large language model

Agent SPI-WSI: In context learning for computationally spatial pathwayinferring on whole slide histopathology images conditioned on bulk RNAsequencing using pathologist in the loop.

The paper introduces an AI agent that localizes bulk RNA-seq pathway activity in histopathology images using pathologist feedback and large language models.

DeviceAgent: An autonomous multimodal AI agent for flexible bioelectronics

DeviceAgent is an AI agent that integrates LLMs and VLMs to automate bioelectronics research tasks, demonstrating capabilities in design, fabrication, defect inspection, and electrophysiological analysis.

Base-editing a single missense mutation in A20 enhances CAR-T cell efficacy

This study uses base-editing to inactivate a missense mutation in A20ZF7, enhancing CAR-T cell efficacy by reducing exhaustion and improving anti-tumor responses.

Automating Candidate Gene Prioritization with Large Language Models: From Naive Scoring to Literature-Grounded Validation

This paper develops a framework using large language models for gene prioritization, validated against literature, identifying 30 high-confidence therapeutic candidates for sepsis.

Qimai: a multi-agent framework for zero-shot DNA-protein interaction prediction

Qimai improves DNA-protein interaction prediction for unseen proteins by integrating deep learning with LLM-based reasoning, achieving higher AUC-PR, AUC-ROC, and MCC than standalone models.

Execution-aware agent harness for accessible and responsible synthetic biology automation

LabscriptAI translates natural language into robot scripts for synthetic biology, achieving high simulation accuracy and enabling secure, standardized, and traceable lab automation.

Mechanistically explainable AI model for predicting synergistic cancer therapy combinations

This paper introduces an LLM-based framework that predicts synergistic cancer drug combinations using drug data and a knowledge graph, achieving an F1 score of 0.80.

Descriptron: Testing Artificial Intelligence for Automating Taxonomic Species Descriptions with a User-friendly Software Package

Descriptron uses a Vision Language Model to automate taxonomic species descriptions with error correction, but requires taxonomist supervision to prevent hallucinations.

GETgene-AI: A Framework for Prioritizing Actionable Cancer Drug Targets

GETgene-AI prioritizes actionable cancer drug targets by integrating network-based methods, machine learning, and literature analysis, achieving higher precision and efficiency than existing tools.

Designing proteins with reduced T-cell epitopes through policy optimization

The paper designs proteins with reduced T-cell epitopes using deep generative models and policy optimization to improve immune compatibility across MHC Class I alleles.

Edit Distance Embedding with Genomic Large Language Model

This paper introduces LLMED, a genomic large language model-based embedding method that improves edit distance approximation and similar sequence search accuracy.

Operate a Cell-Free Biofoundry using Large Language Models

This paper uses large language models and active learning to optimize cell-free protein synthesis, achieving significant yield improvements for antimicrobial proteins.

Artificial intelligence for precision oncology: AI-HOPE-MAPK uncovers clinically actionable MAPK alterations in colorectal cancer

AI-HOPE-MAPK identifies age- and ancestry-specific MAPK pathway alterations in colorectal cancer, revealing clinically relevant mutation patterns and survival differences.

Predicting Risk of Transfusion-Induced Red Blood Cell Alloimmunization Using Statistical and Machine Learning Approaches in the Recipient Epidemiology and Donor Evaluation Study (REDS-III) Database

This study builds prediction models for RBC alloimmunization using statistical and machine learning methods on the REDS-III database, finding XGBoost provides the best performance with an AUC-ROC of 0.752.

GPT-4 accurately predicts human emotions and their neural correlates

This study shows GPT-4 can predict human emotion ratings and model associated neural responses with high accuracy.

ProTDyn: a foundation Protein language model for Thermodynamics and Dynamics generation

ProTDyn generates thermodynamically consistent protein ensembles and multi-timescale dynamics, offering a scalable alternative to molecular dynamics simulations.

Medical Abbreviation Disambiguation with Large Language Models: Zero- and Few-Shot Evaluation on the MeDAL Dataset

This study evaluates zero- and few-shot performance of large language models on medical abbreviation disambiguation using the MeDAL dataset, showing GPT-4 outperforms LLaMA.

Automating RNA-Ligand Interaction Modeling via a Self-Improving LLM Agent

This paper introduces RLAgent, an LLM-based framework for RNA-ligand interaction modeling that enables interactive, code-free prediction at the RNA region level.

EAGLE-AI: A large language model workflow for automated extraction and scoring of literature evidence linking genes to autism spectrum disorder

EAGLE-AI automates gene-autism linkage evidence extraction and scoring with high accuracy, though challenges remain in handling unscreened papers and supplementary materials.

CIViC-Fact: a proof-of-concept framework for AI-assisted verification of cancer variant interpretations

CIViC-Fact evaluates AI models for verifying cancer variant interpretations using full-text evidence, showing abstracts are insufficient for accurate validation.

DeepPGDB: A Novel Paradigm for AI-Guided Interactive Plant Genomic Database

DeepPGDB provides an AI-driven plant genomics database with natural language interfaces for multi-omics data access and analysis, enhancing usability and accelerating research in agriculture and biotechnology.

Fast and accurate taxonomic domain assignment of short metagenomic reads using BBERT

BBERT is a nucleotide large language model that accurately assigns taxonomic domains to short metagenomic reads without reference databases, improving assembly and downstream analysis.

Leveraging Open-Source Large Language Models to Identify Undiagnosed Patients with Rare Genetic Aortopathies

This paper develops an open-source LLM-based pipeline to identify patients with rare genetic aortopathies using clinical notes, achieving high accuracy in recommending genetic testing.

Automated Labeling of Scientific Names and Etymological Trend Analysis in Phytophagous Arthropods Using Large Language Model

This study uses a large language model to classify scientific names of phytophagous arthropods and analyzes etymological trends over time, finding shifts in naming patterns.

Large-language-model-based antibiotic resistance gene prediction and resistomes mining in cyanobacterial blooms

ESMARG, a large-language-model-based tool, improves antibiotic resistance gene detection in metagenomes and reveals seasonal dynamics and ecological factors in cyanobacterial blooms.

Query Augmented Generation (QAG) from the Genomic DataCommons for Accurate Variant Statistics

The paper introduces QAG, a method to improve LLM accuracy for somatic variant frequencies by integrating with the Genomic Data Commons.

Creating a biomedical knowledge base by addressing GPT inaccurate responses and benchmarking context

GNQA, a retrieval-augmented GPT question-answering system over 3000 GeneNetwork, aging and diabetes papers, cites source paragraphs; RAGAS rated answer relevance above human thumbs-up ratings (89% vs 76%).

Instruction-tuned extraction of virus-host interactions from integrated scientific evidence

This study develops an instruction-tuned LLM for extracting virus-host interactions from full-text biomedical articles, showing improved performance under low-resource conditions.

In Silico Tool for Predicting and Scanning Rheumatoid Arthritis-Inducing Peptides in an Antigen

This paper develops models to predict RA-inducing peptides using machine learning, deep learning, and large language models, achieving high AUC scores and implementing them in a web tool.

ChatMDV: Democratising Bioinformatics Analysis Using Large Language Models

ChatMDV provides a natural language interface for generating interactive visualizations of biological data using large language models and the MDV platform.