Spatial bioinformatics integration portal with programmable machine learning flow orchestration tool

Abstract

A platform, system, medium and method for spatial bioinformatics analysis includes an instrument interface communicatively coupled to one or more laboratory instruments; a software element configured to directly or indirectly receive data from the one or more laboratory instruments, where the data includes biological image data and one or more of the following data: genomic, proteomic, metabonomic, metagenomic, phenotypic, and transcriptomic data; a software element configured to provide a flow orchestration tool that allows a user to create, edit, manage and execute an analysis flow, where the flow orchestration tool allows the user to link the modules together and run them in sequence or in parallel to convert the received data; and, a software element configured to generate a visualization of the data.

Description

[0001] Cross-references This application claims the benefit of U.S. Provisional Patent Application No. 63 / 348,936 filed on June 3, 2022 and U.S. Provisional Patent Application No. 63 / 381,528 filed on October 28, 2022, which are incorporated herein by reference in their entirety for all purposes. Background Art

[0002] Spatial biology is the study of tissues in their own 2D or 3D environment. The field of spatial biology studies the spatial location and organization of gene expression in situ within each cell and structure in a given tissue sample. Maintaining the spatial context of biological data is important to understand how cells organize and interact with their surroundings to drive various biological functions. Summary of the invention

[0003] Spatial transcriptomics and spatial proteomics can be used to study healthy and diseased tissues by understanding the mechanisms behind development, tissue heterogeneity, and therapeutic response. Historically, spatial patterns of gene expression have been captured through immunohistochemistry (IHC) and in situ hybridization (ISH). These techniques allow researchers to spatially visualize biological processes by directly mapping the location of DNA, RNA, and protein molecules within tissues. However, these methods are limited to analyzing only a few genes or proteins at a time.

[0004] Several new technologies have been developed that aim to combine gene expression data with spatial context. Most of the spatial transcriptomics technologies available today are based on in situ and scRNA sequencing and can be mainly divided into: (1) NGS-based methods, which encode positional information onto transcripts prior to sequencing; and, (2) imaging-based methods based on in situ sequencing (ISS), in which transcripts are amplified and sequenced in tissues; or imaging-based methods based on fluorescence in situ hybridization (FISH), in which imaging probes are sequentially hybridized in tissues. Although both NGS-based and imaging-based technologies are powerful, they each have significant limitations. No single method currently addresses all the required parameters, such as high throughput, sensitivity, resolution, and sample compatibility.

[0005] In one aspect, the present invention discloses a system including at least one processor and instructions executable by the at least one processor to provide a spatial bioinformatics application, the application comprising: an instrument interface coupled to one or more laboratory instruments; a software element configured to directly or indirectly receive data from the one or more laboratory instruments, wherein the data includes biological image data and one or more of the following data: genomics, proteomics, metabolomics, metagenomics, phenomics and transcriptomics data; a software element configured to provide a process orchestration tool to enable users to create, edit, manage and execute analysis processes, wherein the process orchestration tool allows users to link modules together and run them sequentially or in parallel to transform the received data; and a software element configured to generate visualizations of the received and / or transformed data. In various embodiments, the one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer or a combination thereof. In some embodiments, the instrument interface enables the application to perform one or more of the following operations: monitoring one or more laboratory instruments, receiving data from the one or more laboratory instruments, and sending operating instructions to the one or more laboratory instruments. In some embodiments, the process orchestration tool includes a graphical user interface (GUI) in which a user creates and / or edits an analysis process by dragging and dropping modules from a module library within the GUI. In some embodiments, the process orchestration tool allows a user to create, edit, manage, and execute branch analysis processes. In some embodiments, one or more modules available in the process orchestration tool include training a machine learning model and / or applying a machine learning model. In some embodiments, the application also includes a software element configured to provide a user interface that allows a user to create and manage studies. In other embodiments, the application also includes a software element configured to provide a user interface that allows users to collaborate and share studies. In some embodiments, the visualization is a three-dimensional (3D) representation.

[0006] On the other hand, the present invention discloses a non-transitory computer-readable storage medium, which is encoded with instructions that can be executed by one or more processors to provide a spatial bioinformatics application, the application comprising: an instrument interface coupled to one or more laboratory instruments; a software element configured to directly or indirectly receive data from the one or more laboratory instruments, wherein the data includes biological image data and one or more of the following data: genomics, proteomics, metabolomics, metagenomics, phenomics and transcriptomics data; a software element configured to provide a process orchestration tool to enable users to create, edit, manage and execute analysis processes, wherein the process orchestration tool enables users to link modules together and run them sequentially or in parallel to convert the received data; and a software element configured to generate visualizations of the received and / or converted data. In various embodiments, the one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer or a combination thereof. In some embodiments, the instrument interface enables the application to perform one or more of the following: monitoring one or more laboratory instruments, receiving data from the one or more laboratory instruments, and sending operation instructions to the one or more laboratory instruments. In some embodiments, the process orchestration tool includes a graphical user interface (GUI) in which a user creates and / or edits an analysis process by dragging and dropping modules from a module library within the GUI. In some embodiments, the process orchestration tool allows a user to create, edit, manage, and execute branch analysis processes. In some embodiments, one or more modules available in the process orchestration tool include training machine learning models and / or applying machine learning models. In some embodiments, the application also includes a software element configured to provide a user interface that allows a user to create and manage research. In other embodiments, the application also includes a software element configured to provide a user interface that allows users to collaborate and share research. In some embodiments, the visualization is a three-dimensional (3D) representation.

[0007] In another aspect, the present invention discloses a computer-implemented method, comprising: providing an instrument interface communicatively coupled to one or more laboratory instruments on a computer; receiving data from one or more laboratory instruments at the instrument interface, wherein the data includes biological image data and one or more of the following data: genomics, proteomics, metabolomics, metagenomics, phenomics and transcriptomics data; providing a process orchestration tool on a computer to allow a user to create, edit, manage and execute an analysis process, wherein the process orchestration tool allows a user to link modules together and run them sequentially or in parallel to transform the received data; and generating a visualization of the received and / or transformed data by a computer. In various embodiments, the one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer or a combination thereof. In some embodiments, the instrument interface also performs one or more of the following operations: monitoring one or more laboratory instruments, receiving data from the one or more laboratory instruments, and sending operation instructions to the one or more laboratory instruments. In some embodiments, the process orchestration tool includes a graphical user interface (GUI), and a user creates and / or edits an analysis process by dragging and dropping modules from a module library in the GUI. In some embodiments, the process orchestration tool allows a user to create, edit, manage, and execute branch analysis processes. In some embodiments, one or more modules available in the process orchestration tool include training machine learning models and / or applying machine learning models. In some embodiments, the method also includes providing a user interface that allows users to create and manage studies. In other embodiments, the method also includes providing a user interface that allows users to collaborate and share studies. In some embodiments, the visualization is a three-dimensional (3D) representation.

[0008] In various embodiments, the platforms, systems, media, and methods disclosed herein include features and functionality for image analysis and storage as well as data analysis, data visualization, artificial intelligence (AI) and machine learning (ML) support, global collaboration, and scalable computing and storage capacity.

[0009] In some embodiments, the platforms, systems, media and methods disclosed herein are used in conjunction with biological / biochemical laboratory equipment, such as nucleic acid sequencers, digital spatial analyzers (e.g., GeoMx ® ), spatial multi-omics single-cell imaging platforms (e.g., CosMx™), and / or RNA expression analyzers (e.g., nCounter ® )integrated.

[0010] The GeoMx® Digital Spatial Analyzer (DSP) is a platform for acquiring spatially resolved, highly complex gene (or protein) expression data from tissue. In some embodiments, the DSP includes RNA detection capabilities to analyze the entire transcriptome in tissue on a single formalin-fixed paraffin-embedded (FFPE) sample or fresh frozen (FF) sample slide. In some embodiments, the DSP includes protein detection capabilities to generate quantitative and spatial analysis of multiple proteins on a single FFPE or FF sample slide. In some embodiments, FFPE or FF tissue sections can be stained with barcoded in situ hybridization probes that bind to endogenous mRNA transcripts. In other embodiments, the user can select regions of interest (ROIs) for analysis; if desired, each ROI segment can be further subdivided into areas of illumination (AOIs) based on tissue morphology. In some other embodiments, the GeoMx ® Each AOI segment can be photodissected separately and expression tags or barcodes can be collected. In other embodiments, the tags or barcodes can be used for downstream sequencing and data processing. In certain embodiments, the workflow of the digital spatial analyzer includes, for example, image slides, selecting regions of interest (ROIs), collecting ROIs, sequencing, data processing, QC and normalization, and data visualization and interpretation.

[0011] The CosMx™ Spatial Multi-Omics Imager (SMI) platform is an integrated system with sophisticated cyclic fluorescence in situ hybridization (FISH) chemistry, high-resolution imaging readouts, interactive data analysis, and visualization software. In some embodiments, the workflow of CosMx™SMI includes, for example, sample preparation, integrated readouts, or interactive data analysis. In some embodiments, the sample preparation may include permeabilization or fixation of the target. In some other embodiments, the sample preparation may include hybridization so that RNA-specific probes or antibodies bind to the target. In some other embodiments, sample preparation includes flow cell assembly. In some embodiments, the workflow includes multiple cycles of hybridization, UV cleavage imaging, or fluorescent dye washing.

[0012] In various embodiments, the data analysis includes: 1) primary data analysis, e.g., machine-specific steps required to call base pairs and calculate quality scores for those called base pairs; 2) secondary data analysis, referred to as a "process," e.g., aligning and assembling DNA or RNA fragments that provide a complete sequence of a sample, from which genetic variation can be determined; and / or 3) tertiary data analysis, e.g., from sequence data, using biological data mining and interpretation tools to convert the data into information.

[0013] Raw data from each laboratory instrument may contain different formats, so analysis of raw data on a laboratory instrument may include decoding of the raw data to correspond to the presence of a specific target identity. In some embodiments, raw data on a CosMx™SMI may include a series of fluorescent signals with a limited number of colors that are detected at specific times during the instrument cycle. In some embodiments, raw data on a CosMx™SMI may include a single color detected during a specific cycle to indicate the presence of a specific target. In some embodiments, raw data on a CosMx™SMI may include a series of colors for a specific cycle to indicate the presence of a specific target. In some embodiments, nCounter ® The raw data from the instrument may include a linear sequence of fluorescent molecules in a limited number of colors that can be used to identify specific targets based on the color sequence. ® The raw data on the DSP may contain the format of the nCounter instrument readout. In some embodiments, GeoMx ® The raw data on the DSP may include NGS (next generation sequencer) readout formats. In some embodiments, GeoMx ® The raw data in NGS readout format on the DSP can be further linked to specific target RNA, DNA or protein molecules during the analysis phase.

[0014] In various embodiments, image segmentation software based on machine learning (ML) algorithms can be used to create cell boundaries from fluorescent images of protein analysis. In some embodiments, protein analysis can include protein antibodies that bind to membrane proteins. In some embodiments, the ML algorithm applied to image segmentation can include semantic segmentation, instance segmentation, or a generative network for segmentation. In some embodiments, the image segmentation software can include ImageJ, CellProfiller, Cellpose, Ilastik, or QuPath.

[0015] In various embodiments, applications and use cases include, as non-limiting examples, discovery and mapping of cell types and cell states, phenotypes of tissue microenvironments, differential expression of cell types based on spatial context, quantification of subcellular expression, and spatially resolved biomarker identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] This patent or patent application file contains at least one drawing executed in color. Copies of this patent or patent application publication with color drawing(s) will be provided by the Office upon request and payment of the necessary fee.

