Integrating Machine Learning-Based Approaches into the Design of ASO Therapies
Bibliographic record
Abstract
Rare diseases impose a significant burden on affected individuals, caregivers, and healthcare systems worldwide. Developing effective therapeutics for these small patient populations presents substantial challenges. Antisense oligonucleotides (ASOs) have emerged as a promising therapeutic approach that targets the underlying genetic cause of disease at the RNA level. Several ASOs have gained FDA approval for the treatment of genetic conditions, including use in personalized N-of-1 trials. However, despite their potential, ASOs often exhibit limited clinical efficacy, and optimizing their design is a complex process influenced by numerous factors. Machine learning-based platforms, including eSkip-Finder and ASOptimizer, have been developed to address these challenges by predicting optimal ASO sequences and chemical modifications to enhance efficacy. eSkip-Finder focuses on exon-skipping applications, while ASOptimizer aims to optimize ASOs for RNA degradation. Preliminary in vitro results have demonstrated the promising predictive power of these platforms. However, limitations remain, including their generalizability to alternative targets and gaps in their consideration of all factors influencing ASO efficacy and safety. Continued advancements in machine learning models, alongside efforts to incorporate additional features affecting ASO efficacy and safety, hold significant promise for the field. These platforms have the potential to streamline ASO development, reduce associated costs, and improve clinical outcomes, positioning machine learning as a key tool in the future of ASO therapeutics.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".