Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Evaluation and Ranking of Protein Docking Models by 3D Convolutional Neural Networks
Download
HIBIT22_paper_128.pdf
Date
2022-10
Author
Fathi, Amir
Rehman Azhar Khokhar, Moaaz Ur
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
55
views
21
downloads
Cite This
Protein-protein interactions, which occur at protein-protein interfaces, are essential for biological activities. Understanding the mechanics of protein binding and predicting new interactions requires identifying protein-protein interface areas. It’s crucial to be able to determine protein-protein interactions quickly and accurately. Protein-protein complex structure is required to extract a protein interface. Because finding a single protein complex structure experimentally requires time and effort, computational docking technologies that can offer thousands of alternative complex structures, called decoys, in a short amount of time are promising. The ability to distinguish near-native decoys from thousands of proposed decoys is a hurdle using computational approaches. DeepInterface, a threedimensional convolutional neural network-based decoys scoring and ranking system, was enhanced in this work. We analyzed different convolutional neural network architectures and explored the hyperparameter space to discover the highest performing DeepInterface model that resembled VGG16. We created positive datasets from the Protein Data Bank complexes and negative datasets from the PPI4DOCK and DOCKGROUND docking databases’ erroneous decoys. We demonstrated that the model that was proposed originally can accurately distinguish positive interfaces, such as those recorded in the PDB, from erroneous ones using the CAPRI criterion, with the accuracy of 81%
URI
https://hibit2022.ims.metu.edu.tr/
https://hdl.handle.net/11511/101944
Conference Name
The International Symposium on Health Informatics and Bioinformatics
Collections
Graduate School of Informatics, Conference / Seminar
Suggestions
OpenMETU
Core
Visualizing the protein-protein interactions network in virtual reality and mixed reality environments
Şenderin, Büşra; Sürer, Elif; Tunçbağ, Nurcan; Department of Modeling and Simulation (2021-8)
Protein-protein interactions (PPI) define the physical contact of two or more protein structures. When these interactions are combined, the protein-protein interaction network (PPIN) is formed. The interactions between protein structures are distinct interactions—they happen in specific binding locations on proteins, and they have a specific biological function that they take on. With these networks, the processes within a cell or a living organism when healthy or diseased can be studied. In this thesis, a ...
Novel Method for Modeling IBIS4.2 Four-Level Hysteresis Behavior in an Analog Simulator
Sabry, Yasser M.; Hareedy, Ahmed; Selim, Mohamed A. (2008-01-01)
IBIS4.2 (I/O Buffer Information Specification) standard describes the hysteresis behavior from one simulation point to the other. In an analog simulator, solution is obtained based oil multiple iterations in between simulation points. These iterations call lead to undesired behavior. The common problem that might be encountered with this specific behavior in an analog simulator due to iterations will be discussed, and a novel way for implementation that overcomes this problem will be proposed.
Comparison of fluorescent protein labelled and wild type NMDA receptor distribution
Pirinçci, Şerife Şeyda; Son, Çağdaş Devrim; Department of Biology (2013)
NMDA (N-methyl D-aspartate) Receptor is a ligand and voltage gated ion channel and involved in many processes such as synaptic plasticity, memory formation, behavioral responses and cell survival. In the sense of functional activity, cellular localization of NMDAR is important since this receptor shows its activity on the membrane. Although NMDA receptor is intensely studied there are no satisfying study showing its localization with microscobic methods. Besides, the effect of florescent protein labelling o...
DiPPI: Drugs in Protein-Protein Interaction Interfaces
Cankara, Fatma; Şenyüz , Simge; Keskin , Özlem; Gürsoy , Attila (Orta Doğu Teknik Üniversitesi Enformatik Enstitüsü; 2022-10)
Protein-protein interactions (PPIs) modulation has been associated with various diseases. Proteins interact through their interfaces and interface characterization is important to understand the underlying mechanisms of the interaction. There has been an increasing interest in PPIs as drug targets, as analysis of binding regions and critical contacts may reveal more information about these mechanisms. Therefore, investigating the properties of the interactions is critical for the identification of drug targ...
INVESTIGATION OF PHYSICAL INTERACTION BETWEEN Gαi AND Gαs PROTEINS VIA FRET IN LIVE CELLS
Balkan, Seyda Tuğçe; Son, Çağdaş Devrim; Küçük Baloğlu, Fatma; Department of Biochemistry (2021-8-11)
GPCR’s are seven-transmembrane receptors that transmit external signals to the intracellular environment via secondary messenger systems through heterotrimeric G proteins. Heterotrimeric G proteins consist of α and β-γ subunits. Until recent years, scientists thought that GPCR signal transduction occurs between one GPCR and one heterotrimeric G protein; however, recently, it has been shown that GPCR’s can make oligomers. Oligomerization of GPCR allows cells to tune the intensity of the signal and respond ap...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
A. Fathi and M. U. Rehman Azhar Khokhar, “Evaluation and Ranking of Protein Docking Models by 3D Convolutional Neural Networks,” Erdemli, Mersin, TÜRKİYE, 2022, p. 3128, Accessed: 00, 2023. [Online]. Available: https://hibit2022.ims.metu.edu.tr/.