Particle Analyzer Characterization and Sorting

By using neural network parameterized non-parametric transformations in flow cytometry, an accurate parameter model is generated, and the problem of inconsistent data transformation in flow cytometry is solved, and efficient particle sorting in low-latency and resource-limited environments is achieved. .

CN113811754BActive Publication Date: 2024-11-01BECTON DICKINSON & CO
View PDF 23 Cites 0 Cited by

Patent Information

Application Number
CN201980071128.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2018-08-30
Filing Date
2019-08-30
Publication Date
2024-11-01
Estimated Expiration
2039-08-30

AI Technical Summary

Technical Problem

Existing nonparametric transformation techniques are difficult to effectively process new observations in flow cytometry, resulting in inconsistent data transformation, limiting the application of particle analysis and sample processing, especially on low-latency and resource-limited sorting electronic devices. Real-time sorting.

Method used

By training neural networks with a small training dataset, parameterize non-parametric transformations, generate accurate parametric models for data transformation and sorting decisions in flow cytometry and achieve low on field programmable gate arrays (FPGAs) Delayed sorting operation.

Benefits of technology

The consistency and accuracy of data transformation in flow cytometry is achieved, the requirements for sample size and resources are reduced, and the efficiency and accuracy of particle sorting are improved. It is suitable for low-latency and resource-limited environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113811754B_ABST
    Figure CN113811754B_ABST
Patent Text Reader

Abstract

Non-parametric transformations, such as t-distributed stochastic neighbor embedding (tSNE), can be used to analyze multi-parametric data, such as data derived from flow cytometry or other particle analysis systems and methods. The present invention can include these transformations for dimensionality reduction and subpopulation identification (e.g., gating). In essence, non-parametric transformations cannot transform new observations without training the new transformation on the entire data set (including the new observations). The functionality utilizes neural networks to parameterize non-parametric transformations, allowing small training data sets to be transformed using non-parametric techniques. The training data set can then be used to generate an accurate parametric model to evaluate other events in a manner consistent with the initial event.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] Cross-references to related patent applications

[0002] This patent application claims priority under 35 U.S.C. § 119(e) to U.S. Provisional Patent Application No. 62 / 724,834, filed on August 30, 2018; the contents of which are incorporated herein by reference. Technical Field

[0003] The present invention relates generally to the field of automated particle assessment technology and, more particularly, to sample analysis and particle characterization methods. Background Art

[0004] Particle analyzers (e.g., flow cytometers and scanning cytometers) are analytical tools that characterize particles based on electro-optical measurements such as light scattering and fluorescence. In a flow cytometer, for example, particles in a fluid suspension (e.g., molecules, microbeads bound to an analyte, or individual cells) pass through a detection region where they are exposed to excitation light, typically from one or more lasers, and the light scattering and fluorescence properties of the particles are measured. Particles or their components are typically labeled with fluorescent dyes for detection. Various particles or components can be detected simultaneously by labeling with fluorescent dyes with different spectral characteristics. In some embodiments, the analyzer includes a plurality of photodetectors, one for each scattering parameter to be determined, and one or more for each different dye to be detected. For example, some embodiments include a spectral structure in which more than one sensor or detector is used for each dye. The data obtained includes the signals measured for each of the light scattering detectors and the fluorescence emission.

[0005] The particle analyzer may further include means for recording the measured data and analyzing the data. For example, a computer connected to the detection electronics may be used for data storage and analysis. For example, the data may be stored in a tabular form, where each row corresponds to data for one particle and the columns correspond to each measured feature. Storing data from a particle analyzer using a standard file format (e.g., an "FCS" file format) facilitates analysis of the data using a separate program and / or machine. When current analysis methods are used, the data is typically displayed in the form of a one-dimensional histogram or a two-dimensional (2D) graph for ease of visualization, but other methods may also be used to visualize multi-dimensional data.

[0006] For example, the parameters measured using flow cytometry typically include light scattered by the particles at a narrow angle at the excitation wavelength primarily in the forward direction (referred to as forward scatter (FSC)); the excitation light scattered by the particles in a direction orthogonal to the excitation laser (referred to as side scatter (SSC)); and light emitted by fluorescent molecules in one or more detectors (used to measure signals within a certain spectral wavelength range), or light emitted by fluorescent dyes detected primarily in the specific detector or detector array. Different cell types can be identified by light scattering characteristics and fluorescent emissions obtained / generated by labeling various cellular proteins or other components with antibodies or other fluorescent probes labeled with fluorescent dyes.

[0007] Flow cytometers and scanning cytometers are available from, for example, BD Biosciences (San Jose, CA). Flow cytometry is described in, for example, Landy et al. (eds.), Clinical Flow Cytometry, Annals of the New York Academy of Sciences, Vol. 677 (1993); Bauer et al. (eds.), Clinical Flow Cytometry: Principles and Applications, Williams & Wilkins (1993); Ormerod (ed.), Flow Cytometry: A Practical Approach, Oxford University Press (1994); Jaroszeski et al. (eds.), Flow Cytometry Protocols, Methods in Molecular Biology, No. 91, Humana Press (1997); and Shapiro, Practical Flow Cytometry, 4th Edition, Wiley-Liss (2003); all of which are incorporated herein by reference. Fluorescence imaging microscopy is described in, for example, Pawley (ed.), Handbook of Biological Confocal Microscopy, 2nd ed., Plenum Press (1989), which is incorporated herein by reference.

[0008] The data obtained by analyzing cells (or other particles) using multicolor flow cytometry is multidimensional, where each cell corresponds to a point in the multidimensional space defined by the measured parameters. Cell populations or particle populations are identified as clusters of points in the data space. Clusters and populations can be manually identified by drawing gates around a population displayed in one or more two-dimensional graphs of the data (referred to as "scatter plots" or "dot plots"). Alternatively, clusters can be automatically identified, and gates defining the boundaries of the population can be automatically determined. Examples of methods for automatic gating are shown in the following publications, for example, U.S. Patents No. 4,845,653; 5,627,040; 5,739,000; 5,795,727; 5,962,238; 6,014,904; 6,944,338; and U.S. Patent Publication No. 2012 / 0245889, each of which is incorporated herein by reference.

[0009] Flow cytometry is an effective method for analyzing and separating biological particles (e.g., cells and constituent molecules), and therefore, it is widely used in diagnosis and treatment. The method utilizes a fluid medium to linearly separate particles so that the particles can be arranged in a row to pass through a detection device. Individual cells can be distinguished based on their location in the fluid medium and the presence or absence of detectable markers. Therefore, flow cytometry can be used to characterize and generate diagnostic profiles of biological particle populations.

[0010] Separation of biological particles has been achieved by adding a sorting or collection function to flow cytometers. Particles in the separation stream that have been detected to have one or more desired characteristics are individually separated from the sample stream by mechanical or electrical separation. This flow sorting method has been used to sort different types of cells, separate sperm containing X and Y chromosomes for animal breeding, sort chromosomes for genetic analysis, and isolate specific organisms from complex biological populations.

[0011] Gating is used to help understand and classify the large amount of data that may be generated by a sample. Given the large amount of data presented by a given sample, there is a need to effectively control the graphical display of that data.

[0012] Fluorescence activated particle sorting or cell sorting is a specialized form of flow cytometry. It provides a method for sorting a heterogeneous mixture of particles into one or more containers, one cell at a time, based on the specific light scattering and fluorescence properties of each cell. It records the fluorescent signals from individual cells and physically separates the specific cells of interest. The abbreviation FACS is a trademark of and owned by Becton Dickinson and may be used to refer to equipment that performs fluorescence activated particle sorting or cell sorting.

[0013] The particle suspension is placed near the center of a narrow, fast-flowing stream. The stream is arranged so that, on average, there are large spacings between particles relative to their diameters as they randomly arrive (Poisson process) at the detection area. A vibration mechanism causes the outflowing fluid medium to steadily break up into single droplets containing particles previously characterized in the detection area. The system is typically tuned so that the probability of more than one particle being present in a droplet is low. If a particle is classified as being collected, an electrical charge is applied to the flow cell and outflow stream over a period of time to form one or more droplets that detach from the stream. These charged droplets then pass through an electrostatic deflection system, which transfers the droplets to a target container based on the charge applied to the droplets.

[0014] The sample may include thousands, if not millions, of cells. The cells may be sorted to purify the sample to cells of interest. The sorting process typically identifies three types of cells: cells of interest, non-cells of interest, and unidentifiable cells. In order to sort cells of high purity (e.g., high concentrations of cells of interest), a cell sorter that generates droplets typically electronically aborts the sort if the desired cell is too close to another undesirable cell, thereby reducing contamination of the sorted population by inadvertent inclusion of undesirable particles in droplets containing particles of interest. Summary of the invention

[0015] In one innovative aspect, a computer-implemented method executed under the control of one or more processing devices is provided. The method includes receiving a measurement value of a first portion of particles associated with an experiment from a particle analyzer. The method includes converting the measurement value to an initial transformed measurement value using a non-parametric transformation. The method includes generating a parametric model to receive the measurement value of the first portion of particles associated with the experiment as input and generate the initial transformed measurement value as output. The method also includes configuring the particle analyzer. The particle analyzer is configured to convert the measurement value of particles included in the second portion of the particles based at least in part on the parametric model, and to classify the particles based at least in part on the measurement value and a sorting criterion.

[0016] Some embodiments of the method include receiving gate information identifying a range of measurement values ​​in a non-parametric space for classifying the particles, wherein the sorting criteria comprises the gate information.

[0017] Some embodiments of the method include transmitting the parameter model to the particle analyzer and causing the particle analyzer to configure sorting circuitry based at least in part on the parameter model and the sorting criteria. For example, the sorting circuitry may be implemented in the form of a field programmable gate array.

[0018] The measurements received from the particle analyzer may include measurements of light emitted by the first portion of particles in the form of fluorescence. The light emitted by the first portion of particles in the form of fluorescence may include light emitted by antibodies bound to the first portion of particles in the form of fluorescence.

[0019] Some embodiments of the method may include selecting a measurement value and an initial transformed measurement value of a particle, and generating a composite measurement value pair based at least in part on: (i) the measurement value of the particle, (ii) the initial transformed measurement value of the particle; and (iii) a noise value, wherein the composite measurement value pair includes the composite measurement value and the composite transformed measurement value. The parametric model may further receive the composite measurement value as input and generate the composite transformed measurement value as output. In some embodiments, the method may also include receiving gate information, which identifies a range of measurements for classifying the particle. For example, the particle may be selected based at least in part on the measurement value corresponding to the range of measurements.

[0020] Some embodiments of the method may include receiving a hardware identifier from the particle analyzer, the hardware identifier indicating a sorting circuit implemented in the particle analyzer, and determining an architecture of the parameter model based at least in part on the hardware identifier, wherein the architecture of the parameter model is applicable to the sorting circuit. In such embodiments, generating the parameter model may include generating the parameter model consistent with the architecture. For example, the parameter model may include a neural network, and wherein the architecture identifies the number of layers of the neural network and the number of nodes per layer.

[0021] In an embodiment in which the parameter model includes a neural network, generating the parameter model may include assigning initial weights to connections between a first node in a first layer of the parameter model and a second node in a second layer of the parameter model of a second layer; generating an output applicable to a particle measurement; comparing the output to the transformed measurement of the particle; and adjusting the initial weights based at least in part on a difference between the output and the transformed measurement, wherein a subsequent difference for the particle is less than the difference after adjusting the initial weights.

[0022] In another innovative aspect, a system is provided that includes one or more processing devices and a computer-readable storage medium (including instructions). When the instructions are executed by the one or more processing devices, the system receives a measurement value of a first portion of particles associated with an experiment from a particle analyzer; converts the measurement value to an initial transformed measurement value using a non-parametric transformation; generates a parametric model to receive as input the original measurement value of the first portion of particles associated with the experiment and generates as output the initial transformed measurement value; and configures the particle analyzer. The particle analyzer is configured to convert the measurement value of particles included in the second portion of the particles based at least in part on the parametric model; generates a control signal to adjust the operating state of an analysis device included in the particle analyzer; and transmits the control signal to the analysis device to achieve the operating state.

[0023] In some embodiments, the analysis device may include sorting electronics communicatively coupled to the deflection plates. The particle analyzer may be further configured to identify a target container suitable for particles based at least in part on the converted measurements corresponding to a sorting criterion associated with the target container. Adjusting the operating state may include applying an electrical charge through the deflection plates to direct the particles into the target container. In some embodiments, the analysis device may include a fluidics system, and adjusting the operating state includes adjusting a pressure applied during the experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A functional block diagram of an example of a transformation control system for analyzing and displaying biological events is shown.

[0025] Figure 2A is a schematic diagram of a particle sorter system according to an embodiment described herein.

[0026] Figure 2B is a schematic diagram of a particle sorting system 200 according to an embodiment described herein

[0027] Figure 3 A functional block diagram of a particle analysis system for computation-based sample analysis and particle characterization is shown.

[0028] Figure 4 is a simplified diagram illustrating an example system for dynamically transforming event data.

[0029] Figure 5 is a simplified diagram showing an example system that uses parametric machine learning transformations to dynamically transform event data.

[0030] Figure 6is a process flow diagram depicting an example of a parametric machine learning transformation method applicable to multidimensional event data.

