Trained neural network model for parameterless peak detection

Abstract

Scientific instrument support systems and related methods, computing devices, and computer readable media are disclosed herein. For example, in some embodiments, a chromatograph support apparatus may include: first logic to receive a chromatogram data set; second logic to determine one or more peak positions of the chromatogram data set by processing the chromatogram data set via a machine learning computational model to determine a plurality of input parameter values that fit a Gaussian curve of the chromatogram data set; and a third logic to provide the one or more peak positions for further small molecule liquid chromatography mass spectrometry (LC / MS) processing.

Description

Background Art

[0001] Chromatography is a technique for separating the components of a sample mixture by exploiting the different properties of the components when they interact with other materials. Types of chromatography include gas chromatography and liquid chromatography, among others. BRIEF DESCRIPTION OF THE DRAWINGS

[0002] The embodiment will be readily understood by the following detailed description in conjunction with the accompanying drawings. For ease of description, the same reference numerals designate the same structural elements. The embodiment is illustrated in the various figures of the accompanying drawings by way of example and not by way of limitation.

[0003] Figure 1 is a block diagram of an exemplary chromatograph support module for determining peak positions of a chromatogram dataset, according to various embodiments.

[0004] Figure 2A is a flow chart of an exemplary method for determining peak positions of a chromatogram dataset, according to various embodiments.

[0005] Figure 2B is a flow chart of an exemplary method of generating and selecting a machine learning computational model for determining peak positions of a chromatogram dataset, according to various embodiments.

[0006] Figures 3A to 3D Depicted are example graphical representations for training a neural network to determine peak locations for a chromatogram dataset, according to various embodiments.

[0007] Figures 4A to 4F Depicted is a graphical representation of a performance comparison of various approaches for training a neural network to determine peak locations for a chromatogram dataset, according to various embodiments.

[0008] Figure 5 is an example of a graphical user interface that may be used to perform some or all of the supporting methods disclosed herein, according to various embodiments.

[0009] Figure 6 is a block diagram of an exemplary computing device that may perform some or all of the chromatograph support methods disclosed herein, according to various embodiments.

[0010] Figure 7 is a block diagram of an exemplary chromatography support system in which some or all of the chromatography support methods disclosed herein may be performed, according to various embodiments. DETAILED DESCRIPTION

[0011] Disclosed herein are scientific instrument support systems and related methods, computing devices, and computer-readable media. For example, in some embodiments, a chromatogram support device may include: first logic for receiving a chromatogram dataset; second logic for determining one or more peak positions of the chromatogram dataset by processing the chromatogram dataset through a machine learning computational model to determine a plurality of input parameter values for fitting a Gaussian curve to the chromatogram dataset; and third logic for providing the one or more peak positions for further small molecule liquid chromatography mass spectrometry (LC / MS) processing.

[0012] The scientific instrument support embodiments disclosed herein can achieve improved performance relative to conventional methods. As discussed in further detail below, non-targeted metabolomics studies using LC / MS are often characterized by complex and challenging data sets that require a set of algorithms to extract the data into useful information for the end user. Two major challenges of LC / MS include: 1) improving the accuracy of results using increasingly complex samples, and 2) reducing the computational time of data processing algorithms. To address these challenges, the described system employs a neural network-assisted chromatographic peak detector for the LC / MS data processing pipeline. In addition, many current data processing workflows include multiple data analysis stages that aim to locate and identify compounds in the vast amount of instrumental data generated by modern LC / MS instruments.

[0013] Therefore, the chromatograph support embodiment disclosed herein may include the deep learning technology of metabolomics and small molecule LC / MS data processing by utilizing feedforward neural network inside the chromatographic peak detector, which is used for the application in metabolomics and small molecule data. More specifically, in some embodiments, the described system uses machine learning components for peak detection algorithm to estimate the parameter values of the Gaussian curve fitting target data. In some embodiments, the peak detection algorithm includes an empirical transformed Gaussian function (ETG), a polynomial modified Gaussian function (PMG), a generalized exponential modified Gaussian function (GEMG) or a mixture (EGH) of a Gaussian and truncated exponential function. In some embodiments, the system replaces the traditional multivariate optimization algorithm by adopting a trained neural network to determine the parameter values of the Gaussian curve. Thus, the embodiments disclosed herein provide improvements to scientific instrument technology (e.g., improvements in computer technology supporting such scientific instruments, and other improvements).

[0014] In some embodiments, the engine that drives small molecule LC / MS data processing (small molecule workflow) is called component analysis (CE). Peak detection is a key optimization step in this workflow because it affects downstream steps. In some embodiments, the peak detector used by CE includes parameter-free peak detection (PPD). Typically, PPD handles co-elution peaks better than other detectors (e.g., Avalon, Genesis, and Interactive Chemical Information System (ICIS)); however, in some cases, PPD is computationally slower than other peak detectors. In some embodiments, the described system attempts to fit a Gaussian curve to the chromatogram of the PPD. This optimization step is one of the bottlenecks of PPD performance. In some embodiments, the type of Gaussian curve used includes four input parameters: retention time, peak width, peak height, and exponential decay factor.

[0015] In some embodiments, the described systems employ machine learning (e.g., via a trained neural network) to determine input parameter values for a Gaussian curve to optimize the PPD. In some embodiments, the system modifies the PPD by employing a trained neural network rather than, for example, a Marquadt-Levenberg method to determine input parameter values for the Gaussian curve and improve the accuracy or runtime of the peak detection step. Although the following disclosure describes the use of a trained neural network for peak detection within a CE, the system can be used for additional chromatographic peak models to, for example, deconvolute overlapping peaks of an experimental peak and smooth the experimental peak to determine statistical moments. In some embodiments, the described systems employ a machine learning framework (e.g., Keras.NET, Microsoft.ML) to train a neural network model for PPD peak parameter determination (see Figures 4A to 4F ).

