TP-LMMSG: a peptide prediction graph neural network incorporating flexible amino acid property representation.

Bioactive peptide therapeutics has been a long-standing research topic. Notably, the antimicrobial peptides (AMPs) have been extensively studied for its therapeutic potential. Meanwhile, the demand for annotating other therapeutic peptides, such as antiviral peptides (AVPs) and anticancer peptides (ACPs), also witnessed an increase in recent years. However, we conceive that the structure of peptide chains and the intrinsic information between the amino acids is not fully investigated among the existing protocols. Therefore, we develop a new graph deep learning model, namely TP-LMMSG, which offers lightweight and easy-to-deploy advantages while improving the annotation performance in a generalizable manner. The results indicate that our model can accurately predict the properties of different peptides. The model surpasses the other state-of-the-art models on AMP, AVP and ACP prediction across multiple experimental validated datasets. Moreover, TP-LMMSG also addresses the challenges of time-consuming pre-processing in graph neural network frameworks. With its flexibility in integrating heterogeneous peptide features, our model can provide substantial impacts on the screening and discovery of therapeutic peptides. The source code is available at https://github.com/NanjunChen37/TP_LMMSG.

Discovering DNA shape motifs with multiple DNA shape features: generalization, methods, and validation.

DNA motifs are crucial patterns in gene regulation. DNA-binding proteins (DBPs), including transcription factors, can bind to specific DNA motifs to regulate gene expression and other cellular activities. Past studies suggest that DNA shape features could be subtly involved in DNA-DBP interactions. Therefore, the shape motif annotations based on intrinsic DNA topology can deepen the understanding of DNA-DBP binding. Nevertheless, high-throughput tools for DNA shape motif discovery that incorporate multiple features altogether remain insufficient. To address it, we propose a series of methods to discover non-redundant DNA shape motifs with the generalization to multiple motifs in multiple shape features. Specifically, an existing Gibbs sampling method is generalized to multiple DNA motif discovery with multiple shape features. Meanwhile, an expectation-maximization (EM) method and a hybrid method coupling EM with Gibbs sampling are proposed and developed with promising performance, convergence capability, and efficiency. The discovered DNA shape motif instances reveal insights into low-signal ChIP-seq peak summits, complementing the existing sequence motif discovery works. Additionally, our modelling captures the potential interplays across multiple DNA shape features. We provide a valuable platform of tools for DNA shape motif discovery. An R package is built for open accessibility and long-lasting impact: https://zenodo.org/doi/10.5281/zenodo.10558980.

DeepSeq2Drug: An expandable ensemble end-to-end anti-viral drug repurposing benchmark framework by multi-modal embeddings and transfer learning.

Drug repurposing is promising in multiple scenarios, such as emerging viral outbreak controls and cost reductions of drug discovery. Traditional graph-based drug repurposing methods are limited to fast, large-scale virtual screens, as they constrain the counts for drugs and targets and fail to predict novel viruses or drugs. Moreover, though deep learning has been proposed for drug repurposing, only a few methods have been used, including a group of pre-trained deep learning models for embedding generation and transfer learning. Hence, we propose DeepSeq2Drug to tackle the shortcomings of previous methods. We leverage multi-modal embeddings and an ensemble strategy to complement the numbers of drugs and viruses and to guarantee the novel prediction. This framework (including the expanded version) involves four modal types: six NLP models, four CV models, four graph models, and two sequence models. In detail, we first make a pipeline and calculate the predictive performance of each pair of viral and drug embeddings. Then, we select the best embedding pairs and apply an ensemble strategy to conduct anti-viral drug repurposing. To validate the effect of the proposed ensemble model, a monkeypox virus (MPV) case study is conducted to reflect the potential predictive capability. This framework could be a benchmark method for further pre-trained deep learning optimization and anti-viral drug repurposing tasks. We also build software further to make the proposed model easier to reuse. The code and software are freely available at http://deepseq2drug.cs.cityu.edu.hk.

Chromothripsis detection with multiple myeloma patients based on deep graph learning.

