Merge pull request #3 from eweitz/continuous-integration

Add continuous integration

.circleci/config.yml

@@ -0,0 +1,41 @@
+# Python CircleCI 2.0 configuration file
+#
+# Check https://circleci.com/docs/2.0/language-python/ for more details
+#
+version: 2.1
+
+jobs:
+  build:
+    docker:
+      - image: circleci/python:3.7.5-stretch
+
+    working_directory: ~/degenome
+
+    steps:
+      - checkout
+
+      # Download and cache dependencies
+      - restore_cache:
+          keys:
+            - v3-dependencies-{{ checksum "requirements.txt" }}
+            # fallback to using the latest cache if no exact match is found
+            - v3-dependencies-
+
+      - run:
+          name: Install Python dependencies
+          command: |
+            python3 -m venv venv
+            . venv/bin/activate
+            pip install -r requirements.txt
+
+      - save_cache:
+          paths:
+            - ./venv
+          key: v3-dependencies-{{ checksum "requirements.txt" }}
+
+      - run:
+          name: Run tests
+          command: |
+            . venv/bin/activate
+            cd tests
+            pytest

.gitignore

@@ -3,8 +3,8 @@ env
 __pycache__
 
 # Ignore app-specific miscellanea
-*.gen_pos.tsv
 sampled_GLDS*json
 
 # Ignore macOS miscellanea
 .DS_Store
+.vscode

README.rst

@@ -1,9 +1,12 @@
 DEGenome – Differential expression of the genome
 ================================================
+|Build|
 
 DEGenome transforms differential gene expression (DGE) data to Ideogram_ JSON.
 
 For more details, `read the docs`_!
 
+.. |Build| image:: https://img.shields.io/circleci/build/github/eweitz/degenome.svg
+  :target: https://circleci.com/gh/eweitz/degenome
 .. _Ideogram: https://github.com/eweitz/ideogram
 .. _read the docs: https://degenome.readthedocs.io

degenome/dge_to_ideogram.py

@@ -112,6 +112,8 @@ def parse_dge_matrix(dge_matrix_path):
         reader = csv.reader(f)
 
         headers = next(reader, None)
+        print('headers')
+        print(headers)
         metadata_keys = [headers[2], headers[4]] # GENENAME, ENTREZID
 
         comparisons_by_group = get_comparisons(headers)

docs/_build/html/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: fab0cd7db8c71b3156c3d61df2acb437
+config: 479bdea2a5cc6824685e8eade7ac6a25
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/_build/html/_sources/index.rst.txt

@@ -1,5 +1,6 @@
 DEGenome – Differential expression of the genome
 ================================================
+|Build|
 
 DEGenome transforms differential gene expression (DGE) data to Ideogram_ JSON.
 
@@ -12,6 +13,9 @@ https://eweitz.github.io/ideogram/differential-expression.
 
 .. _Ideogram: https://github.com/eweitz/ideogram
 
+.. |Build| image:: https://img.shields.io/circleci/build/github/eweitz/degenome.svg
+  :target: https://circleci.com/gh/eweitz/degenome
+
 .. image:: images/explore_differential_expression_across_the_genome.png
   :width: 600
   :alt: Explore differential expression across the genome

docs/_build/html/index.html

@@ -147,6 +147,7 @@
 
   <div class="section" id="degenome-differential-expression-of-the-genome">
 <h1>DEGenome – Differential expression of the genome<a class="headerlink" href="#degenome-differential-expression-of-the-genome" title="Permalink to this headline">¶</a></h1>
+<p><a class="reference external" href="https://circleci.com/gh/eweitz/degenome"><img alt="Build" src="https://img.shields.io/circleci/build/github/eweitz/degenome.svg" /></a></p>
 <p>DEGenome transforms differential gene expression (DGE) data to <a class="reference external" href="https://github.com/eweitz/ideogram">Ideogram</a> JSON.</p>
 <p>Written in Python, the DEGenome pipeline takes in genome annotations and DGE
 matrices, and outputs Ideogram.js JSON annotation files.</p>

docs/_build/html/installation.html

@@ -35,7 +35,7 @@
   <link rel="stylesheet" href="_static/pygments.css" type="text/css" />
     <link rel="index" title="Index" href="genindex.html" />
     <link rel="search" title="Search" href="search.html" />
-    <link rel="prev" title="DEGenome – Differential expression across the genome" href="index.html" /> 
+    <link rel="prev" title="DEGenome – Differential expression of the genome" href="index.html" /> 
 </head>
 