[0031] Figure 7 is a process flow diagram depicting an example of a method for sample sorting using a parametric machine learning transformation. DETAILED DESCRIPTION

[0032] Before describing the present invention in more detail, it should be understood that the present invention is not limited to the specific embodiments described, because there will be differences in actual implementation. It should also be understood that the terms used herein are only used to describe specific embodiments, and are not intended to limit the inventive concept, and the scope of the present invention will only be limited by the appended claims.

[0033] Where a numerical range is provided, it is to be understood that each intermediate value between the upper and lower limits of the range and any other specified value or intermediate value within the range are included within the scope of the present invention. Unless the context clearly specifies otherwise, each intermediate value should be as low as one-tenth of the lower limit unit. The upper and lower limits of these smaller ranges may be independently included within the smaller ranges, and are also included within the present invention, subject to the requirements of any specifically excluded limits within the range. Where the range includes one or two limits, the range excluding any one or two of those included limits is also included within the present invention.

[0034] Certain ranges set forth herein are preceded by the term "about." The term "about" is used herein for the purpose of providing literal support for the exact number that follows, as well as for numbers that are close to or approximately the number that follows the term. In determining whether a number is close to or approximately a specifically recited number, a close or approximately unrecited number may be a number that is substantially equivalent to the specifically recited number in the context in which it appears.

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those of ordinary skill in the art to which the invention belongs. Although methods and materials similar or equivalent to those described herein can also be used in the practice or testing of the present invention, representative exemplary methods and materials are described below.

[0036] All publications and patents cited in this specification are incorporated herein by reference as if each individual publication or patent was specifically and individually indicated to be incorporated by reference, and the purpose of incorporating by reference into this document is to disclose and describe the methods and / or materials related to the cited publications. The citation of any publication is for its disclosure prior to the filing date and should not be construed as an admission that the present invention is not entitled to antedate such publication by reason of prior invention. In addition, the publication dates provided may be different from the actual publication dates, which may need to be independently confirmed.

[0037] It is noted that, as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. It is also noted that claims may be drafted to exclude any optional elements. Thus, this statement is intended to serve as antecedent basis for use of special terminology such as "solely," "only," etc. in connection with reciting claim elements or use of a "negative" limitation.

[0038] After reading the present invention, the following contents will be obvious to those skilled in the art, each individual embodiment described and listed in this patent has layered components and features, which can be quickly decomposed or combined with the features of any of the other several embodiments without departing from the scope and spirit of the present invention. Any stated method can be implemented in the order of events stated or in any other order that is logically possible.

[0039] Although the apparatus and method have been or will be described for grammatical fluency and functional description, it should be clearly understood that unless otherwise expressly provided in Chapter 35 of the United States Code, the claims shall not be construed as necessarily being limited to "means" or "steps" but shall be consistent with the meaning and full scope of equivalents in accordance with the judicial doctrine of equivalents, and when the claims are expressly drafted in accordance with the provisions of Chapter 35 of the United States Code, the claims shall be fully consistent with the statutory equivalents in Chapter 35 of the United States Code.

[0040] Nonparametric transformations, such as t-distributed stochastic neighbor embedding (tSNE), can be used to analyze multiparametric data, such as data from flow cytometry or other particle analysis systems and methods. The present invention may include these transformations for dimensionality reduction and subpopulation identification (e.g., gating). In essence, nonparametric transformations cannot transform new observations without training the new transformation based on the entire data set (including the new observations). This poses a significant challenge to computationally based particle analysis and sample processing based on such analysis (e.g., sorting, instrument control, etc.). The functionality parameterizes nonparametric transformations using neural networks (e.g., artificial neural networks or other computational models trained to approximate the nonparametric transformations), thereby allowing small training data sets to be transformed using nonparametric techniques while allowing accurate parametric models to be generated using the small training data sets so that other events can be evaluated in a manner consistent with the initial event.

[0041] In some embodiments, a small training data set is transformed using a non-parametric transformation such as tSNE (e.g., tens of thousands of examples). The small training data set can be used to synthesize a large training data set. For example, transformed / untransformed pairs are randomly extracted from the small training data set, and random noise is added to the transformed and untransformed data. The random extraction can be weighted arbitrarily, for example, by density, target population, or uniform weight. The added noise can be based on a probability distribution, including a uniform distribution, a Gaussian distribution, or a Poisson distribution.

[0042] The resulting large training data set is used to train a neural network to perform the transformations produced by the nonparametric transformations (which are performed on the small training data set). The neural network can have a variety of architectures, with any number of layers, any number of neurons in a layer, and any activation function between connected neurons. However, in order to facilitate the conversion of the neural network to the configuration of the sorting electronics included in the analytical instrument, the network training can be restricted to the architecture that can be converted to the target analytical instrument. For example, the neural network can be composed of an entry layer (whose number of nodes is equal to the dimension of the untransformed data), four fully connected rectified linear unit (re-lu) activation layers (each with 30 nodes), and an output layer (with two nodes, linear activation). Training can be performed using a variety of error functions (e.g., mean square error, Kullback-Leibler divergence) and optimization procedures (e.g., Adadelta, RMSProp).

[0043] After training, the neural network approximates the transformation that was originally used to transform the small training data set. Thus, the neural network represents the transformation between the space occupied by the original, untransformed data and the space occupied by the transformed data. Thus, the neural network can transform new observations by feeding new data into the input layer and collecting the resulting transformed data in the output layer. The output data can then be used in downstream applications, such as cell sorting decisions.

[0044] The functionality described herein is a significant improvement over existing particle analysis systems, such as systems that include nonparametric transformations. Nonparametric transformations are often used to analyze multiparametric data, such as flow cytometry data. For example, tSNE is used to perform dimensionality reduction on flow cytometry data to visualize cell subpopulations. A fundamental limitation of nonparametric transformations is that, once trained, they cannot be used to transform new observations. Therefore, the introduction of new data requires re-execution of the entire transformation, which often results in a completely different transformation. Therefore, nonparametric transformations have limited utility in areas where new observations need to be analyzed, such as FACS. The functionality described herein overcomes these limitations through nonparametric transformations.

[0045] Other ways to parameterize nonparametric transformations rely on large training sets (e.g., about 100,000 or more data points). The technology described herein utilizes a small training set (which can be used to synthesize a representative data set of sufficient size) to train a machine learning model that produces accurate results using parameterized changes. This saves time and materials for the user and is more compatible with the sample size common when evaluating biological samples. For example, a typical flow cytometry setup experiment typically contains tens of thousands of data points. The number of these data points may be too small to train an accurate neural network. It is time-consuming to require users to collect hundreds of thousands to millions of data points, and a large number of samples are required, which is usually expensive and difficult to obtain.

[0046] Still other approaches to parameterizing non-parametric transformations rely on large, complex neural networks with many layers and many nodes. These large networks are computationally intensive to evaluate and therefore cannot be implemented in sufficiently short computational times for low-latency applications such as cell sorting on sorting electronics with limited processing resources. The techniques described herein utilize a relatively small number of layers and nodes to enable low-latency implementations on resource-efficient sorting electronics such as field programmable gate arrays (FPGAs).

[0047] In the case of flow sorting, the functionality allows the collection of a small data set similar to the data set currently used to establish the sorting gating strategy. Non-parametric transformations can then be performed on the small data set. For example, tSNE can be performed to reduce the dimensionality of the data. The system can then receive a gate specified using the data after tSNE transformation. The pre-tSNE data and the post-tSNE data are then used to train a neural network that learns the transformation between the original data space and the reduced dimensionality space. The trained neural network can then be programmed into an FPGA and used to sort cells (or other particles) for actual sorting experiments. In previous implementations, sorting could not be performed based on data transformed using non-parametric transformations.

[0048] In some embodiments, the transformation model includes a dynamic algorithm, such as a machine learning algorithm. According to the conventional meaning, the term "machine learning" used herein refers to the adjustment of programming by computational methods, which directly use data to determine and implement information without relying on predetermined equations as models. In certain embodiments, machine learning includes a learning algorithm that finds patterns in data signals (e.g., from a variety of particles in a flow cytometry sample). In these embodiments, the learning algorithm is configured to generate better and more accurate decisions and predictions based on the number of data signals (i.e., as the number of characterization particles from the sample increases, the learning algorithm becomes more robust). Purpose machine learning schemes may include, but are not limited to, artificial neural networks, decision tree learning, decision tree predictive modeling, support vector machines, Bayesian networks, dynamic Bayesian networks, genetic algorithms, and other machine learning schemes.

[0049] A neural network or neural network model can be conceptualized as a network of nodes. The nodes can be organized into layers, where the first layer is an input layer into which data flows. The neural network can also include an output layer, from which transformed data flows out. Each individual node can have multiple inputs and a single output (e.g., an input layer node has only a single input). The output of a node represents a linear combination of the inputs. In other words, the inputs can be multiplied by a relevant constant. The product can be accumulated along a path of nodes with a constant bias. The constant bias or "bias" can represent another degree of freedom that can be adjusted during the training process. For example, for a re-lu based neural network model, the constant bias can be a threshold because it has the ability to reduce the node value below zero, thereby causing the activation function to output zero.

[0050] The resulting value is evaluated using an activation function and used as the output of the node. A node in a given layer of the neural network is connected to each node in an adjacent layer. A neural network can be trained by comparing the desired output of the network with the actual output of the network using a gradient descent algorithm and an error function to minimize the error of the network. The weights of one or more nodes can be adjusted to model the desired results produced by the network.

[0051] Typically, neural networks require a large amount of data for training. In this article, a small data set can be used for training by bootstrapping (generating synthetic data based on the small data set). According to the conventional meaning, the term "bootstrapping" used in this article refers to generating one or more additional data sets with a larger amount of data than the original data set, such as generating a data set with 10 data points or more (e.g., 100 data points or more, 1000 data points or more, 100,000 data points or more, and including 1,000,000 data points or more) more than the original data set. In some cases, the data points included in the generated data set are increased by 2 times or more compared to the original data set, such as 3 times or more, 5 times or more, 10 times or more, 25 times or more, 50 times or more, 100 times or more, and including 1000 times or more. In some embodiments, bootstrapping includes random permutable sampling. In some embodiments, bootstrapping includes estimating the characteristics of the estimation function (e.g., by variance) by measuring the characteristics when sampling from an approximate distribution (e.g., an empirical distribution function). Bootstrapping according to certain embodiments may include using data from the flow cytometer in combination with noise components generated by the flow cytometer, such as vibrations from the laser assembly or detection system and noise from the photodetector.

[0052] Careful selection of the neural network architecture to minimize the number of nodes per layer and the number of layers allows the neural network to be implemented in computing hardware (e.g., FPGAs). In addition, the selection of activation functions that are compatible with FPGAs can further facilitate hardware implementation of the network. Hardware implementation is critical for the data transformation to have sufficiently low latency for cell sorting applications.

[0053] The terms used herein and specifically set forth below have the following definitions. Unless otherwise defined in this section, all terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0054] As used herein, "system," "apparatus," "device," and "equipment" generally encompass hardware (e.g., mechanical and electronic hardware) and, in some embodiments, related software (e.g., a dedicated computer program for graphics control) components.

[0055] As used herein, "event" or "event data" generally refers to a data packet measured from a single particle (e.g., a cell or a synthetic particle). Typically, the data measured from a single particle includes a number of parameters, including one or more light scattering parameters, and at least one parameter or feature derived from fluorescence detected from the particle, such as the fluorescence intensity. Thus, each event is represented as a measurement value and a feature vector, where each measured parameter or feature corresponds to a dimension of the data space. In some embodiments, the data measured from a single particle includes images, electrical data, time data, or acoustic data. An event can be associated with an experiment, assay, or sample source (which can be identified by the measurement data).

[0056] As used herein, a "population" or "subpopulation" of particles (e.g., cells or other particles) generally refers to a group of particles having properties (e.g., optical, impedance, or time properties) relative to one or more measured parameters that cause the measured parameter data to form clusters in the data space. Thus, a population is identified as a cluster in the data. In contrast, each data cluster is typically interpreted as corresponding to a particular type of cell or particle population, although clusters corresponding to noise or background are also typically observed. Clusters can be defined in a subset of the dimensions (e.g., a subset relative to the measured parameters), corresponding to populations that differ only in a subset of the measured parameters or features (extracted from the cell or particle measurements).

[0057] As used herein, "gate" generally refers to the boundaries of a classifier that identifies a subset of data of interest. In cytometry, a gate may be associated with a specific set of events of interest. As used herein, "gating" generally refers to the process of classifying a given data set using a defined gate, where the gate can be one or more regions of interest combined with Boolean logic.

[0058] As used herein, an "event" generally refers to an assembled package of data measured from a single particle (e.g., a cell or synthetic particle). Typically, the data measured from a single particle includes many parameters or features, including one or more light scattering parameters or features, and at least one other parameter or feature derived from the measured fluorescence. Thus, each event is represented as a vector of parameter and feature measurements, where each measured parameter or feature corresponds to a dimension of the data space.

[0059] Aspects of the present invention also include systems having a light detection system to characterize particles in a sample within a fluid medium (e.g., cells in a biological sample). Systems according to certain embodiments include: a light source configured to irradiate a sample (having particles) in a fluid medium; a light detection system including a photodetector, the photodetector configured to generate a data signal using light detected from particles within the fluid medium; and a processor having a memory operably coupled to itself, wherein the memory has instructions stored thereon, which, when executed by the processor, cause the processor to perform the following operations: applying a nonparametric transformation to a first set of data signals from the light detection system to generate a first transformed data set; generating a second transformed data set using the first transformed data set; generating a transformation model using the second transformed data set; and applying the transformation model to a second set of data signals from the light detection system.

