Method using reinforcement learning to control mass spectrometer

Abstract

To provide a system that facilitates neural network control of mass spectrometry processes.SOLUTION: A system can comprise a memory that stores computer executable components and a processor that executes the computer executable components. The computer executable components can comprise an acquisition component that acquires data for a compound, the data defining a first mass spectrometry spectrum for the compound, an evaluation component that, on the basis of the data, and by employing a neural network that is trained on an input dataset comprising an acquisition metric and employing an associated score that is associated with the acquisition metric, generates a recommendation to perform a mass spectrometry action for the compound, and an execution component that, on the basis of the recommendation, directs execution of the mass spectrometry action at a mass spectrometer and obtains a mass spectrum result.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to neural network control of mass spectrometry processes. [Background technology]

[0002] Scientific instruments for use in materials analysis can help determine the composition and properties of unknown compositions. In one or more examples, scientific instruments that provide analysis by mass spectrometry (MS) or analyze test results of an MS device can help identify unknown compositions by providing or aiding in the understanding of one or more spectra to compare mass calculations based on detection of molecular mass-to-charge ratios after ionization. Summary of the Invention

[0003] The following presents a summary to provide a basic understanding of one or more embodiments described herein. This summary is not intended to identify key or critical elements and / or to delineate the scope of particular embodiments or claims. Its sole purpose is to present concepts in a simplified form as a prelude to the more detailed description that is presented later. In one or more embodiments, the systems, computer-implemented methods, apparatus, and / or computer programs described herein may provide a process for training a neural network and controlling a mass spectrometry-based experiment using reinforcement learning-based training.

[0004] According to one embodiment, a system may include a memory that stores computer-executable components and a processor that executes the computer-executable components stored in the memory, the computer-executable components including an acquisition component that acquires data for a compound, the data defining a first mass spectrometry spectrum of the compound, an evaluation component that uses a neural network trained on an input data set including acquisition metrics based on the data and an association score associated with the acquisition metrics to generate a recommendation for performing a mass spectrometry operation for the compound, and an execution component that directs the performance of a mass spectrometry operation in a mass spectrometer based on the recommendation to obtain a mass spectrum result.

[0005] According to another embodiment, a computer-implemented method may include: comparing, by a system operatively coupled to a processor, first data for the compound to an input dataset including one or more capture metrics of the compound and one or more association scores associated with the one or more capture metrics; using a neural network trained on the input dataset on the obtained metrics of interest associated with the compound based on the comparison; and generating, by the system, a first recommendation for performing a recommended mass spectrometry operation for the compound, where the recommended mass spectrometry operation includes use of a mass spectrometry device to obtain capture of the compound.

[0006] According to yet another embodiment, there is provided a computer program that facilitates a process for reinforcement learning based mass spectrometry control, the computer program including a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by a processor to cause the processor to generate, by the processor, an input dataset including one or more acquisition metrics and one or more associated scores associated with the one or more acquisition metrics and corresponding to a type of compound, the one or more associated scores defining a probability that one or more thresholds corresponding to the one or more acquisition metrics will be met by a mass spectrometry operation for the type of compound, train, by the processor, a neural network on the input dataset, and generate, by the processor, a recommended mass spectrometry operation for obtaining second data for a compound of the type of compound by comparing, using the neural network, first data for the compound to the input dataset associated with the type of compound. [Brief description of the drawings]

[0007] BRIEF DESCRIPTION OF THE DRAWINGS The embodiments will be readily understood from the following detailed description taken in conjunction with the accompanying drawings, in which: For ease of description, like reference numerals refer to like structural elements, and in which the embodiments are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings, in which: [Figure 1] 1 illustrates a block diagram of an example scientific instrument for performing operations according to one or more embodiments described herein. [Diagram 2] 2 illustrates a flow diagram of an example method of performing operations using the scientific instrument of FIG. 1 according to one or more embodiments described herein. [Diagram 3] 1 illustrates a Graphical User Interface (GUI) that may be used in performing one or more of the methods described herein, according to one or more embodiments described herein. [Figure 4]FIG. 1 illustrates a block diagram of an example computing device that may execute one or more methods disclosed herein, in accordance with one or more embodiments described herein. [Diagram 5] FIG. 1 shows a block diagram of an exemplary non-limiting system that can facilitate reinforcement learning-based mass spectrometry control in accordance with one or more embodiments described herein. [Figure 6] FIG. 1 shows a block diagram of another exemplary, non-limiting system that can facilitate reinforcement learning-based mass spectrometry control in accordance with one or more embodiments described herein. [Figure 7] 7 illustrates an exemplary high-level process performed by the materials analysis system of FIG. 6 in accordance with one or more embodiments described herein. [Figure 8] 8 provides an example score matrix illustrating input values ​​used by the materials analysis system of FIG 6 according to one or more embodiments described herein. FIG 8 also provides an example scoring key for defining scores in the example score matrix according to one or more embodiments described herein. [Figure 9] 6 illustrates a set of example reward functions that may be used by the materials analysis system of FIG. 5 in accordance with one or more embodiments described herein. [Figure 10] 7 shows a flow diagram of one or more processes that may be performed by the materials analysis system of FIG. 6 according to one or more embodiments described herein. [Figure 11] 10 of one or more processes that may be performed by the materials analysis system of FIG. 6 in accordance with one or more embodiments described herein. [Figure 12] 7 shows a flow diagram of one or more processes that may be performed by the materials analysis system of FIG. 6 according to one or more embodiments described herein. [Figure 13] 13 illustrates a continuation of the flow diagram of FIG. 12 of one or more processes that may be performed by the materials analysis system of FIG. 6 in accordance with one or more embodiments described herein. [Figure 14]7 shows a flow diagram of one or more processes that may be performed by the materials analysis system of FIG. 6 according to one or more embodiments described herein. [Figure 15] 15 illustrates a continuation of the flow diagram of FIG. 14 of one or more processes that may be performed by the materials analysis system of FIG. 6 in accordance with one or more embodiments described herein. [Figure 16] 1 shows a block diagram of an example scientific instrument system in which one or more of the methods described herein may be performed, according to one or more embodiments described herein. [Figure 17] FIG. 1 illustrates a block diagram of an exemplary operating environment that may incorporate embodiments of the subject matter described herein. [Figure 18] FIG. 1 illustrates an exemplary schematic block diagram of a computing environment with which the subject matter described herein can at least partially interact and / or be implemented. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0008] The following detailed description is merely illustrative and is not intended to limit the embodiments and / or the application or utilization of the embodiments. Furthermore, no one is intended to be bound by any expressed or implied information presented in the Summary of the Invention section or the Detailed Description section above. One or more embodiments will now be described with reference to the drawings, in which like reference numerals are utilized to refer to like elements throughout. In the following description, for ease of explanation, numerous specific details are set forth in order to provide a more thorough understanding of one or more embodiments. However, it will be apparent that in various instances, one or more embodiments may be practiced without these specific details.

[0009] Various operations may be described as multiple separate operations or operations in the order that is most helpful for understanding the subject matter disclosed herein. However, the order of description should not be construed as implying that these operations are necessarily order dependent. In particular, these operations may be performed in different orders than presented. Operations that are described may be performed in different orders than in the described embodiment. Various additional operations may be performed and / or described operations may be omitted in additional embodiments.

[0010] Referring now to the subject of materials analysis and one or more embodiments described herein, when performing materials analysis using mass spectrometry (e.g., a mass spectrometry experiment), the end goal may be to determine the maximum amount of a compound (also referred to herein as a "precursor") within a given amount of time. This given amount of time may be defined as a required period of time to test results, where, for example, the cost of time may be defined in terms of one or more of: instrument depreciation over the period, analyst costs, and / or reagent costs.

[0011] In general, a mass spectrometer is an instrument that can detect, identify, and quantify molecules in a sample based on the molecular mass-to-charge ratio after ionization, i.e., mass spectrometers can employ a variety of ionization methods and can be used in parallel with different separation techniques.

[0012] Mass spectrometry (MS) experiments can be complex endeavors that use multiple acquisition metrics to tune. Extensive research can go into optimizing methodologies and their acquisition metrics, which can be complicated by varying sample, batch, and experimental effects.

[0013] One existing approach, data-dependent analysis, A DDA (Dependent Acquisition) experiment involves acquiring an MS1 ​​spectrum, processing the MS1 spectrum, and proceeding to acquire an MSn spectrum for the expected compound (where n is the total number of mass spectrometry steps, such as for MS2, MS3, etc.). In such a case, the isolated event may be the mass spectrometry step. As a further example, DDA experiments may often employ MS2 acquisition, and TMT-DDA experiments may employ MS3 acquisition. The MSn spectrum may be used for relative quantification if Tandem Mass Tag (TMT) technology is used, or may be used only for identification purposes if a Label-Free (LF) strategy is used and quantification is performed using the MS1 spectrum, but is not limited thereto.

[0014] Such LF-DDA can achieve good identification and quantification coverage, but this may come at the expense of reproducibility due to stochastic triggering of expected compounds, and at the expense of sensitivity due to the use of MS1 for quantification.TMT-DDA may have better throughput due to sample multiplexing, but has problems with reproducibility and coverage.

[0015] Another existing approach, data-independent analysis, A DIA (Independent Acquisition) experiment involves repeatedly acquiring a set of MS / MS spectra spanning the expected precursor range. DIA can achieve greater reproducibility and simplicity, potentially at the expense of some sensitivity and specificity from spectral multiplexing.

[0016] As used herein, an "MS / MS" spectrum refers to the isolation process, fragmentation events, and mass analysis of one with final mass analysis to produce a mass spectrum. Note that additional " / MS" can be added if this process continues for first stage fragment isolation + fragmentation (e.g., MS / MS / MS). Note that MS / MS=MS2, and MS / MS / MS=MS3.

[0017] A series of these acquisitions may span the precursor m / z space, where precursor m / z space refers to the range of precursor mass-to-charge (m / z) values, i.e., the minimum and maximum values ​​that include all of the precursor m / z values. For example, for peptide analysis, the range of m / z 400-1000, or 400-1200, may contain the majority of the compounds in the sample, and [400,1000] may be selected as the precursor m / z space to be processed by the experiment.

[0018] Yet another existing approach, the Targeted MSn (tMsn) experiment, can increase sensitivity over other existing approaches, but the number of identified compounds is the lowest. Although under certain conditions, such as low sample volume and low total number of processable compounds, the number of quantified compounds for tMsn experiments can approach and / or exceed that of other existing approaches.

[0019] These types of optimizations can generally be incorporated into automated workflows, however, they are generally used to enable achievement of the maximum amount of compound captured based on the user entity providing the capture metrics and MS settings.

[0020] As used herein, "real time" may refer to performing one or more optimizations and / or modifications to an experiment while one or more mass spectrometry devices are operating (e.g., in real time).

[0021] That is, the structure of the experiment and the gates and thresholds that control the transition from one state to another are still very well defined by the programmer, which may have advantages in terms of predictability, but may not be able to fully utilize the instrument capabilities or adapt to different experimental conditions. For example, the target number of ions / spectra or the signal thresholds that control the transition from MS to MS2 may vary depending on the LC gradient length, the sample type, and / or the chemical details of the specific elution time. During one or more specific parts of the experiment, there may be extra time to devote to the analysis of certain compounds, while at other times of the experiment, the instrument resources should be more evenly distributed among some eluting compounds due to the specific details of the compound elution from the chromatographic system, etc. These details are difficult or impossible to capture using existing optimization methods.

[0022] To account for one or more incapacities or deficiencies of existing frameworks (e.g., existing materials analysis frameworks using spectral comparisons), one or more embodiments are described herein that may specify high-level results and achieve one or more of the high-level results using a Neural Network (NN) trained based on a Reinforcement Learning (RL) based approach. The RL-trained NN may automatically determine acquisition metrics and operational settings for recommending and / or directing subsequent acquisitions and / or for defining such acquisitions based on the environment (e.g., m / z precursor space) resulting from each subsequent fragmentation acquisition and / or further fragmentation acquisition.

[0023] That is, as opposed to controlling experiments at a lower level of granulation with each and every capture metric and MS operating setting, it may instead be desirable to control such experiments at a higher level than is permitted by existing approaches by setting one or more metrics of interest: total capture time, number of compounds to capture, and / or type of compounds to capture.

[0024] Thus, one or more embodiments described herein may enable advanced compound-specific acquisition metrics at each stage of an experiment (e.g., for each subsequent acquisition, whether a subsequent acquisition or a further fragmentation acquisition such as an MS / MS acquisition or an MS / MS / MS acquisition), without explicit programming of the acquisition metrics.

[0025] We now describe reinforcement learning (RL), a field of optimization that can be used to direct the behavior of an agent (e.g., a system, device, processor, etc.) where the environment can be changing and uncertain and / or writing explicit instructions for behavior can be fragile and inflexible. Creating a program that allows a robot to get up and run, or clean a house, are good examples of such situations, where it may be easy to describe what you want to happen, but writing explicit instructions to achieve the goal under a wide range of circumstances can be difficult.

[0026] Using traditional RL vocabulary, agents interact with the environment by performing actions. During training, agents receive information about the environment state, select actions that update the environment, and receive rewards. Rewards may be amortized over future states to help the system find actions that do not yield immediate rewards but pay off later. For example, in extreme cases, an agent may receive little or no reward (or penalty) until the end of a set of many steps, such as when training an agent to navigate to a goal, or when the agent experiences some kind of catastrophe (such as falling into a hole). This process may be repeated over an "episode" that includes one or more MS experiments, such as a liquid chromatography MS experiment. Typically, hundreds or thousands of training episodes are needed to train an effective agent for a particular task.

[0027] In one or more embodiments described herein, there may be an opportunity to employ in silico optimization concepts to utilize a reinforcement learning framework to direct the operation of one or more mass spectrometry devices in real time, as well as to optimize acquisition metrics and / or MS operational settings using the general RL framework described above. For example, a general optimization scheme may include determining a list of experiments with their respective different acquisition metrics and MS operational settings, using an RL trained NN, and running the experiments either in real life or in simulation, resulting in a corresponding experimental score for each. The experimental score may take the form of some unique identification metric that refers to the number of compounds detected in the experiment and the quality of their detection (e.g., their signal-to-noise ratio S / N). The optimization may be a simple enumeration over a grid of experimental acquisition metrics, or a more advanced optimization, for example, using design of experiments, genetic algorithms, or particle optimization.

[0028] The discussion then moves to a general discussion of one or more scientific instrument systems, as well as associated methods, computing devices, and computer-readable media disclosed herein. For example, in one or more embodiments, the system may include a memory that stores computer-executable components, and a processor that executes the computer-executable components stored in the memory. The computer-executable components include a capture component that captures data of a compound, the data defining a first mass spectrometry spectrum of the compound, an evaluation component that uses a neural network trained on an input data set including one or more capture metrics based on the data, and uses one or more relevance scores associated with the one or more capture metrics to generate a recommendation for performing a mass spectrometry operation on the compound, and an execution component that directs the performance of a mass spectrometry operation in a mass spectrometer based on the recommendation, and obtains a mass spectrum result.

[0029] One or more embodiments disclosed herein may achieve improved performance compared to existing approaches. For example, based on RL training and historical data on which the NN may be RL trained, a system using a RL trained NN as described herein may use better compound-specific capture operations than may simply be pre-programmed by a management entity. That is, such a system may learn to recognize when resources should be consumed during a current capture and during future recommended or prescribed capture operations. As discussed above, there may be precursor environments where extended accumulation times may result in lower detection limits, or where rapid capture times may be necessary given the large number of compounds entering the mass spectrometer.

[0030] Additionally, the embodiments described herein may advantageously provide focus / direction on multiple compounds at once, even based on different recommended capture actions, i.e., the embodiments described herein may use mixed optimization techniques to achieve the best test results based on selected high-level objectives, such as analytical specificity, increased probability of accuracy, and / or increased number of compound detections.

[0031] Furthermore, the embodiments described herein can be adapted to different types of experiments, labeling techniques, and / or mass or cross-section analysis techniques. That is, depending on the level of sample description or applicable high-level experimental goals, the framework described herein can be adapted to suit the sample. For example, rewards, high-level goals, available capture actions, etc. can be input into the system and NN, which is updated to operate within the range of the inputs.

[0032] Thus, the embodiments disclosed herein provide improvements to scientific instrument technology (eg, improvements to the computer technology supporting such scientific instruments, among other things).

