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

May 2023 Genome Biol

Synopsis of Social media discussions

Discussions around the publication show strong interest, with posts highlighting Introme’s ability to integrate multiple prediction tools for assessing splicing impacts, and words like 'accurate prediction,' 'clinical applications,' and 'superior accuracy' demonstrate a sense of significance and optimism about its transformative potential.

A
Agreement
 Moderate agreement

Most discussions express support for the significance of Introme's capabilities, highlighting its superior accuracy and clinical relevance, indicating general consensus on its importance.

I
Interest
 High level of interest

Posts frequently mention the innovative use of machine learning and the potential implications for understanding splicing, showing strong curiosity and engagement with the topic.

E
Engagement
 Moderate level of engagement

Several posts delve into the technical aspects, such as integration of multiple prediction tools and gene architecture considerations, reflecting active engagement beyond surface-level mentions.

I
Impact
 High level of impact

Many comments emphasize the potential of Introme to improve diagnoses and influence genetic research, suggesting high perceived impact on clinical and scientific fields.

Social Mentions

YouTube

1 Videos

Facebook

2 Posts

Twitter

40 Posts

Blogs

2 Articles

News

3 Articles

Metrics

Video Views

9

Total Likes

90

Extended Reach

377,494

Social Features

48

Timeline: Posts about article

Top Social Media Posts

Posts referencing the article

Accurate Prediction of Variants Impact on Gene Splicing Using Introme

Accurate Prediction of Variants Impact on Gene Splicing Using Introme

Introme uses machine learning to predict how genetic variants, including non-coding ones, affect gene splicing, aiding in clinical diagnosis. It combines multiple tools and gene structure to enhance accuracy, showing superior results in tests with thousands of variants.

Social RTCL TV

August 25, 2023

9 views

  • NGS Bioinformatics
    @ngsbioinfo (Twitter)

    RT @BioMedCentral: An article in @GenomeBiology presents Introme, which uses machine learning to integrate predictions from several splice…
    view full post

    June 21, 2023

    1

  • BMC
    @BioMedCentral (Twitter)

    An article in @GenomeBiology presents Introme, which uses machine learning to integrate predictions from several splice detection tools and gene architecture features to comprehensively evaluate the likelihood of a variant impacting splicing. https://t.co/hJlMncYKgg
    view full post

    June 21, 2023

    5

    1

  • John Giraldo
    @jngo89 (Twitter)

    RT @BioMedCentral: An article in @GenomeBiology presents Introme: a tool which uses machine learning to integrate predictions from several…
    view full post

    June 16, 2023

    2

  • Rene Sugar
    @renesugar (Twitter)

    https://t.co/4UyUadTXKC "Splice-altering variants can cause exon skipping, intronic read-through, cryptic exon inclusion, or shift the open reading frame to produce an aberrant gene product."
    view full post

    June 15, 2023

  • Rene Sugar
    @renesugar (Twitter)

    https://t.co/4UyUadTXKC "This can result in reduced or absent function at the protein level or complete loss of protein expression due to mechanisms such as nonsense-mediated mRNA decay."
    view full post

    June 15, 2023

  • Rene Sugar
    @renesugar (Twitter)

    https://t.co/4UyUadTpV4 "Additionally, there are regulatory elements, such as enhancers and silencers, in exons and introns that influence splice-site usage and exon inclusion."
    view full post

    June 15, 2023

  • Rene Sugar
    @renesugar (Twitter)

    https://t.co/4UyUadTXKC "The main splicing motifs are the essential donor (5′) and acceptor (3′) splice sites at either end of the intron, the branchpoint, and the polypyrimidine tract (PPT)."
    view full post

    June 15, 2023

  • Rene Sugar
    @renesugar (Twitter)

    https://t.co/4UyUadTXKC "The delineation of coding regions by the precise removal of intronic DNA from pre-mRNA is orchestrated by over 200 proteins and small nuclear RNAs (snRNAs) through the recognition of defined sequence motifs."
    view full post

    June 15, 2023

  • Rene Sugar
    @renesugar (Twitter)

    https://t.co/4UyUadTXKC "Introme is available at https://t.co/72KkFCKKHA." "The process of splicing is critical for the accurate generation of mRNA and ultimately protein."
    view full post

