Predicting variant deleteriousness in non-human species: applying the CADD approach in mouse
Abstract Background Predicting the deleteriousness of observed genomic variants has taken a step forward with the introduction of the Combined Annotation Dependent Depletion (CADD) approach, which trains a classifier on the wealth of available human genomic information. This raises the question whet...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2018-10-01
|
Series: | BMC Bioinformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12859-018-2337-5 |
_version_ | 1811273906051350528 |
---|---|
author | Christian Groß Dick de Ridder Marcel Reinders |
author_facet | Christian Groß Dick de Ridder Marcel Reinders |
author_sort | Christian Groß |
collection | DOAJ |
description | Abstract Background Predicting the deleteriousness of observed genomic variants has taken a step forward with the introduction of the Combined Annotation Dependent Depletion (CADD) approach, which trains a classifier on the wealth of available human genomic information. This raises the question whether it can be done with less data for non-human species. Here, we investigate the prerequisites to construct a CADD-based model for a non-human species. Results Performance of the mouse model is competitive with that of the human CADD model and better than established methods like PhastCons conservation scores and SIFT. Like in the human case, performance varies for different genomic regions and is best for coding regions. We also show the benefits of generating a species-specific model over lifting variants to a different species or applying a generic model. With fewer genomic annotations, performance on the test set as well as on the three validation sets is still good. Conclusions It is feasible to construct species-specific CADD models even when annotations such as epigenetic markers are not available. The minimal requirement for these models is the availability of a set of genomes of closely related species that can be used to infer an ancestor genome and substitution rates for the data generation. |
first_indexed | 2024-04-12T23:08:02Z |
format | Article |
id | doaj.art-76a63ace48834db182ae8707dae12f2d |
institution | Directory Open Access Journal |
issn | 1471-2105 |
language | English |
last_indexed | 2024-04-12T23:08:02Z |
publishDate | 2018-10-01 |
publisher | BMC |
record_format | Article |
series | BMC Bioinformatics |
spelling | doaj.art-76a63ace48834db182ae8707dae12f2d2022-12-22T03:12:52ZengBMCBMC Bioinformatics1471-21052018-10-0119111010.1186/s12859-018-2337-5Predicting variant deleteriousness in non-human species: applying the CADD approach in mouseChristian Groß0Dick de Ridder1Marcel Reinders2Delft Bioinformatics Lab, University of Technology DelftBioinformatics Group, Wageningen University & ResearchDelft Bioinformatics Lab, University of Technology DelftAbstract Background Predicting the deleteriousness of observed genomic variants has taken a step forward with the introduction of the Combined Annotation Dependent Depletion (CADD) approach, which trains a classifier on the wealth of available human genomic information. This raises the question whether it can be done with less data for non-human species. Here, we investigate the prerequisites to construct a CADD-based model for a non-human species. Results Performance of the mouse model is competitive with that of the human CADD model and better than established methods like PhastCons conservation scores and SIFT. Like in the human case, performance varies for different genomic regions and is best for coding regions. We also show the benefits of generating a species-specific model over lifting variants to a different species or applying a generic model. With fewer genomic annotations, performance on the test set as well as on the three validation sets is still good. Conclusions It is feasible to construct species-specific CADD models even when annotations such as epigenetic markers are not available. The minimal requirement for these models is the availability of a set of genomes of closely related species that can be used to infer an ancestor genome and substitution rates for the data generation.http://link.springer.com/article/10.1186/s12859-018-2337-5GenomicsGenome annotationVariant annotationSequence annotationMouse genetics |
spellingShingle | Christian Groß Dick de Ridder Marcel Reinders Predicting variant deleteriousness in non-human species: applying the CADD approach in mouse BMC Bioinformatics Genomics Genome annotation Variant annotation Sequence annotation Mouse genetics |
title | Predicting variant deleteriousness in non-human species: applying the CADD approach in mouse |
title_full | Predicting variant deleteriousness in non-human species: applying the CADD approach in mouse |
title_fullStr | Predicting variant deleteriousness in non-human species: applying the CADD approach in mouse |
title_full_unstemmed | Predicting variant deleteriousness in non-human species: applying the CADD approach in mouse |
title_short | Predicting variant deleteriousness in non-human species: applying the CADD approach in mouse |
title_sort | predicting variant deleteriousness in non human species applying the cadd approach in mouse |
topic | Genomics Genome annotation Variant annotation Sequence annotation Mouse genetics |
url | http://link.springer.com/article/10.1186/s12859-018-2337-5 |
work_keys_str_mv | AT christiangroß predictingvariantdeleteriousnessinnonhumanspeciesapplyingthecaddapproachinmouse AT dickderidder predictingvariantdeleteriousnessinnonhumanspeciesapplyingthecaddapproachinmouse AT marcelreinders predictingvariantdeleteriousnessinnonhumanspeciesapplyingthecaddapproachinmouse |