[0033] Various of the embodiments disclosed herein may improve upon existing approaches to achieve the technical advantage of high accuracy and / or mass identification of material compounds through the use of reinforcement learning agents (e.g., NNs trained using RL), i.e., generation of output data may be achieved without specific low-level control of capture metrics and / or operational settings for each and every step of a multi-step material analysis experiment using MS.

[0034] Such technical advantages are routine and unattainable by existing approaches, and all user entities of a system including such embodiments can benefit from such advantages (e.g., by assisting the user entities in performing a technical task, such as identifying one or more chemical compounds, through a guided human-machine-NN interaction process).

[0035] It will be appreciated that the technical features of the embodiments disclosed herein (e.g., the ability to generate one or more MS results using RL-based control), as well as the combination of features of the embodiments disclosed herein, are therefore unprecedented in the field of materials analysis.

[0036] As discussed further herein, various aspects of the embodiments disclosed herein may improve the functionality of the computer itself. Furthermore, the computational and user interface features disclosed herein do not only involve the collection and comparison of information, but apply new analytical and technical techniques to modify the operation of the computational analysis of material compounds. For example, an update process may be used by the system / NN combination to enhance good recommendations by the NN based on the result output of the experiment and based on one or more reward indicators corresponding to the result output. Thus, the non-limiting systems described herein, including the material analysis system and the NN, may be self-improving.

[0037] Thus, the present disclosure introduces capabilities that neither existing computing devices nor humans can perform. Rather, such existing computing devices would instead require low-level control of MS-based or MS-enabled experiments, including, but not limited to, specific control of capture metrics and operational settings for each step of a multi-stage experiment. Given the lack of computerized reference using historical data, plus the associated time, energy, and human error, it is not practical to operate within the scope of existing approaches.

[0038] Thus, embodiments of the present disclosure may be useful for any of a number of technical purposes, such as controlling a particular technical system or process, determining how to control a machine from measurements, separating material sources in digital audio, image, or video enhancement or analytical mixed signals, generating data for reliable and / or efficient transmission or storage, providing estimates and confidence intervals for material samples, or providing faster processing of sensor data. In particular, the present disclosure provides technical solutions to technical problems including, but not limited to, providing capture recommendations and / or directing capture, making capture recommendations using historical data, generating updated scores corresponding to one or more probabilities, and / or providing faster, more complete, and / or more efficient processing of material compounds.

[0039] Thus, the embodiments disclosed herein provide improvements in materials analysis techniques (eg, improvements in computer techniques to aid in materials analysis, among other improvements).

[0040] As used herein, the phrase "based on" should be understood to mean "based at least in part on," unless otherwise specified.

[0041] As used herein, the term "component" may refer to an atomic element, a molecular element, a phase of an atomic or molecular element, or a combination thereof.

[0042] As used herein, the terms "compound" and "precursor" may be used interchangeably.

[0043] As used herein, the term "data" may include metadata.

[0044] As used herein, the terms “entity,” “requesting entity,” and “user entity” may refer to a machine, device, component, hardware, software, smart device, party, organization, individual, and / or human being.

[0045] One or more embodiments will now be described with reference to the drawings, in which like reference numerals are used to refer to like drawing elements throughout. In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a more thorough understanding of one or more embodiments. It will be apparent, however, that in various instances, one or more embodiments may be practiced without these specific details.

[0046] Furthermore, it should be understood that the embodiments illustrated in one or more of the figures described herein are for illustrative purposes only, and thus the architecture of the embodiments is not limited to the systems, devices, and / or components illustrated herein, nor to any particular ordering, connections, and / or couplings of the systems, devices, and / or components illustrated herein.

[0047] Referring now in particular to one or more figures, and initially to FIG. 1, there is shown a block diagram of a scientific instrument module 100 for performing material analysis operations using a RL trained NN and performing at least one or more aspects of the training, according to various embodiments described herein. The scientific instrument module 100 may be implemented by a circuit (e.g., including electrical and / or optical components) such as a programmed computing device. The logic of the scientific instrument module 100 may be included in a single computing device or may be distributed across multiple computing devices that communicate with each other as needed. An example of a computing device that may implement the scientific instrument module 100, alone or in combination, is described herein with reference to the computing device 400 of FIG. 4, and an example of a system of interconnected computing devices in which the scientific instrument module 100 may be implemented across one or more of the computing devices is described herein with reference to the scientific instrument system 1600 of FIG. 16.

[0048] The scientific instrument module 100 may include a first logic 102, a second logic 104, a third logic 106, a fourth logic 108, and a fifth logic 110. As used herein, the term "logic" may include an apparatus that performs a set of operations associated with the logic. For example, any of the logic elements included in the module 100 may be implemented by one or more computing devices programmed with instructions to cause one or more processing devices of the computing devices to perform a set of operations associated with the one or more computing devices. In certain embodiments, a logic element may include one or more non-transitory computer-readable media having instructions that, when executed by one or more processing devices of the one or more computing devices, cause one or more computing devices to perform a set of operations associated with the one or more computing devices. As used herein, the term "module" may refer to a collection of one or more logic elements that together perform a function associated with the module. Different ones of the logic elements in a module may take the same form or different forms. For example, some logic in a module may be implemented by a programmed general-purpose processing device, while other logic in a module may be implemented by an Application-Specific Integrated Circuit (ASIC). In another embodiment, different ones of the logic elements in a module may be associated with different sets of instructions executed by one or more processing devices. A module may omit one or more of the logic elements shown in the associated figure, but, for example, a module may include a subset of the logic elements shown in the associated figure if the module performs a subset of the operations described herein with reference to that module.

[0049] The first logic 102 may compare compound input data with capture metrics, historical data, and / or compound type data to generate a dataset matrix that includes a scoring that defines a probability of achieving one or more capture metrics and / or target metrics, i.e., the first logic 102 may generate and / or transform data for use in performing capture action recommendations.

[0050] The second logic 104 may generate one or more scores for the aforementioned scoring, i.e., the second logic 104 may help define (including, e.g., ranking) capture metrics and / or target metrics, and focus the capture metrics and target metrics upon which the resumed capture operation may be based.

[0051] The third logic 106 may include performing an evaluation with a RL trained neural network, such as based on the output of either the first logic 102 or the second logic 104.

[0052] The fourth logic 108 may include outputting a recommended capture action or outputting instructions for performing the capture action.

[0053] The fifth logic 110 may include a performance evaluation of the NN based on the output of the fourth logic 108. That is, the fifth logic 110 may employ a reward system to reinforce outputs that meet and / or satisfy one or more capture metrics and / or target metrics.

[0054] As used herein, capture metrics can be, but are not limited to, probability of detection, signal strength, fit to expected isotopic cluster, mass accuracy, delta time between estimated current time and expected elution time, and / or whether the capture was for the same precursor in the last iteration (e.g., step or stage) of the experiment. Another capture metric can be identification of adjacent compounds, where identification of one compound corresponds to an increased probability that another compound (e.g., the compound of interest) is present or will soon be present.

[0055] Alternatively, as used herein, a metric of interest may be a high level aspect such as, but not limited to, the amount of precursor identified, the specificity of the precursor identified, the precision of the precursor abundance measurement, and / or the speed of precursor identification.

[0056] 2 illustrates a flow diagram of a method 200 of performing operations by a scientific instrument module 100, according to various embodiments. The operations of method 200 may be illustrated with reference to particular embodiments disclosed herein (e.g., the scientific instrument module 100 described herein with reference to FIG. 1, the GUI 300 described herein with reference to FIG. 3, the computing device 400 described herein with reference to FIG. 4, and / or the scientific instrument system 1600 described herein with reference to FIG. 16), but method 200 may be used in any suitable configuration to perform any suitable operations. Although the operations are illustrated in FIG. 2 once each and in a particular order, the operations may be appropriately reordered and / or repeated as desired (e.g., different operations performed may be performed in parallel, as appropriate).

[0057] A first operation may be performed at 202. For example, the first logic 102 of the module 100 may perform the first operation 202. The first operation 202 may include identifying one or more compounds to use for an experiment (e.g., identifying one or more precursors therefrom).

[0058] As used herein, a precursor is a compound, but the term can be used to refer to a compound that is identified from another compound.

[0059] A second operation may be performed at 204. For example, the second logic 104 of the module 100 may perform the second operation 204. The second operation 204 may include assigning scores to the process parameters and / or the target metrics.

[0060] A third operation may be performed at 206. For example, the third logic 106 of the module 100 may perform the third operation 206. The third operation 206 may include performing an evaluation of the data using an RL trained neural network.

[0061] A fourth operation may be performed at 208. For example, the fourth logic 108 of the module 100 may perform the fourth operation 208. The fourth operation 208 may include determining one or more recommended capture operations and / or directing the performance of the one or more capture operations.

[0062] At 210, a fifth operation may be performed. For example, the fifth logic 110 of the module 100 may perform the fifth operation 210. The fifth operation 210 may include performing a performance evaluation of the NN based on the output from the fourth operation. The fifth operation 210 may include using a reward system and updating data and / or functions of the NN based on the reward system.

[0063] Scientific instrument methods disclosed herein may include interactions with a user entity (e.g., via a user local computing device 1620, described herein with reference to FIG. 16 ). These interactions may include providing information to the user entity (e.g., information regarding the operation of a scientific instrument such as the scientific instrument 1610 of FIG. 16 , information regarding a sample being analyzed or other tests or measurements performed by the scientific instrument, information obtained from a local or remote database, or other information), or providing options for the user entity to enter commands (e.g., to control the operation of a scientific instrument such as the scientific instrument 1610 of FIG. 16 or to control the analysis of data generated by the scientific instrument), queries (e.g., to a local or remote database), or other information. In some embodiments, these interactions may be performed through a Graphical User Interface (GUI) including a visual display on a display device (e.g., display device 410, described herein with reference to FIG. 4) that provides output to a user entity and / or directs the user entity to provide input (e.g., via one or more input devices, such as a keyboard, mouse, trackpad, or touch screen included in other I / O (Input / Output) devices 412 described herein with reference to FIG. 4). The scientific instrument system 1600 disclosed herein may include any suitable GUI for interaction with a user entity.

[0064] 3, an exemplary GUI 300 that may be used in performing some or all of the methods described herein, according to various embodiments described herein, is shown. As noted above, the GUI 300 may be provided on a display device (e.g., display device 410 described herein with reference to FIG. 4) of a computing device (e.g., computing device 400 described herein with reference to FIG. 4) of a scientific instrument system (e.g., scientific instrument system 1600 described herein with reference to FIG. 16), and a user entity may interact with the GUI 300 using any suitable input device (e.g., any of the input devices included in other I / O devices 412 described herein with reference to FIG. 4) and input technique (e.g., cursor movement, motion capture, face recognition, gesture detection, voice recognition, button actuation, etc.).

[0065] GUI 300 may include a data display area 302, a data analysis area 304, a scientific instrument control area 306, and a settings area 308. The particular number and arrangement of areas shown in FIG. 3 is merely exemplary, and any number and arrangement of areas containing any desired features may be included in GUI 300.

[0066] The data display area 302 may display data generated by a scientific instrument (e.g., the scientific instrument 1610 described herein with reference to FIG. 16). For example, the data display area 302 may display one or more output results 682, which may include, but are not limited to, text, graphs, charts, matrices, and / or spectra.

[0067] The data analysis area 304 may display the results of a data analysis (e.g., the results of analyzing the data shown in the data display area 302 and / or other data). For example, the data analysis area 304 may display one or more compound results 682 and / or one or more reward indicators 722. In one or more cases, the data analysis area 304 may display a list, flow chart, or other schematic of capture actions taken and / or recommended for the experiment. In one or more embodiments, the data display area 302 and the data analysis area 304 may be combined in the GUI 300 (e.g., to include data output from scientific instruments and some analysis of the data in a common graph or area).

[0068] The scientific instrument control area 306 may include options that enable a user entity to control a scientific instrument (e.g., the scientific instrument 1810 described herein with reference to FIG. 18 ). For example, the scientific instrument control area 306 may include one or more controls for inputting one or more metrics of interest.

[0069] Settings area 308 may include options that enable a user entity to control features and functionality of GUI 300 (and / or other GUIs) and / or perform common computing operations related to data display area 302 and data analysis area 304 (e.g., saving data on a storage device such as storage device 404 described herein with reference to FIG. 4, sending data to another user entity, labeling data, etc.). For example, settings area 308 may include one or more options for changing the color, fill, or format of an illustration, such as illustrations 1150 and 1160 of FIG. 11.

[0070] As noted above, the scientific instrument module 100 may be implemented by one or more computing devices. Accordingly, referring now to FIG. 4, FIG. 4 illustrates a block diagram of a computing device 400 that may perform some or all of the scientific instrument methods disclosed herein, according to various embodiments. In one or more embodiments, the scientific instrument module 100 may be implemented by a single computing device 400, or by multiple computing devices 400. Additionally, as discussed below, a computing device 400 (or multiple computing devices 400) that implements the scientific instrument module 100 may be part of one or more of the scientific instrument 1610, user local computing device 1620, service local computing device 1630, or remote computing device 1640 of FIG. 16.

[0071] 4 is illustrated as having several components, any one or more of which may be omitted or duplicated as appropriate for the application and setting. As shown, these components may include one or more of a processor 402, a storage device 404, an interface device 406, a battery / power circuitry 408, a display device 410, and other input / output (I / O) devices 412, as described below.

[0072] In one or more embodiments, one or more of the components included in computing device 400 may be mounted on one or more motherboards and housed within a housing (e.g., comprising plastic, metal, and / or other materials). In one or more embodiments, some of these components may be fabricated on a single System-On-a-Chip (SoC) (e.g., an SoC may include one or more processors 402 and one or more storage devices 404). Note that in one or more embodiments, computing device 400 may omit one or more of the components shown in FIG. 4. In one or more embodiments, computing device 400 may include interface circuitry (not shown) for coupling to one or more components using any suitable interface (e.g., a Universal Serial Bus (USB) interface, a High-Definition Multimedia Interface (HDMI) interface, a Controller Area Network (CAN) interface, a Serial Peripheral Interface (SPI) interface, an Ethernet interface, a wireless interface, or any other suitable interface). For example, computing device 400 may omit display device 410, but may include display device interface circuitry (eg, connectors and driver circuitry) to which display device 410 can be coupled.

[0073] Computing device 400 may include a processor 402 (e.g., one or more processing devices). As used herein, the term "processing device" may refer to any device or portion of a device that processes electronic data from registers and / or memory and converts the electronic data into other electronic data that may be stored in registers and / or memory. Processor 402 may include one or more digital signal processors (DSPs), application-specific integrated circuits (ASICs), and / or other integrated circuits (ICs). Integrated Circuits (ASIC), Central Processing Unit These may include CPUs, Graphics Processing Units (GPUs), cryptographic processors (dedicated processors that execute cryptographic algorithms in hardware), server processors, or any other suitable processing device.

[0074] The computing device 400 may include a storage device 404 (e.g., one or more storage devices). The storage device 404 may include Random Access Memory (RAM) (e.g., static RAM). The storage device 404 may include one or more memory devices, such as a static random access memory (SRAM) device, a magnetic RAM (MRAM) device, a dynamic RAM (DRAM) device, a resistive RAM (RRAM) device, or a conductive-bridging RAM (CBRAM) device, a hard drive-based memory device, a solid-state memory device, a network drive, a cloud drive, or any combination of memory devices. In one or more embodiments, the storage device 404 may include a memory that shares a die with the processor 402. In such an embodiment, the memory may be used as a cache memory and may include, for example, an embedded dynamic random access memory (eDRAM) or a spin transfer torque magnetic random access memory (STT-MRAM). In one or more embodiments, storage device 404 may include a non-transitory computer-readable medium having instructions thereon that, when executed by one or more processing devices (e.g., processor 402), cause computing device 400 to perform any suitable ones of the methods or portions of those methods disclosed herein.