    June 15, 2023

  • Rene Sugar
    @renesugar (Twitter)

    Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications https://t.co/4UyUadTXKC
    view full post

    June 15, 2023

  • Valentina Riggio
    @ValeRiggio (Twitter)

    RT @BioMedCentral: An article in @GenomeBiology presents Introme: a tool which uses machine learning to integrate predictions from several…
    view full post

    June 15, 2023

    2

  • BMC
    @BioMedCentral (Twitter)

    An article in @GenomeBiology presents Introme: a tool which uses machine learning to integrate predictions from several splice detection tools and gene architecture features to comprehensively evaluate the likelihood of a variant impacting splicing. https://t.co/hJlMncYKgg
    view full post

    June 15, 2023

    7

    2

  • Fulbright Australia
    @FulbrightAUS (Twitter)

    RT @PatSullivann:
    view full post

    June 14, 2023

    21

  • Tamino
    @taminolex (Twitter)

    RT @BioMedCentral: An article in @GenomeBiology presents Introme: a tool which uses machine learning to integrate predictions from several…
    view full post

    June 3, 2023

    1

  • BMC
    @BioMedCentral (Twitter)

    An article in @GenomeBiology presents Introme: a tool which uses machine learning to integrate predictions from several splice detection tools and gene architecture features to comprehensively evaluate the likelihood of a variant impacting splicing. https://t.co/hJlMncYKgg
    view full post

    June 3, 2023

    2

    1

  • Amanda Haddock
    @AmandaHaddock (Twitter)

    RT @PatSullivann:
    view full post

    June 2, 2023

    21

  • Escamez Lab
    @ALEscamez (Twitter)

    RT @PatSullivann:
    view full post

    May 27, 2023

    21

  • Eriseld Krasniqi
    @KrasniqiEriseld (Twitter)

    RT @PatSullivann:
    view full post

    May 27, 2023

    21

  • Daniel Lee
    @zzzang5889 (Twitter)

    RT @PatSullivann:
    view full post

    May 27, 2023

    21

  • Renato Puga
    @renatopuga (Twitter)

    RT @PatSullivann:
    view full post

    May 27, 2023

    21

  • Marion Mateos
    @Dr_MMateos (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • James Ferguson
    @Psy_Fer_ (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Dianne Sylvester
    @muppys (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Alicia Oshlack
    @AliciaOshlack (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Genomic Technologies Group
    @GenTechGp (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Chelsea Mayoh
    @cmayoh_bio (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Martin Smith
    @martinalexsmith (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Pat Adams
    @PathologyPat (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • aaaa
    @ngsstudent (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Amarinder
    @amarinder_thind (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • BMC
    @BioMedCentral (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Jovana Maksimovic
    @JovMaksimovic (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Wilfried Haerty
    @WHaerty (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Yuichi Shiraishi
    @friend1_ws (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Sam El-Kamand
    @SamElkamand (Twitter)

    RT @PatSullivann:
    view full post

    May 26, 2023

    21

  • Patricia Sullivan
    @PatSullivann (Twitter)


    view full post

    May 26, 2023

    76

    21

  • I gotta change my name but I haven't
    @epi_boto (Twitter)

    Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications https://t.co/i9C9okReyV
    view full post

    May 21, 2023

  • Seiichi Mori
    @seiichi_mori (Twitter)

    Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications https://t.co/8qbUCnNcr1 https://t.co/pVrZPRcWiH
    view full post

    May 19, 2023

  • Oncology & Machine Learning
    @MlOncology (Twitter)

    Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications https://t.co/NfOmEDnxga
    view full post

    May 18, 2023

  • MyJournals
    @myjournals (Twitter)

    Introme accurately predicts the impact of coding and noncoding variants on gene splicing, with clinical applications https://t.co/6ZkMeVsUKQ
    view full post

    May 17, 2023

Abstract Synopsis

  • Predicting the effect of genetic variants on splicing is tough, especially for non-canonical splice sites, often leading to missed diagnoses.
  • Introme is a new tool that uses machine learning to combine predictions from various splice detection tools and factors in gene architecture to assess the impact of variants on splicing.
  • In tests with 21,000 variants, Introme showed superior accuracy (auPRC: 0.98) compared to other tools for identifying clinically significant splice variants, and it's accessible on GitHub.