[0017] The features and advantages of the present invention will be better understood through the following detailed description of exemplary embodiments with reference to the accompanying drawings, in which: FIG1 illustrates a non-limiting example of a computing device; in this example, the device has one or more processors, memory, storage, and a network interface; FIG2 illustrates a non-limiting example of a web / mobile application configuration system; in this example, a system that provides a browser-based and / or native mobile user interface; Figure 3 A non-limiting example of a cloud-based web / mobile application configuration system is shown; in this example, the system includes elastic load balancing, automatically scaling web server and application server resources, and synchronously replicated databases; FIG4 illustrates a non-limiting example of a graphical user interface (GUI) for a spatial bioinformatics integration portal; in this example, the GUI includes a default study screen; FIG5 shows a non-limiting example of a GUI for a spatial bioinformatics integration portal; in this example, the GUI includes a process orchestration tool that allows a user to create and edit analysis processes by dragging and dropping predefined editable module elements from a toolbox and linking them together; FIG6 shows a non-limiting example of a GUI of a spatial bioinformatics integration portal; in this example, the GUI includes a process editing environment of a process orchestration tool, allowing a user to edit process and / or module run parameters; FIG7 shows a non-limiting example of a GUI of a spatial bioinformatics integration portal; in this example, the GUI includes a process branching function of a process orchestration tool, allowing a user to perform iterative analysis by modifying parameters and rerunning a step or creating a new branch of the same process; FIG8 shows a non-limiting example of a GUI for a spatial bioinformatics integrated portal; in this example, the GUI includes an environment for opening an existing study; FIG. 9 shows a non-limiting example of a GUI for a spatial bioinformatics integrated portal; in this example, the GUI includes an environment for viewing the analysis pipeline of a study and visualizing the results of the pipeline modules; FIG. 10 shows a non-limiting example of a GUI for a spatial bioinformatics integrated portal; in this example, the GUI includes customizable layout options, such as variable sizes of different panes; 11A-11C illustrate non-limiting examples of a GUI for a spatial bioinformatics integrated portal; in this example, the GUI includes an environment for graphically representing data in the form of, for example, an XY scatter plot of cell or transcript coordinates; 12A-12C illustrate non-limiting examples of a GUI for a spatial bioinformatics integrated portal; in this example, the GUI includes an environment for graphically representing data in the form of a heat map; FIG. 13 shows a non-limiting example of a GUI for a spatial bioinformatics integrated portal; in this example, the GUI includes an environment for graphically representing data in the form of a histogram; 14A-14C illustrate non-limiting examples of a GUI for a spatial bioinformatics integrated portal; in this example, the GUI includes an environment for graphically representing data in the form of a box plot; Fig.15 A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown; in this example, the GUI includes an environment for graphically representing data in the form of violin plots; Fig.16A and 16B A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown; in this example, the GUI includes an environment for performing dimensionality reduction, for example, by principal component analysis (PCA) and unified manifold approximation and projection (UMAP); Fig.17A and 17B A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown; in this example, the GUI includes an environment that allows a user to annotate data using drawing tools to identify regions of an image and / or graphical drawing; Fig.18 A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown; in this example, the GUI includes a test annotation service for interactive annotation linked to flow cytometry images and tables; Figure 19-22 A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown; in this example, the GUI includes an environment for interactive data viewing, allowing a user to select a flow cell image and visualize the associated data using any running workflow module; Fig.23 A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown; in this example, the GUI includes a data visualization environment with an integrated image viewer, allowing a user to control the image viewer display and view updates to the associated visualization data; Figure 24-30 , 31A, 31B, 32, 33A, 33B, 34A and 34B show exemplary data (spatially resolved high-density RNA data) from a spatial molecular imaging study of formalin-fixed paraffin-embedded (FFPE) samples of non-small cell lung cancer (NSCLC); in this example, the subject matter disclosed herein is used to study the ecosystem that exists within a tissue, how cells respond to their environment, and how cells interact with their neighbors; Fig.35 A non-limiting example of an architectural diagram is shown; in this example, an architectural diagram of a data access pattern; Figure 36-40 A first non-limiting exemplary embodiment of a spatial bioinformatics integrated portal is shown; Figure 41-61 A second non-limiting exemplary embodiment of a spatial bioinformatics integrated portal is shown; Fig.62 A non-limiting example of an interactive editing interface of a process orchestration tool is shown; Fig.63 A non-limiting example of a user interface enhancement for quality control (QC) is shown; Fig.64 A non-limiting example of a cell segmentation module diagram is shown; Fig.65 A non-limiting example of a cell segmentation overlay upon launching the image viewer is shown; Fig.66 Non-limiting examples of cell typing module displays are shown; Fig.67 A non-limiting example of an application architecture and service overview for graphics processing development is shown; Fig.68 Non-limiting examples of RNA transcript maps are shown; Fig.69 A non-limiting example of Unified Manifold Approximation and Projection (UMAP) is shown; Fig.70 Non-limiting examples of in situ RNA cytotyping maps are shown; Fig.71 A non-limiting example of a Leiden cluster diagram is shown; Fig.72 Non-limiting examples of spatial expression analysis graphical displays are shown; Fig.73 Non-limiting examples of heat maps of cell type co-localization analysis are shown; Fig.74 shows a non-limiting example of a graphical display of a marker gene module analysis; and Fig.75 Non-limiting examples of graphical displays of ligand-receptor analyses are shown. DETAILED DESCRIPTION

[0018] In certain embodiments, the present invention describes a system including at least one processor and instructions executable by the at least one processor to provide a spatial bioinformatics application, the application comprising: an instrument interface communicatively coupled to one or more laboratory instruments; a software element configured to directly or indirectly receive data from the one or more laboratory instruments, wherein the data includes biological image data and one or more of the following data: genomics, proteomics, metabolomics, metagenomics, phenomics, and transcriptomics data; a software element configured to provide a process orchestration tool, the process orchestration tool allows a user to create, edit, manage, and execute analysis processes, wherein the process orchestration tool allows a user to link modules together and run them sequentially or in parallel to transform the received data; and a software element configured to generate a visualization of the received and / or transformed data. In various embodiments, the one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer, or a combination thereof. In some embodiments, the instrument interface enables the application to perform one or more of the following operations: monitoring one or more laboratory instruments, receiving data from the one or more laboratory instruments, and sending operating instructions to the one or more laboratory instruments. In some embodiments, the process orchestration tool includes a graphical user interface (GUI) in which a user creates and / or edits an analysis process by dragging and dropping modules from a module library within the GUI. In some embodiments, the process orchestration tool allows a user to create, edit, manage, and execute branch analysis processes. In some embodiments, one or more modules available in the process orchestration tool include training machine learning models and / or applying machine learning models. In some embodiments, the application also includes a software element configured to provide a user interface that allows a user to create and manage studies. In other embodiments, the application also includes a software element configured to provide a user interface that allows a user to collaborate and share studies. In some embodiments, the visualization is a three-dimensional (3D) representation.

[0019] In certain embodiments, the present invention also describes a non-transitory computer-readable storage medium, which is encoded with instructions executable by one or more processors to provide a spatial bioinformatics application, the application comprising: an instrument interface coupled to one or more laboratory instruments; a software element configured to directly or indirectly receive data from the one or more laboratory instruments, wherein the data includes biological image data and one or more of the following data: genomics, proteomics, metabolomics, metagenomics, phenomics and transcriptomics data; a software element configured to provide a process orchestration tool to enable users to create, edit, manage and execute analysis processes, wherein the process orchestration tool enables users to link modules together and run them sequentially or in parallel to transform the received data; and a software element configured to generate visualizations of the received and / or transformed data. In various embodiments, the one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer or a combination thereof. In some embodiments, the instrument interface enables the application to perform one or more of the following: monitoring one or more laboratory instruments, receiving data from the one or more laboratory instruments, and sending operation instructions to the one or more laboratory instruments. In some embodiments, the process orchestration tool includes a graphical user interface (GUI) in which a user creates and / or edits an analysis process by dragging and dropping modules from a module library within the GUI. In some embodiments, the process orchestration tool allows a user to create, edit, manage, and execute branch analysis processes. In some embodiments, one or more modules available in the process orchestration tool include training machine learning models and / or applying machine learning models. In some embodiments, the application also includes a software element configured to provide a user interface that allows a user to create and manage research. In other embodiments, the application also includes a software element configured to provide a user interface that allows users to collaborate and share research. In some embodiments, the visualization is a three-dimensional (3D) representation.

[0020] In certain embodiments, the present invention also describes a computer-implemented method, comprising: providing an instrument interface coupled to one or more laboratory instruments on a computer; receiving data from one or more laboratory instruments at the instrument interface, wherein the data includes biological image data and one or more of the following data: genomics, proteomics, metabolomics, metagenomics, phenomics and transcriptomics data; providing a process orchestration tool on the computer to allow users to create, edit, manage and execute analysis processes, wherein the process orchestration tool allows users to link modules together and run them sequentially or in parallel to convert received data; and, generating visualizations of received and / or converted data by a computer. In various embodiments, the one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer or a combination thereof. In some embodiments, the instrument interface also performs one or more of the following: monitoring one or more laboratory instruments, receiving data from the one or more laboratory instruments, and sending operation instructions to the one or more laboratory instruments. In some embodiments, the process orchestration tool includes a graphical user interface (GUI), and the user creates and / or edits the analysis process by dragging and dropping modules from a module library in the GUI. In some embodiments, the process orchestration tool allows a user to create, edit, manage, and execute branch analysis processes. In some embodiments, one or more modules available in the process orchestration tool include training machine learning models and / or applying machine learning models. In some embodiments, the method also includes providing a user interface that allows users to create and manage studies. In other embodiments, the method also includes providing a user interface that allows users to collaborate and share studies. In some embodiments, the visualization is a three-dimensional (3D) representation.

[0021] Some definitions Unless otherwise defined, all technical terms used in the present invention have the same meaning as commonly understood by one of ordinary skill in the art to which the subject matter belongs.

[0022] As used in this specification and the appended claims, the singular forms "a", "an", and "the" include plural references unless the context clearly dictates otherwise. Any reference to "or" herein includes "and / or" unless otherwise stated.

[0023] The references to "some embodiments", "other embodiments" or "specific embodiments" in this specification mean that specific features, structures or characteristics related to the embodiments are included in at least one embodiment. Therefore, the phrases "in some embodiments" or "in other embodiments" or "in a specific embodiment" appearing in various places in this specification do not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics may be combined in any suitable manner in one or more embodiments.

[0024] Computer Systems Referring to FIG1 , a block diagram depicting an exemplary machine is shown, which includes a computer system 100 (e.g., a processing or computing system) within which a set of instructions may be executed to cause a device to perform or implement one or more aspects and / or methods of static code scheduling of the present invention. The components in the figure are exemplary only and do not limit the scope of use or functionality of any hardware, software, embedded logic component, or combination of two or more such components to implement a particular embodiment.

[0025] The computer system 100 may include one or more processors 101, memory 103, and storage 108, which communicate with each other and other components via a bus 140. The bus 140 may also connect a display 132, one or more input devices 133 (for example, the device may include a keypad, a keyboard, a mouse, a stylus, etc.), one or more output devices 134, one or more storage devices 135, and various tangible storage media 136. All of these components may be connected to the bus 140 directly or through one or more interfaces or adapters. For example, various tangible storage media 136 may be connected to the bus 140 through a storage medium interface 126. The computer system 100 may have any suitable physical form, including but not limited to one or more integrated circuits (ICs), printed circuit boards (PCBs), mobile handheld devices (such as mobile phones or PDAs), laptops or notebook computers, distributed computer systems, computing grids, or servers.

