# US 2021/0340599 A1 · Predicting antibiotic resistance and complementary antibiotic combinations > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0340599 A1 - Document ID: US20210340599A1 - Status: Published application - Kind: A1 - Application number: 16/865,743 - Filed: 2020-05-04 - Published: 2021-11-04 - Earliest claimed: 2020-05-04 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: James Kaufman; Ed Seabolt; Kristen Beck; Mary Ann Roth; Akshay Agarwal; Gowri Nayar - Web page: https://patentgrep.com/patent/US20210340599A1 ## 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 - G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof - G16B 5/00: ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks - G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations - G16B 50/30: Data warehousing; Computing architectures - Y02A 90/10: Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation - G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA - Y02A: TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE ## Abstract Techniques are provided for predicting antibiotic resistance from functional omics data and recommending complementary combinations of antibiotics. According to an embodiment, computer implemented method can comprise identifying, by a system operatively coupled to at least one processor, one or more proteins that have one or more functional domains associated with at least one code selected from a coding system for a set of phenotypes, and modelling, by the system, the one or more proteins as a functional capacity vector. In some implementations, the method can further include selecting the coding system and/or the at least one code based on a phenotype of interest. The method can further comprise employing, by the system, the functional capacity vector to identify one or more antibiotic compounds to which an organism within the set of phenotypes is resistant or susceptible, and/or to predict complementary antibiotic combinations. ## Claims ### Claim 1 A method, comprising: identifying, by a system operatively coupled to at least one processor, one or more proteins that have one or more functional domains associated with at least one code selected from a coding system for a set of phenotypes; and modelling, by the system, the one or more proteins as a functional capacity vector. ### Claim 2 (depends on 1) The method of claim 1, further comprising: selecting, by the system, the coding system based on a phenotype of interest. ### Claim 3 (depends on 1) The method of claim 1, further comprising: applying, by the system, one or more restrictions for the coding system restrictions in association with the selecting. ### Claim 4 (depends on 1) The method of claim 1, further comprising: selecting, by the system, the at least one code based on a phenotype of interest. ### Claim 5 (depends on 1) The method of claim 1, further comprising: employing, by the system, the functional capacity vector to identify one or more antibiotic compounds to which an organism within the set of phenotypes is resistant. ### Claim 6 (depends on 1) The method of claim 1, further comprising: employing, by the system, the functional capacity vector to identify one or more antibiotic compounds to which an organism within the set of phenotypes is susceptible. ### Claim 7 (depends on 1) The method of claim 1, further comprising: employing, by the system, the functional capacity vector to identify one or more antibiotic compound combinations to which an organism within the set of phenotypes is susceptible. ### Claim 8 (depends on 1) The method of claim 1, further comprising: employing, by the system, the functional capacity vector to predict one or more minimum inhibitory concentrations for one or more antibiotic compounds against an organism within the set of phenotypes. ### Claim 9 (depends on 1) The method of claim 1, further comprising: employing, by the system, the functional capacity vector to predict one or more minimum inhibitory concentrations for one or more antibiotic compound combinations against an organism within the set of phenotypes. ### Claim 10 A system, comprising: a memory that stores computer executable components; a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise: a protein identification component that identifies one or more proteins that have one or more functional domains associated with at least one code selected from a coding system for a set of phenotypes; and a vectorization component that models the one or more proteins as a functional capacity vector. ### Claim 11 (depends on 10) The system of claim 10, wherein the computer executable components further comprise: a coding system selection component that that selects the coding system based on a phenotype of interest. ### Claim 12 (depends on 10) The system of claim 10, wherein the computer executable components further comprise: a code selection component that that selects the at least one code based on a phenotype of interest. ### Claim 13 (depends on 10) The system of claim 10, wherein the computer executable components further comprise: a susceptibility forecasting component that employs the functional capacity vector to identify one or more antibiotic compounds to which an organism within the set of phenotypes is resistant. ### Claim 14 (depends on 10) The system of claim 10, wherein the computer executable components further comprise: a susceptibility forecasting component that employs the functional capacity vector to identify one or more antibiotic compounds to which an organism within the set of