Method and system for integrated query of genomic and phenotypic data - Patent Application 20070229633

Abstract

A method 100 for federated searching includes the steps of: (i) providing (110) a federated search system comprising a query hub in communication with a plurality of remote servers, each of the remote servers including phenotype information and genotype information for a plurality of individuals; (ii) receiving (120) a query from a user, the query including a request for phenotype information, genotype information, and one or more attributes stored in the remote servers for each individual that satisfies both the request for phenotype information and the request for genotype information; (iii) distributing (130) the received query to two or more of the plurality of remote servers; (iv) receiving (140) responses to the distributed query from each of two or more of the plurality of remote servers; (v) aggregating (150) the received responses into a single aggregated response including both the phenotype information and the genotype information; and (vi) providing (160) the single aggregated response.

Description

[Technical field]

[0001]

[0001] The present disclosure is generally directed to methods and systems for integrated searching of both phenotypic and genotypic information. [Background technology]

[0002]

[0002] In many legacy medical record systems, whether they use HL7 v2, C-CDA, FHIR or not, the presence of genomics data remains somewhat scarce. This is partly due to lack of clinical need, justification, or cost, or outsourcing of testing to third-party laboratories. However, the advent of precision medicine and scientific advances over the last few years have brought genomics to the forefront. Standards have largely caught up in expressing the results of genomic tests, since these tests are designed to look for specific mutations in specific genes and report a relatively small set of data.

[0003]

[0003] However, for example in oncology and genetic diseases, these tests are nowadays scaling up to interrogate hundreds or thousands of genes. Soon, these tests will routinely search all known (approximately 25,000) coding genes (whole exome sequencing) or the entire genome (whole genome sequencing). In some use cases, mainly oncology, the tests also compare sequencing results from multiple samples. Medical record systems are simply not designed for data at this scale, and separate systems, like those for imaging, must exist for the management of genomic data. Foresighted hospital systems are moving to bespoke systems that store raw genomic data and test results, and a small subset of these data and test results is returned to the medical record system. However, different sites have different solutions that are not interoperable, and it is usually not possible to exploit genomic data for research at scale.

[0004]

[0004] Thus, searching disparate sources for genotypic information, let alone both phenotypic and genotypic information, using only one or a few queries is either impractical or completely impossible. Summary of the Invention [Problem to be solved by the invention]

[0005]

[0005] Therefore, there is a need for methods and systems that allow for rapid and efficient searching of multiple disparate databases for both phenotypic and genotypic information. [Means for solving the problem]

[0006]

[0006] The present disclosure is directed to an inventive method and system for federated search. Various embodiments and implementations herein are directed to a federated search system comprising a query hub in communication with a plurality of remote servers, each of which includes phenotypic and genotypic information for a plurality of individuals. The query hub receives a query from a user, the query including a request for (i) phenotypic information, (ii) genotypic information, and (iii) one or more attributes stored in the remote servers for each individual that satisfies both the request for phenotypic information and the request for genotypic information. The query hub distributes the query to the plurality of remote servers and receives responses to the distributed query from the remote servers. The query hub aggregates the received responses into a single aggregated response including both the phenotypic and genotypic information, and provides the single aggregated response to the user via a user interface of the federated search system.

[0007]

[0007] In general, in one aspect, a method for federated searching is provided, the method including: (i) providing a federated search system including a query hub in communication with a plurality of remote servers, each of the remote servers including phenotypic and genotypic information for a plurality of individuals; (ii) receiving a query from a user at the query hub of the federated search system, the query including a request for phenotypic information, genotypic information, and one or more attributes stored in the remote servers for each individual that satisfies both the request for phenotypic information and the request for genotypic information; (iii) distributing the received query by the query hub to two or more of the plurality of remote servers; (iv) receiving responses to the distributed query by the query hub from each of two or more of the plurality of remote servers; (v) aggregating the received responses into a single aggregated response including both the phenotypic and genotypic information by the query hub; and (vi) providing the single aggregated response via a user interface of the federated search system.

[0008]

[0008] According to one embodiment, the received query includes user authentication, and the received query is distributed to a remote server only if the user authentication has been or will be recognized by the remote server.

[0009]

[0009] According to one embodiment, the step of aggregating the received responses into a single aggregated response including both phenotype information and genotype information further includes de-duplication, filtering, and / or anonymization of one or more of the received responses.

[0010]

[0010] According to one embodiment, the phenotype information for each of a plurality of individuals in the remote server is stored in FHIR format.

[0011] According to one embodiment, the query includes a phenopacket object and a request object.

[0012] According to one embodiment, the query comprises a JSON file that is submitted to the query hub via an API.

[0013]

[0013] According to one embodiment, each of the remote servers is configured to: (i) identify one or more of the plurality of individuals that satisfy a request for phenotypic information in the distributed query; (ii) identify one or more of the plurality of individuals that satisfy a request for genotypic information in the distributed query; (iii) identify one or more of the plurality of individuals that satisfy both the request for phenotypic information and the request for genotypic information; and (iv) generate a response to the distributed query including the identified one or more of the plurality of individuals that satisfy both the request for phenotypic information and the request for genotypic information, as well as one or more requested attributes for each of the identified one or more individuals.

