Dataset Information

Fusing dual-event data sets for Mycobacterium tuberculosis machine learning models and their evaluation.

ABSTRACT: The search for new tuberculosis treatments continues as we need to find molecules that can act more quickly, be accommodated in multidrug regimens, and overcome ever increasing levels of drug resistance. Multiple large scale phenotypic high-throughput screens against Mycobacterium tuberculosis (Mtb) have generated dose response data, enabling the generation of machine learning models. These models also incorporated cytotoxicity data and were recently validated with a large external data set. A cheminformatics data-fusion approach followed by Bayesian machine learning, Support Vector Machine, or Recursive Partitioning model development (based on publicly available Mtb screening data) was used to compare individual data sets and subsequent combined models. A set of 1924 commercially available molecules with promising antitubercular activity (and lack of relative cytotoxicity to Vero cells) were used to evaluate the predictive nature of the models. We demonstrate that combining three data sets incorporating antitubercular and cytotoxicity data in Vero cells from our previous screens results in external validation receiver operator curve (ROC) of 0.83 (Bayesian or RP Forest). Models that do not have the highest 5-fold cross-validation ROC scores can outperform other models in a test set dependent manner. We demonstrate with predictions for a recently published set of Mtb leads from GlaxoSmithKline that no single machine learning model may be enough to identify compounds of interest. Data set fusion represents a further useful strategy for machine learning construction as illustrated with Mtb. Coverage of chemistry and Mtb target spaces may also be limiting factors for the whole-cell screening data generated to date.

SUBMITTER: Ekins S

PROVIDER: S-EPMC3910492 | biostudies-literature | 2013 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Fusing dual-event data sets for Mycobacterium tuberculosis machine learning models and their evaluation.

Ekins Sean S Freundlich Joel S JS Reynolds Robert C RC

Journal of chemical information and modeling 20131030 11

The search for new tuberculosis treatments continues as we need to find molecules that can act more quickly, be accommodated in multidrug regimens, and overcome ever increasing levels of drug resistance. Multiple large scale phenotypic high-throughput screens against Mycobacterium tuberculosis (Mtb) have generated dose response data, enabling the generation of machine learning models. These models also incorporated cytotoxicity data and were recently validated with a large external data set. A c ...[more]

PMID: 24144044

Similar Datasets

Project description:BackgroundThe diagnosis of multidrug resistant and extensively drug resistant tuberculosis is a global health priority. Whole genome sequencing of clinical Mycobacterium tuberculosis isolates promises to circumvent the long wait times and limited scope of conventional phenotypic antimicrobial susceptibility, but gaps remain for predicting phenotype accurately from genotypic data especially for certain drugs. Our primary aim was to perform an exploration of statistical learning algorithms and genetic predictor sets using a rich dataset to build a high performing and fast predicting model to detect anti-tuberculosis drug resistance.MethodsWe collected targeted or whole genome sequencing and conventional drug resistance phenotyping data from 3601 Mycobacterium tuberculosis strains enriched for resistance to first- and second-line drugs, with 1228 multidrug resistant strains. We investigated the utility of (1) rare variants and variants known to be determinants of resistance for at least one drug and (2) machine and statistical learning architectures in predicting phenotypic drug resistance to 10 anti-tuberculosis drugs. Specifically, we investigated multitask and single task wide and deep neural networks, a multilayer perceptron, regularized logistic regression, and random forest classifiers.FindingsThe highest performing machine and statistical learning methods included both rare variants and those known to be causal of resistance for at least one drug. Both simpler L2 penalized regression and complex machine learning models had high predictive performance. The average AUCs for our highest performing model was 0.979 for first-line drugs and 0.936 for second-line drugs during repeated cross-validation. On an independent validation set, the highest performing model showed average AUCs, sensitivities, and specificities, respectively, of 0.937, 87.9%, and 92.7% for first-line drugs and 0.891, 82.0% and 90.1% for second-line drugs. Our method outperforms existing approaches based on direct association, with increased sum of sensitivity and specificity of 11.7% on first line drugs and 3.2% on second line drugs. Our method has higher predictive performance compared to previously reported machine learning models during cross-validation, with higher AUCs for 8 of 10 drugs.InterpretationStatistical models, especially those that are trained using both frequent and less frequent variants, significantly improve the accuracy of resistance prediction and hold promise in bringing sequencing technologies closer to the bedside.

Project description:Infra-species taxonomy is a prerequisite to compare features such as virulence in different pathogen lineages. Mycobacterium tuberculosis complex taxonomy has rapidly evolved in the last 20 years through intensive clinical isolation, advances in sequencing and in the description of fast-evolving loci (CRISPR and MIRU-VNTR). On-line tools to describe new isolates have been set up based on known diversity either on CRISPRs (also known as spoligotypes) or on MIRU-VNTR profiles. The underlying taxonomies are largely concordant but use different names and offer different depths. The objectives of this study were 1) to explicit the consensus that exists between the alternative taxonomies, and 2) to provide an on-line tool to ease classification of new isolates. Genotyping (24-VNTR, 43-spacers spoligotypes, IS6110-RFLP) was undertaken for 3,454 clinical isolates from the Netherlands (2004-2008). The resulting database was enlarged with African isolates to include most human tuberculosis diversity. Assignations were obtained using TB-Lineage, MIRU-VNTRPlus, SITVITWEB and an algorithm from Borile et al. By identifying the recurrent concordances between the alternative taxonomies, we proposed a consensus including 22 sublineages. Original and consensus assignations of the all isolates from the database were subsequently implemented into an ensemble learning approach based on Machine Learning tool Weka to derive a classification scheme. All assignations were reproduced with very good sensibilities and specificities. When applied to independent datasets, it was able to suggest new sublineages such as pseudo-Beijing. This Lineage Prediction tool, efficient on 15-MIRU, 24-VNTR and spoligotype data is available on the web interface "TBminer." Another section of this website helps summarizing key molecular epidemiological data, easing tuberculosis surveillance. Altogether, we successfully used Machine Learning on a large dataset to set up and make available the first consensual taxonomy for human Mycobacterium tuberculosis complex. Additional developments using SNPs will help stabilizing it.

Dataset Information

Fusing dual-event data sets for Mycobacterium tuberculosis machine learning models and their evaluation.

Publications

Fusing dual-event data sets for Mycobacterium tuberculosis machine learning models and their evaluation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets