RESUMO
BACKGROUND: Developmental toxicity tests are extremely expensive, require a large number of animals, and are time-consuming. It is necessary to develop a new approach to simplify the analysis of developmental endpoints. One of these endpoints is malformation, and one group of ongoing methods for simplifying is in silico models. In this study, we aim to develop a quantitative structure-activity relationship (QSAR) model and identify the best algorithm for predicting malformations, as well as the most important and effective physicochemical properties associated with malformation. METHODS: The dataset was extracted from a reliable database called COMPTOX. Physicochemical properties (descriptors) were calculated using Mordred and RDKit chemoinformatics software. The data were cleaned, preprocessed, and then split into training and testing sets. Machine learning algorithms, such as gradient boosting model (GBM) and logistic regression (LR), as well as deep learning models, including multilayer perceptron (MLP) and neural networks (NNs) trained with train set data and different sets of descriptors. The models were then validated with test set and various statistical parameters, such as Matthew's correlation coefficient (MCC) and balanced accuracy (BAC) score, were used to compare the models. RESULTS: A set of descriptors containing with 78% AUC was identified as the best set of descriptors. Gradient boosting was determined to be the best algorithm with 78% predictive power. CONCLUSIONS: The descriptors that were the most effective for developing models directly impact the mechanism of malformation, and GBM is the best model due to its MCC and BAC.
RESUMO
21st century brought along a considerable decrease in social interactions, due to the newly emerged lifestyle around the world, which became more noticeable recently of the COVID-19 pandemic. On the other hand, children with autism spectrum disorder have further complications regarding their social interactions with other humans. In this paper, a fully Robotic Social Environment (RSE), designed to simulate the needed social environment for children, especially those with autism is described. An RSE can be used to simulate many social situations, such as affective interpersonal interactions, in which observational learning can take place. In order to investigate the effectiveness of the proposed RSE, it has been tested on a group of children with autism, who had difficulties in emotion recognition, which in turn, can influence social interaction. An A-B-A single case study was designed to show how RSE can help children with autism recognize four basic facial expressions, i.e., happiness, sadness, anger, and fear, through observing the social interactions of two robots speaking about these facial expressions. The results showed that the emotion recognition skills of the participating children were improved. Furthermore, the results showed that the children could maintain and generalize their emotion recognition skills after the intervention period. In conclusion, the study shows that the proposed RSE, along with other rehabilitation methods, can be effective in improving the emotion recognition skills of children with autism and preparing them to enter human social environments.