[0014]

[0014] According to one embodiment, the response includes a set of FHIR objects.

[0015]

[0015] Another aspect is a system for federated search, comprising: a plurality of remote servers, each of the remote servers including phenotypic information and genotypic information for a plurality of individuals; a user interface configured to receive a query from a user, the query including a request for (i) phenotypic information, (ii) genotypic information, and (iii) one or more attributes stored in the remote servers for each individual that satisfies both the request for phenotypic information and the request for genotypic information; and a query hub in communication with the plurality of remote servers, configured to (i) receive the query, (ii) distribute the received query to two or more of the plurality of remote servers, (iii) receive responses to the distributed query from each of the two or more of the plurality of remote servers, (iv) aggregate the received responses into a single aggregated response including both the phenotypic information and the genotypic information, and (v) prompt the user interface to provide the single aggregated response.

[0016]

[0016] It should be appreciated that all combinations of the above-described concepts, and further concepts discussed in more detail below, (provided such concepts are not mutually inconsistent) are contemplated as part of the inventive subject matter disclosed herein. In particular, all combinations of claimed subject matter described at the end of this disclosure are contemplated as part of the inventive subject matter disclosed herein.

[0017]

[0017] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.

[0018]

[0018] In the drawings, like reference characters generally refer to the same parts throughout the different views. Also, the drawings are not necessarily to scale, emphasis instead generally being placed upon illustrating the principles of the invention. [Brief description of the drawings]

[0019] [Figure 1] 1 is a flowchart of a method for federated searching according to one embodiment. [Diagram 2]

[0020] 1 is a schematic diagram of a federated search system according to one embodiment. [Diagram 3]

[0021] 1 is a schematic diagram of a portion of a federated search system according to one embodiment. [Figure 4]

[0022] 1 is a schematic diagram of a portion of a federated search system according to one embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0020]

[0023] This disclosure describes various embodiments of a query system and method. More generally, applicants have recognized and appreciated that it would be beneficial to provide a system for more efficiently searching multiple disparate databases for phenotypic and genotypic information. According to one embodiment, a federated search system includes a query hub in communication with multiple remote servers, each of which includes phenotypic and genotypic information for multiple individuals. The query hub receives a query from a user, the query including a request for (i) phenotypic information, (ii) genotypic information, and (iii) one or more attributes stored in the remote servers for each individual that satisfies both the request for phenotypic information and the request for genotypic information. The query hub distributes the query to the multiple remote servers and receives responses to the distributed query from the remote servers. The query hub aggregates the received responses into a single aggregated response including both the phenotypic and genotypic information, and provides the single aggregated response to the user via a user interface of the federated search system.

[0021]

[0024] According to one embodiment, the methods and systems described or otherwise contemplated herein provide a framework that can accommodate federated queries across multiple systems. Although query federation may hide data sources from users, thus making re-identification of individual samples more difficult, query federation may also be leveraged to bring algorithms to the data to further protect patient privacy and security and enable compliance with various international regulations (e.g., the European Union's General Data Protection Regulation, or GDPR). Each data host system in the federation paradigm leverages an architecture that promotes interoperability with the GA4GH and HL7 standards, e.g., to support the sharing of genotype and phenotype data to their respective strengths.

[0022]

[0025] According to one embodiment, the methods and systems described or otherwise contemplated herein provide a unified architecture for genomic data systems and procedures for querying their contents, as well as the contents of research-consented electronic medical records, via a robust, interoperable clinical exchange standard such as FHIR. This structure solves interoperability issues between systems, allows a single query to be distributed / integrated across multiple systems, and scales the capabilities of even the most technologically advanced health systems to incorporate large-scale genomic and phenotypic data queries for discovery processes.

[0023]

[0026] The Global Alliance for Genomics and Health (GA4GH) is developing standards to enable widespread access to genomic and health-related data on tens of millions of individuals. This access, which will help advance precision medicine, depends on the creation of tools that leverage these interoperable standards. One key aspect of this goal is that clinical records contain genotype and phenotype information that can help support a continuous learning system, one that provides care to individual patients, and that, with open and trusted consent and credentials, can share data to drive research and further improve that care.

[0024]

[0027] One standard from GA4GH is the Beacon network. This standard enables discovery of research-consented [and] sensitive human genetic data stored in databases. Beacon is essentially a standard RESTful API to query genomic databases with questions such as "Do you have records with allele A at position B?" and receive a [yes, no] or a more complex response based on the data available in other situations. However, Beacon so far does not support querying specific records, details of those records, or the ability to supplement queries with additional patient-level information such as phenotype. In this sense, Beacon does not fully support the ideas described above.

