Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications

Patricia J. Sullivan; Velimir Gayevskiy; Ryan L. Davis; Marie Wong; Chelsea Mayoh; Amali Mallawaarachchi; Yvonne Hort; Mark J. McCabe; Sarah Beecroft; Matilda R. Jackson; Peer Arts; Andrew Dubowsky; Nigel Laing; Marcel E. Dinger; Hamish S. Scott; Emily Oates; Mark Pinese; Mark J. Cowley

doi:10.1186/s13059-023-02936-7

Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications

Patricia J. Sullivan
, Velimir Gayevskiy
, Ryan L. Davis
, Marie Wong
, Chelsea Mayoh
, Amali Mallawaarachchi
, Yvonne Hort
, Mark J. McCabe
, Sarah Beecroft
, Matilda R. Jackson
, Peer Arts
, Andrew Dubowsky
, Nigel Laing
, Marcel E. Dinger
, Hamish S. Scott
, Emily Oates
, Mark Pinese
, Mark J. Cowley

Research output: Contribution to journal › Article › peer-review

16 Citations (Web of Science)

Abstract

Predicting the impact of coding and noncoding variants on splicing is challenging, particularly in non-canonical splice sites, leading to missed diagnoses in patients. Existing splice prediction tools are complementary but knowing which to use for each splicing context remains difficult. Here, we describe Introme, which uses machine learning to integrate predictions from several splice detection tools, additional splicing rules, and gene architecture features to comprehensively evaluate the likelihood of a variant impacting splicing. Through extensive benchmarking across 21,000 splice-altering variants, Introme outperformed all tools (auPRC: 0.98) for the detection of clinically significant splice variants. Introme is available at https://github.com/CCICB/introme .

Original language	English
Article number	118
Journal	Genome Biology
Volume	24
Issue number	1
DOIs	https://doi.org/10.1186/s13059-023-02936-7
Publication status	Published - Dec 2023

Funding

Funders	Funder number
NHMRC National Health and Medical Research Council	1176265

Access to Document

10.1186/s13059-023-02936-7Licence: CC BY

Cite this

Sullivan, P. J., Gayevskiy, V., Davis, R. L., Wong, M., Mayoh, C., Mallawaarachchi, A., Hort, Y., McCabe, M. J., Beecroft, S., Jackson, M. R., Arts, P., Dubowsky, A., Laing, N., Dinger, M. E., Scott, H. S., Oates, E., Pinese, M., & Cowley, M. J. (2023). Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications. Genome Biology, 24(1), Article 118. https://doi.org/10.1186/s13059-023-02936-7

@article{e1aa3523b7314be6b7b0745def6d60a7,

title = "Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications",

abstract = "Predicting the impact of coding and noncoding variants on splicing is challenging, particularly in non-canonical splice sites, leading to missed diagnoses in patients. Existing splice prediction tools are complementary but knowing which to use for each splicing context remains difficult. Here, we describe Introme, which uses machine learning to integrate predictions from several splice detection tools, additional splicing rules, and gene architecture features to comprehensively evaluate the likelihood of a variant impacting splicing. Through extensive benchmarking across 21,000 splice-altering variants, Introme outperformed all tools (auPRC: 0.98) for the detection of clinically significant splice variants. Introme is available at https://github.com/CCICB/introme .",

keywords = "Clinical genetics, Deep intronic, Genomics, Intronic variant, Splice region, Splice site, Splicing, Splicing regulatory element, Variant interpretation",

author = "Sullivan, \{Patricia J.\} and Velimir Gayevskiy and Davis, \{Ryan L.\} and Marie Wong and Chelsea Mayoh and Amali Mallawaarachchi and Yvonne Hort and McCabe, \{Mark J.\} and Sarah Beecroft and Jackson, \{Matilda R.\} and Peer Arts and Andrew Dubowsky and Nigel Laing and Dinger, \{Marcel E.\} and Scott, \{Hamish S.\} and Emily Oates and Mark Pinese and Cowley, \{Mark J.\}",

note = "Funding Information: PS was supported by an Australian Government Research Training Program (RTP) scholarship, the Kids Cancer Alliance PhD Top Up scholarship, Petre Foundation PhD Top Up scholarship, and a Fulbright Future scholarship. MP was supported by an NHMRC Investigator Grant (\#1176265). MC was supported by a NSW Health Early-Mid Career Fellowship. This project was supported by grant 1165556 awarded through the 2018 Priority-driven Collaborative Cancer Research Scheme and co-funded by Cancer Australia and My Room. The authors would like to acknowledge Luminesce Alliance – Innovation for Children{\textquoteright}s Health for its contribution and support. Luminesce Alliance is a not-for-profit cooperative joint venture between the Sydney Children{\textquoteright}s Hospitals Network, the Children{\textquoteright}s Medical Research Institute, and the Children{\textquoteright}s Cancer Institute. It has been established with the support of the NSW Government to coordinate and integrate paediatric research. Luminesce Alliance is also affiliated with the University of Sydney and the University of New South Wales Sydney. Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

