BacPaCS-Bacterial Pathogenicity Classification via Sparse-SVM

BacSPaD: A Robust Bacterial Strains' Pathogenicity Resource Based on Integrated and Curated Genomic Metadata

The vast array of omics data in microbiology presents significant opportunities for studying bacterial pathogenesis and creating computational tools for predicting pathogenic potential. However, the field lacks a comprehensive, curated resource that catalogs bacterial strains and their ability to cause human infections. Current methods for identifying pathogenicity determinants often introduce biases and miss critical aspects of bacterial pathogenesis. In response to this gap, we introduce BacSPaD (Bacterial Strains' Pathogenicity Database), a thoroughly curated database focusing on pathogenicity annotations for a wide range of high-quality, complete bacterial genomes. Our rule-based annotation workflow combines metadata from trusted sources with automated keyword matching, extensive manual curation, and detailed literature review. Our analysis classified 5502 genomes as pathogenic to humans (HP) and 490 as non-pathogenic to humans (NHP), encompassing 532 species, 193 genera, and 96 families. Statistical analysis demonstrated a significant but moderate correlation between virulence factors and HP classification, highlighting the complexity of bacterial pathogenicity and the need for ongoing research. This resource is poised to enhance our understanding of bacterial pathogenicity mechanisms and aid in the development of predictive models. To improve accessibility and provide key visualization statistics, we developed a user-friendly web interface.

Versatile Platinum Nanoparticles-Decorated Phage Nanozyme Integrating Recognition, Bacteriolysis, and Catalysis Capabilities for On-Site Detection of Foodborne Pathogenic Strains Vitality Based on Bioluminescence/Pressure Dual-Mode Bioassay

Sensitive and on-site discrimination of live and dead foodborne pathogenic strains remains a significant challenge due to the lack of appropriate assay and signal probes. In this work, a versatile platinum nanoparticle-decorated phage nanozyme (P2@PtNPs) that integrated recognition, bacteriolysis, and catalysis was designed to establish the bioluminescence/pressure dual-mode bioassay for on-site determination of the vitality of foodborne pathogenic strains. Benefiting from the bacterial strain-level specificity of phage, the target Salmonella typhimurium (S.T) was specially captured to form sandwich complexes with P2@PtNPs on another phage-modified glass microbead (GM@P1). As the other part of the P2@PtNPs nanozyme, the introduced PtNPs could not only catalyze the decomposition of hydrogen peroxide to generate a significant oxygen pressure signal but also produce hydroxyl radicals around the target bacteria to enhance the bacteriolysis of phage and adenosine triphosphate release. It significantly improved the bioluminescence signal. The two signals corresponded to the total and live target bacteria counts, so the dead target could be easily calculated from the difference between the total and live target bacteria counts. Meanwhile, the vitality of S.T was realized according to the ratio of live and total S.T. Under optimal conditions, the application range of this proposed bioassay for bacterial vitality was 102-107 CFU/mL, with a limit of detections for total and live S.T of 30 CFU/mL and 40 CFU/mL, respectively. This work provides an innovative and versatile nanozyme signal probe for the on-site determination of bacterial vitality for food safety.

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

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.

Predicting the pathogenicity of bacterial genomes using widely spread protein families

Background

The human body is inhabited by a diverse community of commensal non-pathogenic bacteria, many of which are essential for our health. By contrast, pathogenic bacteria have the ability to invade their hosts and cause a disease. Characterizing the differences between pathogenic and commensal non-pathogenic bacteria is important for the detection of emerging pathogens and for the development of new treatments. Previous methods for classification of bacteria as pathogenic or non-pathogenic used either raw genomic reads or protein families as features. Using protein families instead of reads provided a better interpretability of the resulting model. However, the accuracy of protein-families-based classifiers can still be improved.

Results

We developed a wide scope pathogenicity classifier (WSPC), a new protein-content-based machine-learning classification model. We trained WSPC on a newly curated dataset of 641 bacterial genomes, where each genome belongs to a different species. A comparative analysis we conducted shows that WSPC outperforms existing models on two benchmark test sets. We observed that the most discriminative protein-family features in WSPC are widely spread among bacterial species. These features correspond to proteins that are involved in the ability of bacteria to survive and replicate during an infection, rather than proteins that are directly involved in damaging or invading the host.

Forest and Trees: Exploring Bacterial Virulence with Genome-wide Association Studies and Machine Learning

The advent of inexpensive and rapid sequencing technologies has allowed bacterial whole-genome sequences to be generated at an unprecedented pace. This wealth of information has revealed an unanticipated degree of strain-to-strain genetic diversity within many bacterial species. Awareness of this genetic heterogeneity has corresponded with a greater appreciation of intraspecies variation in virulence. A number of comparative genomic strategies have been developed to link these genotypic and pathogenic differences with the aim of discovering novel virulence factors. Here, we review recent advances in comparative genomic approaches to identify bacterial virulence determinants, with a focus on genome-wide association studies and machine learning.