[0016] In the following detailed description, reference is made to the accompanying drawings, which form a part of the detailed description, wherein like reference numerals designate like parts throughout, and in which are shown by way of illustration embodiments that may be practiced. It should be understood that other embodiments may be utilized and structural or logical changes may be made without departing from the scope of the present disclosure. Therefore, the following detailed description should not be considered in a limiting sense.

[0017] The various operations may be described as a plurality of discrete actions or operations in a manner that is most helpful in understanding the subject matter disclosed herein. However, the described order should not be interpreted as implying that these operations must rely on the order. Specifically, these operations may not be performed in the order presented. The described operations may be performed in an order different from the described embodiments. Various additional operations may be performed, and / or the described operations may be omitted in additional embodiments.

[0018] For purposes of this disclosure, the phrases "A and / or B" and "A or B" mean (A), (B), or (A and B). For purposes of this disclosure, the phrases "A, B, and / or C" and "A, B, or C" mean (A), (B), (C), (A and B), (A and C), (B and C), or (A, B, and C). Although some elements may be referred to in the singular (e.g., "processing device"), any appropriate element may be represented by multiple instances of that element, and vice versa. For example, a set of operations described as being performed by a processing device may be implemented with different ones of those operations being performed by different processing devices.

[0019] This description uses the phrases "embodiment," "various embodiments," and "some embodiments," each of which may refer to one or more of the same or different embodiments. Furthermore, the terms "comprising," "including," "having," and the like, as used with respect to the embodiments of the present disclosure, are synonymous. When used to describe a range of dimensions, the phrase "between X and Y" means a range that includes X and Y. As used herein, "means" may refer to any individual device, collection of devices, portion of a device, or collection of portions of a device. The drawings are not necessarily drawn to scale.

[0020] Figure 1 is a block diagram of a chromatograph support module 1000 for automatic peak detection (peak and baseline generation) according to various embodiments. The chromatograph support module 1000 can be implemented by circuitry (e.g., including electrical and / or optical components) such as a programmed computing device. The logic of the chromatograph support module 1000 can be included in a single computing device or can be distributed across multiple computing devices that communicate with each other, as appropriate. Figure 6 Examples of computing devices that may implement the chromatograph support module 1000, either alone or in combination, are discussed in conjunction with the computing device 4000 of FIG. Figure 7 The chromatograph support system 5000 discussed in detail is an example of a system of interconnected computing devices in which the chromatograph support module 1000 may be implemented across one or more of the computing devices.

[0021] Chromatograph support module 1000 may include parameter value determination logic 1002, training logic 1004, model selection logic 1006 and chromatogram display logic 1008. As used herein, the term "logic" may include a device for performing a set of operations associated with the logic. For example, any of the logic elements included in support module 1000 may be implemented by one or more computing devices, which are programmed with instructions to cause one or more processing devices of the computing device to perform an associated set of operations. In a specific embodiment, the logic element may include one or more non-transient computer-readable media, which have instructions on them, which, when executed by one or more processing devices in one or more computing devices, cause the one or more computing devices to perform an associated set of operations. As used herein, the term "module" may refer to a collection of one or more logic elements, which collectively perform a function associated with a module. Different logic elements in the logic elements in a module may take the same form or may take 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 example, 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 not include all of the logic elements depicted in the associated figures; for example, when the module is to perform a subset of the operations discussed herein with reference to the module, the module may include a subset of the logic elements depicted in the associated figures.

[0022] The parameter value determination logic 1002 may be configured to determine parameter values (e.g., Figure 3A ). The chromatogram dataset can be data generated by a chromatograph, such as any of the chromatographs discussed herein. For example, the chromatogram dataset can include capillary electrophoresis data, cation exchange data, hydrophobic interaction data, reversed phase data, or size exclusion data, among others.

[0023] In some embodiments, the parameter value determination logic 1002 uses a trained neural network instead of a traditional multivariate optimization algorithm to determine the parameter values of the Gaussian curve. In some embodiments, the parameter value determination logic 1002 attempts to fit a Gaussian curve to the chromatogram of the PPD. This optimization step is one of the bottlenecks in PPD performance. In some embodiments, the type of Gaussian curve used includes four input parameters: retention time, peak width, peak height, and exponential decay factor. In some embodiments, the parameter value determination logic 1002 uses machine learning (e.g., via a trained neural network) to determine the input parameter values of the Gaussian curve to optimize the PPD. As described above, the parameter value determination logic 1002 may include a machine learning computational model (see Figures 3A to 3D ), the machine learning computational model outputs parameter values for a Gaussian curve that fits the chromatogram dataset and is trained based on data provided by an individual or institution and reflects that individual's or institution's preferences for peak and baseline identification.

[0024] In some embodiments, the machine learning computational model can be a neural network computational model that receives a chromatogram data set as input and outputs parameter values for a Gaussian curve that fits the chromatogram data set. The architecture of the machine learning computational model can take any of a variety of forms, such as a neural network model (e.g., a convolutional neural network model). For example, the parameter value determination logic 1002 can include a machine learning computational model whose architecture is similar to a U-NET convolutional neural network, but replaces the two-dimensional convolution of U-NET (applicable to two-dimensional input images) with a one-dimensional convolution (applicable to one-dimensional input chromatogram data array). Different kernel sizes (e.g., kernel sizes between 3 and 20) and the number of blocks (e.g., four blocks in the descending portion of the "U" of the U-NET architecture) can be appropriately used and / or adjusted. The training of the machine learning computational model included in the parameter value determination logic 1002 is further discussed below with reference to the training logic 1004.