doi = "10.1186/s13059-023-02936-7",

language = "English",

volume = "24",

journal = "Genome Biology",

issn = "1474-7596",

publisher = "BioMed Central",

number = "1",

}

Sullivan, PJ, Gayevskiy, V, Davis, RL, Wong, M, Mayoh, C, Mallawaarachchi, A, Hort, Y, McCabe, MJ, Beecroft, S, Jackson, MR, Arts, P, Dubowsky, A, Laing, N, Dinger, ME, Scott, HS, Oates, E, Pinese, M & Cowley, MJ 2023, 'Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications', Genome Biology, vol. 24, no. 1, 118. https://doi.org/10.1186/s13059-023-02936-7

TY - JOUR

T1 - Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications

AU - Sullivan, Patricia J.

AU - Gayevskiy, Velimir

AU - Davis, Ryan L.

AU - Wong, Marie

AU - Mayoh, Chelsea

AU - Mallawaarachchi, Amali

AU - Hort, Yvonne

AU - McCabe, Mark J.

AU - Beecroft, Sarah

AU - Jackson, Matilda R.

AU - Arts, Peer

AU - Dubowsky, Andrew

AU - Laing, Nigel

AU - Dinger, Marcel E.

AU - Scott, Hamish S.

AU - Oates, Emily

AU - Pinese, Mark

AU - Cowley, Mark J.

N1 - Funding Information: PS was supported by an Australian Government Research Training Program (RTP) scholarship, the Kids Cancer Alliance PhD Top Up scholarship, Petre Foundation PhD Top Up scholarship, and a Fulbright Future scholarship. MP was supported by an NHMRC Investigator Grant (#1176265). MC was supported by a NSW Health Early-Mid Career Fellowship. This project was supported by grant 1165556 awarded through the 2018 Priority-driven Collaborative Cancer Research Scheme and co-funded by Cancer Australia and My Room. The authors would like to acknowledge Luminesce Alliance – Innovation for Children’s Health for its contribution and support. Luminesce Alliance is a not-for-profit cooperative joint venture between the Sydney Children’s Hospitals Network, the Children’s Medical Research Institute, and the Children’s Cancer Institute. It has been established with the support of the NSW Government to coordinate and integrate paediatric research. Luminesce Alliance is also affiliated with the University of Sydney and the University of New South Wales Sydney. Publisher Copyright: © 2023, The Author(s).

PY - 2023/12

Y1 - 2023/12

N2 - Predicting the impact of coding and noncoding variants on splicing is challenging, particularly in non-canonical splice sites, leading to missed diagnoses in patients. Existing splice prediction tools are complementary but knowing which to use for each splicing context remains difficult. Here, we describe Introme, which uses machine learning to integrate predictions from several splice detection tools, additional splicing rules, and gene architecture features to comprehensively evaluate the likelihood of a variant impacting splicing. Through extensive benchmarking across 21,000 splice-altering variants, Introme outperformed all tools (auPRC: 0.98) for the detection of clinically significant splice variants. Introme is available at https://github.com/CCICB/introme .

AB - Predicting the impact of coding and noncoding variants on splicing is challenging, particularly in non-canonical splice sites, leading to missed diagnoses in patients. Existing splice prediction tools are complementary but knowing which to use for each splicing context remains difficult. Here, we describe Introme, which uses machine learning to integrate predictions from several splice detection tools, additional splicing rules, and gene architecture features to comprehensively evaluate the likelihood of a variant impacting splicing. Through extensive benchmarking across 21,000 splice-altering variants, Introme outperformed all tools (auPRC: 0.98) for the detection of clinically significant splice variants. Introme is available at https://github.com/CCICB/introme .

KW - Clinical genetics

KW - Deep intronic

KW - Genomics

KW - Intronic variant

KW - Splice region

KW - Splice site

KW - Splicing

KW - Splicing regulatory element

KW - Variant interpretation

UR - https://www.scopus.com/pages/publications/85159716509

U2 - 10.1186/s13059-023-02936-7

DO - 10.1186/s13059-023-02936-7

M3 - Article

C2 - 37198692

AN - SCOPUS:85159716509

SN - 1474-7596

VL - 24

JO - Genome Biology

JF - Genome Biology

IS - 1

M1 - 118

ER -

Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications

Abstract

Funding

Access to Document

Other files and links

Fingerprint

Additional file 1 of Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications

Additional file 1 of Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications