Mónica F. Díaz

Polyethylene–polystyrene grafting reaction: effects of polyethylene molecular weight

Abstract Blending of different thermoplastic polymers usually results in segregated and low value materials for almost any mixing condition. Nevertheless, a synergetic combination of properties can be obtained by an adequate compatibilization via reactive blending. In this work a Friedel–Crafts alkylation reaction is used to graft polyethylene chains onto polystyrene. The relation between the initial PE molecular weight (MW) and the structure of the compatibilizer copolymer is studied by a combination of size exclusion chromatography and Fourier transform infrared spectroscopy. The amount of copolymer formed is estimated from the amount of polystyrene reacted. The relative lengths of the grafted polyethylene chains are assessed. It is found that lower MW PE produces, upon reaction, a greater amount of short chain length grafted PE onto PS than higher MW PE. The results are in agreement with theories relating the component MW to the reaction localization at the interface. The low cost Friedel–Crafts alkylation results in a convenient reaction for the in situ compatibilization of PE/PS blends. It produces enough graft copolymer to compatibilize the phases without causing PS crosslinking and PE chain scission.

Visual analytics in cheminformatics: user-supervised descriptor selection for QSAR methods

BackgroundThe design of QSAR/QSPR models is a challenging problem, where the selection of the most relevant descriptors constitutes a key step of the process. Several feature selection methods that address this step are concentrated on statistical associations among descriptors and target properties, whereas the chemical knowledge is left out of the analysis. For this reason, the interpretability and generality of the QSAR/QSPR models obtained by these feature selection methods are drastically affected. Therefore, an approach for integrating domain expert’s knowledge in the selection process is needed for increase the confidence in the final set of descriptors.ResultsIn this paper a software tool, which we named Visual and Interactive DEscriptor ANalysis (VIDEAN), that combines statistical methods with interactive visualizations for choosing a set of descriptors for predicting a target property is proposed. Domain expertise can be added to the feature selection process by means of an interactive visual exploration of data, and aided by statistical tools and metrics based on information theory. Coordinated visual representations are presented for capturing different relationships and interactions among descriptors, target properties and candidate subsets of descriptors. The competencies of the proposed software were assessed through different scenarios. These scenarios reveal how an expert can use this tool to choose one subset of descriptors from a group of candidate subsets or how to modify existing descriptor subsets and even incorporate new descriptors according to his or her own knowledge of the target property.ConclusionsThe reported experiences showed the suitability of our software for selecting sets of descriptors with low cardinality, high interpretability, low redundancy and high statistical performance in a visual exploratory way. Therefore, it is possible to conclude that the resulting tool allows the integration of a chemist’s expertise in the descriptor selection process with a low cognitive effort in contrast with the alternative of using an ad-hoc manual analysis of the selected descriptors.

Feature Learning applied to the Estimation of Tensile Strength at Break in Polymeric Material Design

Several feature extraction approaches for QSPR modelling in Cheminformatics are discussed in this paper. In particular, this work is focused on the use of these strategies for predicting mechanical properties, which are relevant for the design of polymeric materials. The methodology analysed in this study employs a feature learning method that uses a quantification process of 2D structural characterization of materials with the autoencoder method. Alternative QSPR models inferred for tensile strength at break (a well-known mechanical property of polymers) are presented. These alternative models are contrasted to QSPR models obtained by feature selection technique by using accuracy measures and a visual analytic tool. The results show evidence about the benefits of combining feature learning approaches with feature selection methods for the design of QSPR models.

Feature Selection and Polydispersity Characterization for QSPR Modelling: Predicting a Tensile Property

QSPR (Quantitative Structure-Property Relationship) models proposed in Polymer Informatics typically use reduced computational representations of polymers for avoiding the complex issues related with the polydispersion of these industrial materials. In this work, the aim is to assess the effect of this oversimplification in the modelling decisions and to analyze strategies for addressing alternative characterizations of the materials that capture, at least partially, the polydispersion phenomenon. In particular, a cheminformatic study for estimating a tensile property of polymers is presented here. Four different computational representations are analyzed in combination with several machine learning approaches for selecting the most relevant molecular descriptors associated with the target property and for learning the corresponding QSPR models. The obtained results give insight about the limitations of using oversimplified representations of polymers and contribute with alternative strategies for achieving more realistic models.

QSAR Classification Models for Predicting Affinity to Blood or Liver of Volatile Organic Compounds in e-Health

In this work, we present Quantitative Structure-Activity Relationship (QSAR) classification models for characterization of molecules affinity to blood or liver for volatile organic compounds (VOCs), using information provided from log P liver measures for VOCs. The models are computed from a dataset of 122 molecules. As a first phase, alternative subsets of relevant molecular descriptors related to the target property are selected by using feature selection methods and visual analytics techniques. From these subsets, several QSAR models are inferred by different machine learning methods. These models allow classifying a new compound as a molecule with affinity to blood, to the liver or equal affinity to both. The model with the highest performance correctly classifies 72.13% of VOCs and has an average receiver operating characteristic area equal to 0.83. As a conclusion, this QSAR model can predict the medium affinity of a VOC, which can help in the development of physiologically based pharmacokinetic computational models required in e-health.