Benchmarking foundation models for splice site and exon annotation
This study benchmarks foundation models for splice site and exon annotation, finding performance varies greatly depending on exon type and training data representation.
Author
Johns Hopkins UniversityORCID 0000-0002-9308-2003Unclaimed ORCID profile · follow to get notified of new preprints
3 papers
Recent·Most cited
This study benchmarks foundation models for splice site and exon annotation, finding performance varies greatly depending on exon type and training data representation.
Wui Wang Lui, Guangyu Yang, Zitong He, Liliana Florea
The paper introduces MntJULiP and Jutils for differential splicing analysis of RNA-seq data, incorporating covariates to identify age and sex-related splicing patterns in GTEx brain samples.
Zitong He, Ou Chen, Noelani Phillips…·Liliana Florea
The paper develops a deep learning model, eXAlu, to predict Alu exonization events in the human genome and estimates their prevalence to be 55-110K, significantly higher than in GENCODE.