Support vector machine regression for the prediction of maize hybrid performance

Accurate prediction of the phenotypical performance of untested single-cross hybrids allows for a faster genetic progress of the breeding pool at a reduced cost. We propose a prediction method based on ɛ-insensitive support vector machine regression (ɛ-SVR). A brief overview of the theoretical background of this fairly new technique and the use of specific kernel functions based on commonly applied genetic similarity measures for dominant and co-dominant markers are presented. These different marker types can be integrated into a single regression model by means of simple kernel operations. Field trial data from the grain maize breeding programme of the private company RAGT R2n are used to assess the predictive capabilities of the proposed methodology. Prediction accuracies are compared to those of one of today’s best performing prediction methods based on best linear unbiased prediction. Results on our data indicate that both methods match each other’s prediction accuracies for several combinations of marker types and traits. The ɛ-SVR framework, however, allows for a greater flexibility in combining different kinds of predictor variables.     

Testcross additive and dominance effects in best linear unbiased prediction of maize single-cross performance

Best linear unbiased prediction (BLUP) has been found to be useful in maize (Zea mays L.) breeding. The advantage of including both testcross additive and dominance effects (Intralocus Model) in BLUP, rather than only testcross additive effects (Additive Model), has not been clearly demonstrated. The objective of this study was to compare the usefulness of Intralocus and Additive Models for BLUP of maize single-cross performance. Multilocation data from 1990 to 1995 were obtained from the hybrid testing program of Limagrain Genetics. Grain yield, moisture, stalk lodging, and root lodging of untested single crosses were predicted from (1) the performance of tested single crosses and (2) known genetic relationships among the parental inbreds. Correlations between predicted and observed performance were obtained with a delete-one cross-validation procedure. For the Intralocus Model, the correlations ranged from 0.50 to 0.66 for yield, 0.88 to 0.94 for moisture, 0.47 to 0.69 for stalk lodging, and 0.31 to 0.45 for root lodging. The BLUP procedure was consistently more effective with the Intralocus Model than with the Additive Model. When the Additive Model was used instead of the Intralocus Model, the reductions in the correlation were largest for root lodging (0.06–0.35), smallest for moisture (0.00–0.02), and intermediate for yield (0.02–0.06) and stalk lodging (0.02–0.08). The ratio of dominance variance (v _D) to total genetic variance (v _G) was highest for root lodging (0.47) and lowest for moisture (0.10). The Additive Model may be used if prior information indicates that V_D for a given trait has little contribution to V_G. Otherwise, the continued use of the Intralocus Model for BLUP of single-cross performance is recommended.     

Prediction of single-cross hybrid performance in maize using haplotype blocks associated with QTL for grain yield

Marker-based prediction of hybrid performance facilitates the identification of untested single-cross hybrids with superior yield performance. Our objectives were to (1) determine the haplotype block structure of experimental germplasm from a hybrid maize breeding program, (2) develop models for hybrid performance prediction based on haplotype blocks, and (3) compare hybrid performance prediction based on haplotype blocks with other approaches, based on single AFLP markers or general combining ability (GCA), under a validation scenario relevant for practical breeding. In total, 270 hybrids were evaluated for grain yield in four Dent × Flint factorial mating experiments. Their parental inbred lines were genotyped with 20 AFLP primer–enzyme combinations. Adjacent marker loci were combined into haplotype blocks. Hybrid performance was predicted on basis of single marker loci and haplotype blocks. Prediction based on variable haplotype block length resulted in an improved prediction of hybrid performance compared with the use of single AFLP markers. Estimates of prediction efficiency (R ² ) ranged from 0.305 to 0.889 for marker-based prediction and from 0.465 to 0.898 for GCA-based prediction. For inter-group hybrids with predominance of general over specific combining ability, the hybrid prediction from GCA effects was efficient in identifying promising hybrids. Considering the advantage of haplotype block approaches over single marker approaches for the prediction of inter-group hybrids, we see a high potential to substantially improve the efficiency of hybrid breeding programs. Tobias A. Schrag and Hans Peter Maurer contributed equally to this work.     

