Icon

20221207 Pikairos Bayesian Classifier for CDPK1 using H20 plugin and Fingerprints

This workflow tries to bring an answer to question asked in the KNIME forum thread

https://forum.knime.com/t/table-to-h2o-using-fingerprints/52933

Is it possible to use fingerprints (e.g. from RDKIT) with the H2O nodes? I’ve seen people using H2O for chemical applications so hoping so, but can’t get it to work myself.

When I try to pass a fingerprint column to the table to H2O node it is not recognised.

Training on80 %Random IIDPartitioning 80% - 20 %Testing on20 %Statisticsof Classification ModelPerformanceAn Example ofH2O available ModelPredict Test Datausing PreviousBayes Trained ModelStatisticsof Classification ModelPerformanceRead TheCDPK1 DataCast StringstoSMILESFilteronly Classand FingerprintsSet Molecule IDsas RowIDNaive Bayes Learner Partitioning Naive BayesPredictor Scorer H2O NaiveBayes Learner Table to H2O H2O Local Context Expand Bit Vector Expand Bit Vector H2O Predictor(Classification) Table to H2O H2O to Table Scorer RDKit Fingerprint Table Reader Molecule Type Cast Column Filter RowID Training on80 %Random IIDPartitioning 80% - 20 %Testing on20 %Statisticsof Classification ModelPerformanceAn Example ofH2O available ModelPredict Test Datausing PreviousBayes Trained ModelStatisticsof Classification ModelPerformanceRead TheCDPK1 DataCast StringstoSMILESFilteronly Classand FingerprintsSet Molecule IDsas RowIDNaive Bayes Learner Partitioning Naive BayesPredictor Scorer H2O NaiveBayes Learner Table to H2O H2O Local Context Expand Bit Vector Expand Bit Vector H2O Predictor(Classification) Table to H2O H2O to Table Scorer RDKit Fingerprint Table Reader Molecule Type Cast Column Filter RowID

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: molina
Created at: 2015-02-14
On NodePit since: 2022-12-07
Last update: 2024-04-27
Created with KNIME version: v4.5.2
Tags: H2OFingerprintsMoleculesRDKitQSAR

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!