Compositions and methods for cellular phenotype assessment of a sample using confined volume arrays
Inventors
Fisher, Matthew • Arab, Nicolas • Johnson, Ross • Bussian, David
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12595505-B2
Publication Date
2026-04-07
Expiration Date
Abstract
Certain embodiments of the invention are directed to evaluating and identifying cells by recording and interpreting a time-dependent signal produced by unique cell respiration and permeability attributes of isolated viable cells. Some methods comprise dividing the sample into two or more sub-samples or sample portions, mixing each sub-sample or sample portion with one or more reagents and/or one or more reactants forming distinct sub-sample or sample portion mixtures, compartmentalizing each of the sub-sample or sample portion mixtures into a plurality of small volume compartments, monitoring characteristics of the small volume compartments over time and collecting compartment data, and transmitting the collected data to at least one neural network.
Core Innovation
The method evaluates a sample by partitioning it into portions and placing resulting mixtures into small-volume droplet compartments, some containing a cell or cellular aggregate. Signals are detected over time, and collected droplet data are processed through a first neural network to generate a classifier output. A second neural network subsequently receives the classifier output to generate an analysis output for clinical predictions.
The method performs phenotype-based analysis to assess resistance beyond known genetic markers through comparisons of control portions and drug-treated test portions. Cellular responses are evaluated across compartments over time to determine treatment efficacy. The resulting evaluations generate analytical endpoints that include pathogen classification, antimicrobial susceptibility, minimum inhibitory concentration, patient outcome, and clinical prognosis.
Claims Coverage
The claim coverage includes one independent claim reciting four inventive features directed to sample compartmentalization, time-dependent signal collection, and two-stage neural network processing.
Droplet compartmentalization of sample portions
The claim covers dividing a sample into portions, mixing each portion with reagents or reactants, and compartmentalizing the resulting mixtures into droplets, some of which contain one cell or cellular aggregate.
Time-dependent signal collection
The claim covers detecting signals over time from droplets and collecting the detected signals as droplet data.
Classifier output from a first neural network
The claim covers transmitting collected droplet data to a first neural network to generate a classifier output for a cell or cellular aggregate.
Analysis output from a second neural network
The claim covers transmitting the classifier output to a second neural network to generate an analysis output.
The independent claim combines droplet compartmentalization and time-dependent signal collection with a first neural network generating a classifier output and a second neural network generating an analysis output. Dependent claims cover endpoints including antimicrobial susceptibility, minimum inhibitory concentration, classifying susceptible or resistant cells, patient outcome, and prognosis.
Stated Advantages
Small-volume compartments enable rapid signal detection and results.
Phenotype-based analysis can assess resistance beyond known genetic markers.
The reported antimicrobial susceptibility testing categorical agreement is 97.9% against broth microdilution, with high sensitivity and specificity reported for pathogen-identification results.
The figure summary reports pathogen identification with 93.3% overall test accuracy (126/135) and antimicrobial susceptibility testing in 2–4 hours, with species-level accuracies ranging from 75% to 100%.
Documented Applications
Pathogen classification and pathogen identification.
Antimicrobial susceptibility testing, including testing of antimicrobial response, determining minimum inhibitory concentration, and classifying cells as susceptible or resistant.
Generating clinical endpoints that include patient outcome and prognosis.
Interested in licensing this patent?