ACon: predicting protein contact-map using additive neural networks and subgroups balancing method

Shahram Ramesht¹ Mitra Mirzarezaee² Mehdi Sadeghi³

Abstract :
Proteins’ contact-map is a binary matrix which shows contact points between residues in a protein sequence that is very essential in defining tertiary structure of proteins. Although contact-maps have been studied vastly over the last decade, predicting contact-maps from protein’s sequence is a difficult task to do. Many algorithms are developed to predict contact-maps from protein sequences by using evolutionary information and physical constraints but the accuracy of almost all of them are not promising[1]. In this paper, we present a neural network based method called ACon. This method uses a multi-level additive neural networks to predict proteins residue-residue contact-maps. Inputs of each level of the network are provided by the output of previous levels. For training the unbalanced data of contact-map, we used subgroups method which shows better results over prevalent sampling methods. In this method, we keep all samples instead of randomly selecting a portion of them. We have devided our samples to seven groups. Each of these groups have trained separately. This method, divides these groups to L subgroups. Where L is the ratio of the number of non-contacts to the number of contacts in our contact map matrix. Each of these subgroups have trained separately and the results of each L subgroups have summed up by votting. ACon reaches the accuracy of 77 percent with TPR and SPC equals 74 and 78 percent respectively.

Keywords : protein structure prediction contact map additive neural networks unbalanced datasets

---

زبان مقاله : انگلیسی
محور مقاله : بیوانفورماتیک ساختاری
محل انتشار : هفتمین همايش بیوانفورماتیک ايران
آدرس وب سایت کنفرانس : icb7.ir
کد IOI مقاله : XAAH-BKAHC
لینک مستقیم مقاله : https://isnac.ir/XAAH-BKAHC

سایر مقالات ارائه دهنده

1. ACon: predicting protein contact-map using additive neural networks and subgroups balancing method

سایر مقالات محل انتشار

1. Registration Paper
2. ACon: predicting protein contact-map using additive neural networks and subgroups balancing method
3. In Silico Design, Analysis and Structure Prediction of Tow New Chimeras of VK210/VK247CSP Antigen for Development of a Malaria Pre-erythrocytic Subunit Vaccine Candidate
4. Bioinformatics for Plant genome
5. In silico evaluation and prediction of intra/inter-species relationships & properties of antigenic region 4 of HA protein of swine influenza H1N1 virus in Iran in order to present a proper candidate for vaccine
6. In-silico evaluation of Human papioma virus L1 protein in order to present effective vaccine candidate
7. Assessing the stability of a drug-like inhibitory peptide in complex with β-Catenin using umbrella sampling
9. Immunogenic epitopes prediction of SP15 protein of Phlebotomus papatasi salivary gland by bioimmunoinformatic
11. Molecular docking study on anticancer activity of phycocyanobilin
12. Engineering of ovine pancreatic Ribonuclease for increasing of cytotoxicity activity: an in silico approach
13. Feature Selection in Quantitative Structure-Activity Relationship (QSAR) Study: Combining Firefly and Neural Network methods
14. Molecular Dynamics Studies of Truncated Human Cathelicidin LL:37 Peptide Interacting with a Bacterial Model Membrane
15. Bioinformatic analysis of acyl carier protein (ACP) in eukaryotes and prokaryotes