Method and apparatus for molecular toxicity prediction based on multi-task graph neural network
A toxicity prediction, neural network technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as high thresholds, and achieve the effect of improving performance
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0080] Example: such as figure 1 and figure 2 Described, this molecular toxicity prediction method based on multi-task graph neural network, comprises the following steps:
[0081] S1: Collect data sets about molecular toxicity in public databases and literature, remove inorganic and organic metals, salts and mixtures, discard chemical substances with missing label values in the data set, remove duplicate molecules, and save the data set. Toxicity prediction labels are provided and molecular compounds are saved to the dataset as SMILES strings. :
[0082] S2: Preprocess the chemical molecular canonical expression SMILES, and divide the complete data set randomly into a training set and a test set according to a certain ratio, and a part of the training set is divided by k-fold cross-validation to verify the performance of the verification model set.
[0083] Use the chemical toolkit rdkit to preprocess the canonical expression SMILES molecular formula of each chemical m...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com