[0060] The purpose system includes a light source configured to irradiate a sample in a fluid medium. In an embodiment, the light source can be any suitable broadband or narrowband light source. Depending on the components in the sample (e.g., cells, microbeads, non-cellular particles, etc.), the light source can be configured to emit light of different wavelengths in the range of 200nm to 1500nm, for example, 250nm to 1250, 300nm to 1000nm, 350nm to 900nm, including 400nm to 800nm. For example, the light source may include a broadband light source with a wavelength range of 200nm to 900nm for the emitted light. In other cases, the light source includes a narrowband light source with a wavelength range of 200nm to 900nm for the emitted light. For example, the light source can be a narrowband LED (1nm–25nm) with a wavelength range of 200nm to 900nm for the emitted light.

[0061] In some embodiments, the light source is a laser. The target laser may include a pulsed laser or a continuous wave laser. For example, the laser may be a gas laser, such as a helium-neon laser, an argon laser, a krypton laser, a xenon laser, a nitrogen laser, a CO2 laser, a CO laser, an argon fluoride (ArF) excimer laser, a krypton fluoride (KrF) excimer laser, a xenon chloride (XeCl) excimer laser, or a xenon fluoride (XeF) excimer laser, or a combination thereof; or a metal vapor laser, such as a helium cadmium (HeCd) laser, a helium mercury (HeHg) laser, a helium selenium ( The laser may be a HeSe laser, a helium silver (HeAg) laser, a strontium laser, a neon copper (NeCu) laser, a copper laser or a gold laser, and combinations thereof; or a solid-state laser, for example, a ruby ​​laser, a Nd:YAG laser, a NdCrYAG laser, an Er:YAG laser, a Nd:YLF laser, a Nd:YVO4 laser, a Nd:YCa4O(BO3)3 laser, a Nd:YCOB laser, a titanium sapphire laser, a thulim YAG laser, a YAG ytterbium laser, an ytterbium trioxide laser or a cerium-doped laser, and combinations thereof; or a semiconductor diode laser, an optically pumped semiconductor laser (OPSL) or a frequency doubled or frequency tripled implementation of any of the above lasers.

[0062] In other embodiments, the light source is a non-laser light source, such as a lamp (including but not limited to a halogen lamp, a deuterium arc lamp, a xenon arc lamp), a light emitting diode (e.g., a broadband LED with a continuous spectrum, a superluminescent diode, a semiconductor light emitting diode, a wide spectrum LED white light source, a plurality of LED integrated light sources). In some cases, the non-laser light source is a stable fiber-coupled broadband light source, a white light source, and other light sources or any combination thereof.

[0063] In some embodiments, the light source is a beam generator configured to generate two or more beams of frequency-shifted light. In some cases, the beam generator includes a laser and a radio frequency generator, and the radio frequency generator is configured to apply a radio frequency drive signal to the acousto-optic device to generate two or more angle-deflected laser beams. In these embodiments, the laser can be a pulsed laser or a continuous wave laser. For example, the laser in the target beam generator can be a gas laser, such as a helium-neon laser, an argon laser, a krypton laser, a xenon laser, a nitrogen laser, a CO2 laser, a CO laser, an argon fluoride (ArF) excimer laser, a krypton fluoride (KrF) excimer laser, a xenon chloride (XeCl) excimer laser, or a xenon fluoride (XeF) excimer laser, or a combination thereof; or a metal vapor laser, such as a helium cadmium (HeCd) laser, a helium mercury (HeHg) laser, Helium selenium (HeSe) laser, helium silver (HeAg) laser, strontium laser, neon copper (NeCu) laser, copper laser or gold laser and combinations thereof; or a solid-state laser, for example, a ruby ​​laser, Nd:YAG laser, NdCrYAG laser, Er:YAG laser, Nd:YLF laser, Nd:YVO4 laser, Nd:YCa4O(BO3)3 laser, Nd:YCOB laser, titanium sapphire laser, thulim YAG laser, Ytterbium YAG laser, ytterbium trioxide laser or cerium-doped laser and combinations thereof.

[0064] The acousto-optic device can be any suitable acousto-optic scheme configured to frequency shift a laser using an applied acoustic wave. In some embodiments, the acousto-optic device is an acousto-optic deflector. The acousto-optic device in the target system is configured to generate an angle-deflected laser beam using light from a laser and an applied RF drive signal. The RF drive signal can be applied to the acousto-optic device using any suitable RF drive signal source, such as a direct digital frequency synthesizer (DDS), an arbitrary waveform generator (AWG), or an electrical pulse generator.

[0065] In an embodiment, the controller is configured to apply an RF drive signal to the acousto-optic device to produce a desired number of angularly deflected laser beams in the output laser beam, for example, configured to apply 3 or more RF drive signals, 4 or more RF drive signals, 5 or more RF drive signals, 6 or more RF drive signals, 7 or more RF drive signals, 8 or more RF drive signals, 9 or more RF drive signals, 10 or more RF drive signals, 15 or more RF drive signals, 25 or more RF drive signals, 50 or more RF drive signals, including being configured to apply 100 or more RF drive signals.

[0066] In some cases, in order to obtain the intensity distribution of the angularly deflected laser beam in the output laser beam, the controller is configured to apply RF drive signals with different amplitudes, for example, the amplitude ranges from about 0.001V to about 500V, about 0.005V to about 400V, about 0.01V to about 300V, about 0.05V to about 200V, about 0.1V to about 100V, about 0.5V to about 75V, about 1V to 50V, about 2V to 40V, 3V to about 30V, including about 5V to about 25V. In some embodiments, each applied RF drive signal has a frequency ranging from about 0.001 MHz to about 500 MHz, for example, from about 0.005 MHz to about 400 MHz, from about 0.01 MHz to about 300 MHz, from about 0.05 MHz to about 200 MHz, from about 0.1 MHz to about 100 MHz, from about 0.5 MHz to about 90 MHz, from about 1 MHz to about 75 MHz, from about 2 MHz to about 70 MHz, from about 3 MHz to about 65 MHz, from about 4 MHz to about 60 MHz, including from about 5 MHz to about 50 MHz.

[0067] In some embodiments, the controller has a processor having a memory operably coupled thereto such that the memory includes instructions stored thereon that, when executed by the processor, cause the processor to generate an output laser beam having an angularly deflected laser beam having a desired intensity distribution. For example, the memory may include instructions to generate two or more angularly deflected laser beams having the same intensity, for example, 3 or more, 4 or more, 5 or more, 10 or more, 25 or more, 50 or more, and include the following memory: that is, a memory that may include instructions to generate 100 or more angularly deflected laser beams having the same intensity. In other embodiments, the memory may include instructions to generate two or more angularly deflected laser beams having different intensities, for example, 3 or more, 4 or more, 5 or more, 10 or more, 25 or more, 50 or more, and include the following memory: that is, a memory that may include instructions to generate 100 or more angularly deflected laser beams having different intensities.

[0068] In certain embodiments, the controller has a processor having a memory operably coupled thereto such that the memory includes instructions stored thereon that, when executed by the processor, cause the processor to generate an output laser beam having an intensity along a transverse axis that increases gradually from the edge to the center thereof. In these cases, the intensity of the angularly deflected laser beam measured at the center of the output beam can be 0.1% to about 99% of the intensity of the angularly deflected laser beam measured at the edge of the output laser beam along the transverse axis, for example, 0.5% to about 95%, 1% to about 90%, about 2% to about 85%, about 3% to about 80%, about 4% to about 75%, about 5% to about 70%, about 6% to about 65%, about 7% to about 60%, about 8% to about 55%, including about 10% to about 50% of the intensity of the angularly deflected laser beam measured at the edge of the output laser beam along the transverse axis. In other embodiments, the controller has a processor having a memory operably coupled thereto such that the memory includes instructions stored thereon that, when executed by the processor, cause the processor to generate an output laser beam having an intensity that increases gradually from the edge to the center thereof along the transverse axis. In these cases, the intensity of the angularly deflected laser beam measured at the edge of the output beam can be from 0.1% to about 99% of the intensity of the angularly deflected laser beam measured at the center of the output laser beam along the transverse axis, for example, from 0.5% to about 95%, from 1% to about 90%, from about 2% to about 85%, from about 3% to about 80%, from about 4% to about 75%, from about 5% to about 70%, from about 6% to about 65%, from about 7% to about 60%, from about 8% to about 55%, including from about 10% to about 50% of the intensity of the angularly deflected laser beam measured at the center of the output laser beam along the transverse axis. In other embodiments, the controller has a processor having a memory operably coupled thereto, such that the memory includes instructions stored thereon, which when executed by the processor, cause the processor to generate an output laser beam having an intensity distribution along the horizontal axis that conforms to a Gaussian distribution. In certain embodiments, the controller has a processor having a memory operably coupled thereto, such that the memory includes instructions stored thereon, which when executed by the processor, cause the processor to generate an output laser beam having a top-hat intensity distribution along the horizontal axis.

[0069] In an embodiment, the purpose beam generator can be configured to generate spatially separated angular deflected laser beams in the output laser beam. Depending on the applied RF drive signal and the desired irradiation profile of the output laser beam, the spacing between the angular deflected laser beams can be 0.001m or more, for example, 0.005μm or more, 0.01μm or more, 0.05μm or more, 0.1μm or more, 0.5μm or more, 1μm or more, 5μm or more, 10μm or more, 100μm or more, 500μm or more, 1000μm or more, including 5000μm or more. In some embodiments, the system is configured to generate overlapping angular deflected laser beams in the output laser beam, for example, overlapping with adjacent angular deflected laser beams distributed along the horizontal axis of the output laser beam. The overlapping portion between adjacent angle-deflected laser beams (e.g., beam spot overlap) can be an overlap of 0.001 μm or more, for example, an overlap of 0.005 μm or more, an overlap of 0.01 μm or more, an overlap of 0.05 μm or more, an overlap of 0.1 μm or more, an overlap of 0.5 μm or more, an overlap of 1 μm or more, an overlap of 5 μm or more, an overlap of 10 μm or more, including an overlap of 100 μm or more.

[0070] In some cases, a beam generator configured to generate two or more beams of frequency-shifted light includes a laser excitation module described in the following publications: U.S. Patent Nos. 9,423,353, 9,784,661, and 10,006,852; and U.S. Patent Publication Nos. 2017 / 0133857 and 2017 / 0350803, the contents of which are incorporated herein by reference.

[0071] In an embodiment, the system includes a light detection system having one or more of a bright field photodetector, a light scattering (forward light scattering, side light scattering) detector, and a fluorescence detector for detecting and measuring light from the sample. The target bright field, light scattering, and fluorescence detectors may include, but are not limited to, optical sensors, such as active pixel sensors (APS), avalanche photodiodes, image sensors, charge coupled devices (CCD), enhanced charge coupled devices (ICCD), light emitting diodes, photon counters, bolometers, pyroelectric detectors, photoresistors, photovoltaic cells, photodiodes, photomultipliers, phototransistors, quantum dot photoconductors or photodiodes, and combinations thereof, and other photodetectors. In certain embodiments, a charge coupled device (CCD), a semiconductor charge coupled device (CCD), an active pixel sensor (APS), a complementary metal oxide semiconductor (CMOS), an image sensor, or an N-type metal oxide semiconductor (NMOS) image sensor is used to measure light from the sample. In certain embodiments, the bright field photodetector includes an avalanche photodiode (APD). In some cases, the light scattering detector is an avalanche photodiode. In some cases, one or more of the fluorescence detectors is an avalanche photodiode.

[0072] In some embodiments, the optical detection system of interest includes a plurality of fluorescence detectors. In some cases, the optical detection system includes a plurality of solid-state detectors, such as photodiodes. In some cases, the optical detection system includes a fluorescence photodetector array, such as a photodiode array. In these embodiments, the photodetector array may include 4 or more photodetectors, for example, 10 or more photodetectors, 25 or more photodetectors, 50 or more photodetectors, 100 or more photodetectors, 250 or more photodetectors, 500 or more photodetectors, 750 or more photodetectors, including 1000 or more photodetectors. For example, the detector may be a photodiode array having 4 or more photodiodes, for example, 10 or more photodiodes, 25 or more photodiodes, 50 or more photodiodes, 100 or more photodiodes, 250 or more photodiodes, 500 or more photodiodes, 750 or more photodiodes, including 1000 or more photodiodes.

[0073] The photodetectors may be arranged in any geometric configuration as desired, wherein the intended arrangement configurations include but are not limited to square configurations, rectangular configurations, trapezoidal configurations, triangular configurations, hexagonal configurations, heptagonal configurations, octagonal configurations, nonagonal configurations, decagonal configurations, dodecagonal configurations, circular configurations, elliptical configurations, and irregular pattern configurations. The photodetectors in the photodetector array may be oriented at an angle to another photodetector (as described in the XZ plane), the angle ranging from 10° to 180°, for example, 15° to 170°, 20° to 160°, 25° to 150°, 30° to 120°, including 45° to 90°. The photodetector array may be of any suitable shape, and may be a shape surrounded by straight lines (e.g., square, rectangular, trapezoidal, triangular, hexagonal, etc.), a shape surrounded by curves (e.g., circular, elliptical), and an irregular shape (e.g., a parabolic bottom connected to a flat top). In certain embodiments, the photodetector array has a rectangular active surface.

