Detecting DNA of novel fungal pathogens using ResNets and a curated fungi-hosts data collection

Abstract

AbstractBackgroundEmerging pathogens are a growing threat, but large data collections and approaches for predicting the risk associated with novel agents are limited to bacteria and viruses. Pathogenic fungi, which also pose a constant threat to public health, remain understudied. Relevant, curated data remains comparatively scarce and scattered among many different sources, hindering the development of sequencing-based detection workflows for novel fungal pathogens. No prediction method working for agents across all three groups is available, even though the cause of an infection is often difficult to identify from symptoms alone.ResultsWe present a curated collection of fungal host range data, comprising records on human, animal and plant pathogens, as well as other plant-associated fungi, linked to publicly available genomes. We show that the resulting database can be used to predict the pathogenic potential of novel fungal species directly from DNA sequences with either sequence homology or deep learning. We develop learned, numerical representations of the collected genomes and show that the human pathogens are separable from non-human pathogens. Finally, we train multi-class models predicting if next-generation sequencing reads originate from novel fungal, bacterial or viral threats.ConclusionsThe neural networks trained using the presented data collection enable accurate detection of novel pathogens from DNA inputs. A curated set of over 1,400 fungal genomes with host and pathogenicity annotation supports development of machine learning models and direct sequence comparison, not limited to the pathogen detection task.AvailabilityThe data, models and code are hosted at https://zenodo.org/record/5846345, https://zenodo.org/record/5711877 and https://gitlab.com/dacs-hpi/deepac.