 <body class="wy-body-for-nav">
@@ -162,7 +162,7 @@ <h1>Installation<a class="headerlink" href="#installation" title="Permalink to t
     <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
 
 
-        <a href="index.html" class="btn btn-neutral float-left" title="DEGenome – Differential expression across the genome" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
+        <a href="index.html" class="btn btn-neutral float-left" title="DEGenome – Differential expression of the genome" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
 
     </div>
 

docs/conf.py

@@ -56,4 +56,4 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = []

docs/index.rst

@@ -1,5 +1,6 @@
 DEGenome – Differential expression of the genome
 ================================================
+|Build|
 
 DEGenome transforms differential gene expression (DGE) data to Ideogram_ JSON.
 
@@ -12,6 +13,9 @@ https://eweitz.github.io/ideogram/differential-expression.
 
 .. _Ideogram: https://github.com/eweitz/ideogram
 
+.. |Build| image:: https://img.shields.io/circleci/build/github/eweitz/degenome.svg
+  :target: https://circleci.com/gh/eweitz/degenome
+
 .. image:: images/explore_differential_expression_across_the_genome.png
   :width: 600
   :alt: Explore differential expression across the genome

requirements.txt

@@ -1 +1,3 @@
-pytest==5.3.2
+pytest==5.3.2
+sphinx==2.3.1
+sphinx-rtd-theme==0.4.3

