Wei Wang

ProteinAligner improves protein function and property prediction by integrating sequence, structure, and literature text modalities in a multi-modal pretraining framework.

Raygun is a generative AI framework that miniaturizes, modifies, and expands proteins while preserving function and structural integrity, validated through cell-based experiments.

TUnA is a Transformer model that predicts protein-protein interactions from sequence data and provides uncertainty estimates for unseen sequences, improving reliability.

The R136S mutation on APOE3 enhances resistance to tau-related pathology and toxicity by downregulating the cGAS-STING-IFN signaling pathway.

This paper introduces a simple generative model, SAM, for antibody sequence modeling that outperforms complex models and provides fast, interpretable tools for antibody sequence analysis.

This paper conducts a multi-ancestry genome-wide meta-analysis of Parkinson's disease, identifying 78 independent loci and 23 genes associated with PD risk.

The paper shows ADAM10 regulates macroglial cell fate by promoting astrocyte generation and inhibiting oligodendrocyte production in developing brains.

This study investigates how locus coeruleus-norepinephrine system activity and astrocytic responses change during sleep states, revealing dynamic fluctuations in norepinephrine levels and their relationship to sleep processes.

The paper introduces tGPT, a generative model for integrating large-scale single-cell transcriptomes, showing its effectiveness in clustering, trajectory inference, and linking gene patterns to clinical outcomes.

This paper integrates monogenic, polygenic, and clinical risk factors to predict disease risk for carriers of rare variants, identifying elevated risk in 18.22% of UK Biobank participants for breast cancer, familial hypercholesterolemia, and colorectal cancer.

This study shows that TNAP activity in brain endothelial cells maintains barrier integrity via the ROCK pathway, and its inhibition leads to barrier dysfunction.

This study shows doxorubicin enhances rAAV-mediated gene expression in the cortex of mice, cats, and monkeys, with effects observed across multiple serotypes and without significant cytotoxicity.

This study identifies 49 genetic signals associated with varicose veins through a large GWAS and replication, highlighting potential therapeutic targets and biological pathways.

The paper investigates how CTCF knockdown affects genome-wide cell-to-cell variation using single-cell RNA-seq, finding increased expression noise and enrichment of transcription factor-related genes in CTCF-KD cells.

The paper identifies candidate genes regulated by Neurogenin in Ciona's bipolar tail neurons, suggesting conserved roles in neuronal migration and development.

DTI-CDF improves drug-target interaction prediction by integrating hybrid features into a cascade deep forest model, achieving higher performance than existing methods.

This study identifies Armitage as a protein linking piRNA amplification in nuage to phased piRNA production on mitochondria in Drosophila.

This study identifies a signaling network involving ER, PXY, PXL1, and PXL2 that coordinates radial patterning and expansion in plant vascular tissue through intertissue signaling.

The paper introduces contextual regression, a nonlinear model that combines interpretability and accuracy, demonstrating its effectiveness on simulated data and open chromatin prediction.

This study investigates how sulforaphane affects microRNA expression in colon cancer and non-cancer cells, identifying potential targets like CDC25A, HMGA2, and MYC.

The paper creates a gene set database for pathway analysis in mouse, enabling pathway analysis and meta-analysis of gene expression signatures.

This study evaluates seven single cell RNA-seq normalization methods using diluted RNA data, finding that methods incorporating spike-in ERCC RNA outperform those without.

This study evaluates the performance of three scRNA-seq methods through controlled experiments, finding they reliably detect genes above 5-10 molecules with linear measurement transfer functions.

The paper introduces a method to identify both cis- and trans-cooperation between DNA-binding proteins using ChIP-seq and Hi-C data, revealing new insights into 3D chromosomal interactions.

The paper identifies cancer-specific genotype variations that target 3D chromosomal hubs, altering local interactions and revealing principles of genome organization.

This study evaluates China's National Forest Protection Program and National-level Nature Reserves from 2000 to 2010, finding reduced deforestation rates within protected areas despite overall losses.

This study uses whole-genome sequencing of C. briggsae isolates to infer population history, selection effects, and speciation dynamics across different geographic groups.

This study investigates the early stages of diploidization in Capsella bursa-pastoris, finding that gene loss is not rapid but rather associated with reduced selection efficacy due to demographic and genomic factors.