Protein

Generate either a convex or concave hull based on specified alpha and num_points. Hulls are created by radially distributing random points, then optimizing a perimeter based on the specified alpha. Shapes can be convex by setting relatively lower alpha and higher num_points. Hull coordinates are then converted to grid based shapes, where pixels within the hull perimeter are assigned a value of 1, and 0 otherwise.

class Dock2D.DatasetGeneration.Protein.Protein(bulk, hull=None)
__init__(bulk, hull=None)
Parameters

  • bulk – protein shape bulk

  • hull – coordinates for the convex/concave hull

classmethod generateConcave(size, alpha, num_points, occupancy=0.8, debug=False)

Generate concave hull coordinates and convert to grid based shape filled with 1 inside the shape, 0 otherwise.

Parameters

  • size – the dimensions of the box containing the shape

  • alpha – the level of concavity used to generate convex hulls

  • num_points – number of points randomly radially distributed to generate the hull

  • occupancy – distance to span the the point distributions, 0.8 of size 50 gives 40pixels.

Returns

concave protein shape bulk

Dock2D.DatasetGeneration.Protein.get_random_points(num_points, xspan, yspan, debug=False)

Generate coordinate points uniformly distributed inside the ellipse inscribed in the rectangle defined by xspan and yspan.

Parameters

  • num_points – number of points used to generate hulls

  • xspan – distance to span points in the x dimension

  • yspan – distance to span points in the y dimension

Returns

points distribution

Dock2D.DatasetGeneration.Protein.hull2array(hull, array, xspan, yspan)

Convert a hull to a grid based shape. All grid pixels are filled with 1 inside the shape, 0 otherwise.

Parameters

  • hull – convex or concave hull points

  • array – grid to convert hull to gridshape

  • xspan – distance to span grid points in the x dimension

  • yspan – distance to span grid points in the y dimension

Returns

bulk hull converted to a grid