분류 전체보기229 RECOVERING TIME-VARYINGNETWORKS FROM SINGLE-CELLDATA PAPERhttps://arxiv.org/abs/2410.01853 Recovering Time-Varying Networks From Single-Cell DataGene regulation is a dynamic process that underlies all aspects of human development, disease response, and other key biological processes. The reconstruction of temporal gene regulatory networks has conventionally relied on regression analysis, graphicalarxiv.org PAPER REVIEWhttps://doraemin.tistory.com/.. 2025. 11. 25. Graph Attention Networkfor Link Prediction of Gene Regulationsfrom Single-cell RNA-sequencing Data(GENELink) PAPERhttps://academic.oup.com/bioinformatics/article/38/19/4522/6663989 PAPER REVIEWhttps://doraemin.tistory.com/252 [GENELink] Graph attention network for link prediction of gene regulations from single-cell RNA-sequencing dataPAPERhttps://academic.oup.com/bioinformatics/article/38/19/4522/6663989GENELink의 목적과 접근 방식이미 주어진 GRN 그래프 A를 기반으로 학습하고, 그 구조 안에서 잠재된(score) 연결 및 인과관계를 예측하는 것 ✅ 1doraemin.t.. 2025. 11. 25. Graph Attention Networks (GAT) PAPERhttps://arxiv.org/abs/1710.10903 Graph Attention NetworksWe present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximationsarxiv.orgFoundational Knowledge for GATsSimple neighborhood aggregationhttps://d.. 2025. 11. 25. CASCC: a co-expression-assisted single-cell RNA-seq data clustering method PAPERhttps://academic.oup.com/bioinformatics/article/40/5/btae283/7658302 PAPER REVIEWhttps://doraemin.tistory.com/237 CASCC: a co-expression-assisted single-cell RNA-seq data clustering methodPAPERhttps://academic.oup.com/bioinformatics/article/40/5/btae283/7658302 핵심 개요CASCC(Co-expression-Assisted Single-Cell Clustering)는 기존의 클러스터링 방법이 갖는 한계―특히 세포 상태 전이 등으로 인해 클러스터 경doraemin.tistory.com PAPER .. 2025. 11. 25. Hierarchical Marker Genes Selection in scRNA-seq Analysis PAPERhttps://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1012643 Hierarchical marker genes selection in scRNA-seq analysisAuthor summary In the analysis and interpretation of scRNA-seq data, one important step is to identify marker genes to annotate cell clusters with the biologically meaningful names. Existing marker gene selection methods typically perform differential exprj.. 2025. 11. 25. Healthcare Biclustering of Predictive Gene Expression Using LSTM-SVM Hybrid PAPERhttps://www.informingscience.org/Publications/5446 InformingSciJ - Healthcare Biclustering of Predictive Gene Expression Using LSTM Based Support Vector MachineHealthcare Biclustering of Predictive Gene Expression Using LSTM Based Support Vector Machine Aim/PurposeThe major goal of this work is to establish prediction patterns that can influence better diagnosis and treatment strategies usi.. 2025. 11. 25. 이전 1 2 3 4 ··· 39 다음
