Biomedical subjects

Peter D Fields

Publications and source records attributed to Peter D Fields.

3 recordsLinked to original sources

PubMed2026

Predicting genome-wide functional constraints with GPN-Star.

Genomic language models have emerged as a powerful approach for learning genome-wide functional constraints directly from DNA sequences1. However, standard genomic language models adapted from natural language processing often require large model sizes and computational resources, yet still fall short of classical evolutionary models in predictive tasks2-4. Here we introduce a genomic pretrained network with species tree and alignment representations (GPN-Star), which is a biologically grounded genomic language model featuring a phylogeny-aware architecture that leverages whole-genome alignments and species trees to model evolutionary relationships explicitly. Trained on alignments spanning vertebrate, mammal and primate evolutionary timescales, GPN-Star achieves state-of-the-art performance across a wide range of variant effect prediction tasks in both coding and non-coding regions of the human genome. Analyses across timescales show task-dependent advantages of modelling more recent versus deeper evolution. To demonstrate its potential to advance human genetics, we show that GPN-Star substantially outperforms previous methods in prioritizing pathogenic and fine-mapped genome-wide association study variants, yields strong enrichments of complex trait heritability and improves power in rare variant association testing5. Extending beyond humans, we train GPN-Star for five model organisms-Mus musculus, Gallus gallus, Drosophila melanogaster, Caenorhabditis elegans and Arabidopsis thaliana-demonstrating the robustness and generalizability of the framework. Taken together, these results position GPN-Star as a scalable, powerful and flexible tool for genome interpretation, well suited to leverage the growing abundance of comparative genomics data.

Journal Article↗

PubMed2025

Predicting functional constraints across evolutionary timescales with phylogeny-informed genomic language models.

Genomic language models (gLMs) have emerged as a powerful approach for learning genome-wide functional constraints directly from DNA sequences. However, standard gLMs adapted from natural language processing often require extremely large model sizes and computational resources, yet still fall short of classical evolutionary models in predictive tasks. Here, we introduce GPN-Star (Genomic Pretrained Network with Species Tree and Alignment Representation), a biologically grounded gLM featuring a phylogeny-aware architecture that leverages whole-genome alignments and species trees to model evolutionary relationships explicitly. Trained on alignments spanning vertebrate, mammalian, and primate evolutionary timescales, GPN-Star achieves state-of-the-art performance across a wide range of variant effect prediction tasks in both coding and non-coding regions of the human genome. Analyses across timescales reveal task-dependent advantages of modeling more recent versus deeper evolution. To demonstrate its potential to advance human genetics, we show that GPN-Star substantially outperforms prior methods in prioritizing pathogenic and fine-mapped GWAS variants; yields unprecedented enrichments of complex trait heritability; and improves power in rare variant association testing. Extending beyond humans, we train GPN-Star for five model organisms - Mus musculus, Gallus gallus, Drosophila melanogaster, Caenorhabditis elegans, and Arabidopsis thaliana - demonstrating the robustness and generalizability of the framework. Taken together, these results position GPN-Star as a scalable, powerful, and flexible new tool for genome interpretation, well suited to leverage the growing abundance of comparative genomics data.

Journal Article↗

PubMed2025

Accessible, realistic genome simulation with selection using stdpopsim.

Selection is a fundamental evolutionary force that shapes patterns of genetic variation across species. However, simulations incorporating realistic selection along heterogeneous genomes in complex demographic histories are challenging, limiting our ability to benchmark statistical methods aimed at detecting selection and to explore theoretical predictions. stdpopsim is a community-maintained simulation library that already provides an extensive catalog of species-specific population genetic models. Here we present a major extension to the stdpopsim framework that enables simulation of various modes of selection, including background selection, selective sweeps, and arbitrary distributions of fitness effects (DFE) acting on annotated subsets of the genome (for instance, exons). This extension maintains stdpopsim's core principles of reproducibility and accessibility while adding support for species-specific genomic annotations and published DFE estimates. We demonstrate the utility of this framework by comparing methods for demographic inference, DFE estimation, and selective sweep detection across several species and scenarios. Our results demonstrate the robustness of demographic inference methods to selection on linked sites, reveal the sensitivity of DFE-inference methods to model assumptions, and show how genomic features, like recombination rate and functional sequence density, influence power to detect selective sweeps. This extension to stdpopsim provides a powerful new resource for the population genetics community to explore the interplay between selection and other evolutionary forces in a reproducible, user-friendly framework.

Journal Article↗