Classification Experiments of DNA Sequences by Using a Deep Neural Network and Chaos Game Representation

Rizzo, Riccardo; Fiannaca, Antonino; Rosa, Massimo La; Urso, Alfonso

doi:10.1145/2983468.2983489

Cited by 30 publications

(37 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chaos game representation (CGR) and its extension, the frequency matrix CGR (FCGR) are promising alternatives able to encode an arbitrary sequence in an image-like format. FCGR has been used to encode genomic inputs for deep learning approaches, including full bacterial genomes (22) and coding sequences of HIV for the drug resistance prediction task (23). In this study, we use one-hot encoding with N s as zeroes, which was previously shown to perform well for raw NGS reads (24) and abstract phenotype labels.…”

Section: Deep Learning For Dna Sequencesmentioning

confidence: 99%

Interpretable detection of novel human viruses from genome sequencing data

Bartoszewicz

Seidel

Renard

2020

Preprint

View full text Add to dashboard Cite

AbstractViruses evolve extremely quickly, so reliable methods for viral host prediction are necessary to safeguard biosecurity and biosafety alike. Novel human-infecting viruses are difficult to detect with standard bioinformatics workflows. Here, we predict whether a virus can infect humans directly from next-generation sequencing reads. We show that deep neural architectures significantly outperform both shallow machine learning and standard, homology-based algorithms, cutting the error rates in half and generalizing to taxonomic units distant from those presented during training. We propose a new approach for convolutional filter visualization to disentangle the information content of each nucleotide from its contribution to the final classification decision. Nucleotide-resolution maps of the learned associations between pathogen genomes and the infectious phenotype can be used to detect virulence-related genes in novel agents, for example the SARS-CoV-2 coronavirus, unknown before it caused a COVID-19 pandemic in 2020.

show abstract

Section: Deep Learning For Dna Sequencesmentioning

confidence: 99%

Interpretable detection of novel human viruses from genome sequencing data

Bartoszewicz

Seidel

Renard

2020

Preprint

View full text Add to dashboard Cite

show abstract

“… Wang et al (2005) used FCGR to calculate the image distance between genomes to generate phylogenetic trees. Rizzo et al (2016) showed that deep neural networks (DNNs) trained on genomes encoded with FCGR yielded very accurate predictions. They used a convolutional neural network (CNN) to divide bacteria into three different phyla, order, family and genus, and showed very high accuracy for the method.…”

Section: Introductionmentioning

confidence: 99%

Prediction of antimicrobial resistance based on whole-genome sequencing and machine learning

et al. 2021

View full text Add to dashboard Cite

Motivation Antimicrobial resistance (AMR) is one of the biggest global problems threatening human and animal health. Rapid and accurate AMR diagnostic methods are thus very urgently needed. However, traditional antimicrobial susceptibility testing (AST) is time-consuming, low throughput, and viable only for cultivable bacteria. Machine learning methods may pave the way for automated AMR prediction based on genomic data of the bacteria. However, comparing different machine learning methods for the prediction of AMR based on different encodings and whole-genome sequencing data without previously known knowledge remains to be done. Results In the current study, we evaluated logistic regression (LR), support vector machine (SVM), random forest (RF), and convolutional neural network (CNN) for the prediction of AMR for the antibiotics ciprofloxacin (CIP), cefotaxime (CTX), ceftazidime (CTZ), and gentamicin (GEN). We could demonstrate that these models can effectively predict AMR with label encoding, one-hot encoding, and frequency matrix chaos game representation (FCGR encoding) on whole-genome sequencing data. We trained these models on a large AMR dataset and evaluated them on an independent public data set. Generally, RFs and CNNs perform better than LR and SVM with AUCs up to 0.96. Furthermore, we were able to identify mutations that are associated with AMR for each antibiotic. Availability Source code in data preparation and model training are provided at GitHub website (https://github.com/YunxiaoRen/ML-iAMR). Supplementary information Supplementary data are available at Bioinformatics online.

show abstract

“…Chaos game representation (CGR) and its extension, the frequency matrix CGR (FCGR) are promising alternatives able to encode an arbitrary sequence in an image-like format. FCGR has been used to encode genomic inputs for deep learning approaches, including full bacterial genomes ( 22 ) and coding sequences of HIV for the drug resistance prediction task ( 23 ). In this study, we use one-hot encoding with N s as zeroes, which was previously shown to perform well for raw NGS reads ( 24 ) and abstract phenotype labels.…”

Section: Introductionmentioning

confidence: 99%

Interpretable detection of novel human viruses from genome sequencing data

Bartoszewicz

Seidel

Renard

2021

NAR Genomics and Bioinformatics

View full text Add to dashboard Cite

Viruses evolve extremely quickly, so reliable methods for viral host prediction are necessary to safeguard biosecurity and biosafety alike. Novel human-infecting viruses are difficult to detect with standard bioinformatics workflows. Here, we predict whether a virus can infect humans directly from next-generation sequencing reads. We show that deep neural architectures significantly outperform both shallow machine learning and standard, homology-based algorithms, cutting the error rates in half and generalizing to taxonomic units distant from those presented during training. Further, we develop a suite of interpretability tools and show that it can be applied also to other models beyond the host prediction task. We propose a new approach for convolutional filter visualization to disentangle the information content of each nucleotide from its contribution to the final classification decision. Nucleotide-resolution maps of the learned associations between pathogen genomes and the infectious phenotype can be used to detect regions of interest in novel agents, for example, the SARS-CoV-2 coronavirus, unknown before it caused a COVID-19 pandemic in 2020. All methods presented here are implemented as easy-to-install packages not only enabling analysis of NGS datasets without requiring any deep learning skills, but also allowing advanced users to easily train and explain new models for genomics.

show abstract

Classification Experiments of DNA Sequences by Using a Deep Neural Network and Chaos Game Representation

Cited by 30 publications

References 18 publications

Interpretable detection of novel human viruses from genome sequencing data

Interpretable detection of novel human viruses from genome sequencing data

Prediction of antimicrobial resistance based on whole-genome sequencing and machine learning

Interpretable detection of novel human viruses from genome sequencing data

Contact Info

Product

Resources

About