[0025]

[0028] FHIR (Fast Healthcare Interoperability Resources) is an HL7 standard framework created to support real-world clinical and operational scenarios across a wide variety of contexts: mobile phone apps, cloud communications, EHR-based data sharing, server communications in large-scale healthcare providers, and more. In essence, FHIR is a next-generation RESTful exchange approach to clinical data interoperability and is key to the GA4GH initiative paradigm. FHIR provides interoperability between health systems and may support a wide range of standard operations, including operations that probe patient records for phenotypes. FHIR can also express genomic data and genomic data queries, but in practice much of the genomic data will necessarily be stored in other systems (such as Beacons). Thus, FHIR may be a key component of the methods and systems described or otherwise envisioned herein.

[0026]

[0029] According to one embodiment, the methods and systems described or otherwise contemplated herein provide numerous advantages over the prior art. By providing an integrated query system that queries multiple different remote servers for both phenotypic and genotypic information, it allows for more efficient retrieval of information. This information can be important for patient care, research, and many other applications. Having the ability to not only find this information, but find it quickly and efficiently, allows for broader uses of the data, improving research and care outcomes and potentially even saving lives.

[0027]

[0030] The embodiments and implementations disclosed or otherwise contemplated herein may be utilized with any system, including, but not limited to, medical and research databases or systems, among other systems. For example, one application of the embodiments and implementations herein is to improve analytical systems, such as, for example, Philips IntelliSpace® products (manufactured by Koninklijke Philips, NV), among other products. However, the disclosure is not limited to those devices or systems, and thus the disclosures and embodiments disclosed herein may encompass any device or system that utilizes phenotypic and / or genotypic queries.

[0028]

[0031] Referring to FIG. 1, in one embodiment, a flow chart of a method 100 for federated searching using a federated search system. It is understood that the method described in connection with the figure is provided by way of example only and does not limit the scope of the present disclosure. The federated search system may be any of the systems described or otherwise contemplated herein. The federated search system may be a single system or multiple different systems.

[0029]

[0032] At step 110 of the method, a federated search system 200 is provided that includes a query hub in communication with a plurality of remote servers. Referring to an embodiment of the federated search system 200 depicted in FIG. 2, for example, the system includes one or more query hubs 202, which include a processor 220, a memory 230, a user interface 240, a communication interface 250, and a storage 260 interconnected via one or more system buses 212. The system 200 also includes a plurality of remote servers 270 connected to the query hub 202 via the communication interface 250 via wired and / or wireless communication. It will be understood that FIG. 2 represents an abstraction in some respects, and that the actual organization of the components of the system 200 is different and more complex than illustrated. Additionally, the federated search system 200 may be any of the systems described or otherwise contemplated herein. Other elements and components of the system 200 are disclosed and / or contemplated elsewhere herein.

[0030]

[0033] 3, in one embodiment, a federated search system 200 includes a query hub 202 in communication with multiple remote servers 270. Each remote server includes a query handler and phenotype and genotype information for multiple individuals. According to one embodiment, a user submits a query to a query hub 202 that is distributed across any number of remote servers 270. The remote servers retrieve and send the results to the query hub, which performs various de-duplication, filtering, aggregation, and anonymization techniques before returning the final data set to the user.

[0031]

[0034] Referring to FIG. 4, in one embodiment, one of multiple remote servers 270 of the integration network. According to one embodiment, the system supports the incorporation of VCF files (and by extension raw genomic data such as FASTQ or BAM) and FHIR data into the database management system. Each remote server receives simple and complex queries from the query hub. The server contains logic to retrieve clinical records and search for genomic attributes in those records as well as in the genomic information storage system. Clinical and genomic data is dynamically and automatically imported. The query handler is responsible for balancing queries among the service containers in the remote servers.

[0032]

[0035] At step 120 of the method, the query hub receives a query from a user. The query may be provided via a user interface of the integrated query system. The user interface may be a user interface associated with the query hub or a user interface in wired and / or wireless communication with the query hub. For example, the user interacts with the query hub remotely, such as through remote access, cloud access, or any other remote access. Thus, the user may be at a clinical site, a laboratory, or any other location and can submit a query via a locally or remotely accessed user interface. Alternatively, the user accesses the system at a query hub location, such as a centralized query hub location.

[0033]

[0036] The query includes, for example, a request from a user for phenotypic information, genotypic information, and one or more attributes for each individual that satisfy both the request for phenotypic information and the request for genotypic information. For example, a response to the query will identify one or more people, e.g., records for one or more people from one or more of the remote servers that satisfy both the phenotypic and genotypic requirements in the query. Once identified, the system will provide information for the requested one or more attributes for each of those identified people. The attributes may be any information about the person, such as demographics, phenotype, genotype, diagnosis, treatment information, and / or any other information that may be associated with an individual at the remote server.

