Chapter 4: QsarDB Editor tutorial
This step-by-step tutorial guides you through the process of building a real QDB archive with the QsarDB Editor. This tutorial includes the following steps:
- Create a new archive
- Add archive description
- Import data
- Validate the created archive
- Prepare for uploading
The tutorial is based on a scientific article and will represent one regression model from the article (equation 9) in QsarDB data format.
Before proceeding, please download the following:
The QsarDB Editor (latest version). You'll also need a Java runtime to run the editor.
The tutorial data file (Example_dataset.xlsx) with the raw data. The data file consists 10 columns with following column names:
- Id Compound identifiers
- Name Compound names
- Cas CAS registry numbers
- InChI InChI codes
- SMILES Chemical structures as SMILES strings
- Labels Labels that indicate compound types (Neutral, Ampholyte)
- LogPeff_average Average logarithmic effective membrane permeability for pH range 3 to 9 of neutral compounds
- Eq9.train Predicted membrane permeability values for the training set
- Eq9.valid Predicted membrane permeability values for the validation set
- HDCA2 Descriptor values for HA dependent HDCA-2 (Zefirov PC)
Chemical structures in SDF format (Example_structures.sdf)
Start with step 1