Carlo Bertinetto

Evaluation of hierarchical structured representations for QSPR studies of small molecules and polymers by recursive neural networks

This paper reports some recent results from the empirical evaluation of different types of structured molecular representations used in QSPR analysis through a recursive neural network (RNN) model, which allows for their direct use without the need for measuring or computing molecular descriptors. This RNN methodology has been applied to the prediction of the properties of small molecules and polymers. In particular, three different descriptions of cyclic moieties, namely group, template and cyclebreak have been proposed. The effectiveness of the proposed method in dealing with different representations of chemical structures, either specifically designed or of more general use, has been demonstrated by its application to data sets encompassing various types of cyclic structures. For each class of experiments a test set with data that were not used for the development of the model was used for validation, and the comparisons have been based on the test results. The reported results highlight the flexibility of the RNN in directly treating different classes of structured input data without using input descriptors.

QSPR Analysis of Copolymers by Recursive Neural Networks: Prediction of the Glass Transition Temperature of (Meth)acrylic Random Copolymers

The glass transition temperature (Tg) of acrylic and methacrylic random copolymers was investigated by means of Quantitative Structure‐Property Relationship (QSPR) methodology based on Recursive Neural Networks (RNN). This method can directly take molecular structures as input, in the form of labelled trees, without needing predefined descriptors. It was applied to three data sets containing up to 615 polymers (340 homopolymers and 275 copolymers). The adopted representation was able to account for the structure of the repeating unit as well as average macromolecular characteristics, such as stereoregularity and molar composition. The best result, obtained on a data set focused on copolymers, showed a Mean Average Residual (MAR) of 4.9 K, a standard error of prediction (S) of 6.1 K and a squared correlation coefficient (R2) of 0.98 for the test set, with an optimal rate with respect to the training error. Through the treatment of homopolymers and copolymers both as separated and merged data sets, we also showed that the proposed approach is particularly suited for generalizing prediction of polymer properties to various types of chemical structures in a uniform setting.

Adaptive modelling of structured molecular representations for toxicity prediction

We investigated the possibility of modelling structure-toxicity relationships by direct treatment of the molecular structure (without using descriptors) through an adaptive model able to retain the appropriate structural information. With respect to traditional descriptor-based approaches, this provides a more general and flexible way to tackle prediction problems that is particularly suitable when little or no background knowledge is available. Our method employs a tree-structured molecular representation, which is processed by a recursive neural network (RNN). To explore the realization of RNN modelling in toxicological problems, we employed a data set containing growth impairment concentrations (IGC50) for Tetrahymena pyriformis.