SYSTEM AND METHOD FOR SECURE DRUG DISCOVERY INFORMATION PROCESSING

1 . A system for secure drug discovery information processing over a blockchain based platform, the system comprising:

a database to store a plurality of data records and related metadata, and a plurality of ontologies; and

a processor to:

receive a data record from the plurality of data records and a metadata associated with the data record from the database, wherein the data record corresponds to one of a predefined data type recognized by the blockchain based platform;

retrieve one or more ontologies from amongst the plurality of ontologies, based on the metadata of the data record;

measure a term frequency of keywords in the retrieved ontology against a term frequency of keywords in the data record;

validate the data record to belong to a domain of the retrieved ontology, if the keywords from the retrieved ontology are present in the data record above a predetermined value; and

extract one or more value features from the validated data record to determine an association of the data record to a node in a network map of biomedical entities.

2 . A system according to claim 1 , wherein the predefined data type comprises: experimental reports, publications, research articles.

3 . A system according to claim 1 , wherein the one or more value features extracted from the validated data record is one of: genetic association score, somatic association score, specifically targeted experimental records mapping to a predetermined entity.

4 . A system according to claim 1 , wherein the processor is further configured to:

generate a hash of the data record, the metadata and the determined association of the data record to the node in the network map; and

store the hash on a cryptographic ledger associated with the blockchain platform along with a timestamp.

5 . A system according to claim 4 , wherein the cryptographic ledger is a distributed ledger.

6 . A system according to claim 1 , wherein the processor is configured to validate the data record by:

calculating a confidence score based on a presence of keywords in the data record, from the retrieved ontology; and/or

determining a pre-existing association for the extracted one or more value features of the data record.

7 . A system according to claim 1 , wherein the processor is further configured to create the network map of biomedical entities using associations within the plurality of data records.

8 . A method for secure drug discovery information processing over a blockchain based platform, the method comprising:

(i) accessing a data record and a metadata associated with the data record, wherein the data record corresponds to one of a predefined data type recognized by the blockchain based platform;

(ii) retrieving one or more ontologies from amongst a plurality of ontologies, based on the metadata of the data record;

(iii) measuring a term frequency of keywords in the retrieved ontology against a term frequency of keywords in the data record;

(iv) validating the data record to belong to a domain of the retrieved ontology, if the keywords from the retrieved ontology are present in the data record above a predetermined value; and

(v) extracting one or more value features from the validated data record to determine an association of the data record to a node in a network map of biomedical entities.

9 . A method according to claim 8 , wherein the predefined data type comprises: experimental reports, publications, research articles.

10 . A method according to claim 8 , wherein the one or more value features extracted from the validated data record is one of: genetic association score, somatic association score, specifically targeted experimental records mapping to a predetermined entity.

11 . A method according to claim 8 , further comprising:

generating a hash of the data record, the metadata and the determined association of the data record to the node in the network map; and

storing the hash on a cryptographic ledger along with a timestamp.

12 . A method according to claim 11 , wherein the cryptographic ledger is a distributed ledger.

13 . A method according to claim 8 , wherein validating the data record comprises:

calculating a confidence score based on a presence of keywords in the data record, from the retrieved ontology; and/or

determining a pre-existing association for the extracted one or more value features of the data record.

14 . A method according to claim 8 , further comprising creating the network map of biomedical entities using associations within the plurality of data records.

15 . A computer readable medium containing program instructions for execution on a computer system, which when executed by a computer, cause the computer to perform a method, wherein the method is implemented via a system comprising:

(i) accessing a data record and a metadata associated with the data record, wherein the data record corresponds to one of a predefined data type recognized by the blockchain based platform;

(ii) retrieving one or more ontologies from amongst a plurality of ontologies, based on the metadata of the data record;

(iii) measuring a term frequency of keywords in the retrieved ontology against a term frequency of keywords in the data record;

(iv) validating the data record to belong to a domain of the retrieved ontology, if the keywords from the retrieved ontology are present in the data record above a predetermined value; and

(v) extracting one or more value features from the validated data record to determine an association of the data record to a node in a network map of biomedical entities.