Advancing drug-target interaction prediction: a comprehensive graph-based approach integrating knowledge graph embedding and ProtBert pretraining.

BACKGROUND: The pharmaceutical field faces a significant challenge in validating drug target interactions (DTIs) due to the time and cost involved, leading to only a fraction being experimentally verified. To expedite drug discovery, accurate computational methods are essential for predicting potential interactions. Recently, machine learning techniques, particularly graph-based methods, have gained prominence. These methods utilize networks of drugs and targets, employing knowledge graph embedding (KGE) to represent structured information from knowledge graphs in a continuous vector space. This phenomenon highlights the growing inclination to utilize graph topologies as a means to improve the precision of predicting DTIs, hence addressing the pressing requirement for effective computational methodologies in the field of drug discovery. RESULTS: The present study presents a novel approach called DTIOG for the prediction of DTIs. The methodology employed in this study involves the utilization of a KGE strategy, together with the incorporation of contextual information obtained from protein sequences. More specifically, the study makes use of Protein Bidirectional Encoder Representations from Transformers (ProtBERT) for this purpose. DTIOG utilizes a two-step process to compute embedding vectors using KGE techniques. Additionally, it employs ProtBERT to determine target-target similarity. Different similarity measures, such as Cosine similarity or Euclidean distance, are utilized in the prediction procedure. In addition to the contextual embedding, the proposed unique approach incorporates local representations obtained from the Simplified Molecular Input Line Entry Specification (SMILES) of drugs and the amino acid sequences of protein targets. CONCLUSIONS: The effectiveness of the proposed approach was assessed through extensive experimentation on datasets pertaining to Enzymes, Ion Channels, and G-protein-coupled Receptors. The remarkable efficacy of DTIOG was showcased through the utilization of diverse similarity measures in order to calculate the similarities between drugs and targets. The combination of these factors, along with the incorporation of various classifiers, enabled the model to outperform existing algorithms in its ability to predict DTIs. The consistent observation of this advantage across all datasets underlines the robustness and accuracy of DTIOG in the domain of DTIs. Additionally, our case study suggests that the DTIOG can serve as a valuable tool for discovering new DTIs.

Geoprocess of geospatial urban data in Tallinn, Estonia.

The new digital era brings increasingly massive and complex interdisciplinary projects in various fields. At the same time, the availability of an accurate and reliable database plays a crucial role in achieving project goals. Meanwhile, urban projects and issues usually need to be analyzed to support the objectives of sustainable development of the built environment. Furthermore, the volume and variety of spatial data used to describe urban elements and phenomena have grown exponentially in recent decades. The scope of this dataset is to process spatial data to provide input data for the urban heat island (UHI) assessment project in Tallinn, Estonia. The dataset builds the generative, predictive, and explainable machine learning UHI model. The dataset presented here consists of multi-scale urban data. It provides essential baseline information for (i) urban planners, researchers, and practitioners to incorporate urban data in their research activities, (ii) architects and urban planners to improve the features of buildings and the city, considering urban data and the UHI effect, (iii) stakeholders, policymakers and administration in cities implementing built environment projects, and supporting urban sustainability goals. The dataset is available for download as supplementary material to this article.

An Alignment-Based Implementation of a Holistic Ontology Integration Method.

Despite the intense research activity in the last two decades, ontology integration still presents a number of challenging issues. As ontologies are continuously growing in number, complexity and size and are adopted within open distributed systems such as the Semantic Web, integration becomes a central problem and has to be addressed in a context of increasing scale and heterogeneity. In this paper, we describe a holistic alignment-based method for customized ontology integration. The holistic approach proposes additional challenges as multiple ontologies are jointly integrated at once, in contrast to most common approaches that perform an incremental pairwise ontology integration. By applying consolidated techniques for ontology matching, we investigate the impact on the resulting ontology. The proposed method takes multiple ontologies as well as pairwise alignments and returns a refactored/non-refactored integrated ontology that faithfully preserves the original knowledge of the input ontologies and alignments. We have tested the method on large biomedical ontologies from the LargeBio OAEI track. Results show effectiveness, and overall, a decreased integration cost over multiple ontologies.•OIAR and AROM are two implementations of the proposed method.•OIAR creates a bridge ontology, and AROM creates a fully merged ontology.•The implementation includes the option of ontology refactoring.