Better data for better predictions: data curation improves deep learning for sgRNA/Cas9 prediction
Bibliographic record
Abstract
ABSTRACT The Cas9 enzyme along with a single guide RNA molecule is a modular tool for genetic engineering and has shown effectiveness as a species-specific anti-microbial. The ability to accurately predict on-target cleavage is critical as activity varies by target. Using the sgRNA nucleotide sequence and an activity score, predictive models have been developed with the best performance resulting from deep learning architectures. Prior work has emphasized robust and novel architectures to improve predictive performance. Here, we explore the impact of a data-centric approach through optimization of the input target site adjacent nucleotide sequence length and the use of data filtering for read counts in the control conditions to improve input data utility. Using the existing crisprHAL architecture, we develop crisprHAL Tev, a best-in-class bacterial SpCas9 prediction model with performance that generalizes between related species and across data types. During this process, we also rebuild two prior E. coli Cas9 datasets, demonstrating the importance of data quality, and resulting in the production of an improved bacterial eSpCas9 prediction model. The crisprHAL models are available through GitHub ( https://github.com/tbrowne/crisprHAL ).
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 | 0.006 | 0.027 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.001 | 0.004 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".