Relationship of restriction fragment length polymorphisms to single-cross hybrid performance of maize

Summary Isozymes and restriction fragment length polymorphisms (RFLPs) have been proposed for use in varietal identification and selection for agronomic traits. Although the use of isozymes for these purposes has been well documented, evaluation of the efficacy of RFLP technology as applied to crop improvement is far from complete. This investigation was conducted to study the relationship between RFLP-derived genotypes and heterotic patterns of a group of maize (Zea mays L.) inbred lines. A total of 22 inbreds was crossed to four testers (B73, B76, Mo17, and Va26) in combinations that minimized crossing within heterotic groups. Forty-seven single-cross progeny were subsequently evaluated for several agronomic traits (including grain yield and moisture, ear height, and root lodging) over 2–4 consecutive years at two to four Iowa locations in a randomized complete-block design. The inbred lines were subjected to RFLP analysis, which involved 47 genomic clones and the restriction enzymes EcoRI and HindIII. Hybrid RFLP patterns were predicted from their inbred parents. Modified Roger's distances were computed to estimate genetic distance among the inbred lines. Principal component analysis facilitated ascertainment of relative dispersion of the inbreds based on the frequency of variants at specific RFLP loci. Evident associations of variants with genes affecting agronomic traits were identified by principal component regression analysis, in which adjusted hybrid means were regressed on the matrix of hybrid variants frequencies. The hybrid means were adjusted by removing environmental effects, using residuals as dependent variables in the regression analysis. Results from this study suggest that RFLP analysis may be of value in allocating maize inbreds to heterotic groups, but no relationship between RFLP-based genetic distance and hybrid performance was apparent. Principal component regression identified variants potentially linked to genes that control specific agronomic traits.Joint contribution: USDA-ARS and Journal Paper No. J-13590 of the Iowa Agriculture and Home Economics Experiment Station, Ames, IA 50011, USA. Projects No. 2818 and 2778     

Genetic distance of inbred lines and prediction of maize single-cross performance using RAPD markers

 To evaluate the genetic diversity of 18 maize inbred lines, and to determine the correlation between genetic distance and single-cross hybrid performance, we have used random amplified polymorphic DNA (RAPD), a PCR-based technique. Eight of these lines came from a Thai synthetic population (BR-105), and the others derived from a Brazilian composite population (BR-106). Thirty two different primers were used giving a total of 325 reproducible amplification products, 262 of them being polymorphic. Genetic divergence was determinated using Jaccard’s similarity coefficient, and a final dendrogram was constructed using an unweighted pair-group method with arithmetical averages (UPGMA). Cluster analysis divided the samples into three distinct groups (GI, GII and GIII) that were confirmed by principal-coordinate analysis. The genetic distances (GD) were correlated with important agronomic traits for single-cross hybrids and heterosis. No correlation was found when group division was not considered, but significant correlations were detected between GI×GII and GI×GIII GDs with their respective single-cross hybrid grain-yield values. Three groups were identified; that is, the BR-106 population was divided in two different groups and the BR-105 population remained mostly as one group. The results indicated that RAPD can be used as a tool for determining the extent of genetic diversity among tropical maize inbred lines, for allocating genotypes into different groups, and also to aid in the choice of the superior crosses to be made among maize inbred lines, so reducing the number of crosses required under field evaluation. Received: 24 May 1996 / Accepted: 22 November 1996     

Prediction of maize double-cross hybrids using the best linear unbiased prediction with microsatellite marker information

We examined the usefulness of the best linear unbiased prediction associated with molecular markers for prediction of untested maize double-cross hybrids. Ten single-cross hybrids from different commercial backgrounds were crossed using a complete diallel design. These 10 single-cross hybrids were genotyped with 20 microsatellite markers. The best linear unbiased prediction associated with microsatellite information gave relatively good prediction ability of the double-cross hybrid performance, with correlations between observed phenotypic values and genotypic prediction values varying from 0.27 to 0.54. Taking into account the predictions of specific combing ability, the correlation between observed and predicted specific combining ability varied from 0.50 to 0.88. Based on these results, we infer that it is feasible to predict maize double-cross hybrids with different unbalance degrees without including any prior information about parental inbreed lines or single-cross hybrid performance.     