MOTIVATION: Chromothripsis, associated with poor clinical outcomes, is prognostically vital in multiple myeloma. The catastrophic event is reported to be detectable prior to the progression of multiple myeloma. As a result, chromothripsis detection can contribute to risk estimation and early treatment guidelines for multiple myeloma patients. However, manual diagnosis remains the gold standard approach to detect chromothripsis events with the whole-genome sequencing technology to retrieve both copy number variation (CNV) and structural variation data. Meanwhile, CNV data are much easier to obtain than structural variation data. Hence, in order to reduce the reliance on human experts' efforts and structural variation data extraction, it is necessary to establish a reliable and accurate chromothripsis detection method based on CNV data. RESULTS: To address those issues, we propose a method to detect chromothripsis solely based on CNV data. With the help of structure learning, the intrinsic relationship-directed acyclic graph of CNV features is inferred to derive a CNV embedding graph (i.e. CNV-DAG). Subsequently, a neural network based on Graph Transformer, local feature extraction, and non-linear feature interaction, is proposed with the embedding graph as the input to distinguish whether the chromothripsis event occurs. Ablation experiments, clustering, and feature importance analysis are also conducted to enable the proposed model to be explained by capturing mechanistic insights. AVAILABILITY AND IMPLEMENTATION: The source code and data are freely available at https://github.com/luvyfdawnYu/CNV_chromothripsis.

Time-Series Expression Analysis of Epidermal Stem Cells from High Fat Diet Mice.

We aimed to identify differentially expressed genes (DEGs) in epidermal stem cells (epiSCs) in response to high fat diet (HFD). DEGs were identified by time-series analysis of the gene expression profile (GSE84510) in Gene Expression Omnibus (GEO) database. Functions and pathways affected by HFD were identified by functional annotation of DEGs. Key factors responding to HFD was identified by protein-protein interaction (PPI) network analysis. Two groups of genes with the same tendency in response to HFD were identified. ECM-related processes and PI3K pathway were altered in the early stage of obesity. A PPI network was constructed to delineate the interactions among proteins encoded by DEGs and ICAM1 and RELA were key epiSC factors respond to HFD. Our studies may provide valuable insights into the molecular mechanisms underlying how obesity affects the functions of epiSC.

Identification of differentially expressed genes in Budd­Chiari syndrome by RNA­sequencing.

Budd­Chiari syndrome (BCS) is an uncommon disease characterized by the occlusion or obstruction of hepatic venous outflow. The mechanism of BCS is still unclear and there are no accurate and effective diagnostic or therapeutic tools. In the present study, blood samples from BCS patients and healthy controls were used for RNA­sequencing. The differentially expressed genes (DEGs) in BCS patients compared with healthy controls were identified. Gene Ontology (GO) enrichment analysis, Kyoto Encyclopedia of Genes and Genomes pathway analysis and Protein­Protein Interaction (PPI) networks construction were performed for DEGs. A total of 405 DEGs including 317 upregulated and 88 downregulated DEGs were identified. The cytosol was the most significantly enriched GO term and the proteasome was also identified as significant enriched pathway. According to the PPI network of 30 DEGs (18 upregulated and 12 downregulated DEGs), synuclein α, tubulin ß­2A class IIa and zinc finger protein Gfi­1b (GFIIB) were the three most significant hub proteins. In conclusion, several DEGs including secreted protein acidic and cysteine rich, lipocalin­2, GFI1B and proteasome­associated DEGs may be associated with the pathological process of BCS. These results can provide novel clues for the pathogenesis and provide novel diagnostic and therapeutic strategies for BCS.

Epigallocatechin-3-gallate attenuates neointimal hyperplasia in a rat model of carotid artery injury by inhibition of high mobility group box 1 expression.

