# US 2026/0265840 A1 · Probability enhanced ai configured to perform a task impacted by molecular abundance and related ai-driven models, devices, methods and systems

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0265840 A1
- Document ID: US20260265840A1
- Status: Published application
- Kind: A1
- Application number: 19/337,768
- Filed: 2025-09-23
- Published: 2026-09-10
- Earliest claimed: 2025-03-05
- Assignees: California Institute of Technology
- Applicants: California Institute of Technology
- Inventors: Rustem F ISMAGILOV; Matthew M COOPER; Matthew W THOMSON
- Web page: https://patentgrep.com/patent/US20260265840A1

## CPC

- G06N 20/00: Machine learning
- C12Q 1/689: for bacteria
- C12Q 1/6895: for plants, fungi or algae
- G06N 3/047: Probabilistic or stochastic networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G16B 5/20: Probabilistic models
- G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B 40/00: ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B 40/20: Supervised data analysis
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- C12Q: MEASURING OR TESTING PROCESSES INVOLVING ENZYMES, NUCLEIC ACIDS OR MICROORGANISMS (immunoassay G01N33/53); COMPOSITIONS OR TEST PAPERS THEREFOR; PROCESSES OF PREPARING SUCH COMPOSITIONS; CONDITION-RESPONSIVE CONTROL IN MICROBIOLOGICAL OR ENZYMOLOGICAL PROCESSES
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

A probability enhanced AI configured to perform tasks impacted by molecular abundance and related models, devices, methods and systems, which are powered by probability distributions for a parameter used in detection of molecular abundance, and enable performance of tasks based on detected molecular abundances with higher accuracy and precision that is than accuracy and precision achievable by existing approaches, according to a probability-enhanced approach for AI performance of tasks. Described are also StochQuant detection methods and systems and related models and devices of a StochQuant approach to detection of molecular abundance which can be performed with AI-driven models and/or non-AI driven models alone or in connection with the probability-enhanced approach for AI performance of tasks impacted by molecular abundance.

## Claims

### Claim 1

A computer-implemented method to perform a task based on a target abundance of a target molecule in a target physical environment, the method being performed by at least one hardware processor of a computing system and comprising:
(a) receiving by the computing system, inference data comprising one or more probability distributions of the target abundance of the target molecule in a testing physical environment;
(b) inputting by the computing system the inference data into an AI-driven model configured to sample abundance values from the one or more probability distributions of the inference data, and trained to map the abundance values to performance of the task;
(c) generating by the computing system a distribution of inferences by sampling one or more times from the one or more probability distributions, to produce a set of plausible output for the AI-driven model via a forward pass of the AI-driven model; and
(d) performing the task based on the distribution of inferences from the set of plausible output for the AI-driven model.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, where at least one probability distribution of the target abundance is a probability distribution of the target molecule abundance in the target physical environment generated by a model of a measuring workflow for a molecular count of the target molecule and a reference molecule, the stochastic model being configured, by execution on one or more hardware processors, to:
divide the measuring workflow into one or more measuring segments arranged in a measuring workflow order, each measuring segment comprising one or more physical manipulations impacting the molecular count of the target molecule and/or the reference molecule;
connect outputs of said measuring segments into inputs of subsequent measuring segments in the measuring workflow order; and
receive model inputs comprising physical parameters, and produce, in a memory accessible by the one or more hardware processors, the probability distribution of the target abundance of the target molecule based on the measuring workflow,
wherein the probability distribution of the target molecule abundance is obtained as a function of
i) a molecular count of the target molecule detected
a. in the target physical environment or a sample thereof, or
b. in the testing physical environment, or a sample thereof,
ii) a molecular count of a reference molecule added to or detected
a. in the target physical environment or a sample thereof, or
b. in the testing physical environment, or a sample thereof in combination with
iii) an absolute anchoring value of the reference molecule
a. in the target physical environment or a sample thereof, or
b. in the testing physical environment, or a sample thereof.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, wherein the probability distribution is at least one of: a Poisson distribution, a binomial distribution, a gamma-Poisson distribution, a negative binomial distribution and an empirical distribution.

### Claim 4 (depends on 2)

The computer-implemented method of claim 2, wherein the one or more physical manipulations comprise one or more of: separation of a sample from the target physical environment or the testing physical environment, flow cell binding, amplification manipulations, hybridization, isolation of the target molecule, reverse transcription, and target enrichment.

