Dataset Information

Machine learning with random subspace ensembles identifies antimicrobial resistance determinants from pan-genomes of three pathogens.

ABSTRACT: The evolution of antimicrobial resistance (AMR) poses a persistent threat to global public health. Sequencing efforts have already yielded genome sequences for thousands of resistant microbial isolates and require robust computational tools to systematically elucidate the genetic basis for AMR. Here, we present a generalizable machine learning workflow for identifying genetic features driving AMR based on constructing reference strain-agnostic pan-genomes and training random subspace ensembles (RSEs). This workflow was applied to the resistance profiles of 14 antimicrobials across three urgent threat pathogens encompassing 288 Staphylococcus aureus, 456 Pseudomonas aeruginosa, and 1588 Escherichia coli genomes. We find that feature selection by RSE detects known AMR associations more reliably than common statistical tests and previous ensemble approaches, identifying a total of 45 known AMR-conferring genes and alleles across the three organisms, as well as 25 candidate associations backed by domain-level annotations. Furthermore, we find that results from the RSE approach are consistent with existing understanding of fluoroquinolone (FQ) resistance due to mutations in the main drug targets, gyrA and parC, in all three organisms, and suggest the mutational landscape of those genes with respect to FQ resistance is simple. As larger datasets become available, we expect this approach to more reliably predict AMR determinants for a wider range of microbial pathogens.

SUBMITTER: Hyun JC

PROVIDER: S-EPMC7067475 | biostudies-literature | 2020 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning with random subspace ensembles identifies antimicrobial resistance determinants from pan-genomes of three pathogens.

Hyun Jason C JC Kavvas Erol S ES Monk Jonathan M JM Palsson Bernhard O BO

PLoS computational biology 20200302 3

The evolution of antimicrobial resistance (AMR) poses a persistent threat to global public health. Sequencing efforts have already yielded genome sequences for thousands of resistant microbial isolates and require robust computational tools to systematically elucidate the genetic basis for AMR. Here, we present a generalizable machine learning workflow for identifying genetic features driving AMR based on constructing reference strain-agnostic pan-genomes and training random subspace ensembles ( ...[more]

PMID: 32119670

Similar Datasets

Project description:BackgroundAutomated, image based high-content screening is a fundamental tool for discovery in biological science. Modern robotic fluorescence microscopes are able to capture thousands of images from massively parallel experiments such as RNA interference (RNAi) or small-molecule screens. As such, efficient computational methods are required for automatic cellular phenotype identification capable of dealing with large image data sets. In this paper we investigated an efficient method for the extraction of quantitative features from images by combining second order statistics, or Haralick features, with curvelet transform. A random subspace based classifier ensemble with multiple layer perceptron (MLP) as the base classifier was then exploited for classification. Haralick features estimate image properties related to second-order statistics based on the grey level co-occurrence matrix (GLCM), which has been extensively used for various image processing applications. The curvelet transform has a more sparse representation of the image than wavelet, thus offering a description with higher time frequency resolution and high degree of directionality and anisotropy, which is particularly appropriate for many images rich with edges and curves. A combined feature description from Haralick feature and curvelet transform can further increase the accuracy of classification by taking their complementary information. We then investigate the applicability of the random subspace (RS) ensemble method for phenotype classification based on microscopy images. A base classifier is trained with a RS sampled subset of the original feature set and the ensemble assigns a class label by majority voting.ResultsExperimental results on the phenotype recognition from three benchmarking image sets including HeLa, CHO and RNAi show the effectiveness of the proposed approach. The combined feature is better than any individual one in the classification accuracy. The ensemble model produces better classification performance compared to the component neural networks trained. For the three images sets HeLa, CHO and RNAi, the Random Subspace Ensembles offers the classification rates 91.20%, 98.86% and 91.03% respectively, which compares sharply with the published result 84%, 93% and 82% from a multi-purpose image classifier WND-CHARM which applied wavelet transforms and other feature extraction methods. We investigated the problem of estimation of ensemble parameters and found that satisfactory performance improvement could be brought by a relative medium dimensionality of feature subsets and small ensemble size.ConclusionsThe characteristics of curvelet transform of being multiscale and multidirectional suit the description of microscopy images very well. It is empirically demonstrated that the curvelet-based feature is clearly preferred to wavelet-based feature for bioimage descriptions. The random subspace ensemble of MLPs is much better than a number of commonly applied multi-class classifiers in the investigated application of phenotype recognition.

