همایش ملی بیوانفورماتیک ایران

صفحه اصلی / 4th international edition and 13th Iranian Conference on Bioinformatics

Integrating Biological Networks and Deep Learning for Microbe-Disease Prediction

نویسندگان :

Sobhan Ahmadian Moghadam¹ Zahra Ghorbanali² Fatemeh Zare-Mirakabad³ Hesam Montazeri⁴

1- Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran 2- Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran 3- Department of Mathematics and Computer Science, Amirkabir University of Technology, Tehran, Iran 4- Department of Bioinformatics, Institute Biochemistry and Biophysics, University of Tehran, Tehran, Iran

کلمات کلیدی :

Microbe-Disease،Association Prediction،Deep Learning

چکیده :

The human microbiome, consisting of diverse microbial communities, plays a crucial role in health and disease. Identifying associations between microbes and diseases holds the potential to revolutionize diagnosis, prevention, and treatment strategies. Despite the high accuracy reported by many predictive models in microbe-disease association tasks, their evaluation frameworks often overlook biases and distributional challenges inherent in the datasets, resulting in unreliable performance metrics. To overcome this limitation, we propose a novel evaluation framework that systematically adjusts for node degree distribution, ensuring a more rigorous and reliable assessment of model performance. Furthermore, we present a predictive model that leverages deep artificial neural networks and graph learning algorithms, designed to be improved under these new evaluation criteria for microbe-disease association prediction. A comparative analysis with six state-of-the-art models shows that our approach consistently outperforms existing methods across both traditional and newly proposed evaluation frameworks. Our proposed evaluation framework introduces a sampling algorithm to construct test sets with nearly balanced numbers of positive and negative associations for each node, offering a more unbiased and comprehensive evaluation. Our new predictive model integrates heterogeneous biological network data through the MDKG knowledge graph, which encompasses nine biological entities, including microbes and diseases, connected by 39 distinct edge types. We employ the Node2Vec algorithm to extract meaningful features from this knowledge graph, generating rich feature representations for microbes and diseases. These features are then processed by a deep artificial neural network specifically designed for microbe-disease association prediction. In our study, we used the HMDAD dataset, a widely utilized resource that compiles known microbe-disease associations from previous research articles. This dataset is the most commonly used benchmark in this problem domain, ensuring comparability and relevance. Our model achieved an average AUC of 0.91 in the traditional evaluation framework, outperforming or matching existing models. Under the proposed evaluation framework, it achieved an average AUC of 0.73, surpassing the performance of competing models, which ranged between 0.41 and 0.67. Using the Wilcoxon signed-rank test, we demonstrated that our model significantly outperforms all other models in the new evaluation framework and outperforms five models in the traditional framework, achieving equal performance with the sixth.

لیست مقالات

لیست مقالات بایگانی شده

Molecular docking and bioinformatics study of active compounds of thyme) Thymus vulgaris( in inhibiting COX-2 enzyme related to inflammatory diseases

Razieh Biglari Farash - Azizollah Kheiry - Najmaddin Mortazavi - Mohsen Sani khani

Comprehensive Computational Strategies for Multi-Target Drug Discovery in Inflammatory Bowel Disease Utilizing Bioactive Compounds

Pardis Mansouri - Pegah Mansouri - Sohrab Najafipour - Seyed Amin Kouhpayeh - Akbar Farjadfar - Esmaeil Behmard

3D-QSAR Modeling on 2-Pyrimidine Carbohydrazides as Utrophin Modulators for the Treatment of Duchenne Muscular Dystrophy by Combining CoMFA, CoMSIA, and Molecular Docking Studies

Reza Mahmoudzadeh Laki - Eslam Pourbasheer

Encoding the gRNA-DNA Pairs with Deep Transformers to Predict off-target Effects of CRISPR

Roghayyeh Alipanahi - Leila Safari - Alireza Khanteymoori

AcrB Inhibition: A Molecular Docking Approach to Combat Escherichia coli Infections

Faezeh Mohammadzadeh Habil - ٍElnaz Afshari

Insilico study of CD4+ T cells epitopes in ORF1ab protein of SARS-COV-2 for Iranian common MHCII alleles

Fatemeh Hajighasem - Atefeh Shirkavand

Bioinformatics Analysis of Prostate Cancer by the Construction of circRNA-miRNA-mRNA Regulatory Network

Fatemeh Zamani - Ali Taravati

Diabetes nephropathy indicators for early diagnosis

Sedigheh Momenzadeh - Masumeh Jalalvand - Reza Nedaeinia

Leveraging Machine Learning Models for Virtual Screening of ZINC Database to Identify JAK1 Inhibitors

Negar Abdolmaleki - Hamid Mahdiuni

Identifying mRNAs and miRNAs in extracellular vesicles through comparative transcriptome analyses of healthy and mastitic bovine milk

Farzad Ghafouri - Seyed Midia Pirkhezranian - Mostafa Sadeghi - Seyed Reza Miraei-Ashtiani - John P. Kastelic - Herman W. Barkema - Vahid Razban - Masoud Shirali

بیشتر