### Claim 5 (depends on 2)

The computer-implemented method of claim 2, wherein at least one of the one or more measuring segments comprise one or more of: separation of a sample from the target physical environment or the testing physical environment, flow cell binding, amplification, isolation of the target molecule, reverse transcription, hybridization, sequencing and target enrichment.

### Claim 6 (depends on 2)

The computer-implemented method of claim 2, wherein the physical parameters comprise at least a target molecule molecular count, a reference molecule molecular count, and an absolute anchoring value of the reference molecule.

### Claim 7 (depends on 6)

The computer-implemented method of claim 6, wherein the reference molecule is at least one of: a synthetic nucleic acid that contains a unique sequence detectably different from sequences of the target molecule and other molecules in the target physical environment or the testing physical environment; a synthetic nucleic acid having physical properties similar to the target molecule such that manipulations of the measuring workflow affect the reference molecule molecular count in the same way as the target molecule molecular count; a plurality of 16S rRNA gene molecules; and a molecule known or expected to be in the target physical environment or the testing physical environment and to be detectable with a testing measurement.

### Claim 8 (depends on 6)

The computer-implemented method of claim 6, wherein the reference molecule is at least one of: a gene marker of an organism known or expected to be in the target physical environment or the testing physical environment and to be detectable with the testing measurement or a human sequence expected to be in the target physical environment or the testing physical environment and to be detectable with the testing measurement.

### Claim 9 (depends on 6)

The computer-implemented method of claim 6, wherein the absolute anchoring value of the reference molecule is determined by one or more of: a spike-in of a reference molecule into the target physical environment or a sample thereof or the testing physical environment or a sample thereof, a digital PCR measurement, or a qPCR with a standard curve.

### Claim 10 (depends on 2)

The computer-implemented method of claim 2, wherein the target molecule comprises a plurality of target molecules and a detected count of the target molecule from the measurement workflow comprises a plurality of detected counts of each target molecule of the plurality of target molecules.

### Claim 11 (depends on 10)

The computer-implemented method of claim 10, wherein:
the plurality of detected counts forms an omics dataset; and one or more of:
the plurality of target molecules comprises biological molecules of an organism and the omics data set is a biological dataset of the organism; or
the plurality of target molecules comprises DNA molecules of an organism and the omics data set is a genomics dataset of the organism; or
the plurality of target molecules comprises RNA molecules of an organism and the omics data set is a transcriptomics dataset of the organism; or
the plurality of target molecules comprises a protein molecule of an organism and the omics data set is a proteomics dataset of the organism.

### Claim 12 (depends on 2)

The computer-implemented method of claim 2, wherein the target molecule is related to one or more of: prenatal testing, cancer testing, autoimmune testing, testing for a sexually transmitted disease, testing for bacterial vaginosis, and testing for Vulvovaginal Candidiasis.

### Claim 13 (depends on 2)

The computer-implemented method of claim 2, wherein the measurement workflow comprises amplicon sequencing and/or multiplex amplicon sequencing.

### Claim 14 (depends on 2)

The computer-implemented method of claim 2, wherein the measurement workflow comprises one or more of: shotgun metagenomic sequencing; bulk RNA sequencing; single cell RNA sequencing; Hybrid-capture sequencing, Nanopore Sequencing, Whole-genome sequencing (WGS), RNA sequencing (RNA-seq), Long-read sequencing, Single-cell sequencing, Whole exome sequencing (WES), Illumina Sequencing, Third Generation Sequencing, and methyl DNA sequencing.

### Claim 15 (depends on 1)

The computer-implemented method of claim 1, wherein the inference data further comprises biological or medical data relating to the testing physical environment.

### Claim 16 (depends on 1)

The computer-implemented method of claim 1, wherein at least one of the testing physical environment and the target environment comprises one or more of:
a sample obtained from a human, plant, fungi, bacteria colony, or animal;
material derived from a sample obtained from a human, plant, fungi, bacteria colony, or animal; food;
a tagged or encoded library of molecules;
wastewater;
a pooled sample of any of the human, plant, fungi, bacteria colony and animal samples, any material derived therefrom, any tagged or encoded library of molecules, and/or wastewater sample; and
a liquid biopsy sample.

