Felix Heinrich, Thomas Martin Lange, Magdalena Kircher, Faisal Ramzan, Armin Otto Schmitt, Mehmet Gültas
{"title":"探索增量特征选择提高基因组预测准确性的潜力","authors":"Felix Heinrich, Thomas Martin Lange, Magdalena Kircher, Faisal Ramzan, Armin Otto Schmitt, Mehmet Gültas","doi":"10.1186/s12711-023-00853-8","DOIUrl":null,"url":null,"abstract":"The ever-increasing availability of high-density genomic markers in the form of single nucleotide polymorphisms (SNPs) enables genomic prediction, i.e. the inference of phenotypes based solely on genomic data, in the field of animal and plant breeding, where it has become an important tool. However, given the limited number of individuals, the abundance of variables (SNPs) can reduce the accuracy of prediction models due to overfitting or irrelevant SNPs. Feature selection can help to reduce the number of irrelevant SNPs and increase the model performance. In this study, we investigated an incremental feature selection approach based on ranking the SNPs according to the results of a genome-wide association study that we combined with random forest as a prediction model, and we applied it on several animal and plant datasets. Applying our approach to different datasets yielded a wide range of outcomes, i.e. from a substantial increase in prediction accuracy in a few cases to minor improvements when only a fraction of the available SNPs were used. Compared with models using all available SNPs, our approach was able to achieve comparable performances with a considerably reduced number of SNPs in several cases. Our approach showcased state-of-the-art efficiency and performance while having a faster computation time. The results of our study suggest that our incremental feature selection approach has the potential to improve prediction accuracy substantially. However, this gain seems to depend on the genomic data used. Even for datasets where the number of markers is smaller than the number of individuals, feature selection may still increase the performance of the genomic prediction. Our approach is implemented in R and is available at https://github.com/FelixHeinrich/GP_with_IFS/ .","PeriodicalId":55120,"journal":{"name":"Genetics Selection Evolution","volume":null,"pages":null},"PeriodicalIF":3.6000,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Exploring the potential of incremental feature selection to improve genomic prediction accuracy\",\"authors\":\"Felix Heinrich, Thomas Martin Lange, Magdalena Kircher, Faisal Ramzan, Armin Otto Schmitt, Mehmet Gültas\",\"doi\":\"10.1186/s12711-023-00853-8\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The ever-increasing availability of high-density genomic markers in the form of single nucleotide polymorphisms (SNPs) enables genomic prediction, i.e. the inference of phenotypes based solely on genomic data, in the field of animal and plant breeding, where it has become an important tool. However, given the limited number of individuals, the abundance of variables (SNPs) can reduce the accuracy of prediction models due to overfitting or irrelevant SNPs. Feature selection can help to reduce the number of irrelevant SNPs and increase the model performance. In this study, we investigated an incremental feature selection approach based on ranking the SNPs according to the results of a genome-wide association study that we combined with random forest as a prediction model, and we applied it on several animal and plant datasets. Applying our approach to different datasets yielded a wide range of outcomes, i.e. from a substantial increase in prediction accuracy in a few cases to minor improvements when only a fraction of the available SNPs were used. Compared with models using all available SNPs, our approach was able to achieve comparable performances with a considerably reduced number of SNPs in several cases. Our approach showcased state-of-the-art efficiency and performance while having a faster computation time. The results of our study suggest that our incremental feature selection approach has the potential to improve prediction accuracy substantially. However, this gain seems to depend on the genomic data used. Even for datasets where the number of markers is smaller than the number of individuals, feature selection may still increase the performance of the genomic prediction. Our approach is implemented in R and is available at https://github.com/FelixHeinrich/GP_with_IFS/ .\",\"PeriodicalId\":55120,\"journal\":{\"name\":\"Genetics Selection Evolution\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2023-11-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Genetics Selection Evolution\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1186/s12711-023-00853-8\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURE, DAIRY & ANIMAL SCIENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Genetics Selection Evolution","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s12711-023-00853-8","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, DAIRY & ANIMAL SCIENCE","Score":null,"Total":0}
Exploring the potential of incremental feature selection to improve genomic prediction accuracy
The ever-increasing availability of high-density genomic markers in the form of single nucleotide polymorphisms (SNPs) enables genomic prediction, i.e. the inference of phenotypes based solely on genomic data, in the field of animal and plant breeding, where it has become an important tool. However, given the limited number of individuals, the abundance of variables (SNPs) can reduce the accuracy of prediction models due to overfitting or irrelevant SNPs. Feature selection can help to reduce the number of irrelevant SNPs and increase the model performance. In this study, we investigated an incremental feature selection approach based on ranking the SNPs according to the results of a genome-wide association study that we combined with random forest as a prediction model, and we applied it on several animal and plant datasets. Applying our approach to different datasets yielded a wide range of outcomes, i.e. from a substantial increase in prediction accuracy in a few cases to minor improvements when only a fraction of the available SNPs were used. Compared with models using all available SNPs, our approach was able to achieve comparable performances with a considerably reduced number of SNPs in several cases. Our approach showcased state-of-the-art efficiency and performance while having a faster computation time. The results of our study suggest that our incremental feature selection approach has the potential to improve prediction accuracy substantially. However, this gain seems to depend on the genomic data used. Even for datasets where the number of markers is smaller than the number of individuals, feature selection may still increase the performance of the genomic prediction. Our approach is implemented in R and is available at https://github.com/FelixHeinrich/GP_with_IFS/ .
期刊介绍:
Genetics Selection Evolution invites basic, applied and methodological content that will aid the current understanding and the utilization of genetic variability in domestic animal species. Although the focus is on domestic animal species, research on other species is invited if it contributes to the understanding of the use of genetic variability in domestic animals. Genetics Selection Evolution publishes results from all levels of study, from the gene to the quantitative trait, from the individual to the population, the breed or the species. Contributions concerning both the biological approach, from molecular genetics to quantitative genetics, as well as the mathematical approach, from population genetics to statistics, are welcome. Specific areas of interest include but are not limited to: gene and QTL identification, mapping and characterization, analysis of new phenotypes, high-throughput SNP data analysis, functional genomics, cytogenetics, genetic diversity of populations and breeds, genetic evaluation, applied and experimental selection, genomic selection, selection efficiency, and statistical methodology for the genetic analysis of phenotypes with quantitative and mixed inheritance.