[0026] Computer system 100 includes one or more processors 101 (e.g., central processing unit (CPU), general purpose graphics processing unit (GPGPU) or quantum processing unit (QPU)) for performing functions. Processor 101 optionally includes cache memory unit 102 for temporarily storing instructions, data or computer addresses locally. Processor 101 is configured to assist in executing computer-readable instructions. Because processor 101 can execute non-temporary, processor-executable instructions contained in one or more tangible computer-readable storage media (e.g., memory 103, storage 108, storage device 135 and / or storage medium 136), computer system 100 can be Figure 1The components shown provide functionality. The computer-readable medium may store software that implements a particular embodiment, and the processor 101 may execute the software. The memory 103 may read the software from one or more other computer-readable media (e.g., mass storage devices 135, 136) or from one or more other sources through an appropriate interface, such as a network interface 120. The software may cause the processor 101 to perform one or more processes described or shown herein or one or more steps of one or more processes. Executing such processes or steps may include defining a data structure stored in the memory 103 and modifying the data structure according to the instructions of the software.

[0027] The memory 103 may include various components (e.g., machine-readable media), including, but not limited to, random access memory components (e.g., RAM 104) (e.g., static RAM (SRAM), dynamic RAM (DRAM), ferroelectric random access memory (FRAM), phase change random access memory (PRAM), etc.), read-only memory components (e.g., ROM 105), and any combination thereof. ROM 105 may be used to transfer data and instructions unidirectionally to processor 101, while RAM 104 may be used to transfer data and instructions bidirectionally with processor 101. ROM 105 and RAM 104 may include any suitable tangible computer-readable media described below. In one example, a basic input / output system 106 (BIOS), which includes basic routines that help transfer information between elements within computer system 100, such as during startup, may be stored in memory 103.

[0028] Fixed memory 108 is optionally bidirectionally connected to processor 101 via storage control unit 107. Fixed memory 108 provides additional data storage capacity and may also include any suitable tangible computer-readable medium described herein. Memory 108 may be used to store operating system 109, executable file 110, data 111, application 112 (application program), etc. Memory 108 may also include an optical drive, a solid-state storage device (e.g., a flash memory-based system), or a combination of any of the above devices. Where appropriate, the information in memory 108 may be incorporated into memory 103 as virtual memory.

[0029] In one example, storage device 135 may be removably connected to computer system 100 via storage device interface 125 (e.g., via an external port connector (not shown)). Specifically, storage device 135 and associated machine-readable media may provide non-volatile and / or volatile storage of machine-readable instructions, data structures, program modules, and / or other data for computer system 100. In one example, the software may reside in whole or in part in the machine-readable media on storage device 135. In another example, the software may reside in whole or in part within processor 101.

[0030] Bus 140 connects various subsystems.Herein, where appropriate, bus may include one or more digital signal lines that provide common functions.Bus 140 may be any of a variety of bus structures, including but not limited to memory bus, memory controller, peripheral bus, local bus and any combination thereof, using any of a variety of bus architectures.As non-restrictive examples, such architectures include industrial standard architecture (ISA) bus, enhanced ISA (EISA) bus, micro channel architecture (MCA) bus, video electronics standard association local bus (VLB), peripheral component interconnect (PCI) bus, PCI-Express (PCI-X) bus, accelerated graphics port (AGP) bus, super transmission (HTX) bus, serial advanced technology attachment (SATA) bus and any combination thereof.

[0031] The computer system 100 may also include an input device 133. In one example, a user of the computer system 100 may input commands and / or other information into the computer system 100 via the input device 133. Examples of the input device 133 include, but are not limited to, an alphanumeric input device (e.g., a keyboard), a pointer device (e.g., a mouse or touchpad), a touchpad, a touch screen, a multi-touch screen, a joystick, a stylus, a game controller, an audio input device (e.g., a microphone, a voice response system, etc.), an optical scanner, a video or still image acquisition device (e.g., a camera), and any combination thereof. In some embodiments, the input device is a Kinect, a Leap Motion, etc. The input device 133 may be connected to the bus 140 via any of a variety of input interfaces 123 (e.g., input interface 123), including but not limited to a serial interface, a parallel interface, a game port, a USB, a FireWire interface, a Thunderbolt interface, or any combination thereof.

[0032] In particular embodiments, when computer system 100 is connected to network 130, computer system 100 may communicate with other devices, particularly mobile devices and enterprise systems, distributed computing systems, cloud storage systems, cloud computing systems, etc., connected to network 130. Communications to and from computer system 100 may be sent through network interface 120. For example, network interface 120 may receive incoming communications (e.g., requests or responses from other devices) in the form of one or more packets (e.g., Internet Protocol (IP) packets) from network 130, and computer system 100 may store the incoming communications in memory 103 for processing. Computer system 100 may similarly store outgoing communications (e.g., requests or responses to other devices) in the form of one or more packets in memory 103 and transmit them from network interface 120 to network 130. Processor 101 may access these communication packets stored in memory 103 for processing.

[0033] Examples of network interface 120 include, but are not limited to, network interface cards, modems, and any combination thereof. Examples of network 130 or network segment 130 include, but are not limited to, distributed computing systems, cloud computing systems, wide area networks (WANs) (e.g., the Internet, enterprise networks), local area networks (LANs) (e.g., networks associated with offices, buildings, campuses, or other relatively small geographic spaces), telephone networks, direct connections between two computing devices, peer-to-peer networks, and any combination thereof. Networks, such as network 130, may employ wired and / or wireless communication modes. In general, any network topology may be used.

[0034] Information and data may be displayed via a display 132. Examples of the display 132 include, but are not limited to, a cathode ray tube (CRT), a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT-LCD), an organic liquid crystal display (OLED) such as a passive matrix OLED (PMOLED) or an active matrix OLED (AMOLED) display, a plasma display, and any combination thereof. The display 132 may interface with the processor 101, the memory 103, and the fixed storage 108, as well as other devices such as an input device 133, via a bus 140. The display 132 is linked to the bus 140 via a video interface 122, and data transfer between the display 132 and the bus 140 may be controlled by a graphics control 121. In some embodiments, the display is a video projector. In some embodiments, the display is a head mounted display device (HMD), such as a VR head mounted device. In other embodiments, suitable VR headsets include, but are not limited to, HTC Vive, Oculus Rift, Samsung Gear VR, Microsoft HoloLens, Razer OSVR, FOVE VR, Zeiss VR One, Avegant Glyph, Freefly VR headsets, etc. In further embodiments, the display is a combination of devices such as those disclosed herein.

[0035] In addition to the display 132, the computer system 100 may also include one or more other peripheral output devices 134, including but not limited to audio speakers, printers, storage devices, and any combination thereof. Such peripheral output devices may be connected to the bus 140 via an output interface 124. Examples of the output interface 124 include but are not limited to a serial port, a parallel connection, a USB port, a FireWire interface, a Thunderbolt interface, and any combination thereof.

[0036] Additionally or alternatively, the computer system 100 may provide functions that can replace software or work with software to perform one or more processes or one or more steps of one or more processes described or illustrated by the present invention by means of logic that is hardwired or otherwise embodied in circuits. The software mentioned in the present invention may include logic, and the logic mentioned may cover software. In addition, where appropriate, reference to a computer-readable medium may include a circuit (e.g., an IC) storing software for execution, a circuit for executing logic, or both. The present invention covers any suitable combination of hardware, software, or both.

[0037] It should be understood by those skilled in the art that the various illustrative logic blocks, modules, circuits and algorithm steps associated with the various embodiments disclosed in the present invention can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been generally described above from a functional perspective.

[0038] Various illustrative logic blocks, modules, and circuits associated with the various embodiments disclosed herein may utilize a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof to implement or perform the functions described in the present invention. A general purpose processor may be a microprocessor, but may also be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, a combination of one or more microprocessors and a DSP core, or any other such configuration.

[0039] The steps of the methods or algorithms related to the various embodiments disclosed in the present invention can be implemented directly in hardware, or in a software module executed by one or more processors, or in a combination of the two. The software module can reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Alternatively, the storage medium can be integrated with the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. Alternatively, the processor and the storage medium can reside in a user terminal as discrete components.

[0040] According to the description herein, suitable computing devices include, but are not limited to, distributed computing systems, cloud computing platforms, server clusters, server computers, desktop computers, laptops, notebook computers, small notebook computers, netbook computers, network tablet computers, handheld computers, Internet devices, mobile smart phones and tablet computers. Those skilled in the art will also recognize that certain televisions, video players and digital music players with optional computer network connections are also suitable for the system described in the present invention. In various embodiments, suitable tablet computers include brochures, tablets and convertible configuration computers known to those skilled in the art.

[0041] In some embodiments, the computing device includes an operating system configured to execute executable instructions. For example, the operating system is software including programs and data that manages the hardware of the device and provides services for the execution of application programs. Those skilled in the art will recognize that suitable server operating systems include, but are not limited to, FreeBSD, OpenBSD, NetBSD, and the like. ® , Linux, Apple ® Mac OS X Server ® 、Oracle ® Solaris ® 、Windows Server ® and Novell ® NetWare ® Those skilled in the art will recognize that suitable personal computer operating systems include, but are not limited to, Microsoft ® Windows ® , Apple ® Mac OS X ® ,UNIX ® and UNIX-like operating systems, such as GNU / Linux ® In some embodiments, the operating system is provided by cloud computing. Those skilled in the art will also recognize that suitable mobile smartphone operating systems include, but are not limited to, Nokia ® Symbian ® OS, Apple ® iOS ® 、Research In Motion ® BlackBerry OS ® , Google ® Android ® , Microsoft ® Windows Phone ® OS, Microsoft ® Windows Mobile ® OS, Linux ® and Palm ® WebOS ® .

[0042] Non-transitory computer readable storage medium In some embodiments, the platform, system, medium and method disclosed in the present invention include one or more non-transitory computer-readable storage media encoded with a program, which includes instructions that can be executed by an operating system of an optionally networked computing device. In other embodiments, the computer-readable storage medium is a tangible component of the computing device. In further embodiments, the computer-readable storage medium is optionally removable from the computing device. In some embodiments, the computer-readable storage medium includes, but is not limited to, a CD-ROM, a DVD, a flash memory device, a solid-state memory, a disk drive, a tape drive, an optical disk drive, a distributed computing system including a cloud computing system and services, and the like. In some cases, the programs and instructions are permanently, substantially permanently, semi-permanently, or non-temporarily encoded on the medium.

[0043] Computer Programs In some embodiments, the platform, system, medium and method disclosed in the present invention include at least one computer program or its use. A computer program includes a series of instructions that can be executed by one or more processors of a CPU of a computing device and is written to perform a specified task. Computer-readable instructions can be implemented as program modules that perform specific tasks or implement specific abstract data types, such as functions, objects, application programming interfaces (APIs), computational data structures, etc. Based on the content disclosed in the present invention, those skilled in the art will recognize that computer programs can be written in various versions of various languages.

[0044] The functions of the computer readable instructions can be combined or distributed in various environments as needed. In some embodiments, the computer program includes an instruction sequence. In some embodiments, the computer program includes multiple instruction sequences. In certain embodiments, the computer program is provided from one location. In other embodiments, the computer program is provided from multiple locations. In various embodiments, the computer program includes one or more software modules. In various embodiments, the computer program includes, in part or in whole, one or more web applications, one or more mobile applications, one or more stand-alone applications, one or more web browser plug-ins, extensions, add-ons or add-ons, or a combination thereof.

