A bioinformatics tool for identifying intratumoral microbes from the ORIEN dataset.

Cankun Wang Anjun MaMegan E McNuttRebecca Hoyd Caroline E Dravillas Lary A Robinson Carlos H F ChanYousef ZakhariaRebecca D DoddCornelia M Ulrich Sheetal HardikarMichelle L ChurchmanAhmad A TarhiniEric A SingerAlexandra P Ikeguchi Martin D McCarter Nicholas C Denko Gabriel Tinoco Marium Husain Ning Jin Afaf E G Osman Islam El Jilany Aik Choon TanSamuel S ColemanLouis DenkoGregory M Riedlinger Bryan Paul Schneider Daniel J Spakowicz Qin Ma

Published in: bioRxiv : the preprint server for biology (2023)

Studying the tumor microbiome in high-throughput sequencing data is challenging because of the extremely sparse data matrices, heterogeneity, and high likelihood of contamination. We present a new deep-learning tool, microbial graph attention (MEGA), to refine the organisms that interact with tumors.

Keyphrases

high throughput sequencing
deep learning
electronic health record
big data
convolutional neural network
risk assessment
machine learning
working memory
microbial community
artificial intelligence
neural network
health risk
climate change
human health