deer_lib_gen.m

From Spinach Documentation Wiki
Jump to: navigation, search

Generates a library of distance distributions and corresponding DEER traces for use in neural network training. Full details are given in our paper on the subject.

Syntax

    [time_grid,dist_grid,dist_distr_lib,...
     deer_ffact_lib,background_lib,deer_trace_lib,...
     noise_line_lib,exchange_lib,parameters]=deer_lib_gen(file_name,parameters)

Arguments

Required fields of the parameters.* structure:

   min_dist          - lower limit of distance distributions, 
                       Angstrom

   max_dist          - upper limit of distance distributions, 
                       Angstrom

   max_time          - DEER trace duration, seconds

   max_exch          - maximum exchange coupling, MHz
                       (NMR convention)

   min_exch          - minimum exchange coupling, MHz
                       (NMR convention)

   ntraces           - number of traces you wish to generate

   ndistmax          - maximum number of skewed gaussians 
                       in the distance distribution

   npoints           - number of digitisation points in the
                       DEER trace and the distance distribu-
                       tion

   noise_lvl         - RMS noise level as a fraction of the
                       modulation depth

   min_fwhm          - minimum FWHM for a skewed gaussian in
                       the distance distribution, fraction of
                       distance

   max_fwhm          - maximum FWHM for a skewed gaussian in
                       the distance distribution, fraction of
                       distance

   min_skew          - minimum shape parameter for a skewed 
                       gaussian in the distance distribution

   max_skew          - maximum shape parameter for a skewed 
                       gaussian in the distance distribution

   max_mdep          - minimum DEER modulation depth

   min_mdep          - maximum DEER modulation depth

   max_brate         - maximum background signal decay
                       rate, s^-1

   min_brate         - minimum background signal decay 
                       rate, s^-1

   min_bdim          - minimum background dimensionality

   max_bdim          - maximum background dimensionality

Outputs

   time_grid         - time grid (seconds) as a row vector

   dist_grid         - distance grid (Angsrom) as a row vector

   dist_distr_lib    - all distance distributions as a horizonal 
                       stack of row vectors

   deer_ffact_lib    - all DEER form factors as a horizonal 
                       stack of row vectors

   background_lib    - all background signals as a horizonal 
                       stack of row vectors, shifted and scaled
                       to match DEER traces

   deer_trace_lib    - all complete DEER traces as a horizonal 
                       stack of row vectors

   noise_line_lib    - all noise tracks as a horizonal 
                       stack of row vectors
 
   exchange_lib      - exchange interaction (MHz), a row vector
                       conataining the value for each example

   parameters        - parameters array as received

If a file name is provided, these variables are written into that file.

Examples

The example below loads the parameters from one of the example files and generates a library of 1000 DEER traces.

	% Load the training set parameters
	run('net_set_any_peaks/netset_params.m'); 

	% Specify number of traces to produce
	parameters.ntraces=1000;

	% Set the training database name
	file_name='dlg_example_set.mat';

	% Generate the training library
	[time_grid,dist_grid,dist_distr_lib,...
 	deer_ffact_lib,background_lib,deer_trace_lib,...
 	noise_line_lib,exchange_lib,parameters]=deer_lib_gen(file_name,parameters);

One of the resulting DEER traces is shown below.

Notes

Multiple caveats exist in the training process. Please read our paper carefully before training your own networks.

See also

Neural network module

DEER/PELDOR experiments


Version 2.5, authors: Ilya Kuprov, Steve Worswick, Jake Keeley, Gunnar Jeschke