Mycofier: a new machine learning-based classifier for fungal ITS sequences.

BACKGROUND: The taxonomic and phylogenetic classification based on sequence analysis of the ITS1 genomic region has become a crucial component of fungal ecology and diversity studies. Nowadays, there is no accurate alignment-free classification tool for fungal ITS1 sequences for large environmental surveys. This study describes the development of a machine learning-based classifier for the taxonomical assignment of fungal ITS1 sequences at the genus level. RESULTS: A fungal ITS1 sequence database was built using curated data. Training and test sets were generated from it. A Naïve Bayesian classifier was built using features from the primary sequence with an accuracy of 87 % in the classification at the genus level. CONCLUSIONS: The final model was based on a Naïve Bayes algorithm using ITS1 sequences from 510 fungal genera. This classifier, denoted as Mycofier, provides similar classification accuracy compared to BLASTN, but the database used for the classification contains curated data and the tool, independent of alignment, is more efficient and contributes to the field, given the lack of an accurate classification tool for large data from fungal ITS1 sequences. The software and source code for Mycofier are freely available at https://github.com/ldelgado-serrano/mycofier.git .

Respiratory tract clinical sample selection for microbiota analysis in patients with pulmonary tuberculosis.

BACKGROUND: Changes in respiratory tract microbiota have been associated with diseases such as tuberculosis, a global public health problem that affects millions of people each year. This pilot study was carried out using sputum, oropharynx, and nasal respiratory tract samples collected from patients with pulmonary tuberculosis and healthy control individuals, in order to compare sample types and their usefulness in assessing changes in bacterial and fungal communities. FINDINGS: Most V1-V2 16S rRNA gene sequences belonged to the phyla Firmicutes, Bacteroidetes, Proteobacteria, Actinobacteria, and Fusobacteria, with differences in relative abundances and in specific taxa associated with each sample type. Most fungal ITS1 sequences were classified as Ascomycota and Basidiomycota, but abundances differed for the different samples. Bacterial and fungal community structures in oropharynx and sputum samples were similar to one another, as indicated by several beta diversity analyses, and both differed from nasal samples. The only difference between patient and control microbiota was found in oropharynx samples for both bacteria and fungi. Bacterial diversity was greater in sputum samples, while fungal diversity was greater in nasal samples. CONCLUSIONS: Respiratory tract microbial communities were similar in terms of the major phyla identified, yet they varied in terms of relative abundances and diversity indexes. Oropharynx communities varied with respect to health status and resembled those in sputum samples, which are collected from tuberculosis patients only due to the difficulty in obtaining sputum from healthy individuals, suggesting that oropharynx samples can be used to analyze community structure alterations associated with tuberculosis.