[0025] The training logic 1004 can be configured to initially train the machine learning computational model used by the parameter value determination logic 1002 (e.g., based on a body of training data of chromatogram datasets generated manually or otherwise using common separated value (csv) files and / or raw files), and to retrain the machine learning computational model when additional chromatogram datasets are received. Any suitable training technique for the machine learning computational model can be implemented by the training logic 1004, such as a gradient descent method using a suitable loss function. In some embodiments, in order to retrain the machine learning computational model, the training logic 1004 output parameter values can utilize dropout or other regularization methods, and some training data can be retained for verification and to evaluate when to stop using in the retraining process. The training logic 1004 can be scheduled on a regular basis (e.g., weekly), after a certain number (e.g., 20) of confirmed chromatogram datasets have been accumulated, according to any other suitable schedule, or at (e.g., via a GUI such as Figure 5 Such retraining may be performed under the command of a user of the GUI 3000. In some embodiments, the training data for retraining the machine learning computational model may include a Network Common Data Format (NetCDF) file, which includes a chromatogram dataset (e.g., an array of specified chromatogram signal values, a sampling rate value corresponding to a detection frequency or a resampling frequency of a chromatograph, and optionally, an array of retention time values corresponding to the array of chromatogram signal values) and a plain text file containing information about the chromatogram dataset.

[0026] The model selection logic 1006 can be configured to provide a plurality of machine learning computational models, which can be selectively determined by the parameter value determination logic 1002 to determine the parameter values of the Gaussian curve fitting the chromatogram data set. For example, one machine learning computational model can be trained to analyze one type of sample mixture, while another machine learning computational model can be trained to analyze a different type of sample mixture (thus, different machine learning computational models can be trained on different training data sets). The display logic 1008 can display the chromatogram data set through a GUI (such as Figure 5 The GUI 3000 of FIG. 1000 provides the user with the option of selecting the machine learning computational model they wish to use for a particular sample mixture from a set of stored machine learning computational models (e.g., identified by different names), which is implemented by the model selection logic 1006, and the selected machine learning computational model can be used by the parameter value determination logic 1002 as part of determining the parameter values for the Gaussian curve that fits the chromatogram data set. The model selection logic 1006 can also be used by the GUI (such as Figure 5GUI 3000) provides the user with the option of creating a new machine learning computational model; model selection logic 1006 can prompt the user to enter a name or other identifier for the new machine learning computational model and specify data that can be used to train the new machine learning computational model. In some embodiments, model selection logic 1006 may require a threshold amount of training data before training of the new machine learning computational model can proceed, and once trained, the new machine learning computational model is available for selection via model selection logic 1006.

[0027] Figure 2A and Figure 2B 2000 and 2100, respectively, are flow diagrams of methods 2000 and 2100 for performing support operations according to various embodiments. Although the operations of methods 2000 and 2100 may be illustrated with reference to specific embodiments disclosed herein (e.g., the scientific instrument support module 1000 discussed herein with reference to FIG. Figure 5 The GUI 3000 discussed herein is referenced Figure 6 The computing device 4000 discussed and / or herein with reference to Figure 7 The scientific instrument support system 5000 is discussed, but the methods 2000 and 2100 may be used in any suitable setting to perform any suitable support operations. Figure 2A and Figure 2B Each is illustrated once in a particular order, but these operations may be reordered and / or repeated as needed and appropriate (eg, different operations performed may be performed in parallel as appropriate).

[0028] For the method 2000, at 2002, a first operation may be performed. For example, the support module 1000 may perform the operation of 2002 (eg, via Figure 1 Receive logic not shown in FIG). A first operation may include receiving a chromatogram dataset.

[0029] At 2004, a second operation may be performed. For example, the determination logic 1002 of the support module 1000 may perform the operation of 2004. The second operation may include determining one or more peak positions of the chromatogram dataset by processing the chromatogram dataset through a machine learning computational model to determine a plurality of input parameter values that fit a Gaussian curve to the chromatogram dataset.

[0030] At 2006, a third operation can be performed. For example, the display logic 1008 of the support module 1000 can perform the operation of 2006. The third operation can include providing one or more peak positions for further small molecule LC / MS processing.

[0031] For method 2100, at 2102, a first operation can be performed. For example, the receiving logic (described above) of support module 1000 can perform the operation of 2002. The first operation can include receiving a command to train a machine learning computational model. In some embodiments, the command includes identification of multiple chromatogram data sets and multiple input parameter values for fitting a Gaussian curve to each of the chromatogram data sets for training the machine learning computational model.

[0032] At 2104, a second operation can be performed. For example, the training logic 1004 of the support module 1000 can perform the operation of 2104. The second operation can include initially training a machine learning computational model based on the plurality of chromatogram datasets and the input parameter values for fitting a Gaussian curve to each of the chromatogram datasets. In some embodiments, the machine learning computational model outputs the plurality of input parameter values for fitting a Gaussian curve to the input chromatogram datasets.

[0033] At 2106, a third operation can be performed. For example, the selection logic 1006 of the support module 1000 can perform the operation of 2106. The third operation can include providing an option to select a machine learning computational model to apply to subsequent chromatogram data sets after the initial training.