Prediction of single-cross hybrid performance for grain yield and grain dry matter content in maize using AFLP markers associated with QTL

Prediction methods to identify single-cross hybrids with superior yield performance have the potential to greatly improve the efficiency of commercial maize (Zea mays L.) hybrid breeding programs. Our objectives were to (1) identify marker loci associated with quantitative trait loci for hybrid performance or specific combining ability (SCA) in maize, (2) compare hybrid performance prediction by genotypic value estimates with that based on general combining ability (GCA) estimates, and (3) investigate a newly proposed combination of the GCA model with SCA predictions from genotypic value estimates. A total of 270 hybrids was evaluated for grain yield and grain dry matter content in four Dent × Flint factorial mating experiments, their parental inbred lines were genotyped with 20 AFLP primer-enzyme combinations. Markers associated significantly with hybrid performance and SCA were identified, genotypic values and SCA effects were estimated, and four hybrid performance prediction approaches were evaluated. For grain yield, between 38 and 98 significant markers were identified for hybrid performance and between zero and five for SCA. Estimates of prediction efficiency (R ²) ranged from 0.46 to 0.86 for grain yield and from 0.59 to 0.96 for grain dry matter content. Models enhancing the GCA approach with SCA estimates resulted in the highest prediction efficiency if the SCA to GCA ratio was high. We conclude that it is advantageous for prediction of single-cross hybrids to enhance a GCA-based model with SCA effects estimated from molecular marker data, if SCA variances are of similar or larger importance as GCA variances.     

Prediction of biological activity of Aurora-A kinase inhibitors by multilinear regression analysis and support vector machine

Several QSAR (quantitative structure-activity relationships) models for predicting the inhibitory activity of 117 Aurora-A kinase inhibitors were developed. The whole dataset was split into a training set and a test set based on two different methods, (1) by a random selection; and (2) on the basis of a Kohonen’s self-organizing map (SOM). Then the inhibitory activity of 117 Aurora-A kinase inhibitors was predicted using multilinear regression (MLR) analysis and support vector machine (SVM) methods, respectively. For the two MLR models and the two SVM models, for the test sets, the correlation coefficients of over 0.92 were achieved.     

Prediction of protein accessible surface areas by support vector regression

A novel support vector regression (SVR) approach is proposed to predict protein accessible surface areas (ASAs) from their primary structures. In this work, we predict the real values of ASA in squared angstroms for residues instead of relative solvent accessibility. Based on protein residues, the mean and median absolute errors are 26.0 A(2) and 18.87 A(2), respectively. The correlation coefficient between the predicted and observed ASAs is 0.66. Cysteine is the best predicted amino acid (mean absolute error is 13.8 A(2) and median absolute error is 8.37 A(2)), while arginine is the least predicted amino acid (mean absolute error is 42.7 A(2) and median absolute error is 36.31 A(2)). Our work suggests that the SVR approach can be directly applied to the ASA prediction where data preclassification has been used.     

Application of support vector regression to genome-assisted prediction of quantitative traits

A byproduct of genome-wide association studies is the possibility of carrying out genome-enabled prediction of disease risk or of quantitative traits. This study is concerned with predicting two quantitative traits, milk yield in dairy cattle and grain yield in wheat, using dense molecular markers as predictors. Two support vector regression (SVR) models, ε-SVR and least-squares SVR, were explored and compared to a widely applied linear regression model, the Bayesian Lasso, the latter assuming additive marker effects. Predictive performance was measured using predictive correlation and mean squared error of prediction. Depending on the kernel function chosen, SVR can model either linear or nonlinear relationships between phenotypes and marker genotypes. For milk yield, where phenotypes were estimated breeding values of bulls (a linear combination of the data), SVR with a Gaussian radial basis function (RBF) kernel had a slightly better performance than with a linear kernel, and was similar to the Bayesian Lasso. For the wheat data, where phenotype was raw grain yield, the RBF kernel provided clear advantages over the linear kernel, e.g., a 17.5% increase in correlation when using the ε-SVR. SVR with a RBF kernel also compared favorably to the Bayesian Lasso in this case. It is concluded that a nonlinear RBF kernel may be an optimal choice for SVR, especially when phenotypes to be predicted have a nonlinear dependency on genotypes, as it might have been the case in the wheat data.     

