large language model

From Closed-Set Annotation to In-Context Discovery: Biologically Grounded LLMs for Cellular Profiling

CellScribe is a generative framework that unifies cell identity and state by using a language model to generate cell type annotations and meta-program profiles, outperforming baselines and identifying new cell types through in-context learning.

IVA, a locally deployable Intelligent Variant Analyser based on a small language model for complete case-level and trio-based genomic interpretation.

IVA uses a small language model to perform local genomic variant interpretation, achieving high sensitivity but lower precision in identifying pathogenic variants.

Towards Robust Automated Mouse Scratching Behavior Detection for Itch Research

This paper develops Scratch-AID+, an automated mouse scratching detection framework, showing that fine-tuned video foundation models outperform classic models in generalizability and accuracy.

CLARA: Compound Library Active Learning with Reasoning Agents

CLARA uses a language model to make strategy decisions in compound library active learning, outperforming random sampling across multiple protein targets.

Inherent limitations of zero-shot mutation prediction in protein engineering

This study evaluates zero-shot mutation prediction models in protein engineering, finding they struggle to identify optimal mutations and predict new functions due to limitations in capturing evolutionary constraints.

Autonomous AI agents discover reverse transcriptases with tandem repeat arrays

The paper uses large language models to discover a novel family of reverse transcriptases with tandem repeat arrays from metagenomic data.

Dementia Language Models: a generalizable and controllable representation of cognitive impairment

This paper introduces Dementia Language Models (DeLMs) that generate patient-like narratives and predict cognitive impairment, validated by neurologists and MMSE scores.

Structured biological evidence enables general-purpose language models to predict bacteriophage-host interactions

The paper introduces a structured-evidence framework for predicting bacteriophage-host interactions using a large language model, achieving high accuracy and enabling interpretable inference.

Large language models unlock the ecology of species interactions

This paper uses large language models to extract species interaction data from citizen science comments, expanding ecological data coverage and enabling new ecological research.

FragDockRL: A Reinforcement Learning Method for Fragment-Based Ligand Design via Building Block Assembly and Tethered Docking

FragDockRL uses reinforcement learning to design ligands by assembling building blocks and tethered docking, outperforming random search on three protein targets.

LLM-powered automatic scoring tools for memory recall

This paper introduces an LLM-powered pipeline for automatically scoring free recall of naturalistic stimuli, achieving high agreement with human raters and low cost.

Enrich.AI: An Agentic AI Platform for Interactive GeneSet Enrichment Analysis and Biological Interpretation

Enrich.AI provides an AI-driven platform for gene set enrichment analysis and biological interpretation, offering interactive visualizations and literature-based insights.

EdiProPred: Prediction of Edible Plant Tissue-Associated Proteins Using Large Language Models

The paper develops EdiProPred, a model using large language models to classify plant proteins as edible or non-edible based on sequence data, achieving high accuracy.

Agentic campaign control for high-throughput de novo binder design

This paper introduces T-REX, an agentic framework for protein binder design that adaptively allocates compute resources across methods, achieving higher throughput of structurally distinct hits than baselines.

Integrating Developmental Neurotoxicity Prediction with Adverse Outcome Pathway Reasoning

This study integrates large language models with adverse outcome pathways to predict developmental neurotoxicity and generate mechanistic explanations, showing improved performance with few-shot prompting.

Dataset structure outweighs method choice in single-cell cell-type annotation

In a 63-tool benchmark, dataset identity explained ≈84% of Cohen's κ variance on synthetic data versus ≈4% for tool identity, and k-nearest-neighbor (kNN) purity predicted accuracy near-linearly (R² = 0.85–0.99).

DAPHNE: A global database of pest herbivores and their natural enemies

The paper constructs a global database of pest herbivores and their natural enemies by using a large language model to extract species interactions from scientific literature.

Evidence Scaling for Zero-Shot Protein Reasoning with Large Language Models

This paper shows that adding biological evidence to large language models improves zero-shot protein variant prediction without retraining the model.

An fMRI dataset of verbalized spontaneous thought with annotated transcripts and self-report trait measures

The paper provides an fMRI dataset of verbalized spontaneous thought with transcripts, timestamps, and self-report measures for studying neural dynamics and individual differences.

Fusion2AI: functional re-annotation of the bacterial transparent matter proteins

The paper uses large language models to generate human-readable function descriptions for bacterial protein clusters, expanding functional annotations for genome and microbiome analyses.

Drought-Spec-Net: Early Tomato Drought Detection and Potential Yield-Impact Assessment Using Vis NIR Data

This paper develops Drought-Spec-Net, a model for early tomato drought detection using Vis NIR data, achieving high accuracy and providing yield impact assessments.

Biological rationales from language models enable leakage-resistant forecasts of target-indication success

PRIORITI uses language models to predict target-indication success in drug discovery, achieving high accuracy and robustness across different benchmarks.

RNASeek: A Cross-Phyla Generative Foundation Model for Multipurpose RNA Modeling and Reinforcement Learning-Based Design

RNASeek is a generative foundation model for RNA sequence design and functional prediction, using reinforcement learning to optimize RNA properties like stability and cleavage activity.

FiberPro 1.0: Multiagent AI-Guided Design for High-Throughput Production and Conformal Deposition of Functional Protein Micro/Nanofibers

FiberPro 1.0 uses a multiagent AI framework to design and optimize functional protein micro/nanofiber production through high-throughput spinning and real-time feedback, achieving spinnable formulations in two iterations.

Large language model-based bibliometric evaluation of population descriptors in human genetics

This study evaluates adherence to NASEM recommendations on population descriptors in GWAS papers using a large language model-based toolkit, finding improvements over time but limited impact post-report publication.

OmicsResonance: An LLM-assisted cloud ecosystem for interactiveand reproducible single-cell transcriptomic analysis

OmicsResonance provides a code-free web platform for scRNA-seq analysis, integrating LLM-assisted tools and interactive features to enable reproducible and transparent single-cell research.

AnewDDE: An Agentic Drug Discovery Engine for Biomolecular Interaction Modelling and Closed-Loop Design

AnewDDE integrates AI tools for biomolecular interaction modelling and drug design, demonstrating improved performance in structure prediction, binder identification, affinity estimation, and ADMET prediction.

BOTANIC-1: a series of long-context plant genomic foundation models in the agentic era

Bidirectional Mamba2 plant genomic language models (318M to 3.2B parameters) trained on 320 land-plant genomes top a 22-task frozen-model aggregate; a small variant reaches 131,072 bp context.

Scrub Data: A Framework for Reproducible Data Curation with AI Coding Agents

Scrub Data routes AI-agent data edits through an API-enforced provenance graph of executable Python steps; it curated 89M wildlife GPS points into the 2.6M-point MoveBench benchmark.

Scaling Network Medicine with LLMs for Combinatorial Drug Repurposing in ER+ Breast Cancer

The paper develops an LLM-driven framework for drug repurposing in ER+ breast cancer, identifying 166 significant drug combinations using pathway analysis and consensus networks.