[0034] The scientific instrument support methods disclosed herein may include interaction with a human user (e.g., via the reference herein). Figure 7 The user's local computing device 5020 is discussed. These interactions may include providing information to the user (e.g., about scientific instruments such as Figure 7 information about the operation of a scientific instrument such as a scientific instrument 5010, information about samples being analyzed or other tests or measurements being performed by the scientific instrument, information retrieved from a local or remote database, or other information) or provide a user with a means for entering commands (e.g., for controlling a scientific instrument such as a Figure 7 In some embodiments, these interactions can be performed through a graphical user interface (GUI) that includes a display device (e.g., a display device such as a display device shown in FIG. Figure 5 A visual display on a display device 4010 as discussed herein that provides output to a user and / or prompts a user to provide input (e.g., via a display device 4010 as discussed herein). Figure 5 Other I / O devices 4012 discussed include one or more input devices such as a keyboard, mouse, trackpad, or touch screen. The scientific instrument support system disclosed herein may include any suitable GUI for interacting with a user.

[0035] Figure 5 An example GUI 3000 is depicted that can be used to perform some or all of the supporting methods disclosed herein, according to various embodiments. As described above, the GUI 3000 can be provided on a scientific instrument support system (e.g., a system described herein with reference to FIG. Figure 7 The computing device of the scientific instrument support system 5000 discussed herein (e.g., Figure 6 The display device of the computing device 4000 discussed herein (eg, Figure 6 The display device 4010 discussed herein) and the user may use any suitable input device (e.g., Figure 6 Any of the input devices included in the other I / O devices 4012 discussed) and input techniques (e.g., cursor movement, motion capture, facial recognition, gesture detection, voice recognition, button actuation, etc.) interact with the GUI 3000.

[0036] The GUI 3000 may include a data display area 3002 , a data analysis area 3004 , a scientific instrument control area 3006 , and a settings area 3008 . Figure 5 The specific number and arrangement of regions depicted in GUI 3000 are merely illustrative, and any number and arrangement of regions (including any desired characteristics) may be included in GUI 3000.

[0037] The data display area 3002 can display data generated by a scientific instrument (e.g., Figure 7 For example, the data display area 3002 may provide the user with the option of selecting a machine learning computational model that they wish to use for a particular sample mixture from a set of stored machine learning computational models provided by the model selection logic 1006, and the selected machine learning computational model may be used by the parameter value determination logic 1002 as part of determining parameter values for a Gaussian curve that fits the chromatogram data set.

[0038] The data analysis area 3004 can display the results of the data analysis (e.g., the results of analyzing the data illustrated in the data display area 3002 and / or other data). For example, the data display area 3004 can display the parameter values determined by the determination logic 1002. In some embodiments, the data display area 3002 and the data analysis area 3004 can be combined in the GUI 3000 (e.g., to include data output from a scientific instrument and some analysis of the data in a common graph or area).

[0039] The scientific instrument control area 3006 may include a user-friendly interface that allows the user to control scientific instruments (e.g., Figure 7The settings area 3008 may include options that allow the user to control the features and functions of the GUI 3000 (and / or other GUIs) and / or perform common computing operations with respect to the data display area 3002 and the data analysis area 3004 (e.g., saving data to a storage device (such as the one referenced herein)). Figure 6 the storage device 4004 in question), transferring data to another user, marking data, etc.).

[0040] As noted above, the scientific instrument support module 1000 may be implemented by one or more computing devices. Figure 6 is a block diagram of a computing device 4000 that can perform some or all of the scientific instrument support methods disclosed herein, according to various embodiments. In some embodiments, the scientific instrument support module 1000 can be implemented by a single computing device 4000 or by multiple computing devices 4000. In addition, as discussed below, the computing device 4000 (or multiple computing devices 4000) that implements the scientific instrument support module 1000 can be Figure 7 A portion of one or more of a scientific instrument 5010, a user local computing device 5020, a service local computing device 5030, or a remote computing device 5040.

[0041] Figure 6 The computing device 4000 is illustrated as having multiple components, but any one or more of these components may be omitted or repeated depending on suitability for the application and setting. In some embodiments, some or all of the components included in the computing device 4000 may be attached to one or more motherboards and enclosed in a housing (e.g., comprising plastic, metal, and / or other materials). In some embodiments, some of these components may be manufactured on a single system on a chip (SoC) (e.g., the SoC may include one or more processing devices 4002 and one or more storage devices 4004). Additionally, in various embodiments, the computing device 4000 may not include Figure 6 One or more of the illustrated components 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 4000 may not include display device 4010, but may include display device interface circuitry (e.g., a connector and driver circuitry) to which display device 4010 may be coupled.

[0042] The computing device 4000 may include a processing device 4002 (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 to convert the electronic data into other electronic data that can be stored in registers and / or memory. The processing device 4002 may include one or more digital signal processors (DSPs), application-specific integrated circuits (ASICs), central processing units (CPUs), graphics processing units (GPUs), cryptographic processors (specialized processors that execute cryptographic algorithms in hardware), server processors, or any other suitable processing devices.

[0043] The computing device 4000 may include a storage device 4004 (e.g., one or more storage devices). The storage device 4004 may include one or more memory devices, such as random access memory (RAM) (e.g., static RAM (SRAM) devices, magnetic RAM (MRAM) devices, dynamic RAM (DRAM) devices, resistive RAM (RRAM) devices, or conductive bridge RAM (CBRAM) devices), hard drive-based memory devices, solid-state memory devices, network drives, cloud drives, or any combination of memory devices. In some embodiments, the storage device 4004 may include memory that shares a die with the processing device 4002. In such embodiments, the memory may be used as a cache memory and may include, for example, embedded dynamic random access memory (eDRAM) or spin-transfer torque magnetic random access memory (STT-MRAM). In some embodiments, the storage device 4004 may include a non-transitory computer-readable medium having instructions thereon that, when executed by one or more processing devices (e.g., processing device 4002), cause the computing device 4000 to perform any appropriate method or portion of the methods disclosed herein.