[0045] Web Application In some embodiments, the computer program includes a web application. Based on the content disclosed in the present invention, those skilled in the art will recognize that in various embodiments, the web application utilizes one or more software frameworks and one or more database systems. In some embodiments, the web application is created based on a software framework such as Microsoft® .NET or Ruby on Rails (RoR). In some embodiments, the web application utilizes one or more database systems, including but not limited to relational, non-relational, object-oriented, associative, XML, and document-oriented database systems. In other embodiments, suitable relational database systems include but are not limited to Microsoft ® SQL Server, mySQL™ and Oracle ® . Those skilled in the art will also recognize that, in various embodiments, the Web application is written in one or more versions of one or more languages. The Web application may be written in one or more markup languages, presentation definition languages, client-side scripting languages, server-side coding languages, database query languages, or combinations thereof. In some embodiments, the Web application is written to some extent in a markup language, such as Hypertext Markup Language (HTML), Extensible Hypertext Markup Language (XHTML), or Extensible Markup Language (XML). In some embodiments, the Web application is written to some extent in a presentation definition language, such as Cascading Style Sheets (CSS). In some embodiments, the Web application is written to some extent in a client-side scripting language, such as Asynchronous JavaScript and XML (AJAX), Flash ® ActionScript, JavaScript or Silverlight ® In some implementations, the Web application is written in some way using a server-side coding language, such as Active Server Pages (ASP), ColdFusion ® , Perl, Java™, JavaServer Pages (JSP), Hypertext Preprocessor (PHP), Python™, Ruby, Tel, Smalltalk, WebDNA ® In some embodiments, the Web application is written in part in a database query language, such as Structured Query Language (SQL). In some embodiments, the Web application is integrated with an enterprise server product, such as IBM ® Lotus Domino ®In some embodiments, the Web application includes a media player component. In other embodiments, the media player component utilizes one or more of a variety of suitable multimedia technologies, including but not limited to Adobe ® Flash ® , HTML 5, Apple ® QuickTime ® , Microsoft ® Silverlight ® , Java™ and Unity ® .

[0046] refer to Figure 2 In a specific embodiment, the application providing system includes one or more databases 200 accessed by a relational database management system (RDBMS) 210. Suitable RDBMS include Firebird, MySQL, PostgreSQL, SQLite, Oracle database, Microsoft SQL server, IBM DB2, IBM Informix, SAP Sybase, Teradata, etc. In this embodiment, the application providing system also includes one or more application servers 220 (such as Java server, .NET server, PHP server, etc.) and one or more Web servers 230 (such as Apache, IIS, GWS, etc.). The Web server optionally exposes one or more Web services through an app application programming interface (API) 240. Through a network, such as the Internet, the system provides a browser-based and / or mobile local user interface.

[0047] refer to Figure 3 In a specific embodiment, the application providing system alternatively has a distributed cloud-based architecture 300 and includes elastic load-balanced automatically-scaling Web server resources 310 and application server resources 320 and a synchronously replicated database 330 .

[0048] Standalone Application In some embodiments, computer program comprises stand-alone application, and it is as independent computer process rather than the program of add-on operation of existing process, for example, not plug-in.Those skilled in the art will recognize that stand-alone application is usually compiled.Compiler is the computer program that source code written in programming language is converted into binary target code of for example, assembly language or machine code.Suitable compiled programming language includes but is not limited to C, C++, Objective-C, COBOL, Delphi, Eiffel, Java ™, Lisp, Python ™, Visual Basic and VB.NET, or their combination.Compilation will be performed usually, at least part of compilation is to create executable program.In some embodiments, computer program comprises one or more executable compiled applications.

[0049] Software Modules In some embodiments, the platform, system, medium and method disclosed in the present invention include software, server and / or database modules, or use thereof. In view of the content disclosed in the present invention, the software module is created by techniques known to those skilled in the art, using machines, software and languages ​​known in the art. The software module disclosed in the present invention can be implemented in a variety of ways. In various embodiments, the software module includes files, code snippets, programming objects, programming structures, distributed computing resources, cloud computing resources, or a combination thereof. In other embodiments, the software module includes multiple files, multiple code snippets, multiple programming objects, multiple programming structures, multiple distributed computing resources, multiple cloud computing resources, or a combination thereof. In various embodiments, one or more software modules include, but are not limited to, Web applications, mobile applications, stand-alone applications, and distributed or cloud computing applications. In some embodiments, the software module is located in a computer program or application. In other embodiments, the software module exists in multiple computer programs or applications. In some embodiments, the software module is hosted on a single machine. In other embodiments, the software module is hosted on multiple machines. In other embodiments, the software module is hosted on a distributed computing platform, such as a cloud computing platform. In some embodiments, the software module is hosted on one or more machines at a certain location. In other embodiments, the software modules are hosted on one or more machines in multiple locations.

[0050] database In some embodiments, the platform, system, medium and method disclosed in the present invention include one or more databases, or the utilization thereof. In view of the content disclosed in the present invention, those skilled in the art will appreciate that many databases are suitable for storing and retrieving user information, research information, slide information, field of view (FoV) information, flow cell information, image information, genome information, transcriptome information and proteome information. In various embodiments, suitable databases include but are not limited to relational databases, non-relational databases, object-oriented databases, object databases, entity relationship model databases, associated databases, XML databases, document-oriented databases and graphic databases. Other non-limiting examples include SQL, PostgreSQL, MySQL, Oracle, DB2, Sybase and MongoDB. In some embodiments, the database is based on the Internet. In other embodiments, the database is based on the Web. In other embodiments, the database is based on cloud computing. In specific embodiments, the database is a distributed database. In other embodiments, the database is based on one or more local computer storage devices.

[0051] Instrument interface In some embodiments, the platforms, systems, media, and methods disclosed herein include an instrument interface. In further embodiments, the instrument interface is a hardware and / or software interface that is communicatively coupled to one or more laboratory instruments. Many laboratory instruments are suitable, including but not limited to nucleic acid sequencers or sequencing platforms, digital spatial analyzers (e.g., NanoString GeoMx ® ), spatial molecular imagers (e.g., NanoString CosMx™), RNA expression analyzers (e.g., NanoString nCounter ® In some embodiments, the digital spatial analyzer includes an RNA detection function for analyzing the entire transcriptome from a tissue and / or sample on a single FFPE or fresh frozen (FF) slide. In some embodiments, the digital spatial analyzer includes a protein measurement function to generate quantitative and spatial analysis of multiple proteins on a single FFPE or FF slide.

[0052] In various embodiments, as non-limiting examples, the instrument interface allows an application to perform monitoring of one or more laboratory instruments, receiving data from one or more laboratory instruments, and / or sending operating instructions to one or more laboratory instruments. In some embodiments, the instrument interface is a unidirectional link to one or more laboratory instruments. In other embodiments, the instrument interface is a bidirectional link to one or more laboratory instruments.

[0053] In some embodiments, the platforms, systems, media, and methods disclosed herein receive data via an instrument interface that is communicatively coupled to one or more laboratory instruments. In some embodiments, data is received directly from one or more laboratory instruments. In other embodiments, data is received indirectly from one or more laboratory instruments. Many types of data are suitable. In the field of space biology, useful data include, but are not limited to, biological image data, such as microscope images (e.g., micrographs) of formalin-fixed paraffin-embedded (FFPE) and / or fresh-frozen (FF) cells and / or tissue samples. In some embodiments, data from a single slide for RNA determination and protein determination is divided into two data sets. In some embodiments, data from a single slide for RNA determination and protein determination is merged together. In some embodiments, the image data is two-dimensional data. In some embodiments, the image data is three-dimensional image data. In addition, in the field of space biology, useful data include, but are not limited to, "omics" data, such as genomic data, proteomic data, metabolomic data, metagenomic data, phenotypic group data, and / or transcriptomic data. In some embodiments, omics data is associated with image data. In other embodiments, the omics data is associated with the image data in two and / or three dimensions. In various embodiments, the omics data is associated with the image data as metadata and / or as an overlay of the image. Other useful information includes patient data, demographic data, diagnostic data, disease data, treatment data, research data, etc.

[0054] In some embodiments, the platforms, systems, media, and methods disclosed herein can receive data through an instrument interface and save it in its original file format. In some embodiments, the platforms, systems, media, and methods disclosed herein can receive data through an instrument interface and add it to a data set.

[0055] Research Administration In some embodiments, the disclosed platforms, systems, media, and methods include features and functionality for study management. In other embodiments, the disclosed subject matter includes tools that allow users to create studies, edit and / or modify studies, and delete studies.

[0056] Figure 4 A non-limiting example of a GUI for a spatial bioinformatics integration portal including a default study screen is shown. The study screen has a study data section, a flow structure section, and a flow data section. Continuing with reference to FIG4 , the study data section includes the study name, the number of fields of view (FoV) associated with the study, the number of cells associated with the study, the complexity of the study, a list of flow cells associated with the study, and a list of flow runs for the study.

[0057] Figure 8 shows a non-limiting example of a GUI for a spatial bioinformatics integrated portal including an environment for opening studies including previously created studies. Referring to Figure 8, the pipeline structure section includes a schematic diagram of a pipeline consisting of a series of editable modules for a study.

[0058] Process orchestration tools In some embodiments, the platform, system, medium and method disclosed in the present invention include a process orchestration tool. In other embodiments, the process orchestration tool includes features and functions that allow a user to, for example, create, edit, save, open, manage and execute analysis processes. In further embodiments, the process orchestration tool includes features and functions that allow a user to connect modules together and run them sequentially or in parallel to transform data.

[0059] In some embodiments, the user selects a module from a module library. Each module may have defined "interactions" to achieve seamless integration of process structure, process data, and image viewers, thereby achieving the goal of visualizing each algorithm in an organizational space. Fig.62 A non-limiting example of an interactive editing module of a process orchestration tool is shown, which integrates a process structure pane with full access to toolboxes and process data. The editing interface provides a grid workspace that provides real-time updates for end users to perform analysis tasks, and full access to toolboxes and modules, combined with data displays to visualize results and adjust analysis plans. Fig.63 Non-limiting examples of QC user interface enhancements are shown. The figure shows the functionality to connect cell visualization with downstream analysis selection. QC results can be displayed by simply clicking on the image. The user can exclude data from downstream analysis based on low QC results. However, checking the box does not delete the data from the object, but only removes it as an input for downstream analysis. In some embodiments, the module may include the ability to change input data. In some embodiments, the module may include the ability to change input data before the downstream module is executed.

[0060] Figure 5 A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown, which includes a pipeline orchestration tool that allows users to create and edit analysis pipelines by dragging and dropping predefined editable module elements from a searchable toolbox and linking them together. Figure 5 ,The searchable toolbox contains a list of available modules, which include normalization, PCA, clustering, nearest neighbor, etc. The user has placed the initial data module into the interface, and can name the pipeline, save the pipeline, and / or save and run the pipeline being developed.

[0061] In some embodiments, a user selects a module from a module library. In some embodiments, a module may include GeoMx® In some embodiments, the modules may include applications for CosMx™ SMI. In some embodiments, the modules may include applications for biomarker discovery and validation, immunoassays, unbiased pathway analysis, tissue atlases, subcellular localization analysis, cell neighborhood analysis, cell atlases, or receptor-ligand interactions. In other embodiments, the modules may be editable by the user and / or have user-configurable parameters. Many modules are applicable. Table 1 provides non-limiting examples of modules.

