MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122899 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'multi-omics clustering system for cancer subtyping using latent subspace learning.'
Inventor(s) include V. Ezhil Arasi; and Izhan Ahmed H.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a multi-omics clustering system for cancer subtyping that includes a data processing module configured to receive multi-omics datasets having at least two omics types selected from genomics, transcriptomics, proteomics, methylation, and miRNA expression data, wherein the datasets include complete samples having data for all omics types and incomplete samples having data for fewer omics types. The system includes a feature extraction module configured to apply dimensionality reduction to generate reduced-dimension feature matrices, a latent subspace construction module configured to construct a latent subspace using feature matrices from complete samples, a projection learning module configured to learn projection matrices based on the latent subspace and complete sample feature matrices, a projection module configured to project incomplete samples into the latent subspace using learned projection matrices, and a clustering module configured to perform clustering on all samples in the latent subspace to identify cancer subtypes."
Disclaimer: Curated by HT Syndication.