[0044] The computing device 4000 may include an interface device 4006 (e.g., one or more interface devices 4006). The interface device 4006 may include one or more communication chips, connectors, and / or other hardware and software to manage communications between the computing device 4000 and other computing devices. For example, the interface device 4006 may include circuitry for managing wireless communications for transmitting data to and from the computing device 4000. The term "wireless" and its derivatives may be used to describe circuits, devices, systems, methods, techniques, communication channels, and the like that can communicate data through a non-solid medium using modulated electromagnetic radiation. The term does not imply that the associated device does not contain any wires, although in some embodiments, it may not contain any wires. The circuitry included in the interface device 4006 for managing wireless communications may implement any of a plurality of wireless standards or protocols, including, but not limited to, Institute of Electrical and Electronics Engineers (IEEE) standards, including Wi-Fi (IEEE 802.11 series), IEEE 802.16 standards (e.g., IEEE 802.16-2005 amendment), the Long Term Evolution (LTE) project, and any amendments, updates, and / or revisions (e.g., the LTE-Advanced project, the Ultra Mobile Broadband (UMB) project (also known as "3GPP2"), etc.). In some embodiments, the circuitry included in the interface device 4006 for managing wireless communications may operate in accordance with a Global System for Mobile Communications (GSM), General Packet Radio Service (GPRS), Universal Mobile Telecommunications System (UMTS), High Speed Packet Access (HSPA), Evolved HSPA (E-HSPA), or LTE network. In some embodiments, the circuitry included in the interface device 4006 for managing wireless communications may operate in accordance with Enhanced Data for GSM Evolution (EDGE), GSM Evolution Radio Access Network (GERAN), Universal Terrestrial Radio Access Network (UTRAN), or Evolved UTRAN (E-UTRAN). In some embodiments, the circuitry included in the interface device 4006 for managing wireless communications may operate in accordance with Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Digital Enhanced Cordless Telecommunications (DECT), Evolution-Data Optimized (EV-DO), and derivatives thereof, as well as any other wireless protocols designated as 3G, 4G, 5G, and higher. In some embodiments, the interface device 4006 may include one or more antennas (e.g., one or more antenna arrays) for receiving and / or transmitting wireless communications.

[0045] In some embodiments, interface device 4006 can include a circuit for managing wired communication, such as electrical communication protocol, optical communication protocol or any other suitable communication protocol. For example, interface device 4006 can include a circuit supporting the communication according to Ethernet technology. In some embodiments, interface device 4006 can support both wireless and wired communication, and / or can support multiple wired communication protocols and / or multiple wireless communication protocols. For example, a first group of circuits of interface device 4006 can be dedicated to shorter distance wireless communication such as Wi-Fi or Bluetooth, and a second group of circuits of interface device 4006 can be dedicated to longer distance wireless communication such as global positioning system (GPS), EDGE, GPRS, CDMA, WiMAX, LTE, EV-DO etc. In some embodiments, a first group of circuits of interface device 4006 can be dedicated to wireless communication, and a second group of circuits of interface device 4006 can be dedicated to wired communication.

[0046] The computing device 4000 may include a battery / power circuit 4008. The battery / power circuit 4008 may include one or more energy storage devices (e.g., batteries or capacitors), and / or circuitry for coupling components of the computing device 4000 to an energy source separate from the computing device 4000 (e.g., AC line power).

[0047] Computing device 4000 may include a display device 4010 (e.g., multiple display devices). Display device 4010 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.

[0048] The computing device 4000 may include other input / output (I / O) devices 4012. The other I / O devices 4012 may include, for example, one or more audio output devices (e.g., speakers, headphones, earbuds, an alarm, etc.), one or more audio input devices (e.g., a microphone or microphone array), a positioning device (e.g., a GPS device that communicates with a satellite-based system to receive the location of the computing device 4000, as is known in the art), an audio codec, a video codec, a printer, sensors (e.g., thermocouples or other temperature sensors, humidity sensors, pressure sensors, vibration sensors, accelerometers, gyroscopes, etc.), an image capture device such as a camera, a keyboard, a cursor control device such as a mouse, stylus, trackball, or touchpad, a barcode reader, a Quick Response (QR) code reader, or a Radio Frequency Identification (RFID) reader.

[0049] The computing device 4000 can have any suitable form factor suitable for its applications and settings, such as a handheld or mobile computing device (e.g., a cellular phone, a smart phone, 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 computing device, or a server computing device or other networked computing component.

[0050] One or more computing devices implementing any of the scientific instrument support modules or methods disclosed herein may be part of a scientific instrument support system. Figure 7 FIG5 is a block diagram of an example scientific instrument support system 5000 in which some or all of the scientific instrument support methods disclosed herein may be performed, according to various embodiments. The scientific instrument support modules and methods disclosed herein (e.g., the scientific instrument support module 1000 of FIG5 A and the method 2000 of FIG5 B) may be implemented by one or more of a scientific instrument 5010, a user local computing device 5020, a service local computing device 5030, or a remote computing device 5040 of the scientific instrument support system 5000.

[0051] Any of the scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may include a Figure 6 Any of the embodiments of the computing device 4000 discussed herein, and any of the scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 may take the form described herein with reference to Figure 6 Any suitable form of implementation of the computing device 4000 discussed.

