clarifications to comments in code

classification_and_analysis/analysis/backwards_select_analysis.m

@@ -52,10 +52,6 @@ end
 % save the workspace used
 overall_vars.WORKSPACE = chosen_workspaces;
 
-% save whether efflux was in lipid or not
-overall_vars.EFFLUX_IN_LIPID = efflux_in_lipid;
-
-
 disp(strcat("distance metric is ", d_metric))
 
 if large_group

classification_and_analysis/analysis/classification_loop_content.m

@@ -521,7 +521,6 @@ backwards_select_analysis
 % from the overall vars --> just straight up look for highest percent
 % and if there is more than one, take lowest value
 
-% did I steal this from another section of code? what are you, a cop
 % get all of the fieldnames for overall vars 
 field_names = fieldnames(overall_vars);
 

classification_and_analysis/cKNN_creator.m

@@ -231,7 +231,7 @@ moa_table = sortrows(moa_table,'DRUG');
 %connectivity_plot(moa_table,color_struct,all_categories,chosen_colormap,wbg)
 %sgtitle({bayes_file,run_tot_string},'Interpreter','none')
 
-%% want to go through and make it into funky two way table time
+%% want to go through and make it into a two way table 
 
 % add a moa column
 results_table.MOA = results_table.DRUG;
@@ -268,11 +268,6 @@ two_way_table= make_two_way_table(results_table,'DRUG','NEIGHBOR');
 %title("drugs on bottom have the neighbors of drugs on left")
 
 %% want to create a table that adds together all of the connections 
-% would it be easier to start with the bayes struct or 1 way table? 
-% we'd need to add together first again before taking the percents... hm
-
-% could actually just get raw values back by multiplying and dividng by 100
-
 raw_two_way_table = two_way_table; 
 
 raw_two_way_table{:,:} = raw_two_way_table{:,:}/100*total_runs;

classification_and_analysis/functions/change_to_moa.m

 function drug_moas = change_to_moa(drugList,all_categories)
 % INPUT list of drugs 
 % will read them in and change them to their MoA
-% is this like assign MoA? probably
-% let me live my life
 % all_categories is a struct where ,for example, all_categories.protein has
 % an array of all of the different protein drugs
 

classification_and_analysis/functions/combine_workspaces.m

@@ -5,7 +5,7 @@ function final_data_table = combine_workspaces(chosen_workspaces,workspace_direc
     % create a structure to store the final_data_table s from each workspace
     all_spaces = struct;
     for i = chosen_workspaces
-       % get each individual spacee
+       % get each individual space
        one_space = i{1};
        % need to get final data table from each space and concat final_data_table
        fpath = strcat(workspace_directory, '/', one_space);

classification_and_analysis/functions/graph_color_moa.m

 function  graph_color_moa(fig)
-%less loopy than before, this bad boy ensures everything is exactly the
-% same every time 
-% jk ended up being p loopy 
-% color_maker and graph_helper2 needed to run this
+% like graph_color_s but color by MoA
 
     %now to the scatter plot colors
     ca = get(fig,'CurrentAxes');
@@ -32,22 +29,19 @@ function  graph_color_moa(fig)
     
     % sort drug by MoA
     RNAP = ["RifT","RIF","RNAP"];
-    lipid = ["PZA","CCCP","Gra","Mon","Nig","Nis","Sulf","BDQ","Clz","Cerold"];
-    lipid_2 = ["Tri","Ver","Thi"];
+    efflux = ["efflux","Ver","Thi"];
+    lipid = ["PZA","CCCP","Gra","Mon","Nig","Nis","BDQ","Clz"];
     protein = ["Kan","Amk","Cam","AZT","Cla","Dox","Gent","Strep","Tet","Tig","Lin","protein"];
-    dna = ["Dau","Nal","Lev","Mox","MIT","Olf","dna","MOX","Olfold","Nit"];
-    cell_wall = ["Mer","Amp","Amox","Ctax","Clex","INH","ETA","IMI","Pip","Cfox", ...
-        "Mec","Oxa","PenG","Van","Pre","Cyc","A22","Carb","Del","EMB","cell_wall","Cer","THL"];
+    dna = ["Lev","Mox","MIT","Olf","dna","MOX"];
+    cell_wall = ["Mer","Amp","Ctax","INH","ETA","IMI", ...
+        "Van","Pre","Cyc","Del","EMB","cell_wall","Cer","THL"];
     controls = ["MeOH","EtOH","NaOH","water","DMSO","Untreated","control"];
-    unknowns = ["Unknown2019", "Unknown2239", "Unknown2911","Unknown3285","Unknown4050"];
+    unknowns = ["Unknown2019", "Unknown2239","Unknown3285"];
     extras = ["INH_control","INH_control_3x"];
     
