No commit message

phylogenetic_tree_software_with_matlab_wrappers/EXACT/run_me.m

@@ -48,4 +48,4 @@
 generate_joint_plot_of_tree_donut_muller_and_errors(U, clust, Mutant_Frequencies_M,  Ugt, clustgt);
 
 % generate a list of top 10 trees ranked by their probabilities according to our assumed model
-generate_list_of_top_k_trees_with_probabilities(10,top_k_value, max_tree_size, min_tree_size, error_rate, ourcode_all_Ms, ourcode_output);
+generate_list_of_top_k_trees_with_probabilities(10, top_k_value, max_tree_size, min_tree_size, error_rate, ourcode_all_Ms, ourcode_output);

phylogenetic_tree_software_with_matlab_wrappers/all_tests/compare_algs_real_data.m

@@ -10,67 +10,71 @@
 % MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 % GNU General Public License for more details.
 
-%% Skeleton code demonstrating the calculation of standard deviation among the results of the four error types for the various tools
+%% Calculates of standard deviation among the results of the four error types for the various tools
 % The tools have been run on the the simulated data provided in the
 % AncesTree paper. The results have been contrasted against ground truth
 % provided in the same paper to calculate the errors.
 
-phylowgs_exact_mean_error = mean(all_four_errors_phylowgs_exact,2);
-phylowgs_exact_mean_error_std = zeros(4,1);
-for i = 1:4
-phylowgs_exact_mean_error_std(i,1) = std(all_four_errors_phylowgs_exact(i,:))/sqrt(size(all_four_errors_phylowgs_exact,2));
-end
+function compare_algs_real_data[phylowgs_exact_mean_error, phylowgs_exact_mean_error_std, phylowgs_citup_mean_error, phylowgs_citup_mean_error_std, phylowgs_exact_mean_error_std ] = compute_means_and_std_of_error_for_all_tools_vs_all_tools(all_four_errors_phylowgs_exact, all_four_errors_phylowgs_exact, all_four_errors_phylowgs_citup)
 
-phylowgs_citup_mean_error = mean(all_four_errors_phylowgs_citup,2);
-phylowgs_citup_mean_error_std = zeros(4,1);
-for i = 1:4
-phylowgs_citup_mean_error_std(i,1) = std(all_four_errors_phylowgs_citup(i,:))/sqrt(size(all_four_errors_phylowgs_citup,2));
-end
+	phylowgs_exact_mean_error = mean(all_four_errors_phylowgs_exact,2);
+	phylowgs_exact_mean_error_std = zeros(4,1);
+	for i = 1:4
+	phylowgs_exact_mean_error_std(i,1) = std(all_four_errors_phylowgs_exact(i,:))/sqrt(size(all_four_errors_phylowgs_exact,2));
+	end
 
-phylowgs_ancestree_mean_error = mean(all_four_errors_phylowgs_ancestree,2);
-phylowgs_ancestree_mean_error_std = zeros(4,1);
-for i = 1:4
-phylowgs_ancestree_mean_error_std(i,1) = std(all_four_errors_phylowgs_ancestree(i,:))/sqrt(size(all_four_errors_phylowgs_ancestree,2));
-end
+	phylowgs_citup_mean_error = mean(all_four_errors_phylowgs_citup,2);
+	phylowgs_citup_mean_error_std = zeros(4,1);
+	for i = 1:4
+	phylowgs_citup_mean_error_std(i,1) = std(all_four_errors_phylowgs_citup(i,:))/sqrt(size(all_four_errors_phylowgs_citup,2));
+	end
 
-exact_citup_mean_error = mean(all_four_errors_exact_citup,2);
-exact_citup_mean_error_std = zeros(4,1);
-for i = 1:4
-exact_citup_mean_error_std(i,1) = std(all_four_errors_exact_citup(i,:))/sqrt(size(all_four_errors_exact_citup,2));
-end
+	phylowgs_ancestree_mean_error = mean(all_four_errors_phylowgs_ancestree,2);
+	phylowgs_ancestree_mean_error_std = zeros(4,1);
+	for i = 1:4
+	phylowgs_ancestree_mean_error_std(i,1) = std(all_four_errors_phylowgs_ancestree(i,:))/sqrt(size(all_four_errors_phylowgs_ancestree,2));
+	end
 
