Mingyue Zheng

MG2Act: A Mechanism-Inspired Sequential Attention Framework for Molecular Glue Degradation Prediction

MG2Act predicts molecular glue degradation by modeling sequential interactions between E3 ligase and substrate, outperforming baselines and identifying new degraders.

Functional orthogonality of WRN inhibitor resistance enables alternating therapy and mutation-tolerant inhibitor design in MSI-H cancers

This study shows that resistance to different WRN inhibitors in MSI-H cancers creates orthogonal vulnerabilities, enabling alternating therapy and mutation-tolerant inhibitor design.

MetaReact: A Reaction-Aware Transformer for End-to-End Prediction of Drug Metabolism

MetaReact predicts drug metabolites and enzyme selectivity using a reaction-aware Transformer, outperforming existing methods in accuracy and generalizability.

Benchmarking Real-World Applicability of Molecular Generative Models from De novo Design to Lead Optimization with MolGenBench

This paper introduces MolGenBench, a benchmark for evaluating molecular generative models in drug discovery, highlighting gaps between current models and real-world pharmaceutical workflows.

Advancing Ligand Binding Affinity Prediction with Cartesian Tensor-Based Deep Learning

PBCNet2.0 predicts protein-ligand binding affinity using a cartesian tensor-based Siamese Neural Network, achieving high accuracy and efficiency compared to physics-based simulations.

Bridging 3D Molecular Structures and Artificial Intelligence by a Conformation Description Language

The paper introduces ConfSeq, a conformation description language for 3D molecular structures, enabling sequence-based modeling and achieving state-of-the-art results in 3D molecular tasks.

SurfDock is a Surface-Informed Diffusion Generative Model for Reliable and Accurate Protein-ligand Complex Prediction

SurfDock improves protein-ligand complex prediction by integrating multiple protein representations into a diffusion model, achieving higher accuracy and physical plausibility than existing methods.

Covalent DNA-Encoded Library Workflow Drives Discovery of SARS-CoV-2 Non-structural Proteins Inhibitors

This study uses covalent DNA-encoded libraries to discover inhibitors targeting SARS-CoV-2 proteases 3CLpro and PLpro, identifying novel compounds with potent activity and unique binding modes.

FAPM: Functional Annotation of Proteins using Multi-Modal Models Beyond Structural Modeling

FAPM improves protein functional annotation by combining protein sequence and language models, outperforming sequence-only methods on benchmarks and phage proteins with few homologs.

Embryonic origins of forebrain oligodendrocytes revisited by combinatorial genetic fate mapping

The paper revisits the embryonic origins of forebrain oligodendrocytes using genetic fate mapping, finding that LGE/CGE-derived OLs dominate specific brain regions while MGE/POA-derived OLs contribute uniquely to the cortex.

Identify compound-protein interaction with knowledge graph embedding of perturbation transcriptomics

PertKGE improves compound-protein interaction prediction using knowledge graph embedding of perturbation transcriptomics, outperforming baselines in cold-start settings and identifying novel therapeutic targets.

GDOP: A graph convolutional network-based drug "on-target" pathway prediction algorithm

GDOP predicts drug 'on-target' pathways using graph convolutional networks, achieving high AUC-ROC and Top10 accuracy on LINCS data.

PackDock: a Diffusion Based Side Chain Packing Model for Flexible Protein-Ligand Docking

PackDock predicts accurate protein-ligand complex conformations using a diffusion model for side-chain packing, validated through multiple docking experiments.

SciMind: A Multimodal Mixture-of-Experts Model for Advancing Pharmaceutical Sciences

SciMind is a multimodal model designed to handle pharmaceutical sciences data, showing good performance in text comprehension and molecular tasks.

TranSiGen: Deep representation learning of chemical-induced transcriptional profile

TranSiGen denoises and reconstructs chemical-induced transcriptional profiles using deep generative modeling, effectively predicting differential expression genes and serving as alternative phenotype information for drug discovery.

Transfer Learning Enhanced Graph Neural Network for Aldehyde Oxidase Metabolism Prediction and Its Experimental Application

This study develops AOMP, a graph neural network for predicting AOX metabolism, outperforming benchmarks and identifying new scaffolds validated experimentally.

EquiScore: A generic protein-ligand interaction scoring method integrating physical prior knowledge with data augmentation modeling

EquiScore is a protein-ligand interaction scoring method that outperforms existing methods on external test sets and shows potential for lead compound optimization.

Drug design and repurposing with a sequence-to-drug paradigm

This paper introduces a sequence-to-drug paradigm using TransformerCPI2.0 to discover drug-like molecules from protein sequences and validates its effectiveness for three targets.

AutoGGN: A Gene Graph Network AutoML Tool for Multi-Omics Research

AutoGGN integrates multi-omics data and molecular interaction networks using graph convolutional neural networks, achieving better performance in cancer and single-cell classification tasks.

Automated design and optimization of multitarget schizophrenia drug candidates by deep learning

This paper develops a deep learning system to design multitarget antipsychotic drugs, generating novel compounds with activity against multiple receptors and demonstrating efficacy in animal models.

AutoGenome V2: New Multimodal Approach Developed for Multi-Omics Research

AutoGenome V2 integrates multi-omics data using a novel multimodal deep learning approach, achieving state-of-the-art results in four tasks.

Computational target fishing by mining transcriptional data using a novel Siamese spectral-based graph convolutional network

The paper introduces a Siamese spectral-based graph convolutional network to infer protein targets of chemical compounds from gene expression data, achieving better performance than existing methods.