DeepAMR for predicting co-occurrent resistance of Mycobacterium tuberculosis

Abstract Motivation Resistance co-occurrence within first-line anti-tuberculosis (TB) drugs is a common phenomenon. Existing methods based on genetic data analysis of Mycobacterium tuberculosis (MTB) have been able to predict resistance of MTB to individual drugs, but have not considered the resistance co-occurrence and cannot capture latent structure of genomic data that corresponds to lineages. Results We used a large cohort of TB patients from 16 countries across six continents where whole-genome sequences for each isolate and associated phenotype to anti-TB drugs were obtained using drug susceptibility testing recommended by the World Health Organization. We then proposed an end-to-end multi-task model with deep denoising auto-encoder (DeepAMR) for multiple drug classification and developed DeepAMR_cluster, a clustering variant based on DeepAMR, for learning clusters in latent space of the data. The results showed that DeepAMR outperformed baseline model and four machine learning models with mean AUROC from 94.4% to 98.7% for predicting resistance to four first-line drugs [i.e. isoniazid (INH), ethambutol (EMB), rifampicin (RIF), pyrazinamide (PZA)], multi-drug resistant TB (MDR-TB) and pan-susceptible TB (PANS-TB: MTB that is susceptible to all four first-line anti-TB drugs). In the case of INH, EMB, PZA and MDR-TB, DeepAMR achieved its best mean sensitivity of 94.3%, 91.5%, 87.3% and 96.3%, respectively. While in the case of RIF and PANS-TB, it generated 94.2% and 92.2% sensitivity, which were lower than baseline model by 0.7% and 1.9%, respectively. t-SNE visualization shows that DeepAMR_cluster captures lineage-related clusters in the latent space. Availability and implementation The details of source code are provided at http://www.robots.ox.ac.uk/∼davidc/code.php. Supplementary information Supplementary data are available at Bioinformatics online.

[1]  Barbara Hammer,et al.  Parametric nonlinear dimensionality reduction using kernel t-SNE , 2015, Neurocomputing.

[2]  Zhaolei Zhang,et al.  Deep Autoencoders for Dimensionality Reduction of High-Content Screening Data , 2015, ArXiv.

[3]  Dongfang Li,et al.  Genome sequencing of 161 Mycobacterium tuberculosis isolates from China identifies genes and intergenic regions associated with drug resistance , 2013, Nature Genetics.

[4]  Zhi-Hua Zhou,et al.  Multilabel Neural Networks with Applications to Functional Genomics and Text Categorization , 2006, IEEE Transactions on Knowledge and Data Engineering.

[5]  Csaba Szepesvári,et al.  Deep Representations and Codes for Image Auto-Annotation , 2012, NIPS.

[6]  Christian Stolte,et al.  Genetic Determinants of Drug Resistance in Mycobacterium tuberculosis and Their Diagnostic Value. , 2016, American journal of respiratory and critical care medicine.

[7]  Phelim Bradley,et al.  Whole-genome sequencing for prediction of Mycobacterium tuberculosis drug susceptibility and resistance: a retrospective cohort study , 2015, The Lancet. Infectious diseases.

[8]  Volker Tresp,et al.  Multi-label informed latent semantic indexing , 2005, SIGIR '05.

[9]  Hans-Peter Kriegel,et al.  Multi-Output Regularized Feature Projection , 2006, IEEE Transactions on Knowledge and Data Engineering.

[10]  Jianmin Wang,et al.  Multi-label Classification via Feature-aware Implicit Label Space Encoding , 2014, ICML.

[11]  M. Donald Cave,et al.  Population Genetics Study of Isoniazid Resistance Mutations and Evolution of Multidrug-Resistant Mycobacterium tuberculosis , 2006, Antimicrobial Agents and Chemotherapy.

[12]  Zhi-Hua Zhou,et al.  Multilabel dimensionality reduction via dependence maximization , 2008, TKDD.

[13]  Leland McInnes,et al.  UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction , 2018, ArXiv.

[14]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.

[15]  Eyke Hüllermeier,et al.  Multilabel classification for exploiting cross-resistance information in HIV-1 drug resistance prediction , 2013, Bioinform..

[16]  Michael I. Jordan,et al.  DiscLDA: Discriminative Learning for Dimensionality Reduction and Classification , 2008, NIPS.

[17]  Xiangji Huang,et al.  Discovery of the relations between genetic polymorphism and adverse drug reactions , 2015, 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[18]  Wei Wang,et al.  Multi-task deep neural network for multi-label learning , 2013, 2013 IEEE International Conference on Image Processing.

[19]  David A. Clifton,et al.  Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data , 2017, Bioinform..

[20]  Phelim Bradley,et al.  Evaluation of Whole-Genome Sequencing for Mycobacterial Species Identification and Drug Susceptibility Testing in a Clinical Setting: a Large-Scale Prospective Assessment of Performance against Line Probe Assays and Phenotyping , 2017, Journal of Clinical Microbiology.

[21]  Tao Mei,et al.  Correlative multi-label video annotation , 2007, ACM Multimedia.

[22]  Geoff Holmes,et al.  Classifier chains for multi-label classification , 2009, Machine Learning.

[23]  Eyke Hüllermeier,et al.  Bayes Optimal Multilabel Classification via Probabilistic Classifier Chains , 2010, ICML.

[24]  Xinghua Shi,et al.  A predictive model of gene expression using a deep learning framework , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[25]  V Sintchenko,et al.  Mutations in rpoB gene and rifabutin susceptibility of multidrug-resistant Mycobacterium tuberculosis strains isolated in Australia. , 1999, Pathology.

[26]  Eyke Hüllermeier,et al.  Exploiting HIV-1 protease and reverse transcriptase cross-resistance information for improved drug resistance prediction by means of multi-label classification , 2016, BioData Mining.

[27]  Stefan Kramer,et al.  A Nonlinear Label Compression and Transformation Method for Multi-label Classification Using Autoencoders , 2016, PAKDD.

[28]  Annelies Van Rie,et al.  Analysis for a Limited Number of Gene Codons Can Predict Drug Resistance of Mycobacterium tuberculosis in a High-Incidence Community , 2001, Journal of Clinical Microbiology.

[29]  Liang Wang,et al.  Unconstrained Multimodal Multi-Label Learning , 2015, IEEE Transactions on Multimedia.

[30]  Zhi-Hua Zhou,et al.  ML-KNN: A lazy learning approach to multi-label learning , 2007, Pattern Recognit..

[31]  Pascal Vincent,et al.  The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training , 2009, AISTATS.

[32]  Mehmet Gönen,et al.  Coupled dimensionality reduction and classification for supervised and semi-supervised multilabel learning , 2014, Pattern Recognit. Lett..

[33]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .