Can I read DeepViFi: detecting oncoviral infections in cancer genomes using transformers on EtoBox?

DeepViFi: detecting oncoviral infections in cancer genomes using transformers by Utkrisht Rajkumar; Sara Javadzadeh; Mihir Bafna; Dongxia Wu; Rose Yu; Jingbo Shang; Vineet Bafna is a scholarly article available to read on EtoBox.

What is DeepViFi: detecting oncoviral infections in cancer genomes using transformers about?

We consider the problem of identifying viral reads in human host genome data. We pose the problem as open-set classification as reads can originate from unknown sources such as bacterial and fungal genomes. Sequence-matching methods have low sensitivity in recognizing viral reads when the viral family is highly diverged. Hidden Markov models have higher sensitivity but require domainspecific training and are difficult to repurpose for identifying different viral families. Supervised learning methods can be trained with little domain-specific knowledge but have reduced sensitivity in open-set scenarios. We present DeepViFi, a transformer-based pipeline, to detect viral reads in short-read whole genome sequence data. At 90% precision, DeepViFi achieves 90% recall compared to 15% for other deep learning methods. DeepViFi provides a semisupervised framework to learn representations of viral families without domain-specific knowledge, and rapidly and accurately identify target sequences in open-set settings. CCS CONCEPTS • Computing methodologies → Machine learning; Natural language processing; • Applied computing → Bioinformatics.

Author

Utkrisht Rajkumar; Sara Javadzadeh; Mihir Bafna; Dongxia Wu; Rose Yu; Jingbo Shang; Vineet Bafna

Publisher

ACM

Published

2022

Language

EN