Dataset Information

Interpretable modeling of genotype-phenotype landscapes with state-of-the-art predictive power.

ABSTRACT: Large-scale measurements linking genetic background to biological function have driven a need for models that can incorporate these data for reliable predictions and insight into the underlying biophysical system. Recent modeling efforts, however, prioritize predictive accuracy at the expense of model interpretability. Here, we present LANTERN (landscape interpretable nonparametric model, https://github.com/usnistgov/lantern), a hierarchical Bayesian model that distills genotype-phenotype landscape (GPL) measurements into a low-dimensional feature space that represents the fundamental biological mechanisms of the system while also enabling straightforward, explainable predictions. Across a benchmark of large-scale datasets, LANTERN equals or outperforms all alternative approaches, including deep neural networks. LANTERN furthermore extracts useful insights of the landscape, including its inherent dimensionality, a latent space of additive mutational effects, and metrics of landscape structure. LANTERN facilitates straightforward discovery of fundamental mechanisms in GPLs, while also reliably extrapolating to unexplored regions of genotypic space.

SUBMITTER: Tonner PD

PROVIDER: S-EPMC9245639 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Interpretable modeling of genotype-phenotype landscapes with state-of-the-art predictive power.

Tonner Peter D PD Pressman Abe A Ross David D

Proceedings of the National Academy of Sciences of the United States of America 20220621 26

Large-scale measurements linking genetic background to biological function have driven a need for models that can incorporate these data for reliable predictions and insight into the underlying biophysical system. Recent modeling efforts, however, prioritize predictive accuracy at the expense of model interpretability. Here, we present LANTERN (landscape interpretable nonparametric model, https://github.com/usnistgov/lantern), a hierarchical Bayesian model that distills genotype-phenotype landsc ...[more]

PMID: 35733251

Similar Datasets

Project description:Discovery of genetic variants underlying bacterial phenotypes and the prediction of phenotypes such as antibiotic resistance are fundamental tasks in bacterial genomics. Genome-wide association study (GWAS) methods have been applied to study these relations, but the plastic nature of bacterial genomes and the clonal structure of bacterial populations creates challenges. We introduce an alignment-free method which finds sets of loci associated with bacterial phenotypes, quantifies the total effect of genetics on the phenotype, and allows accurate phenotype prediction, all within a single computationally scalable joint modeling framework. Genetic variants covering the entire pangenome are compactly represented by extended DNA sequence words known as unitigs, and model fitting is achieved using elastic net penalization, an extension of standard multiple regression. Using an extensive set of state-of-the-art bacterial population genomic data sets, we demonstrate that our approach performs accurate phenotype prediction, comparable to popular machine learning methods, while retaining both interpretability and computational efficiency. Compared to those of previous approaches, which test each genotype-phenotype association separately for each variant and apply a significance threshold, the variants selected by our joint modeling approach overlap substantially.IMPORTANCE Being able to identify the genetic variants responsible for specific bacterial phenotypes has been the goal of bacterial genetics since its inception and is fundamental to our current level of understanding of bacteria. This identification has been based primarily on painstaking experimentation, but the availability of large data sets of whole genomes with associated phenotype metadata promises to revolutionize this approach, not least for important clinical phenotypes that are not amenable to laboratory analysis. These models of phenotype-genotype association can in the future be used for rapid prediction of clinically important phenotypes such as antibiotic resistance and virulence by rapid-turnaround or point-of-care tests. However, despite much effort being put into adapting genome-wide association study (GWAS) approaches to cope with bacterium-specific problems, such as strong population structure and horizontal gene exchange, current approaches are not yet optimal. We describe a method that advances methodology for both association and generation of portable prediction models.

Project description:AimTo investigate genotype-phenotype correlations in patients with perianal Crohn's disease (PCD) in order to determine which factors predispose to development of perianal disease in Crohn's patients.MethodsSeven-hundred and ninety-five Caucasian individuals (317 CD patients and 478 controls without inflammatory bowel disease, IBD) were prospectively enrolled into a clinical/genetic database. Demographic and clinical data, as well as peripheral blood leukocyte DNA were obtained from all patients. The following were evaluated: three NOD2/CARD15 polymorphisms: R702W, G908R, and 1007insC; five IL-23r risk alleles: rs1004819, rs10489629, rs2201841, rs11465804, and rs11209026; a well-characterized single-nucleotide polymorphism (SNP) on the IBD5 risk haplotype (OCTN1) and two peripheral tag SNPs (IGR2060 and IGR3096).ResultsPCD occurred in 147 (46%) of CD patients. There was no significant difference in the age at disease diagnosis between non-PCD and PCD patients (33 vs. 29 years, respectively). PCD patients were more likely to have disease located in the colon and ileocolic regions (79 PCD vs. 57% non-PCD; n = 116 vs. n = 96; p < 0.001), whereas patients with non-PCD were more likely to have Crohn's within the terminal ileum and upper gastrointestinal tract (43% non-PCD vs. 21% PCD; n = 73 vs. n = 31; p < 0.05). Thirty-four percent of patients with PCD required a permanent ileostomy (n = 50) compared to only 4% of non-PCD patients (n = 6; p < 0.05). Mutations in CARD15/NOD2 and IL-23r were risk factors for CD overall; however, in contrast to prior reports, in this patient population, OCTN1 and IGR variations within the IBD5 haplotype were not significant predictors of PCD.ConclusionColon/ileocolic CD location appears to be a significant predictor of perianal manifestations of CD. Patients with PCD are more likely to require permanent fecal diversion. We did not identify any genetic variations or combination of clinical findings and genetic variations within the CARD15/NOD2, IL-23r, and OCTN1 genes or IGR that were predictive of PCD.

Dataset Information

Interpretable modeling of genotype-phenotype landscapes with state-of-the-art predictive power.

Publications

Interpretable modeling of genotype-phenotype landscapes with state-of-the-art predictive power.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets