Hongming Chen

A novel AR molecular glue degrader via bivalent engagement of the N-terminal domain and RNF213-UBE2J2 complex

This paper introduces GZL626, a novel AR degrader that targets the N-terminal domain and RNF213-UBE2J2 complex, effectively degrading AR and AR-V7 and showing antitumor and antiviral activity.

SynPROTAC: synthesizable PROTACs design through synthesis constrained generative model and reinforcement learning

SynPROTAC generates novel PROTAC molecules with feasible synthetic routes and favorable properties using a synthesis-constrained generative model and reinforcement learning.

Discovery of orally bioavailable SARS-CoV-2 papain-like protease inhibitor as a potential treatment for COVID-19

The paper identifies a potent orally bioavailable SARS-CoV-2 PLpro inhibitor with in vitro and in vivo antiviral activity against SARS-CoV-2 and related coronaviruses.

Discovery of resistance-resilient quinoline papain-like protease inhibitors through topology-constrained molecular generative design

This paper discovers a novel quinoline-based PLpro inhibitor, GZNL-2016, that remains effective against drug-resistant SARS-CoV-2 variants like Omicron BA.5 and XBB.1.

Functional metagenomics reveals an alternative, broad-specificity pathway for metabolism of carbohydrates in human gut commensal bacteria

The paper identifies a novel, broad-specificity glycosidase pathway in gut bacteria that operates via a non-Koshland mechanism, capable of hydrolyzing diverse substrates including thioglycosides and pharmaceuticals.

A Comprehensive Benchmark Study on Biomedical Text Generation and Mining with ChatGPT

This study evaluates ChatGPT's performance on biomedical text generation and mining tasks using various biomedical corpora.

X-DPI: A structure-aware multi-modal deep learning model for drug-protein interactions prediction

X-DPI is a structure-aware multi-modal deep learning model for drug-protein interactions prediction that outperforms existing methods on benchmark datasets.

MolRep: A Deep Representation Learning Library for Molecular Property Prediction

The paper develops MolRep, a library unifying 16 molecular representation models, and evaluates them on 12 benchmarks to identify top-performing models for property prediction.