Clasnip: a web-based intraspecies classifier and multi-locus sequence typing for pathogenic microorganisms using fragmented sequences
Bibliographic record
Abstract
Bioinformatic approaches for the identification of microorganisms have evolved rapidly, but existing methods are time-consuming, complicated or expensive for massive screening of pathogens and their non-pathogenic relatives. Also, bioinformatic classifiers usually lack automatically generated performance statistics for specific databases. To address this problem, we developed Clasnip ( www.clasnip.com ), an easy-to-use web-based platform for the classification and similarity evaluation of closely related microorganisms at interspecies and intraspecies levels. Clasnip mainly consists of two modules: database building and sample classification. In database building, labeled nucleotide sequences are mapped to a reference sequence, and then single nucleotide polymorphisms (SNPs) statistics are generated. A probability model of SNPs and classification groups is built using Hidden Markov Models and solved using the maximum likelihood method. Database performance is estimated using three replicates of two-fold cross-validation. Sensitivity (recall), specificity (selectivity), precision, accuracy and other metrics are computed for all samples, training sets, and test sets. In sample classification, Clasnip accepts inputs of genes, short fragments, contigs and even whole genomes. It can report classification probability and a multi-locus sequence typing table for SNPs. The classification performance was tested using short sequences of 16S, 16–23S and 50S rRNA regions for 12 haplotypes of Candidatus Liberibacter solanacearum (CLso), a regulated plant pathogen associated with severe disease in economically important Apiaceous and Solanaceous crops. The program was able to classify CLso samples with even only 1–2 SNPs available, and achieved 97.2%, 98.8% and 100.0% accuracy based on 16S, 16–23S, and 50S rRNA sequences, respectively. In comparison with all existing 12 haplotypes, we proposed that to be classified as a new haplotype, given samples have at least 2 SNPs in the combined region of 16S rRNA (OA2/Lsc2) and 16–23S IGS (Lp Frag 4–1611F/Lp Frag 4–480R) regions, and 2 SNPs in the 50S rplJ/rplL (CL514F/CL514R) regions. Besides, we have included the databases for differentiating Dickeya spp., Pectobacterium spp. and Clavibacter spp. In addition to bacteria, we also tested Clasnip performance on potato virus Y (PVY). 251 PVY genomes were 100% correctly classified into seven groups (PVY C , PVY N , PVY O , PVY NTN , PVY N:O , Poha, and Chile3). In conclusion, Clasnip is a statistically sound and user-friendly bioinformatic application for microorganism classification at the intraspecies level. Clasnip service is freely available at www.clasnip.com .
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.007 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.005 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".