Workflows

Antiviral activity multiclass Predictor (1)

• Download

A simple multi-class antiviral activity predictor based on expanded Pubchem fingerprints and random forest algorithm. Seems to work well to perform quick screens for antiviral molecules.Download training data from CTD (http://ctdbase.org/downloads/) or  use this preprocessed version https://www.myexperiment.org/files/2285.html. Write to me at rajeev.gangal@gmail.com regarding any queries.I make no claim that the predictive model is accurate for clinical hypotheses or that it will find mo...

Created: 2020-03-23 | Last updated: 2020-03-25

Credits: Insilicoconsulting

Genetic Algorithms for BIOISOSTERIC Struct... (1)

• Download

Genetic algorithm workflow to generate novel structures by recombination and mutation and that uses an ML model as a fitness function. Both the fitness function and the fingerprints modified in the model should be the same. ML model cannot have any descriptors other than given fingerprint.Reverse molecular mapping/generation is not part of this workflow and can be done by creating a large Structure-FP database.

Created: 2018-11-06

Credits: Insilicoconsulting

Mining Semantic Web data using Corresponde... (1)

• Download

This workflow will explain that how an example set can be extracted from an RDF resource using the provided SPARQL query. This example set is then divided into training and test parts. These sub-example sets are used by the Correspondencce Analysis operators (encapsulate the Correspondencce Analysis data transformation technique) which processes each feature at a time and transform the data into a different space. This transformed data is more meaningful and helps the learner to improve clas...

Created: 2011-06-25 | Last updated: 2011-06-25

Mining Semantic Web data using Corresponde... (1)

• Download

This workflow describes how to learn from the Semantic Web's data using a data transformation algorithm 'Correspondence Analysis'. The input to the workflow is a feature vector developed from a RDF resource. The loaded example set is divided into training and test parts. These sub-example sets are used by the Correspondence Analysis operators (encapsulate the Correspondence Analysis data transformation technique) which processes each feature at a time and transform the data into a different...

Created: 2011-06-25 | Last updated: 2011-06-25

Mining Semantic Web data using FastMap - E... (1)

• Download

This workflow describes how to learn from the Semantic Web's data. The input to the workflow is a feature vector developed from a RDF resource. The loaded example set is then divided into training and test parts. These sub-example sets are used by the FastMap operators (encapsulate the FastMap data transformation technique), which processes each feature at a time and transform the data into a different space. This transformed data is more meaningful and helps the learner to improve classfica...

Created: 2011-06-25 | Last updated: 2011-06-25