Dataset Information

A Pipeline for Classifying Deleterious Coding Mutations in Agricultural Plants.

ABSTRACT: The impact of deleterious variation on both plant fitness and crop productivity is not completely understood and is a hot topic of debates. The deleterious mutations in plants have been solely predicted using sequence conservation methods rather than function-based classifiers due to lack of well-annotated mutational datasets in these organisms. Here, we developed a machine learning classifier based on a dataset of deleterious and neutral mutations in Arabidopsis thaliana by extracting 18 informative features that discriminate deleterious mutations from neutral, including 9 novel features not used in previous studies. We examined linear SVM, Gaussian SVM, and Random Forest classifiers, with the latter performing best. Random Forest classifiers exhibited a markedly higher accuracy than the popular PolyPhen-2 tool in the Arabidopsis dataset. Additionally, we tested whether the Random Forest, trained on the Arabidopsis dataset, accurately predicts deleterious mutations in Orýza sativa and Pisum sativum and observed satisfactory levels of performance accuracy (87% and 93%, respectively) higher than obtained by the PolyPhen-2. Application of Transfer learning in classifiers did not improve their performance. To additionally test the performance of the Random Forest classifier across different angiosperm species, we applied it to annotate deleterious mutations in Cicer arietinum and validated them using population frequency data. Overall, we devised a classifier with the potential to improve the annotation of putative functional mutations in QTL and GWAS hit regions, as well as for the evolutionary analysis of proliferation of deleterious mutations during plant domestication; thus optimizing breeding improvement and development of new cultivars.

SUBMITTER: Kovalev MS

PROVIDER: S-EPMC6279870 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Pipeline for Classifying Deleterious Coding Mutations in Agricultural Plants.

Kovalev Maxim S MS Igolkina Anna A AA Samsonova Maria G MG Nuzhdin Sergey V SV

Frontiers in plant science 20181128

The impact of deleterious variation on both plant fitness and crop productivity is not completely understood and is a hot topic of debates. The deleterious mutations in plants have been solely predicted using sequence conservation methods rather than function-based classifiers due to lack of well-annotated mutational datasets in these organisms. Here, we developed a machine learning classifier based on a dataset of deleterious and neutral mutations in <i>Arabidopsis thaliana</i> by extracting 18 ...[more]

PMID: 30546376

Similar Datasets

Project description:In Montbéliarde cattle two candidate mutations on bovine chromosomes 19 and 29 responsible for embryonic lethality have been detected. Montbéliarde bulls have been introduced into Vorderwald cattle to improve milk and fattening performance. Due to the small population size of Vorderwald cattle and the wide use of a few Montbéliarde bulls through artificial insemination, inbreeding on Montbéliarde bulls in later generations was increasing. Therefore, we genotyped an aborted fetus which was inbred on Montbéliarde as well as Vorderwald x Montbéliarde crossbred bulls for both deleterious mutations. The abortion was observed in an experimental herd of Vorderwald cattle. The objectives of the present study were to prove if one or both lethal mutations may be assumed to have caused this abortion and to show whether these deleterious mutations have been introduced into the Vorderwald cattle population through Montbéliarde bulls. The aborted fetus was homozygous for the SLC37A2:g.28879810C>T mutation (ss2019324563) on BTA29 and both parents as well as the paternal and maternal grandsire were heterozygous for this mutation. In addition, the parents and the paternal grandsire were carriers of the MH2-haplotype linked with the T-allele of the SLC37A2:g.28879810C>T mutation. For the SHBG:g.27956790C>T mutation (rs38377500) on BTA19 (MH1), the aborted fetus and its sire were heterozygous. Among all further 341 Vorderwald cattle genotyped we found 27 SLC37A2:g.28879810C>T heterozygous animals resulting in an allele frequency of 0.0396. Among the 120 male Vorderwald cattle, there were 12 heterozygous with an allele frequency of 0.05. The SLC37A2:g.28879810C>T mutation could not be found in further nine cattle breeds nor in Vorderwald cattle with contributions from Ayrshire bulls. In 69 Vorderwald cattle without genes from Montbéliarde bulls the mutated allele of SLC37A2:g.28879810C>T could not be detected. The SHBG:g.27956790C>T mutation appeared unlikely to be responsible for the present case of abortion and, in addition, we observed this mutation in a homozygous state in a living animal. In conclusion, we could demonstrate the first case of an aborted fetus carrying the deleterious SLC37A2:g.28879810C>T mutation homozygous and show that this deleterious mutation had been introduced through Montbéliarde bulls into Vorderwald cattle.

Dataset Information

A Pipeline for Classifying Deleterious Coding Mutations in Agricultural Plants.

Publications

A Pipeline for Classifying Deleterious Coding Mutations in Agricultural Plants.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets