Icon

CA IX XGBoost Classification - Final Model & Prospective Prediction

Dataset Curation Descriptor and fingerprint generation Generate fingerprintExtract columnsneeded for ML nodesSplit fingerprint to one bit per columnString to SmilesSmiles to RDKitCAIX-KiCHEMBL-databaseChanges "None" to "" in AlogP columnAlogP>5 removalKi into pKitransformationRemove missing values in Ki columnActive/InactiveClassificationObtain Murko ScaffoldMurko Scaffoldto SMILESDe-duplication ofrepeated moleculesTable with numberof k-foldsEvaluationmetrics tableDescriptor CalculationSalt removalFrom RDKit to SMILESCSV file with activity prediction for new compoundsFilter by Assay FormatRetrieve only exact Ki measurementsOnly nM Ki valuesStructure NormalizerRemove non-allowed values for CSVRDKit Fingerprint Column Filter Expand Bit Vector Molecule Type Cast RDKit From Molecule CSV Reader String Manipulation(Multi Column) Row Filter Math Formula Rule-basedRow Filter Rule Engine RDKit FindMurcko Scaffolds RDKit Canon SMILES GroupBy Table Creator Table View RDKit DescriptorCalculation RDKit Salt Stripper Removal of pKiz-score outliers RDKit Canon SMILES CSV Writer XGBoost Linear Learnerand Tanimoto Evaluation Row Filter Row Filter Row Filter Partition of compoundsinto k-folds RDKit StructureNormalizer Column Filter Dataset Curation Descriptor and fingerprint generation Generate fingerprintExtract columnsneeded for ML nodesSplit fingerprint to one bit per columnString to SmilesSmiles to RDKitCAIX-KiCHEMBL-databaseChanges "None" to "" in AlogP columnAlogP>5 removalKi into pKitransformationRemove missing values in Ki columnActive/InactiveClassificationObtain Murko ScaffoldMurko Scaffoldto SMILESDe-duplication ofrepeated moleculesTable with numberof k-foldsEvaluationmetrics tableDescriptor CalculationSalt removalFrom RDKit to SMILESCSV file with activity prediction for new compoundsFilter by Assay FormatRetrieve only exact Ki measurementsOnly nM Ki valuesStructure NormalizerRemove non-allowed values for CSVRDKit Fingerprint Column Filter Expand Bit Vector Molecule Type Cast RDKit From Molecule CSV Reader String Manipulation(Multi Column) Row Filter Math Formula Rule-basedRow Filter Rule Engine RDKit FindMurcko Scaffolds RDKit Canon SMILES GroupBy Table Creator Table View RDKit DescriptorCalculation RDKit Salt Stripper Removal of pKiz-score outliers RDKit Canon SMILES CSV Writer XGBoost Linear Learnerand Tanimoto Evaluation Row Filter Row Filter Row Filter Partition of compoundsinto k-folds RDKit StructureNormalizer Column Filter

Nodes

Extensions

Links