[0075] Computing device 400 may include interface device 406 (e.g., one or more interface devices 406). Interface device 406 may include one or more communication chips, connectors, and / or other hardware and software to manage communications between computing device 400 and other computing devices. For example, interface device 406 may include circuitry to manage wireless communications to transfer data to and from computing device 400. The term "wireless" and its derivatives may be used to describe circuits, devices, systems, methods, techniques, communication channels, etc. that may communicate data through the use of modulated electromagnetic radiation over a non-solid medium. This term does not imply that the associated devices do not include any wiring, although in one or more embodiments, the associated devices may not include any wiring. The circuitry included in interface device 406 for managing wireless communications may implement any of a number of wireless standards or protocols, including, but not limited to, Wi-Fi (IEEE 802.11 family), Institute for Electrical and Electronic Engineers (IEEE) standards including the IEEE 802.16 standard (e.g., the IEEE 802.16-2005 Amendment), the Long-Term Evolution (LTE) project with any amendments, updates, and / or revisions (e.g., the Advanced LTE project, the Ultra-Mobile Broadband (UMB) project (also referred to as “3GPP®2”), etc.).In one or more embodiments, the circuitry included in the interface device 406 for managing wireless communications may be adapted to support a variety of standards, including Global System for Mobile Communication (GSM), General Packet Radio Service (GPRS), Universal Mobile Telecommunications System (UMTS), High Speed ​​Packet Access (HSPA), Evolved HSPA (Evolved HSPA), and / or LTE. In one or more embodiments, the interface device 406 may operate in accordance with a HSPA, E-HSPA, or LTE network. In one or more embodiments, the interface device 406 may operate in accordance with an Enhanced Data for GSM Evolution (EDGE), GSM EDGE Radio Access Network (GERAN), Universal Terrestrial Radio Access Network (UTRAN), or Evolved UTRAN (E-UTRAN). In one or more embodiments, the interface device 406 may operate in accordance with a Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), or LTE network. Division Multiple Access (TDMA), Digital Enhanced Cordless Communications (Digital Enhanced Cordless Telecommunications (DECT), Evolution-Data Optimization EV-DO (Echo Optimized, EV-DO), and derivatives thereof, as well as any other wireless protocols designated as 3G, 4G, 5G, and beyond. In one or more embodiments, the interface device 406 may include one or more antennas (e.g., one or more antenna arrays) for receiving and / or transmitting wireless communications.

[0076] In one or more embodiments, the interface device 406 may include circuitry for managing wired communications, such as electrical, optical, or any other suitable communications protocol. For example, the interface device 406 may include circuitry to support communications according to Ethernet technology. In one or more embodiments, the interface device 406 may support both wireless and wired communications, and / or may support multiple wired and / or multiple wireless communications protocols. For example, a first set of circuits of the interface device 406 may be dedicated to short-range wireless communications, such as Wi-Fi or Bluetooth, and a second set of circuits of the interface device 406 may be dedicated to long-range wireless communications, such as Global Positioning System (GPS), EDGE, GPRS, CDMA, WiMAX, LTE, EV-DO, or others. In one or more embodiments, the first set of circuits of the interface device 406 may be dedicated to wireless communications, and the second set of circuits of the interface device 406 may be dedicated to wired communications.

[0077] Computing device 400 may include battery / power circuitry 408. Battery / power circuitry 408 may include one or more energy storage devices (e.g., batteries or capacitors) and / or circuitry for coupling components of computing device 400 to an energy source (e.g., AC line power) separate from computing device 400.

[0078] Computing device 400 may include a display device 410 (e.g., multiple display devices). Display device 410 may include any visual indicator, such as a heads-up display, a computer monitor, a projector, a touch screen display, a Liquid Crystal display (LCD), a light emitting diode display, or a flat panel display.

[0079] Computing device 400 may include other input / output (I / O) devices 412, such as, for example, one or more audio output devices (e.g., a speaker, a headset, an earpiece, an alarm, etc.), one or more audio input devices (e.g., a microphone or microphone array), a location device (e.g., a GPS device that communicates with a satellite-based system to receive the location of computing device 400, as is known in the art), an audio codec, a video codec, a printer, sensors (e.g., a thermocouple or other temperature sensor, a humidity sensor, a pressure sensor, a vibration sensor, an accelerometer, a gyroscope, etc.), an image data capture device such as a camera, a keyboard, a cursor control device (e.g., a mouse, a stylus, a trackball, or a touchpad), a barcode reader, a Quick Response (QR) code reader, or a radio frequency identification (RFID) device. RFID (radio frequency identification) readers may be mentioned.

[0080] Computing device 400 may have any suitable form factor for the application and setting, such as a handheld or mobile computing device (e.g., a cell phone, a smartphone, a mobile Internet device, a tablet computer, a laptop computer, a netbook computer, an ultrabook computer, a personal digital assistant (PDA), an ultra-mobile personal computer, etc.), a desktop or server computing device, or other networked computing component.

[0081] 5 and 6, in one or more embodiments, the non-limiting systems 500 and / or 600 shown in Figures 5 and 6, and / or the systems thereof, may further comprise one or more computers and / or computing-based elements described herein with reference to a computing environment, such as the computing environment 1800 illustrated in Figure 18. In one or more described embodiments, the computers and / or computing-based elements may be used in connection with implementing one or more of the systems, devices, components and / or computer-implemented operations shown and / or described in connection with Figures 5 and / or 6 and / or other figures described herein.

[0082] 5, a block diagram of an exemplary non-limiting system 500 may include a materials analysis system 502, a neural network (NN) 570, and an MS instrument 550. The materials analysis system 502 may facilitate the process of using the RL-trained NN to control an MS-based experiment.

[0083] In one or more embodiments, materials analysis system 502 may be configured, at least in part, by computing device 400.

[0084] In one or more embodiments, materials analysis system 502 may at least partially comprise NN 570 and / or MS device 550.

[0085] It should be noted that materials analysis system 502 is merely detailed in a simplified manner to provide an introduction to a more complex and / or more extensive materials analysis system 602 as shown in Figure 6. That is, further details regarding processes that may be performed by one or more embodiments described herein are provided below in connection with the non-limiting system 600 of Figure 6.

[0086] 5, material analysis system 502 may include at least a memory 504, a bus 505, a processor 506, a capture component 510, an evaluation component 516, and an execution component 518. Processor 506 may be the same as processor 402, may be included in processor 402, or may be different from processor 402. Memory 504 may be the same as storage device 404, may be included in storage device 404, or may be different from storage device 404.

[0087] Using the above-mentioned components, the materials analysis system 502 may use the RL-trained NN to control an MS-based experiment and provide output information related to the compound 562 being analyzed. That is, the materials analysis system 502 may determine acquisition metrics 810 (FIG. 8) and / or operational settings for one or more stages of the MS experiment based on the acquired data (e.g., input data 560), historical data 542, and / or analysis thereof. Based on these acquisition metrics 810, operational settings, and / or historical data 542, the materials analysis system may define at least one recommended acquisition action to be taken to achieve a target metric corresponding to the compound 562.

[0088] The metrics of interest may be provided by a user entity and / or may be programmed into the experimental program being used by materials analysis system 502. The metrics of interest may include, but are not limited to, a focus on one or more of the number of compounds identified, the speed of identification, the accuracy of identification, and / or the precision of identification.

[0089] Generally, the capture component 510 may capture data (e.g., input data 560, also referred to herein as first data) for a compound 562. In one or more embodiments, the data may define a first mass spectrometry spectrum 566 of the compound 562. The data may include one or more compound parameters 564 (e.g., but not limited to, physical phase temperature range, physical properties, mechanical properties, chemical properties, etc.).

[0090] Based on the data, and using the neural network 570 trained on an input dataset including one or more capture metrics and one or more associated scores associated with the one or more capture metrics, the evaluation component 516 may generate a recommendation to perform a mass spectrometry operation (e.g., capture operation 580) on the compound 562. Note that the input dataset is different from the input data 560, but the input data 560 may be used to populate, generate, update, and / or transform the input dataset. Input datasets, such as the exemplary scoring matrix 800, are described in more detail below in connection with the materials analysis system 602.

[0091] Based on the recommendation to perform a mass analysis operation (e.g., capture operation 580), the execution component 518 can direct the execution of the mass analysis operation in a mass spectrometer (e.g., MS device 550) and obtain mass spectral results therefrom (e.g., including composite result 582).

[0092] The capture component 510, the evaluation component 516, and the execution component 518 may be operatively coupled to a processor 506, which may be operatively coupled to the memory 504. A bus 505 may provide the operative coupling. The processor 506 may facilitate the execution of the capture component 510, the evaluation component 516, and the execution component 518. The capture component 510, the evaluation component 516, and the execution component 518 may be stored in the memory 504.

[0093] In general, the non-limiting system 500 may use any suitable communication method (e.g., electronic, telecommunications, internet, infrared, fiber, etc.) to provide communication between the material analysis system 502, the database 540, the NN 570, the MS device 550, and / or any devices associated with a user entity.

[0094] Referring now to Figure 6, a non-limiting system 600 is shown that may include a materials analysis system 602, a NN 670, a database 640, and an MS device 550. Repeated descriptions of similar elements and / or processes used in each embodiment are omitted for brevity. The description of the embodiment of Figure 5 may be applicable to the embodiment of Figure 6. Similarly, the description of the embodiment of Figure 6 may be applicable to the embodiment of Figure 5.

[0095] In general, the materials analysis system 502 can facilitate the process of using a RL-trained NN to control an MS-based experiment.

[0096] In one or more embodiments, materials analysis system 602 may be configured, at least in part, by computing device 400 .

[0097] In one or more embodiments, materials analysis system 602 may at least partially comprise NN 670, database 640, and / or MS device 650.

[0098] NN670 may be and / or include any suitable artificial intelligence embodiment, neurons, layers of neurons, clusters of neurons, and / or the like. NN670 may be initially trained using reinforcement learning by update component 622 and / or any external training system. For example, during training of NN670, NN670 may receive information about the state of the environment, be asked to select an action that updates the environment, and receive a reward. The reward may be amortized over future states to help NN670 find actions that do not result in an immediate reward but pay off later. For example, in extreme cases, NN670 may receive little or no reward (or penalty) until the end of a set of many steps, such as when training an agent to navigate to a goal, or when NN670 experiences some kind of catastrophe (such as falling into a hole). This process is repeated over an "episode" that includes one or more LC-MS experiments. Typically, hundreds or thousands of training episodes may be used to train NN670 for materials analysis of a particular compound or type of compound. As used herein, "type" can include a variety of compounds such as human tissue, mining gases, and the like.

[0099] As used herein, an example of an NN670 experiencing a catastrophic event may refer to the use of a metric to characterize the entire elution peak (e.g., capturing 8-10 points per LC peak). The NN may have difficulty determining completion until the entire peak has been characterized, thus resulting in initiating or intermediate operations on the peak, resulting in a lower reward. Rather, a reward amortization scheme may be used over time, such as to transfer final rewards backwards to earlier operations.

[0100] In one or more embodiments, an array of two or more NNs 670 may be trained and used for different precursors, etc. In one or more examples, two or more such NNs 670 may be aggregated (e.g., stacked) to form a super-NN (super neural network), which may be used to generate recommended capture operations 720, for example, for different precursors, more quickly and more efficiently.

[0101] The database 640 may include historical data 542 in any suitable format, including but not limited to numbers, text, code, data, metadata, images, etc. The historical data 542 may include historical acquisition metrics 544, historical spectra 546, and / or historical acquisition actions 548. The historical acquisition metrics 544 may include but are not limited to ion amounts required for analysis, analysis temperatures, and / or analysis resolution parameters. The historical acquisition actions 548 may have been taken to achieve a particular metric of interest in a past MS-based experiment, or in a previous acquisition in the same experiment.

[0102] Database 640 may, in one or more embodiments, be included at least in part in materials analysis system 602 .

[0103] The MS device 650 may be any suitable MS device capable of providing a material analysis output, such as one or more spectra.

[0104] One or more communications between one or more components of the non-limiting system 600 may be provided by wired and / or wireless means, including, but not limited to, using a cellular network, a Wide Area Network (WAN) (e.g., the Internet), and / or a Local Area Network (LAN). Suitable wired or wireless technologies for facilitating communications include, but are not limited to, wireless fidelity (Wi-Fi), Global Mobile Telecommunications (GMT), and / or LTE. System for Mobile communication, GSM, Universal Mobile Communication System Mobile Telecommunications System (UMTS), WiMAX (worldwide interoperability for microwave access (WiMAX), enhanced General Packet Radio Service (enhanced GPRS), third generation partnership project (3GPP) long term evolution (LTE), third generation partnership project 2 (3GPP2) ultra-mobile broadband (UMB), high speed packet access (High This includes standards such as High Speed ​​Packet Access (HSPA), Zigbee and other 802.XX wireless technologies and / or legacy telecommunications technologies, BLUETOOTH®, Session Initiation Protocol (SIP), ZIGBEE®, RF4CE protocol, WirelessHART protocol, 6LoWPAN (IPv6 over Low Power Wireless Area Networks), Z-Wave, ultra-wideband (UWB) standard protocols and / or other proprietary and / or non-proprietary communication protocols.

[0105] Materials analysis system 602 may be associated with (e.g., accessible via) a cloud computing environment, such as cloud computing environment 1700 of FIG. 17.

[0106] Materials analysis system 602 may include multiple components, which may include a memory 604, a processor 606, a bus 605, a capture component 610, an analysis component 612, a metrics component 614, an evaluation component 616, an execution component 618, a rewards component 620, and / or an update component 622. Using these components, materials analysis system 602 may output one or more recommendations 720, one or more prescribed capture actions 680, and / or one or more composite results 682.

[0107] The processor 606, memory 604, and bus 605 of the material analysis system 602 will now be described. For example, in one or more embodiments, the material analysis system 602 may comprise a processor 606 (e.g., a computer processing unit, a microprocessor, a classical processor, a quantum processor, and / or the like). In one or more embodiments, components associated with the material analysis system 602 may include one or more computer and / or machine readable, writable, and / or executable components and / or instructions, as described herein with or without reference to one or more figures of one or more embodiments, and may be executed by the processor 606 to provide for the execution of one or more processes defined by such components and / or instructions. In one or more embodiments, the processor 606 may comprise a capture component 610, an analysis component 612, a metrics component 614, an evaluation component 616, an execution component 618, a reward component 620, and / or an update component 622.

[0108] In one or more embodiments, material analysis system 602 may comprise a computer-readable memory 604, which may be operatively coupled to processor 606. Memory 604 may store computer-executable instructions that, when executed by processor 606, may cause processor 606 and / or one or more other components of material analysis system 602 (e.g., capture component 610, analysis component 612, metrics component 614, evaluation component 616, execution component 618, reward component 620, and / or update component 622) to perform one or more operations. In one or more embodiments, memory 604 may store computer-executable components (e.g., capture component 610, analysis component 612, metrics component 614, evaluation component 616, execution component 618, reward component 620, and / or update component 622).

[0109] The materials analysis system 602 and / or components thereof described herein may be communicatively, electrically, operatively, optically, and / or otherwise coupled to one another via a bus 605. The bus 605 may include one or more of a memory bus, a memory controller, a peripheral bus, an external bus, a local bus, a quantum bus, and / or another type of bus that may employ one or more bus architectures. One or more of these examples of the bus 605 may be used.

[0110] In one or more embodiments, materials analysis system 602 may be coupled (e.g., communicatively, electrically, operatively, optically, and / or with similar functionality) to one or more external systems (e.g., an electrical output generating system, not shown, one or more output target systems, one or more controllers for the output targets, and / or controllers for the output targets), sources, and / or devices (e.g., classical and / or quantum computing devices, communication devices, and / or similar devices). In one or more embodiments, materials analysis system 602 and / or one or more of the components of non-limiting system 600 may reside in the cloud and / or may reside locally (e.g., at a designated location) in a local computing environment.

[0111] In addition to the processor 606 and / or memory 604 described above, materials analysis system 602 may comprise one or more computer- and / or machine-readable, writeable, and / or executable components and / or instructions that, when executed by processor 606, may provide for the performance of one or more operations defined by such components and / or instructions.

[0112] Turning now to the additional components of material analysis system 602 (e.g., capture component 610, analysis component 612, metrics component 614, evaluation component 616, execution component 618, rewards component 620, and / or update component 622), generally, material analysis system 602 may perform a series of processes that may be divided into three steps: initial capture and analysis, evaluation and recommendation, and rewards and updates.

[0113] Referring now first to initial acquisition and analysis, details regarding acquisition component 610, analysis component 612, and metrics component 614 are provided.

[0114] Referring now first to the capture component 610, this component may generally capture data (e.g., input data 660) for a compound 662, the data defining a first mass spectrometry spectrum 665 of the compound 662. The input data 660 may further include one or more compound metrics 664 (e.g., but not limited to, physical phase temperature range, physical properties, mechanical properties, chemical properties, etc.).

