# US 12,118,446 B2 · Computer-implemented method for determining survey sampling parameters for environmental nucleic acid

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

- Number: US 12,118,446 B2
- Document ID: US12118446B2
- Status: Granted
- Kind: B2
- Application number: 17/356,409
- Filed: 2021-06-23
- Published: 2021-10-14
- Granted: 2024-10-15
- Earliest claimed: 2019-01-31
- Assignees: Nature Metrics Ltd.
- Applicants: Precision Biomonitoring Inc.
- Inventors: Mario Thomas; Wenjuan Qi; Steven Crookes; Jessmyn Adriane Niergarth
- Web page: https://patentgrep.com/patent/US12118446B2

## CPC

- G06N 20/20: Ensemble learning
- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06N 3/0499: Feedforward networks
- G06N 3/09: Supervised learning
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G16B 40/20: Supervised data analysis
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

A computer-implemented method for determining survey sampling parameters for species marker detection comprises receiving a species selection identifying selected species and receiving environmental specifications for an environment to be tested for the species. A sampling plan is generated using the environmental specifications and the species selection, and detectability prediction(s) are generated using the environmental specifications, the species selection, and the current sampling plan to predict whether species marker(s) for the selected species are detectable according to the current sampling plan. Where at least one species marker is undetectable according to the current sampling plan, the process iterates, with each subsequent iteration incorporating an increase in the total volume to be sampled, until either every species marker is detectable according to the then-current sampling plan or an iteration stop limit is reached. The sampling plan(s) and detection prediction(s) are generated using different algorithms.

## Claims

### Claim 1

A computer-implemented method for determining survey sampling parameters for at least one species marker selected from the group consisting of:
(i) environmental DNA (eDNA) barcoding;
(ii) environmental RNA (eRNA) barcoding;
(iii) eDNA metabarcoding; and
(iv) methylation of environmental DNA (eDNAm);
the method comprising:
(a) receiving a species selection identifying at least one selected species;
(b) receiving environmental specifications for an environment to be tested for the at least one species marker, wherein each species marker corresponds to a respective selected species:
(c) receiving a current sampling plan, wherein the current sampling plan is generated using the environmental specifications and the species selection and comprises:
total volume to be sampled;
total number of samples;
volume per sample; and
sample locations;
(d) receiving, for each of the selected species, a respective detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan, wherein the respective detectability prediction is generated using the environmental specifications, the species selection and the current sampling plan;
(e) testing, according to each respective detectability prediction, whether the at least one respective species marker for any of the respective selected species is undetectable according to the current sampling plan;
(f) where, according to each respective detectability prediction, at least one of the at least one respective species marker for any of the respective selected species is undetectable according to the current sampling plan, iterating through step (c), step (d), and step (e), wherein each subsequent iteration of step (c) incorporates an increase in the total volume to be sampled, until the earlier of:
(I) according to each respective detectability prediction, every respective species marker for every respective selected species is detectable according to the current sampling plan; or
(II) an iteration stop limit is reached; and
(g) upon completion of step (f)(I), setting the then-current sampling plan as a final sampling plan; wherein:
the respective detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan is generated using a detection prediction algorithm set;
the current sampling plan is generated using a survey design algorithm set;
and wherein the detection prediction algorithm set is different from the survey design algorithm set.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the at least one species marker comprises eDNA barcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts at least one of:
whether an eDNA barcode of the respective selected species is detectable according to the current sampling plan;
whether an eDNA barcode of a respective selected subspecies of the respective selected species is detectable according to the current sampling plan;
whether an eDNA barcode of a respective selected population of the respective selected species is detectable according to the current sampling plan;
whether the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan;
whether a respective selected subspecies of the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan; and
whether a respective selected population of the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan.

### Claim 3 (depends on 1)

The method of claim 1, wherein:
the at least one species marker comprises eRNA barcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts at least one of:
whether an eRNA barcode of the respective selected species is detectable according to the current sampling plan;
whether an eRNA barcode of a respective selected subspecies of the respective selected species is detectable according to the current sampling plan;
whether an eRNA barcode of a respective selected population of the respective selected species is detectable according to the current sampling plan;
whether the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan;
whether a respective selected subspecies of the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan; and
whether a respective selected population of the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan.