tests/data/Mus_musculus.gen_pos.tsv

@@ -0,0 +1,188 @@
+# Organism: Mus musculus; assembly: GRCm38; annotation: GENCODE sampled_gencode.vM23.basic.annotation.gtf.gz
+# Gene_ID	Gene_symbol	Chromosome	Start	End	Gene_type
+ENSMUSG00000102693.1	4933401J01Rik	1	3073253	3074322	TEC
+ENSMUSG00000064842.1	Gm26206	1	3102016	3102125	snRNA
+ENSMUSG00000051951.5	Xkr4	1	3205901	3671498	protein_coding
+ENSMUSG00000102851.1	Gm18956	1	3252757	3253236	processed_pseudogene
+ENSMUSG00000103377.1	Gm37180	1	3365731	3368549	TEC
+ENSMUSG00000104017.1	Gm37363	1	3375556	3377788	TEC
+ENSMUSG00000103025.1	Gm37686	1	3464977	3467285	TEC
+ENSMUSG00000089699.1	Gm1992	1	3466587	3513553	lncRNA
+ENSMUSG00000103201.1	Gm37329	1	3512451	3514507	TEC
+ENSMUSG00000103147.1	Gm7341	1	3531795	3532720	processed_pseudogene
+ENSMUSG00000103161.1	Gm38148	1	3592892	3595903	TEC
+ENSMUSG00000102331.1	Gm19938	1	3647309	3658904	lncRNA
+ENSMUSG00000102348.1	Gm10568	1	3680155	3681788	TEC
+ENSMUSG00000102592.1	Gm38385	1	3752010	3754360	TEC
+ENSMUSG00000088333.2	Gm27396	1	3783876	3783933	snRNA
+ENSMUSG00000102343.1	Gm37381	1	3905739	3986215	lncRNA
+ENSMUSG00000025900.12	Rp1	1	3999557	4409241	protein_coding
+ENSMUSG00000102948.1	Gm6101	1	4256234	4260519	processed_pseudogene
+ENSMUSG00000104123.1	Gm37483	1	4363346	4364829	TEC
+ENSMUSG00000025902.13	Sox17	1	4490931	4497354	protein_coding
+ENSMUSG00000104238.1	Gm37587	1	4496551	4499558	lncRNA
+ENSMUSG00000102269.1	Gm7357	1	4522905	4526737	processed_pseudogene
+ENSMUSG00000096126.1	Gm22307	1	4529017	4529123	snRNA
+ENSMUSG00000103003.1	Gm38076	1	4534837	4535286	processed_pseudogene
+ENSMUSG00000104328.1	Gm37323	1	4583129	4586252	lncRNA
+ENSMUSG00000102735.1	Gm7369	1	4610471	4611406	processed_pseudogene
+ENSMUSG00000098104.1	Gm6085	1	4687934	4689403	processed_pseudogene
+ENSMUSG00000102175.1	Gm6119	1	4692219	4693424	processed_pseudogene
+ENSMUSG00000088000.1	Gm25493	1	4723277	4723379	snRNA
+ENSMUSG00000103265.1	Gm2053	1	4735046	4735676	processed_pseudogene
+ENSMUSG00000103922.1	Gm6123	1	4771131	4772199	processed_pseudogene
+ENSMUSG00000033845.13	Mrpl15	1	4773206	4785739	protein_coding
+ENSMUSG00000102275.1	Gm37144	1	4778063	4779212	TEC
+ENSMUSG00000025903.14	Lypla1	1	4807788	4848410	protein_coding
+ENSMUSG00000104217.1	Gm37988	1	4807892	4886770	protein_coding
+ENSMUSG00000033813.15	Tcea1	1	4857814	4897909	protein_coding
+ENSMUSG00000062588.4	Gm6104	1	4880049	4880651	processed_pseudogene
+ENSMUSG00000103280.1	Gm37277	1	4905751	4906861	TEC
+ENSMUSG00000002459.17	Rgs20	1	4909576	5070285	protein_coding
+ENSMUSG00000103120.1	Gm37392	2	3065573	3066088	processed_pseudogene
+ENSMUSG00000099154.1	Gm27306	2	3075107	3075213	miRNA
+ENSMUSG00000050530.14	Fam171a1	2	3114224	3227806	protein_coding
+ENSMUSG00000026643.16	Nmt2	2	3284212	3328877	protein_coding
+ENSMUSG00000075837.1	Gm22005	2	3291378	3291518	snRNA
+ENSMUSG00000049950.6	Rpp38	2	3328949	3332643	protein_coding
+ENSMUSG00000026644.7	Acbd7	2	3336168	3340993	protein_coding
+ENSMUSG00000026645.11	Olah	2	3341982	3397210	protein_coding
+ENSMUSG00000103786.1	Gm37525	2	3351134	3354004	lncRNA
+ENSMUSG00000026650.15	Meig1	2	3409043	3422648	protein_coding
+ENSMUSG00000026648.18	Dclre1c	2	3424131	3464130	protein_coding
+ENSMUSG00000026646.16	Suv39h2	2	3455815	3475031	protein_coding
+ENSMUSG00000110943.1	Gm30674	10	3104119	3104849	processed_pseudogene
+ENSMUSG00000111106.1	Gm3318	10	3117805	3118987	processed_pseudogene
+ENSMUSG00000071434.2	9230019H11Rik	10	3119841	3129546	lncRNA
+ENSMUSG00000110909.1	B020014A21Rik	10	3125091	3133193	lncRNA
+ENSMUSG00000111242.1	Gm8155	10	3139447	3141058	processed_pseudogene
