V0.99.5 (#29)

* additional viz tests * fix bar filtering bug * fix filter_to_sig bug and add test * column check in heatmap * fix heatmap bug introduced in last bugfix * update dependencies and fix pca error (coming from r > 3.5?) * fix tabfile bug * rotate x axis text more (more vertical) * fix data frame - probably due to new pandas * pull out obo download links * GeneOntologyDb code rewrites; Check_args fix (#30) * condense ifelse conditional for is_in_db function * fix incorrect filename for tax_check * simplify slim-ancestors loop * filter ontology in barplot * bump version to 0.99.5
galaxyproteomics · Apr 1, 2019 · e35586a · e35586a
2 parents a568978 + d6d5f58
commit e35586a
Show file tree

Hide file tree

Showing 21 changed files with 415 additions and 49 deletions.
diff --git a/.gitignore b/.gitignore
@@ -2,6 +2,9 @@
 metaquantome/data/test/taxa.sqlite
 metaquantome/data/test/taxa.sqlite.traverse.pkl
 
+# sometimes ggplot makes empty Rplots.pdf
+Rplots.pdf
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]

diff --git a/dev_environment.yml b/dev_environment.yml
@@ -5,14 +5,15 @@ channels:
 - conda-forge
 - r
 dependencies:
-- python==3.5.*
-- ete3==3.1.1
-- goatools==0.7.11
-- statsmodels==0.8.0
-- biopython==1.70
+- python>=3
+- ete3==3.1.*
+- goatools==0.7.*
+- statsmodels==0.8.*
+- biopython==1.73.*
 - pandas==0.23.*
-- r-gplots==3.0.1
-- r-ggplot2
-- r-base==3.4.*
-- r-jsonlite=1.5
-- libiconv
+- numpy 1.15.*
+- r-gplots==3.0.*
+- r-ggplot2==3.0.*
+- r-base==3.5.1
+- r-jsonlite=1.5.*
+- libiconv 1.15.*
diff --git a/metaquantome/cli.py b/metaquantome/cli.py
@@ -54,13 +54,15 @@ def cli():
                 flip_fc=args.flip_fc,
                 gosplit=args.gosplit,
                 sinfo=args.samps,
+                filter_to_sig=args.filter_to_sig,
                 alpha=args.alpha,
                 whichway=args.whichway,
                 name=args.name,
                 id=args.id,
                 target_onto=args.target_onto,
                 width=args.width,
-                height=args.height)
+                height=args.height,
+                tabfile=args.tabfile)
     else:
         ValueError('incorrect mode. please provide one of "db", "expand", "filter", "stat", or "viz".')
     sys.exit(0)
@@ -242,6 +244,9 @@ def parse_args_cli():
                           ' heatmap and PCA plot, so the colors can be tweaked to match. ')
     bar.add_argument('--target_rank',
                      help="(Tax bar and FT dist). Taxonomic rank to restrict to in the plot. ")
+    bar.add_argument('--target_onto', choices=["mf", "bp", "cc"],
+                     help="(Function and FT dist bar only) " +
+                          "Ontology to restrict to, for function distribution.")
     bar.add_argument("--whichway", choices=["f_dist", "t_dist"],
                      help="(FT dist only) " +
                           "Which distribution - functional distribution for a taxon (f_dist) or " +
@@ -252,9 +257,6 @@ def parse_args_cli():
     bar.add_argument("--id",
                      help="(FT dist bar only) " +
                           "Taxonomic or functional term id - either a NCBI taxID or a GO term id (GO:XXXXXXX)")
-    bar.add_argument('--target_onto', choices=["mf", "bp", "cc"],
-                     help="(FT dist bar only) " +
-                          "Ontology to restrict to, for function distribution.")
 
     volc = parser_viz.add_argument_group('Volcano Plot')
     volc.add_argument('--fc_name',

