Choosing SNPs using feature selection

Phương, Từ Minh; Lin, Zhen; Altman, Russ B.

doi:10.1109/csb.2005.22

Cited by 80 publications

(35 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The identification of markers related to this phenotype using FS is based on these techniques to provide an interpretable model due to the close relation between trait and genotype; i.e., using the subset of high-density markers might help elucidate the regions most likely to be involved in phenotypic differentiation 120 . This strategy of selecting a subgroup of SNPs with higher predictive power and closeness to the predictive class has already been employed in different contexts 48,121,122 . In this study, we tested five different strategies and found three promising alternatives for executing this methodology.…”

Section: Discussionmentioning

confidence: 99%

Machine learning approaches reveal genomic regions associated with sugarcane brown rust resistance

Aono

Costa

Rody

et al. 2020

Preprint

View full text Add to dashboard Cite

Sugarcane is an economically important crop, but its genomic complexity has hindered advances in molecular approaches for genetic breeding. New cultivars are released based on the identification of interesting traits, and for sugarcane, brown rust resistance is a desirable characteristic due to the large economic impact of the disease. Although marker-assisted selection for rust resistance has been successful, the genes involved are still unknown, and the associated regions vary among cultivars, thus restricting methodological generalization. We used genotyping by sequencing of full-sib progeny to relate genomic regions with brown rust phenotypes. We established a pipeline to identify reliable SNPs in complex polyploid data, which were used for phenotypic prediction via machine learning. We identified 14,540 SNPs, which led to a mean prediction accuracy of 50% by using different models. We also tested feature selection algorithms to increase predictive accuracy, resulting in a reduced dataset with more explanatory power for rust phenotypes. Using different feature selection techniques, we achieved accuracy of up to 95% with a dataset of 131 SNPs related to brown rust QTL regions and auxiliary genes. Therefore, our novel strategy has the potential to assist studies of the genomic organization of brown rust resistance in sugarcane. 3/154/15 10/15

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning approaches reveal genomic regions associated with sugarcane brown rust resistance

Aono

Costa

Rody

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…These characteristics include the genome distribution (that is, whether SNPs are evenly spaced across the genome), the MAF (that is, whether SNPs are segregating within the population) and the LD pattern between SNPs. Methods that combine these attributes, such as the Wellman SNP selection method (Wellman et al, 2013), and methods that incorporate machine-learning algorithms, such as feature similarity (Phuong et al, 2006), have been used to select informative SNPs for Irish cattle (Judge et al, 2016). Wu et al (2016) also developed a multi-objective local optimization (MOLO) method for SNP selection, which uses a function that adjusts for gaps in the genomic data and incorporates Shannon entropy and other attributes, such as MAF and distribution, to select optimal SNPs.…”

Section: Cost-effective Genomic Selectionmentioning

confidence: 99%

Genotype imputation as a cost-saving genomic strategy for South African Sanga cattle: A review

Lashmar¹,

Muchadeyi²,

Visser³

2019

SA J. An. Sci.

View full text Add to dashboard Cite

The South African beef cattle population is heterogeneous and consists of a variety of breeds, production systems and breeding goals. Indigenous cattle breeds are uniquely adapted to their native surroundings, necessitating conservation of these breeds as usable genetic resources to sustain efficient production of beef. Current projections indicate positive growth in human population size, with parallel growth in nutritional demand, in the midst of intensifying environmental conditions. Sanga cattle, therefore, are invaluable assets to the South African beef industry. Modern genomic methodologies allow for an extensive insight into the genome architecture of local breeds. The evolution of these methodologies has also provided opportunities to incorporate deoxyribonucleic acid (DNA) information into breed improvement programs in the form of genomic selection (GS). Certain challenges, such as the high cost of generating adequate numbers of dense genotypic profiles and the introduction of ascertainment bias when non-commercial breeds are genotyped with commercial single nucleotide polymorphism (SNP) panels, have caused a lag in progress on the genomics front in South Africa. Genotype imputation is a statistical method that infers unavailable or missing genotypic data based on shared haplotypes within a population using a population or breed representative reference sample. Genotypes are generated in silico, providing an animal with genotypic information for SNP markers that were not genotyped, based on predictive model-based algorithms. The validation of this method for indigenous breeds will enable the development of cost-effective low-density bead chips, allowing more animals to be genotyped, and imputation to high-density information. The improvement in SNP densities, at lower cost, will allow enhanced power in genome-wide association studies (GWAS) and genomic estimated breeding value (GEBV)-based selection for these breeds. To fully reap the benefits of this methodology, however, will require the setting up of accurate and reliable frameworks that are optimized for its application in Sanga breeds. This review paper aims, first, to identify the challenges that have been impeding genomic applications for Sanga cattle and second, to outline the advantages that a method such as genotype imputation might provide.

show abstract

“…Lin and Altman [61] investigated methods for tag SNPs selection by use of principal components analysis (PCA). Phuong et al [62] regarded the SNPs as features and the haplotypes as learning instances. They adopted a feature selection algorithm to select tag SNPs efficiently.…”

Section: Minimum Tag Snps Selection According To Other Criteriamentioning

confidence: 99%

An overview of the haplotype problems and algorithms

Zhao

Zhang

et al. 2007

Front. Comput. Sc. China

View full text Add to dashboard Cite

A single nucleotide polymorphism (SNP), as the most common form of genetic variation, has been widely studied to help analyze the possible association between diseases and genomes. To gain more information, SNPs on a single chromosome are usually studied together, which constitute a haplotype. Gaining haplotypes from biological experiments is usually very costly and timeconsuming, which causes people to develop efficient methods to determine haplotypes from the computational angle. Many problems and algorithms about haplotypes have been proposed to reduce the cost of studies of disease association. In general, four categories of problems are widely researched: the haplotype assembly problem, the haplotype inference problem, the haplotype block partition problem, and the haplotype tagging SNP selection problem. The former two problems have been well reviewed by many researchers, whereas the latter two have not been comprehensively surveyed to our knowledge. In this paper, we try to make a detailed introduction to the four problems, especially the latter two.

show abstract

Choosing SNPs using feature selection

Cited by 80 publications

References 25 publications

Machine learning approaches reveal genomic regions associated with sugarcane brown rust resistance

Machine learning approaches reveal genomic regions associated with sugarcane brown rust resistance

Genotype imputation as a cost-saving genomic strategy for South African Sanga cattle: A review

An overview of the haplotype problems and algorithms

Contact Info

Product

Resources

About