4CAC: 4-class classifier of metagenome contigs using machine learning and assembly graphs

Abstract

Microbial communities usually harbor a mix of bacteria, archaea, phages, plasmids, and microeukaryotes. Phages, plasmids, and microeukaryotes, which are present in low abundance in microbial communities, have complex interactions with bacteria and play important roles in horizontal gene transfer and antibiotic resistance. However, due to the difficulty of identifying phages, plasmids, and microeukaryotes from microbial communities, our understanding of these minor classes lags behind that of bacteria and archaea. Recently, several classifiers have been developed to separate one or two minor classes from bacteria and archaea in metagenome assemblies, but none can classify all of the four classes simultaneously. Moreover, existing classifiers have low precision on minor classes. Here, we developed for the first time a classifier called 4CAC that is able to identify phages, plasmids, microeukaryotes, and prokaryotes simultaneously from metagenome assemblies. 4CAC generates an initial four-way classification using several sequence length-adjusted XGBoost algorithms and further improves the classification using the assembly graph. Evaluation of 4CAC against existing classifiers on simulated and real metagenome datasets demonstrates that 4CAC substantially outperforms existing classifiers on short reads. On long reads, it shows an advantage unless the abundance of the minor classes is very low. It is also by far the fastest. The 4CAC software is available at https://github.com/Shamir-Lab/4CAC.

Modelo de ensamble para predecir el diagnóstico de pacientes con sospecha de Covid-19

“…Los expertos en el campo coinciden en que combinar diferentes modelos en un ensamblado puede ser beneficioso por tres razones principales: Primero, desde una perspectiva estadística, cualquier algoritmo de aprendizaje busca el mejor modelo en un espacio de hipótesis (Pu y Shamir, 2023). Sin embargo, debido a la incertidumbre asociada al proceso de selección del modelo y sus parámetros, siempre existe el riesgo de elegir una hipótesis incorrecta debido a un conjunto de entrenamiento limitado.…”