	US 12,394,504 B2
	Predicting device, predicting method, predicting program, learning model input data generating device, and learning model input data generating program
Yoshihiro Uesawa, Tokyo (JP)
Assigned to MEIJI PHARMACEUTICAL UNIVERSITY, Tokyo (JP)
Filed by MEIJI PHARMACEUTICAL UNIVERSITY, Tokyo (JP)
Filed on Nov. 27, 2019, as Appl. No. 16/698,129.
Application 16/698,129 is a continuation of application No. PCT/JP2018/024835, filed on Jun. 29, 2018.
Claims priority of application No. 2017-129823 (JP), filed on Jun. 30, 2017; and application No. 2018-122565 (JP), filed on Jun. 28, 2018.
Prior Publication US 2020/0098450 A1, Mar. 26, 2020
Int. Cl. G16C 20/30 (2019.01); G16C 20/70 (2019.01); G16C 20/80 (2019.01)

CPC G16C 20/30 (2019.02) [G16C 20/70 (2019.02); G16C 20/80 (2019.02)]

9 Claims

1. A predicting device which predicts an activity of a target compound based on a structure of the target compound, the predicting device comprising:

a processor configured to:

capture images of a three dimensional structural model of the target compound relatively from a plurality of directions with a virtual camera to generate a plurality of captured images as a set of RGB three-color dots with position information in a two-dimensional plane; and

predict the activity of the target compound from the plurality of captured images that are generated, using a learning model, the learning model being a neural network,

wherein the processor is further configured to learn the learning model and the learning model receives the plurality of captured images as an input.