skip to main content


Title: Evolutionarily informed machine learning enhances the power of predictive gene-to-phenotype relationships
Inferring phenotypic outcomes from genomic features is both a promise and challenge for systems biology. Using gene expression data to predict phenotypic outcomes, and functionally validating the genes with predictive powers are two challenges we address in this study. We applied an evolutionarily informed machine learning approach to predict phenotypes based on transcriptome responses shared both within and across species. Specifically, we exploited the phenotypic diversity in nitrogen use efficiency and evolutionarily conserved transcriptome responses to nitrogen treatments across Arabidopsis accessions and maize varieties. We demonstrate that using evolutionarily conserved nitrogen responsive genes is a biologically principled approach to reduce the feature dimensionality in machine learning that ultimately improved the predictive power of our gene-to-trait models. Further, we functionally validated seven candidate transcription factors with predictive power for NUE outcomes in Arabidopsis and one in maize. Moreover, application of our evolutionarily informed pipeline to other species including rice and mice models underscores its potential to uncover genes affecting any physiological or clinical traits of interest across biology, agriculture, or medicine.  more » « less
Award ID(s):
1812235
NSF-PAR ID:
10302299
Author(s) / Creator(s):
; ; ; ; ; ; ; ; ; ; ; ; ;
Date Published:
Journal Name:
Nature communications
ISSN:
2041-1723
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Inferring phenotypic outcomes from genomic features is both a promise and challenge for systems biology. Using gene expression data to predict phenotypic outcomes, and functionally validating the genes with predictive powers are two challenges we address in this study. We applied an evolutionarily informed machine learning approach to predict phenotypes based on transcriptome responses shared both within and across species. Specifically, we exploited the phenotypic diversity in nitrogen use efficiency and evolutionarily conserved transcriptome responses to nitrogen treatments across Arabidopsis accessions and maize varieties. We demonstrate that using evolutionarily conserved nitrogen responsive genes is a biologically principled approach to reduce the feature dimensionality in machine learning that ultimately improved the predictive power of our gene-to-trait models. Further, we functionally validated seven candidate transcription factors with predictive power for NUE outcomes in Arabidopsis and one in maize. Moreover, application of our evolutionarily informed pipeline to other species including rice and mice models underscores its potential to uncover genes affecting any physiological or clinical traits of interest across biology, agriculture, or medicine.

     
    more » « less
  2. INTRODUCTION A major challenge in genomics is discerning which bases among billions alter organismal phenotypes and affect health and disease risk. Evidence of past selective pressure on a base, whether highly conserved or fast evolving, is a marker of functional importance. Bases that are unchanged in all mammals may shape phenotypes that are essential for organismal health. Bases that are evolving quickly in some species, or changed only in species that share an adaptive trait, may shape phenotypes that support survival in specific niches. Identifying bases associated with exceptional capacity for cellular recovery, such as in species that hibernate, could inform therapeutic discovery. RATIONALE The power and resolution of evolutionary analyses scale with the number and diversity of species compared. By analyzing genomes for hundreds of placental mammals, we can detect which individual bases in the genome are exceptionally conserved (constrained) and likely to be functionally important in both coding and noncoding regions. By including species that represent all orders of placental mammals and aligning genomes using a method that does not require designating humans as the reference species, we explore unusual traits in other species. RESULTS Zoonomia’s mammalian comparative genomics resources are the most comprehensive and statistically well-powered produced to date, with a protein-coding alignment of 427 mammals and a whole-genome alignment of 240 placental mammals representing all orders. We estimate that at least 10.7% of the human genome is evolutionarily conserved relative to neutrally evolving repeats and identify about 101 million significantly constrained single bases (false discovery rate < 0.05). We cataloged 4552 ultraconserved elements at least 20 bases long that are identical in more than 98% of the 240 placental mammals. Many constrained bases have no known function, illustrating the potential for discovery using evolutionary measures. Eighty percent are outside protein-coding exons, and half have no functional annotations in the Encyclopedia of DNA Elements (ENCODE) resource. Constrained bases tend to vary less within human populations, which is consistent with purifying selection. Species threatened with extinction have few substitutions at constrained sites, possibly because severely deleterious alleles have been purged from their small populations. By pairing Zoonomia’s genomic resources with phenotype annotations, we find genomic elements associated with phenotypes that differ between species, including olfaction, hibernation, brain size, and vocal learning. We associate genomic traits, such as the number of olfactory receptor genes, with physical phenotypes, such as the number of olfactory turbinals. By comparing hibernators and nonhibernators, we implicate genes involved in mitochondrial disorders, protection against heat stress, and longevity in this physiologically intriguing phenotype. Using a machine learning–based approach that predicts tissue-specific cis - regulatory activity in hundreds of species using data from just a few, we associate changes in noncoding sequence with traits for which humans are exceptional: brain size and vocal learning. CONCLUSION Large-scale comparative genomics opens new opportunities to explore how genomes evolved as mammals adapted to a wide range of ecological niches and to discover what is shared across species and what is distinctively human. High-quality data for consistently defined phenotypes are necessary to realize this potential. Through partnerships with researchers in other fields, comparative genomics can address questions in human health and basic biology while guiding efforts to protect the biodiversity that is essential to these discoveries. Comparing genomes from 240 species to explore the evolution of placental mammals. Our new phylogeny (black lines) has alternating gray and white shading, which distinguishes mammalian orders (labeled around the perimeter). Rings around the phylogeny annotate species phenotypes. Seven species with diverse traits are illustrated, with black lines marking their branch in the phylogeny. Sequence conservation across species is described at the top left. IMAGE CREDIT: K. MORRILL 