[0074] The active surface width of each photodetector (e.g., photodiode) in the array ranges from 5 μm to 250 μm, for example, 10 μm to 225 μm, 15 μm to 200 μm, 20 μm to 175 μm, 25 μm to 150 μm, 30 μm to 125 μm, including 50 μm to 100 μm; its length ranges from 5 μm to 250 μm, for example, 10 μm to 225 μm, 15 μm to 200 μm, 20 μm to 175 μm, 25 μm to 150 μm, 30 μm to 125 μm, including 50 μm to 100 μm. μm, 25μm to 150μm, 30μm to 125μm, including 50μm to 100μm; wherein the surface area of ​​each photodetector (e.g., photodiode) in the array ranges from 25μm2 to 10000μm2, for example, 50μm2 to 9000μm2, 75μm2 to 8000μm2, 100μm2 to 7000μm2, 150μm2 to 6000μm2, including 200μm2 to 5000μm2.

[0075] The size of the photodetector array may vary depending on the amount and intensity of light, the number of photodetectors and the required sensitivity, and may range in length from 0.01 mm to 100 mm, for example, 0.05 mm to 90 mm, 0.1 mm to 80 mm, 0.5 mm to 70 mm, 1 mm to 60 mm, 2 mm to 50 mm, 3 mm to 40 mm, 4 mm to 30 mm, including 5 mm to 25 mm. The width of the photodetector array may also vary, ranging from 0.01 mm to 100 mm, for example, 0.05 mm to 90 mm, 0.1 mm to 80 mm, 0.5 mm to 70 mm, 1 mm to 60 mm, 2 mm to 50 mm, 3 mm to 40 mm, 4 mm to 30 mm, including 5 mm to 25 mm. Thus, the surface area of ​​the active surface of the photodetector array ranges from 0.1 mm2 to 10000 mm2, for example, 0.5 mm2 to 5000 mm2, 1 mm2 to 1000 mm2, 5 mm2 to 500 mm2, including 10 mm2 to 100 mm2.

[0076] The intended photodetector is configured to measure light collected at one or more wavelengths, for example, 2 or more wavelengths, 5 or more different wavelengths, 10 or more different wavelengths, 25 or more different wavelengths, 50 or more different wavelengths, 100 or more different wavelengths, 200 or more different wavelengths, 300 or more different wavelengths, including measuring light emitted by a sample in a fluid medium at 400 or more different wavelengths.

[0077] In some embodiments, the light detection system includes a bright field photodetector configured to generate a bright field data signal. The bright field photodetector may be configured to detect light from the sample at one or more wavelengths, such as 5 or more different wavelengths, 10 or more different wavelengths, 25 or more different wavelengths, 50 or more different wavelengths, 100 or more different wavelengths, 200 or more different wavelengths, 300 or more different wavelengths, including detecting light at 400 or more different wavelengths. The bright field photodetector may be configured to detect light at one or more wavelengths in the wavelength range of 200nm–1200nm. In some cases, the method includes detecting light from the sample with a bright field photodetector within a certain wavelength range, for example, 200nm to 1200nm, 300nm to 1100, 400nm to 1000nm, 500nm to 900nm, including 600nm to 800nm.

[0078] In some embodiments, the brightfield photodetector in the target light detection system is configured to generate one or more brightfield data signals in response to the detected light, such as 2 or more, 3 or more, 4 or more, 5 or more, and including 10 or more brightfield data signals in response to the detected light. In the case where the brightfield photodetector is configured to detect light at multiple light wavelengths (e.g., 400nm to 800nm), the method may include, in some cases, generating one or more brightfield data signals in response to each wavelength of the detected light. In other cases, a single brightfield data signal is generated in response to light detected by the brightfield photodetector over the entire wavelength range.

[0079] In some embodiments, the light detection system includes a light scattering photodetector configured to generate a light scattering data signal. The light scattering photodetector may be configured to detect light from the sample at one or more wavelengths, such as 5 or more different wavelengths, 10 or more different wavelengths, 25 or more different wavelengths, 50 or more different wavelengths, 100 or more different wavelengths, 200 or more different wavelengths, 300 or more different wavelengths, including detecting light at 400 or more different wavelengths. The light scattering photodetector may be configured to detect light at one or more wavelengths in the wavelength range of 200nm–1200nm. In some cases, the method includes detecting light from the sample with a light scattering photodetector within a certain wavelength range, for example, 200nm to 1200nm, 300nm to 1100, 400nm to 1000nm, 500nm to 900nm, including 600nm to 800nm.

[0080] In certain embodiments, the light scattering photodetector in the target light detection system is configured to generate one or more light scattering data signals in response to the detected light, such as 2 or more, 3 or more, 4 or more, 5 or more, and including 10 or more light scattering data signals in response to the detected light. In the case where the light scattering photodetector is configured to detect light at multiple light wavelengths (e.g., 400nm to 800nm), the method may include, in some cases, generating one or more light scattering data signals in response to each wavelength of the detected light. In other cases, a single light scattering data signal is generated in response to light detected by the light scattering photodetector over the entire wavelength range.

[0081] The light detection system includes one or more bright field, light scattering or fluorescence detectors, for example, 2 or more, 3 or more, 4 or more, 5 or more, 6 or more, 7 or more, 8 or more, 9 or more, 10 or more, 15 or more, including 25 or more detectors. In an embodiment, each of the detectors is configured to generate a data signal. Each detector can be independently used to detect light from the sample at one or more wavelengths in the wavelength range of 200nm–1200nm. In some cases, one or more detectors are configured to detect light from the sample within a certain wavelength range, for example, 200nm to 1200nm, 300nm to 1100, 400nm to 1000nm, 500nm to 900nm, including 600nm to 800nm. In other cases, one or more detectors are configured to detect light at one or more specific wavelengths. For example, the fluorescence can be detected at one or more wavelengths of 450nm, 518nm, 519nm, 561nm, 578nm, 605nm, 607nm, 625nm, 650nm, 660nm, 667nm, 670nm, 668nm, 695nm, 710nm, 723nm, 780nm, 785nm, 647nm, 617nm, and any combination thereof, depending on the number of different detectors in the target light detection system. In some embodiments, one or more detectors are configured to detect wavelengths of light corresponding to the peak fluorescence wavelengths of certain fluorophores in the sample.

[0082] The light detection system is configured to measure light continuously or at discrete time intervals. In some cases, the detectors in the light detection system are configured to measure the collected light continuously. In other cases, the light detection system is configured to measure at discrete time intervals, for example, the time intervals for measuring light are 0.001 milliseconds, 0.01 milliseconds, 0.1 milliseconds, 1 millisecond, 10 milliseconds, 100 milliseconds, including 1000 milliseconds or some other time intervals.

[0083] In some embodiments, the system is configured to generate frequency-encoded fluorescence data by irradiating a sample (having particles) in a fluid medium. In some embodiments, the light source includes a light generator assembly that generates multiple angularly deflected laser beams, each laser beam having an intensity based on the amplitude of an applied RF drive signal (e.g., from a direct digital synthesizer coupled to an acousto-optic device). For example, the target system may include a light generator assembly that generates 2 or more angularly deflected laser beams, for example, 3 or more, 4 or more, 5 or more, 6 or more, 7 or more, 8 or more, 9 or more, 10 or more, and includes 25 or more angularly deflected laser beams. In an embodiment, each of the angularly deflected laser beams has a different frequency, and the frequency is offset by a predetermined RF compared to the frequency of the input laser beam.

[0084] The target system is configured to generate angled deflected laser beams that are spatially offset from each other according to certain embodiments. Depending on the applied RF drive signal and the desired irradiation profile of the output laser beam, the target system can be configured to generate angled deflected laser beams, and the spacing between the laser beams can be 0.001 μm or more, for example, 0.005 μm or more, 0.01 μm or more, 0.05 μm or more, 0.1 μm or more, 0.5 μm or more, 1 μm or more, 5 μm or more, 10 μm or more, 100 μm or more, 500 μm or more, 1000 μm or more, including 5000 μm or more. In some embodiments, the angled deflected laser beams overlap, for example, with adjacent angled deflected laser beams distributed along the horizontal axis of the output laser beam. The overlapping portion between adjacent angle-deflected laser beams (e.g., beam spot overlap) can be an overlap of 0.001 μm or more, for example, an overlap of 0.005 μm or more, an overlap of 0.01 μm or more, an overlap of 0.05 μm or more, an overlap of 0.1 μm or more, an overlap of 0.5 μm or more, an overlap of 1 μm or more, an overlap of 5 μm or more, an overlap of 10 μm or more, including an overlap of 100 μm or more.

[0085] In some embodiments, a system includes a processor having a memory operably coupled thereto, wherein the memory includes instructions stored thereon, which when executed by the processor, cause the processor to perform the following operations: generate frequency-encoded fluorescence data by calculating the difference between the optical frequencies of incident overlapping sub-beams of light on the fluid medium. In one example, a system includes a processor having a memory operably coupled thereto, wherein the memory includes instructions stored thereon, which when executed by the processor, cause the processor to calculate a beat frequency at each position on the horizontal axis of the fluid medium. In these embodiments, the frequency-encoded fluorescence emitted by the particles is a beat frequency corresponding to the difference between the frequency of the local oscillator beam (fLO) and the frequency of the radio frequency offset sub-beam. For example, the frequency-encoded fluorescence data includes the beat frequency of the fLO-fRF offset sub-beam. In the case where the irradiation of the fluid medium includes a local oscillator that spans the width of the fluid medium (e.g., the entire horizontal axis), the frequency-encoded fluorescence data includes a beat frequency corresponding to the difference between the frequency of the local oscillator beam (fLO) and the frequency of each RF offset beamlet (f1, f2, f3, f4, f5, f6, etc.). In these embodiments, the frequency-encoded fluorescence data may include multiple beat frequencies, each beat frequency corresponding to a position on the horizontal axis of the fluid medium.

[0086] In some embodiments, the subject system includes a particle sorting component for sorting particles (e.g., cells) in the sample. In some cases, the particle sorting component is a particle sorting module, for example, a particle sorting module described in the following publications: U.S. Patent Publication No. 2017 / 0299493 filed on March 28, 2017; and U.S. Provisional Patent Application No. 62 / 752,793 filed on October 30, 2018, the contents of which are incorporated herein by reference. In some embodiments, the particle sorting component includes one or more droplet deflectors, for example, a droplet deflector described in U.S. Patent Publication No. 2018 / 0095022 filed on June 14, 2017, the contents of which are incorporated herein by reference.

[0087] In some embodiments, the subject system is a flow cytometry system. Suitable flow cytometry systems may include, but are not limited to, those described in the following publications: Ormerod (ed.), Flow Cytometry: A Practical Approach, Oxford University Press (1997); Jaroszeski et al. (eds.), Flow Cytometry Protocols, Methods in Molecular Biology 91, Humana Press (1997); Practical Flow Cytometry, 3rd ed., Wiley-Liss (1995); Virgo et al. (2012), Annals of Clinical Biochemistry, January; 49(pt 1): 17-28; Linden et al., Seminars in Thrombosis and Hemostasis, October 2004; 30(5): 502-11; Alison et al., Journal of Pathology, December 2010; 222(4): 335-344; and Herbig et al. (2007) Crit Rev Ther Drug Carrier Syst. 24(3): 203-255; the contents of these publications are incorporated herein by reference. In some cases, the flow cytometry system of interest includes BD Biosciences FACSCanto™ II flow cytometer, BD Accuri™ flow cytometer, BD Biosciences FACSCelesta™ flow cytometer, BD Biosciences FACSLyric™ flow cytometer, BD Biosciences FACSVerse™ flow cytometer, BD Biosciences FACSymphony™ flow cytometer, BD Biosciences LSRFortessa™ flow cytometer, BD Biosciences LSRFortess™ X-20 flow cytometer, and BD Biosciences FACSCalibur™ cell sorter, BD Biosciences FACSCount™ cell sorter, BD Biosciences FACSLyric™ cell sorter, BD Biosciences Via™ cell sorter, BD Biosciences Influx TM Cell sorter, BD Biosciences Jazz TM Cell sorter, BD Biosciences Aria TM Cell Sorter and BD Biosciences FACSMelody TM Cell sorter, etc.

[0088] In some embodiments, the target particle sorting system is a flow cytometry system, for example, a system described in the following U.S. Patent Nos. 10,006,852; 9,952,076; 9,933,341; 9,784,661; 9,726,527; 9,453,789; 9,200,334; 9,097,640; 9,095,494; 9,092,034; 8,975,595; 8,753,5 The contents of these documents are incorporated herein by reference in their entirety.

[0089] In some cases, the target system is a flow cytometry system configured to characterize and image particles in a fluid medium by fluorescence imaging using radio frequency labeled emission (FIRE), such as the systems described in Diebold et al., Nature Photonics, Vol. 7(10); 806-810 (2013); U.S. Pat. Nos. 9,423,353, 9,784,661, and 10,006,852; and U.S. Pat. Nos. 2017 / 0133857 and 2017 / 0350803, the contents of which are incorporated herein by reference.

[0090] Specific examples of various embodiments and systems in which the embodiments and systems may be implemented are described further below.

[0091] Figure 1 A functional block diagram of an example of a transformation control system for analyzing and displaying biological events is shown. The analysis controller 190 may be configured to implement various processes for controlling the graphical display of biological events.

[0092] The particle analyzer 102 may be configured to collect biological event data. For example, a flow cytometer may generate flow cytometry event data. The particle analyzer 102 may be configured to provide the biological event data to the analysis controller 190. A data communication channel may be included between the particle analyzer 102 and the analysis controller 190. The biological event data may be provided to the analysis controller 190 via the data communication channel.