[0062] Table 1 Individual analysis methods

[0063] In some embodiments, the normalization module in Table 1 may include using total counts as a normalization factor. In some embodiments, the normalization module in Table 1 may include using Pearson residuals. In some embodiments, the normalization module in Table 1 may include generating background-subtracted protein data from raw mean fluorescence intensity (MFI) values. In some embodiments, the quality control module in Table 1 may be performed on cells, targets, or FOVs.

[0064] The spatial network modules listed in Table 1 create a network or graph structure of the physical distribution of cells. Cells are converted into nodes in a graph, and connections between cells (e.g., nearest neighbors) are represented as edges. The network can be constructed in one of three ways: based on radius (connecting all cells within a given radius), nearest neighbor, or Delaunay triangulation.

[0065] The quality control modules listed in Table 1 cover quality control for both RNA assays and protein assays. The application of RNA assay quality control is to flag unreliable negative probes, cells, FOVs, and target genes. The user can choose to remove those flagged negative probes, cells, target genes, and FOVs and generate a filtered dataset as input for downstream analysis. The application of protein assay quality control is to flag unreliable cells based on segmented cell regions, negative probe expression, and high / low target expression. Specifically, cells with abnormal Grubb's test p-values ​​(p<0.05) in the segmented regions are flagged. Cells with average negative probe values ​​below a lower threshold (default = 2) or above an upper threshold (default = 50) are flagged. Cells with at least a% of proteins in the bth quantile (default a = 0.5, b = 0.9) are considered cells with high target expression and are therefore flagged. Cells with at least less than c proteins in the d quantile (default c = 3, d = 0.5) are considered cells with low expression and are also flagged. The normalization modules listed in Table 1 cover both RNA and protein assays. Normalization for RNA assays is based on the concept of adjusting the library size factor to ensure cell-specific total transcript abundance and count distribution, which may vary somewhat between FOVs and, more notably, between different samples, but which does not affect downstream visualization and analysis of the data. Two normalization methods are available: (1) Pearson residual normalization (default method) based on estimated mean and variance: (raw counts - mean) / sd; (2) another normalization method based on total count size factor: raw counts / total counts. Normalization for protein assays is based on the following concepts: (1) background subtraction to ensure that cell-specific protein expression accounts for the background counts observed in the IgG isotype control antibody. (2) total intensity to reduce the impact of technical artifacts (e.g., shadowing / edge effects). (3) arcsine transformation to improve visualization clarity and stabilize variance.

[0066] The principal component analysis listed in Table 1 performs orthogonal constrained dimensionality reduction on the count data for all cells in the dataset. It produces output values ​​(PCs) that represent the axes of variation within the data, which are composite values ​​of weighted expression within a given cell. The PCs are sorted in descending order of how much variation they explain in the data. These data can be used to better understand variation within a dataset, but are most often used for single-cell analysis as input to UMAP analysis.

[0067] The Unified Manifold Approximation and Projection (UMAP) module in Table 1 provides a method to visualize high-complexity datasets in two-dimensional space, using nonlinear methods to estimate related cell groups or features. This method is a common method for visualizing single-cell data to identify related cell clusters that may be from the same lineage.

[0068] The InSitu Type (RNA Cell Typing) module in Table 1 is a cell typing algorithm designed for statistical and computational efficiency of spatial transcriptomics data. It is based on a likelihood model that weights the evidence for each expression value and extracts all available information from the expression profile of each cell. This likelihood model is the basis for the Bayesian classifier for supervised cell typing and the expectation maximization algorithm for unsupervised and semi-supervised clustering. Insitu type also exploits other data types collected in spatial studies, such as cell images and spatial contexts, by using them to provide a priori probabilities for cell type calls, as shown in Figure 70.

[0069] The CELESTA (Cell Typing for Protein) module in Table 1 applies an algorithm to perform cell typing by considering the marker expression profile of each cell and, if desired, spatial information. Cell typing calls are guided by a feature matrix that specifies markers known to have high / low expression for each cell type. A bimodal Gaussian mixture model can then be fit to estimate the probability that each cell has "high expression" for each marker considered. When the probability is high enough, the cell is considered an "anchor cell". When the probability is not high enough to make a high-certainty cell type call, the algorithm also considers spatial information by considering the cell type calls of neighboring cells. These are considered "index cells".

[0070] The nearest neighbor module in Table 1 builds a KNN (k-nearest neighbor) graph based on the Euclidean distance in PCA space, and then builds a SNN (shared nearest network) graph with edge weights between any two units based on shared overlap (Jaccard distance) in the local neighborhood and pruning of distant edges.

[0071] The Leiden clustering module in Table 1 is an unsupervised clustering method used to determine related groups of cells based on their similarity in the graph structure. Clusters are defined by moving cells to determine groups of cells that can be clustered without changing the overall relationship of the graph, and finding unstable nodes that act as bridges between related groups to help define the boundaries of different clusters, as shown in Figure 71.

[0072] The neighborhood analysis module in Table 1 identifies distinct clusters of cell neighborhoods based on their cell type composition across tissues. This module helps automatically define the structural composition of tissues by looking for regional differences in cell type composition. Structures can be repetitive structures that are frequently found but not contiguous within a tissue (e.g., glomeruli in the kidney, germinal centers in lymph nodes) or repetitive structures that are physically connected across tissues (e.g., epithelial layers in the colon).

[0073] The spatial expression analysis module in Table 1 is used to identify genes with non-uniform / autocorrelated spatial distribution throughout the tissue, which may be associated with specific tissue architectures, microenvironmental niches, or cell types. Use this module to find genes that carry spatially correlated information. This module also measures the correlated spatial expression between genes, which can be used to group genes into different spatial expression patterns. Two statistics calculated related to spatial expression patterns are Moran's I and Lee's L. Fig.72 The spatial expression pattern based on Lee's L is shown.

[0074] The cell type colocalization module in Table 1 investigates the tendency of different cell types to be close to each other. Each pair of cell types defined from supervised or unsupervised clustering is tested using the Ripley K function (a function of the distance between different cell types) to determine whether the spatial distribution of the cells differs from a theoretical Poisson point process, where the position of one cell does not depend on the position of another cell. The results are summarized in a heatmap, which indicates which cell types tend to cluster together or separate from each other, as shown in Figure 1. Fig.73 In addition, plotting the pairwise correlation function for a given pair of cell types as a function of radius provides a more detailed view that illustrates the specific distances at which the various cell types colocalize.

[0075] The marker gene module in Table 1 will identify marker genes associated with each cell type or cluster previously identified within the dataset. This module looks for genes that are consistently expressed above background, but are also most specifically limited to each cell type or cluster within the dataset. This module acts on each gene independently. This module can also be used to find marker genes in identified neighborhoods, but these genes will be associated with the overall cellular composition of those neighborhoods, such as Fig.74 shown.

[0076] The Ligand-Receptor Analysis (RNA Only) module in Table 1 scores and explores ligand-receptor signaling for cell pairs and single cells. Ligand-receptor target expression in neighboring cells is used to calculate co-expression scores. A test is then performed to determine whether the overall score average for each connected receptor pair is enriched by the spatial arrangement of the cells, such as Fig.75 shown.

[0077] The signaling pathway (RNA only) modules in Table 1 are calculated on a per-cell basis using gene sets of predefined pathways. This method calculates the relative enrichment of genes within each pathway. Gene sets with insufficient coverage are excluded from the analysis.

[0078] The Differential Expression (RNA Only) module in Table 1 estimates and summarizes generalized linear (mixed) models for single-cell expression. Expression in tissue-neighboring cells was controlled by including the “neighboring cell expression” of the analyzed gene as a fixed effect control variable in the DE model. Controlling for neighboring cell expression was based on the observation that tissue-neighboring cells are not independent and that comparisons of DE between groups may be affected by uncertainty in cell parcellation and cell type. Single-cell DE analysis can test whether groups within a specific cell type are DE. In practice, imperfect cell parcellation may result in transcript “contamination” or “spillover” from neighboring cells, which can also increase uncertainty in downstream cell typing analyses. For these reasons, including expression in neighboring cells of the analyzed gene can be a useful control variable.

[0079] Figure 64 shows a non-limiting example of a user interface for a cell segmentation module on a flow orchestration tool. One or more flow cells can be selected to create a study and displayed on the cell segmentation module. The flow orchestration tool is responsible for handling the loading of morphological images and sending them to the cell segmentation module. In some embodiments, the cell segmentation module includes one or more deep learning models. In some embodiments, one or more deep learning models are trained using cell or tissue images. In some embodiments, the images of cells or tissues include microscope-derived images, morphological images, or fluorescence images. In some embodiments, deep learning models are trained to be suitable for segmenting specific tissue types.

[0080] The inference engine will be responsible for loading the model and segmenting cells from input images of cells and tissues based on the model predictions in the cell segmentation module. The model selection function will then be responsible for selecting the best model for a given input image. Users can modify various cell segmentation parameters such as cell diameter, expansion parameter, cell probability, and gradient flow threshold through the parameter selection interface. The process orchestration tool saves these parameter sets to the current study. The process can support multiple segmentation results. The process orchestration tool will provide communication methods between the cell segmentation module and the image viewer to display the cell segmentation result overlay. Fig.65 The cell segmentation output is shown integrated into the image viewer. As the user interacts with the module and changes parameters, the flow orchestration tool will distinguish between temporary and permanent states of the cell segmentation results. The flow is preloaded with default parameters, and each flow cell segmentation result can be restored to its initial default state. In some embodiments, the image viewer can overlay different segmentation results. Upon completion of a cell re-segmentation action, the flow orchestration tool will trigger the transcript to cell reassignment logic, which will trigger the rest of the data analysis in the flow. In some embodiments, the re-segmentation module can complete execution before the user can visualize the results with the image viewer.

[0081] In some embodiments, one or more available modules in the process orchestration tool include training machine learning models and / or applying machine learning models. In some embodiments, the machine learning model may include dimensionality reduction through a nonlinear dimensionality reduction algorithm. In some embodiments, the nonlinear dimensionality reduction algorithm may include Sammon mapping, principal curves and manifolds, Laplace eigenmaps, isometric mapping, local linear embedding, local tangent space alignment, maximum variance expansion, Gaussian process latent variable model, t-distributed random neighborhood embedding, relational perspective, infection map, curve component analysis, curve distance analysis, differential homeomorphism dimensionality reduction, manifold alignment, diffusion mapping, local multidimensional scaling, nonlinear PCA, data-driven high-dimensional scaling, manifold carving (Manifold sculpting), RankVisu, topologically constrained isometric embedding, unified manifold approximation and projection (UMAP). In some embodiments, the UMAP module in Table 1 may apply a feedforward neural network (e.g., an autoencoder) on a subset of the data to project the manifold clustering onto the entire data set. In some embodiments, a feedforward neural network may be trained to approximate an identity function (i.e., trained to map from a vector of values ​​to the same vector). In some embodiments, a feed-forward neural network may be used for dimensionality reduction purposes, where a hidden layer of a network may be restricted to contain only a small number of network units.

[0082] In some embodiments, machine learning may include methods combined with methods for estimating probability distributions. In some embodiments, the cell typing module in Table 1 may be clustered based on known gene expression profiles using a maximum likelihood estimation method. In some embodiments, the cell typing module may be a stand-alone application.

[0083] In some embodiments, the orchestration tool may also include a data extraction process. In some embodiments, the data extraction process may generate a set of output files that include summary information of image data from laboratory instruments. In some embodiments, a user can select a set of data files organized by flow cells within the orchestration tool. In some other embodiments, the data extraction process may generate a set of tileDB arrays connected to Seurat objects. In some further embodiments, the user can analyze the arrays. In some further embodiments, the analysis results within the orchestration tool can be written back to the Seurat / tileDB object. In some embodiments, the raw files are exported. In some embodiments, the raw files are exported once for each study.