[0052] The scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 can each include a processing device 5002, a storage device 5004, and an interface device 5006. The processing device 5002 can take any suitable form, including any of the processing devices in the processing device 4002 discussed herein with reference to FIG4 , and the processing devices 5002 included in different devices of the scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 can take the same form or different forms. The storage device 5004 can take any suitable form, including any of the storage devices in the storage device 5004 discussed herein with reference to FIG4 , and the storage devices 5004 included in different devices of the scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 can take the same form or different forms. The interface device 5006 can take any suitable form, including the form of any interface device in the interface device 4006 discussed herein with reference to FIGURE 4, and the interface devices 5006 included in different devices of the scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, or the remote computing device 5040 can take the same form or different forms.

[0053] The scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, and the remote computing device 5040 can communicate with other elements of the scientific instrument support system 5000 via a communication path 5008. The communication path 5008 can communicatively couple the interface device 5006 (as shown) of different ones of the elements of the scientific instrument support system 5000 and can be a wired or wireless communication path (e.g., according to the present reference Figure 6 any of the communication technologies discussed for the interface device 4006 of the computing device 4000). Figure 7The particular scientific instrument support system 5000 depicted in FIG5 includes a communication path between each pair of devices among the scientific instrument 5010, the user local computing device 5020, the service local computing device 5030, and the remote computing device 5040, but this "fully connected" implementation is merely illustrative, and in various embodiments, various communication paths in the communication paths 5008 may not exist. For example, in some embodiments, the service local computing device 5030 may not have a direct communication path 5008 between its interface device 5006 and the interface device 5006 of the scientific instrument 5010, but may communicate with the scientific instrument 5010 via the communication path 5008 between the service local computing device 5030 and the user local computing device 5020, as well as the communication path 5008 between the user local computing device 5020 and the scientific instrument 5010.

[0054] The user-local computing device 5020 can be a computing device local to the user of the scientific instrument 5010 (e.g., according to any of the embodiments of the computing device 4000 discussed herein). In some embodiments, the user-local computing device 5020 can also be local to the scientific instrument 5010, but this is not necessarily the case; for example, a user-local computing device 5020 in a user's home or office can be remote from the scientific instrument 5010 but in communication with the scientific instrument such that the user can use the user-local computing device 5020 to control and / or access data from the scientific instrument 5010. In some embodiments, the user-local computing device 5020 can be a laptop, smartphone, or tablet device. In some embodiments, the user-local computing device 5020 can be a portable computing device.

[0055] The service local computing device 5030 can be a computing device local to the entity serving the scientific instrument 5010 (e.g., according to any of the embodiments of the computing device 4000 discussed herein). For example, the service local computing device 5030 can be a device local to the manufacturer of the scientific instrument 5010 or a third-party service company. In some embodiments, the service local computing device 5030 can communicate with the scientific instrument 5010, the user local computing device 5020, and / or the remote computing device 5040 (e.g., via a direct communication path 5008 or via multiple "indirect" communication paths 5008, as described above) to receive data regarding the operation of the scientific instrument 5010, the user local computing device 5020, and / or the remote computing device 5040 (e.g., self-test results of the scientific instrument 5010, calibration coefficients used by the scientific instrument 5010, measurements of sensors associated with the scientific instrument 5010, etc.). In some embodiments, the service local computing device 5030 can communicate with the scientific instrument 5010, the user local computing device 5020 and / or the remote computing device 5040 (e.g., via a direct communication path 5008 or via multiple "indirect" communication paths 5008, as described above) to send data to the scientific instrument 5010, the user local computing device 5020 and / or the remote computing device 5040 (e.g., to update programmed instructions (such as firmware) in the scientific instrument 5010 to initiate execution of a test or calibration sequence in the scientific instrument 5010, update programmed instructions (such as software) in the user local computing device 5020 or the remote computing device 5040, etc.). A user of the scientific instrument 5010 may utilize the scientific instrument 5010 or the user's local computing device 5020 to communicate with the service local computing device 5030 to report problems with the scientific instrument 5010 or the user's local computing device 5020, thereby requesting a technician visit to improve the operation of the scientific instrument 5010, order consumables or replacement parts associated with the scientific instrument 5010, or for other purposes.

[0056] The remote computing device 5040 can be a computing device remote from the scientific instrument 5010 and / or the user's local computing device 5020 (e.g., according to any of the embodiments of the computing device 4000 discussed herein). In some embodiments, the remote computing device 5040 can be included in a data center or other large-scale server environment. In some embodiments, the remote computing device 5040 can include a network-attached storage device (e.g., as part of the storage device 5004). The remote computing device 5040 can store data generated by the scientific instrument 5010, perform analysis of the data generated by the scientific instrument 5010 (e.g., according to programmed instructions), facilitate communication between the user's local computing device 5020 and the scientific instrument 5010, and / or facilitate communication between the service's local computing device 5030 and the scientific instrument 5010.

