Dataset Information

2D nanomaterial sensing array using machine learning for differential profiling of pathogenic microbial taxonomic identification.

ABSTRACT: An integrated custom cross-response sensing array has been developed combining the algorithm module's visible machine learning approach for rapid and accurate pathogenic microbial taxonomic identification. The diversified cross-response sensing array consists of two-dimensional nanomaterial (2D-n) with fluorescently labeled single-stranded DNA (ssDNA) as sensing elements to extract a set of differential response profiles for each pathogenic microorganism. By altering the 2D-n and different ssDNA with different sequences, we can form multiple sensing elements. While interacting with microorganisms, the competition between ssDNA and 2D-n leads to the release of ssDNA from 2D-n. The signals are generated from binding force driven by the exfoliation of either ssDNA or 2D-n from the microorganisms. Thus, the signal is distinguished from different ssDNA and 2D-n combinations, differentiating the extracted information and visualizing the recognition process. Fluorescent signals collected from each sensing element at the wavelength around 520 nm are applied to generate a fingerprint. As a proof of concept, we demonstrate that a six-sensing array enables rapid and accurate pathogenic microbial taxonomic identification, including the drug-resistant microorganisms, under a data size of n = 288. We precisely identify microbial with an overall accuracy of 97.9%, which overcomes the big data dependence for identifying recurrent patterns in conventional methods. For each microorganism, the detection concentration is 10⁵ ~ 10⁸ CFU/mL for Escherichia coli, 10² ~ 10⁷ CFU/mL for E. coli-β, 10³ ~ 10⁸ CFU/mL for Staphylococcus aureus, 10³ ~ 10⁷ CFU/mL for MRSA, 10² ~ 10⁸ CFU/mL for Pseudomonas aeruginosa, 10³ ~ 10⁸ CFU/mL for Enterococcus faecalis, 10² ~ 10⁸ CFU/mL for Klebsiella pneumoniae, and 10³ ~ 10⁸ CFU/mL for Candida albicans. Combining the visible machine learning approach, this sensing array provides strategies for precision pathogenic microbial taxonomic identification. • A molecular response differential profiling (MRDP) was established based on custom cross-response sensor array for rapid and accurate recognition and phenotyping common pathogenic microorganism. • Differential response profiling of pathogenic microorganism is derived from the competitive response capacity of 6 sensing elements of the sensor array. Each of these sensing elements' performance has competitive reaction with the microorganism. • MRDP was applied to LDA algorithm and resulted in the classification of 8 microorganisms.

SUBMITTER: Li Z

PROVIDER: S-EPMC9259531 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundTaxonomic classification of genetic markers for microbiome analysis is affected by the numerous choices made from sample preparation to bioinformatics analysis. Paired-end read merging is routinely used to capture the entire amplicon sequence when the read ends overlap. However, the exclusion of unmerged reads from further analysis can result in underestimating the diversity in the sequenced microbial community and is influenced by bioinformatic processes such as read trimming and the choice of reference database. A potential solution to overcome this is to concatenate (join) reads that do not overlap and keep them for taxonomic classification. The use of concatenated reads can outperform taxonomic recovery from single-end reads, but it remains unclear how their performance compares to merged reads. Using various sequenced mock communities with different amplicons, read length, read depth, taxonomic composition, and sequence quality, we tested how merging and concatenating reads performed for genus recall and precision in bioinformatic pipelines combining different parameters for read trimming and taxonomic classification using different reference databases.ResultsThe addition of concatenated reads to merged reads always increased pipeline performance. The top two performing pipelines both included read concatenation, with variable strengths depending on the mock community. The pipeline that combined merged and concatenated reads that were quality-trimmed performed best for mock communities with larger amplicons and higher average quality sequences. The pipeline that used length-trimmed concatenated reads outperformed quality trimming in mock communities with lower quality sequences but lost a significant amount of input sequences for taxonomic classification during processing. Genus level classification was more accurate using the SILVA reference database compared to Greengenes.ConclusionsMerged sequences with the addition of concatenated sequences that were unable to be merged increased performance of taxonomic classifications. This was especially beneficial in mock communities with larger amplicons. We have shown for the first time, using an in-depth comparison of pipelines containing merged vs concatenated reads combined with different trimming parameters and reference databases, the potential advantages of concatenating sequences in improving resolution in microbiome investigations.

Dataset Information

2D nanomaterial sensing array using machine learning for differential profiling of pathogenic microbial taxonomic identification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets