Feature Selection in Quantitative Structure-Activity Relationship (QSAR) Study: Combining Firefly and Neural Network methods

Masoud Arabfard¹ Mazaher Maghsoudloo² Kaveh kavousi³ Sajjad Gharaghani⁴

Abstract :
Abstract: Over the past decade, the use of feature selection methods in bioinformatics has become a major need for model building. This is due to the high dimension of data in various bioinformatics sciences, such as Quantitative Structure-Activity Relationship, which leads to the use of machine learning techniques such as feature selection. Therefore, the use of feature selection methods is inevitable. In this paper, we use a combination method to select important descriptors in a QSAR dataset in drug design. Optimization algorithms and evolutionary random search for feature selection are new and effective methods used to find global optima of problems. The randomness feature of these algorithms prevents clogging in local optima. In this paper, we propose a method for selecting the features with combination of a firefly and a neural network. We use a QSAR data set with 55 instance and 221 attributes to estimate the IC50. Results of experiment obtained in each run, proved that our method selects about 50 percent of the features that give the best result. The proposed method has been able to achieve a good regression with a significant reduction in features. The results show the acceptable accuracy of the proposed method in identifying important descriptors in QSAR.

Keywords : drug design qsar firefly algorithm neural network feature selection

---

زبان مقاله : انگلیسی
محور مقاله : طراحی و کشف محاسباتی دارو
محل انتشار : هفتمین همايش بیوانفورماتیک ايران
آدرس وب سایت کنفرانس : icb7.ir
کد IOI مقاله : XAAH-BKBKE
لینک مستقیم مقاله : https://isnac.ir/XAAH-BKBKE

سایر مقالات ارائه دهنده

1. Feature Selection in Quantitative Structure-Activity Relationship (QSAR) Study: Combining Firefly and Neural Network methods
2. Step by Step from Machine Learning Algorithm to Making QSAR model: Present a Combined Feature Selection with a Case Study

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