autonomously 🧵👇 -- We test Locus across a number of tasks related to molecular scoring and design: training molecular property prediction models for a proprietary task, fine-tuning Boltz-2 to predict small-molecule potency, and building antibody design workflows around BoltzGen, Boltz-2, ESMC, and ESMFold2. Each of these settings are real-world AI for science use cases, where tasks are often out-of-distribution for existing foundation models and limited in data, while featuring expensive and noisy evaluators. Compared to state-of-the-art baselines and LLM agents set to optimize these tasks, Locus achieves higher performance. Additionally, Locus generalizes better despite limited data, finds more sample efficient solutions, and explores a higher diversity of solutions.
Body
An AI system just designed better molecular models than the specialist tools built by the labs that own those models.
@intology’s Locus does a machine-learning researcher’s job: > proposes experiments, > runs many batches of them in parallel on GPUs > keeps what works and repeats, > now applied to drug and antibody design.
Locus beat GPT-6 Astra and Claude Opus 5.5 agents on molecular prediction