[0034]

[0037] According to one embodiment, a query is created by a user, such as a clinician or researcher. A query may consist of a phenopacket object combined with a request object, which may be submitted directly to the query hub, or optionally a user interface is provided for generating the phenopacket and request object in-place. According to one embodiment, a phenopacket is a standard from GA4GH, an anonymous description of an individual or biosample with a gene of interest and / or potential diagnostic. Although a phenopacket can support a variety of use cases, according to one use, a phenopacket is a standard representation of genomic and phenotypic data for an individual or sample.

[0035]

[0038] According to one embodiment, the query request contains basic information about the patient matching criteria and the requested information for matching records. These queries, defined in a standard JSON file generated by the user, can be submitted to the query hub through a unified API. This JSON itself leverages existing standard representations for the matching criteria (clinical and genomic data), such as phenopackets, as well as any standard representations that specify the requested information. The connection between the query hub and the remote server is secured and authorized. The source of each database in the remote server is VCF files (although extensions can be made to incorporate other genomic data formats, such as FASTQ, SAM, BAM, or downstream formats that represent gene expression and other data), and patient information in FHIR format. Every module is containerized, making it easier to replace or scale up.

[0036]

[0039] According to one embodiment, the content of the phenopacket is constrained to the phenopacket specification to ensure interoperability, although some fields in the specification are likely to be unused on the query side of the system (given that the general goal is to build cohorts, fields such as "Subject" and "Biosample" are only relevant when returning results). However, to maximize flexibility for tracking queries, and assuming the system has proper consent and credentialing procedures, these fields remain optional. The phenopacket typically contains an ID (a reference to the phenopacket itself), a phenotypic feature, a biosample, a gene, a variant, and a disease. The content of each field (some of which are objects themselves) is similarly constrained to the phenopacket specification.

[0037]

[0040] While the phenopacket describes the cohort the user is looking for, the user must specify what data they want from that cohort. The data the user wants to retrieve is conditional and limited to data the user has access to and that has been consented to by the patient for the user's intended purpose. The request object itself generally applies to the clinical data the user wants to retrieve based on the membership of the desired cohort. The request object conforms to the FHIR search object in order to interoperate with where phenotypic data is stored that can be created in or with the FHIR environment.

[0038]

[0041] Below is an example of a query to a FHIR server for all FHIR resources with a particular condition (by tag of 12345): Implementations of the invention will typically ensure that any requested data complies with user credentials and patient consent prior to delivery to the query server. GET[base] / Condition?_tag=http: / / acme.org / codes|12345

[0039]

[0042] Thus, according to one embodiment, a user creates a JSON file containing a phenopacket object and a request object and sends the request to the query hub through a unified URL. Authorization is controlled by adding a token to the header of each request or through other authentication and access control mechanisms. One such other authentication mechanism may be to leverage API requests to separate services, for example, GA4GH Data Use & Researcher Identities.

[0040]

[0043] In step 130 of the method, the query hub distributes the received query to at least some, and possibly all, of the multiple remote servers. There may be a preliminary check in which the query hub determines to which of the multiple remote servers to send the query. For example, according to one embodiment, the received query may include a user authentication, and the received query is distributed to a remote server only if the user authentication is recognized or will be recognized by the remote server. In this way, the user needs authorization to search the remote servers.

[0041]

[0044] According to one embodiment, each remote server receives a GET request (POST method is not supported) from the query hub. These requests contain information about the type of patients to find (defined in the pheno packet object) and the data to extract from those patients. The phenotype information (from the pheno packet) is first used to identify patients in the FHIR server that match the user description. This is done, facilitated by a FHIR GET request, by searching various resource types (Condition, Observation, DiagnosticReport, etc.) in the FHIR server for matching attributes. In tandem, the genotype information (also from the pheno packet) is used to query the Beacon server. The matched records are mapped to patients in the FHIR server and an intersection is performed to retrieve patient records that match both the phenotype and genotype attributes in the pheno packet. The request object is then used together with the resulting patient records (i.e., resource IDs) to generate another FHIR GET request to retrieve the requested attributes for each patient. These attributes may be quantitative (eg, age) or categorical in nature (eg, disease, treatment administered, outcome) and are then returned to the query hub.

[0042]

[0045] In response, at method step 132, the remote server identifies one or more of the plurality of individuals, whose information is stored at the server, that satisfy the request for phenotype information in the distributed query. Similarly, at method step 134, the remote server identifies one or more of the plurality of individuals that satisfy the request for genotype information in the distributed query. Notably, steps 132 and 134 may be performed sequentially in any order or simultaneously.

[0043]

[0046] In method step 136, the remote server identifies one or more individuals of the plurality of individuals who satisfy both the request for phenotypic information and the request for genotypic information. For example, the remote server may identify 50 people who satisfy the phenotypic requirement in the query and 100 people who satisfy the genotypic requirement in the query. The remote server will then find the intersection between the 50 people and the 100 people, identifying a total of 10 people who satisfy both the phenotypic requirement in the query and the genotypic requirement in the query.

