# US 12,009,066 B2 · Automated transitive read-behind analysis in big data toxicology > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,009,066 B2 - Document ID: US12009066B2 - Status: Granted - Kind: B2 - Application number: 16/419,100 - Filed: 2019-05-22 - Published: 2020-11-26 - Granted: 2024-06-11 - Earliest claimed: 2019-05-22 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Rebecca Morones; Sarah K. Czaplewski-Campbell; Melissa K. Miller; Mary E. Rudden; Craig M. Trim - Web page: https://patentgrep.com/patent/US12009066B2 ## CPC - G16C 20/30: Prediction of properties of chemical compounds, compositions or mixtures - G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications} - G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06N 5/02: Knowledge representation; Symbolic representation - G06N 5/022: Knowledge engineering; Knowledge acquisition - G16C 20/10: Analysis or design of chemical reactions, syntheses or processes - G16C 20/70: Machine learning, data mining or chemometrics - G16C 20/40: Searching chemical structures or physicochemical data - G16C: COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Techniques for probabilistic analysis of chemicals are provided. An indication of a proposed chemical composition is received. A predicted toxicity score is generated for the proposed chemical composition by performing probabilistic analysis on the proposed chemical composition. The probabilistic analysis includes identifying, based on a knowledge graph, at least one similar composition that is structurally similar to the proposed chemical composition. The analysis also includes identifying a set of chemical reactions that include the at least one similar composition, and determining one or more products of the identified set of chemical reactions. The probabilistic analysis further includes determining a toxicity of at least one of the one or more products. Finally, the predicted toxicity score is returned. ## Claims ### Claim 1 A method comprising: receiving a first indication of a first proposed chemical composition; generating a first predicted toxicity score for the first proposed chemical composition by performing, by operation of one or more computer processors, a probabilistic read-across analysis on the first proposed chemical composition, wherein performing the probabilistic read-across analysis comprises: identifying, based on a knowledge graph, at least one similar composition that is structurally similar to the first proposed chemical composition, wherein the knowledge graph comprises: a plurality of nodes, each respective node corresponding to a respective chemical composition, and a plurality of edges indicating learned structural similarity among chemical compositions, wherein at least one of the plurality of edges comprises a strength defined based on regulatory similarity, with respect to at least one regulatory body, between corresponding chemical compositions; identifying a set of chemical reactions that include the at least one similar composition; determining one or more products of the identified set of chemical reactions; and determining a toxicity of at least one of the one or more products; and returning the first predicted toxicity score; receiving a second indication of a second proposed chemical composition, wherein the second proposed chemical composition comprises a modification to the first proposed chemical composition selected based on the first predicted toxicity score; and generating a second predicted toxicity score for the second proposed chemical composition, wherein the second predicted toxicity score provides an understanding regarding potential risks of the second proposed chemical composition and can be used to ensure that the second proposed chemical composition will not be potentially dangerous or toxic. ### Claim 2 (depends on 1) The method of claim 1, the method further comprising: receiving information about a plurality of chemical compositions, the information including environmental and toxicological effects of each of the plurality of chemical compositions; receiving information about a plurality of chemical reactions possible among the plurality of chemical compositions; and generating the knowledge graph reflecting the plurality of chemical compositions and the plurality of chemical reactions. ### Claim 3 (depends on 2) The method of claim 2, the method further comprising generating one or more connections in the knowledge graph based on similarity between each of the plurality of chemical compositions, wherein the similarity includes: (i) a structural similarity; (ii) a toxicological similarity; (iii) an environmental similarity; and (iv) a regulatory similarity. ### Claim 4 (depends on 1) The method of claim 1, wherein performing the probabilistic read-across analysis on the proposed chemical composition comprises recursively traversing the knowledge graph by: identifying a respective plurality of similar compositions that are structurally similar to the proposed chemical composition; identifying, for each respective similar composition of the respective plurality of similar compositions, a respective set of chemical reactions; determining one or more products of each respective chemical reaction in the respective set of chemical reactions; and determining respective toxicities of each of the one or more products. ### Claim 5 (depends on 1) The method of claim 1, the method further comprising: generating a gap measure based on the probabilistic read-across analysis; and upon determining that the gap measure exceeds a predefined threshold, generating an alert indicating that using the proposed chemical composition is uncertain. ### Claim 6 (depends on 1) The method of claim 1, the method further comprising: generating, based on the probabilistic read-across analysis, a predicted likelihood that the proposed chemical composition will be regulated by a relevant government entity. ### Claim 7 (depends on 1) The method of claim 1, the method further comprising: generating a confidence value for the predicted toxicity score, based on the probabilistic read-across analysis; and upon determining that the confidence value is above a predefined threshold, generating an alert indicating that using the proposed chemical composition is dangerous. ### Claim 8 A computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation comprising: receiving an indication of a proposed chemical composition; generating a predicted toxicity score for the proposed chemical composition by performing, by operation of one or more computer processors, a probabilistic read-across analysis on the proposed chemical composition, wherein performing the probabilistic read-across analysis comprises: identifying, based on a knowledge graph, at least one similar composition that is structurally similar to the proposed chemical composition, wherein the knowledge graph comprises: a plurality of nodes, each respective node corresponding to a respective chemical composition, and a plurality of edges indicating learned structural similarity among chemical compositions, wherein at least one of the plurality of edges comprises a strength defined based on regulatory similarity, with respect to at least one