# US 11,908,670 B2 · Systems and methods of ion population regulation in mass spectrometry > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,908,670 B2 - Document ID: US11908670B2 - Status: Granted - Kind: B2 - Application number: 17/745,780 - Filed: 2022-05-16 - Published: 2023-11-16 - Granted: 2024-02-20 - Earliest claimed: 2022-05-16 - Assignees: Thermo Finnigan LLC - Applicants: Thermo Finnigan LLC - Inventors: Philip M. Remes; Jesse D. Canterbury - Web page: https://patentgrep.com/patent/US11908670B2 ## CPC - G01N 30/8651: {Recording, data aquisition, archiving and storage} - H01J 49/0036: {Step by step routines describing the handling of the data generated during a measurement} - G01N 30/7233: {interfaced to liquid or supercritical fluid chromatograph (interfaces in general for introducing or extracting samples to be analysed with specially adapted mass spectrometer, see H01J49/04)} - G01N 30/8675: {Evaluation, i.e. decoding of the signal into analytical information (for analysis of specific compounds see also G01N30/88 and subgroups of G01N33/00; chemical libraries per se C40B)} - G01N 30/8693: {Models, e.g. prediction of retention times, method development and validation} - G06N 3/08: Learning methods - H01J 49/0031: {Step by step routines describing the use of the apparatus (H01J49/0081 takes precedence)} - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - H01J: ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS (spark-gaps H01T; electric arc lamps H05B31/00; particle accelerators H05H) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method of performing mass spectrometry includes accessing a series of mass spectra of detected ions derived from components eluting from a chromatography column; obtaining, based on the series of mass spectra, an elution profile including a plurality of detection points representing intensity of at least a set of the detected ions as a function of time; and determining, based on a set of detection points included in the plurality of detection points, a predicted next detection point of the elution profile to be obtained based on a next mass spectrum to be acquired subsequent to acquisition of the series of mass spectra. ## Claims ### Claim 1 A method of performing mass spectrometry, comprising: obtaining, based on a series of mass spectra of detected ions derived from components eluting from a chromatography column, an elution profile comprising a plurality of detection points representing intensity of the detected ions as a function of time; and determining, based on a set of detection points included in the plurality of detection points, a predicted next detection point of the elution profile to be obtained based on a next mass spectrum to be acquired. ### Claim 2 (depends on 1) The method of claim 1, wherein determining the predicted next detection point comprises applying the set of detection points to a trained machine learning model configured to determine the predicted next detection point based on the set of detection points. ### Claim 3 (depends on 2) The method of claim 2, wherein the trained machine learning model comprises a Recurrent Neural Network (RNN). ### Claim 4 (depends on 2) The method of claim 2, wherein the trained machine learning model comprises a Long Short-Term Memory (LSTM) neural network or a Gated Recurrent Unit (GRU) neural network. ### Claim 5 (depends on 1) The method of claim 1, further comprising: acquiring, subsequent to acquisition of the series of mass spectra, the next mass spectrum; obtaining, based on the next mass spectrum, an acquired next detection point; determining, based on a comparison of the predicted next detection point and the acquired next detection point, that the predicted next detection point satisfies an error condition; and training, based on the determining that the predicted next detection point satisfies the error condition, the machine learning model based on the plurality of detection points of the elution profile and the acquired next detection point. ### Claim 6 (depends on 1) The method of claim 1, further comprising selecting, based on a set of experiment conditions for analyzing a sample comprising the components eluting from the chromatography column, the trained machine learning model from among a plurality of machine learning models each trained for a particular set of experiment conditions. ### Claim 7 (depends on 6) The method of claim 6, wherein the set of experiment conditions comprises at least one of a flow rate of the chromatography column, a gradient of the chromatography column, a list of target analytes included in the sample, a type of chromatography performed, or a type of stationary phase and/or mobile phase of the chromatography column. ### Claim 8 (depends on 1) The method of claim 1, wherein the trained machine learning model was trained based on mass spectra acquired from a plurality of experiments each performed with a different set of experiment conditions. ### Claim 9 (depends on 1) The method of claim 1, further comprising setting, based on the predicted next detection point and for an acquisition of the next mass spectrum, an accumulation time for accumulating the ions produced from the components eluting from the chromatography column. ### Claim 10 (depends on 9) The method of claim 9, wherein setting the accumulation time comprises: estimating, based on the predicted next detection