Dataset Information

A Deep Learning Approach to Population Structure Inference in Inbred Lines of Maize.

ABSTRACT: Analysis of population genetic variation and structure is a common practice for genome-wide studies, including association mapping, ecology, and evolution studies in several crop species. In this study, machine learning (ML) clustering methods, K-means (KM), and hierarchical clustering (HC), in combination with non-linear and linear dimensionality reduction techniques, deep autoencoder (DeepAE) and principal component analysis (PCA), were used to infer population structure and individual assignment of maize inbred lines, i.e., dent field corn (n = 97) and popcorn (n = 86). The results revealed that the HC method in combination with DeepAE-based data preprocessing (DeepAE-HC) was the most effective method to assign individuals to clusters (with 96% of correct individual assignments), whereas DeepAE-KM, PCA-HC, and PCA-KM were assigned correctly 92, 89, and 81% of the lines, respectively. These findings were consistent with both Silhouette Coefficient (SC) and Davies-Bouldin validation indexes. Notably, DeepAE-HC also had better accuracy than the Bayesian clustering method implemented in InStruct. The results of this study showed that deep learning (DL)-based dimensional reduction combined with ML clustering methods is a useful tool to determine genetically differentiated groups and to assign individuals into subpopulations in genome-wide studies without having to consider previous genetic assumptions.

SUBMITTER: Lopez-Cortes XA

PROVIDER: S-EPMC7732446 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Deep Learning Approach to Population Structure Inference in Inbred Lines of Maize.

López-Cortés Xaviera Alejandra XA Matamala Felipe F Maldonado Carlos C Mora-Poblete Freddy F Scapim Carlos Alberto CA

Frontiers in genetics 20201124

Analysis of population genetic variation and structure is a common practice for genome-wide studies, including association mapping, ecology, and evolution studies in several crop species. In this study, machine learning (ML) clustering methods, K-means (KM), and hierarchical clustering (HC), in combination with non-linear and linear dimensionality reduction techniques, deep autoencoder (DeepAE) and principal component analysis (PCA), were used to infer population structure and individual assignm ...[more]

PMID: 33329691

Similar Datasets

Project description:BackgroundMolecular characterization is important for efficient utilization of germplasm and development of improved varieties. In the present study, we investigated the genetic purity, relatedness and population structure of 265 maize inbred lines from the Ethiopian Institute of Agricultural Research (EIAR), the International Maize and Wheat Improvement Centre (CIMMYT) and the International Institute of Tropical Agriculture (IITA) using 220,878 single nucleotide polymorphic (SNP) markers obtained using genotyping by sequencing (GBS).ResultsOnly 22% of the inbred lines were considered pure with <5% heterogeneity, while the remaining 78% of the inbred lines had a heterogeneity ranging from 5.1 to 31.5%. Pairwise genetic distances among the 265 inbred lines varied from 0.011 to 0.345, with 89% of the pairs falling between 0.301 and 0.345. Only <1% of the pairs had a genetic distance lower than 0.200, which included 14 pairs of sister lines that were nearly identical. Relative kinship analysis showed that the kinship coefficients for 59% of the pairs of lines was close to zero, which agrees with the genetic distance estimates. Principal coordinate analysis, discriminant analysis of principal components (DAPC) and the model-based population structure analysis consistently suggested the presence of three groups, which generally agreed with pedigree information (genetic background). Although not distinct enough, the SNP markers showed some level of separation between the two CIMMYT heterotic groups A and B established based on pedigree and combining ability information.ConclusionsThe high level of heterogeneity detected in most of the inbred lines suggested the requirement for purification or further inbreeding except those deliberately maintained at early inbreeding level. The genetic distance and relative kinship analysis clearly indicated the uniqueness of most of the inbred lines in the maize germplasm available for breeders in the mid-altitude maize breeding program of Ethiopia. Results from the present study facilitate the maize breeding work in Ethiopia and germplasm exchange among breeding programs in Africa. We suggest the incorporation of high density molecular marker information in future heterotic group assignments.

Project description:Within computational neuroscience, the algorithmic and neural basis of structure learning remains poorly understood. Concept learning is one primary example, which requires both a type of internal model expansion process (adding novel hidden states that explain new observations), and a model reduction process (merging different states into one underlying cause and thus reducing model complexity via meta-learning). Although various algorithmic models of concept learning have been proposed within machine learning and cognitive science, many are limited to various degrees by an inability to generalize, the need for very large amounts of training data, and/or insufficiently established biological plausibility. Using concept learning as an example case, we introduce a novel approach for modeling structure learning-and specifically state-space expansion and reduction-within the active inference framework and its accompanying neural process theory. Our aim is to demonstrate its potential to facilitate a novel line of active inference research in this area. The approach we lay out is based on the idea that a generative model can be equipped with extra (hidden state or cause) "slots" that can be engaged when an agent learns about novel concepts. This can be combined with a Bayesian model reduction process, in which any concept learning-associated with these slots-can be reset in favor of a simpler model with higher model evidence. We use simulations to illustrate this model's ability to add new concepts to its state space (with relatively few observations) and increase the granularity of the concepts it currently possesses. We also simulate the predicted neural basis of these processes. We further show that it can accomplish a simple form of "one-shot" generalization to new stimuli. Although deliberately simple, these simulation results highlight ways in which active inference could offer useful resources in developing neurocomputational models of structure learning. They provide a template for how future active inference research could apply this approach to real-world structure learning problems and assess the added utility it may offer.

Dataset Information

A Deep Learning Approach to Population Structure Inference in Inbred Lines of Maize.

Publications

A Deep Learning Approach to Population Structure Inference in Inbred Lines of Maize.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets