Application of deep learning with bivariate models for genomic prediction of sow lifetime productivity-related traits

OBJECTIVE

Pig breeders cannot obtain phenotypic information at the time of selection for sow lifetime productivity (SLP). They would benefit from obtaining genetic information of candidate sows. Genomic data interpreted using deep learning (DL) techniques could contribute to the genetic improvement of SLP to maximize farm profitability because DL models capture nonlinear genetic effects such as dominance and epistasis more efficiently than conventional genomic prediction methods based on linear models. This study aimed to investigate the usefulness of DL for the genomic prediction of two SLP-related traits; lifetime number of litters (LNL) and lifetime pig production (LPP).

METHODS

Two bivariate DL models, convolutional neural network (CNN) and local convolutional neural network (LCNN), were compared with conventional bivariate linear models (i.e., genomic best linear unbiased prediction, Bayesian ridge regression, Bayes A, and Bayes B). Phenotype and pedigree data were collected from 40,011 sows that had husbandry records. Among these, 3,652 pigs were genotyped using the PorcineSNP60K BeadChip.

RESULTS

The best predictive correlation for LNL was obtained with CNN (0.28), followed by LCNN (0.26) and conventional linear models (approximately 0.21). For LPP, the best predictive correlation was also obtained with CNN (0.29), followed by LCNN (0.27) and conventional linear models (approximately 0.25). A similar trend was observed with the mean squared error of prediction for the SLP traits.

CONCLUSION

This study provides an example of a CNN that can outperform against the linear model-based genomic prediction approaches when the nonlinear interaction components are important because LNL and LPP exhibited strong epistatic interaction components. Additionally, our results suggest that applying bivariate DL models could also contribute to the prediction accuracy by utilizing the genetic correlation between LNL and LPP.

Independent and Interactive Effect of CYPs and GSTs Genetic Variants and Tobacco Smoking on the Risk of Non-Small Cell Lung Carcinoma

BACKGROUND

CYP and GST gene families detoxify tobacco carcinogens and have been linked to the risk of non-small cell lung carcinoma (NSCLC).

AIM

Independent and combined effects of CYP and GST genetic variations and smoking on the risk of non-small cell lung carcinoma (NSCLC) and its sub-histological types.

METHODS

We modelled an epistatic interaction via the effects of particular genotypes in two genes as OR (odds ratio), OR1, and OR2, a combination of both genotypes were characterized as OR_combine. In contrast, the two ORs' epistatic interaction for the individual genotypes has been represented as OR_interaction = OR_combine/(OR1 × OR2).

RESULTS

The variant genotypes of CYP2A6 (OR:4.2, p <0.001), GSTT1 (OR:3.9, p <0.001), and GSTM1 (OR: 4.5, p <0.001) were showed a significant risk with NSCLC. GSTM1 (del.)/CYP2A6 (variant) genotype was associated with a higher risk of NSCLC (OR:12.5, p <0.001). GSTM1 (del.)/CYP2A6 (Ser/Pro+Pro/Pro) and GSTM1 (del.)/CYP2A13 (CT+TT) interacted redundantly (OR_intraction = 0.66 and 0.64). A co-suppressive interaction was observed between GSTT1 (del.)/CYP2A6 (Ser/Pro+Pro/Pro) (OR_intraction = 0.41). Simultaneously, both GSTT1/GSTM1 del. genotype was associated with a significantly higher risk to NSCLC. In contrast, GSTT1 del./GSTM1 del. genotype interaction displayed a co-suppressive effect (OR_intraction = 0.15). CYP1A1(TC+CC)/CYP2A13(CT+TT)mutually interacted synergistically (OR_intraction = 1.27).CYP1A1 (TC+CC)/GSTP1 (Val/Val+Ile/Val) genotype demonstrated an additive (OR_intraction = 1) effect. GSTP1(Val/Val+Ile/Val) interacts with GSTT1 (del.) genotype exerted a suppressive effect (OR_intraction = 0.69). CYP2A6 in smokers increased risk by 4.2 (p = 0.001) to 5.6 fold (p <0.001), while GSTM1 and GSTT1 were independent of smoking.

CONCLUSION

Epistatic interactions revealed that CYPs/GSTs might follow a web of the interactions to modify the risk of NSCLC.