    more » « less
  3. INTRODUCTION The Anthropocene is marked by an accelerated loss of biodiversity, widespread population declines, and a global conservation crisis. Given limited resources for conservation intervention, an approach is needed to identify threatened species from among the thousands lacking adequate information for status assessments. Such prioritization for intervention could come from genome sequence data, as genomes contain information about demography, diversity, fitness, and adaptive potential. However, the relevance of genomic data for identifying at-risk species is uncertain, in part because genetic variation may reflect past events and life histories better than contemporary conservation status. RATIONALE The Zoonomia multispecies alignment presents an opportunity to systematically compare neutral and functional genomic diversity and their relationships to contemporary extinction risk across a large sample of diverse mammalian taxa. We surveyed 240 species spanning from the “Least Concern” to “Critically Endangered” categories, as published in the International Union for Conservation of Nature’s Red List of Threatened Species. Using a single genome for each species, we estimated historical effective population sizes ( N e ) and distributions of genome-wide heterozygosity. To estimate genetic load, we identified substitutions relative to reconstructed ancestral sequences, assuming that mutations at evolutionarily conserved sites and in protein-coding sequences, especially in genes essential for viability in mice, are predominantly deleterious. We examined relationships between the conservation status of species and metrics of heterozygosity, demography, and genetic load and used these data to train and test models to distinguish threatened from nonthreatened species. RESULTS Species with smaller historical N e are more likely to be categorized as at risk of extinction, suggesting that demography, even from periods more than 10,000 years in the past, may be informative of contemporary resilience. Species with smaller historical N e also carry proportionally higher burdens of weakly and moderately deleterious alleles, consistent with theoretical expectations of the long-term accumulation and fixation of genetic load under strong genetic drift. We found weak support for a causative link between fixed drift load and extinction risk; however, other types of genetic load not captured in our data, such as rare, highly deleterious alleles, may also play a role. Although ecological (e.g., physiological, life-history, and behavioral) variables were the best predictors of extinction risk, genomic variables nonrandomly distinguished threatened from nonthreatened species in regression and machine learning models. These results suggest that information encoded within even a single genome can provide a risk assessment in the absence of adequate ecological or population census data. CONCLUSION Our analysis highlights the potential for genomic data to rapidly and inexpensively gauge extinction risk by leveraging relationships between contemporary conservation status and genetic variation shaped by the long-term demographic history of species. As more resequencing data and additional reference genomes become available, estimates of genetic load, estimates of recent demographic history, and accuracy of predictive models will improve. We therefore echo calls for including genomic information in assessments of the conservation status of species. Genomic information can help predict extinction risk in diverse mammalian species. Across 240 mammals, species with smaller historical N e had lower genetic diversity, higher genetic load, and were more likely to be threatened with extinction. Genomic data were used to train models that predict whether a species is threatened, which can be valuable for assessing extinction risk in species lacking ecological or census data. [Animal silhouettes are from PhyloPic] 
    more » « less
  4. Abstract Changes in gene expression are important for responses to abiotic stress. Transcriptome profiling of heat- or cold-stressed maize genotypes identifies many changes in transcript abundance. We used comparisons of expression responses in multiple genotypes to identify alleles with variable responses to heat or cold stress and to distinguish examples of cis- or trans-regulatory variation for stress-responsive expression changes. We used motifs enriched near the transcription start sites (TSSs) for thermal stress-responsive genes to develop predictive models of gene expression responses. Prediction accuracies can be improved by focusing only on motifs within unmethylated regions near the TSS and vary for genes with different dynamic responses to stress. Models trained on expression responses in a single genotype and promoter sequences provided lower performance when applied to other genotypes but this could be improved by using models trained on data from all three genotypes tested. The analysis of genes with cis-regulatory variation provides evidence for structural variants that result in presence/absence of transcription factor binding sites in creating variable responses. This study provides insights into cis-regulatory motifs for heat- and cold-responsive gene expression and defines a framework for developing models to predict expression responses across multiple genotypes. 