-    stonybrooks = ["high_692","high_701","high_702","low_691","low_692","low_701","low_702"];
-    
     %Set up arrays of similar colors for different MoA
     RNAPcol = color_maker(RNAP, [255 255 0], [0 0 50]);
     lipidcol = color_maker(lipid,[0 83 166],[8 13 35]);
-    lipid_2col = color_maker(lipid_2,[0, 211, 211],[100 10 5]);
     proteincol = color_maker(protein,[55 92 0],[10 20 4]);
     dnacol = color_maker(dna,[255 234 196],[0,-38,-62]);
     cell_wallcol = color_maker(cell_wall,[52 0 109],[9 8 14]);

classification_and_analysis/functions/graph_color_s.m

 function  graph_color_s(fig)
-%less loopy than before, this bad boy ensures everything is exactly the
-% same every time 
-% jk ended up being p loopy 
-% color_maker and graph_helper2 needed to run this
+% used to color graph using the same color scheme each time
+% apply to existing figure handle 
 
     %now to the scatter plot colors
     ca = get(fig,'CurrentAxes');
@@ -33,30 +31,25 @@ function  graph_color_s(fig)
     % sort drug by MoA
     RNAP = ["RifT","RIF","RNAP"];
     efflux = ["efflux","Ver","Thi"];
-    lipid = ["PZA","CCCP","Gra","Mon","Nig","Nis","Sulf","BDQ","Clz","Cerold"];
-    lipid_2 = ["Tri"];
+    lipid = ["PZA","CCCP","Gra","Mon","Nig","Nis","BDQ","Clz"];
     protein = ["Kan","Amk","Cam","AZT","Cla","Dox","Gent","Strep","Tet","Tig","Lin","protein"];
-    dna = ["Dau","Nal","Lev","Mox","MIT","Olf","dna","MOX","Olfold","Nit"];
-    cell_wall = ["Mer","Amp","Amox","Ctax","Clex","INH","ETA","IMI","Pip","Cfox", ...
-        "Mec","Oxa","PenG","Van","Pre","Cyc","A22","Carb","Del","EMB","cell_wall","Cer","THL"];
+    dna = ["Lev","Mox","MIT","Olf","dna","MOX"];
+    cell_wall = ["Mer","Amp","Ctax","INH","ETA","IMI", ...
+        "Van","Pre","Cyc","Del","EMB","cell_wall","Cer","THL"];
     controls = ["MeOH","EtOH","NaOH","water","DMSO","Untreated","control"];
-    unknowns = ["Unknown2019", "Unknown2239", "Unknown2911","Unknown3285","Unknown4050"];
+    unknowns = ["Unknown2019", "Unknown2239","Unknown3285"];
     extras = ["INH_control","INH_control_3x"];
     
