US 10,832,799 B2 · Multi-level architecture of pattern recognition in biological data

Abstract

Methods, systems and apparatus for detecting patterns in constituents of at least one biological organism are disclosed. In accordance with one method, clusters of the constituents are determined (208) by selecting (210) different subsets of at least one of genes or proteins and identifying (212) the clusters from biological data corresponding to the selected subsets. Here, membership values for the constituents, indicating membership within the clusters, are calculated for use as a basis of an additional cluster determination process (208) to obtain final clusters of constituents. By underpinning the preliminary clustering on different subsets of biological data and formulating the higher-level clustering on the basis of the membership values, the embodiments can enable an evaluation of a large variety of biological data in a practical, accurate and highly efficient manner.

Claims20

Dependent claims

A system for detecting patterns in constituents of at least one biological organism, said system being implemented by a user interface and at least one hardware processor and comprising:

a data pre-processor of the at least one hardware processor configured to compile a first feature data set from at least one of genomic or proteomic data of the constituents of said at least one biological organism;
a clustering module of the at least one hardware processor configured to:
select multiple subsets of at least one of genes or proteins,
identify clusters of said constituents from portions of the first feature data set corresponding to said selected subsets,
compute membership values for said constituents indicating membership within said clusters, and
perform an additional cluster determination process to obtain final clusters of constituents, wherein said additional cluster determination process clusters said constituents based on said membership values;
and
a representation generator of the at least one hardware processor configured to generate a visual representation of at least the final clusters of constituents, and further configured to output the generated visual representation to the user interface.

5 more elements

A method for detecting patterns in constituents of at least one biological organism, said method being implemented by a user interface and at least one hardware processor and comprising:

receiving a dataset comprising at least one of genomic or proteomic data of the constituents of said at least one biological organism;
compiling a first feature data set from the received at least one of genomic or proteomic data of the constituents of said at least one biological organism;
selecting multiple subsets of at least one of genes or proteins;
identifying said clusters from portions of the first feature data set corresponding to said selected subsets;
computing membership values for said constituents indicating membership within said clusters;
performing an additional cluster determination process to obtain final clusters of constituents, wherein said additional cluster determination process clusters said constituents based on said membership values;
generating a visual representation of at least the final clusters of constituents;
and
displaying the generated visual representation via the user interface.

6 more elements

A non-transitory computer-readable medium comprising a computer-readable program for execution by a processor, the non-transitory computer-readable medium comprising:

instructions for receiving a dataset comprising at least one of genomic or proteomic data of the constituents of said at least one biological organism;
instructions for compiling a first feature data set from the received at least one of genomic or proteomic data of the constituents of said at least one biological organism;
instructions for selecting multiple subsets of at least one of genes or proteins;
instructions for identifying clusters from portions of the first feature data set corresponding to said selected subsets;
instructions for computing membership values for said constituents indicating membership within said clusters;
instructions for performing an additional cluster determination process to obtain final clusters of constituents, wherein said additional cluster determination process clusters said constituents based on said membership values;
instructions for generating a visual representation of at least the final clusters of constituents;
and
instructions for displaying the generated visual representation via the user interface.

6 more elements

Dependencies are inferred from the claim text.

Multi-level architecture of pattern recognition in biological data

Life of this patent

Multi-level architecture of pattern recognition in biological data

Life of this patent

Abstract

Claims20