    more » « less
  5. INTRODUCTION Diverse phenotypes, including large brains relative to body size, group living, and vocal learning ability, have evolved multiple times throughout mammalian history. These shared phenotypes may have arisen repeatedly by means of common mechanisms discernible through genome comparisons. RATIONALE Protein-coding sequence differences have failed to fully explain the evolution of multiple mammalian phenotypes. This suggests that these phenotypes have evolved at least in part through changes in gene expression, meaning that their differences across species may be caused by differences in genome sequence at enhancer regions that control gene expression in specific tissues and cell types. Yet the enhancers involved in phenotype evolution are largely unknown. Sequence conservation–based approaches for identifying such enhancers are limited because enhancer activity can be conserved even when the individual nucleotides within the sequence are poorly conserved. This is due to an overwhelming number of cases where nucleotides turn over at a high rate, but a similar combination of transcription factor binding sites and other sequence features can be maintained across millions of years of evolution, allowing the function of the enhancer to be conserved in a particular cell type or tissue. Experimentally measuring the function of orthologous enhancers across dozens of species is currently infeasible, but new machine learning methods make it possible to make reliable sequence-based predictions of enhancer function across species in specific tissues and cell types. RESULTS To overcome the limits of studying individual nucleotides, we developed the Tissue-Aware Conservation Inference Toolkit (TACIT). Rather than measuring the extent to which individual nucleotides are conserved across a region, TACIT uses machine learning to test whether the function of a given part of the genome is likely to be conserved. More specifically, convolutional neural networks learn the tissue- or cell type–specific regulatory code connecting genome sequence to enhancer activity using candidate enhancers identified from only a few species. This approach allows us to accurately associate differences between species in tissue or cell type–specific enhancer activity with genome sequence differences at enhancer orthologs. We then connect these predictions of enhancer function to phenotypes across hundreds of mammals in a way that accounts for species’ phylogenetic relatedness. We applied TACIT to identify candidate enhancers from motor cortex and parvalbumin neuron open chromatin data that are associated with brain size relative to body size, solitary living, and vocal learning across 222 mammals. Our results include the identification of multiple candidate enhancers associated with brain size relative to body size, several of which are located in linear or three-dimensional proximity to genes whose protein-coding mutations have been implicated in microcephaly or macrocephaly in humans. We also identified candidate enhancers associated with the evolution of solitary living near a gene implicated in separation anxiety and other enhancers associated with the evolution of vocal learning ability. We obtained distinct results for bulk motor cortex and parvalbumin neurons, demonstrating the value in applying TACIT to both bulk tissue and specific minority cell type populations. To facilitate future analyses of our results and applications of TACIT, we released predicted enhancer activity of >400,000 candidate enhancers in each of 222 mammals and their associations with the phenotypes we investigated. CONCLUSION TACIT leverages predicted enhancer activity conservation rather than nucleotide-level conservation to connect genetic sequence differences between species to phenotypes across large numbers of mammals. TACIT can be applied to any phenotype with enhancer activity data available from at least a few species in a relevant tissue or cell type and a whole-genome alignment available across dozens of species with substantial phenotypic variation. Although we developed TACIT for transcriptional enhancers, it could also be applied to genomic regions involved in other components of gene regulation, such as promoters and splicing enhancers and silencers. As the number of sequenced genomes grows, machine learning approaches such as TACIT have the potential to help make sense of how conservation of, or changes in, subtle genome patterns can help explain phenotype evolution. Tissue-Aware Conservation Inference Toolkit (TACIT) associates genetic differences between species with phenotypes. TACIT works by generating open chromatin data from a few species in a tissue related to a phenotype, using the sequences underlying open and closed chromatin regions to train a machine learning model for predicting tissue-specific open chromatin and associating open chromatin predictions across dozens of mammals with the phenotype. [Species silhouettes are from PhyloPic] 
    more » « less