Drug Target Binding Affinity Prediction Using a Deep Generative Model Based on Molecular and Biological Sequences

Please enable javascript in your browser.

Zamani Emani, Mojtaba | 2023

95 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 56225 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Koohi, Somayyeh
Abstract:
Drug-target binding affinity prediction is one of the most important and vital part of drug discovery. The computational methods to predict binfing affinity is a standing challenge in drug discovery. State-of-the-art models are usually based on supervised machine learning with known label information. It is expensive and time-consuming to collect labeled data. This thesis proposes a semi-supervised model based on convolutional GAN (Generative adversarial networks). The model consists of two Gans and Two CNN blocks for feature extraction and fully connected layers for prediction. Gan can learn protein and drug features from unlabeled data. We evaluate the performance of our method using four benchmark datasets i.e. Davis, Kiba, Bindingdb, PDBbind. Experimental results demonstrate that our method achieves competitive performance while utilizing freely available unlabeled data
Keywords:
Ligands ; Proteins ; Binding Affinity ; Deep Neural Networks ; Deep Generative Modeling ; Drug-Target Interaction ; Pharmaceutical Compound

No TOC