Communication generation using sparse indicators and sensor data
Techniques, systems, and products for analyzing sparse indicators and sensor data and generating communications are disclosed. The sensors may be associated with or incorporated into devices that may automatically relay sensor data for use in analyses and communication generation.
1. A system for generating communications based on variant information and sensor data, comprising:
one or more hardware processors; and
a non-transitory computer readable storage medium in data communication with the one or more hardware processors, the non-transitory computer readable storage medium comprising instructions that, when executed by the one or more hardware processors, cause the one or more hardware processors to perform operations including:
obtaining, at the one or more hardware processors, genetic-variant data corresponding to one or more variants associated with a client, wherein each of the one or more variants corresponds to an instance of one or more bases positioned at one or more first positions in a first genetic sequence differ from corresponding one or more bases positioned in a reference genetic sequence, wherein the first genetic sequence is a genetic sequence of the client;
obtaining sensor data providing an indication of past physical activity, sleep or physiological metrics associated with the client;
processing the genetic-variant data and the sensor data to generate a disease-risk metric corresponding to a predicted risk of the client developing a particular disease;
generating a communication indicative of the disease-risk metric; and
transmitting the communication to a remote device.
2. The system for generating communications based on variant information and sensor data as recited in claim 1 , wherein the sensor data includes data from an accelerometer and provides an indication of past physical activity of the client.
3. The system for generating communications based on variant information and sensor data as recited in claim 1 , wherein the sensor data indicates one or more estimated sleep durations corresponding to the client.
4. The system for generating communications based on variant information and sensor data as recited in claim 1 , wherein the sensor data is indicative of a physiological measurement.
5. The system for generating communications based on variant information and sensor data as recited in claim 1 , wherein the operations further include:
determining target sensor data for the client predicted to correspond to a different disease risk relative to the predicted risk corresponding to the disease-risk metric; and
outputting a specification of the target sensor data.
6. The system for generating communications based on variant information and sensor data as recited in claim 1 , wherein the disease-risk metric corresponds to a predicted risk of the client developing cancer.
7. The system for generating communications based on variant information and sensor data as recited in claim 1 , wherein the remote device includes a device of the client, and wherein the sensor data was generated by one or more sensors of the remote device.
8. A computer-implemented method comprising:
obtaining genetic-variant data corresponding to one or more variants associated with a client, wherein each of the one or more variants corresponds to an instance of one or more bases positioned at one or more first positions in a first genetic sequence differ from corresponding one or more bases positioned in a reference genetic sequence, wherein the first genetic sequence is a genetic sequence of the client;
obtaining sensor data providing an indication of past physical activity, sleep or physiological metrics associated with the client;
processing the genetic-variant data and the sensor data to generate a disease-risk metric corresponding to a predicted risk of the client developing a particular disease;
generating a communication indicative of the disease-risk metric; and
transmitting the communication to a remote device.
9. The computer-implemented method as recited in claim 8 , wherein the sensor data includes data from an accelerometer and provides an indication of past physical activity of the client.
10. The computer-implemented method as recited in claim 8 , wherein the sensor data indicates one or more estimated sleep durations corresponding to the client.
11. The computer-implemented method as recited in claim 8 , wherein the sensor data is indicative of a physiological measurement.
12. The computer-implemented method as recited in claim 8 , further comprising:
determining target sensor data for the client predicted to correspond to a different disease risk relative to the predicted risk corresponding to the disease-risk metric; and
outputting a specification of the target sensor data.
13. The computer-implemented method as recited in claim 8 , wherein the disease-risk metric corresponds to a predicted risk of the client developing cancer.
14. The computer-implemented method as recited in claim 8 , wherein the remote device includes a device of the client, and wherein the sensor data was generated by one or more sensors of the remote device.
15. A non-transitory computer readable storage medium for generating communications based on variant information and sensor data, the non-transitory computer readable storage medium comprising instructions that, when executed by one or more hardware processors, cause the one or more hardware processors to perform operations including:
obtaining genetic-variant data corresponding to one or more variants associated with a client, wherein each of the one or more variants corresponds to an instance of one or more bases positioned at one or more first positions in a first genetic sequence differ from corresponding one or more bases positioned in a reference genetic sequence, wherein the first genetic sequence is a genetic sequence of the client;
obtaining sensor data providing an indication of past physical activity, sleep or physiological metrics associated with the client;
processing the genetic-variant data and the sensor data to generate a disease-risk metric corresponding to a predicted risk of the client developing a particular disease;
generating a communication indicative of the disease-risk metric; and
transmitting the communication to a remote device.
16. The non-transitory computer readable storage medium as recited in claim 15 , wherein the operations further include:
determining target sensor data for the client predicted to correspond to a different disease risk relative to the predicted risk corresponding to the disease-risk metric; and
outputting a specification of the target sensor data.
17. The non-transitory computer readable storage medium as recited in claim 15 , wherein the disease-risk metric corresponds to a predicted risk of the client developing cancer.
