# US 11,443,181 B2 · Apparatus and method for characterization of synthetic organisms > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,181 B2 - Document ID: US11443181B2 - Status: Granted - Kind: B2 - Application number: 16/010,637 - Filed: 2018-06-18 - Published: 2019-12-19 - Granted: 2022-09-13 - Earliest claimed: 2018-06-18 - Assignees: Peraton Inc. - Applicants: Northrop Grumman Systems Corporation - Inventors: David A. Selck; Om Prakash, II; H. Morgan Crafts, Jr.; Sam S. Shekar - Web page: https://patentgrep.com/patent/US11443181B2 ## CPC - G06N 3/08: Learning methods - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/09: Supervised learning - 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 - G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY ## Abstract A system for classifying an origin of genomic sequence data may include a training database comprising sample data including first samples corresponding to sequences of natural origin and second samples corresponding to sequences of synthetic origin, and a classifier comprising a genomic classification module. The genomic classification module may be trained via machine learning on the first and second samples. The genomic classification module may be configured to receive genomic sequence data of any read length and determine a classification output indicating whether the genomic sequence data has a natural origin or synthetic origin. ## Claims ### Claim 1 A system for classifying an origin of genomic sequence data, the system comprising: a training database comprising sample data including first samples corresponding to sequences of natural origin and second samples corresponding to sequences of synthetic origin; and a classifier comprising a genomic classification module, the genomic classification module trained via machine learning on the first and second samples, wherein the genomic classification module is configured to receive genomic sequence data of any read length and determine a classification output indicating whether the genomic sequence data has a natural origin or synthetic origin. ### Claim 2 (depends on 1) The system of claim 1, wherein the genomic classification module comprises a first neural network and a second neural network, the first and second neural networks each being optimized for operation over respective different read length ranges. ### Claim 3 (depends on 2) The system of claim 2, wherein the first neural network comprises a convolutional neural network and the second neural network comprises a recurrent neural network. ### Claim 4 (depends on 2) The system of claim 2, wherein an output of the first neural network is provided as an input to the second neural network. ### Claim 5 (depends on 4) The system of claim 4, wherein a combined output from the first and second neural networks is provided to a decision engine, and wherein the decision engine provides the classification output based on the combined output. ### Claim 6 (depends on 1) The system of claim 1, wherein the classifier is further comprises a second genomic classification module and a second training database, and wherein the second genomic classification module is configured, via the second training database, to determine an attribute of the genomic sequence data. ### Claim 7 (depends on 1) The system of claim 1, wherein the classifier is further comprises a second genomic classification module and a second training database, and wherein the second genomic classification module is configured, via the second training database, to determine a function associated with the genomic sequence data. ### Claim 8 (depends on 1) The system of claim 1, wherein the classifier is further comprises a second genomic classification module and a second training database, and wherein the second genomic classification module is configured, via the second training database, to determine an author of the genomic sequence data. ### Claim 9 (depends on 1) The system of claim 1, wherein the classifier is further comprises a second genomic classification module and a second training database, and wherein the second genomic classification module is configured, via the second training database, to determine harmfulness of the genomic sequence data. ### Claim 10 (depends on 1) The system of claim 1, wherein genomic classification module determines a function or functions to define a pathway between features of the first and second samples and a respective determination that the sequences are of natural origin or synthetic origin, and wherein the genomic classification module applies the function or functions to the genomic sequence data to determine whether the genomic sequence data is of natural origin or synthetic origin. ### Claim 11 (depends on 1) The system of claim 1, wherein the genomic classification module is further configured to define a confidence level associated with the classification output. ### Claim 12 A method of determining an origin of genomic sequence data, the method comprising: training a genomic classification module of a classifier via machine learning on first samples corresponding to sequences of natural origin and second samples corresponding to sequences of synthetic origin; receiving raw or processed genomic sequence data of any read length at the classifier; and determining a classification output indicating whether the raw or processed genomic sequence data has a natural origin or synthetic origin via the genomic classification module. ### Claim 13 (depends on 12) The method of claim 12, wherein training the genomic classification module comprises training a first neural network and a second neural network, the first and second neural networks each being optimized for operation over respective different read length ranges. ### Claim 14 (depends on 13) The method of claim 13, wherein determining the classification comprises providing an output of the first neural network, which comprises a convolutional neural network, as an input to the second neural network, which comprises a recurrent neural network. ### Claim 15 (depends on 14) The method of claim 14, further comprising combining an output from the first and second neural networks to determine the classification output. ### Claim 16 (depends on 12) The method of claim 12, further comprising training a second genomic classification module and a second training database, and utilizing the second genomic classification module to determine an attribute of the genomic sequence data. ### Claim 17 (depends on 12) The method of claim 12, further comprising training a second genomic classification module and a second training database, and utilizing the second genomic classification module to determine a function associated with the genomic sequence data. ### Claim 18 (depends on 12) The method of claim 12, further comprising training a second genomic classification module and a second training database, and utilizing the second genomic classification module to determine an author of the genomic sequence data. ### Claim 19 (depends on 12) The method of claim 12, further comprising training a second genomic classification module and a second training database, and utilizing the second genomic classification module to determine harmfulness of the genomic sequence data. ### Claim 20 (depends on 12) The method of claim 12, further comprising defining a confidence level associated with the classification output.