+ENSMUSG00000111625.1	Gm48097	10	3176020	3176188	processed_pseudogene
+ENSMUSG00000110787.1	Gm6667	10	3212803	3235033	unprocessed_pseudogene
+ENSMUSG00000091618.3	H60c	10	3256208	3267771	protein_coding
+ENSMUSG00000111114.1	Gm18703	10	3303049	3303381	processed_pseudogene
+ENSMUSG00000040653.6	Ppp1r14c	10	3366057	3464975	protein_coding
+ENSMUSG00000080655.1	Gm24482	10	3425023	3425115	miRNA
+ENSMUSG00000019762.4	Iyd	10	3540240	3554877	protein_coding
+ENSMUSG00000040624.18	Plekhg1	10	3740364	3967303	protein_coding
+ENSMUSG00000082123.1	Gm16149	10	3869299	3869607	processed_pseudogene
+ENSMUSG00000089392.1	Gm23023	10	3934769	3934877	rRNA
+ENSMUSG00000082605.1	Gm16148	10	3946199	3947091	processed_pseudogene
+ENSMUSG00000040675.17	Mthfd1l	10	3973118	4167081	protein_coding
+ENSMUSG00000082247.1	Gm16074	10	3992371	3992814	processed_pseudogene
+ENSMUSG00000065792.1	Gm25515	10	4104313	4104469	snRNA
+ENSMUSG00000089473.1	Gm25369	10	4169887	4170018	snoRNA
+ENSMUSG00000111266.1	Gm30570	10	4206426	4213114	lncRNA
+ENSMUSG00000038587.9	Akap12	10	4266380	4359470	protein_coding
+ENSMUSG00000075327.10	Zbtb2	10	4367075	4388108	protein_coding
+ENSMUSG00000095123.1	Gm21781	10	4391587	4396424	lncRNA
+ENSMUSG00000019763.11	Rmnd1	10	4401915	4432388	protein_coding
+ENSMUSG00000100969.7	1700030N03Rik	19	3053071	3197732	lncRNA
+ENSMUSG00000117761.1	Gm50428	19	3134645	3134959	IG_V_pseudogene
+ENSMUSG00000093983.1	Gm25431	19	3136984	3137090	snRNA
+ENSMUSG00000118182.1	Gm50427	19	3142760	3143065	IG_V_pseudogene
+ENSMUSG00000117928.1	Gm42068	19	3156623	3157012	processed_pseudogene
+ENSMUSG00000118393.1	Gm50426	19	3184959	3185273	IG_V_pseudogene
+ENSMUSG00000118052.1	Gm50432	19	3205607	3206258	transcribed_processed_pseudogene
+ENSMUSG00000118203.1	Gm7798	19	3248804	3250214	processed_pseudogene
+ENSMUSG00000117886.1	Gm2106	19	3253518	3255067	processed_pseudogene
+ENSMUSG00000024831.14	Ighmbp2	19	3259076	3283017	protein_coding
+ENSMUSG00000024829.12	Mrpl21	19	3282901	3292837	protein_coding
+ENSMUSG00000099261.1	Mir6984	19	3288920	3288983	miRNA
+ENSMUSG00000118213.1	Gm50307	19	3316782	3317581	processed_pseudogene
+ENSMUSG00000024900.5	Cpt1a	19	3322334	3385733	protein_coding
+ENSMUSG00000024905.15	Tesmin	19	3388857	3407823	protein_coding
+ENSMUSG00000024907.7	Gal	19	3409915	3414544	protein_coding
+ENSMUSG00000024908.15	Ppp6r3	19	3454928	3575749	protein_coding
+ENSMUSG00000114315.1	Gm48696	19	3486090	3488014	lncRNA
+ENSMUSG00000075908.1	Gm23940	19	3490309	3490413	snRNA
+ENSMUSG00000114302.1	Gm48683	19	3527104	3528613	lncRNA
+ENSMUSG00000024913.16	Lrp5	19	3584828	3686564	protein_coding
+ENSMUSG00000100249.1	Btbd35f23	X	3076875	3078817	protein_coding
+ENSMUSG00000096426.2	Btbd35f24	X	3193887	3195827	protein_coding
+ENSMUSG00000084298.1	Gm14331	X	3225600	3230364	processed_pseudogene
+ENSMUSG00000095907.2	Gm14333	X	3231695	3231958	processed_pseudogene
+ENSMUSG00000080876.3	Gm14332	X	3276856	3278543	processed_pseudogene
+ENSMUSG00000083144.1	Gm14334	X	3328043	3328735	processed_pseudogene
+ENSMUSG00000083918.1	Gm14352	X	3404837	3405285	processed_pseudogene
+ENSMUSG00000094558.1	Btbd35f11	X	3441731	3443690	protein_coding
+ENSMUSG00000081589.1	Gm14353	X	3446558	3447426	processed_pseudogene
+ENSMUSG00000082167.1	Gm14360	X	3484012	3486883	processed_pseudogene
+ENSMUSG00000095492.1	Gm14361	X	3696491	3697358	processed_pseudogene
+ENSMUSG00000094876.1	Btbd35f18	X	3700233	3702192	protein_coding
+ENSMUSG00000095716.1	Btbd35f10	X	3750934	3752885	protein_coding
+ENSMUSG00000095259.1	Gm14357	X	3755775	3756642	processed_pseudogene