### Claim 4 (depends on 1)

The method of claim 1, wherein:
the at least one species marker comprises eDNA metabarcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts whether a value of a diversity metric calculated based on eDNA metabarcoding for at least one of the respective selected species, a subspecies of the respective selected species and a population of the respective selected species that can be detected with the current sampling plan satisfies a threshold.

### Claim 5 (depends on 1)

The method of claim 1, wherein:
the at least one species marker comprises eDNAm; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts whether a count of eDNAm sites correlated with at least one of a target demographic characteristic and a target physiological state of at least one of the respective selected species, a respective selected a subspecies of the respective selected species and a population of the respective selected species that can be detected with the current sampling plan satisfies a threshold.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
before using the environmental specifications and the species selection to generate a first current sampling plan, providing the environmental specifications and the species selection to a filter;
wherein the method terminates responsive to a determination by the filter that every respective species marker for every respective selected species is undetectable.

### Claim 7 (depends on 6)

The method of claim 6, wherein, for a particular one of the selected species, the filter determines that every respective species marker for that particular one of the selected species is undetectable because that particular one of the selected species cannot be naturally present in the environment.

### Claim 8 (depends on 1)

The method of claim 1, wherein the iteration stop limit is one of:
a volume limit; and
a number of iterations.

### Claim 9 (depends on 1)

The method of claim 1, wherein, for a particular one of the selected species, the respective detectability prediction indicates that each respective species marker for that particular one of the selected species is undetectable according to the current sampling plan because the particular one of the species cannot be naturally present in the environment.

### Claim 10 (depends on 1)

The method of claim 1, wherein the environmental specifications comprise one or more of site type, study site surface area, study site perimeter, study site average depth, survey month, water flow rate, water pH, water conductivity, water temperature, dissolved oxygen, turbidity, total suspended solids, total dissolved solids, presence of inhibitors, aquatic vegetation, and eDNA and/or eRNA detection results obtained from past surveys under given site data.

### Claim 11 (depends on 10)

The method of claim 10, wherein each respective detectability prediction is derived from the environmental specifications and is further derived from a species-specific dataset for that species, the species-specific dataset comprising, for each species, one or more of the class of life, at least one of a common name of the species itself and a scientific name of the species itself, average biomass, habitat preference, diet type, preferred water depth range, preferred temperature, spawning period, detection limit, and quantitation limit.

### Claim 12 (depends on 1)

The method of claim 1, wherein:
at least one of the at least one selected species is an aquatic species;
the environment is an aquatic environment; and
the current sampling plan comprises filter pore size.

### Claim 13 (depends on 12)

The method of claim 12, wherein the current sampling plan further comprises sample depth.

### Claim 14 (depends on 1)

The method of claim 1, wherein the detection prediction algorithm set comprises at least two of Generalized Linear Model, Generalized Estimating Equation, Generalized Additive Model, Random Forest, and Neural Network.

### Claim 15 (depends on 1)

The method of claim 1, wherein:
the detection prediction algorithm set comprises a plurality of detection prediction algorithms; and
for a given one of the at least one respective species marker for the respective selected species, the detectability prediction indicates that that species marker is detectable according to the current sampling plan where at least one of the detection prediction algorithms indicates that that species marker is detectable according to the current sampling plan.

