Machine Learning Based Classification of Microsatellite Variation: An Effective Approach for Phylogeographic Characterization of Olive Populations

Abstract

Finding efficient analytical techniques is overwhelmingly turning into a bottleneck for the effectiveness of large biological data. Machine learning offers a novel and powerful tool to advance classification and modeling solutions in molecular biology. However, these methods have been less frequently used with empirical population genetics data. In this study, we developed a new combined approach of data analysis using microsatellite marker data from our previous studies of olive populations using machine learning algorithms. Herein, 267 olive accessions of various origins including 21 reference cultivars, 132 local ecotypes, and 37 wild olive specimens from the Iranian plateau, together with 77 of the most represented Mediterranean varieties were investigated using a finely selected panel of 11 microsatellite markers. We organized data in two ‘4-targeted’ and ‘16-targeted’ experiments. A strategy of assaying different machine based analyses (i.e. data cleaning, feature selection, and machine learning classification) was devised to identify the most informative loci and the most diagnostic alleles to represent the population and the geography of each olive accession. These analyses revealed microsatellite markers with the highest differentiating capacity and proved efficiency for our method of clustering olive accessions to reflect upon their regions of origin. A distinguished highlight of this study was the discovery of the best combination of markers for better differentiating of populations via machine learning models, which can be exploited to distinguish among other biological populations.

A large-scale study of indicators of sub-clinical mastitis in dairy cattle by attribute weighting analysis of milk composition features: highlighting the predictive power of lactose and electrical conductivity

“…Data mining, also known as knowledge discovery, is a relatively new technique to extract useful knowledge from data (compared to traditional multivariate analysis) (Shekoofa et al 2014). The main strength of data mining resides in its ability to handle large data sets and to extract meaningful and easy-to-understand results, which is usually impossible by human calculations (Torkzaban et al 2015). A few studies have looked into this field to improve early detection techniques by novel data mining tools (Sharifi et al 2018).…”

Development, evaluation, and validation of new EST-SSR markers in olive (Olea europaea L.)

“…In the last decades, the development of more effective molecular markers has been promoted for genotyping purposes in several fruit crop species (Guo et al 2014;Jiao et al 2014;Sun et al 2015), and especially for the olive (Biton et al 2015;Dominguez-Garcia et al 2012;Kaya et al 2013;Torkzaban et al 2015). Despite the availability of a large set of molecular tools, olive fingerprinting still remains a difficult task, mainly due to the several weaknesses of most widely used markers (Bracci et al 2011) that include the lack of sequence information, the difficulties in distinguishing among alleles, and the impossibility to share data among labs.…”

Chemometrical and molecular methods in olive oil analysis: A review

“…Torkzaban et al () analyzed with a carefully selected group of 11 microsatellite markers 267 olive tree genotypes including reference cultivars, local ecotypes and wild olives from Iran as well as some widely employed Mediterranean varieties. As a first step, Torkzaban et al () conducted a feature selection in order to identify significant variables in the multidimensional data. For that they assessed a series of attribute weighting algorithms while searching for the most indicative predictor attributes (SSR marker alleles).…”

“…The method Naive Bayes based on Bayes conditional probability rule is used for performing classification tasks. It was perfectly performed (90.98% correct classifications) in the application of phylogeographic characterization of olive tree populations in Iran on the basis of SSR markers (Torkzaban et al, ). The method operated in preprocessed data which were cleaned and subjected to selection of the most diagnostic alleles.…”

“…Such approaches are only now starting to be employed with empirical population genetics data. Torkzaban et al () analyzed with a carefully selected group of 11 microsatellite markers 267 olive tree genotypes including reference cultivars, local ecotypes and wild olives from Iran as well as some widely employed Mediterranean varieties. As a first step, Torkzaban et al () conducted a feature selection in order to identify significant variables in the multidimensional data.…”