Wide range of metabolic adaptations to the acquisition of the Calvin cycle revealed by comparison of microbial genomes

Knowledge of the genetic basis for autotrophic metabolism is valuable since it relates to both the emergence of life and to the metabolic engineering challenge of incorporating CO2 as a potential substrate for biorefining. The most common CO2 fixation pathway is the Calvin cycle, which utilizes Rubisco and phosphoribulokinase enzymes. We searched thousands of microbial genomes and found that 6.0% contained the Calvin cycle. We then contrasted the genomes of Calvin cycle-positive, non-cyanobacterial microbes and their closest relatives by enrichment analysis, ancestral character estimation, and random forest machine learning, to explore genetic adaptations associated with acquisition of the Calvin cycle. The Calvin cycle overlaps with the pentose phosphate pathway and glycolysis, and we could confirm positive associations with fructose-1,6-bisphosphatase, aldolase, and transketolase, constituting a conserved operon, as well as ribulose-phosphate 3-epimerase, ribose-5-phosphate isomerase, and phosphoglycerate kinase. Additionally, carbohydrate storage enzymes, carboxysome proteins (that raise CO2 concentration around Rubisco), and Rubisco activases CbbQ and CbbX accompanied the Calvin cycle. Photorespiration did not appear to be adapted specifically for the Calvin cycle in the non-cyanobacterial microbes under study. Our results suggest that chemoautotrophy in Calvin cycle-positive organisms was commonly enabled by hydrogenase, and less commonly ammonia monooxygenase (nitrification). The enrichment of specific DNA-binding domains indicated Calvin-cycle associated genetic regulation. Metabolic regulatory adaptations were illustrated by negative correlation to AraC and the enzyme arabinose-5-phosphate isomerase, which suggests a downregulation of the metabolite arabinose-5-phosphate, which may interfere with the Calvin cycle through enzyme inhibition and substrate competition. Certain domains of unknown function that were found to be important in the analysis may indicate yet unknown regulatory mechanisms in Calvin cycle-utilizing microbes. Our gene ranking provides targets for experiments seeking to improve CO2 fixation, or engineer novel CO2-fixing organisms.

HDG-select: A novel GUI based application for gene selection and classification in high dimensional datasets

The selection and classification of genes is essential for the identification of related genes to a specific disease. Developing a user-friendly application with combined statistical rigor and machine learning functionality to help the biomedical researchers and end users is of great importance. In this work, a novel stand-alone application, which is based on graphical user interface (GUI), is developed to perform the full functionality of gene selection and classification in high dimensional datasets. The so-called HDG-select application is validated on eleven high dimensional datasets of the format CSV and GEO soft. The proposed tool uses the efficient algorithm of combined filter-GBPSO-SVM and it was made freely available to users. It was found that the proposed HDG-select outperformed other tools reported in literature and presented a competitive performance, accessibility, and functionality.

DeePaC: predicting pathogenic potential of novel DNA with reverse-complement neural networks

MOTIVATION

We expect novel pathogens to arise due to their fast-paced evolution, and new species to be discovered thanks to advances in DNA sequencing and metagenomics. Moreover, recent developments in synthetic biology raise concerns that some strains of bacteria could be modified for malicious purposes. Traditional approaches to open-view pathogen detection depend on databases of known organisms, which limits their performance on unknown, unrecognized and unmapped sequences. In contrast, machine learning methods can infer pathogenic phenotypes from single NGS reads, even though the biological context is unavailable.

RESULTS

We present DeePaC, a Deep Learning Approach to Pathogenicity Classification. It includes a flexible framework allowing easy evaluation of neural architectures with reverse-complement parameter sharing. We show that convolutional neural networks and LSTMs outperform the state-of-the-art based on both sequence homology and machine learning. Combining a deep learning approach with integrating the predictions for both mates in a read pair results in cutting the error rate almost in half in comparison to the previous state-of-the-art.

AVAILABILITY AND IMPLEMENTATION

The code and the models are available at: https://gitlab.com/rki_bioinformatics/DeePaC.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Typing methods based on whole genome sequencing data

Whole genome sequencing (WGS) of foodborne pathogens has become an effective method for investigating the information contained in the genome sequence of bacterial pathogens. In addition, its highly discriminative power enables the comparison of genetic relatedness between bacteria even on a sub-species level. For this reason, WGS is being implemented worldwide and across sectors (human, veterinary, food, and environment) for the investigation of disease outbreaks, source attribution, and improved risk characterization models. In order to extract relevant information from the large quantity and complex data produced by WGS, a host of bioinformatics tools has been developed, allowing users to analyze and interpret sequencing data, starting from simple gene-searches to complex phylogenetic studies. Depending on the research question, the complexity of the dataset and their bioinformatics skill set, users can choose between a great variety of tools for the analysis of WGS data. In this review, we describe the relevant approaches for phylogenomic studies for outbreak studies and give an overview of selected tools for the characterization of foodborne pathogens based on WGS data. Despite the efforts of the last years, harmonization and standardization of typing tools are still urgently needed to allow for an easy comparison of data between laboratories, moving towards a one health worldwide surveillance system for foodborne pathogens.