Towards a Protein-Protein Interactions Framework using Graph Analytics on Apache Spark

Abstract

The field of data science has facilitated the extraction of information from organized and unstructured data. It utilizes several approaches, algorithms, and processes to evaluate complex data effectively. Protein-Protein Interactions (PPIs) are crucial for a variety of chemical processes. This initiative will build predictive models that give a more efficient and straightforward way for PPI prediction to enhance the PPI prediction for high throughput. This work uses the PageRank algorithm for PPI systems' organic properties. PageRank is a method for ranking that can rate the interaction in MIPS datasets. It assigns a value to each interaction and determines the protein IDs with the most significant number of interactions. We have used the Perl programming language, Mlib, and GraphX libraries for PPI predictions. The data suggest that this method yields quicker execution times and good outcomes.