18. The non-transitory computer readable storage medium as recited in claim 15 , wherein the remote device includes a device of the client, and wherein the sensor data was generated by one or more sensors of the remote device.
19. The non-transitory computer readable storage medium as recited in claim 15 , wherein the operations further include:
determining, at the one or more hardware processors, that the first genetic sequence includes the one or more variants;
accessing a work flow for assigning variants to categories, wherein the work flow includes a plurality of stages organized according to a hierarchical structure, and wherein a trajectory through the work flow is determined based on successive results generated for one or more of the plurality of stages;
for each variant of the one or more variants, performing a work flow iteration by:
iteratively performing, at the one or more hardware processors, an automated processing in accordance with each of one or more stages of the plurality of stages according to the work flow based on at least one of:
a position associated with the variant;
the one or more bases associated with the variant; and
a result of a previous stage;
wherein a result of the stage is generated at least partly in response to the automated processing, and wherein a next stage is determined based on the result of the stage;
wherein performing an automated processing in accordance with a stage of the one or more stages includes:
performing, at the one or more hardware processors, a look-up function using an identifier of the variant to determine whether stored data indicates that the variant is to be assigned to a specific category of a plurality of categories; and
generating the result of the iterative performance of the automated processing that identifies the specific category when the stored data indicates that the variant is to be assigned to the specific category; and
assigning the variant to a category of the plurality of categories based on results of the iterative performance of the automated processing;
determining whether a number of variants assigned to a particular category of the plurality of categories exceeds a predefined threshold; and
generating a second communication indicative of whether a number of variants assigned to the particular category exceeds the predefined threshold.
20. The non-transitory computer readable storage medium as recited in claim 15 , wherein the operations further include:
receiving, using the one or more hardware processors, requests from a plurality of client devices for assessing genetic risks associated with a first medical condition, wherein the plurality of client devices are respectively associated with a plurality of clients;
determining genetic information for each of the plurality of clients, wherein genetic information for a client includes sequence information for a plurality of genes for the client;
analyzing a first subset of the genetic information to obtain respective genetic risk assessment results for each of the plurality of clients, wherein the respective genetic risk assessment results are associated with the first medical condition;
making the respective genetic risk assessment results available to the plurality of clients;
determining a plurality of permissions, each permission corresponding to an authorization provided by a particular client for sharing the sequence information for the plurality of genes for the particular client with one or more external assessment systems, wherein an external assessment system corresponds to a remote system distinct from the one or more hardware processors, and wherein the external assessment system has independent access to a data store including analysis results generated by the external assessment system;
after determining the plurality of permissions, receiving a data request from a particular external assessment system, wherein the data request corresponds to a request for sequence information for one or more genes for each of the plurality of clients for assessing genetic risks associated with a second medical condition different from the first medical condition, wherein the sequence information for the one or more genes corresponds to a second subset of the genetic information, and wherein the second subset of the genetic information is at least partially different from the first subset of the genetic information;
determining that an access authorization level for the particular external assessment system is sufficient for accessing the second subset of the genetic information;
determining that the plurality of permissions authorize sharing the second subset of the genetic information for each of the plurality of clients with external assessment systems;
obtaining the second subset of the genetic information for each of the plurality of clients and contact information for each of the plurality of clients; and
transmitting a response to the data request, wherein the response to the data request includes the second subset of the genetic information for each of the plurality of clients and the contact information for each of the plurality of clients, and wherein
receiving the second subset of the genetic information for each of the plurality of clients at the particular external assessment system facilitates the particular external assessment system generating second respective genetic risk assessment results associated with the second medical condition using the second subset of the genetic information, and
receiving the contact information for each of the plurality of clients at the particular external assessment system facilitates the particular external assessment system providing the second respective genetic risk assessment results to the plurality of client devices.
21. The non-transitory computer readable storage medium as recited in claim 15 , wherein the operations further include:
for each client of a set of clients:
receiving, using the one or more hardware processors, a set of reads, each read of the set of reads being associated with the client of the set of clients, each read of the set of reads including a set of identifiers, the set of identifiers being arranged in a particular order in the read;
aligning each read of the set of reads with a portion of a reference data set; and
generating a depth vector for the client of the set of clients that includes a plurality of elements, each element of the plurality of elements being generated based on a quantity of reads that include an identifier aligned to a portion that includes a particular position within the reference data set; and
performing, using the one or more hardware processors, a transformation processing of the depth vectors to produce a plurality of components, each component of the plurality of components assigned a component order based on an extent to which the component accounts for cross-client differences;
identifying a subset of the plurality of components based on the component order; and
for each component in the subset:
generating, for each client of the set of clients, a weight for the component;
determining, for each client of the set of clients, that the weight for the component indicates that the client is to be associated with a new variant;
determining positional data for the new variant based on values in the component; and
storing, for each client of the set of clients, an association between an identifier of the client of the set of clients and variant data that includes the positional data.