Mengdi Wang

The enhanced multi-tissue atlas of regulatory effects in cattle

The paper presents CattleGTEx, a resource characterizing regulatory effects in cattle, resolving GWAS signals and providing insights into adaptive evolution and selection.

Enteric sensory neurons for nutrient detection and gut motility

This study creates a single-cell atlas of the murine enteric nervous system, identifies molecularly defined IPANs, and shows their role in nutrient detection and gut motility regulation.

Structure and function of the nairovirus cap-snatching endonuclease

This study characterizes the structure and function of nairovirus cap-snatching endonucleases, revealing a unique two-metal-ion mechanism and identifying potent inhibitors.

LabOS: The AI-XR Co-Scientist That Sees and Works With Humans

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: End-to-End Autonomous Life Sciences Research with Multi-Agents System Integrating Biological Foundation Models

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

CRISPR-GPT for Agentic Automation of Gene Editing Experiments

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

Genome-Bench: A Scientific Reasoning Benchmark from Real-World Expert Discussions

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.

RNAGenesis: A Generalist Foundation Model for Functional RNA Therapeutics

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.

FoldMark: Safeguarding Protein Structure Generative Models with Distributional and Evolutionary Watermarking

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

Redefining the Game: MVAE-DFDPnet's Low-Dimensional Embeddings for Superior Drug-Protein Interaction Predictions

This paper introduces MVAE-DFDPnet, a deep learning model that generates low-dimensional embeddings for drug-protein interactions, achieving better performance than existing methods.

A 5' UTR Language Model for Decoding Untranslated Regions of mRNA and Function Predictions

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.

Integration of ATAC-seq and RNA-seq identifies novel candidate genes associated with drought tolerance in Zoysia japonica Steud.

This study integrates ATAC-seq and RNA-seq to identify 63 drought-related genes and 6 regulatory motifs in Zoysia japonica, showing a positive correlation between chromatin accessibility and gene expression.

CRISPRa screening with real world evidence identifies potassium channels as neuronal entry factors and druggable targets for SARS-CoV-2

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.