# Graph convolutional neural networks as "general-purpose" property predictors: the universality and limits of applicability

## TL;DR

This paper demonstrates that graph convolutional neural networks (GCNNs) can effectively predict chemical compound properties across diverse domains with minimal feature engineering, offering a universal and interpretable approach.

## Contribution

The study shows that GCNNs serve as a general-purpose, accurate, and interpretable tool for property prediction without extensive feature engineering, broadening applicability.

## Key findings

- GCNNs achieve performance comparable to state-of-the-art methods.
- GCNNs require minimal feature engineering.
- GCNNs successfully predict diverse chemical properties.

## Abstract

Nowadays the development of new functional materials/chemical compounds using machine learning (ML) techniques is a hot topic and includes several crucial steps, one of which is the choice of chemical structure representation. Classical approach of rigorous feature engineering in ML typically improves the performance of the predictive model, but at the same time, it narrows down the scope of applicability and decreases the physical interpretability of predicted results. In this study, we present graph convolutional neural networks (GCNN) as an architecture that allows to successfully predict the properties of compounds from diverse domains of chemical space, using a minimal set of meaningful descriptors. The applicability of GCNN models has been demonstrated by a wide range of chemical domain-specific properties. Their performance is comparable to state-of-the-art techniques; however, this architecture exempts from the need to carry out precise feature engineering.