-    stonybrooks = ["high_692","high_701","high_702","low_691","low_692","low_701","low_702"];
-    
     %Set up arrays of similar colors for different MoA
     RNAPcol = color_maker(RNAP, [255 255 0], [0 0 50]);
     effluxcol = color_maker(efflux,[100 19 38],[0 50 50]);
     lipidcol = color_maker(lipid,[0 83 166],[8 13 35]);
-    lipid_2col = color_maker(lipid_2,[0, 211, 211],[100 10 5]);
     proteincol = color_maker(protein,[55 92 0],[10 20 4]);
     dnacol = color_maker(dna,[255 234 196],[0,-38,-62]);
     cell_wallcol = color_maker(cell_wall,[52 0 109],[9 8 14]);
     controlscol = color_maker(controls,[33 33 33],[25 25 25]);
     unknownscol = color_maker(unknowns,[150 20 170],[20 40 -20]);
     extrascol = color_maker(extras,[255 255 255],[0 -15 -50]);
-    stonybrookscol = color_maker(stonybrooks,[240 120 21], [-28 20 32]);
 
     %failsafe if a drug shows up that is not listed
     nogroup = 0;
@@ -110,10 +103,6 @@ function  graph_color_s(fig)
             ind = find(strcmpi(lipid,name));
             graph_helper(scat(row,1), lipidcol,ind,markers)
             
-        elseif ismember(name, lipid_2)
-            ind = find(strcmp(lipid_2,name));
-            graph_helper(scat(row,1), lipid_2col,ind,markers)
-            
         elseif ismember(name, protein)
             ind = find(strcmpi(protein,name));
             graph_helper(scat(row,1), proteincol,ind,markers)
@@ -126,10 +115,6 @@ function  graph_color_s(fig)
             ind = find(strcmpi(cell_wall,name));
             graph_helper(scat(row,1), cell_wallcol,ind,markers)
             
-        elseif ismember(name,stonybrooks)
-            ind = find(strcmpi(stonybrooks,name));
-            graph_helper(scat(row,1), stonybrookscol,ind,markers)
-
         elseif ismember(name, controls)
             ind = find(strcmpi(controls,name));
             graph_helper(scat(row,1), controlscol,ind,markers)

classification_and_analysis/functions/replace_allcap_name.m

 function full_names = replace_allcap_name(abbv_names)
     % converts all drug abbreviations to all cap versions
-%     % will also change _025x to " low" and _3x to " high" 
-%     
-%     abbv_names = strrep(abbv_names, 'Amp','AMP');
-%     abbv_names = strrep(abbv_names, 'Ctax','CTAX');
-%     abbv_names = strrep(abbv_names, 'Mer','MER');
-% %     abbv_names = strrep(abbv_names, 'INH','isoniazid');
-% %     abbv_names = strrep(abbv_names, 'EMB','ethambutol');
-% %     abbv_names = strrep(abbv_names, 'ETA','ethionamide');
-% %     abbv_names = strrep(abbv_names, 'IMI','imipenem');
-%     abbv_names = strrep(abbv_names, 'Pip','PIP');
-%     abbv_names = strrep(abbv_names, 'Oxa','OXA');
-%     abbv_names = strrep(abbv_names, 'PenG','PENG');
-%     abbv_names = strrep(abbv_names, 'Van','VAN');
-%     abbv_names = strrep(abbv_names, 'Cyc','CYC');
-%     abbv_names = strrep(abbv_names, 'Carb','CARB');
-%     abbv_names = strrep(abbv_names, 'Del','DEL');
-%     abbv_names = strrep(abbv_names, 'Dau','DAU'); 
-%     abbv_names = strrep(abbv_names, 'Nal','NAL');
-%     abbv_names = strrep(abbv_names, 'Lev','LEV');
-%     abbv_names = strrep(abbv_names, 'Mox','MOX');
-%     abbv_names = strrep(abbv_names, 'Clz','CLZ');
-% %     abbv_names = strrep(abbv_names, 'MIT','MIT');
-%     abbv_names = strrep(abbv_names, 'Olf','OLF'); 
-%     abbv_names = strrep(abbv_names, 'Kan','KAN');
-%     abbv_names = strrep(abbv_names, 'Amk','AMK');
-%     abbv_names = strrep(abbv_names, 'Cam','CAM');
-% %     abbv_names = strrep(abbv_names, 'AZT','azithromycin');
-%     abbv_names = strrep(abbv_names, 'Cla','CLA');
-%     abbv_names = strrep(abbv_names, 'Dox','DOX'); 
-%     abbv_names = strrep(abbv_names, 'Gent','GENT');
-%     abbv_names = strrep(abbv_names, 'Strep','STREP');
-%     abbv_names = strrep(abbv_names, 'Tet','TET');
-%     abbv_names = strrep(abbv_names, 'Tig','TIG');
-%     abbv_names = strrep(abbv_names, 'Lin','LIN');
-%     abbv_names = strrep(abbv_names, 'Pre','PRE');
-%  %   abbv_names = strrep(abbv_names, 'CCCP','carbonyl cyanide 3-chlorophenylhydrazone');
-%     abbv_names = strrep(abbv_names, 'Cer','CER');
-%     abbv_names = strrep(abbv_names, 'Gra','GRA');
-%     abbv_names = strrep(abbv_names, 'Mon','MON');
-%     abbv_names = strrep(abbv_names, 'Nig','NIG');
-%     abbv_names = strrep(abbv_names, 'Nis','NIS');
-%     abbv_names = strrep(abbv_names, 'Tri','TRI');
-%     abbv_names = strrep(abbv_names, 'Ver','VER');
-%     abbv_names = strrep(abbv_names, 'Thi','THI');
-%     abbv_names = strrep(abbv_names, 'RifT','RIFT');
-%     abbv_names = strrep(abbv_names, 'Nit','NIT');
-%     abbv_names = strrep(abbv_names, 'Sulf','SULF');
-%     abbv_names = strrep(abbv_names, 'BDQ','bedaquiline');
-%     abbv_names = strrep(abbv_names, 'RIF','rifampicin');
-%     abbv_names = strrep(abbv_names, 'PZA','pyrazinamide');
 
