Search Results (63)

The practice of using optimal descriptors has been applied for more than twenty years to develop in silico models. In the present study, a series of in silico models was built to predict the acute fish toxicity of pharmaceuticals using optimal descriptors. The SMILES format was used to represent the chemical structure. The data were split into five training and validation sets. The obtained model for fish toxicity yielded a determination coefficient of 0.67 for the external validation set, representing an acceptable quality, considering the complexity of the pharmaceuticals given their molecular structure and specific biological activity. This study is useful for assessing the acute fish toxicity of pharmaceuticals and, in general terms, as an approach to building models for complex biological endpoints. Full article

This paper investigates the effectiveness of Word2Vec-based molecular representation learning on SMILES (Simplified Molecular Input Line Entry System) strings for a downstream prediction task related to the market approvability of chemical compounds. Here, market approvability is treated as a proxy classification label derived from approval status, where only the molecular structure is analyzed. We train character-level embeddings using Continuous Bag of Words (CBOW) and Skip-Gram with Negative Sampling architectures and apply the resulting embeddings in a downstream classification task using a multi-layer perceptron (MLP). To evaluate the utility of these lightweight embedding techniques, we conduct experiments on a curated SMILES dataset labeled by approval status under both imbalanced and SMOTE-balanced training conditions. In addition to our Word2Vec-based models, we include a ChemBERTa-based baseline using the pretrained ChemBERTa-77M model. Our findings show that while ChemBERTa achieves a higher performance, the Word2Vec-based models offer a favorable trade-off between accuracy and computational efficiency. This efficiency is especially relevant in large-scale compound screening, where rapid exploration of the chemical space can support early-stage cheminformatics workflows. These results suggest that traditional embedding models can serve as viable alternatives for scalable and interpretable cheminformatics pipelines, particularly in resource-constrained environments. Full article

Humor is widely recognized for its positive effects on well-being, including stress reduction, mood enhancement, and cognitive benefits. Yet, the lack of reliable tools to objectively quantify amusement—particularly its temporal dynamics—has limited progress in this area. Existing measures often rely on self-report or coarse summary ratings, providing little insight into how amusement unfolds over time. To address this gap, we developed a Random Forest model to predict the intensity of amusement evoked by humorous video clips, based on participants’ facial expressions—particularly the co-activation of Facial Action Units 6 and 12 (“% Smile”)—and video features such as motion, saliency, and topic. Our results show that exposure to humorous content significantly increases “% Smile”, with amusement peaking toward the end of videos. Importantly, we observed emotional carry-over effects, suggesting that consecutive humorous stimuli can sustain or amplify positive emotional responses. Even when trained solely on humorous content, the model reliably predicted amusement intensity, underscoring the robustness of our approach. Overall, this study provides a novel, objective method to track amusement on a fine temporal scale, advancing the measurement of nonverbal emotional expression. These findings may inform the design of emotion-aware applications and humor-based therapeutic interventions to promote well-being and emotional health. Full article

