Systematic feature and architecture evaluation reveals tokenized learned embeddings enhance siRNA efficacy prediction
Coffey, R.
Show abstract
Recent advances in machine learning have improved the prediction of siRNA efficacy, with graph neural networks and transformer-based encodings leading the way. However, existing models still face challenges, including potential inaccuracies in thermodynamic feature calculations (such as incorrect strand selection for siRNA-mRNA Gibbs free energy), limited effective utilization of available datasets, and a lack of systematic model refinement. In this study, I systematically evaluated the predictive power of individual features and neural network architectures to identify the most effective configurations. This process led to the development of RN.Ai-Predict, a model built upon a tokenized learned embedding for nucleotide sequences. This work demonstrates that a methodical approach to feature selection and hyperparameter tuning, particularly favoring learned embeddings, can yield a more accurate and reliable model for predicting siRNA efficacy, outperforming more complex architectures in generalizability.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Adversarial training improves model interpretability in single-cell RNA-seq analysis 94%
- Optimizer's dilemma: optimization strongly influences model selection in transcriptomic prediction 92%
- Mining hidden knowledge: Embedding models of cause-effect relationships curated from the biomedical literature 92%
Similar papers in this journal
- shRNAI: a deep neural network for the design of highly potent shRNAs 95%
- Fine scale structural information substantially improves multivariate regression model for mRNA in-vial degradation prediction 94%
- CLCluster: a redundancy-reduction contrastive learning-based clustering method of cancer subtype based on multi-omics data 92%
Similar papers in this journal
Similar papers in this journal
- Informative RNA-base embedding for functional RNA structural alignment and clustering by deep representation learning 94%
- Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer 93%
- Discovering Governing Equations of Biological Systems through Representation Learning and Sparse Model Discovery 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.