https://github.com/itsnileshhere/bioactivity-prediction-app

A WebApp implementation of Drug-Discovery Pipeline using Microsoft Azure
https://github.com/itsnileshhere/bioactivity-prediction-app

azure-machine-learning drug-discovery

Last synced: 6 months ago
JSON representation

A WebApp implementation of Drug-Discovery Pipeline using Microsoft Azure

• Host: GitHub
• URL: https://github.com/itsnileshhere/bioactivity-prediction-app
• Owner: itsNileshHere
• Created: 2024-06-08T10:29:35.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-01-08T14:57:04.000Z (9 months ago)
• Last Synced: 2025-02-02T09:13:31.180Z (8 months ago)
• Topics: azure-machine-learning, drug-discovery
• Language: Python
• Homepage:
• Size: 20.4 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# ChEMBL Bioactivity Prediction Project

This project focuses on predicting the bioactivity of compounds against the SARS coronavirus target using data from ChEMBL (Chemical Biology Database). The goal is to develop a machine learning model that can accurately classify compounds as active, inactive, or intermediate based on their molecular properties.

## Technologies used

Python, RDKit, scikit-learn, Pandas, Numpy

### Core Azure Services

Visual Studio Code, Microsoft Azure Portal

### Azure AI Service

Azure Machine Learning

### Industry

Health

### Project Title

Bioactivity Prediction

## Utilizing Azure ML Core in the Project

This section demonstrates how Azure ML Core is integrated into different parts of the project.

### Setting Up the Azure Environment

![Azure Setup](images/azure_setup.png)

*Azure ML Core is used to set up a machine learning workspace, create an experiment, and establish an environment for running the machine learning model*

### Model Deployment

![Model Deployment](images/deploy_model.png)

*The Azure ML SDK is being used to manage and deploy machine learning models within the Azure ecosystem.*

### Model Evaluation

![Model Evaluation](images/predicted.png)

*The model is evaluated using a web app hosted on Azure. It accepts Canonical smiles as input and predicts the pIC50 value.*

## Setup Instructions

To set up the project environment and deploy the model, follow these steps:

1. Ensure you have Python installed on your machine.

2. Clone this repository to your local machine.

3. Install Conda if you haven't already.

4. Create a Conda environment using the provided environment.yml file:


```conda env create -f environment.yml```

5. Activate the Conda environment:


```conda activate ```

6. Run the ```azure_setup.py``` script to set up the Azure environment and compute resources.

7. Run the ```prepare_data.py``` script to fetch and preprocess the bioactivity data.

8. Run the ```train.py``` script to train the predictive model.

9. Run the ```deploy_model.py``` script to register and deploy the trained model as a web service.

## Usage

1. ```prepare_data.py```: Prepares the bioactivity data by fetching, preprocessing, and computing descriptors.

2. ```train.py```: Trains the predictive model using the preprocessed data.

3. ```score.py```: Scoring script used for model inference in Azure ML deployment.

4. ```deploy_model.py```: Deploys the trained model as a web service in Azure ML.