-exact_ancestree_mean_error = mean(all_four_errors_exact_ancestree,2);
-exact_ancestree_mean_error_std = zeros(4,1);
-for i = 1:4
-exact_ancestree_mean_error_std(i,1) = std(all_four_errors_exact_ancestree(i,:))/sqrt(size(all_four_errors_exact_ancestree,2));
-end
+	exact_citup_mean_error = mean(all_four_errors_exact_citup,2);
+	exact_citup_mean_error_std = zeros(4,1);
+	for i = 1:4
+	exact_citup_mean_error_std(i,1) = std(all_four_errors_exact_citup(i,:))/sqrt(size(all_four_errors_exact_citup,2));
+	end
 
-citup_ancestree_mean_error = mean(all_four_errors_citup_ancestree,2);
-citup_ancestree_mean_error_std = zeros(4,1);
-for i = 1:4
-citup_ancestree_mean_error_std(i,1) = std(all_four_errors_citup_ancestree(i,:))/sqrt(size(all_four_errors_citup_ancestree,2));
-end
+	exact_ancestree_mean_error = mean(all_four_errors_exact_ancestree,2);
+	exact_ancestree_mean_error_std = zeros(4,1);
+	for i = 1:4
+	exact_ancestree_mean_error_std(i,1) = std(all_four_errors_exact_ancestree(i,:))/sqrt(size(all_four_errors_exact_ancestree,2));
+	end
 
-phylowgs_canopy_mean_error = mean(all_four_errors_phylowgs_canopy,2);
-phylowgs_canopy_mean_error_std = zeros(4,1);
-for i = 1:4
-phylowgs_canopy_mean_error_std(i,1) = std(all_four_errors_phylowgs_canopy(i,:))/sqrt(size(all_four_errors_phylowgs_canopy,2));
-end
+	citup_ancestree_mean_error = mean(all_four_errors_citup_ancestree,2);
+	citup_ancestree_mean_error_std = zeros(4,1);
+	for i = 1:4
+	citup_ancestree_mean_error_std(i,1) = std(all_four_errors_citup_ancestree(i,:))/sqrt(size(all_four_errors_citup_ancestree,2));
+	end
 
-exact_canopy_mean_error = mean(all_four_errors_exact_canopy,2);
-exact_canopy_mean_error_std = zeros(4,1);
-for i = 1:4
-exact_canopy_mean_error_std(i,1) = std(all_four_errors_exact_canopy(i,:))/sqrt(size(all_four_errors_exact_canopy,2));
-end
+	phylowgs_canopy_mean_error = mean(all_four_errors_phylowgs_canopy,2);
+	phylowgs_canopy_mean_error_std = zeros(4,1);
+	for i = 1:4
+	phylowgs_canopy_mean_error_std(i,1) = std(all_four_errors_phylowgs_canopy(i,:))/sqrt(size(all_four_errors_phylowgs_canopy,2));
+	end
 
