Cross-Species Splicing Variant Benchmark Datasets (Human, Rat, Pig, Chicken)
收藏资源简介:
Benchmark datasets for evaluating splicing variant prediction models across four species in manuscript: Comprehensive review and assessment of multi-species splicing variant prediction: task-specific deep learning models and genomic foundation models. Each dataset contains balanced positive (splice-altering) and negative (normal) variants with 8,192bp sequence windows as a default. Files included: splicevardb_benchmark.tsv: 23,877 Human variants (SpliceVarDB, GRCh38) ratgtex_benchmark.tsv: 28,120 Rat variants (RatGTEx, Rnor_6.0) piggtex_benchmark.tsv: 26,358 Pig variants (PigGTEx, Sscrofa11.1) chickengtex_benchmark.tsv: 25,000 Chicken variants (ChickenGTEx, GRCg6a) Related GitHub repository for pre-processing: https://github.com/ByronSyun/DL-CrossSpeciesReview.git



