# US 12,006,541 B2 · Methods and apparatuses for generating peptides by synthesizing a portion of a design space to identify peptides having non-canonical amino acids > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,006,541 B2 - Document ID: US12006541B2 - Status: Granted - Kind: B2 - Application number: 18/059,182 - Filed: 2022-11-28 - Published: 2023-05-25 - Granted: 2024-06-11 - Earliest claimed: 2021-05-07 - Assignees: Peptilogics, Inc. - Applicants: Peptilogics, Inc.c - Inventors: Francis Lee; Jonathan D. Steckbeck; Hannes Holste - Web page: https://patentgrep.com/patent/US12006541B2 ## CPC - C12Q 1/6869: Methods for sequencing - G16H 10/40: for data related to laboratory analysis, e.g. patient specimen analysis - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06F 18/23213: with fixed number of clusters, e.g. K-means clustering - G06N 3/0455: Auto-encoder networks; Encoder-decoder networks - G06N 3/047: Probabilistic or stochastic networks - G06N 3/0475: Generative networks - G06N 3/088: Non-supervised learning, e.g. competitive learning - G06N 20/20: Ensemble learning - G16B 30/00: ICT specially adapted for sequence analysis involving nucleotides or amino acids - G16B 35/10: Design of libraries - 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 - 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 - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - 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 In one aspect, a computer-implemented automated flow synthesis platform configured to use an artificial intelligence (AI) engine is disclosed and includes a reaction chamber configured to synthesize a sequence, detectors configured to monitor the synthesis of the sequence in the reaction chamber, wherein the synthesis uses an automated flow process, and a computing device communicatively coupled to the detectors. The computing device receives measurements from the one or more detectors, wherein the measurements comprise a spectral profile at each coupling of each amino acid in the sequence, trains, using training data comprising the measurements, machine learning models to determine a synthesizing recipe that enables the sequence to be synthesized, wherein the synthesizing recipe comprises parameters used during the automated flow process to synthesize the sequence, and controls, using the synthesizing recipe, the synthesis of the sequence in the reaction chamber. ## Claims ### Claim 1 A computer-implemented automated flow synthesis platform configured to use an artificial intelligence (AI) engine and comprising: a reaction chamber configured to synthesize a sequence; one or more detectors configured to monitor the synthesis of the sequence in the reaction chamber, wherein the synthesis uses an automated flow process; and a computing device communicatively coupled to the one or more detectors, wherein the computing device is configured to: receive one or more measurements from the one or more detectors, wherein the one or more measurements comprise a spectral profile at each coupling of each amino acid in the sequence; determine, using one or more trained machine learning models, a synthesizing recipe that enables the sequence to be synthesized, wherein the synthesizing recipe comprises one or more parameters used to control at least the reaction chamber during the automated flow process to synthesize the sequence; and control, using the synthesizing recipe, the synthesis of the sequence in the reaction chamber. ### Claim 2 (depends on 1) The computer-implemented automated flow synthesis platform of claim 1, wherein the sequence comprises an amino acid. ### Claim 3 (depends on 2) The computer-implemented automated flow synthesis platform of claim 2, wherein the amino acid is a non-canonical amino acid. ### Claim 4 (depends on 1) The computer-implemented automated flow synthesis platform of claim 1, further comprising training, using training data comprising the one or more measurements, the one or more trained machine learning models. ### Claim 5 (depends on 1) The computer-implemented automated flow synthesis platform of claim 1, wherein the training data comprises one or more inputs associated with one or more outputs, wherein the one or more inputs comprise an amide coupling, a spectral profile for a chemical reaction associated with the amide coupling, a fidelity of the amide coupling, or some combination thereof. ### Claim 6 (depends on 5) The computer-implemented automated flow synthesis platform of claim 5, wherein the fidelity of the coupling comprises one of a first indication that an expected chemical reaction occurred at the coupling or a second indication that an unexpected chemical reaction occurred at the coupling. ### Claim 7 (depends on 1) The computer-implemented automated flow synthesis platform of claim 1, wherein the one or more machine learning models comprise: a first layer comprising at least a first machine learning model, wherein: the first machine learning model receives, as first input, an amide coupling of the sequence, a fidelity of the amide coupling, and the spectral profile, and the first machine learning model generates, as an output, at least a first subset of the one or more parameters used during the automated flow process to synthesize the sequence. ### Claim 8 (depends on 7) The computer-implemented automated flow synthesis platform of claim 7, wherein the one or more machine learning models comprise: a second layer comprising at least a second machine learning model, wherein: the second machine learning model receives, as input, the output of the first machine learning model, and a plurality of amide couplings, the