[0115] In one or more embodiments, the input data 660 may include data defining one or more initial captures 703 that define and / or identify one or more starting compounds 662 (e.g., starting compounds 662 with which the non-limiting system 600 begins an MS-based experiment).

[0116] In one or more embodiments, the capture component 610 can identify one or more compounds (e.g., at least a first compound 662 and a second compound 662) from the input data (e.g., from a spectrum 665). In one or more other embodiments, the initial compounds 662 can instead be provided as input to the non-limiting system 600.

[0117] The input data 660 may be provided in any suitable format (eg, without limitation, text, code, numbers, data, metadata).

[0118] In one or more embodiments, capture component 610 may provide input data 660 as input to NN 670, and / or NN 670 may obtain input data 660 by one or more other suitable means.

[0119] The metrics component 614 may obtain and provide as input to the NN one or more metrics of interest 668 related to the compounds 662 or types of compounds to be analyzed by the MS-based experiment using the RL-based control provided by one or more embodiments herein. The metrics of interest 668 may be high-level goals to be achieved by the non-limiting system 600. In one or more embodiments, the metrics of interest 668 are less descriptive so as to include lower level acquisition metrics and / or operational settings that would more specifically define one or more stages of the MS-based experiment. For example, the metrics of interest 668 may include, but are not limited to, instructions to achieve a particular number of identifications, achieve a maximum number of identifications, perform a selected number of acquisition operations, achieve a selected identification accuracy, perform rapid identifications within a desired sample separation period (i.e., LC gradient length), use a particular experimental technique or methodology, use a particular MS device 650, etc.

[0120] The subject metrics 668 may be provided by a user entity and / or may be obtained from the input data 660 and / or the historical data 642 (eg, historical compound metrics 644, historical spectra 646, and / or historical capture operations 648).

[0121] Based on the input data 660, the data on which the NN 670 has already been trained, and / or the historical data 642 from the database 640, the analysis component 612 may generate an input data set. The input data set may be the basis of information on which the NN 670 may provide recommendations (e.g., when directed by the evaluation component 616).

[0122] 7, and still with reference to FIG. 6, after the step of acquiring input data 702 is completed by the capture component 610, input data processing 704 may be performed by the analysis component 712. That is, operation of the analysis process 714 by the analysis component 612 may result in information defining one or more relationships between one or more capture metrics 810 (e.g., but not limited to, ion quantity required for analysis, analysis temperature, analysis decomposition parameters, probability of detection, signal strength, predicted next signal strength, predicted fit to isotopic cluster, mass accuracy, delta time between estimated current time and expected elution time, and / or whether capture was captured for precursor in the first iteration) and one or more associated scores 716.

[0123] That is, as a result of the comparison and / or analysis by the analysis component 612 of the input data 660, the historical data 642, and / or the data on which the NN 670 has already been trained, the analysis component 612 may generate a set of precursors P={p1, p2, ...p N}), the method may output one or more relationships between different aspects of these data.

[0124] It should be noted that the analysis process 714 may be based on, and within the scope of, one or more requested target metrics 668, and may be performed by the analysis component 612, etc.

[0125] As a result of the analysis process 714, a scoring assignment 706 may be performed by the analysis component 612. That is, a score 716 may be assigned to one or more of the potential compounds (e.g., for each capture metric for each potential compound) for one or more capture metrics 810. That is, the score 716 may be assigned independently of the NN 670.

[0126] In one or more embodiments, the capture metrics 810 and / or the scores 716 may be determined by input from a user entity and / or may be obtained from the input data 660 and / or the historical data 642 .

[0127] In one or more embodiments, the scores 716 may be generated at least in part by another NN trained to generate scores that define relationships between precursors and capture metrics 810. In one example, an additional NN may be used to predict the next intensity point given a vector of previous intensities, which may be used as input (as initial input data 660 or as capture metrics 810). In one example, an additional NN may be used to infer whether there is evidence in the input data 660 or in the data resulting from the capture operation 680.

[0128] In one or more embodiments, the set of scores (p i , s1,s2,.s k}=E nxk ) can be a number between 0 and 1 (e.g., [0,1]), where n is the number of precursors being considered and k is the number of scores per precursor. The scores can take any value, but in most cases can be normalized to the range [0,1] or [-1,1], or by dividing by the predicted or measured mean and dividing by the predicted or measured standard deviation. In general, the score is a description of the environment in RL terms that, together with a reward feedback loop, allows the system to output a recommended action.

[0129] For example, and referring now in addition to key 850 for neural network operation output in FIG. 8, precursor P1 is entering the mass spectrometer and has a k-score associated with it including, but not limited to, a relatively high intensity, a high next predicted intensity, and a low delta time between the current elution time and the predicted elution time. The RL system has previously determined that it would be advantageous to capture a spectrum for P1, which is indicated in the final score having a value of 1. The other precursors in this example have scores that may indicate to the RL system a lower probability of their presence, such as lower intensity, worse mass accuracy, and a large delta between the current elution time and the predicted elution time, such that it would not be advantageous to capture a spectrum for them.

[0130] Based on these inputs, the NN determines the action a for each precursor. i The operation outputs, which in some embodiments can take values ​​of 0 to indicate not capturing a spectrum for the precursor, and 1 to indicate capturing a spectrum for the precursor. Alternatively, the operation output can be a continuous variable between 0 and 1, whereby 0 indicates no capture, while values ​​above 0 indicate that the spectrum has been captured for a certain amount of accumulation time, e.g., i xt max where t max is the maximum accumulation time. Acquisitions captured with 1.0 may take longer to acquire but may have higher quality (e.g., higher accuracy) than acquisitions with 0.1.

[0131] In one or more embodiments, one or more associated scores 716 may include and / or define one or more probabilities that one or more thresholds corresponding to one or more capture metrics (e.g., capture metrics 810) are met by a mass spectrometry operation performed on a compound or type of compound. As used herein, the term "satisfied" may mean reaching or exceeding a threshold. As used herein, one or more, such as each capture metric 810, may have a threshold associated therewith. For example, with reference to FIG. 8, the thresholds may include thresholds for match, signal strength, mass accuracy, probability of detection, delta time, etc.

[0132] 8, based on the scores 716 and the capture metrics 810, a dataset matrix, such as an exemplary score matrix 800, may be generated by the analysis component 612. As shown in FIG. 8, the matrix 800 includes a set of capture metrics 810 along vertical edges (e.g., rows) and a set of precursors (e.g., potential compounds to be captured / identified) along horizontal edges (e.g., columns).

[0133] 8 as a matrix (or table), the resulting data (e.g., captured metrics 810, scores 716, and the relationships between them) may be stored in any suitable format for use by NN 670. This resulting data may be stored in memory 604 and / or any other suitable location communicatively coupled to non-limiting system 600.

[0134] In one or more embodiments, the input dataset (e.g., dataset matrix) may be pre-generated and the NN 670 may already be trained on the input dataset, i.e., the input dataset may include one or more capture metrics for compounds 662 and / or types of compounds (e.g., capture metrics 810) and one or more associated scores 716 associated with the one or more capture metrics.

[0135] In one or more embodiments, the pre-generated or generated input data set may be updated, for example, by analysis component 612, such as by direction from metrics component 614, to take into account metrics of interest 668. That is, for example, as a result of metrics of interest 668, captured metrics 810 may be expanded, modified, and / or reduced (e.g., the list of captured metrics 810 in table 800 may be changed).

[0136] In one or more embodiments, the metrics component 614 and / or the analytics component 612 may change, modify, update, and / or generate input dataset dimensions based on one or more target metrics 668. For example, a user entity providing a target metric 668 may wish to focus on a particular high-level goal defined by the target metric. Based on that goal, the metrics component 614 may update, for example, but not be limited to, the score 716 or add or remove capture metrics 810. In another example, a precursor may be more or less important based on the target metric 668.

[0137] Based on the scores 716 (such as based on an aggregation or other calculation using the scores 716) and guided by the one or more metrics of interest 668, the NN may perform NN processing 708, resulting in one or more NN outputs 728. The NN outputs 728 may be in any suitable format such that they can be used by the materials analysis system 602. For example, the one or more NN outputs 728 may define a recommended acquisition operation 720, which may itself be defined by and / or include one or more operational settings (e.g., but not limited to, number of ions to use, exposure time, number of fragmentations, etc.).

[0138] In other words, based on the scores 716 (e.g., based on an aggregation or other calculation using the scores 716), guided by one or more metrics of interest 668, and based on one or more NN outputs 728, the evaluation component 616 may generate one or more recommendations (e.g., one or more recommended capture operations 720). In general, the recommended capture operations may be and / or include a recommendation to perform one or more separation and / or mass spectrometry operations. The one or more separation and / or mass spectrometry operations may directly or indirectly result in the capture of the compound.

[0139] In one or more embodiments, NN 670 may be limited to, or preferably instructed to select from an operation database 672 of available mass spectrometry operations, which may be capable of being performed using one or more mass spectrometry devices and / or other separation devices communicatively coupled to non-limiting system 600.

[0140] Operations database 672 may be included in and / or otherwise communicatively coupled to materials analysis system 602 .

[0141] As used herein, any one or more of the groups of any one or more of the historical capture operations 648, the recommended capture operations 720, and / or the prescribed capture operations 680 may include directly or indirectly obtaining capture of a compound using a mass spectrometry device or other separation device. Such operations 648 / 680 / 720 may include, but are not limited to, any one or more of fragmentation capture, MSn capture, selection of a particular mass spectrometry device, selection of a particular separation device, selection of device operation settings, selection of a time range for performing the capture, selection of an amount of ions to use, selection of an ion application schedule and / or ion application pattern to use, selection of two or more captures in parallel, selection of sequential capture, and / or selection of reagents.

[0142] For example, in one or more embodiments, the NN670 may recommend the use of fragmentation-based capture.

[0143] For another example, in one or more embodiments, the NN 670 may recommend acquisition of MS2 or MS3.

[0144] As a further example, with reference to FIG. 8 , with respect to focusing on predicted next signal strength acquisition metrics, an acquisition operation may be recommended for precursor P1 based on a high score, for precursor P2 based on a similarly high score, or for acquisition of two targets (e.g., P1 and P2) based on the two higher scores.

[0145] In one or more embodiments, the output of the NN 670 / evaluation component 616 may be based on historical data 642 that defines the decomposition of potential precursors or initial compounds 662 before a trapping operation 680 is performed. As a result, such input may relate to operational settings, for example, trapping and / or accumulation times, or the number of ions to accumulate during an isolation width.

[0146] The recommended capture action 720 may be defined by Equation 1:

[0147] Formula 1: A = {a i ∈[0,1]:1≦i≦n}, A is the set of precursors p i Action a corresponding to i , enumerated over variables i from precursor i=1 to n, although actions may take values ​​from 0 to 1, inclusive.

[0148] The recommended capture operation 720 may be and / or include one or more transformations of the NN output 728 and may therefore itself be defined by and / or include one or more operational settings (e.g., but not limited to, number of ions to accumulate, accumulation time, number of fragmentations, etc.).

[0149] The recommended acquisition operation 720 (and NN output 728) may satisfy one or more acquisition metrics and / or include one or more recommended operation settings. In one or more embodiments, multiple targets may be specified that correspond to compounds 662 expected to result from fragmentation and / or that correspond to one or more fragmented compounds from a previous spectrum (e.g., spectrum 665) while data is acquired by execution of the recommended acquisition operation 720.

[0150] The recommend capture operation 720 may include recommending a fragmentation capture that is a mass spectrometry / mass spectrometry (MS2) capture of the compound or a mass spectrometry / mass spectrometry / mass spectrometry (MS3) capture of the compound.

[0151] One or more recommended acquisition metrics and / or operational settings may define a recommended amount of resources (eg, time, number of ions, device type, particular device, etc.) to use for the recommended acquisition operation 720.

[0152] In one or more embodiments, the NN 670 , and thus the evaluation component 616 , may additionally or alternatively output instructions to perform a capture operation 680 .

[0153] In one or more embodiments, one or more types or particular capture operations 680 may be pre-approved (e.g., by a user entity or via a template being used) to be executed automatically without additional authorization. In one or more embodiments, one or more types or particular capture operations 680 may be indicated as requiring authorization to proceed with execution. In one or more embodiments, all capture operations 680 may be pre-approved.

[0154] In one or more embodiments, the NN 670, and thus the evaluation component 616, may additionally or alternatively output two or more recommendations, two or more output instructions, and / or two or more combinations of recommendations and output instructions at least partially in parallel with each other. Thus, the operation of the non-limiting system 600 may be scalable.

[0155] As a result of the output instruction or as a result of the approved recommendation 720, the execution component 618 may direct the execution of a mass spectrometry operation (e.g., capture operation 680) in a mass spectrometer (e.g., MS device 650) from which mass spectral results (including, e.g., composite result 682) may be obtained. Approval may be provided by a user entity, for example, using any suitable input and / or input device to the non-limiting system 600.

[0156] Additionally and / or alternatively, based on the execution of the capture operation 680, the execute component 618 may obtain one or more data, outputs, results, and / or composite results 682 resulting from the execution of the capture operation 680. In one or more embodiments, the output of the capture operation 680 may include the generation of one or more spectra that may be obtained by the execute component 618 and analyzed by the execute component 618 and / or the analyze component 612.

[0157] Referring now to the reward component 620, this component may generally execute a reward process 712 that may generate a reward indicator 722 resulting from the recommendation 720 of a mass spectrometry operation and / or resulting from the outcome of the execution of a capture operation 680. In other words, the reward component 620 may evaluate the recommended mass spectrometry operation 720 / performed capture operation 680 by generating a reward indicator 722. The reward indicator 722 may be based on the satisfaction, or non-satisfaction or partial satisfaction, of at least one of the one or more capture metrics 810 of the input data set and / or the satisfaction, or non-satisfaction or partial satisfaction, of one or more of the target metrics 668. That is, more generally, the reward process 712 may serve to reinforce outputs (e.g., the recommended capture operations 720 and the prescribed capture operations 680) that satisfy and / or satisfy one or more capture metrics 810 and / or the target metrics 668.

[0158] For example, the reward may be the output of a function, such as a condition score or action, associated with the NN being and / or providing the nonlinear function module. However, in one or more embodiments, additional NNs may be generated, trained, and used to assist the reward component 620 in generating the reward indicator 722.

[0159] For a specific example, referring briefly to FIG. 9, a table 900 of exemplary reward functions is shown. As shown, one or more reward indicators r resulting from one or more reward functions may be used for any capture operation and its outcome. As shown, each exemplary reward function is associated with a situation in which the reward function may be applicable for ease of understanding. Exemplary reward functions may include, but are not limited to, unique compound identification, completed peaks, experiments with identification of the same outcome, and / or any combination thereof.

[0160] For example, a simple reward function may include the sum of the number of unique peptide detections. As another example, the reward may depend on a capture metric such as the signal-to-noise-ratio (SNR) of the resulting spectra. In yet another example, additional value may be assigned for capturing multiple spectra across the elution profile of a compound. This may be achieved through time-localized "peak completion" analysis, or through higher level rewards such as the precision of measurements across multiple experiments. Value may also be given to detecting the same peptide or other compound type, class, and / or group in each iteration of a set of MS-based experiments.

[0161] Based on the reward indicator 722, whether positive or negative (eg, the term "negative" corresponds to a penalty), the update component 622 may direct a self-update of the NN 670.

[0162] In one or more embodiments, this update process 714 may result in one or more updates 724, including updates to weights used by the NN 670 and / or one or more adjustments to one or more capture metrics 810 based on the particular one or more reward indicators 722 generated.

[0163] In one or more embodiments, the update component 622 may update the NN (e.g., update weights used by the NN or update associated capture metrics 810) according to a set of reward outputs (e.g., reward indicators 722) amortized over time and obtained based on multiple generations (e.g., of recommendations 720) by the evaluation component 616.

[0164] Referring back now to Figure 7, for any MS-based experiment performed by non-limiting system 600, one or more additional iterations of one or more high-level processes 700 (Figure 7) may be performed. For example, after execution of any recommendation process 710, evaluation component 616 may determine whether additional recommendations 720 should be generated to satisfy target metrics 668 for the compound based on the mass spectral results (e.g., composite results 682) resulting from the recommendation 720. This determination may be made at any suitable frequency depending on the number of parallel recommendations for the same compound or different compounds, or compounds combined by subsequent fragmentation.

