PINS: a perturbation clustering approach for data integration and disease subtyping
Disease subtyping is accomplished by a computer-implemented algorithm that manipulates a first genetic dataset to construct a set of first connectivity matrices. To this set of matrices Gaussian noise is introduced to generate a perturbed dataset. The computer-implemented algorithm assesses which of the set of first connectivity matrices was least affected by introduction of noise and that matric is used to define the optimal clustering. Once the optimal clustering is determined, computer-implemented supervised classification is performed to determine, for a particular patient, with which disease subtype cluster that person's genetic data most closely aligns. Armed with this knowledge, the treatment regimen is specified with much higher likelihood of success.
1. A method of conducting at least one of a drug or treatment trial, comprising:
acquiring a first quantitative biological dataset from a population of candidates;
processing the first quantitative biological dataset using a computer-implemented unsupervised cluster analysis process to define a plurality of clusters to partition patient data corresponding to the first quantitative biological dataset;
storing said plurality of clusters in a data store comprising a non-transitory computer-readable memory;
acquiring second quantitative biological data from at least one individual candidate and processing the acquired second quantitative biological data using a computer-implemented classifier, the classifier ingesting the plurality of clusters in said data store and using the plurality of clusters to find which of the plurality of clusters represents a closest match to the acquired second quantitative biological data of an individual patient;
storing a cluster of the plurality of clusters found to represent the closest match as patient classification data in a non-transitory computer-readable memory;
using the patient classification data in determining whether said at least one individual candidate qualifies as a suitable subject of said at least one of the drug or treatment trial; and
administering at least one of a drug or treatment regimen to said at least one candidate that has qualified as a suitable subject of said at least one of drug or treatment trial,
wherein the unsupervised cluster analysis process comprises:
(a) applying a computer-implemented algorithm to the first quantitative biological dataset to construct a set of first connectivity matrices which are then stored in non-transitory computer-readable memory;
(b) using a computer-implemented algorithm to construct and store in non-transitory computer-readable memory a perturbed dataset by introducing noise into the first quantitative biological dataset;
(c) applying a computer-implemented algorithm to the perturbed dataset to construct a set of perturbed connectivity matrices which are then stored in non-transitory computer-readable memory;
(d) using a computer-implemented algorithm to perform a stability assessment that reads from memory and compares the first connectivity matrices with the perturbed connectivity matrices;
(e) using a computer-implemented algorithm to select, from among the first set of connectivity matrices, a matrix whose corresponding perturbed matrix is least affected by the introduction of noise; and
(f) storing the selected matrix in non-transitory computer-readable memory and using a computer-implemented algorithm to construct the plurality of clusters.