[0044]

[0047] In method step 138, the remote server generates a response to the distributed query, which may then be returned to the query hub. The response includes information about one or more identified individuals of the plurality of individuals that satisfy both the request for phenotypic information and the request for genotypic information. The response also includes information about one or more requested attributes from the query for each of the identified one or more individuals of the plurality of individuals that satisfy both the request for phenotypic information and the request for genotypic information.

[0045]

[0048] According to one embodiment, to support a more secure paradigm, the remote server chooses to only respond to requests that contain untrained models. In these setups, the user provides a phenopacket object and a request object along with a model object (an untrained learning model). The query hub will distribute this package repeatedly to remote servers configured to accept the model object. That is, the package is sent to a first remote server, which returns a trained model, the same package is sent with the trained model to a second remote server, which returns a further trained model, and so on. Due to the nature of the federated querying system, only a few learning models, i.e. incremental learning models, are preferred. These models can be trained on blocks of data one after the other, and thus can be trained across a series of remote servers.

[0046]

[0049] In addition to delivering the model, the user will want to specify how to handle (hidden) data preprocessing (perform normalization, how to handle missing values), and therefore the remote server will need a machine learning framework to handle the model and other requirements.

[0047]

[0050] All pre-processing functions (such as data cleaning, feature extraction, etc.) may be encapsulated in a single container that collects data from other containers in remote servers. Models and data configurations may be described in platform metadata or uploaded by users in JSON format to the query hub. All remote server results are routed through query handlers in the container and filtered by the query hub.

[0048]

[0051] At step 140 of the method, the query hub receives responses to the distributed query from each of the multiple remote servers. The responses may include a fully responsive answer that includes all requested information, or an indication that the server does not have information responsive to the request. The responses may also include something in between these two responses, such as a partially responsive answer with only some of the requested information. The received responses may be used immediately or may be stored for future processing.

[0049]

[0052] At method step 150, the query hub aggregates the received responses into a single aggregated response, the aggregated response including both phenotypic and genotypic information and the responded attribute information. According to one embodiment, aggregating the received responses into a single aggregated response including both phenotypic and genotypic information further comprises de-duplication, filtering, and / or anonymization of one or more of the received responses.

[0050]

[0053] According to one embodiment, results from each remote server are collected as a set of FHIR objects (resources) and returned from each host to the query hub. The primary mission of the query hub is to aggregate the total set of results from each host into a single result object. Secondary missions include any number of important post-processing events, including identification and subsequent removal or merging of duplicate records, or further anonymization techniques (such as k-anonymity). The result object is created and processed by the query hub before it is finally sent to the user.

[0051]

[0054] At step 160 of the method, the federated search system provides a single aggregated response to the user via a user interface of the system. The response includes any information returned in response to the query, including attribute information, personal information, phenotypic information, genotypic information, etc. The single aggregated response may be provided via the user interface using any method for communicating or displaying information, and the user interface may be any device, interface, or mechanism for providing communicated or displayed information. For example, the single aggregated response to the user's query is communicated to another device by wired and / or wireless communication. For example, the system communicates the information to a mobile phone, a computer, a laptop, a wearable device, and / or any other device configured to enable display and / or other communication of information. The user interface may be any device or system that enables communication and / or reception of information, including a display, a mouse, and / or a keyboard for receiving user commands.

[0052]

[0055] Referring to Figure 2, there is shown a schematic diagram of an integrated query system 200. System 200 may be any of the systems described or otherwise contemplated herein and may include any of the components described or otherwise contemplated herein. It will be appreciated that Figure 2 represents an abstraction in some respects and that the actual organization of the components of system 200 may be different and more complex than illustrated.

[0053]

[0056] According to one embodiment, the system 200 includes multiple remote servers 270, which may be any of the remote servers described or otherwise contemplated herein. The remote servers may include different databases, each of which may include phenotypic and genotypic information about individuals, as well as other attributes about the individuals.

[0054]

[0057] According to one embodiment, the system 200 comprises a query hub 202. According to one embodiment, the query hub 202 comprises a processor 220 capable of executing instructions stored in the memory 230 or storage 260, or otherwise processing data, for example to perform one or more steps of a method. The processor 220 is formed from one or many modules. The processor 220 takes any suitable form, including, but not limited to, a microprocessor, a microcontroller, multiple microcontrollers, a circuit, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a single processor, or multiple processors.

[0055]

[0058] The memory 230 may take any suitable form, including non-volatile memory and / or RAM. The memory 230 includes various memories, such as, for example, L1, L2, or L3 cache, or system memory. Thus, the memory 230 may include static random access memory (SRAM), dynamic RAM (DRAM), flash memory, read-only memory (ROM), or other similar memory devices. The memory may store, among other things, an operating system. The RAM is used by the processor for temporary storage of data. According to one embodiment, the operating system contains code that, when executed by the processor, controls the operation of one or more components of the query hub 202. In embodiments in which the processor implements one or more of the functions described herein in hardware, it will be apparent that software described as equivalent to such functionality in other embodiments is omitted.