[0165] It should be noted that the reward step 712 and subsequent update step 714 may be performed at any suitable frequency, such as after the recommendation process 710, after a determination of the outcome of the capture operation 680 (eg, by the execution component 618), etc.

[0166] In one or more embodiments, one or more input datasets may be pre-generated and / or one or more NNs 670 may be trained on compounds or types of compounds, such as to provide templates for use by one or more user entities.

[0167] For example, a general methodology is envisaged that can be adapted to different types of experiments, labelling techniques and / or mass or cross-section analysis techniques. For each template, the sample should be well enough understood that the simulation can match the experimental results based on, but not limited to, the number of IDs, signal-to-noise ratio (SNR), measurement accuracy etc. The template may include instructions (e.g., as a target metric 668) for using a chromatogram library, a gas-phase fractionation approach, or actual liquid-phase fractionation, coupled with traditional DIA or DDA analysis. A DDA analysis with a narrow isolation window may be used, whereby it may be possible to generate actual MS / MS spectra for all compounds in the sample at any time. Simulation of LC-MS spectra may then involve a simple search for suitable spectra from this chromatogram library. Alternatively, predictions using available software tools may be used to generate MSn spectra and retention time ordering, and / or experimental information may be used to generate chemical noise and anchor predicted retention times. In one or more embodiments, the simulation of the experiment may utilize data augmentation to prevent overfitting and to cause the NN 670 to experience one or more different conditions. This data augmentation may take the form of random noise arising from the electrospray or detection process, as well as chromatographic drift and / or autosampler sample delivery error.

[0168] Regarding the general methodology, as described above, multiple trained agents (e.g., NN 670) may be generated and trained to cover common use cases, such as a parameter space including organisms, sample types, labeling techniques, separation columns, separation times, and / or analyzer types. For example, a user entity may specify a compound or compound type of human plasma labeled with TMT 10 plex using a C18 column, a 30 minute gradient, and an ion trap analyzer. These specifications may be applied as target metrics 668 or as requested capture metrics 810 and / or operational settings.

[0169] In the example of a particular set of samples or compounds that is not fully represented by multiple trained agents, the setup may involve gas-phase fraction characterization of the samples followed by training of an agent, likely starting from the most similar trained agent in the agent library. It may be possible for agents to be trained in real-time or to evolve over a series of priming experiments, but in general, from the perspective of the user entity, it may be preferable that the same agent is used for capture of all samples in the set.

[0170] The present disclosure now turns to an overview of one or more of the functions described above as being performed by non-limiting system 600. That is, consider an LC-MS situation in which there is a set n (e.g., potential precursors p) of potential precursors p that are known to be present in the sample or suspected to be present in the sample.

[0171] At a given time t, one or more MS or MSn acquisitions may be acquired (e.g., by acquisition component 610) and the spectra may be used as inputs to the processing facility of an agent (e.g., in NN 670). For example, an MS1 ​​spectrum or a set of MS / MS spectra may be acquired across the m / z range of the precursor.

[0172] The system (e.g., analysis component 612) may perform analysis such as cross-correlation of these spectra against a stored set of spectra (e.g., in database 640) to estimate a reference retention time, and / or may perform a search against an experimental or in silico library. Based on the analysis, each precursor may receive (e.g., by analysis component 612) a vector k of scores. The scores may correspond to capture metrics 810 such as probability of detection from the database search, signal strength, match to a predicted isotopic cluster, mass accuracy, predicted next signal strength, delta time between the estimated current time and the expected elution time, and / or whether a capture was captured for the precursor in the last iteration. The scores may include a history of the most recent m values ​​for each score.

[0173] An n x k matrix of scores for each precursor (e.g., exemplary score matrix 800) is one way of describing the environment, and data representing such a matrix may be input to neural network 670. The output of neural network 670 and evaluation component 616 may be a set of actions A, one for each potential precursor p, with values ​​[0,1] as defined by neural network action output key 850.

[0174] Through the execution component 618, one or more instruments (e.g., MS device 650) can generate spectra for each of the potential precursors, which can take a certain amount of time, which in effect changes the environmental conditions as new compounds elute off the column and enter the mass spectrometer (e.g., MS device 650) being used.

[0175] Based on one or more results of the one or more capture operations 680, a reward indicator 722 may be calculated (e.g., by the reward component 620) based on an analysis of the state of the system and the captured spectrum. The reward indicator 722 may be used by the update component 622 to update the neural network 670.

[0176] The next iteration of training and / or use of materials analysis system 602 may then be initiated by acquisition (e.g., by acquisition component 610) of a new batch of exploratory spectra (e.g., DIA spectra). Additionally or alternatively, analysis of the triggered spectra may be used to update the description of the environment for such next experiment. This may result in one or more changes to the input dataset (e.g., to one or more scores 716, acquisition metrics 810, and / or operational settings).

[0177] In relation to the above, it should be noted that acquiring exploratory spectra in the form of DIA may have one or more advantages in terms of data completeness, even with a fairly large isolation window. That is, even if a high-quality acquisition is never triggered, there may be at least some information for all precursors of interest. Alternatively, the exploratory spectrum may include a set of DIA spectra that change over time, or may include a narrow isolated targeted MS / MS acquisition for a compound predicted to elute at a particular time. That is, any type of acquisition operation 680 may trigger another acquisition operation 680 and / or another type of acquisition operation 680. Indeed, in one or more embodiments, the selection of an exploratory acquisition may be part of a set of operations available to the system (e.g., evaluation component 616).

[0178] The triggered spectrum may take the form of an MS2 spectrum or an MS3 spectrum. For example, the set of actions available to the system (e.g., to the evaluation component 616) may have a length of 2n, i.e., an option for acquiring an MS2 spectrum and an option for acquiring an MS3 spectrum. The system (e.g., the evaluation component 616) may determine which one or more acquisition actions 680 to recommend, prescribe, and / or take based on the available information and the state of the neural network 670.

[0179] As a result, an advantage of one or more embodiments described herein may be that, without limitation, the system may not only learn simple behaviors such as which acquisitions to take based on the current environment (e.g., compound environment), but such decisions may result in a way that takes into account higher level metrics of interest 668, such as acquiring spectra on top of LC peaks and / or focusing resources on compounds that are more likely to be quantifiable across multiple experiments.

[0180] As another overview of the above-mentioned components and their functions, reference is now made to Figures 10 and 11, which show a flow diagram of an exemplary non-limiting method 1000 that may facilitate a process for reinforcement learning-based mass spectrometer control according to one or more embodiments described herein, such as the non-limiting system 600 of Figure 6. Although the non-limiting method 1000 is described with respect to the non-limiting system 600 of Figure 6, the non-limiting method 1000 may also be applicable to other systems described herein, such as the non-limiting system 500 of Figure 5. Repeated descriptions of similar elements and / or processes used in each embodiment are omitted for the sake of brevity.

[0181] At 1002, the non-limiting method 1000 may include capturing data (e.g., input data 660) of a compound (e.g., compound 662) by a system operably coupled to a processor (e.g., capture component 610), where the data defines a first mass spectrometry spectrum (e.g., spectrum 665) of the compound.

[0182] At 1004, the non-limiting method 1000 may include capturing, by the system (e.g., metrics component 614), target metrics for the compound (e.g., target metrics 668), where a recommendation to perform a mass spectrometry operation (e.g., recommended capture operation 720) is based at least in part on the target metrics.

[0183] At 1006, the non-limiting method 1000 may include using a neural network (e.g., NN 670) trained on an input data set including capture metrics (e.g., compound metrics 664, capture metrics 810, and / or historical compound metrics 644) based on the data and using association scores (e.g., score 716) associated with the capture metrics to generate a recommendation (e.g., recommended capture operation 720) for performing a mass spectrometry operation on the compound by the system (e.g., evaluation component 616).

[0184] At 1008, the non-limiting method 1000 can include specifying, by the system (e.g., evaluation component 616), an amount of resources or operational settings (e.g., time, energy, selection width) to use for the mass spectrometry operation.

[0185] At 1010, the non-limiting method 1000 can include designating, by the system (e.g., evaluation component 616), a compound or a fragmented compound from the first mass spectrometry spectrum as a target for a mass spectrometry operation.

[0186] As shown at 1012, non-limiting method 1000 may include designating, by the system (e.g., evaluation component 616), a number of targets corresponding to a compound, to be fragmented from a compound, or corresponding to one or more fragmented compounds from the first mass spectrometry spectrum, for which additional data is acquired by performing a mass spectrometry operation.

[0187] At 1014, the non-limiting method 1000 may include, based on the recommendation, directing, by the system (e.g., execution component 618), the performance of a mass spectrometry operation in a mass spectrometer (e.g., MS device 650) to obtain a mass spectral result (e.g., composite result 682).

[0188] At 1016, the non-limiting method 1000 may include generating, by the system (e.g., reward component 620), a reward indicator (e.g., reward indicator 722) resulting from the recommendation of the mass spectrometry operation or from performing the recommended mass spectrometry operation.

[0189] At 1018, the non-limiting method 1000 may include updating, by the system (e.g., update component 622), one or more weights used by the NN based on the reward indicator or making adjustments to the capture metrics (e.g., capture metrics 810).

[0190] At 1020, the non-limiting method 1000 may include updating, by the system (e.g., update component 622), the neural network according to a set of reward indicators amortized over time and obtained based on multiple generation of multiple recommendations, including a recommendation to perform a mass spectrometry operation.

[0191] At 1022, the non-limiting method 1000 may include determining, by the system (e.g., the evaluation component 616), whether additional recommendations should be generated for the compound to satisfy the target metrics based on the mass spectrum results. If yes, the non-limiting method 1000 may return to step 1006. If no, the non-limiting method 1000 may proceed to end.

[0192] As another overview of the above-mentioned components and their functions, reference is now made to Figures 12 and 13, which show a flow diagram of an exemplary non-limiting method 1200 that may facilitate a process for reinforcement learning based mass spectrometer control according to one or more embodiments described herein, such as the non-limiting system 600 of Figure 6. Although the non-limiting method 1200 is described with respect to the non-limiting system 600 of Figure 6, the non-limiting method 1200 may also be applicable to other systems described herein, such as the non-limiting system 500 of Figure 5. Repeated descriptions of similar elements and / or processes used in each embodiment are omitted for the sake of brevity.

[0193] At 1202, the non-limiting method 1200 can include identifying, by a system operably coupled to a processor (e.g., capture component 610), a compound (e.g., compound 662) and a second compound (e.g., another compound 662) from a mass spectrometry spectrum (e.g., spectrum 665) defined by first data (e.g., input data 660).

[0194] At 1204, non-limiting method 1200 may include comparing, by a system (e.g., analysis component 612), first data about the compound (e.g., input data 660) to an input data set that includes one or more capture metrics for the compound (e.g., capture metrics 810 and / or historical data 642) and one or more associated scores (e.g., score 716) related to the one or more capture metrics.

[0195] At 1206, the non-limiting method 1200 may include generating, by the system (e.g., analysis component 612), a dataset matrix (e.g., exemplary score matrix 800) for the compound based on the input dataset and including one or more associated scores. In one or more embodiments, the one or more associated scores may define a probability that one or more thresholds corresponding to one or more capture metrics are met by one or more additional mass spectrometry operations performed on the compound.

[0196] At 1208, the non-limiting method 1200 may include generating, by the system (eg, the evaluation component 616), an associated score as a number between 0 and 1.

[0197] At 1210, the non-limiting method 1200 may include generating, by the system (e.g., evaluation component 616), a first recommendation (e.g., recommended capture operation 720) to perform a mass spectrometry operation (e.g., capture operation 680) on the compound based on the comparison and the obtained target metrics (e.g., target metrics 668) associated with the compound using a neural network (e.g., NN 670) trained on the input dataset.

[0198] At 1212, the non-limiting method 1200 may include generating, by the system (e.g., evaluation component 616), a first recommendation based on historical data (e.g., historical data 642) defining one or more results of capture of the compound caused by mass analysis of the compound.

[0199] As shown at 1214, non-limiting method 1200 may include correlating the input data set with metrics of interest by the system (e.g., update component 622) prior to using the neural network to generate the recommended mass spectrometry operations.

[0200] At 1215, the non-limiting method 1200 can include generating, by the system (e.g., the evaluation component 616 and / or the neural network 670), a first recommended mass spectrometry action that includes using a mass spectrometry device to directly or indirectly obtain capture of the compound.

[0201] At 1216, the non-limiting method 1200 can include selecting, by the system (e.g., the evaluation component 616 and / or the neural network 670), a first recommended mass spectrometry operation that includes a fragmented capture to capture the compound.

[0202] At 1217, non-limiting method 1200 may include selecting, by the system (e.g., evaluation component 616 and / or neural network 670), a first recommended mass spectrometry operation from an operation database (e.g., operation database 1272) of available mass spectrometry operations, where the available mass spectrometry operations can be performed using one or more mass spectrometry devices communicatively coupled to the system.

[0203] At 1218, the non-limiting method 1200 can include generating, in parallel, a first recommendation and a second recommendation (e.g., a second recommended action 720) for the second compound by the system (e.g., the evaluation component 616 and / or the neural network 670).

[0204] As shown at 1220, non-limiting method 1200 may include evaluating the recommended mass spectrometry operation by a system (e.g., reward component 620) resulting in a reward indicator (e.g., reward indicator 722) obtained by the system, where the reward indicator is used to update one or more weights used by the neural network.

[0205] At 1222, non-limiting method 1200 may include determining, by the system (e.g., evaluation component 616), whether additional recommendations should be generated for the compound to satisfy the target metrics based on the mass spectrum results. If yes, non-limiting method 1200 may return to step 1206. If no, non-limiting method 1200 may proceed to end.

[0206] As another overview of the above-mentioned components and their functions, reference is now made to Figures 14 and 15, which show a flow diagram of an exemplary non-limiting method 1400 that may facilitate a process for reinforcement learning based mass spectrometer control according to one or more embodiments described herein, such as the non-limiting system 600 of Figure 6. Although the non-limiting method 1400 is described with respect to the non-limiting system 600 of Figure 6, the non-limiting method 1400 may also be applicable to other systems described herein, such as the non-limiting system 500 of Figure 5. Repeated descriptions of similar elements and / or processes used in each embodiment are omitted for the sake of brevity.

[0207] At 1402, the non-limiting method 1400 may include generating, by a system operatively coupled to a processor (e.g., analysis component 612), an input data set (e.g., exemplary scoring matrix 800) including one or more capture metrics (e.g., capture metrics 810 and / or operational settings) and one or more association scores (e.g., scores 716) associated with the one or more capture metrics corresponding to a type of compound.

[0208] At 1404, the non-limiting method 1400 may generate, by the system (e.g., analysis component 612), an input dataset that includes one or more associated scores that include a probability that one or more thresholds corresponding to one or more capture metrics will be met by a mass spectrometry operation performed on a type of compound.

[0209] At 1406, the non-limiting method 1400 may include training, by the system (eg, the update component 622), a neural network (eg, the neural network 670) on the input data set.

[0210] At 1408, the non-limiting method 1400 may include generating, by the system (e.g., evaluation component 616), a recommended mass spectrometry operation (e.g., recommended capture operation 720) for obtaining second data (e.g., composite result 682) for a compound (e.g., compound 662) of the compound type by comparing the first data (e.g., input data 660) of the compound to an input dataset associated with the compound type (e.g., exemplary score matrix 800) using a neural network.

[0211] At 1410, the non-limiting method 1400 may include generating, by the system (e.g., evaluation component 616), a recommended mass spectrometry action based on target metrics (e.g., target metrics 668) for the compound types, where the target metrics are provided by a user entity to tune the functioning of the neural network.

[0212] As shown in 1412, non-limiting method 1400 can include specifying, by the system (e.g., evaluation component 616), an amount of resources (e.g., time, energy, selection width) to use for the recommended mass spectrometry operation based on historical data (e.g., historical data 642) defining compound capture caused by mass spectrometry of the compound type.

[0213] At 1414, the non-limiting method 1400 can include identifying, by the system (e.g., evaluation component 616), the compound identified or the fragmented compound from the mass spectrometry spectrum (e.g., spectrum 665) as a target for a recommended mass spectrometry operation, where the first data defines the mass spectrometry spectrum of the compound.

[0214] At 1416, the non-limiting method 1400 can include identifying, by the system (eg, the evaluation component 616), a set of two or more targets for acquiring second data by performing the recommended mass spectrometry operation.