### Claim 16

A data processing system adapted for determining survey sampling parameters for at least one species marker selected from the group consisting of:
(i) environmental DNA (eDNA) barcoding;
(ii) environmental RNA (eRNA) barcoding;
(iii) eDNA metabarcoding; and
(iv) methylation of environmental DNA (eDNAm);
the system comprising:
a host computing platform comprising one or more computers each with memory and at least one processor;
a survey design interface configured to receive species selections each identifying at least one selected species and to receive environmental specifications for an environment to be tested for the at least one species marker, wherein each species marker corresponds to a respective selected species;
a survey development iteration module comprising computer program instructions that when executing in the memory of the host computing platform, perform:
(a) receiving a current sampling plan, wherein the current sampling plan is generated using the environmental specifications and the species selection and comprises:
total volume to be sampled;
total number of samples;
volume per sample; and
sample locations;
(b) receiving, for each of the selected species, a respective detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan, wherein the respective detectability prediction is generated using the environmental specifications, the species selection and the current sampling plan;
(c) testing, according to each respective detectability prediction, whether the at least one respective species marker for any of the respective selected species is undetectable according to the current sampling plan;
(d) where, according to each respective detectability prediction, at least one of the at least one respective species marker for any of the respective selected species is undetectable according to the current sampling plan, iterating through step (a), step (b), and step (c) again, wherein each subsequent iteration of step (a) incorporates an increase in the total volume to be sampled, until the earlier of:
(I) according to each respective detectability prediction, every respective species marker for every respective selected species is detectable according to the current sampling plan; or
(II) an iteration stop limit is reached; and
(e) upon completion of step (d)(I), setting the then-current sampling plan as a final sampling plan;
wherein:
the respective detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan is generated using a detection prediction algorithm set;
the current sampling plan is generated using a survey design algorithm set;
and wherein the detection prediction algorithm set is different from the survey design algorithm set.

### Claim 17 (depends on 16)

The data processing system of claim 16, wherein:
the at least one species marker comprises eDNA barcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts at least one of:
whether an eDNA barcode of the respective selected species is detectable according to the current sampling plan;
whether an eDNA barcode of a respective selected subspecies of the respective selected species is detectable according to the current sampling plan;
whether an eDNA barcode of a respective selected population of the respective selected species is detectable according to the current sampling plan;
whether the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan;
whether a respective selected subspecies of the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan; and
whether a respective selected population of the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan.

### Claim 18 (depends on 16)

The data processing system of claim 16, wherein:
the at least one species marker comprises eRNA barcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling predicts at least one of:
whether an eRNA barcode of the respective selected species is detectable according to the current sampling plan;
whether an eRNA barcode of a respective selected subspecies of the respective selected species is detectable according to the current sampling plan;
whether an eRNA barcode of a respective selected population of the respective selected species is detectable according to the current sampling plan;
whether the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan;
whether a respective selected subspecies of the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan; and
whether a respective selected population of the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan.

### Claim 19 (depends on 16)

The data processing system of claim 16, wherein:
the at least one species marker comprises eDNA metabarcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts whether a value of a diversity metric calculated based on eDNA metabarcoding for at least one of the respective selected species, a subspecies of the respective selected species and a population of the respective selected species that can be detected with the current sampling plan satisfies a threshold.

### Claim 20 (depends on 16)

The data processing system of claim 16, wherein:
the at least one species marker comprises eDNAm; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts whether a count of eDNAm sites correlated with at least one of a target demographic characteristic and a target physiological state of at least one of the respective selected species, a respective selected subspecies of the respective selected species and a population of the respective selected species that can be detected with the current sampling plan satisfies a threshold.

### Claim 21 (depends on 16)

The data processing system of claim 16, wherein the computer program instructions when executing in the memory of the host computing platform, perform:
before using the environmental specifications and the species selection to generate a first current sampling plan, providing the environmental specifications and the species selection to a filter; and
responsive to a determination by the filter that every respective species marker for every respective selected species is undetectable, declining to use the environmental specifications and the species selection to generate any sampling plan.

### Claim 22 (depends on 21)

The data processing system of claim 21, wherein, for a particular one of the selected species, the filter determines that every respective species marker for that particular one of the selected species is undetectable because that particular one of the selected species cannot be naturally present in the environment.

### Claim 23 (depends on 16)

The data processing system of claim 16, wherein the iteration stop limit is one of:
a volume limit; and
a number of iterations.

### Claim 24 (depends on 16)

The data processing system of claim 16, wherein, for a particular one of the selected species, the respective detectability prediction indicates that each respective species marker for that particular one of the selected species is undetectable according to the current sampling plan because the particular one of the species cannot be naturally present in the environment.

