Fuchu He

This paper introduces a method to control false discovery rates in deep-learning-based de novo peptide sequencing, improving reliability of peptide identifications.

This study identifies THOC2 as a regulator of DNA repair and growth in HCC, showing that targeting THOC2 enhances PARPi efficacy by disrupting mRNA export of DDR genes.

SciCore-Omics is a tri-modal foundation model that integrates histology, spatial transcriptomics, and language to improve spatial biology analysis and interpretation.

The paper develops Quartet, a proteome reference material with built-in truths, to assess label-free proteomics reproducibility across platforms and labs.

The paper introduces π-HelixNovo, a Transformer-based model for de novo peptide sequencing that outperforms existing methods and improves taxonomic resolution in gut metaproteomes.

pChem assesses chemoproteomic probe performance by evaluating modification-homogeneity, profiling efficiency, and residue selectivity using isotopically coded probe-derived modifications.

The paper systematically explores human genome target spaces for protein and peptide drugs, identifying distinct characteristics and developing genome-wide target estimation models for each.

The paper introduces BiFC-seq, a yeast-based method for genome-wide interactome mapping, and demonstrates its application to Ebola virus and p53 interactomes, identifying known and novel interactions.

LFAQ improves label-free absolute protein quantification by correcting MS intensity biases using predicted peptide quantitative factors, achieving higher accuracy and precision, especially for low-abundance proteins.

PANDA is a proteomics data quantification tool that offers higher accuracy and precision than MaxQuant with reduced computation time, supporting both label-free and labeled quantification.