Polymers have a wide range of applications in materials science, chemistry, and biomedical domains. Conventional design methods for polymers are mostly event-oriented, directed by intuition, experience, and abstract insights. Nevertheless, they have been effectively utilized to determine several essential materials; these techniques are facing important challenges owing to the great requirement of original materials and the huge design area of organic polymers and molecules. Enhanced and inverse materials design is the best solution to these challenges. With developments in high-performing calculations, artificial intelligence (AI) (particularly Deep learning (DL) and Machine learning (ML))-aided materials design is developing as a promising tool to show development in various domains of materials science and engineering. Several ML and DL methods are established to perform well for polymer classification and detection presently. In this paper, we design and develop a Simplified Molecular Input Line Entry System Based Polymer Property Detection and Classification Using Pareto Optimization Algorithm (SMILES-PPDCPOA) model. This study presents a novel deep learning framework tailored for polymer property classification using SMILES input. By integrating a one-dimensional convolutional neural network (1DCNN) with a gated recurrent unit (GRU) and optimizing the model via Pareto Optimization, the SMILES-PPDCPOA model demonstrates superior classification accuracy and generalization. Unlike existing methods, our model is designed to capture both local substructures and long-range chemical dependencies, offering a scalable and domain-specific solution for polymer informatics. Furthermore, the proposed SMILES-PPDCPOA model executes a one-dimensional convolutional neural network and gated recurrent unit (1DCNN-GRU) technique for the classification process. Finally, the Pareto optimization algorithm (POA) adjusts the hyperparameter values of the 1DCNN-GRU algorithm optimally and results in greater classification performance. Results on a benchmark dataset show that SMILES-PPDCPOA achieves an average classification accuracy of 98.66% (70% Training, 30% Testing) across eight polymer property classes, with high precision and recall metrics. Additionally, it demonstrates superior computational efficiency, completing tasks in 4.97 s, outperforming other established methods such as GCN-LR and ECFP-NN. The experimental validation highlights the potential of SMILES-PPDCPOA in polymer property classification, making it a promising approach for materials science and engineering. The simulation result highlighted the improvement of the SMILES-PPDCPOA system when compared to other existing techniques. Full article

Background/Objectives: Smile esthetics are a crucial aspect of facial attractiveness, playing a central role in social interactions. Dental students’ perception of smiling esthetics may evolve as they progress through their education and clinical exposure. This study aimed to investigate the influence of educational level on dental students’ perception of altered smile esthetics. Methods: A cross-sectional study was conducted among 410 undergraduate dental students across five academic years at the National and Kapodistrian University of Athens. Participants evaluated 22 digitally altered smile images, including single and combined esthetic discrepancies, using a visual analog scale (VAS). Perceived attractiveness scores were analyzed in relation to academic year, gender, and specific types of smile alterations. Results: The perception of smile attractiveness varied significantly across academic years for certain esthetic discrepancies, including central incisor length mismatch, midline diastema, and open gingival embrasures (p < 0.05). Clinical-year students (years 4–5) demonstrated a more critical assessment compared to preclinical students. Female students exhibited greater sensitivity to specific discrepancies, including fluorosis and reduced tooth lightness. The combination of a midline diastema, a gummy smile, and reduced lightness received the lowest attractiveness scores across all groups. Conclusions: The perception of altered smile esthetics among undergraduate dental students evolves throughout their education, although this progression does not follow a linear trajectory. Dental education appears to influence the perception of specific smile esthetic discrepancies, reflecting a selective influence on features. Clinical training appears to be a critical parameter of dental education, influencing the perception of smiling esthetics. Full article

Low-dielectric polyimides (PIs) have emerged as essential materials for next-generation microelectronics and communication technologies, yet traditional experimental and theoretical calculation methods for acquiring dielectric constant data face challenges in cost, accuracy, and scalability. This study presents a machine learning (ML) framework that combines polymer domain knowledge with advanced data-driven modeling techniques for accurate prediction of PI dielectric constants at 1 kHz. A dataset of 439 PIs was constructed, and 208 molecular descriptors were derived from SMILES-encoded structures. Through rigorous feature engineering—variance filtering, correlation analysis, and recursive feature elimination—10 key descriptors were identified, capturing electronic and polar interaction, surface area, and structural complexity. Five ML algorithms were evaluated, with Gaussian Process Regression (GPR) achieving superior predictive accuracy (test set: R² = 0.90, RMSE = 0.10). Shapley additive explanations (SHAP) analysis quantifies the contribution of molecular descriptors to PI dielectric constants. By means of SHAP values, it discloses the positive or negative impacts of descriptors on the predictions. Three novel PIs were synthesized for experimental validation, showing strong agreement between predicted and measured dielectric constants (mean percentage deviation: 2.24%). The model demonstrates robust predictions for other structurally similar polymers but reveals a 40% accuracy reduction (R² = 0.60) in 10 GHz cross-frequency predictions, emphasizing the requirement for multi-frequency training datasets to enhance model generalizability. This work advances the research paradigm of polymer dielectric materials and provides a pathway for the rational design of materials guided by machine learning. Full article

