AliMarko: A Novel Tool for Eukaryotic Virus Identification Using Expert-Guided Approach
Popov, N.; Evdokimova, A.; Sonets, I.; Panova, V.; Molchanova, M.; Korneenko, E.; Manolov, A.; Ilina, E.
Show abstract
Metagenomic sequencing is a valuable tool for studying viral diversity in biological samples. Analyzing this data is complex due to the high variability of viral genomes and their low representation in databases. We present the Alimarko pipeline, designed to streamline virus identification in metagenomic data. A key feature of our tool is the focus on the interpretability of findings: results are provided with tabular and visual information to help determine the confidence level in the identified viral sequences. The pipeline employs two approaches for identifying viral sequences: mapping to reference genomes and de novo assembly followed by the application of Hidden Markov Models (HMM). Additionally, it includes a step for phylogenetic analysis, which constructs a phylogenetic tree to determine the evolutionary relationships with reference sequences. We also emphasize reducing false-positive results. Reads related to cellular organisms are computationally depleted, and the identified viral sequences are checked against a list of potential contaminants. The output is an HTML document containing visualizations and tabular information designed to assist researchers in making informed decisions about the presence of viruses. Using our pipeline for total RNA sequencing of bat feces, we identified a range of viruses and rapidly determined the validity and phylogenetic relationships of the findings to known sequences with the aid of reports generated by AliMarko.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Machine learning using intrinsic genomic signatures for rapid classification of novel pathogens: COVID-19 case study 97%
- Short k-mer Abundance Profiles Yield Robust Machine Learning Features and Accurate Classifiers for RNA Viruses 97%
- Machine learning-based approach KEVOLVE efficiently identifies SARS-CoV-2 variant-specific genomic signatures 96%
Similar papers in this journal
Similar papers in this journal
- Full-length genome sequence of segmented RNA virus from ticks was obtained using small RNA sequencing data 94%
- Isolation and Characterization of a Roseophage Representing a Novel Genus in the N4-like Rhodovirinae Subfamily Distributed in Estuarine Waters 94%
- SARS-CoV-2 surveillance in Italy through phylogenomic inferences based on Hamming distances derived from functional annotations of SNPs, MNPs and InDels 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.