How Machine Learning Methods Helped Find Putative Rye Wax Genes Among GBS Data.

The standard approach to genetic mapping was supplemented by machine learning (ML) to establish the location of the rye gene associated with epicuticular wax formation (glaucous phenotype). Over 180 plants of the biparental F2 population were genotyped with the DArTseq (sequencing-based diversity array technology). A maximum likelihood (MLH) algorithm (JoinMap 5.0) and three ML algorithms: logistic regression (LR), random forest and extreme gradient boosted trees (XGBoost), were used to select markers closely linked to the gene encoding wax layer. The allele conditioning the nonglaucous appearance of plants, derived from the cultivar Karlikovaja Zelenostebelnaja, was mapped at the chromosome 2R, which is the first report on this localization. The DNA sequence of DArT-Silico 3585843, closely linked to wax segregation detected by using ML methods, was indicated as one of the candidates controlling the studied trait. The putative gene encodes the ABCG11 transporter.

Putative candidate genes responsible for leaf rolling in rye (Secale cereale L.).

BACKGROUND: Rolling of leaves (RL) is a phenomenon commonly found in grasses. Morphology of the leaf is an important agronomic trait in field crops especially in rice; therefore, majority of the rice breeders are interested in RL. There are only few studies with respect to RL of wheat and barley; however, the information regarding the genetic base of RL with respect to the shape of leaf in rye is lacking. To the best of our knowledge, this is the first study on the localization of loci controlling RL on high density consensus genetic map of rye. RESULTS: Genotypic analysis led to the identification of 43 quantitative trait loci (QTLs) for RL, grouped into 28 intervals, which confirms the multigenic base of the trait stated for wheat and rice. Four stable QTLs were located on chromosomes 3R, 5R, and 7R. Co-localization of QTL for RL and for different morphological, biochemical and physiological traits may suggests pleiotropic effects of some QTLs. QTLs for RL were associated with QTLs for such morphological traits as: grain number and weight, spike number per plant, compactness of spike, and plant height. Two QTLs for RL were found to coincide with QTLs for drought tolerance (4R, 7R), two with QTLs for heading earliness (2R, 7R), one with α-amylase activity QTL (7R) and three for pre-harvest sprouting QTL (1R, 4R, 7R). The set of molecular markers strongly linked to RL was selected, and the putative candidate genes controlling the process of RL were identified. Twelve QTLs are considered as linked to candidate genes on the base of DArT sequences alignment, which is a new information for rye. CONCLUSIONS: Our results expand the knowledge about the network of QTLs for different morphological, biochemical and physiological traits and can be a starting point to studies on particular genes controlling RL and other important agronomic traits (yield, earliness, pre-harvest sprouting, reaction to water deficit) and to appoint markers useful in marker assisted selection (MAS). A better knowledge of the rye genome and genes could both facilitate rye improvement itself and increase the efficiency of utilizing rye genes in wheat breeding.