Icon

04.1. Integrated Deployment

Integrated Deployment

"Integrated Deployment" exercise for the advanced Life Science User Training
- capture the data preprocessing
- capture the model prediction
- deploy the captured workflow

Activity I: Create Model for Deployment - capture the preprocessing of your data and the model prediction using the Capture Workflow Start and Capture Workflow End nodes - combine your captured workflows using the Workflow Combiner - write/deploy your workflow using the Workflow Writer node Integrated DeploymentThis workflow demonstrates integrated deployment for a Random Forest Model for a bioactivity data set using binary fingerprints.The data set represents a subset of 844 compounds evaluated for activity against CDPK1. 181 compounds inhibited CDPK1 with IC50 below 1uM and have "active" as their class.More information is available https://www.ebi.ac.uk/chemblntd/#tcams_dataset. See Set 19. Step 1: Capture Preprocessing- use the Capture Workflow Start node with data porttypes to start capturing your preprocessing part of theworkflow- use the RDKit Fingerprint node to create binaryfingerprints. - use the Capture Workflow End node with data porttypes to end your preprocessing part of the workflow Step 2: Capture Prediction Model- use the Capture Workflow Start node with data port types to start capturingyour prediction model- use the Random Forest Predictor node for your model predictions- use the Column Filter node to remove your binary fingerprint column - use the Capture Workflow End node with data port types to end yourprediction model Step 3: Combine capturedWorkflows and Deploy- use the Workflow Combiner node tocombine the preprocessing workflow andthe model prediction workflow (HINT: thefirst part needs to be connected to theupper input port)- use the Workflow Writer node to deployyour workflow (name: 04.2. deployedworkflow, output location should be in theExercises folder) TCAMS_CDPK1_subset_ML.table Partitioning Random ForestLearner Table Reader Activity I: Create Model for Deployment - capture the preprocessing of your data and the model prediction using the Capture Workflow Start and Capture Workflow End nodes - combine your captured workflows using the Workflow Combiner - write/deploy your workflow using the Workflow Writer node Integrated DeploymentThis workflow demonstrates integrated deployment for a Random Forest Model for a bioactivity data set using binary fingerprints.The data set represents a subset of 844 compounds evaluated for activity against CDPK1. 181 compounds inhibited CDPK1 with IC50 below 1uM and have "active" as their class.More information is available https://www.ebi.ac.uk/chemblntd/#tcams_dataset. See Set 19. Step 1: Capture Preprocessing- use the Capture Workflow Start node with data porttypes to start capturing your preprocessing part of theworkflow- use the RDKit Fingerprint node to create binaryfingerprints. - use the Capture Workflow End node with data porttypes to end your preprocessing part of the workflow Step 2: Capture Prediction Model- use the Capture Workflow Start node with data port types to start capturingyour prediction model- use the Random Forest Predictor node for your model predictions- use the Column Filter node to remove your binary fingerprint column - use the Capture Workflow End node with data port types to end yourprediction model Step 3: Combine capturedWorkflows and Deploy- use the Workflow Combiner node tocombine the preprocessing workflow andthe model prediction workflow (HINT: thefirst part needs to be connected to theupper input port)- use the Workflow Writer node to deployyour workflow (name: 04.2. deployedworkflow, output location should be in theExercises folder) TCAMS_CDPK1_subset_ML.table Partitioning Random ForestLearner Table Reader

Nodes

Extensions

Links

Download

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

Download Workflow
On NodePit since: 2024-01-14
Last update: 2024-04-27
Created with KNIME version: v4.6.1
Tags: machine learningeducationintegrated deploymentlife science

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

Try NodePit Runner!