Metagenomics-based biological surveillance system using big data profiles

1. A method comprising:

obtaining results of metagenomics sequencing performed on biological camples from respective sample sources;

generating a genomic comparison component comprising hit abundance score vectors for respective ones of the samples based at least in part on the metagenomics sequencing results;

obtaining epidemiological data relating to at least one of a disease, infection or contamination characterized by one or more of the hit abundance score vectors;

generating patient comparative indexes based at least in part on the epidemiological data;

obtaining one or more Big Data profiles relating to one or more of the hit abundance score vectors and one or more of the comparative indexes; and

providing surveillance functionality in a decentralized and privacy-preserving manner utilizing a combination of the hit abundance score vectors and the patient comparative indexes based at least in part on information derived from the one or more Big Data profiles,

wherein providing surveillance functionality further comprises:

performing a preprocessing operation to reduce a biclustering sample space of the genomic comparison component;

wherein the method is implemented by at lease one processing device comprising a processor coupled to a memory.

2. The method of claim 1 further comprising updating at least one of the hit abundance score vectors and the patient comparative indexes based at least in part on the one or more Big Data profiles.

3. The method of claim 2 wherein updating at least one of the hit abundance score vectors and the patient comparative indexes based at least in part on the one or more Big Data profiles comprises increasing or decreasing a given one of the comparative indexes in accordance with information derived from the one or more Big Data profiles.

4. The method of claim 1 wherein a given one of the Big Data profiles comprises at least one of location information, climate information, environment information and social media information associated with at least one of the hit abundance score vectors and the patient comparative indexes.

5. The method of claim 1 wherein providing surveillance functionality comprises implementing a machine learning training process that associates particular ones of the hit abundance score vectors and the patient comparative indexes with particular types of information derived from the one or more Big Data profiles.

6. The method of claim 1 wherein providing surveillance functionality comprises detecting at least one characteristic of an actual outbreak of a particular disease, infection or contamination.

7. The method of claim 1 wherein providing surveillance Functionality comprises predicting at least one characteristic of potential outbreak of a particular disease, infection or contamination.

8. The method of claim 7 wherein said at least one characteristic comprises at least one of a location and an affected population of the potential outbreak.

9. The method of claim 1 wherein providing surveillance functionality comprises bounding a search space of the hit abundance score vectors and the patient comparative indexes based at least in part on the information derived from the one or more Big Data profiles.

10. The method of claim 9 wherein bounding a search space of the hit abundance score vectors and the patient comparative indexes based at least in part on the information derived from the one or more Big Data profiles comprises limiting the search space to hit abundance score vectors associated with sample sources that are within a designated proximity to a location derived from the one or more Big Data profiles.

11. The method of claim 1 wherein the hit abundance score vector for a given one of the biological samples comprises a plurality of entries corresponding to respective occurrence frequencies of at least one read of the given biological sample in respective target genomic sequences.

12. The method of claim 11 wherein providing surveillance functionality utilizing a combination of the hit abundance score vectors and the patient comparative indexes based at least in part on information derived from the one or more Big Data profiles further comprises:

generating a hit abundance score matrix comprising a plurality of the hit abundance score vectors wherein one of rows and columns of the hit abundance score matrix correspond to respective different ones of the biological samples and the other of the rows and columns of the hit abundance score matrix correspond to respective different ones of the target genomic sequences; and

performing a biclustering operation on the hit abundance score matrix.

13. The method of claim 12 wherein performing a biclustering operation on the hit abundance score matrix comprises processing the hit abundance score matrix in the form of a bipartite graph in which a first set of nodes represents respective ones of the biological samples, a second set of nodes represents respective ones of the target genomic sequences, and edges between nodes in the first set and nodes in the second set represent hit abundance scores of the hit abundance score vectors of the hit abundance score matrix.

14. A computer program product comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device:

to obtain results of metagenomics sequencing performed on biological samples from respective sample sources;

to generate a genomic comparison component comprising hit abundance score vectors for respective ones of the samples based at least in part on the metagenomics sequencing results;

to obtain epidemiological data relating to at least one of a disease, infection or contamination characterized by one or more of the hit abundance score vectors;

to generate patient comparative indexes based at least in part on the epidemiological data;

to obtain one or more Big Data profiles relating to one or more of the hit abundance score vectors and one or more of the comparative indexes; and

to provide surveillance functionality in a decentralized and privacy-preserving manner utilizing a combination of the hit abundance score vectors and the patient comparative indexes based at least in part on information derived from the one or more Big Data profiles,

wherein providing surveillance functionality further comprises:

performing a preprocessing operation to reduce a biclustering sample space of the genomic comparison component.

15. The computer program product of claim 14 wherein providing surveillance functionality comprises bounding a search space of the hit abundance score vectors and the patient comparative indexes based at least in part on the information derived from the one or more Big Data profiles.

16. The computer program product of claim 15 wherein bounding a search space of the hit abundance score vectors and the patient comparative indexes based at least in part on the information derived from the one or more Big Data profiles comprises limiting the search space to hit abundance score vectors associated with sample sources that are within a designated proximity to a location derived from the one or more Big Data profiles.

17. An apparatus comprising:

at least one processing device having a processor coupled to a memory;

wherein said at least one processing device is configured:

to obtain results of metagenomics sequencing performed on biological samples from respective sample sources;

to generate a genomic comparison component comprising hit abundance score vectors for respective ones of the samples based at least in part on the metagenomics sequencing results;

to obtain epidemiological data relating to at least one of a disease, infection or contamination characterized by one or more of the hit abundance score vectors;

to generate patient comparative indexes based at least in part on the epidemiological data;

to obtain one or more Big Data profiles relating to one or more of the hit abundance score vectors and one or more of the comparative indexes; and

to provide surveillance functionality in a decentralized and privacy-preserving manner utilizing a combination of the hit abundance score vectors and the patient comparative indexes based at least in part on information derived from the one or more Big Data profiles,

wherein providing surveillance functionality further comprises:

performing a preprocessing operation to reduce a biclustering sample space of the genomic comparison component.

18. The apparatus of claim 17 wherein providing surveillance functionality comprises bounding a search space of the hit abundance spore vectors and the patient comparative indexes based at least in part on the information derived from the one or more Big Data profiles.

19. The apparatus of claim 18 wherein bounding a search space of the bit abundance score vectors and the patient comparative indexes based at least in part on the information derived from the one or more Big Data profiles comprises limiting the search space to hit abundance score vectors associated with sample sources that are within a designated proximity to a location derived from the one or more Big Data profles.

20. A metagenomics-based biological surveillance system comprising the apparatus of claim 17 .