-citup_canopy_mean_error = mean(all_four_errors_citup_canopy,2);
-citup_canopy_mean_error_std = zeros(4,1);
-for i = 1:4
-citup_canopy_mean_error_std(i,1) = std(all_four_errors_citup_canopy(i,:))/sqrt(size(all_four_errors_citup_canopy,2));
-end
+	exact_canopy_mean_error = mean(all_four_errors_exact_canopy,2);
+	exact_canopy_mean_error_std = zeros(4,1);
+	for i = 1:4
+	exact_canopy_mean_error_std(i,1) = std(all_four_errors_exact_canopy(i,:))/sqrt(size(all_four_errors_exact_canopy,2));
+	end
+
+	citup_canopy_mean_error = mean(all_four_errors_citup_canopy,2);
+	citup_canopy_mean_error_std = zeros(4,1);
+	for i = 1:4
+	citup_canopy_mean_error_std(i,1) = std(all_four_errors_citup_canopy(i,:))/sqrt(size(all_four_errors_citup_canopy,2));
+	end
+
+	ancestree_canopy_mean_error = mean(all_four_errors_ancestree_canopy,2);
+	ancestree_canopy_mean_error_std = zeros(4,1);
+	for i = 1:4
+	ancestree_canopy_mean_error_std(i,1) = std(all_four_errors_ancestree_canopy(i,:))/sqrt(size(all_four_errors_ancestree_canopy,2));
+	end
 
-ancestree_canopy_mean_error = mean(all_four_errors_ancestree_canopy,2);
-ancestree_canopy_mean_error_std = zeros(4,1);
-for i = 1:4
-ancestree_canopy_mean_error_std(i,1) = std(all_four_errors_ancestree_canopy(i,:))/sqrt(size(all_four_errors_ancestree_canopy,2));
 end

phylogenetic_tree_software_with_matlab_wrappers/all_tests/generate_list_of_PhyloWGS_trees.m

@@ -1,3 +1,26 @@
+% Copyright (c) 2019 Surjyendu Ray
+% 
+% This program is free software: you can redistribute it and/or modify
+% it under the terms of the GNU General Public License as published by
+% the Free Software Foundation, either version 3 of the License, or
+% (at your option) any later version.
+% 
+% This program is distributed in the hope that it will be useful,
+% but WITHOUT ANY WARRANTY; without even the implied warranty of
+% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+% GNU General Public License for more details.
+
+%% Function to plot the inferred trees from PhyloWGS output along with their respective fitting cost
+
+% INPUTS:
+% phylowgs_output is a matlab cell object having 3 components.
+% Each component is a cell object indexed by sol_id, which lists different good solutions.
+% The number of solutions that PhyloWGS outputs is given by how many different sol_id indices there are in the output 
+% phylowgs_output{1}{sol_id} = adjacency matrix for the sol_id th output tree. This is a directed tree. If we have this matrix T, then U = inv(I - T), where U appears in the PPM model as F = UM.
+% phylowgs_output{2}{sol_id} = cluster membership information for the clustering. An array with 2 columns, the 2nd column designating the cluster ID, and the 1st column designating the mutation that belongs to that cluster
+% phylowgs_output{3}{sol_id} = frequencies of the input, after mutations have been clustered, helps in obtaining clustered frequencies of mutants.
+
+
 function generate_list_of_PhyloWGS_trees(phylowgs_output)
 
 	figure;

phylogenetic_tree_software_with_matlab_wrappers/all_tests/generate_list_of_top_k_trees_with_probabilities.m

@@ -1,4 +1,24 @@
-function generate_list_of_top_k_trees_with_probabilities(display_top_k,top_k_value, max_tree_size, min_tree_size, error_rate, ourcode_all_Ms, ourcode_output)
+% Copyright (c) 2019 Surjyendu Ray
+% 
+% This program is free software: you can redistribute it and/or modify
+% it under the terms of the GNU General Public License as published by
+% the Free Software Foundation, either version 3 of the License, or
+% (at your option) any later version.
+% 
+% This program is distributed in the hope that it will be useful,
+% but WITHOUT ANY WARRANTY; without even the implied warranty of
+% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+% GNU General Public License for more details.
+
+%% Function to plot the inferred trees from EXACT output along with their respective probabilities
+
+% INPUT
+% display_top_k = how many top scoring inferred trees we want as output in the plot
+% top_k_value = 
+
+
+
+function generate_list_of_top_k_trees_with_probabilities(display_top_k, top_k_value, max_tree_size, min_tree_size, error_rate, ourcode_all_Ms, ourcode_output)
 
 	figure;