# US 11,309,062 B2 · Hierarchical optimized detection of relatives > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,309,062 B2 - Document ID: US11309062B2 - Status: Granted - Kind: B2 - Application number: 16/148,341 - Filed: 2018-10-01 - Published: 2019-04-04 - Granted: 2022-04-19 - Earliest claimed: 2017-10-01 - Assignees: Syracuse University - Applicants: Michael Marciano; Jonathan D. Adelman - Inventors: Michael Marciano; Jonathan D. Adelman - Web page: https://patentgrep.com/patent/US11309062B2 ## CPC - 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 20/20: Allele or variant detection, e.g. single nucleotide polymorphism [SNP] detection - G16B 30/00: ICT specially adapted for sequence analysis involving nucleotides or amino acids - C12Q 1/68: involving nucleic acids - G16H 10/20: for electronic clinical trials or questionnaires - G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY - 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 - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract A system for evaluating a DNA sample and determining whether the sample contains related individuals and/or unrelated individuals with high levels of alleles sharing. Trained and pre-validated machine learning algorithms are to rapidly and probabilistically assess the presence of relatives in a DNA mixture. To make a probabilistic determination, the system evaluates aspect of the sample that have not be considered before, such as peak heights, peak height ratios, maximum peak heights, minimum peak heights, ratios of allele heights to one another, number of contributors using maximum allele count method, and quantitative measures of the amount of DNA contributed by the male and female organisms. The system identifies whether a DNA sample has contributors that are not readily identifiable based on the data and can thus improve downstream analysis. ## Claims ### Claim 1 A method of determining whether a sample of DNA contains related contributors, comprising the steps of: receiving peak detection signals for a predetermined number of loci in a DNA sample; establishing from the peak detection signals a first set of peak detection data to be transformed and a second set of peak detection data to remain untransformed; transforming the first set of peak detection data using at least one of a plurality of transformation approaches; inputting the transformed first set of peak detection data and untransformed second set of peak detection data into a trained machine learning algorithm to produce a probability for each locus in the DNA sample that there were multiple, genetically related contributors. ### Claim 2 (depends on 1) The method of claim 1, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of performing signal detection by determining an average baseline noise for each locus and then thresholding each locus with the average baseline noise for that locus. ### Claim 3 (depends on 1) The method of claim 1, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of trimming the peak detection signals by [i] and any signals indicating slipped strand mispairing or sequencing errors. ### Claim 4 (depends on 3) The method of claim 3, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of determining a ratio of a minimum trimmed signal and a baseline value. ### Claim 5 (depends on 1) The method of claim 1, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of dividing a peak height for a bi-allelic gender determining marker by a total peak height of a multi-allelic gender specific marker and then by a number of contributors as determined according to a maximum allele count. ### Claim 6 (depends on 1) The method of claim 1, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of determining a difference between a peak height for a female specific allele in a bi-allelic gender determining DNA marker and a total peak height for all alleles detected at a multi-allelic gender specific marker. ### Claim 7 (depends on 6) The method of claim 6, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches further includes the step of dividing the difference between the peak height for the female specific allele in the bi-allelic gender determining DNA marker and the total peak height for all alleles detected at the multi-allelic gender specific marker by a total peak height for all alleles detected at the multi-allelic gender specific marker. ### Claim 8 (depends on 1) The method of claim 1, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of determining an average signal threshold across all loci. ### Claim 9 (depends on 1) The method of claim 1, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of determining a ratio of the locus with a maximum peak height over all loci to the locus with the minimum peak height over all loci. ### Claim 10 (depends on 1) The method of claim 1, wherein the step of transforming the first set of peak detection data using at least one of the plurality of transformation approaches includes the step of determining a ratio of the locus with a maximum peak area over all loci to the locus with the minimum peak area over all loci. ### Claim 11 (depends on 1) The method of claim 1, wherein the trained machine learning algorithm considers allele-sharing when determining the probability that the DNA sample includes DNA from multiple contributors that are genetically related. ### Claim 12 (depends on 1) The method of claim 1, further comprising the step of determining a probability that there were multiple, genetically related contributors to the DNA sample based upon the probability for each locus in the DNA sample that there were multiple, genetically related contributors. ### Claim 13 A system for determining whether a sample of DNA contains related contributors, comprising: a computer processor programmed to include a first module configured to receive data representing peak detection signals for a predetermined number of loci in a DNA sample from a sequencing device; wherein the processor is further programmed to include a second module configured to establish from the peak detection signals a first set of peak detection data to be transformed and a second set of peak detection data to remain untransformed; wherein the processor is further programmed to include a third module configured to transform the first set of peak detection data using at least one of a plurality of transformation approaches; wherein the processor is further programmed to include a fourth module configured to input the transformed first set of peak detection data and untransformed second set of peak detection data into a trained machine learning algorithm to produce a probability for each locus in the DNA sample that there were multiple, genetically related contributors. ### Claim 14 (depends on 1) The system of claim 1, wherein the plurality of transformation approaches used by third module include performing signal detection by determining an average baseline noise for each locus and then thresholding each locus with the average baseline noise for that locus, trimming the peak detection signals by [i] and any signals indicating slipped strand mispairing or sequencing errors, dividing a peak height for a bi-allelic gender determining marker by a total peak height of a multi-allelic gender specific marker and then by a number of contributors as determined according to a maximum allele count, determining a difference between a peak height for a female specific allele in a bi-allelic gender determining DNA marker and a total peak height for all alleles detected at a multi-allelic gender specific marker. ### Claim 15 (depends on 14) The system of claim 14, wherein transforming the first set of peak detection data using at least one of the plurality of transformation approaches comprises determining a ratio of a minimum trimmed signal and a baseline value. ### Claim 16 (depends on 6) The system of claim 6, wherein transforming the first set of peak detection data using at least one of the plurality of transformation approaches comprises dividing the difference between the peak height for the female specific allele in the bi-allelic gender determining DNA marker and the total peak height for all alleles detected at the multi-allelic gender specific marker by a total peak height for all alleles detected at the multi-allelic gender specific marker. ### Claim 17 (depends on 1) The system of claim 1, wherein the trained machine learning algorithm includes consideration of allele-sharing when determining the probability that the DNA sample includes DNA from multiple contributors that are genetically related. ### Claim 18 (depends on 1) The system of claim 1, wherein the processor is further programmed to include a fifth module configured to determine a probability that there were multiple, genetically related contributors to the DNA sample based upon the probability for each locus in the DNA sample that there were multiple, genetically related contributors.