point, an ion flux of the ions produced from the components eluting from the chromatography column during the acquisition of the next mass spectrum; and determining the accumulation time as a target population of ions divided by the estimated ion flux during the acquisition of the next mass spectrum. ### Claim 11 (depends on 1) The method of claim 1, wherein the elution profile comprises an extracted ion chromatogram for a selected m/z. ### Claim 12 (depends on 11) The method of claim 11, further comprising: detecting, based on the series of mass spectra, precursor ions having the selected m/z; performing, based on the detecting of the ions having the selected m/z, the determining of the predicted next detection point; and performing, based on the predicted next detection point, a data-dependent acquisition of product ions produced from the precursor ions. ### Claim 13 An apparatus for performing mass spectrometry, comprising: a mass analyzer configured to acquire, over time, a series of mass spectra of detected ions derived from components eluting from a chromatography column; and a computing device configured to: obtain, based on the series of mass spectra, an elution profile comprising a plurality of detection points representing intensity of the detected ions as a function of time; and determine, based on a set of detection points included in the plurality of detection points, a predicted next detection point of the elution profile to be obtained based on a next mass spectrum to be acquired by the mass analyzer subsequent to acquisition of the series of mass spectra. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein the computing device is configured to determine the predicted next detection point by applying the set of detection points to a trained machine learning model configured to determine the predicted next detection point based on the set of detection points. ### Claim 15 (depends on 14) The apparatus of claim 14, wherein the trained machine learning model comprises a Recurrent Neural Network (RNN). ### Claim 16 (depends on 14) The apparatus of claim 14, wherein the trained machine learning model comprises a Long Short-Term Memory (LSTM) neural network or a Gated Recurrent Unit (GRU) neural network. ### Claim 17 (depends on 13) The apparatus of claim 13, wherein: the mass analyzer is further configured to acquire, subsequent to acquisition of the series of mass spectra, the next mass spectrum; and the computing device is further configured to: obtain, based on the next mass spectrum, an acquired next detection point; determine, based on a comparison of the predicted next detection point and the acquired next detection point, that the predicted next detection point satisfies an error condition; and train, based on the determining that the predicted next detection point satisfies the error condition, the machine learning model based on the plurality of detection points of the elution profile and the acquired next detection point. ### Claim 18 (depends on 13) The apparatus of claim 13, wherein the computing device is further configured to select, based on a set of experiment conditions for analyzing a sample comprising the components eluting from the chromatography column, the trained machine learning model from among a plurality of machine learning models each trained for a particular set of experiment conditions. ### Claim 19 (depends on 18) The apparatus of claim 18, wherein the set of experiment conditions comprises at least one of a flow rate of the chromatography column, a gradient of the chromatography column, a list of target analytes included in the sample, a type of chromatography performed, or a type of stationary phase and/or mobile phase of the chromatography column. ### Claim 20 (depends on 13) The apparatus of claim 13, wherein the trained machine learning model was trained based on mass spectra acquired from a plurality of experiments each performed with a different set of experiment conditions. ### Claim 21 (depends on 13) The apparatus of claim 13, wherein the computing device is further configured to set, based on the predicted next detection point and for an acquisition of the next mass spectrum, an accumulation time for accumulating the ions produced from the components eluting from the chromatography column. ### Claim 22 (depends on 21) The apparatus of claim 21, wherein setting the accumulation time for the acquisition of the next mass spectrum comprises: estimating, based on the predicted next detection point, an ion flux of the ions produced from the components eluting from the chromatography column during the acquisition of the next mass spectrum; and determining the accumulation time as a target population of ions divided by the estimated ion flux during the acquisition of the next mass spectrum. ### Claim 23 (depends on 13) The apparatus of claim 13, wherein the elution profile comprises an extracted ion chromatogram for a selected m/z. ### Claim 24 (depends on 23) The apparatus of claim 23, wherein the computing device is further configured to: detect, based on the series of mass spectra, precursor ions having the selected m/z; perform, based on the detecting of the ions having the selected m/z, the determining the predicted next detection point; and perform, based on the predicted next detection point, a data-dependent acquisition of product ions produced from the precursor ions.