[0057] In some embodiments, Figure 7 One or more of the elements of the scientific instrument support system 5000 illustrated in FIG may not be present. Additionally, in some embodiments, Figure 7 Multiple of the various elements of the scientific instrument support system 5000 may be present. For example, the scientific instrument support system 5000 may include multiple user-local computing devices 5020 (e.g., different user-local computing devices 5020 associated with different users or located in different locations). In another example, the scientific instrument support system 5000 may include multiple scientific instruments 5010, all of which communicate with a service-local computing device 5030 and / or a remote computing device 5040; in such embodiments, the service-local computing device 5030 may monitor these multiple scientific instruments 5010, and the service-local computing device 5030 may cause updates or other information to be "broadcasted" to the multiple scientific instruments 5010 simultaneously. Different ones of the scientific instruments 5010 in the scientific instrument support system 5000 may be located near each other (e.g., in the same room) or far away from each other (e.g., on different floors of a building, in different buildings, in different cities, etc.). In some embodiments, the scientific instrument 5010 can be connected to an Internet of Things (IoT) stack that allows command and control of the scientific instrument 5010 through web-based applications, virtual or augmented reality applications, mobile applications, and / or desktop applications. Any of these applications can be accessed by a user operating a user-local computing device 5020 that communicates with the scientific instrument 5010 through an intermediary remote computing device 5040. In some embodiments, the scientific instrument 5010 can be sold by a manufacturer along with one or more associated user-local computing devices 5020 as part of a local scientific instrument computing unit 5012.

[0058] The following paragraphs provide various examples of the embodiments disclosed herein.

[0059] Embodiment 1 is a chromatography support device comprising: first logic for receiving a chromatogram dataset; second logic for determining one or more peak positions of the chromatogram dataset by processing the chromatogram dataset through a machine learning computational model to determine a plurality of input parameter values that fit a Gaussian curve to the chromatogram dataset; and third logic for providing the one or more peak positions for further small molecule LC / MS processing.

[0060] Embodiment 2 includes the subject matter of embodiment 1, and further comprising fourth logic for causing display of the one or more peak positions and display of the chromatogram data set.

[0061] Embodiment 3 includes the subject matter of any of Embodiments 1 and 2, and further specifies that the machine learning computational model comprises a trained neural network.

[0062] Embodiment 4 includes the subject matter of any one of embodiments 1 to 3, and further specifies that the machine learning computational model comprises a trained feed-forward neural network.

[0063] Embodiment 5 includes the subject matter of any one of embodiments 1 to 4, and further provides that the one or more peak positions are provided to deconvolute overlapping peaks or smooth experimental peaks to determine statistical moments.

[0064] Embodiment 6 includes the subject matter of any one of embodiments 1 to 5, and further specifies that the second logic comprises a peak detection algorithm.

[0065] Embodiment 7 includes the subject matter of any one of embodiments 1 to 6, and further specifies that the peak detection algorithm comprises ETG, PMG, GEMG, or EGH.

[0066] Embodiment 8 includes the subject matter of any one of embodiments 1 to 7, and further specifies that the chromatogram dataset comprises time values and intensity values.

[0067] Embodiment 9 includes the subject matter of any one of embodiments 1 to 8, and further provides that the input parameter values include retention time, peak width, peak height, and exponential decay.

[0068] Embodiment 10 includes the subject matter of any one of Embodiments 1 to 9, and further specifies that the first logic, the second logic, and the third logic are implemented by a common computing device.

[0069] Embodiment 11 is a chromatography support device, comprising: first logic for receiving a command to train a machine learning computational model, wherein the command comprises identifying a plurality of chromatogram data sets for training the machine learning computational model and a plurality of input parameter values for fitting a Gaussian curve to each of the chromatogram data sets; second logic for initially training the machine learning computational model based on the plurality of chromatogram data sets and the input parameter values for fitting the Gaussian curve to each of the chromatogram data sets, wherein the machine learning computational model will output a plurality of input parameter values for fitting the Gaussian curve to the input chromatogram data sets; and third logic for providing an option, after initial training, of selecting the machine learning computational model for application to subsequent chromatogram data sets.

[0070] Embodiment 12 includes the subject matter of embodiment 11, and further specifies that the input to the machine learning computational model comprises a one-dimensional array of chromatogram data.

[0071] Embodiment 13 includes the subject matter of any one of Embodiments 11 and 12, and further specifies that the machine learning computational model is a first machine learning computational model.

[0072] Embodiment 14 includes the subject matter of any one of Embodiments 11 to 13, and further provides that the first logic is to receive a command to train a second machine learning computational model.

[0073] Embodiment 15 includes the subject matter of any one of Embodiments 11 to 14, and further provides that the command for training the second machine learning computational model includes identifying a plurality of chromatogram data sets for training the second machine learning computational model and the input parameter values for fitting the Gaussian curve to each of the chromatogram data sets.

[0074] Embodiment 16 includes the subject matter of any one of embodiments 11 to 15, and further specifies that the input parameter values for training the multiple chromatogram datasets and fitting the Gaussian curve to each of the chromatogram datasets for the second machine learning computational model are different from the input parameter values for training the multiple chromatogram datasets and fitting the Gaussian curve to each of the chromatogram datasets for the first machine learning computational model.

[0075] Embodiment 17 includes the subject matter of any one of embodiments 11 to 16, and further specifies that the second logic is to provide for selecting which computational model to use for analyzing the subsequent chromatogram data set among a plurality of computational models including the first machine learning computational model and the second machine learning computational model.

[0076] Embodiment 18 includes the subject matter of any one of embodiments 11 to 17, and further specifies that the second logic is also to provide selectable options for non-machine learning computational models to apply to the subsequent chromatogram dataset.

[0077] Example 19 is a method for scientific instrument support performed by one or more processing devices. The method includes: receiving a chromatogram dataset; determining one or more peak positions of the chromatogram dataset by processing the chromatogram dataset through a machine learning computational model to determine a plurality of input parameter values that fit a Gaussian curve to the chromatogram dataset; and providing the one or more peak positions for further small molecule liquid chromatography mass spectrometry (LC / MS) processing.

