Dataset Information

A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers.

ABSTRACT: The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, T_g, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic information of PHA monomers. The other input variables included the molecular weight, the polydispersity index, and the percentage of each monomer in the homo- and copolymers. The results indicate that the DNN model achieves high accuracy in estimation of the glass transition temperature of PHAs. In addition, the symmetry of the DNN model is ensured by incorporating symmetry data in the training process. The DNN model achieved better performance than the support vector machine (SVD), a nonlinear ML model and least absolute shrinkage and selection operator (LASSO), a sparse linear regression model. The relative importance of factors affecting the DNN model prediction were analyzed. Sensitivity of the DNN model, including strategies to deal with missing data, were also investigated. Compared with commonly used machine learning models incorporating quantitative structure-property (QSPR) relationships, it does not require an explicit descriptor selection step but shows a comparable performance. The machine learning model framework can be readily extended to predict other properties.

SUBMITTER: Jiang Z

PROVIDER: S-EPMC7765086 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers.

Jiang Zhuoying Z Hu Jiajie J Marrone Babetta L BL Pilania Ghanshyam G Yu Xiong Bill XB

Materials (Basel, Switzerland) 20201214 24

The purpose of this study was to develop a data-driven machine learning model to predict the performance properties of polyhydroxyalkanoates (PHAs), a group of biosourced polyesters featuring excellent performance, to guide future design and synthesis experiments. A deep neural network (DNN) machine learning model was built for predicting the glass transition temperature, <i>T</i><sub>g</sub>, of PHA homo- and copolymers. Molecular fingerprints were used to capture the structural and atomic info ...[more]

PMID: 33327598

Similar Datasets

Project description:Recent heightened interest in inhaled bacteriophage (phage) therapy for combating antibacterial resistance in pulmonary infections has led to the development of phage powder formulations. Although phages have been successfully bioengineered into inhalable powders with preserved bioactivity, the stabilization mechanism is yet unknown. This paper reports the first study investigating the stabilization mechanism for phages in these powders. Proteins and other biologics are known to be preserved in dry state within a glassy sugar matrix at storage temperatures (T s) at least ~50°C below the glass transition temperature (T g). This is because at (T g - T s) >50°C, molecules are sufficiently immobilized with reduced reactivity. We hypothesized that this glass stabilization mechanism may also be applicable to phages comprising mostly of proteins. In this study, spray dried powders of Pseudomonas phage PEV20 containing lactose and leucine as excipients were stored at 5, 25 or 50°C and 15 or 33% relative humidity (RH), followed by assessment of bioactivity (PEV20 stability) and physical properties. PEV20 was stable with negligible titer loss after storage at 5°C/15% RH for 250?days, while storage at 33% RH caused increased titer losses of 1 log10 and 3 log10 at 5 and 25°C, respectively. The plasticizing effect of water at 33% RH lowered the T g by 30°C, thus narrowing the gap between T s and T g to 19-28°C, which was insufficient for glass stabilization. In contrast, the (T g - T s) values were higher (range, 46-65°C) under the drier condition of 15% RH, resulting in the improved stability which corroborated with the vitrification hypothesis. Furthermore, phage remained stable (?1 log10) when the (T g - T s) value lay between 26-48°C, but became inactivated as the value fell below 20°C. In conclusion, this study demonstrated that phage can be sufficiently stabilized in spray dried powders by keeping the (T g - T s) value above 46°C, thus supporting the vitrification hypothesis that phages are stabilized by immobilization inside a rigid glassy sugar matrix. These findings provide a guide to better manufacture and storage practices of inhaled phage powder products using for translational medicines.

Project description:In the present work, we address the problem of utilizing machine learning (ML) methods to predict the thermal properties of polymers by establishing "structure-property" relationships. Having focused on a particular class of heterocyclic polymers, namely polyimides (PIs), we developed a graph convolutional neural network (GCNN), being one of the most promising tools for working with big data, to predict the PI glass transition temperature T g as an example of the fundamental property of polymers. To train the GCNN, we propose an original methodology based on using a "transfer learning" approach with an enormous "synthetic" data set for pretraining and a small experimental data set for its fine-tuning. The "synthetic" data set contains more than 6 million combinatorically generated repeating units of PIs and theoretical values of their T g values calculated using the well-established Askadskii's quantitative structure-property relationship (QSPR) computational scheme. Additionally, an experimental data set for 214 PIs was also collected from the literature for training, fine-tuning, and validation of the GCNN. Both "synthetic" and experimental data sets are included into a PolyAskInG database (Polymer Askadskii's Intelligent Gateway). By using the PolyAskInG database, we developed GCNN which allows estimation of T g of PI with a mean absolute error (MAE) of about 20 K, which is 1.5 times lower than in the case of Askadskii QSPR analysis (33 K). To prove the efficiency and usability of the proposed GCNN architecture and training methodology for predicting polymer properties, we also employed "transfer learning" to develop alternative GCNN pretrained on proxy-characteristics taken from the popular quantum-chemical QM9 database for small compounds and fine-tuned on an experimental T g values data set from PolyAskInG database. The obtained results indicate that pretraining of GCNN on the "synthetic" polymer data set provides MAE which is almost twice as low as that in the case of using the QM9 data set in the pretraining stage (∼41 K). Furthermore, we address the questions associated with the influence of the differences in the size of the experimental and "synthetic" data sets (so-called "reality gap" problem), as well as their chemical composition on the training quality. Our results state the overall priority of using polymer data sets for developing deep neural networks, and GCNN in particular, for efficient prediction of polymer properties. Moreover, our work opens up a challenge for the theoretically supported generation of large "synthetic" data sets of polymer properties for the training of the complex ML models. The proposed methodology is rather versatile and may be generalized for predicting other properties of different polymers and copolymers synthesized through the polycondensation reaction.

Dataset Information

A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers.

Publications

A Deep Neural Network for Accurate and Robust Prediction of the Glass Transition Temperature of Polyhydroxyalkanoate Homo- and Copolymers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets