# Molecule Generation from Input-Attributions over Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2202.05703 · HTML: https://mlsanity.com/paper/2202.05703/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 14 references that are in the map.
- First posted on arXiv 25 Jan 2022.

## Builds on (most cited first, 5 of 5)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Molecular Graph Convolutions: Moving Beyond Fingerprints](https://mlsanity.com/paper/1603.00856/) (2016)
- [Deep Reinforcement Learning for De-Novo Drug Design](https://mlsanity.com/paper/1711.10907/) (2017)
- [A Systematic Assessment of Deep Learning Models for Molecule Generation](https://mlsanity.com/paper/2008.09168/) (2020)

## Abstract (arXiv)

It is well known that Drug Design is often a costly process both in terms of time and economic effort. While good Quantitative Structure-Activity Relationship models (QSAR) can help predicting molecular properties without the need to synthesize them, it is still required to come up with new molecules to be tested. This is mostly done in lack of tools to determine which modifications are more promising or which aspects of a molecule are more influential for the final activity/property. Here we present an automatic process which involves Graph Convolutional Network models and input-attribution methods to generate new molecules. We also explore the problems of over-optimization and applicability, recognizing them as two important aspects in the practical use of such automatic tools.