[0056]

[0059] User interface 240 includes one or more devices for enabling communication with a user. The user interface may be any device or system that enables the transmission and / or reception of information, including a display, a mouse, and / or a keyboard for receiving user commands. In some embodiments, user interface 240 includes a command line interface or a graphical user interface that is presented to a remote terminal via communication interface 250. The user interface may be co-located with one or more other components of the system or may be remote from the system and communicate via a wired and / or wireless communication network.

[0057]

[0060] The communication interface 250 includes one or more devices for enabling communication with other hardware devices. For example, the communication interface 250 includes a network interface card (NIC) configured to communicate according to an Ethernet protocol. Additionally, the communication interface 250 implements a TCP / IP stack for communicating according to a TCP / IP protocol. Various alternative or additional hardware or configurations for the communication interface 250 will be apparent.

[0058]

[0061] Storage 260 includes one or more machine-readable storage media, such as read-only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, or similar storage media. In various embodiments, storage 260 stores instructions for execution by processor 220 or data on which processor 220 operates. For example, storage 260 stores operating system 261 for controlling various operations of system 200.

[0059]

[0062] It will be appreciated that the various information described as being stored in storage 260 may additionally or alternatively be stored in memory 230. In this regard, memory 230 may also be considered a storage device, and storage 260 may be considered a memory. Various other arrangements will be apparent. Furthermore, both memory 230 and storage 260 may be considered non-transitory machine-readable media. As used herein, the term non-transitory will be understood to include all forms of storage, including both volatile and non-volatile memory, but excluding transient signals.

[0060]

[0063] Although system 200 and / or query hub 202 are shown each including one of the described components, in various embodiments, various components are duplicated. For example, processor 220 includes multiple microprocessors configured to independently execute the methods described herein or to perform steps or subroutines of the methods described herein, such that the multiple processors cooperate to achieve the functionality described herein. Furthermore, when one or more components of system 200 and / or query hub 202 are implemented in a cloud computing system, the various hardware components reside in separate physical systems. For example, processor 220 includes a first processor in a first server and a second processor in a second server. Many other variations and configurations are possible.

[0061]

[0064] According to one embodiment, storage 260 of query hub 202 stores one or more algorithms, modules, and / or instructions for performing one or more functions or steps of methods described or otherwise contemplated herein. For example, the system includes distribution instructions 262, aggregation instructions 263, and / or reporting instructions 264, among other instructions or data, as well as many other possible instructions and / or data.

[0062]

[0065] According to one embodiment, as described herein or otherwise contemplated, distribution instructions 262 instruct the system to receive a query from a user interface and / or distribute the query to multiple distributed remote servers. There may be a preliminary check in which the query hub determines to which of multiple remote servers to send the query. For example, according to one embodiment, the received query may include a user authentication, and the received query is distributed to a remote server only if the user authentication is recognized or will be recognized by the remote server. In this manner, the user requires authorization to search the remote server.

[0063]

[0066] According to one embodiment, as described herein or otherwise contemplated, the aggregation instructions 263 instruct the system to receive responses from multiple remote servers and / or to aggregate the received responses into a single aggregated response that includes both phenotypic and genotypic information and the responded attribute information. According to one embodiment, aggregating the received responses into a single aggregated response that includes both phenotypic and genotypic information further includes de-duplication, filtering, and / or anonymization of one or more of the received responses.

[0064]

[0067] According to one embodiment, the reporting instructions 264 instruct the system to generate and provide a report or visualization to the user via the user interface 240 of the integrated search system 200, as described herein or otherwise contemplated. The response includes any information returned in response to the query, including attribute information, personal information, phenotypic information, genotypic information, and others. The single aggregate response may be provided via the user interface using any method for communicating or displaying information, and the user interface may be any device, interface, or mechanism for providing communicated or displayed information. For example, the single aggregate response to the user's query is communicated to another device by wired and / or wireless communication. For example, the system communicates the information to a mobile phone, computer, laptop, wearable device, and / or any other device configured to enable display and / or other communication of information. The user interface may be any device or system that enables communication and / or reception of information, including a display, mouse, and / or keyboard for receiving user commands.

[0065]

[0068] Working Example

[0069] The following are non-limiting examples of implementations of the federated search systems and methods described or otherwise contemplated herein.

[0066]

[0070] According to the first embodiment, all containers may be configured and invoked in the "docker-compose.yml" file. In the remote server, VCF and FHIR files are imported and ports are opened to accept connections from the query hub. The query hub may be located on a separate host with the appropriate IP address of the remote server. Permissions on the shared folder should be carefully configured.

[0067]

[0071] According to a second example, a researcher studying breast cancer demographics wants to test a hypothesis about breast cancer survival rates across different age groups. The researcher has valid credentials to access numerous data servers in an integrated research network. The researcher collects the phenotypes (abnormality = "breast cancer") for which they want to select patients, and packages the phenotypes along with a request object (specifying age, ethnicity, and gender) into a phenopacket into a single JSON. Additionally, they provide an untrained incremental learning model called SGDRegressor (a linear regression model), as well as data preprocessing instructions (e.g., replace missing numeric values ​​with the average of all values ​​of that type, and replace missing categorical values ​​with the mode of that type using one-hot encoding for categorical features). They submit these inputs to a query hub, where these instructions are incrementally fulfilled. The query hub will skip any remote servers that do not accept the researcher's credentials. Finally, once all remote servers have responded (with or without the requested model), the trained model is returned to the user for further testing.