Background: The toxicity of pesticides for fish in general and Rainbow Trout (Oncorhynchus mykiss) in particular is an important ecological indicator required by regulations, and it implies the use of a large number of fish. The number of animals needed would be even higher to evaluate metabolites and pesticide impurities. Considering ethical issues, the costs, and the necessary resources, the use of in silico models is often proposed. Aim of the study: We explore the use of advanced Monte Carlo methods to obtain improved results for models testing Rainbow Trout (Oncorhynchus mykiss) acute toxicity. Several versions of the stochastic Monte Carlo simulation of pesticide toxicity for Rainbow Trout, carried out using CORAL software, were studied. The set of substances was split into four subsets: active training, passive training, calibration, and validation. Modeling was repeated five times to enable better statistical evaluation. To improve the predictive potential of models, the index of ideality of correlation (IIC), correlation intensity index (CII), and coefficient of conformism of correlation prediction (CCCP) were applied. Main results and novelty: The most suitable results were observed in the case of the CCCP-based optimization for SMILES-based descriptors, achieving an R² of 0.88 on the validation set, in all five random splits, demonstrating consistent and robust modeling performance. The relationship of information systems related to QSAR simulation and new ideas is discussed, assigning a key role to fundamental concepts like mass and energy. The study of the mentioned criteria of predictive potential during the conducted computer experiments showed that even though they are all aimed at improving the predictive potential, their values do not correlate, except for the CII and the CCCP. This means that, in general, the information impact of the considered criteria has a different nature, at least in the case of the simulation of toxicity for Rainbow Trout (Oncorhynchus mykiss). The applicability domain of the model is specific for pesticides; the software identifies potential outliers by looking at rare molecular fragments. Full article

The optimal descriptors generated by the CORAL software are studied as potential models of cardiotoxicity. Two significantly different cardiotoxicity databases are studied here. Database 1 contains 394 hERG inhibitors (pIC50) and external 200 substances that are potential drugs, which were used to confirm the predictive potential of the approach for Database 1. Database 2 contains cardiotoxicity data for 13864 different compounds in a format where active is denoted as 1 and inactive is denoted as 0. The same model-building algorithms were applied to all three databases using the Monte Carlo method and Las Vegas algorithm. The latter was used to rationally distribute the available data into training and validation sets. The Monte Carlo optimization for the correlation weights of different molecular features extracted from SMILES was improved by including the conformity coefficient of the correlation prediction (CCCP). This improvement provided greater predictive potential in the considered models. Full article

The development of BACE-1 (β-site amyloid precursor protein cleaving enzyme 1) inhibitors is a crucial focus in exploring early treatments for Alzheimer’s disease (AD). Recently, graph neural networks (GNNs) have demonstrated significant advantages in predicting molecular activity. However, their reliance on graph structures alone often neglects explicit sequence-level semantic information. To address this limitation, we proposed a Graph and multi-level Sequence Fusion Learning (GSFL) model for predicting the molecular activity of BACE-1 inhibitors. Firstly, molecular graph structures generated from SMILES strings were encoded using GNNs with an atomic-level characteristic attention mechanism. Next, substrings at functional group, ion level, and atomic level substrings were extracted from SMILES strings and encoded using a BiLSTM–Transformer framework equipped with a hierarchical attention mechanism. Finally, these features were fused to predict the activity of BACE-1 inhibitors. A dataset of 1548 compounds with BACE-1 activity measurements was curated from the ChEMBL database. In the classification experiment, the model achieved an accuracy of 0.941 on the training set and 0.877 on the test set. For the test set, it delivered a sensitivity of 0.852, a specificity of 0.894, a MCC of 0.744, an F1-score of 0.872, a PRC of 0.869, and an AUC of 0.915. Compared to traditional computer-aided drug design methods and other machine learning algorithms, the proposed model can effectively improve the accuracy of the molecular activity prediction of BACE-1 inhibitors and has a potential application value. Full article