phenotypes is susceptible. ### Claim 15 (depends on 10) The system of claim 10, wherein the computer executable components further comprise: a susceptibility forecasting component that employs pairwise distances between functional capacity vectors to perform hierarchical or clustering or k-mean clustering to identify one or more antibiotic compounds to which an organism within the set of phenotypes is susceptible. ### Claim 16 (depends on 10) The system of claim 10, wherein the computer executable components further comprise: a susceptibility forecasting component that employs the functional capacity vector to predict one or more minimum inhibitory concentrations for one or more antibiotic compounds against an organism included within the set of phenotypes. ### Claim 17 (depends on 10) The system of claim 10, wherein the computer executable components further comprise: a combination forecasting component that employs the functional capacity vector to identify one or more antibiotic compound combinations to which an organism within the set of phenotypes is susceptible. ### Claim 18 A computer program product for representing a genome with a dimensionally reduced coding vector that represents one or more target functions associated with the genome within a target phenotypic space the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing component to cause the processing component to: identify one or more target genes of the genome that encode one or more proteins responsible for the one or more target functions; and generate a functional capacity vector for the genome using one or more distinct codes assigned to the one or more target functions. ### Claim 19 (depends on 18) The computer program product of claim 18, wherein the program instructions further cause the processing component to: select at least one coding system for a set of phenotypes included in the target phenotypic space, wherein the at least one coding system identifies different functions observed for the set of phenotypes and assigns distinct codes to the different functions; and determine the one or more distinct codes using the at least one coding system. ### Claim 20 (depends on 18) The computer program product of claim 18, wherein the program instructions further cause the processing component to: determine one or more functional domains respectively associated with the one or more distinct codes; identify the one or more proteins based on the one or more proteins comprising the one or more functional domains; generate the functional capacity vector based on the one or more proteins; and employ the functional capacity vector to identify one or more antibiotic compounds to which an organism included within target phenotypic space is susceptible. ### Claim 21 A method comprising: generating, by a system comprising a processor, a reference data structure that identifies different genomes, antimicrobial resistance statuses of the different genomes to different antibiotic compounds, and functional capacity vectors for the different genomes, wherein the functional capacity vectors represent sets of phenotypic features expressed by the different genomes in association with exposure to the different antibiotic compounds; generating, by the system, a target functional capacity vector for a target genome excluded from the reference data structure; and employing, by the system, the reference data structure and the target functional capacity vector to determine one or more of the antibiotic compounds to which the target genome is susceptible. ### Claim 22 (depends on 21) The method of claim 21, wherein the employing comprises employing one or more machine learning algorithms to facilitate identifying the one or more antibiotic compounds based on degrees of similarity between the target functional capacity vector and the functional capacity vectors. ### Claim 23 (depends on 20) The method of claim 20, wherein the antimicrobial statuses of the different genomes comprise minimum inhibitory concentration values, and wherein the method further comprises employing, by the system, the reference data structure and the target functional capacity vector to predict one or more minimum inhibitory concentration values for one or more of the antibiotic compounds against the target genome. ### Claim 24 A system, comprising: a memory that stores computer executable components; a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise: a reference data generation component that generates a reference data structure identifying different genomes, antimicrobial resistance statuses of the different genomes to different antibiotic compounds, and functional capacity vectors for the different genomes, wherein the functional capacity vectors represent sets of phenotypic features expressed by the different genomes in association with exposure to the different antibiotic compounds; a vectorization component that generates a target functional capacity vector for a target genome excluded from the reference data structure; and a susceptibility forecasting component that employs the reference data structure and the target functional capacity vector to determine one or more of the antibiotic compounds to which the target genome is susceptible. ### Claim 25 (depends on 24) The system of claim 24, wherein the susceptibility forecasting component employs one or more machine learning algorithms to facilitate determining the one or more antibiotic compounds based on degrees of similarity between the target functional capacity vector and the functional capacity vectors.