arXiv:2605.06728v2 Announce Type: replace-cross
Abstract: Large language models can reason over biological knowledge, but they are not naturally equipped to work with quantitative omics measurements....
By Maciej Sypetkowski, {\L}ukasz Smoli{\'n}ski, Remigiusz Kinas, Joanna Krawczyk, Bart{\l}omiej Hofman, Aleksandra Mo{\.z}wi{\l}{\l}o, Micha{\l} Pikusa, Tomasz Jetka, Rafa{\l} Powalski
arXiv:2606. 08147v1 Announce Type: cross Abstract: DNA cis-regulatory elements (CREs) such as enhancers control gene expression levels.
By Yi Duan, Zhao Yang, Jiwei Zhu, Ying Ba, Chuan Cao, Bing Su
The study evaluates whether biological reasoning models actually use their biological inputs by testing six models on DNA, protein, and single‑cell tasks. By perturbing one biological input while keeping others fixed, the authors find that many models (e.g., Evo2, ESM3, BioReason, BioReason‑Pro) rely primarily on textual information, with minimal impact from the biological representations. In contrast, models like ChatNT, Prot2Text‑V2, CellWhisperer, and Cell2Sentence‑Scale show greater dependence on their biological inputs, yet overall accuracy gains do not consistently reflect increased biological input contribution.
By Ada Fang, Nikitha Thoduguli, Lukas Fesser, Hanlin Zhang, Sham M. Kakade, Marinka Zitnik
Thalamus‑Reasoning is a 9B multimodal large language model that embeds bulk or single‑cell transcriptomes as continuous vectors, allowing them to be interleaved with natural‑language instructions and other samples. The model is trained on a large corpus that links experimental measurements to biological knowledge and task supervision, covering 157 task groups and 5.21 million conversations. It outperforms competing models on several held‑out annotation tasks, the GEO‑OmicsQA benchmark, and PerturbQA perturbation‑response prediction, demonstrating the benefit of continuous omics representations over text‑only gene lists.
By Maciej Sypetkowski, {\L}ukasz Smoli\'nski, Remigiusz Kinas, Joanna Krawczyk, Bart{\l}omiej Hofman, Aleksandra Mo\.zwi{\l}{\l}o, Micha{\l} Pikusa, Tomasz Jetka, Rafa{\l} Powalski
The paper introduces EDB-Bio, a benchmark of 96,000 episodes drawn from real biological studies—drug‑perturbation transcriptomics, CRISPR screens, and GWAS—to test whether language models can weigh empirical evidence and predict hypothesis truth. Initial results show that both open‑weight and frontier models are systematically underconfident, matching a trivial base‑rate forecaster in Brier score, but post‑training with proper scoring rules improves calibration and discrimination. In a downstream experiment‑selection task, a calibrated model (Ibis0) outperforms the best frontier model by 2.5×, and Bayes‑factor analysis reveals how models update beliefs, align with expert relevance judgments, and expose biases.
By Conor Igoe, Gabriel Grand, Zane Koch, Albert Bou, Eli Moss, Michaela M. Hinks, Samuel G. Rodriques, Andrew White, Siddharth Narayanan
Scientific reasoning models for biology combine language models with foundation models trained on multimodal biological data, including DNA, RNA, and proteins. These models are built through post-training, yet how each stage shapes reasoning and generalization remains poorly understood.