Overview / Usage

The DNA Kingdom Prediction application is a cutting-edge tool that helps the scientists to predict which kingdom of biology do the species belong to given the codon of the respective species. A codon is a specific sequence of nucleotides on a DNA or RNA that corresponds to a specific amino acid or to a stop signal during protein translation. A nucleotide is made up of a nucleobase, a sugar, and a phosphate group. A sequence of three nucleotides constitutes a codon. By inputting the codon values such as UUU, UCA, CUC, AUU, etc.. i.e., the combinations of A, U, G, C which stands for Adenine, Uracil, Guanine and Cytosine respectively, the user can identify which kingdom of species do the organism belong to. This helps the bioscientists to proceed their study in a successful manner. The DNA Kingdom Prediction tool is a valuable tool for the scientists looking to ease and optimize their research.

USAGE OF INTEL ONE API: IntelOneDAL from OneAPI is used and it got better results and had a faster computation.

Intel oneAPI Data Analytics Library (oneDAL) is a software library which provides a collection of optimized algorithms and routines for data analytics and machine learning tasks. oneDAL offers a unified programming interface that allows developers to accelerate data processing and analysis across different hardware platforms, including CPUs, GPUs, and FPGAs. It supports popular data science frameworks such as Python, R, and C++ and provides efficient implementations of key algorithms like data preprocessing, clustering, regression, and classification. With oneDAL, developers can leverage Intel's optimized algorithms to improve the performance and scalability of their data analytics applications.

BUILDING THE MODEL USING COLAB took 2 minutes and 43 seconds.

BUILDING THE MODEL USING INTEL ONE API took 55 seconds.

Methodology / Approach

1.Importing the Packages

2.Preprocessing of Data

3.Transformation of Data

4.Preparation of Model

5.Serialization of Objects

6.Deployment

Technologies Used

Libraries used:

1.Numpy

2.Pandas

3.Seaborn

4.MatplotLib

5.Scikit-Learn

6.Pickle

7.StreamLit

Toolkit used is IntelOneAPI

Repository

https://github.com/InaMinaMynahMo/IntelOneAPI