Deep learning (GNN) scoring module

Submodules

haddock.modules.scoring.deeprank.deeprank module

Module contents

Deeprank scoring module.

This module scores complexes using deeprank-gnn-esm, a graph neural network that predicts the fraction of native contacts (fnat) between two chains of an interface.

For more details about this module, please refer to the haddock3 user manual

class haddock.modules.scoring.deeprank.HaddockModule(order: int, path: Path, *ignore: Any, init_params: str | Path = PosixPath('/opt/hostedtoolcache/Python/3.10.20/x64/lib/python3.10/site-packages/haddock/modules/scoring/deeprank/defaults.yaml'), **everything: Any)[source]

Bases: ScoringModule

HADDOCK3 module to perform deeprank-gnn-esm scoring.

classmethod confirm_installation() → None[source]: Confirm if the module is ready to use.

name: str = 'deeprank'

Default Parameters

Easy

chain_i

default: ‘A’
type: string
title: First chain ID
short description: Chain ID of the first partner.
long description: Chain ID of the first partner used by deeprank for scoring.
group: scoring
explevel: easy

chain_j

default: ‘B’
type: string
title: Second chain ID
short description: Chain ID of the second partner.
long description: Chain ID of the second partner used by deeprank for scoring.
group: scoring
explevel: easy