Deep Neural Networks (DNNs) have been widely adopted in several advanced artificial intelligence applications due to their competitive accuracy to the human brain. Nevertheless, the superior accuracy of a DNN is achieved at the expense of intensive computations and storage complexity, requiring custom expandable hardware, i.e., graphics processing units (GPUs). Interestingly, leveraging the synergy of parallelism and edge computing can significantly improve CPU-based hardware platforms. Therefore, this manuscript explores levels of parallelism techniques along with edge computation offloading to develop an innovative hardware platform that improves the efficacy of deep learning computing architectures. Furthermore, the multitask learning (MTL) approach is employed to construct a parallel multi-task classification network. These tasks include face detection and recognition, age estimation, gender recognition, smile detection, and hair color and style classification. Additionally, both pipeline and parallel processing techniques are utilized to expedite complicated computations, boosting the overall performance of the presented deep face analysis architecture. A computation offloading approach, on the other hand, is leveraged to distribute computation-intensive tasks to the server edge, whereas lightweight computations are offloaded to edge devices, i.e., Raspberry Pi 4. To train the proposed deep face analysis network architecture, two custom datasets (HDDB and FRAED) were created for head detection and face-age recognition. Extensive experimental results demonstrate the efficacy of the proposed pipeline-parallel architecture in terms of execution time. It requires 8.2 s to provide detailed face detection and analysis for an individual and 23.59 s for an inference containing 10 individuals. Moreover, a speedup of 62.48% is achieved compared to the sequential-based edge computing architecture. Meanwhile, 25.96% speed performance acceleration is realized when implementing the proposed pipeline-parallel architecture only on the server edge compared to the sever sequential implementation. Considering classification efficiency, the proposed classification modules achieve an accuracy of 88.55% for hair color and style classification and a remarkable prediction outcome of 100% for face recognition and age estimation. To summarize, the proposed approach can assist in reducing the required execution time and memory capacity by processing all facial tasks simultaneously on a single deep neural network rather than building a CNN model for each task. Therefore, the presented pipeline-parallel architecture can be a cost-effective framework for real-time computer vision applications implemented on resource-limited devices. Full article

Youth mental health interventions incorporating trained therapy animals are increasingly popular, but more research is needed to understand the specific interactive behaviors between participants and therapy dogs. Understanding the role of these interactive behaviors is important for supporting both intervention efficacy and animal welfare and well-being. The goal of this study was to develop ethograms to assess interactive behaviors (including both affiliative and stress-related behaviors) of participants and therapy dogs during a social stress task, explore the relationship between human and dog behaviors, and assess how these behaviors may vary between experimental conditions with varying levels of physical contact with the therapy dog. Using video data from a previous experimental study (n = 50 human–therapy dog interactions, n = 25 control group), we successfully developed behavioral ethograms that could be used with a high degree of interrater reliability. Results indicated differences between experimental conditions in dog and human behaviors based on whether participants were interacting with a live or a stuffed dog, and whether they were allowed to touch the dog. These findings suggest that physically interacting with a live dog may be an important feature of these interventions, with participants demonstrating increased positive behaviors such as laughing and smiling in these conditions. Dog behaviors also varied based on whether they were in the touching/petting condition of the study which could indicate reactions to the session and has potential welfare implications for the dogs. Future research should focus on identifying specific patterns of interactive behaviors between dogs and humans that predict anxiolytic outcomes. Full article

