Extracting and Evaluating Features from RNA Virus Sequences to Predict Host Species Susceptibility Using Deep Learning
Bibliographic record
Abstract
Identifying and monitoring hosts of zoonotic RNA viruses, that is, RNA viruses which can be transmitted from one species to another, including the recent SARS-CoV-2 causing the COVID-19 pandemic, is paramount to control their spread. However, efforts to control such spread may be affected if there are unmonitored or unknown hosts. To help identify potential hosts that may harbour such zoonotic viruses, we propose a pipeline that extracts features from sequences of RNA viruses, then uses the extracted features with deep learning to predict host species susceptibility. In addition to using sequence-related features, our method also extracts and uses features derived from the RNA secondary structures that can be formed by the viral sequences, since RNA secondary structures are known to take part in virus-host interaction. We evaluated the performance of our method and the different extracted features with a dataset containing RNA virus sequences and the host they infect, regardless of the viral species, from the NCBI Virus database. Using 10-fold cross validation, we found that a combination of the extracted features yielded the highest overall prediction accuracy of 86.89%.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".