[0093] Analysis controller 190 may be configured to receive biological event data from particle analyzer 102. The biological event data received from particle analyzer 102 may include flow cytometry event data. Analysis controller 190 may be configured to provide a graphical display including a first graph of biological event data to display device 106. Analysis controller 190 may be further configured to render a region of interest as a gate around the plurality of biological event data shown by display device 106, which is overlaid on the first graph. In some embodiments, the gate may be a logical combination of one or more graphical regions of interest drawn on a single parameter histogram or a bivariate graph.

[0094] Analysis controller 190 may further be configured to display the bio-event data on display device 106 inside the door in a manner different from other events in the bio-event data outside the door. For example, analysis controller 190 may be configured to make the color of the bio-event data contained inside the door different from the color of the bio-event data outside the door. Display device 106 may be implemented in the form of a display, tablet computer, smart phone, or other electronic device configured to display a graphical interface.

[0095] The analysis controller 190 can be configured to receive a door selection signal identifying the door from a first input device. For example, the first input device can be implemented in the form of a mouse 110. The mouse 110 can send a door selection signal to the analysis controller 190 to determine the door to be displayed on the display device 106 or manipulated via the display device 106 (for example, clicking on or in the desired door when the cursor is located there). In some embodiments, the first device can be implemented in the form of a keyboard 108 or other device for providing input signals to the analysis controller 190 (such as a touch screen, a stylus, an optical detector, or a voice recognition system). Some input devices may include multiple input functions. In such embodiments, the input functions can be individually regarded as input devices. For example, as Figure 1 As shown, the mouse 110 may include a right mouse button and a left mouse button, both of which may generate a trigger event.

[0096] The trigger event may cause the analysis controller 190 to change the way the data is displayed (actually display a portion of the data on the display device 106), or provide input for further processing, such as selecting a target population for particle sorting.

[0097] In some embodiments, analysis controller 190 may be configured to detect when mouse 110 initiates gate selection. Analysis controller 190 may further be configured to automatically modify the graph visualization to facilitate the gating process. The modification may be based on a particular distribution of bio-event data received by analysis controller 190.

[0098] Analysis controller 190 may be coupled to storage device 104. Storage device 104 may be configured to receive and store biological event data from analysis controller 190. Storage device 104 may also be configured to receive and store flow cytometry event data from analysis controller 190. Storage device 104 may also be configured to allow analysis controller 190 to retrieve biological event data, e.g., flow cytometry event data.

[0099] The display device 106 can be configured to receive display data from the analysis controller 190. The display data can include graphs of biological event data and gates outlining portions of the graphs. The display device 106 can be further configured to change the information displayed based on input received from the analysis controller 190 and input received from the particle analyzer 102, the storage device 104, the keyboard 108, and / or the mouse 110.

[0100] A common flow sorting technique (referred to as "electrostatic cell sorting") employs droplet sorting, in which a stream or moving column of liquid containing linearly separated particles is broken into droplets, and the droplets containing the particles of interest are charged and deflected into a collection tube by an electric field. Current droplet sorting systems are capable of forming droplets at a rate of 100,000 drops per second in a fluid medium passing through a nozzle having a diameter of less than 100 microns. Droplet sorting typically requires that the droplets detach from the stream at a certain distance from the nozzle head. The distance is typically about a few millimeters from the nozzle head, and for an undisturbed fluid medium, the distance is stable and can be maintained by oscillating the nozzle head at a predetermined frequency and an amplitude that keeps the detachment constant. For example, in some embodiments, the amplitude of a sinusoidal waveform voltage pulse is adjusted at a given frequency to keep the detachment stable and constant.

[0101] Typically, linearly separated particles in the stream are characterized by their passage through an observation point located within a flow cell or cuvette or directly below a nozzle tip. Once a particle is determined to meet one or more of the desired criteria, it is possible to predict when it will reach the droplet breakup point and detach from the stream as a droplet. Ideally, a brief charge is applied to the fluid medium before the droplets containing the selected particles detach from the stream, and then the droplets are grounded immediately after breakup. The droplets to be sorted will remain charged when they detach from the fluid medium, while all other droplets will be uncharged. The charged droplets are deflected laterally from the downward trajectory of the other droplets by the electric field and are collected in a sample tube. The uncharged droplets fall directly into a discharge tube.

[0102] Figure 2A is a schematic diagram of a particle sorter system according to an embodiment described herein. Figure 2AThe particle sorter system 250 shown includes deflection plates 252 and 254. Charge is applied via a stream of charge wires in the barbs 256. This creates a particle stream 260 for analysis. The particles can be illuminated with one or more light sources (e.g., lasers) to produce light scattering and generate fluorescence information. The particle information is detected by, for example, sorting electronics or other detection systems ( Figure 2A The deflection plates 252 and 254 can be independently controlled to attract or repel the charged droplets to direct the droplets to a destination collection container (e.g., one of 272, 274, 276, or 278). Figure 2A As shown, the deflector plate can be controlled to direct the particles along the first path 262 toward the container 274 or along the second path 268 toward the container 278. If the particles are not the target particles (e.g., within the specified sorting range, not showing scattering or illumination information), the deflector plate can cause the particles to continue to flow along the flow path 264. Such uncharged droplets can enter a waste container via, for example, an aspirator 270.

[0103] The sorting electronics may be included to begin collecting measurements, receive a fluorescent signal from a particle, and determine how to adjust the deflection plates to sort the particle. Figure 2A The exemplary implementation of the embodiment shown in FIG. 1 includes a BD FACSAria commercially available from Becton, Dickinson and Company located in San Jose, California. TM Serial flow cytometer.

[0104] Figure 2B is a schematic diagram of a particle sorter system 200 according to an embodiment described herein. In some embodiments, the particle sorter system 200 is a cell sorter system. Figure 2B As shown, a droplet formation sensor 202 (e.g., a piezoelectric oscillator) is coupled to a fluid conduit 201 (e.g., a nozzle). Within the fluid conduit 201, a sheath fluid 204 hydrodynamically focuses a sample fluid 206 into a moving liquid column 208 (e.g., a stream). Within the moving liquid column 208, particles (e.g., cells) are aligned to pass through a monitored area 210 (e.g., a laser stream intersection) irradiated by an irradiation source 212 (e.g., a laser). The droplet formation sensor 202 vibrates to break the moving liquid column 208 into a plurality of droplets 209.

[0105] In operation, a detection station 214 (e.g., an event detector) determines when a particle of interest (or cell of interest) passes through the monitored area 210. The detection station 214 feeds a timing circuit 228, which in turn feeds a transient charging circuit 230. At the droplet breakup point, after notification of a timing droplet delay (Δt), a transient charge is applied to the moving liquid column 208 to charge the droplet of interest. The droplet of interest may include one or more particles or cells to be sorted. The charged droplets may then be sorted by activating a deflection plate (not shown) to deflect the droplets into a container such as a collection tube or a multi-well sample plate, where a well may be associated with a particular droplet of interest. Figure 2B As shown, the droplets are collected in a discharge container 238.

[0106] A detection system 216 (e.g., a droplet boundary detector) is used to automatically determine the phase of the droplet drive signal as the target particle passes through the monitored area 210. An exemplary droplet boundary detector is described in U.S. Patent No. 7,679,039, which is incorporated herein by reference in its entirety. The detection system 216 allows the instrument to accurately calculate the position of each detected particle in the droplet. The detection system 216 can be fed with an amplitude signal 220 and / or a phase 218 signal, which in turn is fed (through an amplifier 222) into an amplitude control circuit 226 and / or a frequency control circuit 224. The amplitude control circuit 226 and / or the frequency control circuit 224 in turn control the droplet formation sensor 202. The amplitude control circuit 226 and / or the frequency control circuit 224 can be included in the control system.

[0107] In some embodiments, the sorting electronics (e.g., detection system 216, detection station 214, processor 240) may be coupled to a memory configured to store detected events and sorting decisions based thereon. The sorting decision may be included in the event data of the particle. In some embodiments, the detection system 216 and the detection station 214 may be implemented in the form of a single detection unit or coupled in a communication manner so that event measurements may be collected by one of the detection system 216 or the detection station 214 and provided to the non-collecting element.

[0108] In some embodiments, one or more of the components described herein applicable to particle sorter system 200 may be used for particle analysis and characterization, whether or not the particles are physically sorted into collection containers. Figure 3 ) can also be used for particle analysis and characterization, whether or not the particles are physically sorted into collection containers. For example, one or more of the components in the particle sorter system 200 or the particle analysis system 300 can be used to group particles or display them in a tree that includes at least three of the groupings described herein.

[0109] Figure 3 A functional block diagram of a particle analysis system for computation-based sample analysis and particle characterization is presented. In some embodiments, particle analysis system 300 is a flow system. Figure 3 The particle analysis system 300 shown may be configured to perform, in whole or in part, the methods described herein, for example, Figure 5 8. The particle analysis system 300 includes a fluidics system 302. The fluidics system 302 may include or be coupled to a sample tube 310 and a moving liquid column within the sample tube, within which particles 330 (e.g., cells) in a sample move along a common sample path 320.

[0110] The particle analysis system 300 includes a detection system 304 configured to collect signals from each particle as each particle passes through one or more detection stations along the common sample path. The detection stations 308 are generally referred to as monitored regions 340 of the common sample path. In some embodiments, detection can include detecting light or one or more other characteristics of the particles 330 as they pass through the monitored regions 340. Figure 3 , a detection station 308 is shown having a monitored area 340. Some embodiments of particle analysis system 300 may include multiple detection stations. In addition, some detection stations may monitor more than one area.

[0111] Each signal is assigned a signal value to form a data point for each particle. As described above, the data can be referred to as event data. The data point can be a multi-dimensional data point, which includes a value for each measured characteristic of the particle. The detection system 304 is configured to collect a series of the data points within a first time interval.

[0112] The particle analysis system 300 also includes a control system 306. The control system 306 may include one or more processors, an amplitude control circuit 226, and / or a frequency control circuit 224 (e.g., Figure 2B 306 is operatively associated with the fluidic system 302. The control system 306 is configured to generate a calculated signal frequency for at least a portion of the first time interval based on a Poisson distribution and the number of data points collected by the detection system 804 during the first time interval. The control system 306 is further configured to generate an experimental signal frequency based on the number of data points within the portion of the first time interval. In addition, the control system 306 may compare the experimental signal frequency to the calculated signal frequency or the predetermined signal frequency.

[0113] Figure 44 is a simplified diagram illustrating an example system for dynamically transforming event data. System 400 includes a transformation device 420. Transformation device 420 includes an event data receiver 422. Event data receiver 422 can receive data from a particle analyzer (e.g., Figure 1 In some embodiments, the event data 402 may be generated by the particle analyzer by receiving the event data 402 from, for example, an analysis workstation. For example, a user may provide the event data receiver 422 with the event data 402 obtained from the particle analyzer. The event data receiver 422 may include a transceiver for wireless communication or a port for connecting to a wired network such as an Ethernet local area network or a communication interface such as via a universal serial bus or a serial bus. The connector connects to the port on the device.

[0114] The event data receiver 422 can provide at least a portion of the event data 402 to a transform selection circuit 424 included in the transform device 420. The transform selection circuit 424 can identify a transform applicable to the event data. The identification can include detecting a value in the event data, such as an identifier for the assay or experiment. The available transforms can be stored in a data memory 440 accessible to the transform selection circuit 424. As discussed above, the transform can be a parametric transform or a non-parametric transform. In some embodiments, the transform can be specified by the device providing the event data 402. For example, an analysis workstation can submit a message requesting processing of the event data 402. The message can include a desired transform (e.g., tSNE).

[0115] The transformation device 420 may include event data transformation circuitry 426 to process the event data 402 according to the identified transformation. The event data transformation circuitry 426 may generate transformed event data 490. The transformed event data 490 may be transmitted from the transformation device 420 to a target device, such as a device that verifies the event data 402, a storage location, or an addressable network service (e.g., a laboratory information system).

[0116] As mentioned above, when performing a non-parametric transformation, consistent processing of event data received at different times is unpredictable due to the statistical nature of the transformation. Figure 4The transformation device 420 in can provide suitable results when the event data 402 represents the measured value of the completed experiment. However, for some analytical methods (for example, establishing a sorting standard), the user can make a best guess at the expected position of the target population, or obtain the measured value of a part of the sample, and then use it to specify the gate. In the first case, the guess may not be able to effectively find the real target population, and often may need to obtain a larger sample size, which may be impractical for some experiments. In the case of the initial part of the analysis, if the event data are transformed using non-parametric transformation, any resulting gate requires that future events be transformed in the same manner as the initial part of the event. As mentioned above, non-parametric transformation is usually uncertain, so the event data processed at two different times may provide two different results.

[0117] Figure 5 is a simplified diagram showing an example system that uses parametric machine learning transformations to dynamically transform event data. Figure 5 The transformation device 520 in includes the function of parameterizing non-parametric transformations using neural networks, thereby allowing a small training data set to be transformed using non-parametric techniques, while allowing an accurate parametric model to be generated using the small training data set so that other events can be evaluated in a manner consistent with the initial event.

[0118] System 500 includes a transformation device 520. Transformation device 520 includes an event data receiver 522. Event data receiver 522 can receive data from a particle analyzer (e.g., Figure 1 In some embodiments, the event data 502 may be generated by the particle analyzer by receiving data from, for example, an analysis workstation. For example, a user may provide the event data 502 obtained from the particle analyzer to the event data receiver 522. The event data receiver 522 may include a transceiver for wireless communication or a network port for connecting to a wired network such as an Ethernet local area network.

