Task-conditioned modeling of drug-target interactions

Description

HyperNetworks have been established as an effective technique to achieve fast
adaptation of parameters for neural networks. Recently, HyperNetworks condi-
tioned on descriptors of tasks have improved multi-task generalization in various
domains, such as personalized federated learning and neural architecture search.
Especially powerful results were achieved in few- and zero-shot settings, attributed
to the increased information sharing by the HyperNetwork. With the rise of new dis-
eases fast discovery of drugs is needed which requires proteo-chemometric models
that are able to generalize drug-target interaction predictions in low-data scenarios.
State-of-the-art methods apply a few fully-connected layers to concatenated learned
embeddings of the protein target and drug compound. In this work, we develop a
task-conditioned HyperNetwork approach for the problem of predicting drug-target
interactions in drug discovery. We show that when model parameters are predicted
for the fully-connected layers processing the drug compound embedding, based
on the protein target embedding, predictive performance can be improved over
previous methods. Two additional components of our architecture, a) switching to
L1 loss, and b) integrating a context module for proteins, further boost performance
and robustness. On an established benchmark for proteo-chemometrics models,
our architecture outperforms previous methods in all settings, including few- and
zero-shot settings. In an ablation study, we analyze the importance of each of the
components of our HyperNetwork approach.

Period	28 Nov 2022
Event title	Critical assessment of molecular machine learning workshop
Event type	Workshop
Conference number	2
Degree of Recognition	International