[0215] At 1418, the non-limiting method 1400 can include generating, by the system (e.g., evaluation component 616), a recommended mass spectrometry operation that includes a fragmentation acquisition that is a mass spectrometry / mass spectrometry (MS2) capture of the compound or a mass spectrometry / mass spectrometry / mass spectrometry (MS3) capture of the compound.

[0216] At 1420, the non-limiting method 1400 may include determining, by the system (e.g., the evaluation component 616), based on the second data, whether additional recommended mass spectrometry operations should be generated to satisfy the target metrics for the compound. If yes, the non-limiting method 1400 may return to step 1408. If no, the non-limiting method 1400 may proceed to end.

[0217] Additional Overview For ease of explanation, the computer-implemented and non-computer-implemented methodologies provided herein are depicted and / or described as a series of acts. It should be understood that the present invention is not limited by the acts illustrated and / or by the order of acts, for example, acts may occur in one or more orders and / or simultaneously, as well as with other acts not shown and described herein. Furthermore, not all illustrated acts may be utilized to implement the computer-implemented and non-computer-implemented methodologies in accordance with the described subject matter. However, the computer-implemented and non-computer-implemented methodologies may alternatively be represented as a series of interrelated states via state diagrams or events. Additionally, the computer-implemented methodologies described below and throughout this specification may be stored in an article of manufacture for transmission and transfer of the computer-implemented methodology to a computer. The term article of manufacture, as used herein, is intended to encompass a computer program accessible from any computer-readable device or storage medium.

[0218] Systems and / or devices are described (and / or further described) herein with respect to interactions between one or more components. Such systems and / or components may include components or subcomponents specified herein, one or more of the specified components and / or subcomponents, and / or additional components. Subcomponents may be implemented as components that are communicatively coupled to other components rather than being included within a parent component. One or more components and / or subcomponents may be combined into a single component that provides an aggregate function. Components may interact with one or more other components not specifically described herein for brevity, but known by those skilled in the art.

[0219] In summary, one or more systems, computer programs, and / or computer-implemented methods provided herein relate to neural network control of a mass spectrometry process. The system may include a memory that stores computer-executable components and a processor that executes the computer-executable components. The computer-executable components may include an acquisition component that acquires data of a compound, the data defining a first mass spectrometry spectrum of the compound, an evaluation component that uses a neural network trained on an input data set including acquisition metrics based on the data and uses an association score associated with the acquisition metrics to generate a recommendation for performing a mass spectrometry operation for the compound, and an execution component that directs the performance of a mass spectrometry operation in a mass spectrometer based on the recommendation and obtains a mass spectrum result.

[0220] One or more embodiments disclosed herein may achieve improved performance compared to existing approaches. For example, based on RL training and historical data on which the NN may be RL trained, a system using a RL trained NN as described herein may use better compound specific capture behavior than may simply be pre-programmed by a management entity. That is, such a system may learn to recognize when resources should be consumed during a current capture and during future recommended or prescribed capture behaviors. As noted above, there may be precursor environments where extended capture times may elute more compounds, or where rapid capture times may be necessary given the large number of compounds entering the mass spectrometer.

[0221] Moreover, the embodiments described herein may advantageously provide focus / direction on multiple compounds at once, even based on different recommended capture actions, i.e., the embodiments described herein may use mixed optimization techniques to achieve the best results based on selected high-level goals, such as analytical specificity, improved accuracy of compound abundance estimation, and / or increased number of compound detections.

[0222] Furthermore, the embodiments described herein can be adapted to different types of experiments, labeling techniques, and / or mass or cross-section analysis techniques. That is, depending on the level of sample description or applicable high-level experimental goals, the framework described herein can be adapted to suit the sample. For example, rewards, high-level goals, available capture actions, etc. can be input into the system and NN, which is updated to operate within the range of the inputs.

[0223] Indeed, in view of one or more embodiments described herein, a practical application of one or more systems, computer-implemented methods, and / or computer programs described herein may be the ability to efficiently maximize the output of an MS-based experiment, regardless of whether the output goal corresponds to one or more of: specificity of analysis, increased probability of accuracy, and / or increased number of compound detections, among others. This application may be achieved without specifically setting all acquisition metrics and / or operational settings for the MS-based experiment. Rather, these acquisition metrics and / or operational settings may be generated by the RL-trained NN and corresponding material analysis system, as described herein, in addition to one or more acquisition recommendations. In this manner, one or more embodiments described herein may improve existing approaches to MS-based experiment control.

[0224] These are useful and practical applications of computers, thus providing enhanced (e.g., improved and / or optimized) materials analysis and compound data output (e.g., output regarding one or more identified compounds). Overall, such computerized tools may constitute tangible and tangible technological improvements in the field of materials analysis, particularly in materials analysis using separation and / or MS techniques.

[0225] Furthermore, one or more embodiments described herein may be used in real-world systems based on the teachings disclosed. For example, as described above, one or more embodiments described herein may perform MS-based experiments based on RL-based approaches for control of MS-based experiments even when acquisition metrics and / or instrument operation settings are not explicitly input into the systems described herein. Thus, the embodiments disclosed herein provide improvements to scientific instrument technology (e.g., improvements in the computer technology supporting such scientific instruments, among other things).

[0226] Additionally, the devices and / or methods described herein may be implemented in one or more domains to allow for scaled synthetic spectral output. Indeed, use of the systems described herein may be scalable, such as where multiple high-level goals (e.g., metrics of interest) can be promoted and / or where multiple compounds may be in the current focus of capture, at least simultaneously with each other.

[0227] Systems and / or devices are described (and / or further described) herein with respect to interactions between one or more components. Such systems and / or components may include the components or subcomponents specified herein, one or more of the specified components and / or subcomponents, and / or additional components. Subcomponents may be implemented as components that are communicatively coupled to other components rather than being included within a parent component. One or more components and / or subcomponents may be combined into a single component that provides an aggregate function. Components may interact with one or more other components not specifically described herein for brevity, but known by those skilled in the art.

[0228] One or more embodiments described herein may, in one or more embodiments, be essentially and / or inseparably linked to computer technology and cannot be implemented outside of a computing environment. For example, one or more processes performed by one or more embodiments described herein may provide for more efficient and even more feasible execution of programs and / or program instructions for, for example, material analysis based on RL-based control, as compared to existing systems and / or techniques. Systems, computer-implemented methods and / or computer programs providing for the execution of these processes are highly useful in the field of material analysis, such as those consisting of separation and / or MS instruments, and cannot be implemented as sensibly and practically in other than a computing environment.

[0229] One or more embodiments described herein may employ hardware and / or software to solve problems that are highly technical, not abstract, and cannot be performed as a series of mental acts by a human. For example, one or more embodiments described herein may provide this process such that a single human, or even thousands of humans, cannot efficiently, accurately, and / or effectively automatically generate recommended capture actions based on an RL-trained approach. Furthermore, neither the human mind nor a human with pen and paper can perform one or more of these processes as performed by one or more embodiments described herein.

[0230] In one or more embodiments, one or more of the processes described herein may be executed by one or more special-purpose computers (e.g., a special-purpose processing unit, a special-purpose classical computer, a special-purpose quantum computer, a special-purpose classical / quantum hybrid system, and / or another type of special-purpose computer) to perform defined tasks associated with one or more of the techniques described above. One or more embodiments described herein and / or components thereof may be used to solve new problems that arise through the adoption of advances in the aforementioned technologies, quantum computing systems, cloud computing systems, computer architectures, and / or other technologies.

[0231] One or more of the embodiments described herein may be fully operational to perform one or more other functions (e.g., fully powered on, fully running, and / or another function) while performing one or more of the operations described herein.

[0232] To provide a further overview, a list of embodiments and their features is provided below.

[0233] Item 1. A system comprising: a memory that stores computer-executable components; and a processor that executes the computer-executable components stored in the memory, the computer-executable components including: an acquisition component that acquires data for a compound, the data defining a first mass spectrometry spectrum of the compound; an evaluation component that generates a recommendation for performing a mass spectrometry operation for the compound based on the data using a neural network trained on an input data set including one or more acquisition metrics and using one or more relevance scores associated with the one or more acquisition metrics; and an execution component that directs performance of a mass spectrometry operation in a mass spectrometer based on the recommendation and obtains a mass spectral result.

[0234] Item 2. The system of item 1, wherein the evaluation component further specifies an amount of resources to use for the mass spectrometry operation.

[0235] Item 3. The system of items 1 or 2, wherein the evaluation component further designates compounds or fragmented compounds from the first mass spectrometry spectrum as targets for a mass spectrometry operation.

[0236] Item 4. The system of any one of items 1 to 3, wherein the evaluation component further specifies a plurality of targets corresponding to the compound, fragmented from the compound, or corresponding to one or more fragmented compounds from the first mass spectrometry spectrum, for which additional data is obtained by performing a mass spectrometry operation.

[0237] Item 5. The system of any one of items 1 to 4, further comprising a metrics component that obtains target metrics for the compound, wherein a recommendation for performing a mass spectrometry operation is based at least in part on the target metrics.

[0238] Item 6. The system of any one of items 1 to 5, further comprising: a reward component that generates a reward indicator resulting from the recommendation of a mass spectrometry operation or from the execution of the recommended mass spectrometry operation; and an update component that updates one or more weights used by the NN or performs adjustments to acquisition metrics based on the reward indicator.

[0239] Item 7. The system of any one of items 1 to 6, further comprising an update component that updates the neural network according to a set of reward indicators amortized over time and obtained based on a plurality of recommendations generated by the evaluation component, the set of reward indicators including a recommendation to perform a mass spectrometry operation.

[0240] Item 8. A computer-implemented method, comprising: comparing, by a system operatively coupled to a processor, first data for the compound to an input dataset including one or more capture metrics of the compound and one or more association scores associated with the one or more capture metrics; using a neural network trained on the input dataset on the obtained metrics of interest associated with the compound based on the comparison; and generating, by the system, a first recommendation for performing a recommended mass spectrometry operation for the compound, wherein the recommended mass spectrometry operation includes use of a mass spectrometry device to obtain capture of the compound.

[0241] Item 9. The computer-implemented method of item 8, further comprising: identifying, by the system, the compound and a second compound from the mass spectrometry spectrum defined by the first data; and generating, by the system, in parallel, the first recommendation and a second recommendation for the second compound.

[0242] Item 10. The computer-implemented method of item 8 or 9, wherein the first recommendation is based on historical data defining one or more results of capture of the compound caused by mass spectrometry or other separation analysis of the compound.

[0243] Item 11. The computer-implemented method of any one of items 8 to 10, further comprising: generating, by the system, a compound dataset matrix based on the input dataset, the compound dataset matrix including one or more associated scores, the one or more associated scores defining a probability that one or more thresholds corresponding to one or more capture metrics will be satisfied by one or more additional mass spectrometry operations performed on the compound.

[0244] Item 12. The computer-implemented method of any one of items 8 to 11, further comprising: evaluating the recommended mass spectrometry operations by the system and resulting in a reward indicator obtained by the system, the reward indicator being used to update one or more weights used by the neural network.

[0245] Item 13. The computer-implemented method of any one of items 8 to 12, further comprising generating, by the system, an associated score as a number between 0 and 1.

[0246] Item 14. The computer-implemented method of any one of items 8 to 13, further comprising correlating the input data set with metrics of interest by the system prior to using the neural network to generate the recommended mass spectrometry action.

[0247] Item 15. The computer-implemented method of any one of items 8 to 14, further comprising selecting, by the system, a recommended mass spectrometry operation that includes fragmented capture to capture the compound.

[0248] Item 16. The computer-implemented method of any one of items 8 to 15, further comprising: selecting, by the system, a recommended mass spectrometry operation using a neural network from an operational database of available mass spectrometry operations, wherein the available mass spectrometry operations are capable of being performed using one or more mass spectrometry devices communicatively coupled to the system.

[0249] Item 17. A computer program that facilitates a process for reinforcement learning based mass spectrometry control, the computer program comprising a computer readable storage medium having program instructions embodied therewith, the program instructions being executable by a processor to cause the processor to: generate, by the processor, an input data set including one or more acquisition metrics corresponding to a type of compound and one or more association scores associated with the one or more acquisition metrics, the one or more association scores defining a probability that one or more thresholds corresponding to the one or more acquisition metrics will be met by a mass spectrometry operation performed on the type of compound; train, by the processor, a neural network on the input data set; and generate, by the processor, a recommended mass spectrometry operation for obtaining second data for a compound of the type of compound by using the neural network to compare first data for the compound to the input data set associated with the type of compound.

[0250] Item 18. The computer program of item 17, wherein generating the recommended mass spectrometry action is further based on target metrics for the compound types, the target metrics being provided by a user entity to tune the functioning of the neural network.

[0251] Item 19. The computer program of item 17 or 18, wherein generating the recommended mass spectrometry operation further includes specifying, by the processor, an amount of resources to be used for the recommended mass spectrometry operation based on historical data defining compound capture caused by mass spectrometry of a type of compound.

[0252] Item 20. The computer program of any one of Items 17 to 19, wherein the first data defines a mass spectrometry spectrum of the compound, and generating a recommended mass spectrometry operation further includes designating, by the processor, the compound, or a fragmented compound identified from the mass spectrometry spectrum, as a target for the recommended mass spectrometry operation.

[0253] Item 21. The computer program of any one of Items 17 to 20, wherein generating the recommended mass spectrometry operation further includes specifying, by the system, a set of two or more targets for acquiring second data by performing the recommended mass spectrometry operation.

[0254] Item 22. The computer program of any one of items 17 to 21, wherein the recommended mass spectrometry operation includes a fragmentation capture that is a mass spectrometry / mass spectrometry (MS2) capture of the compound, or a mass spectrometry / mass spectrometry / mass spectrometry (MS3) capture of the compound.

[0255] Scientific Instrument System Description Referring now to FIG. 16, a detailed description of additional context for one or more embodiments described herein in FIGS. 1-15 is provided. One or more computing devices implementing any of the scientific instrument modules or methods disclosed herein may be part of a scientific instrument system. FIG. 16 illustrates a block diagram of an exemplary scientific instrument system 1600 in which one or more of the scientific instrument methods or other methods disclosed herein may be performed in accordance with various embodiments described herein. The scientific instrument modules and methods disclosed herein (e.g., scientific instrument module 100 of FIG. 1 and method 200 of FIG. 2) may be implemented by one or more of the scientific instruments 1610, user local computing device 1620, service local computing device 1630, and / or remote computing device 1640 of the scientific instrument system 1600.

[0256] Any of the scientific instruments 1610, the user local computing device 1620, the service local computing device 1630, and / or the remote computing device 1640 may include any of the embodiments of the computing device 400 described herein with reference to FIG. 4, and any of the scientific instruments 1610, the user local computing device 1620, the service local computing device 1630, and / or the remote computing device 1640 may take the form of any suitable one or more of the embodiments of the computing device 400 described herein with reference to FIG. 4.

[0257] One or more of the scientific instruments 1610, the user local computing device 1620, the service local computing device 1630, and / or the remote computing device 1640 may include a processing device 1602, a storage device 1604, and an interface device 1606. The processing device 1602 may take any suitable form, including any form of the processor 402 described herein with reference to FIG. 4. The processing devices 1602 included in different ones of the scientific instruments 1610, the user local computing device 1620, the service local computing device 1630, and / or the remote computing device 1640 may take the same form or different forms. The storage device 1604 may take any suitable form, including any form of the storage device 404 described herein with reference to FIG. 4. The storage devices 1604 included in different ones of the scientific instruments 1610, the user local computing device 1620, the service local computing device 1630, and / or the remote computing device 1640 may take the same form or different forms. The interface devices 1606 may take any suitable form, including any of the forms of the interface devices 406 described herein with reference to Figure 4. The interface devices 1606 included in different ones of the scientific instruments 1610, the user local computing devices 1620, the service local computing devices 1630, and / or the remote computing devices 1640 may take the same or different forms.