     abbv_names = upper(abbv_names);
     abbv_names = strrep(abbv_names,'_025x',' L');

classification_and_analysis/functions/replace_full_name.m

@@ -8,15 +8,10 @@ function full_names = replace_full_name(abbv_names)
     abbv_names = strrep(abbv_names, 'EMB','ethambutol');
     abbv_names = strrep(abbv_names, 'ETA','ethionamide');
     abbv_names = strrep(abbv_names, 'IMI','imipenem');
-    abbv_names = strrep(abbv_names, 'Pip','piperacillin');
-    abbv_names = strrep(abbv_names, 'Oxa','oxacillin');
-    abbv_names = strrep(abbv_names, 'PenG','penicillin G');
     abbv_names = strrep(abbv_names, 'Van','vancomycin');
     abbv_names = strrep(abbv_names, 'Cyc','cycloserine');
     abbv_names = strrep(abbv_names, 'Carb','carbenicillin');
     abbv_names = strrep(abbv_names, 'Del','delamanid');
-    abbv_names = strrep(abbv_names, 'Dau','daunorubicin'); 
-    abbv_names = strrep(abbv_names, 'Nal','nalidixic acid');
     abbv_names = strrep(abbv_names, 'Lev','levofloxacin');
     abbv_names = strrep(abbv_names, 'Mox','moxifloxacin');
     abbv_names = strrep(abbv_names, 'Clz','clofazimine');
@@ -25,7 +20,6 @@ function full_names = replace_full_name(abbv_names)
     abbv_names = strrep(abbv_names, 'Kan','kanamycin');
     abbv_names = strrep(abbv_names, 'Amk','amikacin');
     abbv_names = strrep(abbv_names, 'Cam','chloramphenicol');
-    abbv_names = strrep(abbv_names, 'AZT','azithromycin');
     abbv_names = strrep(abbv_names, 'Cla','clarithromycin');
     abbv_names = strrep(abbv_names, 'Dox','doxycycline'); 
     abbv_names = strrep(abbv_names, 'Gent','gentamicin');
@@ -34,17 +28,13 @@ function full_names = replace_full_name(abbv_names)
     abbv_names = strrep(abbv_names, 'Tig','tigecycline');
     abbv_names = strrep(abbv_names, 'Lin','linezolid');
     abbv_names = strrep(abbv_names, 'Pre','pretomanid');
- %   abbv_names = strrep(abbv_names, 'CCCP','carbonyl cyanide 3-chlorophenylhydrazone');
     abbv_names = strrep(abbv_names, 'Cer','cerulenin');
     abbv_names = strrep(abbv_names, 'Gra','gramicidin');
     abbv_names = strrep(abbv_names, 'Mon','monensin');
     abbv_names = strrep(abbv_names, 'Nig','nigericin');
     abbv_names = strrep(abbv_names, 'Nis','nisin');
-    abbv_names = strrep(abbv_names, 'Tri','triclosan');
-    abbv_names = strrep(abbv_names, 'Ver','verapamil');
     abbv_names = strrep(abbv_names, 'Thi','thioridazine');
     abbv_names = strrep(abbv_names, 'RifT','rifapentine');
-    abbv_names = strrep(abbv_names, 'Nit','nitrofurantoin');
     abbv_names = strrep(abbv_names, 'Sulf','sulfamethizole');
     abbv_names = strrep(abbv_names, 'BDQ','bedaquiline');
     abbv_names = strrep(abbv_names, 'RIF','rifampicin');