[0119] Event data receiver 522 may activate switch 524 or other routing elements for further processing. Switch 524 may be connected in a branch line between transform selection circuit 540 and training circuit 530. Switch 524 may be activated based on: event data 502; information included in or with event data 502, such as a message requesting processing of event data 502; characteristics of the device providing event data 502; or other factors detectable by event data receiver 522 or switch 524.

[0120] When switch 524 activates a path to transition selection circuit 540, at least a portion of event data 502 is provided to transition selection circuit 540. Figure 4 In general, the transform selection circuit 540 can also identify a transform that is applicable to the event data. The identification can include detecting a value in the event data, such as an identifier for the assay or experiment. The available transforms can be stored in a data memory 540 accessible to the transform selection circuit 540. As discussed above, the transform can be a parametric transform or a non-parametric transform. In some embodiments, the transform can be specified by the device providing the event data 502. For example, an analysis workstation can submit a message requesting the processing of the event data 502. The message can include a desired transform (e.g., tSNE).

[0121] The transformation device 520 may include event data transformation circuitry 542 to process the event data 502 according to the identified transformation. The event data transformation circuitry 542 may generate transformed event data 570. The transformed event data 570 may be transmitted from the transformation device 520 to a target device, such as a device that verifies the event data 502, a storage location, or an addressable network service (e.g., a laboratory information system).

[0122] In a second mode, switch 524 may be activated to route at least a portion of event data 502 to training circuit 530. Training circuit 530 may coordinate parameter model generation for transforming event data 502. Transformation device 520 may include training event data generator 532 to generate a suitable training data set for a machine learning model. The neural network may have a variety of architectures, with any number of layers, any number of neurons in a layer, and any activation function between connected neurons. However, in order to facilitate the conversion of the neural network to the configuration of the sorting electronic device included in the analytical instrument, the network training may be limited to the architecture that can be converted to the target analytical instrument. For example, the neural network may consist of an entry layer (whose number of nodes is equal to the dimension of the untransformed data), four fully connected rectified linear unit (re-lu) activation layers (each layer has 30 nodes) and an output layer (with two nodes, linear activation). Training may be performed using a variety of error functions (e.g., mean square error, Kullback-Leibler divergence) and optimization procedures (e.g., Adadelta, RMSProp).

[0123] After training, the neural network approximates the transformation that was originally used to transform the small training data set. Thus, the neural network represents the transformation between the space occupied by the original, untransformed data and the space occupied by the transformed data. Thus, the neural network can transform new observations by feeding the new data into the input layer and collecting the resulting transformed data in the output layer.

[0124] The generated event data may then be transmitted to a transformation device 520 for processing. The transformation of the training data may include a non-parametric transformation. The non-parametric transformation may be identified in a request message attached to or associated with the generated event data. The generated event data may be processed via an event data receiver 522, a transformation selection circuit 540, and an event data transformation circuit 542 as described above to generate the event data generated after the transformation.

[0125] The event data generated after the transformation and the generated event data can then be received from the training circuit 530 to generate a transformation model. Generating the transformation model can include generating a neural network that approximates the transformation from the generated event data to the event data generated after the transformation. As discussed above, the construction of the model can be constrained based on factors such as a target particle analyzer or sorting electronics. This can facilitate the generation of a transformation model that can be applied to the target particle analyzer or sorting electronics. The particle analyzer or sorting electronics can be indicated using a hardware identifier that can be associated with a model architecture or constraint.

[0126] Transformation model 560 may be stored in data storage 514 and used for subsequent transformation of event data for the experiment or other experiments.

[0127] Figure 6 is a process flow diagram depicting an example of a parametric machine learning transformation method applicable to multi-dimensional event data. The method 600 may be performed by a transformation device (e.g. Figure 5 The transformation device 520 shown is implemented in whole or in part.

[0128] Multidimensional event data 602, such as particle analyzer data, can be provided. Multidimensional event data 602 can be processed using non-parametric transformation 604 (e.g., tSNE) to generate transformed event data 606 representing the initial transformed measured value of the event. Transformed event data 606 can be used to train a model through machine learning 608. The result of the learning can include a parameter transformation neural network model 610. The neural network model 610 can generate transformed data 614 for multidimensional event data 602 or new multidimensional event data 612. Then, transformed data 614 can be provided for other processing or control, such as gate selection 680, event sorting determination 682, or instrument adjustment 684 (e.g., pressure regulation of a flow cytometer). Gate selection 680 can include transmitting the transformed event data to a device to display one or more graphical user interfaces. A graphical user interface can include a control element for selecting a destination event and assigning a sorting destination (e.g., a container, plate, hole, chamber, tube, etc.) to the event. The selection can include receiving gate information that identifies a range of measured values ​​for classifying the particles. The gates may be specified using measurements in a transformed (eg, non-parametric) space. The gate information may be formed or used to generate sorting criteria to configure the particle analyzer to sort particles suitable for the experiment.

[0129] Event sorting determination 682 may include transmitting the transformation and sorting criteria together to a particle analyzer. The particle analyzer (including sorting electronics or other analytical devices for processing particles during the experiment) may be configured to transform the raw event data and apply the specified sorting criteria. As discussed above, the transformation may be a parameterized neural network model that represents a non-parametric transformation of events suitable for gate selection. Instrument adjustment 684 may include transmitting a control signal to a particle analyzer or an analytical device included therein to adjust its operating state. For example, the flow rate may be adjusted based on the distribution of the transformed event data compared to an ideal distribution. If the distribution deviates from the ideal distribution, the flow rate may be reduced. The amount of reduction may be evaluated using the size of the deviation from the ideal distribution. Other operating characteristics of the particle analyzer may be adjusted using the transformed event data (e.g., detector voltage or data scaling factor).

[0130] Figure 7 is a process flow diagram depicting an example of a method for sample sorting using a parametric machine learning transformation. The method 700 may be performed by Figure 1 Aspects of method 700 may be implemented in whole or in part using a management device (e.g. Figure 5 The method 700 illustrates how to process event data to generate a parametric transformation based on a non-parametric transformation of an initial set of events.

[0131] Method 700 begins at block 702. At block 710, initial event data for a portion of a sample is collected. The collecting may include activating a particle analyzer to process the portion of the sample. Processing the sample may include measuring properties of particles, such as graphical, electrical, temporal, or acoustic properties.

[0132] At block 720, the initial event data may be transmitted to a transformation device, such as Figure 5 The transformation device 520 shown. The transmission may include transmitting a message requesting a transformation of the initial event data. The message may include an identifier applicable to an experiment, sample, sample source, or other unique information to identify the event data. The identifier may be used to select a transformation applicable to the event data. The identifier may be used to associate a parameter transformation generated using the event data with a subsequent transformation request.

[0133] At box 730, the initial event data is transformed using a non-parametric transformation. The transformation can be selected from a set of transformations based on, for example, the event data. For example, if the event data includes acoustic measurements, a tSNE transformation customized for acoustic values ​​can be used. In some embodiments, the transformation can be specified in a message requesting processing of the event data. For example, if a researcher requests a chart of the event data for gating, the request can include an indication of the type of transformation to be applied so as to graphically represent the dimensions of the event data for gating.

[0134] At block 740, the initial event data may be amplified to generate model training event data. The amplification may include generating training data based on measurements of the event. For example, the measurements may be used to generate a second synthetic event within a threshold distance of the measurements. The synthetic measurements may include a measurement pair, one of which is a synthetic untransformed measurement and a second of which is a synthetic transformed measurement. Table 1 lists event data applicable to measurements using a threshold of 0.001 (e.g., a synthetic measurement based on an actual measurement should be within 0.001 of the actual measurement).

[0135] Table 1

[0136] EventId Is it synthetic? Measurement 1 no 2.30495 2 yes 2.30492 3 yes 2.30499 4 yes 2.30404

[0137] The threshold may be determined based on the type of measurement. For example, optical measurements (e.g., fluorescence-based measurements) may have a greater tolerance than image-based measurements. The threshold may be specified in a configuration accessible to the device performing the training. Aspects of the generation of the transformed data include the following: Figure 5 and Figure 6 middle.

[0138] At block 750, the parametric model is generated based at least in part on the model training event data. Generating the parametric model may include training a neural network model that approximates a non-parametric transformation from actual and synthetic event data to transformed event data. Generating the parametric model may include generating a neural network that approximates the transformation from the generated event data to the transformed generated event data. As discussed above, the construction of the model may be constrained based on factors such as a target particle analyzer or sorting electronics. This may facilitate the generation of a transformation model that may be applied to the target particle analyzer or sorting electronics.

[0139] At block 760, a selection of a target event may be received. For example, the researcher may draw a polygon on a graph to define a range of transformed data values ​​to be sorted. The polygon may define a gate that may be a sorting criterion or associated with a sorting criterion. The selection may be performed using initial event data transformed by a nonparametric transformation or by a parametric model.

[0140] At block 770, sorting electronics (e.g., sorting circuitry) may be configured using the parameter model and gating criteria specified at block 760. Configuration of the sorting electronics may include storing the model generated at block 750 in a storage location accessible to the sorting electronics. The model may then be used to transform received event data to be evaluated against sorting criteria (e.g., the population identified at block 760). As discussed above, the model may be used to configure a field programmable gate array included in the sorting electronics.

[0141] At block 780, the analyzer may use the configured sorting electronics to evaluate and sort the remainder of the sample. As new event measurements are collected, the measurements may be transformed in real time using the configured sorting electronics and sorted into designated containers. For example, a deflection plate of the particle analyzer may be activated to direct the particles of interest into designated collection tubes.

[0142] Method 700 ends at box 790. However, it should be understood that method 700 can be repeated for other events, samples, or experiments. In some embodiments, it is desirable to retrain the model to accommodate any variation within the sample or to account for changes in the source of the sample. For example, in a therapeutic setting, biological samples can be collected during the administration of a drug or other compound. The model may need to be adjusted to account for the presence of the drug or compound after administration. In such cases, given that the original model has been trained, the model can be retrained to collect data. This can provide higher resource utilization than training a new model using a corpus of event data collected from the sample.

[0143] The functionality can sort particles based on their membership to a target cluster. Mahalanobis distance can be used to measure the distance between a particle and a known cluster. The sorting decision for a particle can be determined based on the cluster to which the particle is closest. For certain samples, particles close to a contaminant cluster may be excluded or transferred to an alternate collection container. The criteria for determining tightness can be determined based on a minimum error probability. The probability can be defined using a configuration or specified as part of a sample experimental setup. Known clusters can be identified using a training set. The training set can include a subset of measurements of particles belonging to a cluster. The mean and covariance of the training set can be generated as a metric representation of a cluster. The metric can then be used as a factor in a Mahalanobis distance equation, which can be evaluated using hardware that can analyze the measurements to generate a sorting decision that directs the particles to a specific collection container in a timely manner.

[0144] As used herein, the term "determining" encompasses a variety of activities. For example, "determining" may include calculating, computer computing, processing, deriving, investigating, looking up (e.g., looking up in a table, database, or another data structure), ascertaining, etc. In addition, "determining" may include receiving (e.g., receiving information), accessing (e.g., accessing data in a memory), etc. In addition, "determining" may include resolving, selecting, choosing, establishing, etc.

[0145] As used herein, the term "providing" encompasses a variety of activities. For example, "providing" may include storing a value at a location on a storage device that facilitates subsequent retrieval, sending a value directly to a recipient via at least one wired or wireless communication medium, sending or storing a reference to a value, etc. "Providing" may also include encoding, decoding, encryption, decryption, validation, verification, etc., performed via hardware elements.

[0146] As used herein, the term "selectively" or "selective" may encompass a variety of activities. For example, a "selective" process may include determining one of a plurality of options. A "selective" process may include one or more of the following: a dynamically determined input, a preconfigured input, or an input initiated by a user for determination. In some embodiments, n-input switching may be included to provide a selective function, where n is the number of inputs used to make a selection.

[0147] The term "message" as used herein encompasses various formats for conveying (e.g., sending or receiving) information. A message may include a machine-readable aggregation of information, such as an XML document, a fixed field message, a comma-delimited message, etc. In some embodiments, a message may include a signal for transmitting one or more information representations. Although described in singular form, it should be understood that a message may be composed, sent, stored, received, etc., in multiple parts.

[0148] As used herein, "user interface" (also referred to as interactive user interface, graphical user interface or UI) may refer to a web-based user interface that includes data fields, buttons or other interactive controls for receiving input signals or providing electronic information or providing information to a user in response to any received input signals. TM 、FLASH TM , JAVA TM ,.NET TM 、WINDOWS OS TM , macOS TM , Web services and rich site summary (RSS) and other technologies to implement the UI in whole or in part. In some embodiments, the UI can be included in a standalone client (e.g., a fat client, a fat client) configured to communicate (e.g., send or receive data) according to one or more aspects described.

[0149] As used herein, a "data storage area" may be embodied in a hard disk drive, solid-state memory, and / or any other type of non-transitory computer-readable storage medium that can access a device or be accessed by the device, including an access device, a server, or other computing device, etc. As is known in the art, the data storage area may also or alternatively be distributed or partitioned across multiple local and / or remote storage devices without departing from the scope of the present invention. In other embodiments, the data storage area may include or be embodied in a data storage network service.