[0258] The scientific instruments 1610, the user local computing device 1620, the service local computing device 1630, and the remote computing device 1640 may communicate with other elements of the scientific instrument system 1600 via communication paths 1608. As shown, the communication paths 1608 may communicatively couple the interface devices 1606 of different elements of the scientific instrument system 1600 (e.g., according to any of the communication techniques described herein with reference to the interface device 406 of the computing device 400 of FIG. 4) and may be wired or wireless communication paths. Although the particular scientific instrument system 1600 shown in FIG. 16 includes communication paths between each pair of the scientific instruments 1610, the user local computing device 1620, the service local computing device 1630, and the remote computing device 1640, this "fully connected" implementation is merely exemplary and various embodiments may omit various ones of the communication paths 1608. For example, in one or more embodiments, the service local computing device 1630 may omit the direct communication path 1608 between its interface device 1606 and the interface device 1606 of the scientific instrument 1610, and instead communicate with the scientific instrument 1610 via the communication path 1608 between the service local computing device 1630 and the user local computing device 1620 and / or the communication path 1608 between the user local computing device 1620 and the scientific instrument 1610.

[0259] The scientific instrument 1610 may include any suitable scientific instrument, such as a separations instrument or MS instrument, or other instrument that facilitates material analysis.

[0260] The user local computing device 1620 may be a computing device that is proximate to a user of the scientific instrument 1610 (e.g., according to any of the embodiments of the computing device 400 described herein). In one or more embodiments, the user local computing device 1620 may also be proximate to the scientific instrument 1610, but need not be. For example, a user local computing device 1620 associated with a home, office, or other building associated with a user entity may be remote from but in communication with the scientific instrument 1610 such that the user entity may use the user local computing device 1620 to control and / or access data from the scientific instrument 1610. In one or more embodiments, the user local computing device 1620 may be a laptop, smartphone, or tablet device. In one or more embodiments, the user local computing device 1620 may be a portable computing device. In one or more embodiments, the user local computing device 1620 may be deployed in the field.

[0261] The service local computing device 1630 may be a computing device that is proximate to an entity that provides services to the scientific instrument 1610 (e.g., according to any of the embodiments of the computing device 400 described herein). For example, the service local computing device 1630 may be proximate to a manufacturer of the scientific instrument 1610 or a third party service company. In one or more embodiments, the service local computing device 1630 may communicate with the scientific instrument 1610, the user local computing device 1620, and / or the remote computing device 1640 (e.g., via a direct communication path 1608 or via multiple “indirect” communication paths 1608, as discussed above) to receive data regarding the operation of the scientific instrument 1610, the user local computing device 1620, and / or the remote computing device 1640 (e.g., results of self-diagnostic tests of the scientific instrument 1610, calibration coefficients used by the scientific instrument 1610, measurements of sensors associated with the scientific instrument 1610, etc.). In one or more embodiments, the service local computing device 1630 may communicate with the scientific instrument 1610, the user local computing device 1620, and / or the remote computing device 1640 (e.g., via a direct communication path 1608 or via multiple “indirect” communication paths 1608, as discussed above) and transmit data to the scientific instrument 1610, the user local computing device 1620, and / or the remote computing device 1640 (e.g., to update programmed instructions such as firmware in the scientific instrument 1610, to initiate performing a test or calibration sequence on the scientific instrument 1610, to update programmed instructions such as software in the user local computing device 1620 or the remote computing device 1640, etc.).A user entity of the scientific instrument 1610 may utilize the scientific instrument 1610 or user local computing device 1620 to communicate with the service local computing device 1630 to report problems with the scientific instrument 1610 or user local computing device 1620, to request a technician visit to improve the operation of the scientific instrument 1610, to order consumables or replacement parts associated with the scientific instrument 1610, or for other purposes.

[0262] The remote computing device 1640 may be a computing device that is located remotely from the scientific instrument 1610 and / or from the user local computing device 1620 (e.g., according to any of the embodiments of the computing device 400 described herein). In one or more embodiments, the remote computing device 1640 may be included in a data center or other large-scale server environment. In one or more embodiments, the remote computing device 1640 may include network-attached storage (e.g., as part of the storage device 1604). The remote computing device 1640 may store data generated by the scientific instrument 1610, perform analysis of data generated by the scientific instrument 1610 (e.g., according to programmed instructions), facilitate communications between the user local computing device 1620 and the scientific instrument 1610, and / or facilitate communications between the service local computing device 1630 and the scientific instrument 1610.

[0263] In one or more embodiments, one or more of the elements of the scientific instrument system 1600 illustrated in FIG. 16 may be omitted. Furthermore, in one or more embodiments, multiple ones of various ones of the elements of the scientific instrument system 1600 of FIG. 16 may be present. For example, the scientific instrument system 1600 may include multiple user local computing devices 1620 (e.g., different user local computing devices 1620 associated with different user entities or different locations). In another example, the scientific instrument system 1600 may include multiple scientific instruments 1610, all in communication with a service local computing device 1630 and / or a remote computing device 1640. In such an embodiment, the service local computing device 1630 may monitor these multiple scientific instruments 1610, and the service local computing device 1630 may cause updates or other information to be "broadcast" to the multiple scientific instruments 1610 simultaneously. Different scientific instruments 1610 in the scientific instrument system 1600 may be located near each other (e.g., in the same room) or far from each other (e.g., on different floors of a building, in different buildings, in different cities, etc.). In one or more embodiments, the scientific instruments 1610 may be connected to an Internet-of-Things (IoT) stack that allows command and control of the scientific instruments 1610 through web-based applications, virtual or augmented reality applications, mobile applications, and / or desktop applications. Any of these applications may be accessed by a user entity operating a user local computing device 1620 that is in communication with the scientific instruments 1610 through an intervening remote computing device 1640. In one or more embodiments, the scientific instruments 1610 may be sold by a manufacturer together with one or more associated user local computing devices 1620 as part of a local scientific instrument computing unit 1612.

[0264] In one or more embodiments, different ones of the scientific instruments 1610 included in the scientific instrument system 1600 may be different types of scientific instruments 1610. For example, one scientific instrument 1610 may be an EDS instrument and another scientific instrument 1610 may be an analytical instrument that analyzes the results of the EDS instrument. In some such embodiments, the remote computing device 1640 and / or the user local computing device 1620 may combine data from different types of scientific instruments 1610 included in the scientific instrument system 1600.

[0265] Example Operating Environment 17 is a schematic block diagram of an operating environment 1700 with which the described subject matter can interact. The operating environment 1700 includes one or more remote components 1710. The remote components 1710 can be hardware and / or software (e.g., threads, processes, computing devices). In one or more embodiments, the remote components 1710 can be a distributed computer system connected via a communications framework 1740 to a local autoscaling component and / or programs using resources of the distributed computer system. The communications framework 1740 can include wired network devices, wireless network devices, mobile devices, wearable devices, wireless access network devices, gateway devices, femtocell devices, servers, etc.

[0266] The operating environment 1700 also includes one or more local components 1720. The local components 1720 can be hardware and / or software (e.g., threads, processes, computing devices). In one or more embodiments, the local components 1720 can include auto-scaling components and / or programs that communicate / use remote resources such as 1710 and 1720 connected to a remotely located distributed computing system via a communications framework 1740.

[0267] Possible communication between the remote component 1710 and the local component 1720 may be in the form of data packets adapted to be transmitted between two or more computer processes. Another possible communication between the remote component 1710 and the local component 1720 may be in the form of circuit-switched data adapted to be transmitted between two or more computer processes in a radio time slot. The operating environment 1700 comprises a communication framework 1740 that may be employed to facilitate communication between the remote component 1710 and the local component 1720 and may comprise an air interface, such as an interface of a UMTS network over an LTE network. The remote component 1710 may include a hard drive, solid state drive, Subscriber Identity Module (SIM) card, electronic SIM, or other storage device that may be employed to store information on the remote component 1710 side of the communication framework 1740. The local component 1720 may be operably connected to one or more remote data storage devices 1750, such as a SIM, an eSIM, device memory, etc. Similarly, the local component 1720 may be operably connected to one or more local storage devices 1730, which may be used to store information on the local component 1720 side of the communications framework 1740.

[0268] Exemplary Computing Environment To provide additional context for the various embodiments described herein, Figure 18 and the following discussion are intended to provide a brief, general description of a suitable computing environment 1800 in which various embodiments of the embodiments described herein may be implemented. Although the embodiments have been described above in the general context of computer-executable instructions that may be executed on one or more computers, those skilled in the art will recognize that the embodiments may also be implemented in combination with other program modules and / or as a combination of hardware and software.

[0269] Generally, program modules include routines, programs, components, data structures, etc. that perform tasks or implement abstract data types. Additionally, the methods may be practiced with other computer system configurations including single-processor or multi-processor computer systems, minicomputers, mainframe computers, Internet of Things (IoT) devices, distributed computing systems, and personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc., each of which may be operatively coupled to one or more associated devices.

[0270] The illustrated embodiments of the present disclosure may also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0271] A computing device typically includes various media, which may include computer-readable storage media, machine-readable storage media, and / or communication media, although these two terms are used differently in this specification as follows. A computer-readable storage medium or machine-readable storage medium may be any available storage medium that can be accessed by a computer, including both volatile and non-volatile media, removable and non-removable media. By way of example and not limitation, a computer-readable storage medium or machine-readable storage medium may be implemented in association with any method or technology for storing information, such as computer-readable or machine-readable instructions, program modules, structured or unstructured data, etc.

[0272] A computer-readable storage medium may include, but is not limited to, Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, Compact Disk Read Only Memory (CD ROM), Digital Versatile Disk (DVD), Blu-ray Disc (BD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, solid state drives or other solid state storage devices, or other tangible and / or non-transitory media that may be used to store the desired information. In this regard, the terms "tangible" or "non-transitory" as applied to storage, memory, or computer-readable medium as modifiers exclude only the propagating transitory signal itself, and do not waive the right to all standard storage, memory, or computer-readable media that do not merely propagate the transitory signal itself.

[0273] The computer-readable storage medium may be accessed by one or more local or remote computing devices for various operations on the information stored by the medium, for example, via access requests, queries, or other data retrieval protocols.

[0274] Communication media typically embodies computer readable instructions, data structures, program modules, or other structured or unstructured data in a data signal, such as a modulated data signal, such as a carrier wave or other transport mechanism, and includes any information delivery or transmission media. The term "modulated data signal" or signal refers to a signal that has one or more characteristics set or changed in such a manner as to encode information in the signal or signals. By way of example, and not limitation, communication media includes wired media, such as a wired network or direct-wired connection, and wireless media, such as acoustic, RF, infrared and other wireless media.

[0275] 18, an exemplary computing environment 1800 in which one or more embodiments described herein may be implemented includes a computer 1802 including a processing unit 1804, a system memory 1806, and a system bus 1808. The system bus 1808 couples system components including, but not limited to, the system memory 1806 to the processing unit 1804. The processing unit 1804 may be any of a variety of commercially available processors. Dual microprocessors and other multi-processor architectures may also be used as the processing unit 1804.

[0276] The system bus 1808 may be any of several types of bus structures, which may further interconnect a memory bus, a peripheral bus, and a local bus (with or without a memory controller) using any of a variety of commercially available bus architectures. The system memory 1806 includes a ROM 1810 and a RAM 1812. The Basic Input / Output System (BIOS) may be stored in non-volatile memory, such as a ROM, erasable programmable read-only memory (EPROM), or EEPROM, but the BIOS contains the basic routines that help to transfer information between elements within the computer 1802, such as during start-up. The RAM 1812 may also include a high-speed RAM, such as a static RAM, for caching data.

[0277] The computer 1802 includes an internal hard disk drive. Drive, HDD) 1814 (e.g. EIDE (Enhanced Integrated Drive Electronics, Enhanced Integrated Drive Electronics (IDE), SATA (Serial The computing environment 1800 may further include a Serial Advanced Technology Attachment (SAT) and one or more external storage devices 1816 (e.g., a magnetic Floppy Disk Drive (FDD) 1816, a memory stick or flash drive reader, a memory card reader, etc.). An internal HDD 1814 is shown disposed within the computer 1802, although the internal HDD 1814 may also be configured for external use in a suitable chassis (not shown). Additionally, although not shown in the computing environment 1800, a solid state drive (SSD) may be used in addition to or in place of the HDD 1814.

[0278] Other internal or external storage devices may include at least one other storage device 1820 having a storage medium 1822 (e.g., a solid-state storage device, a non-volatile memory device, and / or an optical disk drive capable of reading from a removable medium such as a CD-ROM disk, a DVD, or a BD). The external storage device 1816 may be realized by a networked virtual machine. The HDD 1814, the external storage device 1816, and the storage device (e.g., drive) 1820 may be connected to the system bus 1808 by a HDD interface 1824, an external storage interface 1826, and a drive interface 1828, respectively.

[0279] The drives and their associated computer-readable storage media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. In the case of computer 1802, the drives and storage media accommodate the storage of any data in a suitable digital format. Although the above description of computer-readable storage media refers to each type of storage device, other types of storage media readable by a computer, whether currently existing or developed in the future, may also be used in the exemplary operating environment, and further, any such storage media may include computer-executable instructions for performing the methods described herein.

[0280] A number of program modules may be stored in the drives and RAM 1812, including an operating system 1830, one or more application programs 1832, other program modules 1834, and program data 1836. All or portions of the operating system, applications, modules, and / or data may also be cached in RAM 1812. The systems and methods described herein may be implemented using various commercially available operating systems or combinations of operating systems.

[0281] Computer 1802 may optionally include emulation technology. For example, a hypervisor (not shown) or other intermediary may emulate the hardware environment of operating system 1830, where the emulated hardware may optionally differ from the hardware shown in FIG. 18. In such an embodiment, operating system 1830 may comprise a virtual machine (VM) of a number of VMs hosted on computer 1802. Additionally, operating system 1830 may provide a runtime environment, such as the Java Runtime Environment or the .NET Framework, for application 1832. The runtime environment is a consistent execution environment that allows application 1832 to run on any operating system that includes the runtime environment. Similarly, operating system 1830 may support containers, but application 1832 may be in the form of a container, which is a lightweight, standalone, executable package of software that includes, for example, code, runtime, system tools, system libraries, and application settings.

[0282] Additionally, computer 1802 may be enabled with a security module, such as a Trusted Processing Module (TPM). For example, in a TPM, a boot component may then hash the boot component in time and wait for the result to match a secure value before loading the next boot component. This process may occur at any layer within the code execution stack of computer 1802, for example, applied at the application execution level or at the Operating System (OS) kernel level, thereby enabling security at any level of code execution.

[0283] A user entity may enter commands and information into the computer 1802 through one or more wired / wireless input devices, such as a keyboard 1838, a touch screen 1840, and a pointing device such as a mouse 1842. Other input devices (not shown) may include a microphone, an infrared (IR) remote control, a radio frequency (RF) remote control, or other remote control, a joystick, a virtual reality controller and / or a virtual reality headset, a game pad, a stylus pen, an image input device such as a camera, a gesture sensor input device, a visual motion sensor input device, an emotion or face detection device, a biometric input device such as a fingerprint or iris scanner, etc. These and other input devices are often connected to the processing unit 1804 through an input device interface 1844 that may be coupled to the system bus 1808, but may also be connected by other interfaces, such as a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, a BLUETOOTH interface, etc.

[0284] A monitor 1846 or other type of display device may also be connected to the system bus 1808 via an interface, such as a video adapter 1848. In addition to the monitor 1846, computers typically include other peripheral output devices (not shown), such as speakers, printers, etc.

[0285] The computer 1802 may operate in a networked environment using logical connections over wired and / or wireless communications with one or more remote computers, such as a remote computer 1850. The remote computer 1850 may be a workstation, a server computer, a router, a personal computer, a portable computer, a microprocessor-based entertainment device, a peer device, or other common network node, and typically includes many or all of the elements described above with respect to the computer 1802, although for purposes of brevity, only a memory / storage device 1852 is shown. The logical connections shown include wired / wireless connections to a local area network (LAN) 1854 and / or a wide area network (e.g., a wide area network (WAN) 1856). Such LAN and WAN networking environments are commonplace in offices and businesses, facilitating enterprise-wide computer networks, such as intranets, all of which may connect to a global communications network, such as the Internet.

[0286] When used in a LAN networking environment, the computer 1802 may be connected to the local network 1854 via a wired and / or wireless communication network interface or adapter 1858. The adapter 1858 may facilitate wired or wireless communication to the LAN 1854, which may also include a wireless Access Point (AP) disposed thereon for communicating with the adapter 1858 in a wireless mode.