Project description:Infectious diarrhea affects over four billion individuals annually and causes over a million deaths each year. Though not typically prescribed for treatment of uncomplicated diarrheal disease, antimicrobials serve as a critical part of the armamentarium used to treat severe or persistent cases. Due to widespread over- and misuse of antimicrobials, there has been an alarming increase in global resistance, for which a standardized methodology for geographic surveillance would be highly beneficial. To demonstrate that a standardized methodology could be used to provide molecular surveillance of antimicrobial resistance (AMR) genes, we initiated a pilot study to test 130 diarrheal pathogens (Campylobacter spp., Escherichia coli, Salmonella, and Shigella spp.) from the USA, Peru, Egypt, Cambodia, and Kenya for the presence/absence of over 200 AMR determinants. We detected a total of 55 different determinants conferring resistance to ten different categories of antimicrobials: genes detected in ≥ 25 samples included blaTEM, tet(A), tet(B), mac(A), mac(B), aadA1/A2, strA, strB, sul1, sul2, qacEΔ1, cmr, and dfrA1. The number of determinants per strain ranged from none (several Campylobacter spp. strains) to sixteen, with isolates from Egypt harboring a wider variety and greater number of genes per isolate than other sites. Two samples harbored carbapenemase genes, blaOXA-48 or blaNDM. Genes conferring resistance to azithromycin (ere(A), mph(A)/mph(K), erm(B)), a first-line therapeutic for severe diarrhea, were detected in over 10% of all Enterobacteriaceae tested: these included >25% of the Enterobacteriaceae from Egypt and Kenya. Forty-six percent of the Egyptian Enterobacteriaceae harbored genes encoding CTX-M-1 or CTX-M-9 families of extended-spectrum β-lactamases. Overall, the data provide cross-comparable resistome information to establish regional trends in support of international surveillance activities and potentially guide geospatially informed medical care.

Project description:BackgroundOxidative stress produced a large amount of reactive oxygen species (ROS), which played a pivotal role in balanced ability and determining cell fate. The activated Nrf2 signaling pathway that responds to the excessive ROS regulated the expressions of antiapoptotic proteins, antioxidative enzymes, drug transporters, and detoxifying factors.MethodsThe Nrf2 signaling pathway-related genes that had a direct relationship with Nrf2, including ATF4, BACH1, CREBBP, CUL3, EIF2AK3, EP300, FOS, FOSL1, GSK3B, JUN, KEAP1, MAF, MAFF, MAFG, MAFK, MAPK1, MAPK3, MAPK7, MAPK8, MAPK9, PIK3CA, PRRT2, and RIT1, were selected to do a systematic pan-cancer analysis. The relationship of Nrf2 signaling pathway-related gene expressions with tumor mutation burden, microsatellite status, clinical characteristics, immune system, cancer stemness index, and drug sensitivity was calculated by the Spearson correlation analysis across 11,057 subjects representing 33 cancer types. The prognosis models in lung squamous carcinoma, breast cancer, and stomach cancer were constructed with the Cox multivariate regression analysis and least absolute shrinkage and selection operator (Lasso) regression.ResultsMany Nrf2 signaling pathway-related genes were differently expressed between tumor and normal tissues. PIK3CA showed high mutation rate in pan-cancer. The expressions of Nrf2 signaling pathway-related genes were significantly related to tumor mutation burden, copy number variant, microsatellite instability score, survival rate, pathological stage, immune phenotype, immune score, immune cell, cancer stemness index, and drug sensitivity. The prognosis models were significantly associated with survival rate in lung squamous carcinoma, breast cancer, and stomach cancer; and the prognosis model-based riskscore was significantly associated with clinicopathological characteristics of each cancer.ConclusionsThe study provided a comprehensive pan-cancer landscape of Nrf2 pathway-related genes. Based on the same Nrf2 pathway-related genes, the different prognosis models were constructed for different types of cancers.

Dataset Information

Machine learning with random subspace ensembles identifies antimicrobial resistance determinants from pan-genomes of three pathogens.

Publications

Machine learning with random subspace ensembles identifies antimicrobial resistance determinants from pan-genomes of three pathogens.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets