Applied Computational Methods for Drug Discovery Based of Protein Compound Dataset

It is a Machine Learning and Data Analysis based project that is based on Bioinformatics. Computational Drug Discovery is a technique to discover the drugs for newly identified diseases or pandemics. It can even be used to improve the medication for several diseases Bioinformatics is an inter

Project Title

Applied Computational Methods for Drug Discovery Based of Protein Compound Dataset

Project Area of Specialization

Artificial Intelligence

Project Summary

It is a Machine Learning and Data Analysis based project that is based on Bioinformatics. Computational Drug Discovery is a technique to discover the drugs for newly identified diseases or pandemics. It can even be used to improve the medication for several diseases

Bioinformatics is an interdisciplinary field that develops methods and software tools for analyzing biological data, particularly big and complicated data sets. Through the development of ML techniques and the collecting of pharmacological data, AI innovation is a top priority in drug creation. AI is less concerned with hypothetical advances and more concerned with translating medical data into research that can be reused. In general, there are different approaches such as Random Forest, Naive Bayesian Classification (NBC), Multiple Linear Regression (MLR), Logistic Regression (LR), Linear Discriminant Analysis (LDA), Probabilistic Neural Networks (PNN), Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), etc are considered in the context of ML (Lavecchia and Di Giovanni 2013). AI improvements are notably applied as a deep learning approach toward medication creation in order to acquire capacity in feature extraction and feature generalization.

Project Objectives

Objective

Drug discovery aims at finding new compounds with specific chemical properties for the treatment of diseases. In the last years, the approach used in this search presents an important component in computer science with the skyrocketing of machine learning techniques due to its democratization. With the objectives set by the Precision Medicine initiative and the new challenges generated, it is necessary to establish a robust, standard, and reproducible computational methodologies to achieve the objectives set. Currently, predictive models based on Machine Learning have gained great importance in the step prior to preclinical studies. This stage manages to drastically reduce costs and research times in the discovery of new drugs

Project Implementation Method

Methodology

I have divided the complete project into the following six parts:

1. Data collection
   1. Target Protein Search
   2. Collecting database from chEMBL using python library chembl_webresource_client
   3. Get Bioactivity Data
   4. Data Pre-Processing
      1. Dropping Missing Data
      2. Dropping Duplicates
      3. Label Compounds according to bioactivity threshold
   5. Obtain Curated Bioactivity Data
2. Exploratory data analysis
   1. Clean smiles notation which represents the chemical structure of the compound in the dataset that I’ll be going to analyze and then export out as a CSV file
   2. Calculate Descriptors to perform EDA
      1. Visual Part &
      2. Statistical Analysis
3. Descriptor calculation
   1. Complete addition descriptor which will be used to build a machine learning model
4. Model building
   1. Build a Random Forest Model for performing prediction on quantitative data.
   2. Make a scatter plot to see the distribution for the goodness of the fits of the actual and predicted value
5. Model comparison
   1. Compare several machine learning models
   2. Make a performance comparison plot
6. Model deployment
   1. Deploy the model by making a web application so the user can input the molecule of their interest and then the web app will be making a prediction

Benefits of the Project

Problem Statement

In the clinical field, developing a new drug for persistent disease primarily relied on new medications. As of late, various drugs are improvised for recognizing dynamic components from traditional treatments such as penicillin. In chemical laboratories, it consists of natural substances, small molecules that aid in therapeutic medicine to detect substances such as cells or intact organisms. The activity of protein structure is considered the application in drug design. Many impurities have appeared in the human body due to protein dysfunctions. Structural drug design strategies are used to differentiate small molecules in protein targets. Protein structure in 3D format requires more money and time for predicting the 3D structure. And still, it faces the problem i.e., in making more exactness over de-novo prediction in 3D structure. By using deep learning and feature extraction tools, it is mandatory to predict the secondary structure (Spencer et al. 2014) and residing the protein contacts (Li et al. 2017). It precisely gains the information on the connection among structure and sequence from feature extraction. The further goal is to predict the 3D- protein structure by utilizing deep learning techniques for improving the accuracy. To retrieve information from the drug design of protein-protein computer structure, then it is mandatory to conduct investigations on the PPI interface (Xue et al. 2015).

Solution Application Areas

Drug discovery and development pipelines are long, complex, and depend on numerous factors. Machine learning (ML) approaches provide a set of tools that can improve discovery and decision-making for well-specified questions with abundant, high-quality data. Opportunities to apply ML occur in all stages of drug discovery. Examples include target validation, identification of prognostic biomarkers, and analysis of digital pathology data in clinical trials. Applications have ranged in context and methodology, with some approaches yielding accurate predictions and insights. The challenges of applying ML lie primarily with the lack of interpretability and repeatability of ML-generated results, which may limit their application. In all areas, systematic and comprehensive high-dimensional data still need to be generated. With ongoing efforts to tackle these issues, as well as increasing awareness of the factors needed to validate ML approaches, the application of ML can promote data-driven decision making and has the potential to speed up the process and reduce failure rates in drug discovery and development.

Technical Details of Final Deliverable

Project Scope

ML approaches can be applied at several steps during early drug discovery to:

• Predict target structure
• Identify and optimize “hits”
• Explore the biological activity of new ligands

Design models that predict the pharmacokinetic and toxicological properties of the drug candidates

Tools/Technology

The complete project will be done using python3 for Machine Learning and Data Analysis. I’ll be using Google Colaboratory as the Primary tool in this project and all of the tasks will be done in Google Colab. Dataset for this project will be collected from chEMBL. Python Libraries to be used in this project:

1. pandas
2. chembl_webresource_client
3. numpy
4. rdkit
5. seaborn
6. matplotlib.pyplot
7. scipy
8. sklearn
9. lazypredict
10. pickle
11. streamlit
12. PIL
13. subprocess
14. os
15. base64 and PaDEL – Descriptor

Final Deliverable of the Project

Software System

Core Industry

Medical

Other Industries

IT

Core Technology

Artificial Intelligence(AI)

Other Technologies

Others

Sustainable Development Goals

Good Health and Well-Being for People, Industry, Innovation and Infrastructure

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com