Article

Emergence of Biological Structural Discovery in General-Purpose Language Models

2026-01-08

Abstract excerpt

<title>Abstract</title> <p>Large language models (LLMs) are evolving into engines for scientific discovery, yet the assumption that biological understanding requires domain-specific pre-training remains unchallenged. Here, we report that general-purpose LLMs possess an emergent capability for biological structural discovery. First, we demonstrate that a small-scale GPT-2, fine-tuned solely on English paraphrasing...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 18b42076-a7c5-5179-8322-f7a0cc0922cb
DOI: 10.21203/rs.3.rs-8507849/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Emergence of Biological Structural Discovery in General-Purpose Language ModelsDOI 10.21203/rs.3.rs-8507849/v1Read

Emergence of Biological Structural Discovery in General-Purpose Language ModelsSemantic proximity Read

Pretrained protein language models choose between sequence novelty and structural completenessSemantic proximity Read

Out-of-the-box bioinformatics capabilities of large language models (LLMs)Semantic proximity Read

Genomic Touchstone: Benchmarking Genomic Language Models in the Context of the Central DogmaSemantic proximity Read

From Message Passing to Prompting: Rethinking Graph Learning with Large Language ModelsSemantic proximity Read

Genolator: A Multimodal Large Language Model Fusing Natural Language, Genomic, and Structural Tokens for Protein Function InterpretationSemantic proximity Read

CARDBiomedBench: A Benchmark for Evaluating Large Language Model Performance in Biomedical ResearchSemantic proximity Read

Large language models are universal biomedical simulatorsSemantic proximity Read

InstructPLM: Aligning Protein Language Models to Follow Protein Structure InstructionsSemantic proximity Read

Can Large Language Models “Read” Biological Sequences? A Systematic Evaluation of In-Context Learning for Antibody CharacterizationSemantic proximity Read

Multi-Modal Large Language Model Enables Protein Function PredictionSemantic proximity Read

Mixture of Experts Enable Efficient and Effective Protein Understanding and DesignSemantic proximity Read