Related Experiment Video
Updated: Jun 27, 2026
Whole Genome Sequencing of Candida glabrata for Detection of Markers of Antifungal Drug Resistance
Published on: December 28, 2017
Detecting DNA of novel fungal pathogens using ResNets and a curated fungi-hosts data collection
Jakub M Bartoszewicz1,2, Ferdous Nasri1,2, Melania Nowicka1,2
1Hasso Plattner Institute for Digital Engineering, Digital Engineering Faculty, University of Potsdam, Potsdam 14482, Germany.
Background:
Emerging 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 data remain 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.
Results:
We 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 it 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 visualize the landscape of fungal pathogenicity. Finally, we train multi-class models predicting if next-generation sequencing reads originate from novel fungal, bacterial or viral threats.
Conclusions:
The neural networks trained using our data collection enable accurate detection of novel fungal pathogens. A curated set of over 1400 genomes with host and pathogenicity metadata supports training of machine-learning models and sequence comparison, not limited to the pathogen detection task.
Availability And Implementation:
The data, models and code are hosted at https://zenodo.org/record/5846345, https://zenodo.org/record/5711877 and https://gitlab.com/dacs-hpi/deepac.
Supplementary Information:
Supplementary data are available at Bioinformatics online.
Insights
This study introduces a new method for detecting emerging fungal pathogens using DNA sequencing. The developed models accurately identify novel fungal threats, improving public health surveillance.
Area of Science:
- Microbiology
- Bioinformatics
- Computational Biology
Background:
- Emerging pathogens pose a significant global health risk, yet data and predictive tools are limited, particularly for fungal pathogens.
- Fungal pathogens are understudied, with scarce and fragmented data hindering the development of effective detection methods.
- Current prediction methods do not cover all major pathogen groups (fungal, bacterial, viral), despite diagnostic challenges.
Purpose of the Study:
- To develop a comprehensive dataset of fungal host range and pathogenicity.
- To create predictive models for identifying novel fungal pathogens directly from DNA sequence data.
- To build a unified detection system for novel threats across fungal, bacterial, and viral agents.
Main Methods:
- Curated a dataset of fungal host range, including human, animal, and plant pathogens, linked to genomic data.
- Utilized sequence homology and deep learning approaches to predict pathogenic potential from DNA sequences.
- Developed numerical representations of genomes and trained multi-class models for pathogen identification.
Main Results:
- A curated collection of over 1400 fungal genomes with host and pathogenicity metadata was established.
- Predictive models demonstrated accurate identification of novel fungal species based on DNA sequence analysis.
- Multi-class models were successfully trained to differentiate between novel fungal, bacterial, and viral threats using next-generation sequencing reads.
Conclusions:
- The developed dataset and machine learning models enable accurate detection of novel fungal pathogens.
- The approach supports pathogen detection and other sequence analysis tasks, advancing genomic surveillance.
- The study provides a foundation for broader applications in identifying and managing emerging infectious diseases.
Related Concept Videos
01:29Modern Molecular Taxonomy
01:25Rapid Identification of Pathogens