ML Regression using Feature Input

ML Regression using Feature Input is a floe that predicts property from a generic pretrained model on custom feature input. It runs a Tensorflow based fully-connected neural network Regression model which needs to be provided by user. Model can be generated using Regression Custom Input builder floe. The molecules predicted need to contain a FloatVec field of same length as the ones used for training. In addition, the floe also uses Convex Box and Monte Carlo Dropout to determine DOA. Finally, it uses Lime, a model agnostic system, to explain the predictions on the molecule. Very cheap and quick. Takes about a cent for property prediction of 20 molecules.

Inputs

Name

Description

Type

Input Small Molecule(s) Dataset
to predict property of

The dataset(s) to read records from

Molecule Dataset

Input tensorflow Model

Machine Learning model to predict property

Machine Learing Tensorflow Model Dataset

ML Model Options

Name

Description

Type

Model ID of which Tensorflow model to use to predict

Which model to select. Make sure this matches with input Model ID

Int

Preprocess Molecule

Preprocess by Neutral Ph, Largest Mol, Blockbuster Filter

Bool

Apply Blockbuster filter

For every molecule, stores only largest component, adjusts ionization to Neutral Ph

Bool

Number of features to explain

Number of top features to provide LIME explanations for

Int

Explanation and Validation

Name

Description

Type

Property Validation Field

If the dataset has a baseline, the floe reports
a comparison between prediction in Floereport

Float

Custom Feature

Field containing feature vector to train model on.

FloatVec

Outputs

Name

Description

Type

Output Property

Output dataset to write to

Dataset

Failure Property

Output dataset to write to

Dataset