File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1504/IJCBDD.2020.113818
- Scopus: eid_2-s2.0-85103589029
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Skyhawk: an artificial neural network-based discriminator for reviewing clinically significant genomic variants
Title | Skyhawk: an artificial neural network-based discriminator for reviewing clinically significant genomic variants |
---|---|
Authors | |
Keywords | ANN Artificial neural network Clinical decision support Third-generation sequencing Variant calling |
Issue Date | 2021 |
Publisher | Inderscience Publishers. The Journal's web site is located at https://www.inderscience.com/jhome.php?jcode=ijcbdd |
Citation | International Journal of Computational Biology and Drug Design, 2021, v. 13 n. 5-6, p. 431-437 How to Cite? |
Abstract | Genome sequencing has become an important tool in clinical practice. However, variant interpretation remains the bottleneck and may take a specialist several hours of work per patient. On average, one-fifth of this time is spent on visually confirming the authenticity of the candidate variants. We developed Skyhawk, an artificial neural network (ANN)-based discriminator that mimics the process of expert review on clinically significant genomics variants. Skyhawk runs in less than 1 min to review 10,000 variants, and about 30 min to review all variants in a typical whole-genome sequencing sample. Among the false positive singletons identified by GATK HaplotypeCaller, UnifiedGenotyper and 16GT in the HG005 GIAB sample, 79.7% were rejected by Skyhawk. Worked on the variants with unknown significance (VUS), Skyhawk marked most of the false positive variants for manual review and most of the true positive variants no need for review. Skyhawk is freely available at https://github.com/aquaskyline/Skyhawk. |
Persistent Identifier | http://hdl.handle.net/10722/301330 |
ISSN | 2023 SCImago Journal Rankings: 0.120 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Luo, R | - |
dc.contributor.author | Lam, TW | - |
dc.contributor.author | Schatz, MC | - |
dc.date.accessioned | 2021-07-27T08:09:30Z | - |
dc.date.available | 2021-07-27T08:09:30Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | International Journal of Computational Biology and Drug Design, 2021, v. 13 n. 5-6, p. 431-437 | - |
dc.identifier.issn | 1756-0756 | - |
dc.identifier.uri | http://hdl.handle.net/10722/301330 | - |
dc.description.abstract | Genome sequencing has become an important tool in clinical practice. However, variant interpretation remains the bottleneck and may take a specialist several hours of work per patient. On average, one-fifth of this time is spent on visually confirming the authenticity of the candidate variants. We developed Skyhawk, an artificial neural network (ANN)-based discriminator that mimics the process of expert review on clinically significant genomics variants. Skyhawk runs in less than 1 min to review 10,000 variants, and about 30 min to review all variants in a typical whole-genome sequencing sample. Among the false positive singletons identified by GATK HaplotypeCaller, UnifiedGenotyper and 16GT in the HG005 GIAB sample, 79.7% were rejected by Skyhawk. Worked on the variants with unknown significance (VUS), Skyhawk marked most of the false positive variants for manual review and most of the true positive variants no need for review. Skyhawk is freely available at https://github.com/aquaskyline/Skyhawk. | - |
dc.language | eng | - |
dc.publisher | Inderscience Publishers. The Journal's web site is located at https://www.inderscience.com/jhome.php?jcode=ijcbdd | - |
dc.relation.ispartof | International Journal of Computational Biology and Drug Design | - |
dc.rights | International Journal of Computational Biology and Drug Design. Copyright © Inderscience Publishers. | - |
dc.subject | ANN | - |
dc.subject | Artificial neural network | - |
dc.subject | Clinical decision support | - |
dc.subject | Third-generation sequencing | - |
dc.subject | Variant calling | - |
dc.title | Skyhawk: an artificial neural network-based discriminator for reviewing clinically significant genomic variants | - |
dc.type | Article | - |
dc.identifier.email | Luo, R: rbluo@cs.hku.hk | - |
dc.identifier.email | Lam, TW: twlam@cs.hku.hk | - |
dc.identifier.authority | Luo, R=rp02360 | - |
dc.identifier.authority | Lam, TW=rp00135 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1504/IJCBDD.2020.113818 | - |
dc.identifier.scopus | eid_2-s2.0-85103589029 | - |
dc.identifier.hkuros | 323496 | - |
dc.identifier.volume | 13 | - |
dc.identifier.issue | 5-6 | - |
dc.identifier.spage | 431 | - |
dc.identifier.epage | 437 | - |
dc.publisher.place | United Kingdom | - |