Methods and compositions for imputing or predicting genotype or phenotype

Abstract

Methods and compositions to impute or predict genotype, haplotype, molecular phenotype, agronomic phenotypes, and/or coancestry are provided. Methods and compositions provided include using latent space to generate latent space representations or latent vectors that are independent of underlying genotypic or phenotypic data. The methods may include generating a universal latent space representation by encoding discrete or continuous variables derived from genotypic or phenotypic data into latent vectors through a machine learning-based encoder framework. Provided herein are universal methods of parametrically representing genotypic or phenotypic data obtained from one or more populations or sample sets to impute or predict a genotype or phenotype of interest.

1 - 29 . (canceled) 
     
     
         30 . A universal method of parametrically representing genotypic or phenotypic association data from a training data set obtained from a plant population or a plant sample set to impute or predict a genotype and/or a phenotype in a non-training data obtained from a non-training plant population or a non-training plant sample data, the method comprising:
 generating a universal continuous global latent space representation by encoding discrete or continuous variables derived from a genotypic or phenotypic association training data into latent vectors through a machine learning-based global autoencoder framework, wherein the global latent space is independent of the underlying genotypic or phenotypic association;   generating a local latent representation by encoding a subset of the discrete or continuous variables derived from the genotypic or phenotypic association training data set into latent vectors through a machine learning-based local autoencoder framework, wherein the local latent space is generated with inputs from the local autoencoder and the global autoencoder;   decoding the global latent representation and the local latent representation by a local decoder, thereby imputing or predicting the genotype or phenotype of the non-training data by the combination of the decoded global latent representation and the local latent representation; and   selecting one or more plant populations or members thereof based on the imputed or predicted genotype or phenotype.   
     
     
         31 . The method of  claim 30 , wherein the genotypic association training data is genome-wide genotypic association training data. 
     
     
         32 . The method of  claim 30 , wherein the phenotypic association training data is phenome-wide phenotypic association training data. 
     
     
         33 . The method of  claim 30 , wherein the genotypic association data comprises a collection of genotypic markers or single nucleotide polymorphisms (SNPs) from a plurality of genetically divergent populations. 
     
     
         34 . The method of  claim 30 , wherein the subset of the discrete variables is a plurality of single nucleotide polymorphisms (SNPs) localized to a segment of the chromosome. 
     
     
         35 . The method of  claim 30 , wherein the genotypic association data is obtained from populations of plants derived from two or more breeding programs, wherein the breeding programs do not comprise an identical set of markers or single nucleotide polymorphisms (SNPs) corresponding to the genotypic association data. 
     
     
         36 . The method of  claim 30 , wherein the machine learning-based global autoencoder framework or machine learning-based local autoencoder framework or a combination thereof is a variational autoencoder. 
     
     
         37 . The method of  claim 36 , wherein the variational autoencoder is based on a neural network algorithm. 
     
     
         38 . The method of  claim 30 , wherein the machine learning-based global autoencoder framework, machine learning-based local autoencoder framework, or a combination thereof is a generative adversarial network. 
     
     
         39 . The method of  claim 30 , the method comprising: training the decoder to learn a prediction or imputation of a genotype or phenotype of interest based on an objective function for the encoded latent vectors. 
     
     
         40 . The method of  claim 39 , the method further comprising: decoding by the decoder the encoded latent vector for the objective function. 
     
     
         41 . The method of  claim 40 , the method comprising: providing an output for the objective function of the decoded latent vector. 
     
     
         42 . The method of  claim 30 , the method comprising crossing with another population or member the one or more selected populations or members thereof imputed or predicted to comprise a genotype associated with a desirable trait of interest. 
     
     
         43 . The method of  claim 30 , the method comprising counter-selecting from a breeding program the one or more selected populations or members thereof imputed or predicted to comprise a genotype associated with an undesirable trait of interest. 
     
     
         44 . The method of  claim 30 , the method comprising crossing with another population or member the one or more selected populations or members thereof imputed or predicted to comprise a phenotype associated with a desirable trait of interest. 
     
     
         45 . The method of  claim 30 , the method comprising counter-selecting from a breeding program the one or more selected populations or members thereof imputed or predicted to comprise a phenotype associated with an undesirable trait of interest. 
     
     
         46 . The method of  claim 30 , wherein the plant is a soybean, maize, sorghum, cotton, canola, sunflower, rice, wheat, sugarcane, alfalfa tobacco, barley, cassava, peanuts, millet, oil palm, potatoes, rye, or sugar beet plant. 
     
     
         47 . The method of  claim 30 , wherein the imputed or predicted phenotype is yield gain, root lodging, stalk lodging, brittle snap, ear height, grain moisture, plant height, disease resistance, drought tolerance, or a combination thereof. 
     
     
         48 . The method of  claim 30 , wherein the decoder imputes or predicts a molecular phenotype selected from gene expression, chromatin accessibility, DNA methylation, histone modifications, recombination hotspot, genomic landing locations for transgenes, transcription factor binding status, or a combination thereof. 
     
     
         49 . The method of  claim 30 , wherein the imputed or predicted genotype is a plurality of haplotypes. 
     
     
         50 . The method of  claim 30 , the method further comprising the step of:
 (a) imputing or predicting by the local decoder local high-density (HD) SNPs;   (b) imputing or predicting by the local decoder local high-density (HD) SNPs or haplotypes of one population based on the decoding of genotypic association data of another population;   (c) imputing or predicting by the local decoder a molecular phenotype selected from gene expression, chromatin accessibility, DNA methylation, histone modifications, recombination hotspot, genomic landing locations for transgenes, transcription factor binding status, or a combination thereof; or   (d) imputing or predicting by the local decoder population coancestry for one or more of the non-training populations.   
     
     
         51 . A computing device comprising a processor configured to perform the steps of the method of claim  1 . 
     
     
         52 . A computer-readable medium comprising instructions which, when executed by a computing device, cause the computing device to carry out the steps of the method of claim  1 .