Deep-intronic variants often cause genetic diseases by altering RNA splicing. However, these pathogenic variants are overlooked in whole-genome sequencing analyses, because they are quite difficult to segregate from a vast number of benign variants (approximately 1,500,000 deep-intronic variants per individual). Therefore, we developed the Pathogenicity predictor for Deep-intronic Variants causing Aberrant Splicing (PDIVAS), an ensemble machine-learning model combining multiple splicing features and regional splicing constraint metrics. Using PDIVAS, around 27 pathogenic candidates were identified per individual with 95% sensitivity, and causative variants were more efficiently prioritized than previous predictors in simulated patient genome sequences. PDIVAS is available at https://github.com/shiro-kur/PDIVAS.

The authors have declared no competing interest.

This study was supported by JSPS KAKENHI Grant Numbers 22J23899 and 19K07367. This study was also supported by AMED under Grant Number JP22gm4010013.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The study used ONLY openly available human data that were originally located at: http://hgdownload.cse.ucsc.edu/gbdb/hg19/1000Genomes/phase3/. and https://ftp.ensembl.org/pub/data_files/homo_sapiens/GRCh37/variation_genotype/gnomad.genomes.r2.0.1.sites.noVEP.vcf.gz.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

The PDIVAS source code, command-line interface, and predictions for all rare deep-intronic SNVs, short insertion, and deletion within genes of Mendelian disease are available at https://github.com/shiro-kur/PDIVAS. ConSplice scores and precomputed scores of ConSpliceML are available at https://home.chpc.utah.edu/~u1138933/ConSplice/. Precomputed scores of CADD-Splice are available at https://krishna.gs.washington.edu/download/CADD/v1.6/GRCh37/. The pathogenic splice-altering variants from HGMD were downloaded from the HGMD website http://www.hgmd.cf.ac.uk/ under the HGMD commercial license. Due to HGMD commercial licensing, we are not allowed to share these variants publicly. 1000 Genomes Project variants are publically available at http://hgdownload.cse.ucsc.edu/gbdb/hg19/1000Genomes/phase3/. gnomAD variants are publically available at https://ftp.ensembl.org/pub/data_files/homo_sapiens/GRCh37/variation_genotype/gnomad.genomes.r2.0.1.sites.noVEP.vcf.gz. Gene list from OMIM is available to users from academic institutions and non-profit organizations at https://www.omim.org/downloads. Gene lists from CGD are publically available at https://research.nhgri.nih.gov/CGD/download/.

https://github.com/shiro-kur/PDIVAS