Cargando…
Decoding the effects of synonymous variants
Synonymous single nucleotide variants (sSNVs) are common in the human genome but are often overlooked. However, sSNVs can have significant biological impact and may lead to disease. Existing computational methods for evaluating the effect of sSNVs suffer from the lack of gold-standard training/evalu...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8682775/ https://www.ncbi.nlm.nih.gov/pubmed/34850938 http://dx.doi.org/10.1093/nar/gkab1159 |
_version_ | 1784617294655127552 |
---|---|
author | Zeng, Zishuo Aptekmann, Ariel A Bromberg, Yana |
author_facet | Zeng, Zishuo Aptekmann, Ariel A Bromberg, Yana |
author_sort | Zeng, Zishuo |
collection | PubMed |
description | Synonymous single nucleotide variants (sSNVs) are common in the human genome but are often overlooked. However, sSNVs can have significant biological impact and may lead to disease. Existing computational methods for evaluating the effect of sSNVs suffer from the lack of gold-standard training/evaluation data and exhibit over-reliance on sequence conservation signals. We developed synVep (synonymous Variant effect predictor), a machine learning-based method that overcomes both of these limitations. Our training data was a combination of variants reported by gnomAD (observed) and those unreported, but possible in the human genome (generated). We used positive-unlabeled learning to purify the generated variant set of any likely unobservable variants. We then trained two sequential extreme gradient boosting models to identify subsets of the remaining variants putatively enriched and depleted in effect. Our method attained 90% precision/recall on a previously unseen set of variants. Furthermore, although synVep does not explicitly use conservation, its scores correlated with evolutionary distances between orthologs in cross-species variation analysis. synVep was also able to differentiate pathogenic vs. benign variants, as well as splice-site disrupting variants (SDV) vs. non-SDVs. Thus, synVep provides an important improvement in annotation of sSNVs, allowing users to focus on variants that most likely harbor effects. |
format | Online Article Text |
id | pubmed-8682775 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-86827752021-12-20 Decoding the effects of synonymous variants Zeng, Zishuo Aptekmann, Ariel A Bromberg, Yana Nucleic Acids Res Computational Biology Synonymous single nucleotide variants (sSNVs) are common in the human genome but are often overlooked. However, sSNVs can have significant biological impact and may lead to disease. Existing computational methods for evaluating the effect of sSNVs suffer from the lack of gold-standard training/evaluation data and exhibit over-reliance on sequence conservation signals. We developed synVep (synonymous Variant effect predictor), a machine learning-based method that overcomes both of these limitations. Our training data was a combination of variants reported by gnomAD (observed) and those unreported, but possible in the human genome (generated). We used positive-unlabeled learning to purify the generated variant set of any likely unobservable variants. We then trained two sequential extreme gradient boosting models to identify subsets of the remaining variants putatively enriched and depleted in effect. Our method attained 90% precision/recall on a previously unseen set of variants. Furthermore, although synVep does not explicitly use conservation, its scores correlated with evolutionary distances between orthologs in cross-species variation analysis. synVep was also able to differentiate pathogenic vs. benign variants, as well as splice-site disrupting variants (SDV) vs. non-SDVs. Thus, synVep provides an important improvement in annotation of sSNVs, allowing users to focus on variants that most likely harbor effects. Oxford University Press 2021-11-30 /pmc/articles/PMC8682775/ /pubmed/34850938 http://dx.doi.org/10.1093/nar/gkab1159 Text en © The Author(s) 2021. Published by Oxford University Press on behalf of Nucleic Acids Research. https://creativecommons.org/licenses/by/4.0/This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Computational Biology Zeng, Zishuo Aptekmann, Ariel A Bromberg, Yana Decoding the effects of synonymous variants |
title | Decoding the effects of synonymous variants |
title_full | Decoding the effects of synonymous variants |
title_fullStr | Decoding the effects of synonymous variants |
title_full_unstemmed | Decoding the effects of synonymous variants |
title_short | Decoding the effects of synonymous variants |
title_sort | decoding the effects of synonymous variants |
topic | Computational Biology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8682775/ https://www.ncbi.nlm.nih.gov/pubmed/34850938 http://dx.doi.org/10.1093/nar/gkab1159 |
work_keys_str_mv | AT zengzishuo decodingtheeffectsofsynonymousvariants AT aptekmannariela decodingtheeffectsofsynonymousvariants AT brombergyana decodingtheeffectsofsynonymousvariants |