Combined feature selection and cancer prognosis using support vector machine regression

Prognostic prediction is important in medical domain, because it can be used to select an appropriate treatment for a patient by predicting the patient's clinical outcomes. For high-dimensional data, a normal prognostic method undergoes two steps: feature selection and prognosis analysis. Recently, the L?-L?-norm Support Vector Machine (L?-L? SVM) has been developed as an effective classification technique and shown good classification performance with automatic feature selection. In this paper, we extend L?-L? SVM for regression analysis with automatic feature selection. We further improve the L?-L? SVM for prognostic prediction by utilizing the information of censored data as constraints. We design an efficient solution to the new optimization problem. The proposed method is compared with other seven prognostic prediction methods on three realworld data sets. The experimental results show that the proposed method performs consistently better than the medium performance. It is more efficient than other algorithms with the similar performance.     

DomSVR: domain boundary prediction with support vector regression from sequence information alone

Protein domains are structural and fundamental functional units of proteins. The information of protein domain boundaries is helpful in understanding the evolution, structures and functions of proteins, and also plays an important role in protein classification. In this paper, we propose a support vector regression-based method to address the problem of protein domain boundary identification based on novel input profiles extracted from AAindex database. As a result, our method achieves an average sensitivity of ∼36.5% and an average specificity of ∼81% for multi-domain protein chains, which is overall better than the performance of published approaches to identify domain boundary. As our method used sequence information alone, our method is simpler and faster.     

Quantitative prediction of mouse class I MHC peptide binding affinity using support vector machine regression (SVR) models

Background  

The binding between peptide epitopes and major histocompatibility complex proteins (MHCs) is an important event in the cellular immune response. Accurate prediction of the binding between short peptides and the MHC molecules has long been a principal challenge for immunoinformatics. Recently, the modeling of MHC-peptide binding has come to emphasize quantitative predictions: instead of categorizing peptides as "binders" or "non-binders" or as "strong binders" and "weak binders", recent methods seek to make predictions about precise binding affinities.     

SVM-Cabins: prediction of solvent accessibility using accumulation cutoff set and support vector machine

A number of methods for predicting levels of solvent accessibility or accessible surface area (ASA) of amino acid residues in proteins have been developed. These methods either predict regularly spaced states of relative solvent accessibility or an analogue real value indicating relative solvent accessibility. While discrete states of exposure can be easily obtained by post prediction assignment of thresholds to the predicted or computed real values of ASA, the reverse, that is, obtaining a real value from quantized states of predicted ASA, is not straightforward as a two-state prediction in such cases would give a large real valued errors. However, prediction of ASA into larger number of ASA states and then finding a corresponding scheme for real value prediction may be helpful in integrating the two approaches of ASA prediction. We report a novel method of obtaining numerical real values of solvent accessibility, using accumulation cutoff set and support vector machine. This so-called SVM-Cabins method first predicts discrete states of ASA of amino acid residues from their evolutionary profile and then maps the predicted states onto a real valued linear space by simple algebraic methods. Resulting performance of such a rigorous approach using 13-state ASA prediction is at least comparable with the best methods of ASA prediction reported so far. The mean absolute error in this method reaches the best performance of 15.1% on the tested data set of 502 proteins with a coefficient of correlation equal to 0.66. Since, the method starts with the prediction of discrete states of ASA and leads to real value predictions, performance of prediction in binary states and real values are simultaneously optimized.