large language model

Embracing naturalistic paradigms: substituting GPT predictions for human judgments

This study evaluates GPT's ability to predict human affective judgments in narratives and finds it correlates with human ratings and neural activity inferences.

Interpreting Omics Data Analysis with Large Language Models for Disease Target and Drug Discovery

This paper introduces a framework combining large language models with omics data analysis to prioritize disease targets and drug strategies, validated in Alzheimer's and pancreatic cancer.

MARRVEL-MCP enables natural language variant interpretation through autonomous workflow construction

MARRVEL-MCP enables natural language variant interpretation by allowing LLMs to autonomously construct workflows using curated genomic tools, improving performance over models without tool access.

MetaBeeAI: an AI pipeline for structured evidence extraction from biological literature

MetaBeeAI extracts structured evidence from biological literature using a modular LLM pipeline with expert validation, improving consistency and reproducibility across studies.

ChatDIA: A zero-shot large language model workflow for targeted analysis of data-independent acquisition mass spectrometry data

ChatDIA uses a zero-shot large language model to automate targeted DIA proteomics analysis with high accuracy and transparent rationales.

BioGAIP: A Scalable, User-Friendly and Robust LLM-Powered Multi-Agent System for Automated Bioinformatics Tasks

BioGAIP automates complex bioinformatics tasks using an LLM-powered multi-agent system, making advanced analysis accessible to non-experts through natural language input and graphical interfaces.

LeafyVGG-16: Transfer Learning for Plant Disease Detection with Cyber Risk Analysis

This paper introduces LeafyVGG-16, a transfer learning model for plant disease detection, achieving high accuracy and evaluating its vulnerability to adversarial cyber attacks.

EpiReasoner: An Integrated Artificial Intelligence Framework for Phenotype-to-Genotype Reasoning in Plant Epidermal Development

EpiReasoner integrates AI for phenotype-to-genotype reasoning in plant epidermal development, identifying a major QTL for stomatal density in tomatoes.

Evaluating open LLMs for agentic analysis orchestration in a typical biomedical lab

The paper evaluates open LLMs for agentic analysis in biomedical labs, finding that qwen3.6:27b matches frontier accuracy on variant calling tasks using a local setup.

StructAgent: Orchestrating Cryo-EM Model Building and Refinement with a Multi-Agent LLM System

StructAgent automates cryo-EM model building and refinement with a multi-agent system, enabling auditable workflows while preserving expert control.

Bio-BLIP: A Multimodal Architecture for Transferable Reasoning in Genomic Variant Interpretation

Bio-BLIP is a multimodal architecture that integrates DNA, genes, proteins, and text to improve variant interpretation without task-specific fine-tuning, achieving better performance in variant prioritization and target gene prediction.

MethylCurate: Tool For Dataset Curation and Epigenetic Aging Clock Evaluation

MethylCurate automates DNA methylation dataset retrieval and metadata harmonization from Gene Expression Omnibus, enabling scalable evaluation of epigenetic aging clocks.

ConvergeCELL: An end-to-end platform from patient transcriptomics to therapeutic hypotheses

ConvergeCELL translates patient transcriptomics into therapeutic hypotheses by integrating patient representation, interpretability, and large language models, outperforming baselines in gene recovery and classification.

Zero-shot biological reasoning with open-weights large language models reproduces CRISPR screen based prediction of synthetic lethal interactions.

This paper uses open-weight large language models to predict synthetic lethal interactions, outperforming random chance and non-LLM methods in reproducing CRISPR screen results.

STAT: A multi-agent framework for integrated and interactive spatial transcriptomics analysis

STAT is a multi-agent framework that improves spatial transcriptomics analysis by enabling interactive, transparent, and efficient multi-task analysis across different data resolutions.

From Metabolomics to Function: Ranking Plant Stem Cell Metabolomes for Use in Health and Cosmetics

The paper ranks plant callus metabolomes for health and cosmetic applications by identifying functionally relevant metabolites using a new pipeline.

Transforming the cytokine literature into a resource for experimental analysis and discovery

The paper introduces CytED, a database that transforms cytokine literature into a resource for experimental analysis, identifying unexpected biological effects and guiding perturbation experiments.

An LLM-driven pipeline for proteomics-based detection and structural modeling of post-translational modifications

The paper introduces an LLM-driven pipeline for detecting and structurally modeling post-translational modifications using proteomics data.

Evaluating Reference-Independent Pipelines for the Detection of Spreading Organisms in Metagenomic Datasets

This study evaluates four reference-independent pipelines for detecting spreading organisms in metagenomic datasets, finding the coverage-based method most reliable for sensitive pathogen discovery.

A Pilot Evaluation of Open-Weight Large Language Models for Screening RNA-seq Metadata in Public Databases

The paper evaluates open-weight large language models for screening RNA-seq metadata in public databases, finding they significantly improve classification performance over keyword searches.

Guidance for high-quality functional gene embeddings from large language models

This study evaluates gene embeddings from large language models and finds that functional descriptions yield high-quality, biologically meaningful representations.

Behavior-Driven Marine Larval Dispersal and Settlement with AI Agent-Based Modeling

This paper introduces SWARM, an AI agent-based model that improves marine larval dispersal simulations by incorporating LLM-based behavioral agents, enhancing predictive accuracy for connectivity and restoration strategies.

Aiki-GeNano: Multi-Stage Preference Optimization for Generative Design of Developable Nanobodies

Aiki-GeNano improves nanobody design by integrating developability signals into training, enhancing thermal stability and reducing liabilities while preserving humanness.

AutoLead: An LLM-Guided Bayesian Optimization Framework for Multi-Objective Lead Optimization

AutoLead uses LLMs and Bayesian optimization to optimize drug-like molecules for multiple objectives, achieving state-of-the-art results on a new benchmark dataset.

All Models are Wrong, Some are Annotated: Automating Metadata in Biomedical Repositories

This paper evaluates using large language models to infer ion channel and receptor subtype metadata from neuroscience model code, finding LLMs outperform feature-engineered models.

Decoding the phenomenology of spontaneous thought using large language-model ratings on verbal retrospective free reports

This study uses large language models to annotate spontaneous thoughts from verbal reports and decodes their emotional valence from EEG data.

Metappuccino: Large Language Model-driven Reconstruction of Sequence Read Archive Metadata for Cancer Research

Metappuccino uses a fine-tuned large language model to enrich metadata from RNA-seq datasets, improving accuracy and consistency for cancer research.

scConcept enables concept-level exploration of single-cell transcriptomic data

scConcept improves single-cell transcriptomic analysis by creating interpretable biological concepts from gene-level data, enhancing clustering and interpretability across multiple datasets.

H2O: A Foundation Model Bridging Histopathology to Spatial Multi-Omics Profiling

H2O predicts spatial transcriptomics and proteomics from H&E images using a contrastive learning framework, outperforming existing models and recovering biologically relevant cell-cell communication.

MSAgent: An Evidence Grounded Agentic Framework for LLM-driven Scientific Exploration in Mass Spectrometry-based Metabolomics

MSAgent improves molecular identification from mass spectrometry data by integrating LLMs with domain tools, achieving higher accuracy and reliability than existing methods.