classification_and_analysis/helper/filter_drugs.m

@@ -11,7 +11,7 @@
 %%%
 %%% OUTPUT: final_data_table, with the chosen drugs removed
 %%%         apply , whether there are drugs to apply
-%%%         drug_to_apply, a subsection of the final_data_table only for the drug to apply (correct?)
+%%%         drug_to_apply, a subsection of the final_data_table only for the drug to apply 
 %%%         choice_indexes
 %%%         chosen chosen_drugs
 %%%         
@@ -68,7 +68,7 @@ chosen = chosen_drugs;
 
 %%
 % want to make them keep untreated, put in a boolean to get rid of it later
-% after TVN maybe?
+% after TVN 
 % force user to select untreated
 if ~any(contains(chosen,'Untreated'))
     chosen = [chosen {'Untreated'}];

classification_and_analysis/helper/flatten_dose_response.m

@@ -109,41 +109,41 @@ end
 %% for Untreated, we can just put all of the untreated into one rep and call it a day
 % this is just a fix for that bayes stuff right now le'ts go
 if bayesian
-    unt_reps = fieldnames(split_tables.drug52_doseResponse.Untreated)';
+    unt_reps = fieldnames(split_tables.drug34_doseResponse.Untreated)';
 
     % add a new field for all reps
 
-    split_tables.drug52_doseResponse.Untreated.all_reps = struct;
+    split_tables.drug34_doseResponse.Untreated.all_reps = struct;
 
     % want to make this flexible later but now just need to get things going 
     for i = unt_reps
         rep=i{1};
-        unt3x = split_tables.drug52_doseResponse.Untreated.(rep).Untreated_3x;
-        unt025x = split_tables.drug52_doseResponse.Untreated.(rep).Untreated_025x;
+        unt3x = split_tables.drug34_doseResponse.Untreated.(rep).Untreated_3x;
+        unt025x = split_tables.drug34_doseResponse.Untreated.(rep).Untreated_025x;
 
         if strcmp(rep,"rep1")
-            split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_3x = unt3x;
-            split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_025x = unt025x;
+            split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_3x = unt3x;
+            split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_025x = unt025x;
         else
-            split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_3x = ...
-                vertcat(split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_3x, unt3x);
-            split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_025x = ...
-                vertcat(split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_025x, unt025x);
+            split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_3x = ...
+                vertcat(split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_3x, unt3x);
+            split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_025x = ...
+                vertcat(split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_025x, unt025x);
 
         end
-        split_tables.drug52_doseResponse.Untreated = ...
-            rmfield(split_tables.drug52_doseResponse.Untreated,rep);
+        split_tables.drug34_doseResponse.Untreated = ...
+            rmfield(split_tables.drug34_doseResponse.Untreated,rep);
     end 
 
     % go replace the rep column to all have the same thing so it works on next
     % step
 
