Sessions allow users to save snapshots of the Genome Browser and its current configuration, including displayed tracks, position, and custom track data. The Public Sessions tool allows users to easily share those sessions that they deem interesting with the rest of the world's researchers. You can add your own sessions to this list by checking the appropriate box on the Session Management page.
Description: Machine Learning Prediction of Non-Coding Variant Impact in Cell-Class-Specific Human Retinal Cis-Regulatory Elements
Leah S. VandenBosch 1 and Timothy J. Cherry 1,2,3†
1 Center for Developmental Biology and Regenerative Medicine, Seattle Children's Research Institute, Seattle, WA, USA.
2 University of Washington Department of Pediatrics, Seattle, Washington, USA.
3 Brotman Baty Institute for Precision Medicine, Seattle, Washington, USA.
† Corresponding Author: timothy.cherry@seattlechildrens.org
This public session provides access to a track hub of Variant Impact Prediction (VIP) scores for 39,437 candidate human retinal cis-regulatory elements (CREs) in 18 different cell types and developmental stages from the adult and developing human retina.
Non-coding variants in cis-regulatory elements (CREs) like promoters and enhancers contribute to inherited retinal diseases (IRDs) however regulatory variants are typically challenging to interpret and prioritize for follow up studies. To improve identification of variants of interest, we implemented machine learning using a gapped k-mer support vector machine approach (GKM-SVM/deltaSVM) trained on single nucleus ATAC-seq data from specific cell classes and developmental states in the developing and mature human retina. These models demonstrate accuracy over 90% and a high degree of cell class specificity. Variant Impact Prediction Scores (VIPS) nominate specific sequences within candidate CREs, including putative transcription factor (TF) binding motifs, that would likely alter CRE function if mutated. This analysis demonstrates the capacity for singe nucleus-epigenomic data to predict the impact of non-coding sequence variants. It is our hope that these predicted impact scores can assist in identifying and interpreting variants of interest within human retinal cis-regulatory elements.
Author: CherryLab Session Name: csVISIONS_TrackHub Genome Assembly: hg38 Creation Date: 2025-02-16 Views: 3
Description: This public session provides access to a track hub featuring 25,000 predicted forebrain enhancers within the hg19 human genome assembly, identified using a DNA-sequence-based prediction pipeline that incorporates tissue-specific transcription factor occupancy patterns. These enhancers, crucial for regulating gene expression during brain development, were evaluated using chromatin marks, DNase hypersensitivity data, GWAS-based SNP data, and in vivo zebrafish models. The track hub enables researchers to explore the gene regulatory basis of brain-related diseases and development, as well as investigate the role of these predicted enhancers in mammalian and primate brain evolution. For citation, refer to the paper: Shireen et al. (2024), FEBS Letters. Author: abbasiam Session Name: Predicted human forebrain enhancers_hg19 Genome Assembly: hg19 Creation Date: 2025-01-16 Views: 175