Features used to train DeepPVP. A table consisting of the features and their representation used in the training and prediction of DeepPVP. (PDF 33 kb
Private SNPs with multiple VEP consequences. Private SNPs with multiple predicted VEP consequences f...
Summary of AUC scores based on 10-fold cross-validation and the independent test set when benign var...
Table S1. The 31 informative physicochemical properties and their corresponding MED (main effect dif...
Abstract Background Prioritization of variants in personal genomic data is a major challenge. Recent...
BACKGROUND Prioritization of variants in personal genomic data is a major challenge. Recently, co...
Feature contribution analysis in our CNN model. Table S2. Results of simple co-occurrence-based meth...
Table S1. Optimization of hyperparameters of DeepM6ASeq. Table S2. Hyperparameter optimization for o...
Supplemental tables and figures of data set simulation parameters and performance measures for all m...
Table S3. Random common variants matched by region to the pathogenic variants from Table S2. (XLSX 2...
Additional file 1: Includes 11 tables for training and testing data sets used in the study. The name...
Table S1. Distribution of tissue types and images used for the development of the CNN training datas...
Table S5. Prioritization of 37 non-coding pathogenic variants and their associated 37 internal contr...
Additional file 1: Figure S1. QTL mapping with deepGBLUP for a single QTL effect. We simulated herit...
Size of datasets. Number of training, validation and test samples for all cell types. (XLSX 36Â kb
Table S1. Subset of the 737 curated disease-causing non-coding variants. (XLSX 53 kb
Private SNPs with multiple VEP consequences. Private SNPs with multiple predicted VEP consequences f...
Summary of AUC scores based on 10-fold cross-validation and the independent test set when benign var...
Table S1. The 31 informative physicochemical properties and their corresponding MED (main effect dif...
Abstract Background Prioritization of variants in personal genomic data is a major challenge. Recent...
BACKGROUND Prioritization of variants in personal genomic data is a major challenge. Recently, co...
Feature contribution analysis in our CNN model. Table S2. Results of simple co-occurrence-based meth...
Table S1. Optimization of hyperparameters of DeepM6ASeq. Table S2. Hyperparameter optimization for o...
Supplemental tables and figures of data set simulation parameters and performance measures for all m...
Table S3. Random common variants matched by region to the pathogenic variants from Table S2. (XLSX 2...
Additional file 1: Includes 11 tables for training and testing data sets used in the study. The name...
Table S1. Distribution of tissue types and images used for the development of the CNN training datas...
Table S5. Prioritization of 37 non-coding pathogenic variants and their associated 37 internal contr...
Additional file 1: Figure S1. QTL mapping with deepGBLUP for a single QTL effect. We simulated herit...
Size of datasets. Number of training, validation and test samples for all cell types. (XLSX 36Â kb
Table S1. Subset of the 737 curated disease-causing non-coding variants. (XLSX 53 kb
Private SNPs with multiple VEP consequences. Private SNPs with multiple predicted VEP consequences f...
Summary of AUC scores based on 10-fold cross-validation and the independent test set when benign var...
Table S1. The 31 informative physicochemical properties and their corresponding MED (main effect dif...
DOI
Add to ORKG