User: Andreas Truszkowski

Genetic Algorithm for Input Component Anal... (1)

• Download

This workflow uses a genetic algorithm to optimize the given molecular descriptor set. Afterwards the workflow splits the data into a training set and test set and evaluates the results which are stored as PDF files.

Created: 2011-07-22

QSAR CSV to Weka Regression Dataset (1)

• Download

This workflow converts the molecular descriptor data from a CSV file to a Weka XRFF file. The workflow merges the retention time values from IN IDRT CSV with the molecular descriptor values from IN QSAR CSV to create a valid Weka regression set.

Created: 2011-07-21

Substructure filter (1)

• Download

No description

Created: 2011-07-21 | Last updated: 2011-07-21

Weka Regression from XRFF file. (1)

• Download

The here shown workflow splits the given data into a training set and a test set. Afterwards a machine learning model is created by the Weka Regression worker which is evaluated by the Evaluate Regression Results as PDF worker. The resulting sets are stored as XRFF files in the folder determined by the OUT TRAIN XRFF and OUT TEST XRFF input ports. The calcualted machine learning models and the evaluation results are saved in the folder of OUT MODEL input port

Created: 2011-07-21 | Last updated: 2011-07-21

Reaction Enumeration (1)

• Download

This workflow performs a reaction enumeration. Therefore it loads a generic reaction rxn file and two educt lists. The SD files contain the educt lists for the enumeration. The products of the enumerated reaction are stored as RXN files and also a PDF will be created which visualizes the resulting reactions.

Created: 2011-02-18 | Last updated: 2011-07-21

QSAR Descriptor Calculation Workflow (2)

• Download

This workflow calculates QSAR properties and saves them as a CSV file. The molecules are read iteratively from a SD file. Additionally it writes out the molecules with unknown atom types, salt counter ions, curated molecule library with UUIDs and the used calculation time of every QSAR descriptor as a CSV file.Furthermore explicit hydrogens are added and a Hueckel aromaticity detection is performed.

Created: 2011-02-18 | Last updated: 2011-07-21

Split Molecules Into Clusters (1)

• Download

This workflow splits given molecules into their cluster memberships. The molecules are loaded from a SD file and the relationship data from a CSV file. The results are saved into N different SD files, where N is the number of clusters.

Created: 2011-01-17 | Last updated: 2011-07-21

Weka Clustering Considering Different Orig... (2)

• Download

This workflow clusters the given CSV files with the chosen Weka algorithm. The results are visualized in a PDF file. The CSV files are loaded from hard disk and merged together. Afterwards they are converted into a Weka dataset which is the suitable data type for the Weka clustering activity. The results are visualized as a PDF file showing the cluster membership of each input CSV file.

Created: 2011-01-13 | Last updated: 2011-07-21

Weka Clustering With Silhouette Analysis A... (2)

• Download

This workflow clusters given QSAR CSV file and performs a silhouette analysis which is visualised in a PDF file. The QSAR data is loaded from a CSV file and converted into a Weka dataset. After that the data is clustered and the results are visualised in a PDF file.

Created: 2011-01-13 | Last updated: 2011-07-21

Get Molecular Weight Distribution From QSA... (2)

• Download

This workflow calculates a molecular weight distribution from given QSAR vector. The QSAR data containing the molecular weight values is read from a CSV file and converted into a QSAR vector. Finally, the Get_molecular_Weight_Distribution_From_QSAR_vector extracts the weight data and saves it as CSV files.

Created: 2010-12-15 | Last updated: 2011-07-21

Compound Library Screen For Reaction Enume... (2)

• Download

This workflow performs a compound library screen for molecules which match the given template reaction. The reaction is loaded from a RXN file and the Reaction_Reactant_Splitter splits the reaction into its reactants. The compound library is loaded iteratively from a SD file. Afterwards a substructure search is performed for each reactant and the results are saved as SD files.

Created: 2010-12-14 | Last updated: 2011-07-21

ART-2a Classification Considering Differen... (2)

• Download

This workflow classifies the given CSV files with the ART-2a algorithm. The results are visualized in a PDF file. The QSAR dara is loaded from CSV files and merged together by the Merge_QSAR_Vectors worker. Afterwards they are converted into a fingerprint items list which is the suitable data type for the ART-2a algorithm.

Created: 2010-12-13 | Last updated: 2011-07-21

ART-2a Classification Result As PDF (2)

• Download

This workflow classifies a given CSV file with the ART-2a algorithm. The results are visualized in a PDF file. The QSAR data is loaded from a CSV file and converted into a fingerprint items list which is the suitable data type for the ART-2a algorithm.

Created: 2010-12-09 | Last updated: 2011-07-21

Curate QSAR descriptor CSV file (2)

• Download

This workflow erases descriptor entries which were not calculated. The QSAR data is loaded from a CSV file and afterwards processed by the Curate_QSAR_Vector worker. At the end the curated CSV file is written to hard disk.

Created: 2010-12-09 | Last updated: 2011-07-21

Merge QSAR descriptor CSV files (3)

• Download

This workflow merges QSAR descriptor CSV files into a single CSV file. The workflow loads the CSV files from hard disk and builds a single QSAR descriptor vector. Afterwards the vector is converted in one single CSV file and saved to hard disk.

Created: 2010-12-09 | Last updated: 2011-07-21