The Naïve Bayes classifier++ for metagenomic taxonomic classification—query evaluation

Haozhe (Neil) Duan, Gavin Hearne, Robi Polikar, Gail L Rosen · 2025

Read The Naïve Bayes classifier++ for metagenomic taxonomic classification—query evaluation by Haozhe (Neil) Duan, Gavin Hearne, Robi Polikar, Gail L Rosen (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11729721.txt.

Description

Naming the microbes in a DNA sample is a first step in much biology. One tool for it is NBC++, a classifier that learns from known genomes. Four authors test how its answers change with word storage style, word length, database size, and sample size. They compare it with the popular tool Kraken2.

Both tools improved as the database deepened, and both still miss much of life's diversity, viruses above all. NBC++ profiled broad groups well even from a small training set, trained faster, and used a fraction of the memory, at the cost of slower queries. New storage tricks cut its footprint further, and its reports now include a confidence-style score for each reference genome. The study dates from 2024 and maps where the tool's strengths lie.

Catalog record

CREATORHaozhe (Neil) Duan, Gavin Hearne, Robi Polikar, Gail L Rosen
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE26 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC11729721

Browse the full library · About the Tower of Babel