DeepDrug

class DeepDrug(*, molecule_channels=66, num_gcn_layers=4, gcn_layer_hidden_size=64, out_channels=1, dropout_rate=0.1)

Bases: chemicalx.models.base.Model

An implementation of the DeepDrug model from [cao2020].

See also

This model was suggested in https://github.com/AstraZeneca/chemicalx/issues/14

cao2020

Cao, X., et al. (2020). DeepDrug: A general graph-based deep learning framework for drug relation prediction. bioRxiv, 2020.11.09.375626.

Methods Summary

forward(molecules_left, molecules_right)	Run a forward pass of the DeepDrug model.
unpack(batch)	Return the left drug molecules, and right drug molecules.

Methods Documentation

forward(molecules_left, molecules_right)

Run a forward pass of the DeepDrug model.

Parameters

• molecules_left (PackedGraph) – Batched molecules for the left side drugs.

• molecules_right (PackedGraph) – Batched molecules for the right side drugs.

Return type

FloatTensor

Returns

A column vector of predicted synergy scores.

unpack(batch)

Return the left drug molecules, and right drug molecules.