-    maxlen = length(split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_025x.REP);
+    maxlen = length(split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_025x.REP);
 
     for i = 1:maxlen
-        split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_025x.REP(i) = ...
+        split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_025x.REP(i) = ...
             {'ALL'};
-        split_tables.drug52_doseResponse.Untreated.all_reps.Untreated_3x.REP(i) = ...
+        split_tables.drug34_doseResponse.Untreated.all_reps.Untreated_3x.REP(i) = ...
             {'ALL'};
 
 

classification_and_analysis/helper/knn_color_setup.m

@@ -12,65 +12,55 @@ map = interp1(vec,raw,linspace(100,0,N),'pchip');
 
 %% Different drug categories
 % put all drug categories in a structure
-% maybe probably do something about the _025x and _3x nonsence 
 all_categories = struct;
 
 % want to also auto add 025x and 3x to each array 
 
 % categories that are the same regardless of large or small group 
 all_categories.rnap = ["RIF","RifT", "OLDRifT","rifapentine","rifampicin","rif6h","rift6h"];
-all_categories.dna = ["Dau","Lev","MIT","Mox","Nal","Olf","Sulf","Nit", "Olfold", "OLDMOX",...
-    "daunorubicin","nalidixic acid","levofloxacin","moxifloxacin","mitomycin",...
-    "ofloxacin","nitrofurantoin","sulfamethizole","mox6h"];
+all_categories.dna = ["Lev","MIT","Mox","Olf","OLDMOX",...
+    "levofloxacin","moxifloxacin","mitomycin",...
+    "ofloxacin","mox6h"];
 
 
 all_categories.control = ["water","Untreated","NaOH","MeOH","EtOH","DMSO"];
 
 all_categories.unknown = ["Unknown2019","Unknown2238","Unknown2239",...
-    "Unknown2911","Unknown3825","Unknown4050","Unknown3285"];
+    "Unknown3825","Unknown3285"];
 
 % different categories depending on fine grouping 
 if large_group
-    all_categories.protein = ["AZT","Amk","Cam","Cla","Dox","Gent","Kan","Lin","Strep","Tet","Tig",...
-        "kanamycin","amikacin","chloramphenicol","azithromycin","clarithromycin",...
+    all_categories.protein = ["Amk","Cam","Cla","Dox","Gent","Kan","Lin","Strep","Tet","Tig",...
+        "kanamycin","amikacin","chloramphenicol","clarithromycin",...
         "doxycycline","gentamicin","streptomycin","tetracycline","tigecycline",...
         "linezolid","lin6h"];
 
     all_categories.lipid = ["Tri","Nis","Nig","Mon","Gra","CCCP","PZA","Clz","BDQ","OLDBDQ", ...
             "OLDPZA","OLDClz","clofazimine","carbonyl cyanide 3-chlorophenylhydrazone",...
             "gramicidin","monensin","nigericin","nisin","triclosan","bedaquiline",...
-            "pyrazinamide","bdq6h","pza6h","clz6h"  ];
+            "pyrazinamide","bdq6h","pza6h","clz6h","Ver","Thi","verapamil","thioridazine" ];
 
-        % if we want to put the efflux acting drugs into the lipid category...
-    if efflux_in_lipid
-       %...append them to the list of lipids 
-        all_categories.lipid = [all_categories.lipid, "Ver","Thi","verapamil","thioridazine"];
     % for simplicity, create a blank efflux array so that efflux still
-        % exists and won't get upset later
+    % exists and won't get upset later -- outdated 
     all_categories.efflux = [""];
-    else
-        % if not, have them be their own separate array
-        all_categories.efflux = ["Ver","Thi","verapamil","thioridazine"];
-    end 
-
     
