GCRIS

Now showing 1 - 3 of 3

AI-Driven Drug Repositioning: A Diffusion Model Approach on Knowledge Graphs
(Elsevier, 2026) Erkantarci, Betul; Şen, Tarık Üveys; Bakal, Gokhan
Drug repositioning - discovering new therapeutic applications for existing drugs - offers a promising pathway to accelerate cancer treatment development. This study proposes a diffusion model-driven framework that leverages biomedical knowledge graphs and graph-based learning to enhance drug repositioning predictions. The framework integrates data from the Semantic MEDLINE Database (SemMedDB), the Unified Medical Language System (UMLS), and the Repurposing Drugs Database (RepoDB) to construct a comprehensive therapeutic knowledge graph. Drug embeddings are generated using a one-layer Relational Graph Convolutional Network (R-GCN) incorporating semantic type-guided structural perturbations. These embeddings are refined through a flow-matching algorithm to denoise and reconstruct biologically meaningful representations. To evaluate the model's effectiveness, we apply a consensus strategy using Cosine Similarity, Euclidean Distance, and Manhattan Distance as proximity metrics. The model successfully identified, on average, 74 candidate drugs for repositioning in the context of leukemia. Qualitative analysis using t-distributed stochastic neighbor embedding (t-SNE) revealed enhanced clustering of pharmacologically relevant drugs in the denoised embedding space. Trastuzumab, in particular, emerged as a strong repositioning candidate for leukemia, supported by 156 co-mentions in PubMed. These findings demonstrate that the proposed framework improves embedding robustness and semantic fidelity, offering a powerful artificial intelligence (AI)-driven approach for precision oncology. Integrating structural noise modeling with diffusion-based denoising advances the discovery of novel drug-disease associations and holds potential for translational research and clinical hypothesis generation in drug repurposing.
Citation - WoS: 4
Citation - Scopus: 7
Combining N-Grams and Graph Convolution for Text Classification
(Elsevier, 2025-05) Sen, Tarik Uveys; Yakit, Mehmet Can; Gumus, Mehmet Semih; Abar, Orhan; Bakal, Gokhan
Text classification, a cornerstone of natural language processing (NLP), finds applications in diverse areas, from sentiment analysis to topic categorization. While deep learning models have recently dominated the field, traditional n-gram-driven approaches often struggle to achieve comparable performance, particularly on large datasets. This gap largely stems from deep learning' s superior ability to capture contextual information through word embeddings. This paper explores a novel approach to leverage the often-overlooked power of n-gram features for enriching word representations and boosting text classification accuracy. We propose a method that transforms textual data into graph structures, utilizing discriminative n-gram series to establish long-range relationships between words. By training a graph convolution network on these graphs, we derive contextually enhanced word embeddings that encapsulate dependencies extending beyond local contexts. Our experiments demonstrate that integrating these enriched embeddings into an long-short term memory (LSTM) model for text classification leads to around 2% improvements in classification performance across diverse datasets. This achievement highlights the synergy of combining traditional n-gram features with graph-based deep learning techniques for building more powerful text classifiers.
Citation - WoS: 4
Citation - Scopus: 5
Beyond Visual Cues: Emotion Recognition in Images With Text-Aware Fusion
(Elsevier, 2025-04) Sungur, Kerim Serdar; Bakal, Gokhan
Sentiment analysis is a widely studied problem for understanding human emotions and potential outcomes. As it can be performed over textual data, working on visual data elements is also critically substantial to examining the current emotional status. In this effort, the aim is to investigate any potential enhancements in sentiment analysis predictions through visual instances by integrating textual data as additional knowledge reflecting the contextual information of the images. Thus, two separate models have been developed as image-processing and text-processing models in which both models were trained on distinct datasets comprising the same five human emotions. Following, the outputs of the individual models' last dense layers are combined to construct the hybrid multimodel empowered by visual and textual components. The fundamental focus is to evaluate the performance of the hybrid model in which the textual knowledge is concatenated with visual data. Essentially, the hybrid model achieved nearly a 3% F1-score improvement compared to the plain image classification model utilizing convolutional neural network architecture. In essence, this research underscores the potency of fusing textual context with visual information to refine sentiment analysis predictions. The findings not only emphasize the potential of a multi-modal approach but also spotlight a promising avenue for future advancements in emotion analysis and understanding.

Scopus İndeksli Yayınlar Koleksiyonu

Browse

Filters

Settings

Sort By

Results per page

Search Results