In this work we study the use of artificial intelligence models, particularly focusing on transfer learning and interpretability, to predict polymer properties. Given the challenges imposed by data scarcity in polymer science, transfer learning offers a promising solution by using learnt features of models pre-trained on other datasets. We conducted a comparative analysis of direct modelling and transfer learning-based approaches using a polyacrylates’ glass transitions dataset as a proof-of-concept study. The AI models utilized tokenized SMILES strings to represent polymer structures, with convolutional neural networks processing these representations to predict Tg. To enhance model interpretability, Shapley value analysis was employed to assess the contribution of specific chemical groups to the predictions. The results indicate that while transfer learning provides robust predictive capabilities, direct modelling on polymer-specific data offers superior performance, particularly in capturing the complex interactions influencing Tg. This work highlights the importance of model interpretability and the limitations of applying molecular-level models to polymer systems. Full article

Amino acids and peptides are readily available biomolecules and can function as chiral ligands for transition metal catalysis. An example is the copper complex catalyzed 1,4-addition of dialkylzinc to acyclic enones, which employs peptide ligands. This review provides a dataset of amino acids and peptides reported in the literature proving to be effective ligands for metal-centered catalysts. Several parameters were highlighted, including amino acid combination, metal atoms, carboxyl and amino protecting groups, modification of natural amino acids, and the mechanism of catalysis. Along with analyzing physical-chemical properties, the SMILES representation for each amino acid and/or peptide was generated and made available online, providing an easy-to-use means of training machine learning models. This review offers an opportunity for the development of more efficient peptide ligands for enantioselective metal-centered catalysts. The available online dataset is a reliable manually curated table, it enables the benchmark for comparison of new terminal functional groups. Moreover, the review provides insight into the structures of the more successful peptide ligands and can be used as the foundation for the development of the next generation of peptide-based chiral ligands. Full article

This study introduces a deep learning framework based on SMILES representations of chemical structures to predict drug–drug interactions (DDIs). The model extracts Morgan fingerprints and key molecular descriptors, transforming them into raw graphical features for input into a modified ResNet18 architecture. The deep residual network, enhanced with regularization techniques, efficiently addresses training issues such as gradient vanishing and exploding, resulting in superior predictive performance. Experimental results show that StructNet-DDI achieved an AUC of 99.7%, an accuracy of 94.4%, and an AUPR of 99.9%, demonstrating the model’s effectiveness and reliability. These findings highlight that StructNet-DDI can effectively extract crucial features from molecular structures, offering a simple yet robust tool for DDI prediction. Full article

Background: Tyrosyl-DNA phosphodiesterase 1 (Tdp1) repairs damages in DNA induced by abortive topoisomerase 1 activity; however, maintenance of genetic integrity may sustain cellular division of neoplastic cells. It follows that Tdp1-targeting chemical inhibitors could synergize well with existing chemotherapy drugs to deny cancer growth; therefore, identification of Tdp1 inhibitors may advance precision medicine in oncology. Objective: Current computational research efforts focus primarily on molecular docking simulations, though datasets involving three-dimensional molecular structures are often hard to curate and computationally expensive to store and process. We propose the use of simplified molecular input line entry system (SMILES) chemical representations to train supervised machine learning (ML) models, aiming to predict potential Tdp1 inhibitors. Methods: An open-sourced consensus dataset containing the inhibitory activity of numerous chemicals against Tdp1 was obtained from Kaggle. Various ML algorithms were trained, ranging from simple algorithms to ensemble methods and deep neural networks. For algorithms requiring numerical data, SMILES were converted to chemical descriptors using RDKit, an open-sourced Python cheminformatics library. Results: Out of 13 optimized ML models with rigorously tuned hyperparameters, the random forest model gave the best results, yielding a receiver operating characteristics-area under curve of 0.7421, testing accuracy of 0.6815, sensitivity of 0.6444, specificity of 0.7156, precision of 0.6753, and F1 score of 0.6595. Conclusions: Ensemble methods, especially the bootstrap aggregation mechanism adopted by random forest, outperformed other ML algorithms in classifying Tdp1 inhibitors from non-inhibitors using SMILES. The discovery of Tdp1 inhibitors could unlock more treatment regimens for cancer patients, allowing for therapies tailored to the patient’s condition. Full article