-    all_categories.cell_wall = ["A22","Amp","Carb","Ctax","Cyc","Del","EMB","ETA",...
-        "IMI","INH","Mer","Oxa","Pip","Pre","Van","THL","Cer",...
-        "PenG","OLDPre","OLDEMB","OLDINH",...
+    all_categories.cell_wall = ["Amp","Ctax","Cyc","Del","EMB","ETA",...
+        "IMI","INH","Mer","Pre","Van","THL","Cer",...
+        "OLDPre","OLDEMB","OLDINH",...
         "ampicillin","cefotaxime","meropenem","isoniazid","ethambutol",...
-        "ethionamide","imipenem","piperacillin","oxacillin","penicillin G",...
-        "vancomycin","cycloserine","carbenicillin","delamanid","pretomanid",...
+        "ethionamide","imipenem",...
+        "vancomycin","cycloserine","delamanid","pretomanid",...
         "cerulenin","emb6h","inh6h","pre6h"];
     %others = ["PZA", "Ver", "Thi", "Clz","BDQ"];
 else 
     % finer settings
-    all_categories.peptidoglycan = ["Mer","Amp","Ctax","IMI","Pip","Oxa","Carb","Van","Cyc","A22",...
-        "meropenem","ampicillin","cefotaxime","imipenem","piperacillin","oxacillin",...
-        "carbenicillin","vancomycin","cycloserine"];
+    all_categories.peptidoglycan = ["Mer","Amp","Ctax","IMI","Van","Cyc",...
+        "meropenem","ampicillin","cefotaxime","imipenem",...
+        "vancomycin","cycloserine"];
     all_categories.mycolic_acid = ["INH","ETA","Del","EMB","Pre","THL","Cer",...
         "isoniazid","ethionamide","ethambutol","delamanid","pretomanid",...
         "cerulenin"];
-    all_categories.s50_subunit = ["AZT","Cla","Cam","Lin"];
+    all_categories.s50_subunit = ["Cla","Cam","Lin"];
     all_categories.s30_subunit = ["Gent","Kan","Amk","Strep","Tet","Dox","Tig"];
     all_categories.atp_synthesis = ["BDQ","CCCP","Clz","Gra","Mon","Nig","Nis","PZA"];
     %efflux = ["Ver","Thi"];

classification_and_analysis/helper/knn_helper.m

@@ -9,9 +9,6 @@
 % large_group - default to true
 % create_graph - default to false
 % create_cm -default to off 
-% would need knn_with_apply - maybe cut that? could make default to false
-% would need tit_add if random - could make default to false 
-% idk this seems like a lot of inputs I don't feel gr8 about it
 
 % outputs would be
 % pct_correct

classification_and_analysis/helper/load_workspaces.m

@@ -14,8 +14,6 @@
 %       on final data table (default: true)
 %   - (OPTIONAL) remove_extra_controls - Will remove:
 %       EtOH, MeOH, NaOH, water (default: true)
-%   - (OPTIONAL) remove_bad_treated - Will remove:
-%       'IMI', 'Nal', 'Nig', 'Dau' (defualt: true)
 %
 %   - (OPTIONAL) workspace_directory - the directory where to look for
 %   workspaces (default: './workspaces')
@@ -34,16 +32,6 @@
 %       - choice_extension - either 'DRUG' or 'DRUG_EXP' depending on var conditions
 %       - choice_variable - a list of either drugs or drug_exps depending on var conditions
 
-%% TODO
-% - Fix AfterTVN in this file and PCA_analysis
-% - Optimize workspace loading (only load final_data_table)
-
-%% Questions
-% - Is it necessary to normalize/zero-mean merged table if going to do so
-%   anyways after drug filtering?
-% - Why add applied drugs back in before tvn?
-% - Is it ok to normalize final_data_table beforehand?
-
 %% Generate defaults
 if ~exist('remove_INH_control', 'var')
     remove_INH_control = true;

classification_and_analysis/helper/merged_table_setup.m

@@ -5,7 +5,7 @@
 %
 % Called when using multiple workspaces in load_workspaces.m
 %
-% DESCRIPTION: - *NO NOT ANYMORE* Calls normalize_and_zero_mean() on final_data table. 
+% DESCRIPTION: -  
 %              - Initializes several variables which describe the data in
 %                the new normalized table. Many of these exist beforehand,
 %                we just need to make sure they reflect the concatenated

