HUMANN-based system to identify benzimidazole fungicides using multi-synchronous fluorescence spectra: an ensemble approach

Metagenomic analysis of the lung microbiome in pulmonary tuberculosis - a pilot study

The lung microbiome plays an important role in the pathophysiological processes associated with pulmonary tuberculosis (PTB). However, only a few studies using 16S rDNA amplicon sequencing have been reported, and the interactions between Mycobacterium tuberculosis (MTB) and the lung microbiome remain poorly understood. Patients with respiratory symptoms and imaging abnormalities compatible with tuberculosis (TB) were enrolled. We analyzed the lung microbiome in bronchoalveolar lavage (BAL) samples from 30 MTB-positive (MTB+) subjects and 30 MTB negative (MTB-) subjects by shotgun metagenomic sequencing. Alpha diversity tended to be lower in the MTB+ group than in the MTB- group. There was a significant difference in beta diversity between the MTB+ and MTB- subjects. MTB+ lung samples were dominated by MTB, while MTB- samples were enriched with Streptococcus, Prevotella, Nesseria, Selenomonas and Bifidobacterium, which more closely resemble the microbial composition of a healthy lung. Network analysis suggested that MTB could greatly impact the microbial community structure. MTB+ and MTB- communities showed distinct functional signatures. Fungal communities were also found to be associated with the presence or absence of MTB. Furthermore, it was confirmed that 16S rDNA amplicon sequencing underrepresents Mycobacterium. This pilot study is the first to explore the interplay between MTB and the host microbiome by using metagenomic sequencing. MTB dominates the lung microbiome of MTB+ subjects, while MTB- subjects have a Streptococcus-enriched microbiome. The 16S approach underrepresents Mycobacterium and is not the best way to study the TB-associated microbiome.

Supervised neural computing solutions for fluorescence identification of benzimidazole fungicides. Data and decision fusion strategies

Benzimidazole fungicides (BFs) are a type of pesticide of high environmental interest characterized by a heavy fluorescence spectral overlap which complicates its detection in mixtures. In this paper, we present a computational study based on supervised neural networks for a multi-label classification problem. Specifically, backpropagation networks (BPNs) with data fusion and ensemble schemes are used for the simultaneous resolution of difficult multi-fungicide mixtures. We designed, optimized and compared simple BPNs, BPNs with data fusion and BPNs ensembles. The information environment used is made up of synchronous and conventional BF fluorescence spectra. The mixture spectra are not used in the training nor the validation stage. This study allows us to determine the convenience of fusioning the labels of carbendazim and benomyl for the identification of BFs in complex multi-fungicide mixtures.