[0068]

[0072] According to a third example, a clinician has a patient with an undiagnosed abnormality and wants to leverage the integrated research network to find similar patients with a clinical diagnosis. The clinician interacts with the query hub via a web application where he enters the patient's phenotype and the requested diagnostic attributes. The clinician submits his query and two unique diagnoses are returned to the clinician. Based on further review of the medical literature for each, the clinician has a high degree of confidence that the patient has one of the two diseases and arranges for an appropriate treatment plan.

[0069]

[0073] According to a fourth example, a pharmaceutical company is working on developing a drug to treat a particular type of patient. However, it has recently been discovered that the drug may be ineffective and dangerous for patients with a particular genotype. To determine if the eligible patient population is still large enough to justify the high development costs, the pharmaceutical company needs to evaluate the frequency of occurrence of these patients with that genotype. The technical division submits a query containing all of the eligibility criteria in the phenopacket object and a request object containing the genotype (specific gene variant). The query hub distributes the query and returns a binary result for all patients matching the eligibility criteria. Based on further analysis, the pharmaceutical company discovers that an unacceptable percentage of patients have the stated genotype and decides to halt development of the drug.

[0070]

[0074] Searching a genomic dataset for genomic information, much less searching multiple genomic datasets on one of the remote servers of an integrated search system, involves millions or billions of calculations that are beyond the human mind's ability to perform, even with a pen and pencil. In fact, a single genomic dataset contains millions of pieces of information. For example, next-generation DNA sequencing data contains hundreds of millions or even billions of reads.

[0071]

[0075] Moreover, the methods described herein greatly improve the speed and functionality of a distributed search system. For example, by implementing the methods described herein, a federated search system is able to search heterogeneous databases faster and more efficiently than prior art systems. Prior art systems are unable to provide this functionality and are therefore inferior systems. Thus, the methods described herein greatly improve the speed and functionality of a search system.

[0072]

[0076] As defined and used herein, all definitions should be understood to supersede dictionary definitions, definitions in documents incorporated by reference, and / or ordinary meanings of the defined words.

[0073]

[0077] As used in the present specification and claims, the singular terms "a," "an," and "the" should be understood to mean "at least one" unless expressly indicated otherwise.

[0074]

[0078] As used herein and in the claims, the phrase "and / or" should be understood to mean "either or both" of the elements so conjointly connected, i.e., elements that are conjunctive in some cases and disjunctive in other cases. Multiple elements listed with "and / or" should be taken in the same manner, i.e., "one or more" of the elements so conjointly connected. Other elements may optionally be present other than the elements specifically identified by the "and / or" clause, whether related or unrelated to those elements specifically identified.

[0075]

[0079] When used in the text and claims of this specification, "or" should be understood to have the same meaning as "and / or" defined above. For example, when separating items in a list, "or" or "and / or" is interpreted as inclusive, i.e., including at least one, but also including two or more of an element or list of elements, and optionally, additional unlisted items. Only words clearly indicating incompatibility, such as "only one of," or "exactly one of," or "consisting of," when used in the claims, will refer to the inclusion of exactly one element of an element or list of elements. In general, when used in this specification, the word "or" is interpreted as indicating exclusive alternatives (i.e., one or the other, but not both) only when preceded by an exclusive word, such as "either," "one of," "only one of," or "exactly one of."

[0076]

[0080] As used herein and in the claims, the phrase "at least one" in reference to a list of one or more elements should be understood to mean at least one element selected from any one or more of the elements in the list of elements, but not necessarily including at least one of each and every element specifically listed in the list of elements, and not excluding any combination of elements in the list of elements. This definition also allows for the optional presence of elements other than those specifically identified in the list of elements to which the phrase "at least one" refers, whether related or unrelated to those elements specifically identified.

[0077]

[0081] It should also be understood that in any method claimed herein having two or more steps or actions, unless expressly indicated otherwise, the order of the method steps or actions is not necessarily limited to the order in which the method steps or actions are described.

[0078]

[0082] In the claims, as well as in the above specification, all transitional phrases such as "comprises," "includes," "carries," "has," "contains," "accompanying," "holds," "consisting of," and the like, are to be understood as open-ended, i.e., meaning inclusive but not limited to. As set forth in the United States Patent Office Manual of Patent Examining Procedures, Section 2111.03, only the transitional phrases "consisting of" and "consisting essentially of" are closed or semi-closed transitional phrases, respectively.

