Using attribution to decode binding mechanism in neural network models for chemistry.

Clicks: 344
ID: 61046
2019
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #63 of 292 articles by views in Proceedings of the National Academy of Sciences of the United States of America

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 292 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Deep neural networks have achieved state-of-the-art accuracy at classifying molecules with respect to whether they bind to specific protein targets. A key breakthrough would occur if these models could reveal the fragment pharmacophores that are causally involved in binding. Extracting chemical details of binding from the networks could enable scientific discoveries about the mechanisms of drug actions. However, doing so requires shining light into the black box that is the trained neural network model, a task that has proved difficult across many domains. Here we show how the binding mechanism learned by deep neural network models can be interrogated, using a recently described attribution method. We first work with carefully constructed synthetic datasets, in which the molecular features responsible for "binding" are fully known. We find that networks that achieve perfect accuracy on held-out test datasets still learn spurious correlations, and we are able to exploit this nonrobustness to construct adversarial examples that fool the model. This makes these models unreliable for accurately revealing information about the mechanisms of protein-ligand binding. In light of our findings, we prescribe a test that checks whether a hypothesized mechanism can be learned. If the test fails, it indicates that the model must be simplified or regularized and/or that the training dataset requires augmentation.
Reference Key
mccloskey2019usingproceedings Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors McCloskey, Kevin;Taly, Ankur;Monti, Federico;Brenner, Michael P;Colwell, Lucy J;
Journal Proceedings of the National Academy of Sciences of the United States of America
Year 2019
DOI
10.1073/pnas.1820657116
URL
Keywords
Deep learning virtual screening attribution for molecules overfitting

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.