T- Hop: A framework for studying the importance path information in molecular graphs for chemical property prediction

TL;DR

This paper introduces T-Hop, a GNN-based framework that assesses the importance of path information in molecular graphs for chemical property prediction, and predicts dataset-specific usefulness of such information.

Contribution

It presents a toggleable GNN model to compare path and non-path modes, and pioneers a method to predict the usefulness of path information for specific datasets.

Findings

Path information usefulness is dataset-dependent.

Degenerate mode sometimes outperforms SOTA models.

First step towards dataset-specific path information prediction.

Abstract

This paper studies the usefulness of incorporating path information in predicting chemical properties from molecular graphs, in the domain of QSAR (Quantitative Structure-Activity Relationship). Towards this, we developed a GNN-style model which can be toggled to operate in one of two modes: a non-degenerate mode which incorporates path information, and a degenerate mode which leaves out path information. Thus, by comparing the performance of the non-degenerate mode versus the degenerate mode on relevant QSAR datasets, we were able to directly assess the significance of path information on those datasets. Our results corroborate previous works, by suggesting that the usefulness of path information is datasetdependent. Unlike previous studies however, we took the very first steps towards building a model that could predict upfront whether or not path information would be useful for a given dataset at hand. Moreover, we also found that, albeit its simplicity, the degenerate mode of our model yielded rather surprising results, which outperformed more sophisticated SOTA models in certain cases.