ML-DSP: Machine Learning with Digital Signal Processing for ultrafast, accurate, and scalable genome classification at all taxonomic levels
Bibliographic record
Abstract
Abstract Background Although methods and software tools abound for the comparison, analysis, identification, and taxonomic classification of the enormous amount of genomic sequences that are continuously being produced, taxonomic classification remains challenging. The difficulty lies within both the magnitude of the dataset and the intrinsic problems associated with classification. The need exists for an approach and software tool that addresses the limitations of existing alignment-based methods, as well as the challenges of recently proposed alignment-free methods. Results We combine supervised M achine L earning with D igital S ignal P rocessing to design ML-DSP , an alignment-free software tool for ultrafast, accurate, and scalable genome classification at all taxonomic levels. We test ML-DSP by classifying 7,396 full mitochondrial genomes from the kingdom to genus levels, with 98% classification accuracy. Compared with the alignment-based classification tool MEGA7 (with sequences aligned with either MUSCLE, or CLUSTALW), ML-DSP has similar accuracy scores while being significantly faster on two small benchmark datasets (2,250 to 67,600 times faster for 41 mammalian mitochondrial genomes). ML-DSP also successfully scales to accurately classify a large dataset of 4,322 complete vertebrate mtDNA genomes, a task which MEGA7 with MUSCLE or CLUSTALW did not complete after several hours, and had to be terminated. ML-DSP also outperforms the alignment-free tool FFP (Feature Frequency Profiles) in terms of both accuracy and time, being three times faster for the vertebrate mtDNA genomes dataset. Conclusions We provide empirical evidence that ML-DSP distinguishes complete genome sequences at all taxonomic levels. Ultrafast and accurate taxonomic classification of genomic sequences is predicted to be highly relevant in the classification of newly discovered organisms, in distinguishing genomic signatures, in identifying mechanistic determinants of genomic signatures, and in evaluating genome integrity.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.007 | 0.004 |
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".