### Claim 17 (depends on 1)

The computer-implemented method of claim 1, wherein at least one of the target environment and the testing environment comprises one or more of Vaginal swabs, Amniotic fluid, Liquid biopsy samples, including peripheral blood samples for circulating tumor DNA detection, Urine, First catch urine, Cervical/endocervical swabs, Urethral swabs, Penile swabs, Surgical resection specimens, Fecal specimens, Upper respiratory tract specimens including nasopharyngeal oropharyngeal swabs, anterior nasal, or mid-turbinate swabs, Lower respiratory tract specimens including sputum, bronchoalveolar lavage, and endotracheal aspirates, Tissue biopsies, including core needle, incisional, or excisional biopsies, Formalin-fixed or paraffin-embedded tissue, Cytology specimens including fine needle aspirates, minimally invasive sampling, brushings and washings, Saliva, synovial fluid, pericardial fluid, and wound swabs, Blood fraction, pleural, peritoneal, or cerebrospinal fluids, and exhaled breath condensate.

### Claim 18 (depends on 1)

The computer-implemented method of claim 1, wherein each inference for the distribution of inferences comprises a classification based at least in part on class identifier labels.

### Claim 19 (depends on 1)

The computer-implemented method of claim 1, wherein the task comprises:
at least one diagnostic task selected from disease identification and classification, abnormality detection, monitoring disease progression, treatment planning and differential diagnosis; and/or at least one clinical application task selected from treatment of a disease, monitoring disease progression over time, assessing treatment effectiveness, and detecting potential recurrence of disease.

### Claim 20 (depends on 1)

The computer-implemented method of claim 1, wherein the AI-driven model is a probability-enhanced AI-driven model trained using data from at least one measuring workflow that is different than the measuring workflow used for the inference data.

### Claim 21 (depends on 1)

The computer-implemented method of claim 1, wherein the AI-driven model is a probability-enhanced AI-driven model trained using training data that comprise probability distributions from at least two different measuring workflows
wherein the probability distribution of the target molecule abundance is obtained as a function of
i) a molecular count of the target molecule detected
a. in the target physical environment or a sample thereof, or
b. in a testing physical environment, or a sample thereof,
ii) a molecular count of a reference molecule added to or detected
a. in the target physical environment or a sample thereof, or
b. in the testing physical environment, or a sample thereof
in combination with
iii) an absolute anchoring value of the reference molecule
a. in the target physical environment or a sample thereof, or
b. in the testing physical environment, or a sample thereof.

### Claim 22 (depends on 1)

The computer-implemented method of claim 1, wherein the inference data comprise at least two measurement workflows.

### Claim 23 (depends on 1)

The computer-implemented method of claim 1, wherein performing the task comprises computing by the computing system of at least one summary statistic of the distribution of inferences from the set of plausible output for the AI model, and using the summary statistic to perform the task.

### Claim 24 (depends on 23)

The computer-implemented method of claim 23, wherein the summary statistic comprises at least one of: a minimum, maximum, percentile, median, geometric mean, variance, standard deviation, or coefficient of variation, of the distribution of inferences.

### Claim 25 (depends on 1)

The computer-implemented method of claim 1, further comprising: setting a confidence interval for the distribution of inferences, and computing a confidence level of the distribution of inferences by calculating what portion of the distribution of inferences is within the confidence interval.

### Claim 26 (depends on 25)

The computer-implemented method of claim 25, wherein the confidence interval is used in performing the task.

### Claim 27 (depends on 2)

The computer-implemented method of claim 2, wherein the measuring workflow comprises use of a real-time sequencer.

### Claim 28 (depends on 27)

The computer-implemented method of claim 27, further comprising: (a) iteratively updating the one or more probability distributions as new molecular counts are received from the real-time sequencer; and (b) iteratively updating the distribution of inferences to provide a real-time performance of the task.

### Claim 29 (depends on 27)

The computer-implemented method of claim 27, wherein performing the task comprises computing by the computing system at least one summary statistic of the distribution of inferences from the set of plausible output for the AI model, and using the summary statistic to perform the task and wherein the method further comprises terminating the real-time sequencing of the measuring workflow prior to its scheduled completion based on the summary statistic meeting a predefined confidence threshold for the task.

### Claim 30 (depends on 2)

The computer-implemented method of claim 2, wherein the measuring workflow comprises use of one or more of digital immunoassays, single molecule fluorescence in situ hybridization, hybridization chain reaction, or next generation sequencing.