Epigallocatechin-3-gallate (EGCG) is a kind of polyphenol compound, called catechin, and is extracted from green tea. EGCG has a wide range of biological activities. The present study aimed to evaluate the effect of EGCG on neointimal hyperplasia in a rat model of carotid artery balloon injury and to explore the molecular mechanisms involved. Various experiments were performed to assess the effects of EGCG on thickening of neointima, expression levels of high mobility group box 1 protein (HMGB1) and receptor of advanced glycation end products (RAGE), the inflammatory response, oxidative stress and activation of nuclear factor (NF)-κB. Results demonstrated that EGCG decreased the intimal area and the ratio of intimal area/medial area compared with the balloon injury group. The expression levels of HMGB1 and RAGE induced by balloon injury were markedly inhibited by EGCG treatment. Furthermore, the inflammatory response and oxidative stress damage, which have close correlations with HMGB1, were restrained by EGCG. Finally, EGCG treatment markedly inhibited NF-κB activation. The present data provided evidence that EGCG attenuates neointimal hyperplasia in a model of carotid artery balloon injury, which indicated that EGCG may serve as a potential drug for restenosis in clinics.

Upregulation of MicroRNA-15a Contributes to Pathogenesis of Abdominal Aortic Aneurysm (AAA) by Modulating the Expression of Cyclin-Dependent Kinase Inhibitor 2B (CDKN2B).

BACKGROUND The objective of the present study was to identify the association between miR-15a-5p and CDKN2B, and their roles in regulating the development of abdominal aortic aneurysm (AAA). MATERIAL AND METHODS We searched the miRNA database online (www.mirdb.org) and used a luciferase reporter assay system to study the regulatory relationship between miR-15a-5p and CDKN2B. We also conducted real-time PCR and Western blot analysis to study the mRNA and protein expression level of CDKN2B among different patient groups (participants with abdominal aortic aneurysm (AAA) and normal controls) or cells treated with scramble control, miR-15a-5p mimics, CDKN2B siRNA, and miR-15a-5p inhibitors. RESULTS We found that CDKN2B was a virtual target of miR-15a-5p with potential binding sites in the 3'UTR of CDKN2B (77-83 bp). We also showed that miR-15a-5p could bind to the CDKN2B 3'UTR, resulting in a significant decrease in luciferase activity compared with the scramble control. Furthermore, we found that the cells isolated from AAA participants showed an over-expression of miR-15a-5p compared to the normal controls, while the CDKN2B mRNA and protein expression level of the AAA group were much lower than the normal control group. Additionally, the expression of CDKN2B mRNA and the protein of the cells transfected with miR-15a-5p mimics and CDKN2B siRNA was downregulated, while the cells showed upregulated expression subsequent to transfection with miR-15a-5p inhibitors compared to the scramble control. CONCLUSIONS The data revealed a negative regulatory role of miR-15a-5p in the apoptosis of smooth muscle cells via targeting CDKN2B, and showed that miR-15a-5p could be a novel therapeutic target of AAA.

Catheter-Directed Thrombolysis via Small Saphenous Veins for Treating Acute Deep Venous Thrombosis.

BACKGROUND There is little data comparing catheter-directed thrombolysis (CDT) via small saphenous veins vs. systematic thrombolysis on complications and efficacy in acute deep venous thrombosis patients. The aim of our study was to compare the efficacy and safety of CDT via the small saphenous veins with systematic thrombolysis for patients with acute deep venous thrombosis (DVT). MATERIAL AND METHODS Sixty-six patients with acute DVT admitted from June 2012 to December 2013 were divided into 2 groups: 27 patients received systemic thrombolysis (ST group) and 39 patients received CDT via the small saphenous veins (CDT group). The thrombolysis efficiency, limb circumference differences, and complications such as post-thrombotic syndrome (PTS) in the 2 groups were recorded. RESULTS The angiograms demonstrated that all or part of the fresh thrombus was dissolved. There was a significant difference regarding thrombolysis efficiency between the CDT group and ST group (71.26% vs. 48.26%, P=0.001). In both groups the postoperative limb circumference changes were higher compared to the preoperative values. The differences between postoperative limb circumferences on postoperative days 7 and 14 were significantly higher in the CDT group than in the ST group (all P<0.05). The incidence of postoperative PTS in the CDT group (17.9%) was significantly lower in comparison to the ST group (51.85%) during the follow-up (P=0.007). CONCLUSIONS Catheter-directed thrombolysis via the small saphenous veins is an effective, safe, and feasible approach for treating acute deep venous thrombosis.