Abstract: Explicit representation of molecular shape of molecules is combined with neural network learning methods to provide models with high predictive ability that generalize to different chemical classes where structurally diverse molecules exhibiting similar surface characteristics are treated as similar. A new machine-learning methodology is disclosed that can accept multiple representations of objects and construct models that predict characteristics of those objects. An extension of this methodology can be applied in cases where the representations of the objects are determined by a set of adjustable parameters. An iterative process applies intermediate models to generate new representations of the objects by adjusting said parameters and repeatedly. retrains the models to obtain better predictive models. This method can be applied to molecules because each molecule can have many orientations and conformations (representations) that are determined by a set of translation, rotation and torsion angle parameters.

Abstract: An image data registration system and method of storing a first data set of three-dimensional image data associated with a predetermined portion of an object with reference to a first coordinate frame; obtaining and storing a second data set of three-dimensional image data associated with a surface of the predetermined portion of the object with reference to a second coordinate frame; obtaining and storing a third data set of three-dimensional image data associated with a probe in the vicinity of the predetermined portion of the object with reference to a third coordinate frame; and registering the first, second and third data sets to generate a matched image data set in which the first, second and third coordinate frames are relatively aligned with one another.

Abstract: The present invention provides an image data registration system and method of storing a first data set of three-dimensional image data associated with a predetermined portion of an object with reference to a first coordinate frame; obtaining and storing a second data set of three-dimensional image data associated with a surface of the predetermined portion of the object with reference to a second coordinate frame; and registering the first data set and the second data set to generate a matched image data set in which the first coordinate frame is aligned with the second coordinate frame.