large language model

AOPTK: Open-Source Software for AI-Assisted Toxicological Literature Analysis

AOPTK automates toxicological literature analysis using AI, achieving high accuracy in identifying chemical-biological effect relationships.

Roost: Avian Influenza Host Genomics Resource

Roost compiles avian influenza host genomics data and links species, genes, and mechanisms to evidence, highlighting gaps in research coverage.

ProtoPure: Literature Mining and Analysis of Protein Purification Protocols at Proteome Scale

ProtoPure automates the extraction and analysis of protein purification protocols from literature, revealing trends in recombinant expression practices and diverse downstream purification strategies.

Lineage-mixed neurodevelopmental programs in pediatric sarcomas nominate tumor-selective surface antigen pairs.

This paper develops an AI framework to interpret single-cell RNA-seq data from pediatric solid tumors, identifying tumor-specific surface antigen pairs for targeted therapies.

An evidence-governed agent harness for spatial transcriptomics prioritizes ICAM-1 as a target in lung fibrosis

DeepMAST, an AI system for spatial transcriptomics, identifies ICAM-1 as a therapeutic target in lung fibrosis through evidence-based analysis and validation.

In-silico Tandem Mass Spectral Libraries for the Blood Exposome and Metabolomics Workbench Databases: Application of Gemini Large Language Model

The paper generates in-silico mass spectral libraries for human metabolomics using the Gemini large language model, achieving 55% accuracy compared to NIST 23.

Tracking claim changes from preprint to publication across 72,644 biomedical studies using large language models

In 72,644 matched bioRxiv preprint-publication pairs, LLM-extracted primary abstract claims were unchanged or minorly revised in about 90%; hedging shifted toward caution in 8.4% versus confidence in 4.2%.

GEO-BERT: A Retrieval augmented LLM Framework for Intelligent Dataset Retrieval from the Gene Expression Omnibus

GEO-BERT improves dataset retrieval from GEO by using a retrieval-augmented LLM framework with a hierarchical hybrid field-aware system, enhancing semantic search and traditional search performance.

The accessible human surfaceome

The paper curates an accessible human surfaceome using an LLM pipeline, outperforming existing databases and identifying new candidate surface proteins.

CucurbitAgent: An AI agent for exploring cucurbit multi-omics resources

CucurbitAgent is an AI agent that integrates multi-omics data and literature for cucurbit crops, achieving high accuracy in answering gene-specific queries.

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.

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.

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.

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.

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.

BoneGraph: A Domain-Specialised, Self-Correcting Reasoning System for Bone Science Retrieval, Grounded Inference, and Image Mechanics

BoneGraph combines a SPECTER2-indexed bone corpus, knowledge graph, deterministic physics checks, and user-taught rules in a local five-tab system; oracle passages raise accuracy 42% to 78%.

EVd3x: A Bioinformatics Platform for Evidence-aware Interpretation of EV Cargo

EVd3x integrates over 22 million records from 28 public resources so one fixed molecule set can be traced from reported EV cargo through disease, pathway, cell and interaction evidence.

AI-Supported Extraction of Functional Tissue Unit Properties for Human Reference Atlas Construction

The paper introduces an AI framework to automate the extraction of functional tissue unit properties from publications, supporting the construction of the Human Reference Atlas.

AI semantics for biomedical data integration

This paper describes an AI semantics workflow using LLM agents to integrate multimodal biomedical data through ontologies and knowledge graphs.

TigerAI: An AI-powered genetic evidence platform to support clinical development

Domain-grounded prompting lets GPT-5 produce genetic evidence for 13,022 drug target-indication pairs that predicts clinical success as well as expert curation, with wider coverage.

AFIDs-Validator: An Open-Access AI-Guided Platform for Learning Anatomical Landmark Placement

Open browser platform embeds a language-model neuroanatomy tutor in an MRI viewer and scores landmark placements against 21 expert-annotated templates using trained-rater error distributions.

Plant Bioengineering Atlas: A Knowledge Graph of Genes, DNA Constructs, and Plant Traits.

The paper presents the Plant Bioengineering Atlas, a knowledge graph of genes, DNA constructs, and plant traits, revealing gaps in standardization and reproducibility.

ResLit: A Large-Scale Automated Literature Mining Database for Antimicrobial Resistance

ResLit couples BioMistral-7B screening with two-pass Qwen3-30B extraction to build an antimicrobial-resistance database of 3,120 genes and 13,593 mutations, evidence-tiered against CARD, ResFinder, and NCBI RGC.

PubMind: Literature-Based Genetic Variant Extraction and Functional Annotation Using Large Language Models

PubMind extracts and annotates genetic variant functionality from biomedical literature using LLMs, creating a database with over 1.3 million variants.

Automating scientific annotations for open transcriptomic profiles via multi-stage agents

GEOMeta automates metadata curation for GEO transcriptomic data, generating standardized annotations for 600,000 human bulk RNA-seq samples and benchmarking LLMs for annotation quality.

Detailed curation of biological samples and experimental designs for genomics using LLM-supported agentic workflows

The paper describes a software tool using LLMs to automate data curation for genomics, achieving performance near human curators with lower cost and higher speed.

LLM-powered Functional Gene Set Summarization with genesetGPT

genesetGPT is an LLM-based framework that improves gene set annotation by using curated biological context and iterative prompt design to summarize heterogeneous gene sets.

BioPathfinder: Evidence-guided multi-agent platform enables hypothesis discovery for CAR-T engineering

A provenance-tracked multi-agent system curated 57 CAR-T patient scRNA-seq studies, generated reviewable hypotheses, and prioritized KLRC1/NKG2A, whose blockade improved CD8+ CAR-T antitumour activity in a Raji xenograft model.