regulatory body, between corresponding chemical compositions; identifying a set of chemical reactions that include the at least one similar composition; determining one or more products of the identified set of chemical reactions; and determining a toxicity of at least one of the one or more products; and returning the predicted toxicity score, wherein the predicted toxicity score provides an understanding regarding potential risks of the proposed chemical composition and can be used to ensure that the proposed chemical composition will not be potentially dangerous or toxic. ### Claim 9 (depends on 8) The computer-readable storage medium of claim 8, the operation further comprising: receiving information about a plurality of chemical compositions, the information including environmental and toxicological effects of each of the plurality of chemical compositions; receiving information about a plurality of chemical reactions possible among the plurality of chemical compositions; and generating the knowledge graph reflecting the plurality of chemical compositions and the plurality of chemical reactions. ### Claim 10 (depends on 9) The computer-readable storage medium of claim 9, the operation further comprising generating one or more connections in the knowledge graph based on similarity between each of the plurality of chemical compositions, wherein the similarity includes: (i) a structural similarity; (ii) a toxicological similarity; (iii) an environmental similarity; and (iv) a regulatory similarity. ### Claim 11 (depends on 8) The computer-readable storage medium of claim 8, wherein performing the probabilistic read-across analysis on the proposed chemical composition comprises recursively traversing the knowledge graph by: identifying a respective plurality of similar compositions that are structurally similar to the proposed chemical composition; identifying, for each respective similar composition of the respective plurality of similar compositions, a respective set of chemical reactions; determining one or more products of each respective chemical reaction in the respective set of chemical reactions; and determining respective toxicities of each of the one or more products. ### Claim 12 (depends on 8) The computer-readable storage medium of claim 8, the operation further comprising: generating a gap measure based on the probabilistic read-across analysis; and upon determining that the gap measure exceeds a predefined threshold, generating an alert indicating that using the proposed chemical composition is uncertain. ### Claim 13 (depends on 8) The computer-readable storage medium of claim 8, the operation further comprising: generating, based on the probabilistic read-across analysis, a predicted likelihood that the proposed chemical composition will be regulated by a relevant government entity. ### Claim 14 (depends on 8) The computer-readable storage medium of claim 8, the operation further comprising: generating a confidence value for the predicted toxicity score, based on the probabilistic read-across analysis; and upon determining that the confidence value is above a predefined threshold, generating an alert indicating that using the proposed chemical composition is dangerous. ### Claim 15 A system comprising: one or more computer processors; and a memory containing a program which when executed by the one or more computer processors performs an operation, the operation comprising: receiving an indication of a proposed chemical composition; generating a predicted toxicity score for the proposed chemical composition by performing a probabilistic read-across analysis on the proposed chemical composition, wherein performing the probabilistic read-across analysis comprises: identifying, based on a knowledge graph, at least one similar composition that is structurally similar to the proposed chemical composition, wherein the knowledge graph comprises: a plurality of nodes, each respective node corresponding to a respective chemical composition, and a plurality of edges indicating learned structural similarity among chemical compositions, wherein at least one of the plurality of edges comprises a strength defined based on regulatory similarity, with respect to at least one regulatory body, between corresponding chemical compositions; identifying a set of chemical reactions that include the at least one similar composition; determining one or more products of the identified set of chemical reactions; and determining a toxicity of at least one of the one or more products; and returning the predicted toxicity score, wherein the predicted toxicity score provides an understanding regarding potential risks of the proposed chemical composition and can be used to ensure that the proposed chemical composition will not be potentially dangerous or toxic. ### Claim 16 (depends on 15) The system of claim 15, the operation further comprising: receiving information about a plurality of chemical compositions, the information including environmental and toxicological effects of each of the plurality of chemical compositions; receiving information about a plurality of chemical reactions possible among the plurality of chemical compositions; generating the knowledge graph reflecting the plurality of chemical compositions and the plurality of chemical reactions; and generating one or more connections in the knowledge graph based on similarity between each of the plurality of chemical compositions, wherein the similarity includes: (i) a structural similarity; (ii) a toxicological similarity; (iii) an environmental similarity; and (iv) a regulatory similarity. ### Claim 17 (depends on 15) The system of claim 15, wherein performing the probabilistic read-across analysis on the proposed chemical composition comprises recursively traversing the knowledge graph by: identifying a respective plurality of similar compositions that are structurally similar to the proposed chemical composition; identifying, for each respective similar composition of the respective plurality of similar compositions, a respective set of chemical reactions; determining one or more products of each respective chemical reaction in the respective set of chemical reactions; and determining respective toxicities of each of the one or more products. ### Claim 18 (depends on 15) The system of claim 15, the operation further comprising: generating a gap measure based on the probabilistic read-across analysis; and upon determining that the gap measure exceeds a predefined threshold, generating an alert indicating that using the proposed chemical composition is uncertain. ### Claim 19 (depends on 15) The system of claim 15, the operation further comprising: generating, based on the probabilistic read-across analysis, a predicted likelihood that the proposed chemical composition will be regulated by a relevant government entity. ### Claim 20 (depends on 15) The system of claim 15, the operation further comprising: generating a confidence value for the predicted toxicity score, based on the probabilistic read-across analysis; and upon determining that the confidence value is above a predefined threshold, generating an alert indicating that using the proposed chemical composition is dangerous.