diff --git a/metaquantome/data/test/cli_bar_viz.png b/metaquantome/data/test/cli_bar_viz.png
diff --git a/metaquantome/data/test/cli_bar_viz2.png b/metaquantome/data/test/cli_bar_viz2.png
diff --git a/metaquantome/data/test/cli_heatmap_viz.png b/metaquantome/data/test/cli_heatmap_viz.png
diff --git a/metaquantome/data/test/cli_pca_viz.png b/metaquantome/data/test/cli_pca_viz.png
diff --git a/metaquantome/data/test/eggnog_out.tab b/metaquantome/data/test/eggnog_out.tab
diff --git a/metaquantome/data/test/eggnog_viz_file.tab b/metaquantome/data/test/eggnog_viz_file.tab
@@ -0,0 +1,21 @@
+id	name	namespace	NS_mean	WS_mean	int737NS	int737WS	int852NS	int852WS	int867NS	int867WS	int737NS_n_peptide	int737WS_n_peptide	int852NS_n_peptide	int852WS_n_peptide	int867NS_n_peptide	int867WS_n_peptide	int737NS_n_samp_children	int737WS_n_samp_children	int852NS_n_samp_children	int852WS_n_samp_children	int867NS_n_samp_children	int867WS_n_samp_children
+GO:0008152	metabolic process	biological_process	9707895600.63897	34.4676527340745	32.7280807192344	33.639915914834	33.8500846328958	35.3680642871384	32.6033492340827	33.6566592988174	1837	1837	1837	1837	1837	1837	3	3	3	3	3	3
+GO:0009058	biosynthetic process	biological_process	3977879569.3907	33.2068587142223	31.5038426691202	32.3344633958136	32.5457060492145	34.154051958603	31.2863832807592	32.2790138218569	576	576	576	576	576	576	NA	NA	NA	NA	NA	NA
+GO:0006807	nitrogen compound metabolic process	biological_process	3333526855.75693	33.089118314848	31.3274682605914	32.2651614156765	32.2393712217206	33.9854328532233	31.0581331702586	32.2877493545852	763	763	763	763	763	763	NA	NA	NA	NA	NA	NA
+GO:0006412	translation	biological_process	2440026495.81359	32.4930473371394	30.8105936229541	31.6128211401251	31.846608199857	33.4455891939318	30.5527566639519	31.5536159837728	336	336	336	336	336	336	NA	NA	NA	NA	NA	NA
+GO:0006950	response to stress	biological_process	1052880100.76931	31.3981405492947	29.6095404092094	30.439676321524	30.5689283794754	32.393517103388	29.4759257423614	30.3742688501823	124	124	124	124	124	124	NA	NA	NA	NA	NA	NA
+GO:0042221	response to chemical	biological_process	965521061.018174	30.8296096443541	29.4808523042029	29.9278611878217	30.4629201331805	31.8156195431379	29.3138771113971	29.7828763814873	85	85	85	85	85	85	NA	NA	NA	NA	NA	NA
+GO:0044710	metabolic process	biological_process	928705245.346089	30.6072989115392	29.3036916765872	30.0343848802313	30.4615672319471	31.2433837819293	29.2644431642638	30.237026652397	225	225	225	225	225	225	3	3	3	3	3	3
+GO:0071840	cellular component organization or biogenesis	biological_process	833223817.553338	31.5724843198215	29.5524724554893	31.0024286599174	30.1336470253456	32.3466932720115	28.99316994804	30.8738545987975	357	357	357	357	357	357	NA	NA	NA	NA	NA	NA
+GO:0005975	carbohydrate metabolic process	biological_process	379644473.58704	30.2823742633555	27.4581777552516	28.9388737660123	29.2889137336267	31.4249235572303	28.1538245092415	28.9540435785897	76	76	76	76	76	76	NA	NA	NA	NA	NA	NA
+GO:0006091	generation of precursor metabolites and energy	biological_process	373375658.545852	27.5844108414961	26.7198540418534	27.2161871812721	29.5462583955409	27.603990048666	27.749246320597	27.8613248072876	30	30	30	30	30	30	NA	NA	NA	NA	NA	NA
+GO:0006629	lipid metabolic process	biological_process	346873604.466979	28.4302522117954	27.5680638918355	28.0217901314741	29.1700984804642	28.9561582409451	27.8238760468995	28.120421411102	37	37	37	37	37	37	NA	NA	NA	NA	NA	NA
+GO:0065003	protein-containing complex assembly	biological_process	223362430.986751	29.4067502060857	27.7185066355636	29.0195327862999	28.1835372517938	30.0898188984621	27.1053181932927	28.7398209542951	83	83	83	83	83	83	NA	NA	NA	NA	NA	NA
+GO:0044711	biosynthetic process	biological_process	220756695.513963	28.7739551105881	27.1093723370704	28.4003539740075	28.4104810597675	29.3934280879723	27.2597605688579	28.2424502003084	53	53	53	53	53	53	NA	NA	NA	NA	NA	NA
+GO:0044723	carbohydrate metabolic process	biological_process	182807836.125096	28.93667511454	26.448399628704	27.9008315674069	28.2396393635986	29.9843751125869	27.0599307314212	27.7686749761679	34	34	34	34	34	34	NA	NA	NA	NA	NA	NA
+GO:0019222	regulation of metabolic process	biological_process	173056856.95311	28.9389001060965	27.0494629499546	28.2721701007768	27.836284601413	29.6501969737214	27.0673584710354	28.4903755600971	69	69	69	69	69	69	NA	NA	NA	NA	NA	NA
+GO:0006810	transport	biological_process	140537615.614438	28.7939728267842	27.1234873806423	27.9615606778428	27.4144285386699	29.5408914880366	26.524314216561	28.3984348617235	88	88	88	88	88	88	NA	NA	NA	NA	NA	NA
+GO:0016032	viral process	biological_process	111058995.875521	30.4491645013834	26.3289762021563	29.2487087831025	27.1434558706649	31.5367058114516	26.5844879797392	29.263908857592	48	48	48	48	48	48	NA	NA	NA	NA	NA	NA
+GO:0016070	RNA metabolic process	biological_process	91888884.7293597	28.1369040778828	26.1677866053689	27.693875726079	26.8519757597805	28.5989127651248	26.2381122887607	27.9638332212402	81	81	81	81	81	81	NA	NA	NA	NA	NA	NA
+GO:0006461	protein-containing complex assembly	biological_process	88525220.719722	27.5427325704944	26.2738037562703	27.2967939297801	27.0298059946766	27.9798815285066	25.4990572646483	27.2258576018008	40	40	40	40	40	40	NA	NA	NA	NA	NA	NA
+GO:0006457	protein folding	biological_process	75079182.3365918	29.268835134676	25.7050718748645	28.2845189662675	26.7348727386628	30.2745828042056	25.8105457595204	28.2294977490008	32	32	32	32	32	32	NA	NA	NA	NA	NA	NA
diff --git a/metaquantome/data/test/rudney_samples.tab b/metaquantome/data/test/rudney_samples.tab
@@ -0,0 +1,3 @@
+group	colnames
+NS	X730NS,X733NS,X734NS,X737NS,X760NS,X769NS,X781NS,X795NS,X852NS,X861NS,X866NS,X867NS
+WS	X730WS,X733WS,X734WS,X737WS,X760WS,X769WS,X781WS,X795WS,X852WS,X861WS,X866WS,X867WS