[0287] When used in a WAN networking environment, the computer 1802 may include a modem 1860 or may be connected to a communications server on the WAN 1856 via other means for establishing communications over the WAN 1856, such as the Internet. The modem 1860 may be an internal or external device, and a wired or wireless device, and may be connected to the system bus 1808 via the input device interface 1844. In a networked environment, program modules depicted relative to the computer 1802, or portions thereof, may be stored in the remote memory / storage device 1852. The network connections shown are exemplary and other means of establishing a communications link between the computers may be used.

[0288] When used in either a LAN or WAN networking environment, computer 1802 may access a cloud storage system or other network-based storage system in addition to or in place of external storage device 1816, as described above. In general, a connection between computer 1802 and a cloud storage system may be established via LAN 1854 or WAN 1856, for example, by adapter 1858 or modem 1860, respectively. Upon connecting computer 1802 to an associated cloud storage system, external storage interface 1826, with the aid of adapter 1858 and / or modem 1860, may manage storage provided by the cloud storage system as well as other types of external storage. For example, external storage interface 1826 may be configured to provide access to cloud storage sources as if those sources were physically connected to computer 1802.

[0289] The computer 1802 may be operable to communicate with any wireless device or entity operatively disposed in wireless communication, such as printers, scanners, desktop and / or portable computers, portable data assistants, communications satellites, any equipment or location associated with a radio detectable tag (e.g., a kiosk, a newsstand, a store shelf, etc.), and a telephone. This may include Wireless Fidelity (Wi-Fi) and BLUETOOTH® wireless technologies. Thus, communication may be a defined structure similar to an existing network, or simply ad-hoc communication between at least two devices.

[0290] Additional Information The embodiments described herein may relate to one or more of a system, a method, an apparatus, and / or a computer program at any possible level of technical detail of integration. The computer program may include a computer-readable storage medium having computer-readable program instructions for causing a processor to execute aspects of one or more of the embodiments described herein. The computer-readable storage medium may be a tangible device that may hold and store instructions for use by an instruction execution device. The computer-readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a superconducting storage device, and / or any suitable combination thereof. A non-exhaustive list of more specific examples of computer readable storage media may also include: portable computer diskettes, hard disks, random access memories (RAMs), read only memories (ROMs), erasable programmable read only memories (EPROMs or flash memories), static random access memories (SRAMs), portable compact disk read only memories (CD-ROMs), digital versatile disks (DVDs), memory sticks, floppy disks, mechanically encoded devices such as punch cards or raised structures in grooves on which instructions are recorded, and / or any suitable combination of the foregoing. Computer readable storage media as used herein should not be construed as being ephemeral signals per se, such as electric signals transmitted over wires, electromagnetic waves and / or other freely propagating electromagnetic waves, electromagnetic waves propagating through wave guides and / or other transmission media (e.g., light pulses passing through fiber optic cables), and / or other signals transmitted over wires.

[0291] The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to each computing / processing device and / or to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include copper transmission cables, optical transmission fiber, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing / processing device. The computer readable program instructions for carrying out the operations of one or more embodiments described herein may be source code and / or object code written in any combination of one or more programming languages, including assembler instructions, Instruction-Set-Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, and / or object-oriented programming languages ​​such as Smalltalk, C++, etc., and / or procedural programming languages ​​such as the "C" programming language and / or similar programming languages. The computer readable program instructions may be executed entirely on the computer, partially on the computer, as a stand-alone software package, partially on the computer, and / or partially on a remote computer, or entirely on a remote computer and / or server. In the latter scenario, the remote computer may be connected to the computer via any type of network, including a Local Area Network (LAN) and / or a Wide Area Network (WAN), and / or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider).In one or more embodiments, electronic circuitry including, for example, programmable logic circuitry, Field-Programmable Gate Arrays (FPGAs) and / or Programmable Logic Arrays (PLAs) may execute computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry to perform aspects of one or more embodiments described herein.

[0292] Aspects of one or more embodiments described herein are described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer programs according to one or more embodiments described herein. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, may be implemented by computer-readable program instructions. These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, and / or other programmable data processing apparatus to generate a machine such that the instructions executed via the processor of the computer or other programmable data processing apparatus may create means for implementing the functions / operations specified in one or more blocks of the flowcharts and / or block diagrams. These computer-readable program instructions may be stored in a computer-readable storage medium that may direct a computer, programmable data processing apparatus, and / or other device to function in a particular manner, whereby the computer-readable storage medium having instructions stored therein may include an article of manufacture containing instructions that may implement aspects of the functions / operations specified in one or more blocks of the flowcharts and / or block diagrams. The computer-readable program instructions may also be loaded into a computer, other programmable data processing apparatus, and / or other device to cause a series of operational acts to be executed on the computer, other programmable apparatus, and / or other device to generate a computer-implemented process whereby the instructions executing on the computer, other programmable apparatus, and / or other device implement the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0293] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and / or operation of possible implementations of systems, computer-implementable methods, and / or computer programs according to one or more embodiments described herein. In this regard, each block in the flowcharts or block diagrams may represent a module, segment, and / or portion of an instruction, which includes one or more executable instructions for implementing the specified logical function. In one or more alternative implementations, the functions described in the blocks may occur in an order different from that described in the figures. For example, two blocks shown in succession may be executed substantially simultaneously and / or the blocks may sometimes be executed in the reverse order, depending on the functionality involved. It should also be noted that each block of the block diagrams and / or flowchart diagrams, and / or combinations of blocks in the block diagrams and / or flowchart diagrams, may be implemented by a special purpose hardware-based system that may perform the specified functions and / or acts and / or execute one or more combinations of special purpose hardware and / or computer instructions.

[0294] Although the subject matter has been described above in the general context of computer-executable instructions of a computer program executing on one and / or more computers, those skilled in the art will recognize that one or more embodiments herein may also be implemented at least partially in parallel with one or more other program modules. Generally, a program module includes routines, programs, components, and / or data structures that perform particular tasks and / or implement particular abstract data types. Furthermore, the computer-implemented methods described above may be practiced with single-processor and / or multi-processor computer systems, mini-computing devices, mainframe computers, and other computer system configurations including computers, handheld computing devices (e.g., PDAs (Personal Digital Assistants), phones), and / or microprocessor-based or programmable consumer and / or industrial electronic devices. The illustrated aspects may also be practiced in distributed computing environments where tasks are performed by remote processing devices linked through a communications network. However, one or more aspects, if not all, of one or more of the embodiments described herein may be practiced on stand-alone computers. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

[0295] As used in this application, the terms "component," "system," "platform," and / or "interface" may refer to and / or include computer-related entities or entities associated with an operating machine having one or more particular functions. The entities described herein may be either hardware, a combination of hardware and software, software, or software in execution. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, an executable, a thread of execution, a program, and / or a computer. By way of example, both an application running on a server and the server may be a component. One or more components may reside within a process and / or thread of execution, while a component may be localized on one computer and / or distributed between two or more computers. In another example, each component may execute from various computer readable media having various data structures stored thereon. The components may communicate via local and / or remote processes, such as according to signals comprising one or more data packets (e.g., data from one component interacting across a network such as the Internet with a local system, another component in a distributed system, and / or other systems via signals). As another example, a component may be a device having a particular functionality provided by mechanical parts operated by electrical or electronic circuits operated by software and / or firmware applications executed by a processor. In such cases, the processor may be internal and / or external to the device and may execute at least a portion of the software and / or firmware applications.As yet another example, a component may be a device that provides a particular functionality through electronic components without mechanical parts, but the electronic component may include a processor and / or other means for executing software and / or firmware that at least partially provides the functionality of the electronic component. In one aspect, a component may emulate an electronic component, for example, via a virtual machine in a cloud computing system.

[0296] As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise stated or clear from the context, "X employs A or B" is intended to mean all natural inclusive permutations. That is, if X employs A, then X employs B, or if X employs both A and B, then "X employs A or B" is satisfied in any of the foregoing cases. Furthermore, the articles "a" and "an" as used in this specification and the accompanying drawings should be generally construed to mean "one or more" unless otherwise stated or clear from the context to indicate the singular form. As used herein, the terms "example" and / or "exemplary" are utilized to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter described herein is not intended to be limited by such examples. Moreover, any aspect or design described herein as "example" and / or "exemplary" is not necessarily to be construed as preferred or advantageous over other aspects or designs, and is not meant to exclude equivalent exemplary structures and techniques known to those skilled in the art.

[0297] As used herein, the term "processor" may refer to substantially any computing processing unit and / or device, including, but not limited to, a single core processor, a single processor with software multithreading execution capability, a multicore processor, a multicore processor with software multithreading execution capability, a multicore processor with hardware multithreading technology, a parallel platform, and / or a parallel platform with distributed shared memory. Additionally, a processor may refer to an integrated circuit, an application specific integrated circuit (ASIC), a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic controller (PLC), a complex programmable logic device (CPLD), discrete gate or transistor logic, discrete hardware components, and / or any combination thereof designed to perform the functions described herein. Additionally, a processor may utilize nanoscale architectures, such as, but not limited to, molecular and quantum dot-based transistors, switches, and / or gates to optimize space usage and / or improve the performance of associated devices. A processor may be implemented as a combination of computing processing units.

[0298] As used herein, terms such as "store," "storage," "data store," "data storage," "database," and substantially any other information storage component related to the operation and functionality of a component are utilized to refer to a "memory component," an entity embodied in a memory, or a component that includes a memory. The memory and / or memory components described herein may be either volatile or nonvolatile memory, or may include both volatile and nonvolatile memory. By way of example and not limitation, nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM), flash memory, and / or nonvolatile random access memory (RAM) (e.g., Ferroelectric RAM (FeRAM)). Volatile memory may include, for example, RAM, which may function as external cache memory. By way of example and not limitation, the RAM may be synchronous RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (Double Data Rate SDRAM), or the like. Data Rate SDRAM, DDR SDRAM, enhanced SDRAM, ESDRAM, Synchlink DRAM, SLDRAM, Direct Rambus RAM Rambus RAM, DRRAM, Direct Rambus Dynamic RAM (Direct Rambus Dynamic RAM (DRDRAM) and / or Rambus Dynamic RAM (Rambus Dynamic Memory may come in many forms, such as RAM, RDRAM, and the like. Additionally, the memory components of the systems and / or computer-implemented methods described herein are intended to include, but are not limited to, these and / or any other suitable types of memory.

[0299] The foregoing includes merely examples of systems and computer-implemented methods. Of course, for purposes of describing one or more embodiments, it is not possible to describe every conceivable combination of components and / or computer-implemented methods, but one of ordinary skill in the art may recognize that many further combinations and / or permutations of one or more embodiments are possible. Moreover, to the extent that terms such as "includes," "has," "possesses," and the like are used in the detailed description, claims, appendices, and / or drawings, such terms are intended to be as inclusive as the term "comprising" as "comprising" is interpreted when used as a transitional term in the claims.

[0300] In describing various embodiments, references may be made to "an embodiment," "various embodiments," "one or more embodiments," or the like. The phrases "in some embodiments," "in some embodiments," and / or "some embodiments" may be used, each of which may refer to one or more of the same or different embodiments.

[0301] The description of various embodiments is presented for illustrative purposes, but is not intended to be exhaustive or limited to the embodiments described herein. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terms used herein have been selected to best explain the principles of the embodiments, practical applications and / or technical improvements to the art found in the marketplace, and / or to enable those skilled in the art to understand the embodiments described herein.

Claims

1. 1. A system comprising: a memory for storing computer executable components; a processor for executing the computer-executable components stored in the memory, the computer-executable components comprising: a capture component for capturing data for a compound, the data defining a first mass spectrometry spectrum of the compound; an evaluation component that uses a neural network trained on an input data set including acquisition metrics based on the data, uses an association score associated with the acquisition metrics, and generates a recommendation to perform a mass spectrometry operation on the compound; an execution component that directs execution of the mass spectrometry operation in a mass spectrometer based on the recommendation and obtains a mass spectral result.

2. The system of claim 1 , wherein the evaluation component further specifies an amount of resources to use for the mass spectrometry operation.

3. The system of claim 1 , wherein the evaluation component further designates the compound or a fragmented compound from the first mass spectrometry spectrum as a target for the mass spectrometry operation.

4. 2. The system of claim 1, wherein the evaluation component further specifies a plurality of targets corresponding to the compound, fragmented from the compound, or corresponding to one or more fragmented compounds from the first mass spectrometry spectrum, and obtains additional data therefor by performing the mass spectrometry operation.

5. The system of claim 1 , further comprising a metrics component that obtains metrics of interest for the compound, the recommendation for performing the mass spectrometry operation being based at least in part on the metrics of interest.

6. a reward component that generates a reward indicator resulting from the recommendation of the mass spectrometry operation or from performance of the recommended mass spectrometry operation; 2. The system of claim 1, further comprising: an update component that updates one or more weights used by the neural network or performs adjustments to the capture metrics based on the reward indicator.

7. 2. The system of claim 1, further comprising: an update component that updates the neural network according to a set of reward indicators amortized over time and obtained based on multiple recommendations generated by the evaluation component, the recommendation to perform the mass spectrometry operation.

8. 1. A computer-implemented method comprising: comparing, by a system operatively coupled to a processor, a first data set for the compound to an input data set for the compound, the input data set including one or more capture metrics and one or more association scores associated with the one or more capture metrics; generating, by the system based on the comparison and the obtained target metrics associated with the compound and using a neural network trained on the input data set, a first recommendation for performing a recommended mass spectrometry operation on the compound; A computer-implemented method, wherein the recommended mass spectrometry action comprises use of a mass spectrometry device to obtain capture of the compound.

9. identifying, by the system, the compound and a second compound from a mass spectrometry spectrum defined by the first data; 10. The computer-implemented method of claim 8, further comprising generating, by the system, the first recommendation and a second recommendation for the second compound in parallel.

10. The computer-implemented method of claim 8 , wherein the first recommendation is based on historical data defining one or more outcomes of capture of the compound caused by mass spectrometry or other separation analysis of the compound.

11. 9. The computer-implemented method of claim 8, further comprising: generating, by the system, a dataset matrix for the compound based on the input dataset, the dataset matrix including the one or more associated scores, the one or more associated scores defining a probability that one or more thresholds corresponding to the one or more capture metrics will be met by one or more additional mass spectrometry operations performed on the compound.

12. 9. The computer-implemented method of claim 8, further comprising: evaluating, by the system, the recommended mass spectrometry operations and providing a reward indicator obtained by the system, the reward indicator being used to update one or more weights used by the neural network.

13. The computer-implemented method of claim 8 , further comprising generating, by the system, an associated score as a number between 0 and 1.

14. 10. The computer-implemented method of claim 8, further comprising correlating, by the system, the input data set to the metrics of interest prior to using the neural network to generate the recommended mass spectrometry action.

15. The computer-implemented method of claim 8 , further comprising selecting, by the system, a recommended mass spectrometry operation that includes a fragmented capture that captures the compound.

16. 9. The computer-implemented method of claim 8, further comprising: selecting, by the system, the recommended mass spectrometry operation using the neural network from an operational database of available mass spectrometry operations, wherein the available mass spectrometry operations are capable of being performed using one or more mass spectrometry devices communicatively coupled to the system.

17. 1. A computer program that facilitates a process for reinforcement learning based mass spectrometry control, the computer program comprising a computer readable storage medium having program instructions embodied therein, the program instructions being executable by a processor, the processor comprising: generating, by the processor, an input data set comprising one or more capture metrics corresponding to a type of compound and one or more association scores associated with the one or more capture metrics; generating one or more associated scores that define a probability that one or more thresholds corresponding to the one or more capture metrics will be met by a mass spectrometry operation performed on the compound type; training, by said processor, a neural network on said input data set; and generating, by the processor, a recommended mass spectrometry operation for acquiring second data for a compound of the compound type by using the neural network to compare first data for the compound to the input data set associated with the compound type.

18. 20. The computer program product of claim 17, wherein generating the recommended mass spectrometry action is further based on target metrics for the compound type, the target metrics being provided by a user entity to tune function of the neural network.

19. 20. The computer program product of claim 17, wherein generating the recommended mass spectrometry operation further comprises specifying, by the processor, an amount of resources to use for the recommended mass spectrometry operation based on historical data defining capture of the compound caused by mass spectrometry of the compound type.

20. 20. The computer program product of claim 17, wherein the recommended mass spectrometry operation comprises a fragmentation capture that is a mass spectrometry / mass spectrometry (MS2) capture for the compound, or a mass spectrometry / mass spectrometry / mass spectrometry (MS3) capture for the compound.

Images