Min Wu

MiT4SL predicts synthetic lethality in cancer cell lines using multi-omics triplet representation learning, outperforming existing models in cell line-adapted scenarios.

AiPROTAC predicts PROTAC degradation potential and designs an androgen receptor degrader, outperforming existing models and showing improved in vitro efficacy.

This study benchmarks machine learning methods for predicting synthetic lethality in cancer using matrix factorization and deep learning models, highlighting performance differences and emphasizing data and scenario importance.

CLigOpt generates target-specific ligands with desired properties using a controllable fragment-based approach, improving the proportion of feasible active molecules by 10%.

This study uses cross-frequency multilayer network analysis to show increased low-frequency coupling and decreased high-frequency coupling in Alzheimer's disease compared to healthy controls, improving classification performance.

This paper introduces PS-SNC, a method for detecting protein complexes from multiple state-specific signed PPI networks, showing improved performance over existing methods.

GraphST improves spatial transcriptomics analysis by integrating clustering, integration, and deconvolution through graph self-supervised contrastive learning, achieving higher accuracy than existing methods.

This study evaluates graph neural networks for Alzheimer's disease classification using EEG-based functional connectivity measures, finding that GNNs outperform baselines but no single FC measure consistently dominates.

SynLethDB 2.0 is a database that compiles synthetic lethal gene pairs and related knowledge to aid in anticancer drug discovery, including over 16,000 new synthetic lethal interactions.

This paper introduces GCATSL, a graph contextualized attention network for predicting synthetic lethality in human cancers, outperforming existing methods on multiple datasets.