Application of machine learning-based read-across structure-property relationship (RASPR) as a new tool for predictive modelling: Prediction of power conversion efficiency (PCE) for selected classes of organic dyes in dye-sensitized solar cells (DSSCs).

The application of various in-silico-based approaches for the prediction of various properties of materials has been an effective alternative to experimental methods. Recently, the concepts of Quantitative structure-property relationship (QSPR) and read-across (RA) methods were merged to develop a new emerging chemoinformatic tool: read-across structure-property relationship (RASPR). The RASPR method can be applicable to both large and small datasets as it uses various similarity and error-based measures. It has also been observed that RASPR models tend to have an increased external predictivity compared to the corresponding QSPR models. In this study, we have modeled the power conversion efficiency (PCE) of organic dyes used in dye-sensitized solar cells (DSSCs) by using the quantitative RASPR (q-RASPR) method. We have used relatively larger classes of organic dyes-Phenothiazines (n=207), Porphyrins (n=281), and Triphenylamines (n=229) for the modelling purpose. We have divided each of the datasets into training and test sets in 3 different combinations, and with the training sets we have developed three different QSPR models with structural and physicochemical descriptors and validated them with the corresponding test sets. These corresponding modeled descriptors were used to calculate the RASPR descriptors using a Java-based tool RASAR Descriptor Calculator v2.0 (https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home), and then data fusion was performed by pooling the previously selected structural and physicochemical descriptors with the calculated RASPR descriptors. Further feature selection algorithm was employed to develop the final RASPR PLS models. Here, we also developed different machine learning (ML) models with the descriptors selected in the QSPR PLS and RASPR PLS models, and it was found that models with RASPR descriptors superseded in external predictivity the models with only structural and physicochemical descriptors: RMSEP reduced for phenothiazines from 1.16-1.25 to 1.07-1.18, for porphyrins from 1.60-1.79 to 1.45-1.53, for triphenylamines from 1.27-1.54 to 1.20-1.47.

Prediction of cytotoxicity of heavy metals adsorbed on nano-TiO2 with periodic table descriptors using machine learning approaches.

Nanoparticles with their unique features have attracted researchers over the past decades. Heavy metals, upon release and emission, may interact with different environmental components, which may lead to co-exposure to living organisms. Nanoscale titanium dioxide (nano-TiO2) can adsorb heavy metals. The current idea is that nanoparticles (NPs) may act as carriers and facilitate the entry of heavy metals into organisms. Thus, the present study reports nanoscale quantitative structure-activity relationship (nano-QSAR) models, which are based on an ensemble learning approach, for predicting the cytotoxicity of heavy metals adsorbed on nano-TiO2 to human renal cortex proximal tubule epithelial (HK-2) cells. The ensemble learning approach implements gradient boosting and bagging algorithms; that is, random forest, AdaBoost, Gradient Boost, and Extreme Gradient Boost were constructed and utilized to establish statistically significant relationships between the structural properties of NPs and the cause of cytotoxicity. To demonstrate the predictive ability of the developed nano-QSAR models, simple periodic table descriptors requiring low computational resources were utilized. The nano-QSAR models generated good R2 values (0.99-0.89), Q2 values (0.64-0.77), and Q2F1 values (0.99-0.71). Thus, the present work manifests that ML in conjunction with periodic table descriptors can be used to explore the features and predict unknown compounds with similar properties.

Efficient predictions of cytotoxicity of TiO2-based multi-component nanoparticles using a machine learning-based q-RASAR approach.

The availability of experimental nanotoxicity data is in general limited which warrants both the use of in silico methods for data gap filling and exploring novel methods for effective modeling. Read-Across Structure-Activity Relationship (RASAR) is an emerging cheminformatic approach that combines the usefulness of a QSAR model and similarity-based Read-Across predictions. In this work, we have generated simple, interpretable, and transferable quantitative-RASAR (q-RASAR) models which can efficiently predict the cytotoxicity of TiO2-based multi-component nanoparticles. A data set of 29 TiO2-based nanoparticles with specific amounts of noble metal precursors was rationally divided into training and test sets, and the Read-Across-based predictions for the test set were generated. The optimized hyperparameters and the similarity approach, which yield the best predictions, were used to calculate the similarity and error-based RASAR descriptors. A data fusion of the RASAR descriptors with the chemical descriptors was done followed by the best subset feature selection. The final set of selected descriptors was used to develop the q-RASAR models, which were validated using the stringent OECD criteria. Finally, a random forest model was also developed with the selected descriptors, which could efficiently predict the cytotoxicity of TiO2-based multi-component nanoparticles superseding previously reported models in the prediction quality thus showing the merits of the q-RASAR approach. To further evaluate the usefulness of the approach, we have applied the q-RASAR approach also to a second cytotoxicity data set of 34 heterogeneous TiO2-based nanoparticles which further confirmed the enhancement of external prediction quality of QSAR models after incorporation of RASAR descriptors.