[0150] As used herein, a phrase referring to "at least one" of a list of items refers to any combination of the items, including individual members. For example, "at least one of the following items: a, b, or c" is intended to cover: a, b, c, ab, ac, bc, and abc.

[0151] Those skilled in the art will appreciate that any of a variety of different technologies and techniques may be used to represent information, messages, and signals. For example, data, instructions, commands, information, signals, bits, symbols, and chips that may be mentioned throughout the above specification may be represented by voltage, current, electromagnetic waves, magnetic fields or particles, light fields or optical particles, or any combination thereof.

[0152] It will be further understood by those skilled in the art that the various illustrative logic blocks, modules, circuits and algorithmic steps described in conjunction with the embodiments disclosed herein can be used as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been generally described above with respect to their functions. Whether this function is implemented in the form of hardware or software depends on specific applications and design constraints for the entire system. The technician can perform the functions in various ways for each specific application, but this execution decision should not be interpreted as causing departure from the scope of the present invention.

[0153] The technology described herein can be implemented in the form of hardware, software, firmware or any combination thereof. The technology can be implemented in any of a variety of devices, for example, a specially programmed event processing computer, a wireless communication device or an integrated circuit device. Any function described as a module or component can be executed together in an integrated logic device, or separately in a discrete but interoperable logic device. If implemented in software form, the technology can be implemented at least in part by a computer-readable data storage medium, which includes instructions, and when the instructions are executed, one or more of the above methods are executed. The computer-readable data storage medium may constitute a part of a computer program product, which may include packaging materials. The computer-readable medium may include a memory or a data storage medium, for example, a random access memory (RAM) (e.g., a synchronous dynamic random access memory (SDRAM)), a read-only memory (ROM), a non-volatile random access memory (NVRAM), an electrically erasable programmable read-only memory (EEPROM), a flash memory, a magnetic or optical data storage medium, etc. The computer-readable medium may be a non-temporary storage medium. Alternatively or additionally, the techniques may be implemented at least in part by a computer-readable communication medium that carries or communicates program code in the form of instructions or data structures and that can be accessed, read, and / or executed by a computing device, such as a propagated signal or wave.

[0154] The program code may be executed by a specially programmed transformation processor, which may include one or more processors, such as one or more digital signal processors (DSPs), configurable microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuit systems. The graphics processor may be specifically configured to perform any of the techniques described in the present invention. A combination of computing devices (e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in combination with a DSP core, or any other such configuration in at least a portion of the data connection) may perform one or more of the functions described. In some aspects, the functions described herein may be provided in a dedicated software module or hardware module configured for encoding and decoding, or incorporated into a dedicated transformation control card.

[0155] The method disclosed herein includes one or more steps or actions for implementing the method. The method steps and / or actions may be interchangeable with each other without departing from the scope of the claims. In other words, unless a specific order of steps or actions is specified, the order and / or use of specific steps and / or actions may be modified without departing from the scope of the claims.

[0156] Various embodiments of the invention are described herein. These and other embodiments are within the scope of the following claims.

[0157] Aspects of the subject matter described above (including embodiments) may be used alone or in combination with one or more aspects or embodiments. Without limiting the content described herein, certain non-limiting content of the present invention is provided below. After reading the present invention, the following content will be apparent to those skilled in the art, and each individually numbered content may be used alone or in combination with any of the preceding or following individually numbered content. This is intended to provide support for all such combinations of the content, and is not limited to the combinations of the content explicitly provided below:

[0158] 1. A method comprising:

[0159] applying a nonparametric transformation to a first raw data set from a flow cytometer to generate a first transformed data set;

[0160] generating a second transformed data set using the first transformed data set; and

[0161] generating a transformation model using the second transformed data set; and

[0162] The transformation model is applied to a second raw data set from the flow cytometer.

[0163] 2. The method of 1, wherein the non-parametric transformation comprises t-distributed stochastic neighbor embedding (tSNE).

[0164] 3. The method of any one of 1-2, wherein the first raw data set comprises data from 10,000 or fewer detected cells of the flow cytometer.

[0165] 4. A method according to any one of 1-3, wherein generating the second transformed data set includes adding a noise component.

[0166] 5. The method according to 4, wherein generating the second transformed data set includes adding the noise component to one or more of the first original data set, the first transformed data set, and a combination thereof.

[0167] 6. The method of claim 5, wherein generating the second transformed data set comprises adding the noise component to a data pair comprising an original data point and a transformed data point.

[0168] 7. The method according to 6, wherein the original data points and the transformed data points are selected by random selection.

[0169] 8. The method according to 7, wherein the original data points and the transformed data points are selected by weighted random selection.

[0170] 9. The method of 8, wherein the random selection is weighted according to one or more of density and cell population.

[0171] 10. The method according to any one of 4-9, wherein the noise component is determined based on a probability distribution.

[0172] 11. The method according to 10, wherein the probability distribution is selected from the group consisting of uniform distribution, Gaussian distribution or Poisson distribution.

[0173] 12. A method according to any one of 1-11, wherein the transformation model is a dynamic algorithm.

[0174] 13. The method of 12, wherein the dynamic algorithm is a machine learning algorithm.

[0175] 14. A method according to any one of 1-13, wherein the transformation model is applied to real-time data from the flow cytometer.

[0176] 15. The method according to any one of 1-14 further comprises classifying particles in the sample within the fluid medium of the flow cytometer.

[0177] 16. The method according to 15 further comprises generating a sorting decision based on the particle classification.

[0178] 17. The method according to any one of 15-16 further comprises sorting one or more particles in the sample.

[0179] 18. The method according to any one of 1-17, wherein the method is performed by an integrated circuit device.

[0180] 19. The method of 18, wherein the integrated circuit device is a field programmable gate array (FPGA).

[0181] 20. The method of 18, wherein the integrated circuit device is an application specific integrated circuit (ASIC).

[0182] 21. The method of 18, wherein the integrated circuit device is a complex programmable logic device (CPLD).

[0183] 22. A computer-implemented method comprising:

[0184] controlled by one or more processing devices,

[0185] receiving, from a particle analyzer, measurements of a first portion of particles associated with the experiment;

[0186] converting the measurements to initial transformed measurements using a nonparametric transformation;

[0187] generating a parametric model to receive as input the measurements of the first portion of particles associated with the experiment and to generate as output the initial transformed measurements; and

[0188] The particle analyzer is configured as follows:

[0189] converting measurements of particles included in a second portion of the particles based at least in part on the parametric model; and

[0190] The particles are classified based at least in part on the measurements and the sorting criteria.

[0191] 23. The computer-implemented method according to 22, further comprising:

[0192] Gate information is received, the gate information identifying a range of measurement values ​​in a non-parametric space for classifying the particles, wherein the sorting criteria comprises the gate information.

[0193] 24. The computer-implemented method according to any one of 22-23, further comprising:

[0194] transmitting the parameter model to the particle analyzer; and

[0195] The particle analyzer is caused to configure sorting circuitry based at least in part on the parametric model and the sorting criteria.

[0196] 25. The computer-implemented method of 24, wherein the sorting circuit comprises a field programmable gate array.

[0197] 26. A computer-implemented method according to any one of claims 22-25, wherein the measurements received from the particle analyzer include measurements of light emitted by the first portion of particles in the form of fluorescence.

[0198] 27. The computer-implemented method of 26, wherein the light emitted in the form of fluorescence by the first portion of particles comprises light emitted in the form of fluorescence by antibodies bound to the first portion of particles.

[0199] 28. The computer-implemented method according to any one of 22-27, further comprising:

[0200] Selecting the measured values ​​of the particle and the initial transformed measured values; and

[0201] The synthetic measurement pair is generated based at least in part on:

[0202] (i) a measurement value of the particle,

[0203] (ii) an initial transformed measurement of the particle; and

[0204] (iii) a noise value, wherein the integrated measurement value pair comprises an integrated

[0205] measurements and integrated transformed measurements; and

[0206] The parameter model further receives the integrated measurement value as input and generates the integrated transformed measurement value as output.

[0207] 29. The computer-implemented method according to 28, further comprising:

[0208] receiving gate information identifying a range of measurements for classifying the particle, and

[0209] Wherein the particles are selected based at least in part on the measurement values ​​corresponding to the range of measurement values.

[0210] 30. The computer-implemented method of any one of 22-29, further comprising:

[0211] receiving a hardware identifier from the particle analyzer, the hardware identifier indicating sorting circuitry implemented in the particle analyzer;

[0212] determining a structure of the parameter model based at least in part on the hardware identifier, wherein the structure of the parameter model is applicable to the sorting circuit; and

[0213] Generating the parameter model includes generating the parameter model consistent with the architecture.

[0214] 31. A computer-implemented method according to claim 30, wherein the parametric model comprises a neural network, and wherein the architecture identifies the number of layers of the neural network and the number of nodes in each layer.

[0215] 32. The computer-implemented method of any one of 22-31, wherein the parametric model comprises a neural network, and wherein generating the parametric model comprises:

[0216] assigning initial weights to connections between a first node in a first layer of the parameter model and a second node in a second layer of the parameter model of a second layer;

[0217] generating output suitable for particle measurements;

[0218] comparing the output to the transformed measurements of the particles; and

[0219] adjusting the initial weights based at least in part on a difference between the output and the transformed measurements,

[0220] The subsequent difference value of the particle is smaller than the difference value after adjusting the initial weight.

[0221] 33. A system comprising a processor, the processor comprising a memory operably coupled thereto, wherein the memory comprises instructions stored thereon, which when executed by the processor, cause the processor to:

[0222] applying a nonparametric transformation to a first raw data set from a flow cytometer to generate a first transformed data set;

[0223] generating a second transformed data set using the first transformed data set; and

[0224] generating a transformation model using the second transformed data set; and

[0225] The transformation model is applied to a second raw data set from the flow cytometer.

[0226] 34. A system according to 33, wherein the non-parametric transformation comprises t-distributed stochastic neighbor embedding (tSNE).

[0227] 35. A system according to any one of 33-34, wherein the first raw data set comprises data from 10,000 or fewer detected cells of the flow cytometer.

[0228] 36. A system according to any one of 33-35, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate the second transformed data set by adding a noise component.

[0229] 37. A system according to 36, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate the second transformed data set by adding a noise component to one or more of the first original data set, the first transformed data set, and a combination thereof.

[0230] 38. A system according to 37, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate the second transformed data set by adding a noise component to data pairs (comprising original data points and transformed data points).

[0231] 39. A system according to 38, wherein the original data points and the transformed data points are selected by random selection.

[0232] 40. A system according to claim 39, wherein the original data points and the transformed data points are selected by weighted random selection.

[0233] 41. A system according to claim 40, wherein the random selection is weighted according to one or more of density and cell population.

[0234] 42. A system according to any one of 36-41, wherein the noise component is determined based on a probability distribution.

[0235] 43. A system according to 42, wherein the probability distribution is selected from the group consisting of uniform distribution, Gaussian distribution or Poisson distribution.

[0236] 44. A system according to any one of 33-43, wherein the transformation model is a dynamic algorithm.

[0237] 45. A system according to 44, wherein the dynamic algorithm is a machine learning algorithm.

[0238] 46. ​​A system according to any one of 33-45, wherein the transformation model is applied to real-time data from the flow cytometer.

[0239] 47. A system according to any one of 33-46, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to classify particles in a sample within the fluid medium of the flow cytometer.

[0240] 48. A system according to claim 47, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate a sorting decision based on the particle classification.

[0241] 49. The system of any one of 33-48, further comprising an integrated circuit device.

[0242] 50. The system of claim 49, wherein the integrated circuit device is a field programmable gate array (FPGA).

[0243] 51. The system of claim 49, wherein the integrated circuit device is an application specific integrated circuit (ASIC).

[0244] 52. The system of claim 49, wherein the integrated circuit device is a complex programmable logic device (CPLD).

[0245] 53. A system comprising:

[0246] one or more processing devices; and

[0247] A computer-readable storage medium containing instructions that, when executed by the one or more processing devices, cause the system to:

[0248] receiving, from a particle analyzer, measurements of a first portion of particles associated with the experiment;

[0249] converting the measurements to initial transformed measurements using a nonparametric transformation;

[0250] generating a parametric model to receive as input raw measurements of the first portion of particles associated with the experiment and to generate as output the initial transformed measurements;

[0251] The particle analyzer is configured as follows:

[0252] converting measurements of particles included in the second portion of the particles based at least in part on the parameter model;

[0253] generating a control signal to adjust an operating state of an analysis device included in the particle analyzer; and

[0254] The control signal is transmitted to the analysis device to achieve the operating state.

[0255] 54. The system of claim 53, wherein the analysis device comprises sorting electronics communicatively coupled to the deflection plates, and

[0256] wherein the particle analyzer is further configured to identify a target container suitable for particles based at least in part on the converted measurements corresponding to a sorting criterion associated with the target container, and

[0257] Adjusting the operating state includes applying an electric charge through the deflection plate to guide the particles into a target container.

[0258] 55. The system according to 53, wherein the analytical device comprises a fluidics system, and

[0259] Wherein adjusting the operating state comprises adjusting the pressure applied during the experiment.

[0260] 56. A system comprising:

[0261] a light source configured to irradiate a sample (including particles) in a fluid medium;

[0262] a light detection system including a photodetector configured to generate a data signal using light detected from particles within the fluid medium; and

[0263] A processor comprising a memory operatively coupled thereto, wherein the memory comprises instructions stored thereon, which instructions, when executed by the processor, cause the processor to perform the following operations:

[0264] applying a non-parametric transform to a first set of data signals from the light detection system to generate a first transformed data set;

[0265] generating a second transformed data set using the first transformed data set; and

[0266] generating a transformation model using the second transformed data set; and

[0267] The transformation model is applied to a second set of data signals from the light detection system.