[0079]

[0083] Although several inventive embodiments have been described and illustrated herein, those skilled in the art will readily envision a variety of other means and / or structures for performing the functions and / or obtaining one or more of the results and / or advantages described herein. Each such variation and / or modification is deemed to be within the scope of the inventive embodiments described herein. More generally, those skilled in the art will readily appreciate that all parameters, dimensions, materials, and configurations described herein are meant to be exemplary, and that the actual parameters, dimensions, materials, and / or configurations will depend on the specific application in which the inventive teachings are used. Those skilled in the art will recognize, or be able to ascertain, using no more than routine experimentation, many equivalents to the specifically inventive embodiments described herein. It should therefore be understood that the above-described embodiments are presented by way of example only, and that within the scope of the appended claims and equivalents thereof, the inventive embodiments may be practiced otherwise than as specifically described and claimed. Inventive embodiments of the present disclosure are directed to each individual feature, system, article, material, kit, and / or method described herein. In addition, any combination of two or more such features, systems, articles, materials, kits, and / or methods is included within the inventive scope of the present disclosure, provided that such features, systems, articles, materials, kits, and / or methods are not mutually inconsistent.

Claims

1. providing a federated search system comprising a query hub in communication with a plurality of remote servers, each of the remote servers containing phenotype and genotype information for a plurality of individuals; receiving a query from a user at the query hub of the federated search system, the query comprising: (i) Phenotypic information; (ii) genotype information, and (iii) one or more attributes stored on the remote server for each individual who satisfies both the request for phenotypic information and the request for genotypic information. receiving a request for distributing, by the query hub, the received queries to two or more of the plurality of remote servers; receiving, by the query hub, responses to the distributed queries from each of the two or more of the plurality of remote servers; aggregating, by the query hub, the received responses into a single aggregated response that includes both phenotypic and genotypic information; providing the single aggregated response via a user interface of the federated search system; 13. A method for integrated searching comprising:

2. 2. The method of claim 1, wherein the received query includes a user authentication, and the received query is distributed to a remote server only if the user authentication has been or will be recognized by the remote server.

3. 2. The method of claim 1 , wherein aggregating the received responses into a single aggregated response including both phenotypic and genotypic information further comprises de-duplication, filtering, and / or anonymization of one or more of the received responses.

4. 2. The method of claim 1, wherein the phenotype information for each of the plurality of individuals in the remote server is stored in FHIR format.

5. The method of claim 1 , wherein the query includes a phenopacket object and a request object.

6. The method of claim 5 , wherein the query comprises a JSON file that is submitted to the query hub via an API.

7. Each of the remote servers: identifying one or more of the plurality of individuals that satisfy the request for phenotype information in the distributed query; identifying one or more of the plurality of individuals that satisfy the request for genotype information in the distributed query; identifying one or more individuals of said plurality of individuals that satisfy both said request for phenotypic information and said request for genotypic information; generating a response to the distributed query that includes the identified one or more individuals of the plurality of individuals that satisfy both the request for phenotypic information and the request for genotypic information, and the one or more requested attributes for each of the identified one or more individuals. The method of claim 1.

8. The method of claim 7 , wherein the response includes a set of FHIR objects.

9. a plurality of remote servers, each of the remote servers containing phenotypic and genotypic information for a plurality of individuals; A user interface for receiving a query from a user, the query comprising: (i) Phenotypic information; (ii) genotype information, and (iii) one or more attributes stored on the remote server for each individual who satisfies both the request for phenotypic information and the request for genotypic information. a user interface including a request for a query hub in communication with the plurality of remote servers, the query hub (i) receiving the query, (ii) distributing the received query to two or more of the plurality of remote servers, (iii) receiving responses to the distributed query from each of the two or more of the plurality of remote servers, (iv) aggregating the received responses into a single aggregated response that includes both phenotypic and genotypic information, and (v) prompting the user interface to provide the single aggregated response; A system for integrated search comprising:

10. 10. The system of claim 9, wherein the received query includes a user authentication, and the received query is distributed to a remote server only if the user authentication has been or will be recognized by the remote server.

11. 10. The system of claim 9, wherein aggregating the received responses into a single aggregated response including both phenotypic and genotypic information further comprises de-duplication, filtering, and / or anonymization of one or more of the received responses.

12. 10. The system of claim 9, wherein the phenotype information for each of the plurality of individuals in the remote server is stored in FHIR format.

13. The system of claim 9 , wherein the query includes a phenopacket object and a request object.

14. The system of claim 13 , wherein the query comprises a JSON file that is submitted to the query hub via an API.

15. Each of the remote servers: identifying one or more of the plurality of individuals that satisfy the request for phenotype information in the distributed query; identifying one or more of the plurality of individuals that satisfy the request for genotype information in the distributed query; identifying one or more individuals of said plurality of individuals that satisfy both said request for phenotypic information and said request for genotypic information; generating a response to the distributed query that includes the identified one or more individuals of the plurality of individuals that satisfy both the request for phenotypic information and the request for genotypic information, and the one or more requested attributes for each of the identified one or more individuals. The system of claim 9.

Images