Le Cong

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.

This study uses CRISPR activation screening to identify surface ligands that regulate tumor sensitivity to NK cell killing, revealing new targets for improving NK cell-based immunotherapies.

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

LabOS is an AI co-scientist that integrates computational reasoning with physical experimentation through multimodal perception and human-AI collaboration, enhancing scientific discovery in biomedical and materials science.

BioLab uses a multi-agent system with foundation models to autonomously design and validate antibodies, achieving superior performance compared to existing methods.

CRISPR-GPT automates CRISPR-based gene-editing design and analysis by integrating LLMs with domain expertise, demonstrating effectiveness in gene knockout and activation experiments.

STELLA is a self-evolving AI agent that improves through interaction, achieving high performance in biomedical tasks and driving experimental discoveries in oncology and protein engineering.

The paper introduces Genome-Bench, a benchmark created from scientific forum discussions, and presents a pipeline to convert these into reinforcement learning-friendly multiple-choice questions.

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.

This study develops transgenic Cas12a mice to enable efficient, multiplexed somatic genome editing for studying complex genetic interactions in vivo.

This study compares CRISPR-Cas9 and TALEN gene editing in a mouse model of Machado-Joseph disease, showing CRISPR-Cas9 reduces ATXN3 aggregates and delays disease progression.

RNAGenesis is a foundation model for RNA therapeutics that integrates sequence, structure, and function prediction, achieving state-of-the-art performance on multiple tasks and enabling functional RNA design.

This paper introduces FoldMark, a watermarking method for protein generative models that ensures biosecurity by enabling user tracing and maintaining structural quality.

This paper introduces a language model for 5' UTRs that improves predictions of translation efficiency and mRNA expression, and validates novel 5' UTR designs through wet-lab experiments.

This study uses protein language models and high-throughput screening to engineer an anti-CRISPR protein that enhances CRISPR/Cas genome editing precision in human cells.

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.

The paper uses CRISPRa screening and real-world data to identify KCNA6 as a neuronal entry factor for SARS-CoV-2 and shows dalfampridine can suppress viral entry.

The paper identifies IL-33 as a driver of tumor immunosuppression by analyzing longitudinal single-cell RNA-Seq data of regulatory T cells in a mouse model of lung adenocarcinoma.

This paper introduces composite measurements and molecular compressed sensing to efficiently recover gene expression profiles with fewer measurements than genes.