[0084] FIG6 shows a non-limiting example of a GUI for a spatial bioinformatics integration portal; in this example, the GUI includes a process editing environment for a process orchestration tool to allow a user to edit process and / or module run parameters. Figure 6, the module toolbox includes modules such as cell typing, DenseDE, Pre DenseDE, etc. Continuing to refer to Figure 6, the user has named the process and connected the three modules of quality control, normalization and scaling to the process in series. Each module contains an icon that allows the user to access settings.

[0085] Figure 7 shows a non-limiting example of a GUI for the spatial bioinformatics integration portal, which includes a workflow branching feature of the workflow orchestration tool to allow users to perform iterative analysis by modifying parameters and rerunning steps or creating new branches of the same workflow. Modules are optionally configured to run in series, in parallel, and / or in branched workflows.

[0086] Figure 66 shows a non-limiting example of a Cell Typing Module display. CosMx™ is a spatial molecular imager for subcellular resolution of mRNA transcripts and protein targets. A subset of the CosMx™ NSCLC display dataset was analyzed based on semi-supervised clustering. The workflow orchestration tool allows the user to execute data from mRNA transcripts and protein targets and integrate data and analysis. Cell typing is displayed by color based on the frequency of the cell type in the decision.

[0087] Machine Learning In some embodiments, the platform, system, medium, and method disclosed in the present invention include one or more models available in a process orchestration tool, including training a machine learning model and / or applying a machine learning model. In some embodiments, the machine learning model may include an unsupervised machine learning model, a supervised machine learning model, a semi-supervised machine learning model, or a self-supervised machine learning model. In some embodiments, the supervised machine learning model may include, for example, a random forest, a support vector machine (SVM), a neural network, or a deep learning algorithm.

[0088] In some embodiments, the platforms, systems, media, and methods disclosed herein include machine learning models that utilize one or more neural networks. In some embodiments, a neural network is a computing system that can learn the relationship between an input data set and a target data set. A neural network can be a software representation of a human nervous system (e.g., a cognitive system) that is intended to obtain the "learning" and "generalization" capabilities used by humans. In some embodiments, a machine learning algorithm includes a neural network that includes a CNN. Non-limiting examples of structural components of the machine learning algorithms described herein include: CNN, recurrent neural network, dilated CNN, fully connected neural network, deep generative model, and Boltzmann machine.

[0089] In some embodiments, a neural network includes a series of layers called "neurons". In some embodiments, a neural network includes an input layer, to which data is presented; one or more internal and / or "hidden" layers; and an output layer. Neurons can be connected to neurons in other layers via connections with weights, where weights are parameters that control the strength of the connections. The number of neurons in each layer may be related to the complexity of the problem being solved. The minimum number of neurons required for each layer may be determined by the complexity of the problem, while the maximum number may be limited by the generalization ability of the neural network. The input neurons can receive the data being presented and then transmit the data to the first hidden layer through the weights of the connections, where the weights are modified during training. The first hidden layer can process the data and transmit its results to the next layer through a second set of weighted connections. Each subsequent layer can "aggregate" the results of the previous layers into more complex relationships. In addition, while traditional software programs require specific instructions to be written to perform functions, neural networks are programmed by training with known sample sets and allowing them to modify themselves during (and after) training to provide desired outputs, such as output values. After training, when new input data is provided to the neural network, it is configured to generalize what it "learned" during training and apply what it learned from training to new, previously unseen input data in order to generate outputs that are relevant to that input.

[0090] In some embodiments, the neural network includes an artificial neural network (ANN). The ANN can be a machine learning algorithm that can be trained to map an input data set to an output data set, wherein the ANN includes an interconnected node group organized into multiple layers of nodes. For example, the ANN architecture may include at least an input layer, one or more hidden layers, and an output layer. The ANN may include any total number of layers and any number of hidden layers, wherein the hidden layer is used as a trainable feature extractor to allow a set of input data to be mapped to an output value or a set of output values. As used herein, a deep learning algorithm (e.g., a deep neural network (DNN)) is an ANN comprising multiple hidden layers, such as two or more hidden layers. Each layer of a neural network may include multiple nodes (or "neurons"). The node receives input directly from the input data or the output of the node in the previous layer, and performs a specific operation, such as a sum operation. The connection from the input to the node is associated with a weight (or weighting factor). The node can sum the product of all inputs and their associated weights. The weighted sum may produce a bias. The output of a node or neuron can be gated using a threshold or an activation function. The activation function can be a linear function or a nonlinear function. The activation function can be, for example, a rectified linear unit (ReLU) activation function, a leaky ReLU activation function, or other functions, such as saturated hyperbolic tangent, an identity function, a binary step function, a logistic function, an inverse tangent function, a soft sign function, a parametric rectified linear unit function, an exponential linear unit function, a softplus function, a curved identity function, a soft exponential function, a sine function, a Sinc function, a Gaussian function or a S-type function, or any combination thereof.

[0091] The weighting factors, bias values, and thresholds or other computational parameters of a neural network can be "taught" or "learned" using one or more sets of training data during a training phase. For example, the parameters can be trained using input data from a training data set and gradient descent or back-propagation methods so that the output values ​​computed by the ANN are consistent with the examples contained in the training data set.

[0092] The number of nodes used in the input layer of the ANN or DNN may be at least about 10, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10,000, 20,000, 30,000, 40,000, 50,000, 60,000, 70,000, 80,000, 90,000, 100,000 or more. In other cases, the number of nodes used in the input layer can be at most about 100,000, 90,000, 80,000, 70,000, 60,000, 50,000, 40,000, 30,000, 20,000, 10,000, 9000, 8000, 7000, 6000, 5000, 4000, 3000, 2000, 1000, 900, 800, 700, 600, 500, 400, 300, 200, 100, 50, 10 or less. In some cases, the total number of layers used in the ANN or DNN (including input and output layers) can be at least about 3, 4, 5, 10, 15, 20 or more. In other cases, the total number of layers can be at most about 20, 15, 10, 5, 4, 3 or less.

[0093] In some cases, the total number of learnable or trainable parameters, such as weighting factors, biases, or thresholds, used in an ANN or DNN may be at least about 10, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000, 2000, 3000, 4000, 5000, 6000, 7000, 8000, 9000, 10,000, 20,000, 30,000, 40,000, 50,000, 60,000, 70,000, 80,000, 90,000, 100,000, or more. In other cases, the number of learnable parameters can be at most about 100,000, 90,000, 80,000, 70,000, 60,000, 50,000, 40,000, 30,000, 20,000, 10,000, 9000, 8000, 7000, 6000, 5000, 4000, 3000, 2000, 1000, 900, 800, 700, 600, 500, 400, 300, 200, 1000, 900, 800, 700, 600, 500, 400, 300, 200, 100, 50, 10, or less.

[0094] In some embodiments, the platforms, systems, media, and methods disclosed herein include a machine learning model including a neural network, such as a deep CNN. In some embodiments using a CNN, the network is composed of any number of convolutional layers, expansion layers, or fully connected layers. In some embodiments, the number of convolutional layers is between 1-10, and the number of expansion layers is between 0-10. The total number of convolutional layers (including input layers and output layers) can be at least about 1, 2, 3, 4, 5, 10, 15, 20 or more, and the total number of expansion layers can be at least about 1, 2, 3, 4, 5, 10, 15, 20 or more. The total number of convolutional layers can be at most about 20, 15, 10, 5, 4, 3 or less, and the total number of expansion layers can be at most about 20, 15, 10, 5, 4, 3 or less. In some embodiments, the number of convolutional layers is between 1-10, and the number of fully connected layers is between 0-10. The total number of convolutional layers (including input and output layers) may be at least about 1, 2, 3, 4, 5, 10, 15, 20, or more, and the total number of fully connected layers may be at least about 1, 2, 3, 4, 5, 10, 15, 20, or more. The total number of convolutional layers may be at most about 20, 15, 10, 5, 4, 3, 2, 1, or less, and the total number of fully connected layers may be at most about 20, 15, 10, 5, 4, 3, 2, 1, or less.

[0095] In some embodiments, the machine learning algorithm comprises a neural network, including a convolutional neural network (CNN), a recurrent neural network (RNN), a dilated CNN, a fully connected neural network, a deep generative model, and / or a deep restricted Boltzmann machine.

[0096] In some embodiments, the machine learning model includes one or more CNNs. The CNN can be a deep and feed-forward ANN. The CNN can be suitable for analyzing visual images. The CNN can include an input layer, an output layer, and multiple hidden layers. The hidden layers of the CNN can include convolutional layers, pooling layers, fully connected layers, and normalization layers. These layers can be organized in three dimensions: width, height, and depth.

[0097] A convolutional layer can apply a convolution operation to the input and pass the result of the convolution operation to the next layer. For processing images, the convolution operation can reduce the number of free parameters, allowing the network to become deeper with fewer parameters. In a neural network, each neuron can receive input from multiple locations in the previous layer. In a convolutional layer, a neuron can receive input only from a restricted subregion of the previous layer. The parameters of a convolutional layer can include a set of learnable filters (or kernels). Learnable filters may have a small receptive field and extend to the entire depth of the input volume. During the forward pass, each filter can be convolved across the width and height of the input data volume, calculate the dot product between the filter elements and the input data, and generate a two-dimensional activation map for that filter. As a result, the network may learn filters that activate when certain specific types of features are detected at a certain spatial location in the input data.

[0098] In some embodiments, the machine learning model includes an RNN. An RNN is a neural network with recurrent connections that can encode and process sequential data. The RNN may include an input layer configured to receive an input sequence. The RNN may also include one or more hidden recurrent layers that maintain states. In each step, each hidden recurrent layer can calculate the output and next state of the layer. The next state may depend on the previous state and the current input. The state can be maintained across steps and dependencies in the input sequence can be obtained.

[0099] The RNN can be a long short-term memory (LSTM) network. The LSTM network can be composed of LSTM cells. The LSTM cell can include a cell, an input gate, an output gate, and a forget gate. The cell can be responsible for tracking dependencies between elements in the input sequence. The input gate can control the extent to which new values ​​flow into the cell, the forget gate can control the extent to which values ​​are retained in the cell, and the output gate can control the extent to which values ​​in the cell are used to calculate the output activation of the LSTM cell.

[0100] Alternatively, an attention mechanism (e.g., a transformer). An attention mechanism may focus or "attend to" certain regions of the input while ignoring others. This can improve model performance because some regions of the input may be less relevant. At each step, the attention unit may compute the dot product of the context vector and the input to that step, among other operations. The output of the attention unit may define the location of the most relevant information in the input sequence.

[0101] In some embodiments, the pooling layer includes a global pooling layer. The global pooling layer can combine the outputs of the neuron groups of one layer into a single neuron in the next layer. For example, the maximum pooling layer can use the maximum value of each of the neuron groups in the previous layer; the average pooling layer can use the average value of each neuron group in the previous layer.

[0102] In some embodiments, a fully connected layer connects every neuron in one layer to every neuron in another layer. In a neural network, each neuron may receive input from some digital position in the previous layer. In a fully connected layer, each neuron may receive input from every element in the previous layer.

[0103] In some embodiments, the normalization layer is a batch normalization layer. The batch normalization layer can improve the performance and stability of the neural network. The batch normalization layer can provide zero mean / unit variance inputs to any layer in the neural network. Advantages of using a batch normalization layer can include faster training of the network, higher learning efficiency, easier initialization of weights, more feasible activation functions, and a simpler process for creating deep networks.