[0268] 57. A system according to 56, wherein the non-parametric transformation comprises t-distributed stochastic neighbor embedding (tSNE).

[0269] 58. A system according to any one of 56-57, wherein the first set of data signals from the optical detection system includes data from 10,000 or fewer detected cells from the flow cytometer.

[0270] 59. A system according to any one of 56-58, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate the second transformed data set by adding a noise component.

[0271] 60. A system according to 59, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate the second transformed data set by adding a noise component to one or more of the first set of data signals from the optical detection system, the first transformed data set, and a combination thereof.

[0272] 61. A system according to 60, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate the second transformed data set by adding a noise component to data pairs (comprising original data points and transformed data points).

[0273] 62. A system according to claim 61, wherein the original data points and the transformed data points are selected by random selection.

[0274] 63. A system according to claim 62, wherein the original data points and the transformed data points are selected by weighted random selection.

[0275] 64. A system according to claim 63, wherein the random selection is weighted according to one or more of density and cell population.

[0276] 65. A system according to any one of 59-64, wherein the noise component is determined based on a probability distribution.

[0277] 66. A system according to 65, wherein the probability distribution is selected from the group consisting of uniform distribution, Gaussian distribution or Poisson distribution.

[0278] 67. A system according to any one of 56-66, wherein the transformation model is a dynamic algorithm.

[0279] 68. A system according to 67, wherein the dynamic algorithm is a machine learning algorithm.

[0280] 69. A system according to any of 56-68, wherein the transformation model is applied to a real-time data signal from the optical detection system.

[0281] 70. A system according to any one of 56-69, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to classify particles in the sample within the fluid medium.

[0282] 71. A system according to 70, wherein the processor includes a memory operably coupled to itself, wherein the memory includes instructions stored thereon, which, when executed by the processor, cause the processor to generate a sorting decision based on the particle classification.

[0283] 72. The system according to any one of 56-71 further comprises a cell sorter.

[0284] 73. A system according to 72, wherein the cell sorter comprises a droplet deflector.

[0285] 74. The system of any one of 56-73 further comprises an integrated circuit device.

[0286] 75. The system of 74, wherein the integrated circuit device is a field programmable gate array (FPGA).

[0287] 76. A system according to 74, wherein the integrated circuit device is an application-specific integrated circuit (ASIC).

[0288] 77. The system of 74, wherein the integrated circuit device is a complex programmable logic device (CPLD).

[0289] 78. An integrated circuit programmed to:

[0290] applying a nonparametric transformation to a first raw data set from a flow cytometer to generate a first transformed data set;

[0291] generating a second transformed data set using the first transformed data set; and

[0292] generating a transformation model using the second transformed data set; and

[0293] The transformation model is applied to a second raw data set from the flow cytometer.

[0294] 79. An integrated circuit according to claim 78, wherein the non-parametric transformation comprises t-distributed stochastic neighbor embedding (tSNE).

[0295] 80. An integrated circuit according to any one of 78-79, wherein the first raw data set comprises data from 10,000 or fewer detected cells of the flow cytometer.

[0296] 81. An integrated circuit according to any one of 78-80, wherein the integrated circuit is programmed to generate the second transformed data set by adding a noise component.

[0297] 82. An integrated circuit according to 78, wherein the integrated circuit is programmed to generate the second transformed data set by adding a noise component to one or more of the first original data set, the first transformed data set, and a combination thereof.

[0298] 83. An integrated circuit according to 82, wherein the integrated circuit is programmed to generate the second transformed data set by adding a noise component to data pairs (comprising original data points and transformed data points).

[0299] 84. An integrated circuit according to claim 83, wherein the original data points and the transformed data points are selected by random selection.

[0300] 85. An integrated circuit according to 84, wherein the original data points and the transformed data points are selected by weighted random selection.

[0301] 86. An integrated circuit according to 85, wherein the random selection is weighted by one or more of density and cell population.

[0302] 87. An integrated circuit according to any one of 81-86, wherein the noise component is determined based on a probability distribution.

[0303] 88. An integrated circuit according to 87, wherein the probability distribution is selected from the group consisting of a uniform distribution, a Gaussian distribution, or a Poisson distribution.

[0304] 89. An integrated circuit according to any one of 78-88, wherein the transformation model is a dynamic algorithm.

[0305] 90. An integrated circuit according to 89, wherein the dynamic algorithm is a machine learning algorithm.

[0306] 91. An integrated circuit according to any of 78-90, wherein the transformation model is applied to real-time data from the flow cytometer.

[0307] 92. An integrated circuit according to any of 78-91, wherein the integrated circuit is programmed to classify particles in a sample within a fluid medium of the flow cytometer.

[0308] 93. An integrated circuit according to 92, wherein the integrated circuit is programmed to generate a sorting decision based on the particle classification.

[0309] 94. An integrated circuit according to any one of 78-93, wherein the integrated circuit device is a field programmable gate array (FPGA).

[0310] 96. An integrated circuit according to any one of 78-93, wherein the integrated circuit device is an application-specific integrated circuit (ASIC).

[0311] 97. An integrated circuit according to any one of 78-93, wherein the integrated circuit device is a complex programmable logic device (CPLD).

[0312] Although the foregoing invention has been described in some detail by way of illustration and example for purposes of clarity of understanding, in view of the teachings of the invention, it will be apparent to one of ordinary skill in the art that certain changes and modifications may be made thereto without departing from the spirit or scope of the appended claims.

[0313] Therefore, the foregoing only illustrates the principles of the present invention. It should be understood that those skilled in the art will be able to design various structures, although not explicitly stated or shown here, but these designs reflect the principles of the present invention, without exceeding the spirit and scope of the present invention. In addition, all examples and conditional language listed herein are mainly to help readers understand the principles of the present invention and the ideas provided by the inventors to further expand the art, and should be interpreted as not being limited by these specific examples and conditions. Moreover, all statements citing the principles, aspects and embodiments of the present invention and their specific examples herein are intended to cover their equivalents in structure and function. In addition, the equivalents are intended to include currently known equivalents and equivalents to be developed in the future, that is, any functionally identical elements developed without considering their structure. Moreover, regardless of whether the disclosure of the present invention is clearly described in the claims, any content thereof will not be disclosed to the public.

[0314] Therefore, the scope of the present invention is not limited to the exemplary embodiments shown and described herein. Instead, the scope and spirit of the present invention are embodied by the appended claims. In the claims, only when the phrase "means for..." or "step for..." is explicitly used at the beginning of the limitation content of the claim, "35 U.S.C. Section 112(f)" or "35 U.S.C. Section 112(6)" is explicitly defined as being cited; if the phrase is not used in the limitation content of the claim, "35 U.S.C. Section 112(f)" or "35 U.S.C. Section 112(6)" is not cited.

Claims

1. A computer-implemented method for characterization and sorting of a particle analyzer, comprising: controlled by one or more processing devices, receiving, from a particle analyzer, measurements of a first portion of particles associated with the experiment as a first raw data set; applying a nonparametric transformation to the first original data set to generate a first transformed data set, in, The non-parametric transformation reduces the dimension of the first original data set to generate the first transformed data set; generating a second transformed data set using the first transformed data set, wherein the second transformed data set has a larger data volume than the first transformed data set; generating a parametric model using the second transformed data set to receive the first raw data set as an input and to generate the first transformed data set as an output, wherein the parametric model is generated based at least in part on sorting circuitry implemented in the particle analyzer, and wherein the parametric model includes a machine learning algorithm; and The particle analyzer is configured as follows: converting measurements of particles included in a second portion of the particles associated with the experiment based at least in part on the parameter model; classifying the particles based at least in part on the converted measurements and the sorting criteria; and The particles are sorted based at least in part on the results of the particle classification, wherein sorting the particles based at least in part on the results of the particle classification includes activating a deflection plate of the particle analyzer to direct the target particles into a designated collection container.

2. The computer-implemented method of claim 1 , further comprising: receiving gate information identifying a range of measurements in a non-parametric space for classifying the particle, in, The sorting criteria include the gate information.

3. The computer-implemented method according to any one of claims 1-2, further comprising: transmitting the parameter model to the particle analyzer; and The particle analyzer is caused to configure sorting circuitry based at least in part on the parametric model and the sorting criteria.

4. The computer-implemented method of claim 1 or 2, further comprising: Selecting the measured values ​​of the particle and the initial transformed measured values; and A pair of composite measurements is generated based at least in part on: (i) a measurement value of the particle, (ii) The initial transformed measurement of the particle ; as well as (iii) a noise value, wherein the pair of composite measurement values ​​comprises a composite measurement value and a composite transformed measurement value; as well as The parameter model further receives the integrated measurement value as input and generates the integrated transformed measurement value as output.

5. The computer-implemented method of claim 4, further comprising: receiving gate information identifying a range of measurements for classifying the particle, and Wherein the particles are selected based at least in part on the measurement values ​​corresponding to the range of measurement values.

6. The computer-implemented method of claim 1 or 2, further comprising: receiving a hardware identifier from the particle analyzer, the hardware identifier indicating the sorting circuit implemented in the particle analyzer; determining a structure of the parameter model based at least in part on the hardware identifier, wherein the structure of the parameter model is applicable to the sorting circuit; and Generating the parameter model includes generating the parameter model consistent with the architecture.

7. The computer-implemented method of claim 6, wherein the machine learning algorithm of the parametric model comprises a neural network, and wherein the architecture identifies the number of layers of the neural network and the number of nodes in each layer.

8. The computer-implemented method of claim 4, wherein the machine learning algorithm of the parametric model comprises a neural network, and wherein generating the parametric model comprises: assigning initial weights to connections between a first node in a first layer of the parameter model and a second node in a second layer of the parameter model of a second layer; generating output suitable for particle measurements; comparing the output to the transformed measurements of the particles; as well as adjusting the initial weights based at least in part on a difference between the output and the transformed measurements, The subsequent difference value of the particle is smaller than the difference value after adjusting the initial weight.

9. The computer-implemented method of claim 1, in, The non-parametric transformation includes t-distributed random neighbor embedding.

10. A system for performing the computer-implemented method of claim 1, comprising: one or more processing devices; and A computer-readable storage medium containing instructions that, when executed by the one or more processing devices, cause the system to: receiving, from a particle analyzer, measurements of a first portion of particles associated with the experiment as a first raw data set; applying a nonparametric transformation to the first original data set to generate a first transformed data set; generating a second transformed data set using the first transformed data set, wherein the second transformed data set has a larger data volume than the first transformed data set; generating a parametric model using the second transformed data set to receive the first original data set as input and generate the first transformed data set as output; The particle analyzer is configured as follows: converting measurements of particles included in a second portion of the particles associated with the experiment based at least in part on the parameter model; generating a control signal to adjust an operating state of an analysis device included in the particle analyzer based at least in part on the converted measurement value and the sorting criterion, wherein the analysis device includes sorting electronics communicatively coupled to a deflection plate, and adjusting the operating state includes applying an electrical charge through the deflection plate to direct the particles into a target container; as well as The control signal is transmitted to the analysis device to achieve the operating state.

11. The system of claim 10, wherein the analysis device comprises sorting electronics communicatively coupled to the deflection plates, and wherein the particle analyzer is further configured to identify a target container suitable for particles based at least in part on the converted measurements corresponding to a sorting criterion associated with the target container, and Adjusting the operating state includes applying an electric charge through the deflection plate to guide the particles into a target container.

12. The system of claim 10, wherein the analytical device comprises a fluidics system, and Wherein adjusting the operating state comprises adjusting the pressure applied during the experiment.

13. The system of claim 10, further comprising: a light source configured to irradiate a sample containing the first portion of particles in a fluid medium; a light detection system including a photodetector configured to generate a data signal of a measurement of the first raw data set using light detected from the first portion of particles within the fluid medium; A processor comprising a memory operatively coupled thereto, wherein the memory comprises instructions stored thereon, which instructions, when executed by the processor, cause the processor to perform the following operations: applying the nonparametric transform to the first raw data set from the light detection system to generate the first transformed data set; generating the second transformed data set using the first transformed data set; as well as generating the parameter model using the second transformed data set; as well as applying the parametric model to a second set of data signals from measurements of a second portion of the particles from the light detection system; as well as Cell sorter.

14. The system of claim 10, further comprising an integrated circuit programmed to: applying a nonparametric transformation to measurements of a first portion of particles associated with the experiment from a particle analyzer as a first raw data set to generate a first transformed data set; generating a second transformed data set using the first transformed data set, wherein the second transformed data set has a larger data volume than the first transformed data set; generating a parametric model using the second transformed data set to receive the first original data set as input and generate the first transformed data set as output; as well as The parametric model is applied to measurements from the particle analyzer of a second portion of particles associated with the experiment to sort the second portion of particles.

Citation Information

Patent Citations

  • Flow cytometer with optical equalization

    US10006852B2

  • Neighborhood Thresholding in Mixed Model Density Gating

    US20120245889A1

  • Single-stage photovoltaic grid-connected inverter and control method and application thereof

    US20170133857A1

  • Enclosed droplet sorter and methods of using the same

    US20170299493A1

  • Parallel flow cytometer using radiofrequency multiplexing

    US20170350803A1