Single Cell RNA Analysis using Intel oneAPI AI Analytics toolkit
- 0 Collaborators
a user-friendly interface to perform single-cell RNA sequencing analysis on selected datasets using various machine learning classification algorithms. The objective of the project is to help researchers, biologists, and clinicians to identify and classify cancerous and non-cancerous cells accuratel ...learn more
Project status: Published/In Market
Intel Technologies
oneAPI
Overview / Usage
The problem statement for the above code is to provide a user-friendly interface to perform single-cell RNA sequencing analysis on selected datasets using various machine learning classification algorithms. The objective of the project is to help researchers, biologists, and clinicians to identify and classify cancerous and non-cancerous cells accurately, which is a crucial task in cancer research and diagnosis.
The methodology to solve this problem includes preprocessing the single-cell RNA sequencing data, selecting the appropriate classification algorithm, training the model on the dataset, and predicting the cancer status of a selected cell. The Intel oneAPI AI Analytics toolkit and Intel Optimized Scikit-learn library are used to enhance the performance and speed of the classification algorithms.
The scope of the proposed solution is to provide an efficient and accurate method for identifying and classifying cancerous and non-cancerous cells in single-cell RNA sequencing data. The solution includes interactive visualizations and user-friendly interfaces that can be used by non-experts in machine learning and bioinformatics.
Methodology / Approach
The code loads the data using the Scanpy library and preprocesses the data using various methods such as filtering cells and genes, performing principal component analysis (PCA), calculating neighbor graphs, and computing uniform manifold approximation and projection (UMAP).
The code includes a sidebar with options to select the dataset, classification algorithm, and a specific cell for prediction.
The code uses various classification algorithms such as Random Forest, XGBoost, Logistic Regression, Decision Tree, and K-Nearest Neighbors to predict the cancer status of a selected cell.
The code generates scatter plots and visualizations using the Plotly library to display the clustering and predicted cancer status of the cells.
Technologies Used
Intel oneAPI AI Analytics Toolkit
Intel optimized Scikit Learn
Repository
https://github.com/krittika08k/odd