classification_and_analysis/helper/new_34drug_joint.m

@@ -25,7 +25,6 @@ if ~exist('bayesian','var')
    bayesian = false; 
 end
 
-% apply on 24hour timepoint workspace
 apply_timepoint_drugs = false; %ALSO MUST COMMENT OUT CLUSTERGRAM SECTION OF PCA_analysis (idk lol it was throwing an error)
 
 do_joint_profile = true;
@@ -127,9 +126,6 @@ end
 
 
 %% Cool table fixes
-% Eventually, you'll probably want to do all these and save them in the
-% workspace
-
 % Set DRUG to drug_dose
 final_data_table_3x.DRUG = strcat(final_data_table_3x.ID, '_3x');
 
@@ -168,7 +164,7 @@ end
 final_data_table = [final_data_table_025x; final_data_table_3x];
 
 % Set the EXP to the same thing so the joint profile allows them to canoodle
-final_data_table.EXP(:) = {'drug52_doseResponse'};
+final_data_table.EXP(:) = {'drug34_doseResponse'};
 %% Strike fear into the eyes of the enemy and only allow those we chose to survive
 
 %Extract only the ids that the two doses have in common

segmentation_pipeline/MicrobeJ_segmentation.m

@@ -1187,10 +1187,7 @@ if FM_tf
     end 
 end 
 
-%% Getting rid of outliers -- still working on best way to do this 
-% some outliers are egregious (ie 15 orders of magnitude too large) but
-% don't want to accidentally destroy something biologically significant
-% also don't have normal distributions -- quite a few lognormal-apparent
+%% Getting rid of outliers 
 
 bad_bac_out = [];
 bad_FM_out = [];
@@ -2245,7 +2242,7 @@ for i = drugs
         stop_point = length(joined_bacteria_groups.(drug));
     end 
 
-    % for following seciton, we used grouped_no_nan for cell workspace and
+    % for following section, we used grouped_no_nan for cell workspace and
     % we use joined for img workspace. Boolean cell_mode is used to get from
     % one to the other. 
     for j = 1:stop_point    
@@ -2440,26 +2437,6 @@ end
 clear num_bacteria_rows num_FM_rows num_syto_rows numeric_avg_bacteria_cols numeric_avg_FM_cols numeric_avg_syto_cols drug_label
 clear new_row bact_row FM_row syto_row
 
-%~~~~~edit ends
-%% *not implemented* Adds ratio of fluorescence area and cell area as another varaible in bacteria file
-%%%%Should be calculated on cell by cell basis, but this works for now
-%{
-for i = drugs
-    drug = i{1};
-    table = all_data.(drug);
-    
-    syto_area_percentage = [];
-    FM_area_percentage = [];
-    
-    for j = 1:size(table,1)
-        syto_area_percentage(j) = table{j, 'SHAPE_area'}/table{j, 's_SHAPE_area'};
-        FM_area_percentage(j) = table{j, 'SHAPE_area'}/table{j, 'f_SHAPE_area'};
-    end
-    
-    %all_data.(drug).syto_area_percentage = 
-end
-%}
-
 %% Merge all tables into big final table
 
 %create table

segmentation_pipeline/config.yml

@@ -3,7 +3,7 @@
 ################################################
 # MICROBEJ SEGMENTATION CONFIGURATION SETTINGS #
 ################################################
-# Contains all the configuration needed for running bcp_MicrobeJ_processing.m
+# Contains all the configuration needed for running MicrobeJ_segmentation.m
 # Save this file as config.yml and place in the root directory of the program
 
 metadata:

segmentation_pipeline/segmentation_functions/printstructfun.m

 function [outputArg1] = printstructfun(x,transverse_file)
-%function previously contained in bcp_MicrobeJ_processing with the addition
+%function previously contained in MicrobeJ_segmentation with the addition
 %of a timing function that gives the time taken to process each drug at
 %what is the longest section of the code