Zichen Wang

OriGene identifies therapeutic targets by integrating diverse data modalities and outperforms human experts and models in accuracy and robustness.

This paper introduces LC-PLM, a protein language model based on BiMamba-S architecture, showing improved performance on protein tasks compared to Transformer-based models.

GeneCompass is a cross-species foundation model pre-trained on single-cell transcriptomes from human and mouse, integrating biological knowledge to improve gene regulatory mechanism understanding and downstream tasks.

This paper develops an iPSC platform to rapidly generate alpha-synuclein inclusions and investigates their formation, subtypes, and molecular interactions.

EGGNet is a geometric deep learning framework for predicting molecule-protein interactions, achieving competitive performance on binding affinity and interface prediction tasks.

This study introduces LM-GVP, a deep learning framework combining a protein Language Model and Graph Neural Network to predict protein properties from sequence and structure, outperforming existing methods on fluorescence, protease stability, and Gene Ontology function prediction.

Signaling Pathways Project maps over 10,000 transcriptomic and ChIP-Seq experiments to signaling nodes and ranks node targets by meta-analysis (consensomes), validated against literature and bench assays.

The paper shows that hair follicle niche precursors are specified before niche formation and requires FGF20 from progenitors.

This study profiles proteomic changes across postnatal human cortical development, identifies age-related protein modules, and links them to RNA expression and genetic risk loci for intellectual disability.