US 12,406,413 B2
Predictive data analysis using image representations of genomic data
Ahmed Selim, Dublin (IE); Paul J. Godden, London (GB); and Michael Bridges, Dublin (IE)
Assigned to Optum Services (Ireland) Limited, Dublin (IE)
Filed by Optum Services (Ireland) Limited, Dublin (IE)
Filed on Sep. 13, 2021, as Appl. No. 17/473,064.
Claims priority of provisional application 63/201,699, filed on May 10, 2021.
Prior Publication US 2022/0358697 A1, Nov. 10, 2022
Int. Cl. G06T 11/20 (2006.01); G06N 5/04 (2023.01); G06T 7/00 (2017.01); G16B 5/20 (2019.01); G16B 45/00 (2019.01)
CPC G06T 11/206 (2013.01) [G06N 5/04 (2013.01); G06T 7/0012 (2013.01); G16B 5/20 (2019.02); G16B 45/00 (2019.02); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for dynamically generating an image-based prediction, the computer-implemented method comprising:
receiving, by one or more processors, an input feature, wherein the input feature comprises one or more feature values, wherein each feature value of the one or more feature values corresponds to a genetic variant identifier of a plurality of genetic variant identifiers, and wherein each feature value of the one or more feature values is associated with an input feature type designation of a plurality of input feature type designations;
generating, by the one or more processors, one or more image representations of the input feature, wherein: (i) an image representation count of the one or more image representations of the input feature is based at least in part on the plurality of input feature type designations (ii) each image representation of the one or more image representations of the input feature comprises a plurality of image regions, (iii) each image region of the plurality of image regions for an image representation of the one or more image representations of the input feature corresponds to a genetic variant identifier of the plurality of genetic variant identifiers, and (iv) generating each of the one or more image representations of the input feature associated with a character category is performed based at least in part on the one or more feature values of the input feature having the input feature type designation;
generating, by the one or more processors, a tensor representation of the one or more image representations of the input feature;
generating, by the one or more processors, one or more positional encoding maps, wherein: (i) each positional encoding map of the one or more positional encoding maps comprises a plurality of positional encoding map regions, (ii) each positional encoding map region of the plurality of positional encoding map regions for a positional encoding map corresponds to a genetic variant identifier of the plurality of genetic variant identifiers, (iii) each specific genetic variant identifier of the plurality of genetic variant identifiers is associated with a positional encoding map region set, of one or more positional encoding map region sets, comprising each positional encoding map region of the plurality of positional encoding map regions associated with the specific genetic variant identifier across the one or more positional encoding maps, and (iv) each positional encoding map region set of the one or more positional encoding map region sets for a particular genetic variant identifier of the plurality of genetic variant identifiers represents the particular genetic variant identifier;
generating, by the one or more processors, the image-based prediction based at least in part on the tensor representation of the one or more image representations of the input feature and the one or more positional encoding maps; and
performing, by the one or more processors, one or more prediction-based actions based at least in part on the image-based prediction.