MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202621056267 A) filed by Dr. D. Y. Patil Institute Of Technology, Pimpri, Pune - on May 04, 2026, for Genomic Data Pattern Mining And Graph Mining For Disease Association.
Inventors include Mrs. Swati D. Khairnar; Miss. Sanika Kate; and Ms. Shraddha Shingne.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: Its area of invention lies in the area of genomics, bioinformatics, data mining, and graph mining, and more in a computational system of identifying disease-related genes, mutations, and molecular pathways. Most existing approaches to connecting genomic variations to diseases like GWAS and network-based analyses are faced with a number of limitations. They are frequently incapable of dealing with both the size and the complexity of genomic data, are not as strong as modeling the interactions between and among more than one genetic factor, and they are rarely integrated to put together mining methods both on the data and on the network point of view. Moreover, their outcomes cannot be easily interpreted and can hardly be used at clinical scale, limiting their usefulness with precision medicine and translational research. The invention offers an end-to-end system where genomic data mining algorithms e.g., frequent pattern mining, association rule mining, machine learning and deep learning are combined with graph mining algorithms e.g., community detection, link prediction, frequent subgraph mining and graph neural networks. It includes: (i) what is referred to as data mining resources including SNP profiles, DNA sequences, gene expression data and biological interaction networks; (ii) what is referred to as data preprocessing module, which cleans, normalizes and extracts the properties of the data; (iii) what is referred to as data mining module, which identifies predictable co-occurring variants and predictive patterns; (iv) what is referred to as a graph mining module, which analyzes the biological networks; and (v) what is referred to as an integration layer wherein the results are integrated so as to come. The system produces prioritized disease-related genes, pattern variations, molecular modules and individual risk scores. The notable benefits include increased accuracy in disease gene discovery, increased biological interpretability, large and multi-omics data, and the ability to apply personalized medicine and drug discovery platforms. This invention therefore offers a new and non-obvious model of supporting accuracy healthcare with the help of genomics data analysis.
Disclaimer: Curated by HT Syndication.