[0104] The trained algorithm can be configured to accept multiple input variables and generate one or more output values ​​based on the multiple input variables. The trained algorithm may include a classifier so that each of the one or more output values ​​includes one of a fixed number of possible values ​​representing the classification of the classifier to the biological sample and / or the subject (e.g., a linear classifier, a logistic regression classifier, etc.). The trained algorithm may include a binary classifier so that each of the one or more output values ​​includes one of the two values ​​representing the classification of the classifier to the biological sample and / or the subject (e.g., {0, 1}, {positive, negative}, or {high risk, low risk}). The trained algorithm may be another type of classifier so that each of the one or more output values ​​includes one of more than two values ​​(e.g., {0, 1, 2}, {positive, negative or uncertain}, or {high risk, medium risk or low risk}) to represent the classification of the classifier to the biological sample and / or the subject. The output value may include a descriptive label, a numerical value, or a combination thereof. Some output values ​​may include a descriptive label. Some output values ​​may include numerical values, such as binary, integers, or continuous values. Such binary output values ​​may include, for example, {0, 1}, {positive, negative}, or {high risk, low risk}. Such integer output values ​​may include, for example, {0, 1, 2}. Such continuous output values ​​may include, for example, a probability value that is at least 0 and not greater than 1. Such continuous output values ​​may include, for example, a non-normalized probability value that is at least 0. Such continuous output values ​​may indicate the prognosis of a cancer-related category of a subject. Some numerical values ​​may be mapped to descriptive labels, for example, mapping 1 to "positive" and 0 to "negative". If the sample is not classified as "positive", "negative", 1 or 0, the sample classification may be assigned an output value of "uncertain" or 2. In this case, a set of two cutoff values ​​is used to classify the sample into one of three possible output values. Examples of cutoff value sets may include {1%, 99%}, {2%, 98%}, {5%, 95%}, {10%, 90%}, {15%, 85%}, {20%, 80%}, {25%, 75%}, {30%, 70%}, {35%, 65%}, {40%, 60%}, and {45%, 55%}. Similarly, n cutoff value sets may be used to classify the sample into one of n+1 possible output values, where n is an arbitrary positive integer.

[0105] Visualization Fig.67 A non-limiting example of an application architecture and service overview for graph processing development is shown. The core application services are listed in the center, and the visualization services are shown in diagram form in the lower right corner. The front-end application modules are listed on the left. The process service (process management service) receives input from the front-end application for process execution and process construction, manages processes and process run execution processes. The study locking service follows the input from the study UI and is responsible for controlling the study locking state and managing active study locks. The study service is responsible for managing studies and the study creation process. Its input is flow pools, FoVs, visualizations, and other forms of study metadata. The visualization service gateway obtains data from the front-end modules and is the main gateway for visualization data preparation. The visualization service worker prepares data for visualization and communicates with the visualization service gateway through a message queue, such as Fig.67 As shown in the middle right of Figure 67. The Annotation Management Service is responsible for annotation management and annotation search. The Study Notification Service provides access to notification message streams related to a specific study. As shown in the upper right corner of Figure 67, the Worker Manager is responsible for managing the life cycle of process workers. Process workers are responsible for running process steps or custom modules.

[0106] In some embodiments, the platforms, systems, media, and methods disclosed herein include features and functions for generating data summaries, results, and / or visualizations. In some embodiments, summaries, results, and / or visualizations are generated for data received from laboratory equipment. In some embodiments, summaries, results, and / or visualizations are generated for data converted via one or more modules or processes. In some embodiments, visual displays may include graphs, charts, and points that overlay transcripts or cell annotations onto tissue images. In some embodiments, visualizations may query Seurat / tileDB objects to retrieve relevant data from the object for display. In other embodiments, relevant data may include transcript locations and / or cell annotations. In some embodiments, visualizations may display transcript locations as points, cell annotations (e.g., cell types) as points, box plots, violin plots, and dot plots.

[0107] FIG9 shows a non-limiting example of a GUI for a spatial bioinformatics integration portal, including an environment for viewing the analysis pipeline of a study and visualizing the results of pipeline modules and / or pipelines. Fig. 9 , the process run list includes three process runs. The current process includes the initial data module, the create linked object module, the FoV alignment module, the QC module, the normalization module, the scaling module, and the PCA module, among which this module branches to the UMAP module and the nearest neighbor module, and then the clustering module. Continue to refer to Fig. 9 , select the QC module and the Process Data section includes a data summary / visualization (XY plot with a logarithmic scale of Log10 on the Y axis).

[0108] Fig.10 A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown, including customizable layout options, for example, variable sizes of different panes such as a study details pane, a pipeline structure pane, and a pipeline data pane.

[0109] Figures 11A-11C A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown, which includes an environment that can graphically represent pipeline data as, for example, an XY scatter plot of cell or transcript coordinates for a particular FoV associated with a study. Configurable options include selection of FoV, selection of genes, color coding, visualization type, and view.

[0110] Figures 12A-12C A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown, including an environment for graphically representing pipeline data in the form of a heat map for a specific FoV associated with a study. Configurable options include selection of FoV, visualization type, and zoom.

[0111] Fig.13 A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown, which includes an environment for graphically representing pipeline data in the form of a histogram. Configurable options include gene selection, cell type selection, visualization type, and Y-axis scaling.

[0112] Figures 14A-14C A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown, including an environment for graphically representing specific FoVs associated with a study in the form of a box plot. Configurable options include selection of FoV(s), Y-axis scaling, display of outliers, and visualization type.

[0113] Fig.15 A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown, which includes an environment for graphically representing pipeline data in the form of violin plots. Configurable options include selection of FoV(s), Y-axis scaling, display of outliers, visualization type, and minimum expression value.

[0114] Fig.16A and 16B A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown, which includes an environment for performing process data dimensionality reduction, such as by principal component analysis (PCA) and unified manifold approximation and projection (UMAP). Configurable options include selection of components.

[0115] Fig.17A and 17B A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown, which includes an environment that allows a user to utilize drawing tools to identify image regions and / or graphical plots to annotate process data. Configurable options include FoV selection, gene selection, color coding, and view. Referring to FIG17A , a user can freely draw geometric shapes to identify data to be annotated, or draw shapes freehand to identify data to be annotated. Referring now to FIG17A , a user can freely draw geometric shapes to identify data to be annotated, or draw shapes freehand to identify data to be annotated. Fig. 17B ,The user can freely name the annotation, scale the size of the identified area, change the shape used to identify the area, add informative tags to the annotation, assign attributes to the annotation, and / or delete the annotation.

[0116] Fig.18 A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown, including a test annotation service for interactive annotation linked to flow cell images and tables. Fig.18 , the interface allows users to manage annotations and includes an image viewer and FoV editor.

[0117] Figure 19-22A non-limiting example of a GUI for a spatial bioinformatics integration portal is shown, which includes an interactive workflow data viewing environment allowing a user to select a flow cell image and visualize the associated data using any running workflow module.

[0118] Fig.23 A non-limiting example of a GUI for a spatial bioinformatics integrated portal is shown, which includes a data visualization environment with an image viewer integration, allowing a user to control the image viewer display and view updates to the associated visualization data.

[0119] Data export module output In some embodiments, datasets exported from the AtoMx™ Spatial Informatics Platform (SIP) are further analyzed. In some embodiments, data from the SIP are stored both as independent Seurat objects and as equivalent TileDB arrays. In some embodiments, the exported data includes transcript counts / positions, field of view images, annotation metadata, or user-initiated data transformations performed in the AtoMx SIP prior to export.

[0120] The export module can be used at any point in the AtoMx™ pipeline. All results prior to export will be saved in a Seurat object and a TileDB array. They are equivalent outputs in different formats. The format is the same for RNA and protein studies, but the format of the raw file folder will vary from analyte to analyte. If multiple pipelines from the same study export raw files, there could be terabytes of duplicate files. In addition to formats that store data in memory, the AtoMx SIP export also supports the TileDB format, which allows data to be accessed and loaded when memory is needed. This format, while less used in single cell projects, is scalable to very high density analyses. Since many CosMx studies will be well over 1 million cells, this new format will enable robust and scalable computation in very large studies without having to load all the data into memory. By saving the data in a TileDB array, it does not require all of the data to be saved in memory, but only the specific portion that is being used.

[0121] The main object in TileDB is the Stack of Annotated Matrices (SOMA). A TileDB object is a collection of pointers to RNA counts, normalized RNA counts, negative control probes, and pseudocode SOMAs. Having pointer objects reduces memory usage. Each SOMA follows the AnnData shape. For protein datasets, count data is currently stored in the RNA SOMA.

[0122] All matrices in TileDB are stored as sparse matrices. In some embodiments, matrices are organized with targets on rows and cells on columns, just like standard Seurat objects. In some embodiments, matrices are transposed to look more like AnnData. Cell-target expression data for the raw data is stored in the X slot, which can be retrieved and stored in memory. The data is normalized using Pearson residuals to account for library size, ensuring cell-specific total transcript abundance and count distribution, which may vary between FOVs and samples. Metadata at the cell level is stored in the obs slot. It contains cell information read from the CosMx™ SMI output.

[0123] A cell may contain many transcripts, with xy position coordinates for individual transcripts. End users can visualize this by plotting transcripts for individual samples (flow cell 1, normal liver) and specific regions within the tissue (FOV 15). As shown in Figure 68, the centroid of each cell is shown as a black dot and each transcript is shown as a colored dot. In addition to storing data about count information, the AtoMx SIP also supports downstream analysis, including methods such as differential expression and ligand-receptor analysis. Metadata for these analyses can also be included in the results exported by AtoMx™.

[0124] In some embodiments, TileDB objects can also be read into Seurat objects. In some embodiments, some analysis results of a TileDB object can be read in separately from a TileDB array. In some embodiments, a TileDB object can also be read in by appending all results to a Seurat object using a Seurat converter. In some embodiments, TileDB objects can also be read into python. In some embodiments, a user can plot a unified manifold approximation and projection (UMAP) colored by cell type metadata. In some embodiments, a user can read a UMAP from TileDB python, TileDBR, or Seurat. Regardless of the path the data is read in, all UMAPs are the same data, e.g. Fig.69 shown.

[0125] All analysis modules available on AtoMx™ provide methods to add results to a TileDB study. Each study may use only a subset of these modules, and users can create their own analysis modules with different formats and data specifications. Unless otherwise specified, all modules can be run for RNA and protein. The data output of any module run before exporting will be available in TileDB and Seurat objects. In some embodiments, the platforms, systems, media and methods disclosed in the present invention, the modules whose output data is stored in TileDB and Seurat objects include spatial networks, quality control, normalization, principal component analysis (PCA), unified manifold approximation and projection (UMAP), InSituType (RNA cell typing), CELESTA (protein cell typing), nearest neighbor, Leiden clustering, neighborhood analysis, spatial expression analysis, cell type co-localization, marker genes, ligand-receptor analysis (RNA only), signaling pathways (RNA only) or differential expression (RNA only).

[0126] cooperation In some embodiments, the platforms, systems, media, and methods disclosed herein include features and functions that allow users to collaborate on research. In various embodiments, the subject matter described herein allows users to share within an organization, share with external invited users and trial users, share within users from different organizations, share data between organizations, and / or conduct joint learning to develop and train AI / ML algorithms. In such embodiments, data sharing and joint AI / ML can be achieved, for example: 1) crowdsourcing data to assist NSTG analysis including automatic ROI selection; 2) high-throughput AI drug discovery, including identification of new gene signatures and / or new targets; 3) finding individuals with matching morphology and genetic profiles to identify potential phenotypes of patients.

