Secure genomic data accessioning

1. A method comprising:

identifying an image of a plurality of physical items having scannable codes;

generating, using a convolutional neural network, a plurality of physical item identifiers from the scannable codes in the image;

determining, via a request to a network server, that one or more of the plurality of physical item identifiers do not have corresponding user accounts on the network server and that other physical item identifiers of the plurality of physical item identifiers correspond to existing user accounts on the network server;

generating, by a client device, a user interface comprising an interactive composite image depicting the scannable codes as arranged in the image, the user interface displaying visual elements indicating the one or more of the scannable codes in the interactive composite image that do not have corresponding users accounts without displaying user account data for the physical item identifiers having existing user accounts; and

causing, on the client device, presentation of the user interface.

2. The method of claim 1 , wherein each scannable code in the interactive composite image is selectable to access data about a physical item identifier corresponding to the scannable code.

3. The method of claim 1 , further comprising:

receiving, through the user interface, one or more selections of the scannable codes in the interactive composite image that do not have a corresponding network account on the network server; and

storing, in a database, a flag status for each of the one or more selected scannable codes, the flag status indicating that corresponding network accounts do not exist for the physical item identifiers of the selected scannable codes.

4. The method of claim 1 , further comprising:

in response to determining whether each of the plurality of physical item identifiers has a network account identifier that is not accessible on the client device, automatically uploading batch data indicating one or more physical item identifiers that have network accounts on the network server.

5. The method of claim 4 , wherein the batch data comprises physical item identifiers and metadata indicating which of the physical item identifiers have corresponding network accounts.

6. The method of claim 2 , wherein the data accessed about the physical item identifier comprises a network link configured to populate one or more fields in the user interface, the one or more fields comprising a physical item identifier field.

7. The method of claim 1 , wherein the user accounts have user account identifiers, and wherein the user interface does not display the user account identifiers.

8. The method of claim 1 , further comprising:

transmitting the request to the network server, the request comprising one or more of the plurality of physical item identifiers; and

receiving, from the server, a response indicating that the one or more physical item identifiers do not have corresponding user accounts.

9. The method of claim 1 , wherein generating the plurality of physical item identifiers comprises identifying, in the image, regions of interest (ROIs) using the convolutional neural network, each of the ROIs having image coordinates within the image.

10. The method of claim 9 , wherein generating the plurality of physical item identifiers comprises:

specifying, for each ROI, the coordinates of the ROI in the image; and

decoding a scannable code from the image using the specified coordinates of the ROI.

11. The method of claim 1 , wherein generating the plurality of physical item identifiers comprises:

generating a plurality of image portion files by cropping each of the detected ROIs; and

individually decoding a scannable code from each of the image portion files.

12. The method of claim 1 , wherein the physical items are biological sample containers.

13. The method of claim 1 , further comprising:

storing the interactive composite image in memory.

14. A system comprising:

one or more processors of a client device; and

a memory storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

identifying an image of a plurality of physical items having scannable codes;

generating, using a convolutional neural network, a plurality of physical item identifiers from the scannable codes in the image;

determining, via a request to a network server, that one or more of the plurality of physical item identifiers do not have corresponding user accounts on the network server and that other physical item identifiers of the plurality of physical item identifiers correspond to existing user accounts on the network server;

generating, by a client device, a user interface comprising an interactive composite image depicting the scannable codes as arranged in the image, the user interface displaying visual elements indicating the one or more of the scannable codes in the interactive composite image that do not have corresponding users accounts without displaying user account data for the physical item identifiers having existing user accounts; and

causing, on the client device, presentation of the user interface.

15. The system of claim 14 , wherein each scannable code in the interactive composite image is selectable to access data about a physical item identifier corresponding to the scannable code.

16. The system of claim 14 , the operations further comprising:

receiving, through the user interface, one or more selections of the scannable codes in the interactive composite image that do not have a corresponding network account on the network server; and

storing, in a database, a flag status for each of the one or more selected scannable codes, the flag status indicating that corresponding network accounts do not exist for the physical item identifiers of the selected scannable codes.

17. The system of claim 14 , the operations further comprising:

in response to determining whether each of the plurality of physical item identifiers has a network account identifier that is not accessible on the client device, automatically batch uploading a success status for physical item identifiers that do have network accounts on the network server.

18. The system of claim 14 , wherein generating the plurality of physical item identifiers comprises:

generating a plurality of image portion files by cropping each of the detected ROIs; and

individually decoding a scannable code from each of the image portion files.

19. The system of claim 15 , wherein the data accessed about the physical item identifier comprises a network link configured to populate one or more fields in the user interface, the one or more fields comprising a physical item identifier field.

20. A machine-readable storage device embodying instructions that, when executed by a device, cause the device to perform operations comprising:

identifying an image of a plurality of physical items having scannable codes;

generating, using a convolutional neural network, a plurality of physical item identifiers from the scannable codes in the image;

determining, via a request to a network server, that one or more of the plurality of physical item identifiers do not have corresponding user accounts on the network server and that other physical item identifiers of the plurality of physical item identifiers correspond to existing user accounts on the network server;

generating, by a client device, a user interface comprising an interactive composite image depicting the scannable codes as arranged in the image, the user interface displaying visual elements indicating the one or more of the scannable codes in the interactive composite image that do not have corresponding user accounts without displaying user account data for the physical item identifiers having existing user accounts; and

causing, on the client device, presentation of the user interface.