[0078] Embodiment 20 includes the subject matter of embodiment 19, and further comprising fourth logic for causing display of the one or more peak positions and display of the chromatogram data set.

[0079] Embodiment 21 includes the subject matter of any of Embodiments 19 and 20, and further specifies that the machine learning computational model comprises a trained neural network.

[0080] Embodiment 22 includes the subject matter of any one of Embodiments 19 to 21, and further specifies that the machine learning computational model comprises a trained feed-forward neural network.

[0081] Embodiment 23 includes the subject matter of any one of embodiments 19 to 22, and further provides that the one or more peak positions are provided to deconvolute overlapping peaks or smooth experimental peaks to determine statistical moments.

[0082] Embodiment 24 includes the subject matter of any one of Embodiments 19 to 23, and further specifies that the second logic comprises a peak detection algorithm.

[0083] Embodiment 25 includes the subject matter of any one of Embodiments 19 to 24, and further specifies that the peak detection algorithm comprises ETG, PMG, GEMG, or EGH.

[0084] Embodiment 26 includes the subject matter of any one of embodiments 19 to 25, and further specifies that the chromatogram dataset comprises time values and intensity values.

[0085] Embodiment 27 includes the subject matter of any one of embodiments 19 to 26, and further provides that the input parameter values include retention time, peak width, peak height, and exponential decay.

[0086] Embodiment 28 includes the subject matter of any one of Embodiments 19 to 27, and further specifies that the first logic, the second logic, and the third logic are implemented by a common computing device.

Claims

1. A chromatography support device, comprising: first logic for receiving a chromatogram dataset; second logic for determining one or more peak locations of the chromatogram dataset by processing the chromatogram dataset through a machine learning computational model to determine a plurality of input parameter values that fit a Gaussian curve to the chromatogram dataset; and A third logic is provided for providing the one or more peak positions for further small molecule liquid chromatography mass spectrometry (LC / MS) processing.

2. The chromatography support device of claim 1, comprising fourth logic for causing display of the one or more peak positions and display of the chromatogram dataset.

3. The chromatography support device of claim 1, wherein the machine learning computational model comprises a trained neural network.

4. The chromatography support device of claim 3, wherein the machine learning computational model comprises a trained feed-forward neural network.

5. The chromatography support device of claim 1, wherein the one or more peak positions are provided to deconvolute overlapping peaks or smooth experimental peaks to determine statistical moments. The chromatography support device of claim 1 , wherein the second logic comprises a peak detection algorithm.

7. The chromatography support device according to claim 6, wherein the peak detection algorithm comprises an empirical transformed Gaussian function (ETG), a polynomial modified Gaussian function (PMG), a generalized exponential modified Gaussian function (GEMG), or a mixture of Gaussian and truncated exponential functions (EGH).

8. The chromatography support device of claim 1, wherein the chromatogram dataset comprises time values and intensity values.

9. The chromatography support device of claim 1, wherein the input parameter values include retention time, peak width, peak height, and exponential decay.

10. The chromatography support apparatus according to claim 1, wherein the first logic, the second logic, and the third logic are implemented by a common computing device.

11. A chromatography support device, comprising: first logic for receiving a command to train a machine learning computational model, wherein the command comprises identifying a plurality of chromatogram data sets for training the machine learning computational model and a plurality of input parameter values for fitting a Gaussian curve to each of the chromatogram data sets; second logic for initially training the machine learning computational model based on the plurality of chromatogram datasets and the input parameter values for the Gaussian curve fitted to each of the chromatogram datasets, wherein the machine learning computational model outputs a plurality of input parameter values for the Gaussian curve fitted to the input chromatogram datasets; and and third logic for providing an option to select the machine learning computational model for application to subsequent chromatogram datasets after initial training.

12. The chromatography support device of claim 11, wherein the input to the machine learning computational model comprises a one-dimensional array of chromatogram data.

13. The chromatography support device of claim 11 , wherein the machine learning computational model is a first machine learning computational model, wherein the first logic is to receive a command to train a second machine learning computational model, wherein the command to train the second machine learning computational model comprises identifying a plurality of chromatogram datasets for training the second machine learning computational model and the input parameter values for fitting the Gaussian curve to each of the chromatogram datasets.

14. The chromatography support device according to claim 13, wherein the input parameter values for the plurality of chromatogram datasets used to train the second machine learning computational model and the Gaussian curve fitted to each of the chromatogram datasets are different from the input parameter values for the plurality of chromatogram datasets used to train the first machine learning computational model and the Gaussian curve fitted to each of the chromatogram datasets.

15. The chromatography support device of claim 13, wherein the second logic is to provide for selecting which computational model to use for analyzing a subsequent chromatogram dataset among a plurality of computational models including the first machine learning computational model and the second machine learning computational model.

16. The chromatography support device of claim 13, wherein the second logic further provides selectable options regarding non-machine learning computational models to apply to subsequent chromatogram datasets.

17. A method for scientific instrument support performed by one or more processing devices, the method comprising: receiving a chromatogram data set; determining one or more peak positions of the chromatogram dataset by processing the chromatogram dataset through a machine learning computational model to determine a plurality of input parameter values that fit a Gaussian curve to the chromatogram dataset; as well as The one or more peak positions are provided for further small molecule liquid chromatography mass spectrometry (LC / MS) processing.

18. The method according to claim 17, comprising: The one or more peak positions and the chromatogram data set are displayed.

19. The method of claim 17, wherein the machine learning computational model comprises a trained neural network.

20. The method of claim 17, wherein the one or more peak positions are provided to deconvolute overlapping peaks or smooth experimental peaks to determine statistical moments.

Images