[0127] Example The following illustrative examples represent embodiments of the software applications, systems, and methods described herein and are not intended to be limiting in any way.

[0128] Example 1 - Exemplary User Workflow Open a study (containing 1-N flow cells); Process → a series of analytical methods linked together as “modules”; Create / Edit / Run; Visualize the results; Graphical representation of data (output of the analysis module); XY, heatmap, histogram, boxplot, violin plot; Expected iterations (run the process or module, visualize the results, repeat...); Annotate data; Describe data using text or shapes; Subset data → reanalyze; and Interact with data for exploratory analysis.

[0129] Example 2 - Spatial Molecular Imaging Study of Formalin-Fixed Paraffin-Embedded (FFPE) Samples of Non-Small Cell Lung Cancer (NSCLC) (Spatially Resolved High-density RNA Data) 960 genes were analyzed in five NSCLC samples, one of which was replicated three times, for a total of seven slides and 771,236 cells using the NanoString Technologies CosMx™ Spatial Molecular Imager. The CosMx Spatial Molecular Imager measures the number of cells per 1 cm in each of the two flow cells. 2 More than 1,000 genes in one area, 3 million cells can be tested in one run.

[0130] To assess sensitivity, we compared the average signal in CosMx SMI to the average signal in a scRNA-seq dataset of CD45+ cells from NSCLC tumors. Only immune cells were used in the comparison. Figure 24 shows the average expression per cell in CosMx SMI versus scRNA-seq data. Genes below the line have higher average counts in scRNA-seq; genes above the line have higher average counts in CosMx SMI data.

[0131] Validated consistency with RNA-seq in cell lines Sixteen cell lines were analyzed using CosMx SMI and bulk RNA-seq. Fig.25A RNA-seq and "bulk" CosMx profiles are shown. The red line shows the breakpoint regression; the orange line marks the breakpoint between background-dominated and signal-dominated data. Fig.25B Shown are the FPKM values ​​of the breakpoints above which the CosMx SMI and RNA-seq are linearly related. Fig.25C Correlation between RNA-seq and CosMx SMI data above the breakpoints is shown.

[0132] Reproducibility was demonstrated in serial sections. Fig.26 Two serial sections of FFPE lung tissue (lung 5 replicates 3 and 5) are shown divided into a grid. Each square contains between 600 and 2,000 cells. Fig. 27 The agreement between the 980 gene expression profiles of matching grid squares is shown. Fig.28 The agreement between the "overall" profiles of 3 replicate sections is shown.

[0133] NSCLC cells were imaged in both expression and physical space. Fig.29 and 30 .

[0134] The ecosystem that exists within the organization was studied. Fig.31A and 31B Results related to neighborhood clustering are shown. Fig.31A It is shown how to characterize the environment of each cell based on the cell types within its neighborhood and how to cluster cells according to the composition of their neighborhood. Fig.31B Neighborhood clustering results in two tissues are shown.

[0135] The study of how cells respond to their environment. Fig.32 Shown are changes in macrophage gene expression within the tumor “Lung 6.” Yellow dots represent SPP1, a driver of macrophage polarization that upregulates PD-L1, and white dots represent HLA-DQA1, required for MHC-II antigen presentation. Fig.33A and 33B Spatial dependence of tumor expression is shown. Figure 33A shows VEGFA expression within tumor cells. Fig.33B HLA-C expression in tumor cells is shown. The expression patterns of both VEGFA and HLA-C are complex and highly spatially ordered.

[0136] Studied how cells interact with neighboring cells. Fig.34A Ligand-receptor signal analysis is shown. Macrophages were scored for APP→CD74 signals. Grey represents CD74- macrophages, blue represents CD74+ macrophages with only APP- neighbors, and red represents CD74+ macrophages with APP+ neighbors. Fig.34B The response of cells to ligand-receptor signals is shown. The method is to compare the differential expression of CD74+ macrophages with / without APP+ neighbors.

[0137] Example 3 - First exemplary embodiment In a first specific non-limiting embodiment, the spatial bioinformatics portal described herein includes a data analysis suite that provides on-instrument analysis and visualization. Fig.36An exemplary data analysis suite is shown, which includes a slide browser section, a dataset and probe section, and multiple analysis tools. In this example, the spatial bioinformatics portal also includes a workspace for managing studies, images, and results across laboratory instrument platforms. FIG37 shows an exemplary workspace that includes features and functions that provide direct access to experimental data, tools for sharing data and results with global collaborators, and streamlined analysis through integration with specific application workflows. Reference Fig.37 , the workspace includes navigation that provides access to the Dashboard, Gallery, Research Screen, Collaboration Screen, and Marketplace. Continue to Reference Fig.37 The dashboard includes portable access to user-related research, collections, scans, and flow pools, as well as activity and collaboration history. Fig.38 , the research screen includes a list of ongoing studies and a list of studies that have been prepared. For each study, the collaborators are summarized graphically. Fig.39 , the screen for a particular study includes a comprehensive view of the study, including an overview, one or more instruments associated with the study, workflows, one or more data visualizations, a summary of collaborators, and an activity history. Referring to FIG40 , the screen for a particular study includes a study summary for the study, study data, a list of flows providing access to each flow structure, e.g., a flow orchestration tool, and optional visualizations of each step in each flow. In this example, the flow orchestration tool allows a user to: 1) create, execute, and save flows for future analysis; 2) modify flows; 3) add custom modules; and, 4) display selected data files, flows, and visualizations in an integrated viewer.

[0138] Embodiment 4 - Second exemplary embodiment In a second specific non-limiting embodiment, the spatial bioinformatics integrated portal described herein includes a navigation providing access to a home screen, an instrument screen, a shared summary screen, a user management screen, and a public screen. Figure 41-61 .

[0139] Although preferred embodiments of the present invention have been shown and described herein, it will be apparent to those skilled in the art that these embodiments are provided by way of example only. Numerous variations, modifications, and alternatives are contemplated by those skilled in the art without departing from the subject matter of the present invention. It should be understood that various alternatives to the embodiments of the subject matter described herein may be employed in practicing the present subject matter.

Claims

1. A system comprising at least one processor and instructions executable by the at least one processor to provide a spatial bioinformatics application, comprising: a) an instrument interface communicatively coupled to one or more laboratory instruments; b) a software element configured to receive data directly or indirectly from the one or more laboratory instruments, wherein the data comprises biological image data and one or more of the following: genomic, proteomic, metabolomic, metagenomic, phenomic, and transcriptomic data; c) a software element configured to provide a process orchestration tool that allows a user to create, edit, manage and execute analytical processes, wherein the process orchestration tool allows a user to link modules together and run them sequentially or in parallel to transform received data; and d) A software element configured to generate a visualization of the received and / or transformed data.

2. The system according to claim 1, characterized in that: The one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer, or a combination thereof.

3. The system according to claim 1, characterized in that: The instrument interface allows the application to perform one or more of the following operations: monitor the one or more laboratory instruments, receive data from the one or more laboratory instruments, and send operating instructions to the one or more laboratory instruments.

4. The system according to claim 1, characterized in that: The process orchestration tool includes a graphical user interface (GUI), and a user creates and / or edits an analysis process by dragging and dropping modules within the GUI.

5. The system according to claim 1, characterized in that: The process orchestration tool allows users to create, edit, manage and execute branch analysis processes.

6. The system according to claim 1, characterized in that: One or more modules available in the process orchestration tool include training a machine learning model and / or applying a machine learning model.

7. The system according to claim 1, characterized in that: The application also includes a software element configured to provide a user interface that allows the user to create and manage studies.

8. The system according to claim 7, characterized in that: The application also includes software elements configured to provide a user interface that allows the users to collaborate and share research.

9. The system according to claim 1, characterized in that: The visualization is a three-dimensional (3D) representation.

10. A non-transitory computer-readable storage medium encoded with instructions executable by one or more processors to provide a space biology informatics application, the space biology informatics application comprising: a) an instrument interface communicatively coupled to one or more laboratory instruments; b) a software element configured to receive data directly or indirectly from the one or more laboratory instruments, wherein the data comprises biological image data and one or more of the following: genomic, proteomic, metabolomic, metagenomic, phenomic, and transcriptomic data; c) a software element configured to provide a process orchestration tool that allows a user to create, edit, manage and execute analytical processes, wherein the process orchestration tool allows a user to link modules together and run them sequentially or in parallel to transform received data; and d) A software element configured to generate a visualization of the received and / or transformed data.

11. The non-transitory computer-readable storage medium according to claim 10, wherein: The one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer, or a combination thereof.

12. The non-transitory computer-readable storage medium of claim 10, wherein: The instrument interface allows the application to perform one or more of the following operations: monitor the one or more laboratory instruments, receive data from the one or more laboratory instruments, and send operating instructions to the one or more laboratory instruments.

13. The non-transitory computer-readable storage medium of claim 10, wherein: The process orchestration tool includes a graphical user interface (GUI), and a user creates and / or edits an analysis process by dragging and dropping modules within the GUI.

14. The non-transitory computer-readable storage medium of claim 10, wherein: The process orchestration tool allows users to create, edit, manage and execute branch analysis processes.

15. The non-transitory computer-readable storage medium of claim 10, wherein: One or more modules available in the process orchestration tool include training a machine learning model and / or applying a machine learning model.

16. The non-transitory computer-readable storage medium of claim 10, wherein: The application also includes a software element configured to provide a user interface that allows the user to create and manage studies.

17. The non-transitory computer-readable storage medium of claim 16, wherein: The application also includes software elements configured to provide a user interface that allows the users to collaborate and share research.

18. The non-transitory computer-readable storage medium of claim 10, wherein: The visualization is a three-dimensional (3D) representation.

19. A computer-implemented method comprising: a) providing an instrument interface at the computer end for communicatively coupling to one or more laboratory instruments; b) receiving data from the one or more laboratory instruments at the instrument interface, wherein the data comprises biological image data and one or more of the following: genomics, proteomics, metabolomics, metagenomics, phenomics, and transcriptomics data; c) providing a process orchestration tool on the computer side that allows a user to create, edit, manage and execute analysis processes, wherein the process orchestration tool allows a user to link modules together and run them sequentially or in parallel to transform received data; and d) Generating, by the computer, a visualization of the received and / or converted data.

20. The method according to claim 19, characterized in that: The one or more laboratory instruments include a DNA sequencer or sequencing platform, a digital spatial analyzer, a spatial molecular imager, an RNA expression analyzer, or a combination thereof.

21. The method according to claim 19, characterized in that: The instrument interface allows the performing of one or more of the following operations: monitoring the one or more laboratory instruments, receiving data from the one or more laboratory instruments, and sending operating instructions to the one or more laboratory instruments.

22. The method according to claim 19, characterized in that: The process orchestration tool includes a graphical user interface (GUI), and a user creates and / or edits an analysis process by dragging and dropping modules within the GUI.

23. The method according to claim 19, characterized in that: The process orchestration tool allows users to create, edit, manage and execute branch analysis processes.

24. The method according to claim 19, characterized in that: One or more modules available in the process orchestration tool include training a machine learning model and / or applying a machine learning model.

25. The method according to claim 19, characterized in that: Also included is providing a user interface that allows the user to create and manage studies.

26. The method according to claim 25, characterized in that: Also included is providing a user interface that allows the users to collaborate and share research.

27. The method according to claim 19, characterized in that: The visualization is a three-dimensional (3D) representation.

Images