Kexin Huang

AutoScreen improves gene prioritization in functional genomics by integrating AI agents for pre-screen design and post-screen analysis, achieving higher hit recovery and precision than existing methods.

BiomniBench evaluates LLM agents' research processes in biomedical tasks using expert rubrics, revealing performance gaps in method selection and reasoning.

This paper introduces TxConformal, a framework that controls false discoveries in AI-driven therapeutic discovery by adjusting for distribution shifts and providing confidence measures for AI scores.

PRESAGE predicts perturbation expression responses using gene embeddings and outperforms existing methods in functional evaluations.

An LLM agent with a literature-mined environment of 150 tools, 105 packages and 59 databases plans in code, matching reported human accuracy on database and sequence question answering.

SpatialAgent integrates large language models with dynamic tool retrieval, multimodal interpretation, and claim verification to automate end-to-end spatial biology workflows from gene-panel design to tissue annotation and hypothesis generation.

KGWAS improves GWAS power in small cohorts by integrating a functional knowledge graph, discovering more associations for rare diseases.

The paper introduces Therapeutics Commons (TDC-2), a resource integrating cell-type-specific biomarkers with machine learning tasks for drug discovery.

This paper introduces an active learning method to efficiently design Perturb-seq experiments by leveraging multi-modal priors, improving perturbation space exploration with fewer experiments.

The paper reanalyzes millions of molecular profiles to identify aging interventions using AI agents, finding over 500 interventions that reduce biological age and revealing patterns in aging modulation.

This paper introduces PrimeKG, a knowledge graph integrating disease-related data to support precision medicine by connecting molecular, genetic, and clinical information.

GEARS predicts transcriptional responses to single and multi-gene perturbations using single-cell RNA-sequencing data and geometric deep learning, outperforming existing methods in identifying genetic interactions.

Graphein transforms bioinformatics data into machine learning-ready graph representations for geometric deep learning and network analysis.