deer_lib_gen.m

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 first loads the netset parameters from the ensemble optimised for all peak widths, and then generates a library of 1000 trace/distribution pairs. The example may be run from the examples/deernet/ directory.

	% 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);

This example will add the output libraries to the MATLAB workspace, as well as saving them in the working directory as "dlg_example_set.mat"

• 

  Example distance distribution.

• 

  DEER trace and components for example distribution.

Notes

• As the dipolar modulation frequency is a cubic function of the inter-spin distance, a scaling relationship exists betweent the distance range and the duration of the DEER signal.

\[\frac{t_A}{r_A^3}=\frac{t_B}{r_B^3} \]

• An important factor when generating data for training is the dynamic range - the ratio between the longest and shortest distances represented in the training set.

• The training set DEER traces should be sufficiently discretised (parameters.npoints) to reproduce all frequencies present.

See also

netset_curate.m, train_one_net.m

Version 2.2, authors: Ilya Kuprov, Steve Worswick, Gunnar Jeschke