### Claim 25 (depends on 16)

The data processing system of claim 16, wherein the environmental specifications comprise one or more of site type, study site surface area, study site perimeter, study site average depth, survey month, water flow rate, water pH, water conductivity, water temperature, dissolved oxygen, turbidity, total suspended solids, total dissolved solids, presence of inhibitors, aquatic vegetation, and eDNA and/or eRNA detection results obtained from past surveys under given site data.

### Claim 26 (depends on 25)

The data processing system of claim 25, wherein each respective detectability prediction is derived from the environmental specifications and is further derived from a species-specific dataset for that species, the species-specific dataset comprising, for each species, one or more of the class of life, at least one of a common name of the species itself and a scientific name of the species itself, average biomass, habitat preference, diet type, preferred water depth range, preferred temperature, spawning period, detection limit, and quantitation limit.

### Claim 27 (depends on 16)

The data processing system of claim 16, wherein:
at least one of the at least one selected species is an aquatic species;
the environment is an aquatic environment; and
the current sampling plan comprises filter pore size.

### Claim 28 (depends on 27)

The data processing system of claim 27, wherein the current sampling plan further comprises sample depth.

### Claim 29 (depends on 16)

The data processing system of claim 16, wherein the detection prediction algorithm set comprises at least two of Generalized Linear Model, Generalized Estimating Equation, Generalized Additive Model, Random Forest, and Neural Network.

### Claim 30 (depends on 16)

The data processing system of claim 16, wherein:
the detection prediction algorithm set comprises a plurality of detection prediction algorithms; and
for a given one of the at least one respective species marker for the respective selected species, the detectability prediction indicates that that species marker is detectable according to the current sampling plan where at least one of the detection prediction algorithms indicates that that species marker is detectable according to the current sampling plan.

### Claim 31

A computer program product for determining survey sampling parameters for at least one species marker selected from the group consisting of:
(i) environmental DNA (eDNA) barcoding;
(ii) environmental RNA (eRNA) barcoding;
(iii) eDNA metabarcoding; and
(iv) methylation of environmental DNA (eDNAm);
the computer program product including a non-transitory tangible computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to perform a method including:
(a) receiving a species selection identifying at least one selected species;
(b) receiving environmental specifications for an environment to be tested for the at least one species marker, wherein each species marker corresponds to a respective selected species:
(c) receiving a current sampling plan, wherein the current sampling plan is generated using the environmental specifications and the species selection and comprises:
total volume to be sampled;
total number of samples;
volume per sample; and
sample locations;
(d) receiving, for each of the selected species, a respective detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan, wherein the respective detectability prediction is generated using the environmental specifications, the species selection and the current sampling plan;
(e) testing, according to each respective detectability prediction, whether the at least one respective species marker for any of the respective selected species is undetectable according to the current sampling plan;
(f) where, according to each respective detectability prediction, at least one of the at least one respective species marker for any of the respective selected species is undetectable according to the current sampling plan, iterating through step (c), step (d), and step (e) again, wherein each subsequent iteration of step (c) incorporates an increase in the total volume to be sampled, until the earlier of:
(I) according to each respective detectability prediction, every respective species marker for every respective selected species is detectable according to the current sampling plan; or
(II) an iteration stop limit is reached; and
(g) upon completion of step (f)(I), setting the then-current sampling plan as a final sampling plan; wherein:
the respective detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan is generated using a detection prediction algorithm set;
the current sampling plan is generated using a survey design algorithm set;
and wherein the detection prediction algorithm set is different from the survey design algorithm set.

### Claim 32 (depends on 31)

The computer program product of claim 31, wherein:
the species marker comprises eDNA barcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts at least one of:
whether an eDNA barcode of the respective selected species is detectable according to the current sampling plan;
whether an eDNA barcode of a respective selected subspecies of the respective selected species is detectable according to the current sampling plan;
whether an eDNA barcode of a respective selected population of a species is detectable according to the current sampling plan;
whether the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan;
whether a respective selected subspecies of the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan; and
whether a respective selected population of the respective selected species is quantifiable by eDNA barcoding according to the current sampling plan.

