AmorProt: Amino Acid Molecular Fingerprints Repurposing-Based Protein Fingerprint.

As protein therapeutics play an important role in almost all medical fields, numerous studies have been conducted on proteins using artificial intelligence. Artificial intelligence has enabled data-driven predictions without the need for expensive experiments. Nevertheless, unlike the various molecular fingerprint algorithms that have been developed, protein fingerprint algorithms have rarely been studied. In this study, we proposed the amino acid molecular fingerprints repurposing-based protein (AmorProt) fingerprint, a protein sequence representation method that effectively uses the molecular fingerprints corresponding to 20 amino acids. Subsequently, the performances of the tree-based machine learning and artificial neural network models were compared using (1) amyloid classification and (2) isoelectric point regression. Finally, the applicability and advantages of the developed platform were demonstrated through a case study and the following experiments: (3) comparison of dataset dependence with feature-based methods, (4) feature importance analysis, and (5) protein space analysis. Consequently, the significantly improved model performance and data-set-independent versatility of the AmorProt fingerprint were verified. The results revealed that the current protein representation method can be applied to various fields related to proteins, such as predicting their fundamental properties or interaction with ligands.

MGCVAE: Multi-Objective Inverse Design via Molecular Graph Conditional Variational Autoencoder.

The ultimate goal of various fields is to directly generate molecules with desired properties, such as water-soluble molecules in drug development and molecules suitable for organic light-emitting diodes or photosensitizers in the field of development of new organic materials. This study proposes a molecular graph generative model based on an autoencoder for the de novo design. The performance of the molecular graph conditional variational autoencoder (MGCVAE) for generating molecules with specific desired properties was investigated by comparing it to a molecular graph variational autoencoder (MGVAE). Furthermore, multi-objective optimization for MGCVAE was applied to satisfy the two selected properties simultaneously. In this study, two physical properties, calculated logP and molar refractivity, were used as optimization targets for designing de novo molecules. Consequently, it was confirmed that among the generated molecules, 25.89% of the optimized molecules were generated in MGCVAE compared to 0.66% in MGVAE. This demonstrates that MGCVAE effectively produced drug-like molecules with two target properties. The results of this study suggest that these graph-based data-driven models are an effective method for designing new molecules that fulfill various physical properties.

Prediction of Protein Aggregation Propensity via Data-Driven Approaches.

Protein aggregation occurs when misfolded or unfolded proteins physically bind together and can promote the development of various amyloid diseases. This study aimed to construct surrogate models for predicting protein aggregation via data-driven methods using two types of databases. First, an aggregation propensity score database was constructed by calculating the scores for protein structures in the Protein Data Bank using Aggrescan3D 2.0. Moreover, feature- and graph-based models for predicting protein aggregation have been developed by using this database. The graph-based model outperformed the feature-based model, resulting in an R2 of 0.95, although it intrinsically required protein structures. Second, for the experimental data, a feature-based model was built using the Curated Protein Aggregation Database 2.0 to predict the aggregated intensity curves. In summary, this study suggests approaches that are more effective in predicting protein aggregation, depending on the type of descriptor and the database.

AiKPro: deep learning model for kinome-wide bioactivity profiling using structure-based sequence alignments and molecular 3D conformer ensemble descriptors.

The discovery of selective and potent kinase inhibitors is crucial for the treatment of various diseases, but the process is challenging due to the high structural similarity among kinases. Efficient kinome-wide bioactivity profiling is essential for understanding kinase function and identifying selective inhibitors. In this study, we propose AiKPro, a deep learning model that combines structure-validated multiple sequence alignments and molecular 3D conformer ensemble descriptors to predict kinase-ligand binding affinities. Our deep learning model uses an attention-based mechanism to capture complex patterns in the interactions between the kinase and the ligand. To assess the performance of AiKPro, we evaluated the impact of descriptors, the predictability for untrained kinases and compounds, and kinase activity profiling based on odd ratios. Our model, AiKPro, shows good Pearson's correlation coefficients of 0.88 and 0.87 for the test set and for the untrained sets of compounds, respectively, which also shows the robustness of the model. AiKPro shows good kinase-activity profiles across the kinome, potentially facilitating the discovery of novel interactions and selective inhibitors. Our approach holds potential implications for the discovery of novel, selective kinase inhibitors and guiding rational drug design.

A Comparative Study of the Performance for Predicting Biodegradability Classification: The Quantitative Structure-Activity Relationship Model vs the Graph Convolutional Network.

The prediction and evaluation of the biodegradability of molecules with computational methods are becoming increasingly important. Among the various methods, quantitative structure-activity relationship (QSAR) models have been demonstrated to predict the ready biodegradation of chemicals but have limited functionality owing to their complex implementation. In this study, we employ the graph convolutional network (GCN) method to overcome these issues. A biodegradability dataset from previous studies was trained to generate prediction models by (i) the QSAR models using the Mordred molecular descriptor calculator and MACCS molecular fingerprint and (ii) the GCN model using molecular graphs. The performance comparison of the methods confirms that the GCN model is more straightforward to implement and more stable; the specificity and sensitivity values are almost identical without specific descriptors or fingerprints. In addition, the performance of the models was further verified by randomly dividing the dataset into 100 different cases of training and test sets and by varying the test set ratio from 20 to 80%. The results of the current study clearly suggest the promise of the GCN model, which can be implemented straightforwardly and can replace conventional QSAR prediction models for various types and properties of molecules.

Novel Solubility Prediction Models: Molecular Fingerprints and Physicochemical Features vs Graph Convolutional Neural Networks.

Predicting both accurate and reliable solubility values has long been a crucial but challenging task. In this work, surrogated model-based methods were developed to accurately predict the solubility of two molecules (solute and solvent) through machine learning and deep learning. The current study employed two methods: (1) converting molecules into molecular fingerprints and adding optimal physicochemical properties as descriptors and (2) using graph convolutional network (GCN) models to convert molecules into a graph representation and deal with prediction tasks. Then, two prediction tasks were conducted with each method: (1) the solubility value (regression) and (2) the solubility class (classification). The fingerprint-based method clearly demonstrates that high performance is possible by adding simple but significant physicochemical descriptors to molecular fingerprints, while the GCN method shows that it is possible to predict various properties of chemical compounds with relatively simplified features from the graph representation. The developed methodologies provide a comprehensive understanding of constructing a proper model for predicting solubility and can be employed to find suitable solutes and solvents.

Impact of Neighborhood Environment on Pedestrian Route Selection among Elementary Schoolchildren in Korea.

Previous studies on the walking environment of elementary school students have focused on physical factors such as traffic accidents, safety, and the neighborhood environment. However, scholars have yet to consider the behavioral characteristics of elementary school students, particularly in respect to the relationship between environmental factors and behavioral characteristics in pedestrian route selection and safety. Addressing this gap, this study identifies how neighborhood environment factors and behavioral characteristics impact route selection and satisfaction among elementary school students. Accordingly, this study surveyed 251 elementary school students at three elementary schools in Korea and analyzed the spatial forms of the selected sites. In doing so, this study discerns students' satisfaction with their selection of the shortest or non-shortest route and which environmental factors and behavioral characteristics influenced their selection and satisfaction. Study results have practical implications for policymaking, including valuable insights into the planning of school routes for elementary school students.