Communication generation using sparse indicators and sensor data
Genetic-variant data is obtained that corresponds to one or more variants associated with a client. 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. The first genetic sequence is a genetic sequence of the client. Sensor data is obtained that provides an indication of one or more characteristics of a current or past environment of the client. The genetic-variant data and the sensor data is processed to generate a disease-risk metric corresponding to a predicted risk of the client developing a particular disease. A communication is generated that is indicative of the disease-risk metric. The communication is transmitted to a remote device.
1. 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;
predicting a reliability of the genetic-variant data by performing a comparison of the genetic-variant data based on different labs, different devices, or different time periods associated with data collection;
obtaining other data that include at least sensor data providing an indication of one or more characteristics of the client, current quality of the client, behavior of the client, or one or more characteristics of a current or past environment of the client;
processing, based on the reliability of the genetic-variant data, the genetic-variant data and the other 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 computer-implemented method of claim 1 , wherein when the genetic-variant data corresponding to a given lab, device, or time period is different than the genetic-variant data corresponding to one or more other labs, devices or time periods:
identifying a normalization and/or conversion factor, wherein:
the normalization and/or conversion factor is identified based on centroids of data clusters and/or inter-clusters distances, or
deriving a linear or nonlinear function to relate the genetic-variant data from the given lab, device or time period with the genetic-variant data corresponding to the one or more other labs, devices or time periods; or
avoiding utilization of the genetic-variant data corresponding to the given facility, device, or time period; and
generating a communication to instruct the lab to reprocess a material or sample of the client.
3. The computer-implemented method of claim 1 , wherein performing the comparison includes a direct comparison of collected data or preprocessed versions of the collected data, wherein the preprocessed versions are obtained via a transformation and/or dimensionality reduction techniques including principal component analysis, independent component analysis, or canonical correspondence analysis.
4. The computer-implemented method of claim 1 , wherein performing the comparison further comprising:
performing a clustering technique to detect whether the genetic-variant data corresponding to a given facility, device, or time period predominately resides in a different cluster than genetic-variant data corresponding to one or more other facilities, devices or time periods; and
determining whether two or more datasets corresponding to different facilities, devices, or time periods are statistically different or not; or
performing a time series analysis to determine whether output from a given device is gradually changing with time.
5. The computer-implemented method of claim 1 , wherein the other data further comprises:
data indicative of reported experiences by the client and/or evaluation results of one or more tests of the client,
data of other individuals that are related to the client and/or sharing one or more characteristics with the client.
6. The computer-implemented method as recited in claim 1 , wherein the sensor data characterizes indoor and outdoor time spent by the client.
7. The computer-implemented method 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.
8. 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:
obtain, 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;
predict a reliability of the genetic-variant data by performing a comparison of the genetic-variant data based on different labs, different devices, or different time periods associated with data collection;
obtain other data that include at least sensor data providing an indication of one or more characteristics of the client, current quality of the client, behavior of the client, or one or more characteristics of a current or past environment of the client;
process, based on the reliability of the genetic-variant data, the genetic-variant data and the other data to generate a disease-risk metric corresponding to a predicted risk of the client developing a particular disease;
generate a communication indicative of the disease-risk metric; and
transmit the communication to a remote device.
9. The system of claim 8 , wherein when the genetic-variant data corresponding to a given lab, device, or time period is different than the genetic-variant data corresponding to one or more other labs, devices or time periods:
identifying a normalization and/or conversion factor, wherein:
the normalization and/or conversion factor is identified based on centroids of data clusters and/or inter-clusters distances, or
deriving a linear or nonlinear function to relate the genetic-variant data from the given lab, device or time period with the genetic-variant data corresponding to the one or more other labs, devices or time periods; or
avoiding utilization of the genetic-variant data corresponding to the given facility, device, or time period; and
generating a communication to instruct the lab to reprocess a material or sample of the client.
10. The system of claim 8 , wherein performing the comparison includes a direct comparison of collected data or preprocessed versions of the collected data, wherein the preprocessed versions are obtained via a transformation and/or dimensionality reduction techniques including principal component analysis, independent component analysis, or canonical correspondence analysis.
11. The system of claim 8 , wherein performing the comparison further comprising:
performing a clustering technique to detect whether the genetic-variant data corresponding to a given facility, device, or time period predominately resides in a different cluster than genetic-variant data corresponding to one or more other facilities, devices or time periods; and
determining whether two or more datasets corresponding to different facilities, devices, or time periods are statistically different or not; or
performing a time series analysis to determine whether output from a given device is gradually changing with time.
12. The system of claim 8 , wherein the other data further comprises:
data indicative of reported experiences by the client and/or evaluation results of one or more tests of the client,
data of other individuals that are related to the client and/or sharing one or more characteristics with the client.
13. The system of claim 8 , wherein the sensor data characterizes indoor and outdoor time spent by the client.
14. The system of claim 8 , wherein the sensor data includes data from an accelerometer and provides an indication of past physical activity of the client.
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;
predicting a reliability of the genetic-variant data by performing a comparison of the genetic-variant data based on different labs, different devices, or different time periods associated with data collection;
obtaining other data that include at least sensor data providing an indication of one or more characteristics of the client, current quality of the client, behavior of the client, or one or more characteristics of a current or past environment of the client;
processing, based on the reliability of the genetic-variant data, the genetic-variant data and the other 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 when the genetic-variant data corresponding to a given lab, device, or time period is different than the genetic-variant data corresponding to one or more other labs, devices or time periods:
identifying a normalization and/or conversion factor, wherein:
the normalization and/or conversion factor is identified based on centroids of data clusters and/or inter-clusters distances, or
deriving a linear or nonlinear function to relate the genetic-variant data from the given lab, device or time period with the genetic-variant data corresponding to the one or more other labs, devices or time periods; or
avoiding utilization of the genetic-variant data corresponding to the given facility, device, or time period; and
generating a communication to instruct the lab to reprocess a material or sample of the client.
17. The non-transitory computer readable storage medium as recited in claim 15 , wherein performing the comparison includes a direct comparison of collected data or preprocessed versions of the collected data, wherein the preprocessed versions are obtained via a transformation and/or dimensionality reduction techniques including principal component analysis, independent component analysis, or canonical correspondence analysis.
18. The non-transitory computer readable storage medium as recited in claim 15 , wherein performing the comparison further comprising:
performing a clustering technique to detect whether the genetic-variant data corresponding to a given facility, device, or time period predominately resides in a different cluster than genetic-variant data corresponding to one or more other facilities, devices or time periods; and
determining whether two or more datasets corresponding to different facilities, devices, or time periods are statistically different or not; or
performing a time series analysis to determine whether output from a given device is gradually changing with time.
19. The non-transitory computer readable storage medium as recited in claim 15 , wherein the other data further comprises:
data indicative of reported experiences by the client and/or evaluation results of one or more tests of the client,
data of other individuals that are related to the client and/or sharing one or more characteristics with the client.
20. The non-transitory computer readable storage medium as recited in claim 15 , wherein the sensor data characterizes indoor and outdoor time spent by the client.