### Claim 33 (depends on 31)

The computer program product of claim 31, wherein:
the at least one species marker comprises eRNA barcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts at least one of:
whether an eRNA barcode of the respective selected species is detectable according to the current sampling plan;
whether an eRNA barcode of a respective selected subspecies of the respective selected species is detectable according to the current sampling plan;
whether an eRNA barcode of a respective selected population of the respective selected species is detectable according to the current sampling plan;
whether the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan;
whether a respective selected subspecies of the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan; and
whether a respective selected population of the respective selected species is quantifiable by eRNA barcoding according to the current sampling plan.

### Claim 34 (depends on 31)

The computer program product of claim 31, wherein:
the at least one species marker comprises eDNA metabarcoding; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts whether a value of a diversity metric calculated based on eDNA metabarcoding for at least one of the respective selected species, a subspecies of the respective selected species and a population of the respective selected species that can be detected with the current sampling plan satisfies a threshold.

### Claim 35 (depends on 31)

The computer program product of claim 31, wherein:
the at least one species marker comprises eDNAm; and
the detectability prediction as to whether the at least one respective species marker for the respective selected species is detectable according to the current sampling plan predicts whether a count of eDNAm sites correlated with at least one of a target demographic characteristic and a target physiological state of at least one of the respective selected species, a respective selected subspecies of the respective selected species and a population of the respective selected species that can be detected with the current sampling plan satisfies a threshold.

### Claim 36 (depends on 31)

The computer program product of claim 31, wherein:
the instructions cause, before using the environmental specifications and the species selection to generate a first current sampling plan, providing the environmental specifications and the species selection to a filter; and
the method terminates responsive to a determination by the filter that every respective species marker for every respective selected species is undetectable.

### Claim 37 (depends on 36)

The computer program product of claim 36, wherein, for a particular one of the selected species, the filter determines that every respective species marker for that particular one of the selected species is undetectable because that particular one of the selected species cannot be naturally present in the environment.

### Claim 38 (depends on 31)

The computer program product of claim 31, wherein the iteration stop limit is one of:
a volume limit; and
a number of iterations.

### Claim 39 (depends on 31)

The computer program product of claim 31, wherein, for a particular one of the selected species, the respective detectability prediction indicates that each respective species marker for that particular one of the selected species is undetectable according to the current sampling plan because the particular one of the species cannot be naturally present in the environment.

### Claim 40 (depends on 31)

The computer program product of claim 31, wherein the environmental specifications comprise one or more of site type, study site surface area, study site perimeter, study site average depth, survey month, water flow rate, water pH, water conductivity, water temperature, dissolved oxygen, turbidity, total suspended solids, total dissolved solids, presence of inhibitors, aquatic vegetation, and eDNA and/or eRNA detection results obtained from past surveys under given site data.

### Claim 41 (depends on 40)

The computer program product of claim 40, wherein each respective detectability prediction is derived from the environmental specifications and is further derived from a species-specific dataset for that species, the species-specific dataset comprising, for each species, one or more of the class of life, at least one of a common name of the species itself and a scientific name of the species itself, average biomass, habitat preference, diet type, preferred water depth range, preferred temperature, spawning period, detection limit, and quantitation limit.

### Claim 42 (depends on 31)

The computer program product of claim 31, wherein:
at least one of the at least one selected species is an aquatic species;
the environment is an aquatic environment; and
the current sampling plan comprises filter pore size.

### Claim 43 (depends on 42)

The computer program product of claim 42, wherein the current sampling plan further comprises sample depth.

### Claim 44 (depends on 31)

The computer program product of claim 31, wherein the detection prediction algorithm set comprises at least two of Generalized Linear Model, Generalized Estimating Equation, Generalized Additive Model, Random Forest, and Neural Network.

### Claim 45 (depends on 31)

The computer program product of claim 31, wherein:
the detection prediction algorithm set comprises a plurality of detection prediction algorithms; and
for a given one of the at least one respective species marker for the respective selected species, the detectability prediction indicates that that species marker is detectable according to the current sampling plan where at least one of the detection prediction algorithms indicates that that species marker is detectable according to the current sampling plan.