A5073740698- Genomics and Phylogenetic Studies
- RNA and protein synthesis mechanisms
- Genomics and Chromatin Dynamics
- Genomics and Rare Diseases
- Machine Learning in Materials Science
- Computational Drug Discovery Methods
- RNA Research and Splicing
- Bioinformatics and Genomic Networks
- Machine Learning in Bioinformatics
- Genomic variations and chromosomal abnormalities
Soochow University
2020-2025
Accurate prediction of drug–target interactions (DTIs) is pivotal for accelerating the processes drug discovery and repurposing. MVCL-DTI, a novel model leveraging heterogeneous graphs predicting DTIs, tackles challenge synthesizing information from varied biological subnetworks. It integrates neighbor view, meta-path diffusion view to capture semantic features employs an attention-based contrastive learning approach, along with multiview attention-weighted fusion module, effectively...
Accurately predicting the pathogenicity of missense variants is crucial for improving disease diagnosis and advancing clinical research. However, existing computational methods primarily focus on general predictions, overlooking assessments disease-specific conditions. In this study, we propose DS-MVP, a method capable in human genomes. DS-MVP first leverages deep learning model pre-trained large dataset to learn rich representation variants. It then fine-tunes these representations with an...
Protein structure can be severely disrupted by frameshift and nonsense mutations at specific positions in the protein sequence. Frameshift mutation cases also found healthy individuals. A method to distinguish neutral potentially disease-associated is of practical fundamental importance. It would allow researchers rapidly screen out pathogenic sites from a large number mutated genes then use these as drug targets speed up diagnosis improve access treatment. The problem how between remains...
The control of the coordinated expression genes is primarily regulated by interactions between transcription factors (TFs) and their DNA binding sites, which are an integral part transcriptional regulatory networks. There many computational tools focused on determining TF or unbinding to a sequence. However, other further relative preference such needed. Here, we propose regression model with deep learning, called SemanticBI, predict intensities TF-DNA binding. SemanticBI convolutional...
Deep learning has been successfully applied to surprisingly different domains. Researchers and practitioners are employing trained deep models enrich our knowledge. Transcription factors (TFs)are essential for regulating gene expression in all organisms by binding specific DNA sequences. Here, we designed a model named SemanticCS (Semantic ChIP-seq)to predict TF specificities. We on an ensemble of ChIP-seq datasets (Multi-TF-cell)to learn useful intermediate features across multiple TFs...