English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The pharmaceutical Research and development (R&D) process is lengthy andcostly, taking nearly a decade to bring a new drug to the market. However,advancements in biotechnology, computational methods, and machine learningalgorithms have the potential to revolutionize drug discovery, speeding up theprocess and improving patient outcomes. The COVID-19 pandemic has furtheraccelerated and deepened the recognition of the potential of these techniques,especially in the areas of drug repurposing and efficacy predictions.Meanwhile, non-small molecule therapeutic modalities such as cell therapies,monoclonal antibodies, and RNA interference (RNAi) technology have gainedimportance due to their ability to target specific disease pathways and/orpatient populations. In the field of RNAi, many experiments have been carriedout to design and select highly efficient siRNAs. However, the establishedpatterns for efficient siRNAs are sometimes contradictory and unable toconsistently determine the most potent siRNA molecules against a target mRNA.Thus, this paper focuses on developing machine learning models based on thecheminformatics representation of the nucleotide composition (i.e. AUTGC) ofsiRNA to predict their potency and aid the selection of the most efficientsiRNAs for further development. The PLS (Partial Least Square) and SVR (SupportVector Regression) machine learning models built in this work outperformedpreviously published models. These models can help in predicting siRNA potencyand aid in selecting the best siRNA molecules for experimental validation andfurther clinical development. The study has demonstrated the potential ofAI/machine learning models to help expedite siRNA-based drug discoveryincluding the discovery of potent siRNAs against SARS-CoV-2.

Machine Learning Modeling Of SiRNA Structure-Potency Relationship With Applications Against Sars-Cov-2 Spike Gene