Description: RNA is crucial for the regulation of numerous cellular processes and functions. With the in-depth study of disease mechanisms, processes such as RNA expression, splicing, translation, and stability regulation have become new targets for disease intervention. RNA has provided new therapeutic modalities for metabolic diseases, genetic disorders, and cancer patients, resulting in several innovative drugs.
RNA is crucial for the regulation of numerous cellular processes and functions. With the in-depth study of disease mechanisms, processes such as RNA expression, splicing, translation, and stability regulation have become new targets for disease intervention. RNA has provided new therapeutic modalities for metabolic diseases, genetic disorders, and cancer patients, resulting in several innovative drugs.
MCE R&D team collected small molecules targeting RNA from the PDB, R-BIND, ROBIN, and internal database as the positive dataset, and non-targeting RNA small molecules from ROBIN as the negative dataset. Based on the GeminiMol pre-trained model, we encoded the molecules and calculated over 1700 molecular descriptors using Mordred as inputs for the model. Subsequently, we employed 13 deep learning models to learn from the data. All of which yielded good training results, with AUROCs greater than 0.75. Ultimately, we selected the Finetune model to screen HY-L901P, which exhibited the best classification performance, achieving an AUROC of 0.82 and a prediction accuracy of 0.76. We then applied filtering based on StaR rules (with at least two of the following properties: cLogP ≥ 1.5, Molar Refractivity ≥ 4, Relative Polar Surface Area ≤ 0.3) to obtain a library containing approximately 5,000 small molecule compounds targeting RNA. This library serves as a valuable tool for screening small molecules that interact with RNA.
Advantages:
- A unique collection of 5,000 small molecule compounds with potential RNA interaction activity.
- Screened by AI model which shows good classification performance with AUROC of 0.82 and a high accuracy with ACC of 0.76.
- Compatible with “StaR rules”, with at least two of the following properties: cLogP≥1.5, Molar Refractivity≥4, Relative Polar Surface Area≤0.3.
- Compounds were selected by dissimilarity search to provide a higher variety and broader chemical space coverage.
- All compounds are available off the shelf.
- LCMS or NMR validated to ensure high purity and quality.
Formulation: 5,000 small molecule compounds with potential RNA interaction activity. Powered by AI models (AUROC of 0.82 and high accuracy with ACC of 0.76).
Layout: 96-well storage tube or 96-well plate: 1st and 12th column are left empty. 384-well plate: the first two columns and the last two columns are left empty. Compounds with different concentrations or dissolved in different solvents will be put on separate plates. This way of layout may increase the number of plates because there could be three solvents and three concentrations. If you have other requirements, please let us know.
Container: 96- or 384-well Plate with Peelable Foil Seal; 96-well Format Sample Storage Tube With Screw Cap and Optional 2D Barcode.
English
Deutsch