second machine learning model generates, as a second output, at least a second subset of the one or more parameters used during the automated flow process to synthesize the sequence, and the synthesizing recipe comprises the first subset and the second subset of the one or more parameters. ### Claim 9 (depends on 8) The computer-implemented automated flow synthesis platform of claim 8, wherein the sequence is a peptide chain sequence comprising the amide coupling and the plurality of amide couplings. ### Claim 10 (depends on 1) The computer-implemented automated flow synthesis platform of claim 1, wherein the synthesizing recipe of parameters comprises one or more temperatures, solvents, protection groups, resin anchors, pressure, linkers, reagents, catalysts, or some combination thereof. ### Claim 11 (depends on 1) The computer-implemented automated flow synthesis platform of claim 1, further comprising: generating, using the one or more machine learning models, the sequence based on a desired drug activity level in a therapeutic domain. ### Claim 12 (depends on 1) The computer-implemented automated flow synthesis platform of claim 1, wherein the spectral profile comprises ultraviolet light, infrared light, ultraviolet rays, infrared radiation, thermal radiation, thermal light, fluorescent light, visible light, vibrational waves, or some combination thereof. ### Claim 13 A method wherein an artificial intelligence (AI) enabled automated flow synthesis platform, the method comprising: receiving one or more measurements from one or more detectors, wherein the one or more measurements comprise a spectral profile at each coupling of each amino acid in the sequence, and the one or more detectors are monitoring a synthesis of the sequence in a reaction chamber; determining, using one or more trained machine learning models, a synthesizing recipe that enables the sequence to be synthesized, wherein the synthesizing recipe comprises one or more parameters used to control at least the reaction chamber during an automated flow process to synthesize the sequence; and controlling, using the synthesizing recipe, the synthesis of the sequence in the reaction chamber. ### Claim 14 (depends on 13) The method of claim 13, wherein the sequence comprises an amino acid and the amino acid is a non-canonical amino acid. ### Claim 15 (depends on 13) The method of claim 13, wherein the one or more machine learning models comprise: a first layer comprising at least a first machine learning model, wherein: the first machine learning model receives, as first input, an amide coupling of the sequence, a fidelity of the amide coupling, and the spectral profile, and the first machine learning model generates, as an output, at least a first subset of the one or more parameters used during the automated flow process to synthesize the sequence. ### Claim 16 (depends on 15) The method of claim 15, wherein the one or more machine learning models comprise: a second layer comprising at least a second machine learning model, wherein: the second machine learning model receives, as input, the output of the first machine learning model, and a plurality of amide couplings, the second machine learning model generates, as a second output, at least a second subset of the one or more parameters used during the automated flow process to synthesize the sequence, and the synthesizing recipe comprises the first subset and the second subset of the one or more parameters. ### Claim 17 A system for an automated flow synthesis platform configured to use an artificial intelligence (AI) engine and comprising: a reaction chamber configured to synthesize a sequence; one or more detectors configured to monitor the synthesis of the sequence in the reaction chamber, wherein the synthesis uses an automated flow process; and a computing device communicatively coupled to the one or more detectors, wherein the computing device is configured to: receive one or more measurements from the one or more detectors, wherein the one or more measurements comprise a spectral profile at each coupling of each amino acid in the sequence; determine, using one or more trained machine learning models, a synthesizing recipe that enables the sequence to be synthesized, wherein the synthesizing recipe comprises one or more parameters used to control at least the reaction chamber during the automated flow process to synthesize the sequence; and control, using the synthesizing recipe, the synthesis of the sequence in the reaction chamber. ### Claim 18 (depends on 17) The system of claim 17, wherein the training data comprises one or more inputs associated with one or more outputs, wherein the one or more inputs comprise an amide coupling, a spectral profile for a chemical reaction associated with the amide coupling, a fidelity of the amide coupling, or some combination thereof. ### Claim 19 (depends on 18) The system of claim 18, wherein the fidelity of the coupling comprises one of a first indication that an expected chemical reaction occurred at the coupling or a second indication that an unexpected chemical reaction occurred at the coupling. ### Claim 20 (depends on 17) The system of claim 17, wherein the one or more machine learning models comprise: a first layer comprising at least a first machine learning model, wherein: the first machine learning model receives, as first input, an amide coupling of the sequence, a fidelity of the amide coupling, and the spectral profile, and the first machine learning model generates, as an output, at least a first subset of the one or more parameters used during the automated flow process to synthesize the sequence.