+ENSMUSG00000082025.1	Gm14359	X	3779668	3785511	processed_pseudogene
+ENSMUSG00000096524.1	Gm14355	X	3786827	3787090	processed_pseudogene
+ENSMUSG00000080300.4	Spin2-ps1	X	3835901	3837534	processed_pseudogene
+ENSMUSG00000101381.1	Btbd35f16	X	3955054	3957002	protein_coding
+ENSMUSG00000094725.1	Gm15251	X	3959863	3960745	processed_pseudogene
+ENSMUSG00000096733.1	Gm15257	X	4033924	4034806	processed_pseudogene
+ENSMUSG00000078218.2	Btbd35f3	X	4037674	4039616	protein_coding
+ENSMUSG00000085978.1	Gm15258	X	4075022	4075762	processed_pseudogene
+ENSMUSG00000080299.2	Gm14350	X	4076625	4077264	processed_pseudogene
+ENSMUSG00000084955.1	Gm14349	X	4118240	4119931	processed_pseudogene
+ENSMUSG00000082081.1	Gm14358	X	4143537	4146415	processed_pseudogene
+ENSMUSG00000093977.1	Gm14362	X	4147732	4148004	processed_pseudogene
+ENSMUSG00000082489.1	Gm14356	X	4192857	4193725	processed_pseudogene
+ENSMUSG00000094307.1	Btbd35f28	X	4196576	4198535	protein_coding
+ENSMUSG00000094596.1	Btbd35f20	X	4289286	4291245	protein_coding
+ENSMUSG00000094240.1	Gm14348	X	4294124	4294991	processed_pseudogene
+ENSMUSG00000085775.1	Gm14364	X	4339453	4339719	processed_pseudogene
+ENSMUSG00000085966.1	Gm14368	X	4341036	4343915	processed_pseudogene
+ENSMUSG00000095411.1	Gm15260	X	4366897	4367779	processed_pseudogene
+ENSMUSG00000094273.1	Btbd35f17	X	4370636	4372595	protein_coding
+ENSMUSG00000094794.1	Gm6019	X	4409511	4410246	processed_pseudogene
+ENSMUSG00000080073.2	Gm9427	X	4455353	4456003	processed_pseudogene
+ENSMUSG00000094323.1	Gm15256	X	4511847	4512729	processed_pseudogene
+ENSMUSG00000078214.5	Gm5925	X	4515674	4517170	processed_pseudogene
+ENSMUSG00000096800.1	Gm4725	X	4553787	4554373	processed_pseudogene
+ENSMUSG00000085686.1	Gm9498	X	4770778	4771068	processed_pseudogene
+ENSMUSG00000095657.1	Gm15252	X	4796663	4797545	processed_pseudogene
+ENSMUSG00000078213.3	Btbd35f4	X	4800496	4801986	protein_coding
+ENSMUSG00000094693.1	Gm4726	X	4839207	4839942	processed_pseudogene
+ENSMUSG00000078212.4	Gm3757	X	4882412	4883086	processed_pseudogene
+ENSMUSG00000086497.1	Gm15259	X	4905423	4905713	processed_pseudogene
+ENSMUSG00000095436.1	Gm15254	X	4906982	4907254	processed_pseudogene
+ENSMUSG00000094860.1	Btbd35f27	X	4952135	4954077	protein_coding
+ENSMUSG00000094358.1	Gm14370	X	5144852	5145719	processed_pseudogene
+ENSMUSG00000080792.1	Gm14367	X	5148676	5150172	unprocessed_pseudogene
+ENSMUSG00000094401.1	Gm14365	X	5193483	5194069	processed_pseudogene
+ENSMUSG00000085706.1	Gm9428	X	5276735	5278427	processed_pseudogene
+ENSMUSG00000078210.3	Gm5924	X	5338792	5340451	processed_pseudogene
+ENSMUSG00000081626.3	Gm14369	X	5391640	5391924	processed_pseudogene
+ENSMUSG00000082975.1	Gm14363	X	5399249	5402129	processed_pseudogene
+ENSMUSG00000044597.4	Mycs	X	5466898	5469265	protein_coding
+ENSMUSG00000082326.1	Gm14366	X	5608572	5610867	processed_pseudogene
+ENSMUSG00000082270.1	Gm14375	X	5665372	5666226	processed_pseudogene
+ENSMUSG00000095814.1	Btbd35f7	X	5669067	5671026	protein_coding
+ENSMUSG00000081232.3	Gm14373	X	5699727	5701884	processed_pseudogene
+ENSMUSG00000081486.1	Gm14452	X	5859717	5861540	processed_pseudogene
+ENSMUSG00000083939.1	Gm14451	X	5869686	5871506	processed_pseudogene
+ENSMUSG00000080186.2	Gm14448	X	5885743	5885952	processed_pseudogene
+ENSMUSG00000081661.1	Gm14450	X	5984772	5985011	processed_pseudogene
+ENSMUSG00000097342.1	Gm26618	X	6027056	6092269	lncRNA
+ENSMUSG00000073295.4	Nudt11	X	6047453	6055110	protein_coding
+ENSMUSG00000082109.1	Rpl19-ps12	X	6071222	6071812	processed_pseudogene
+ENSMUSG00000099018.1	Gm27360	X	6071478	6071557	miRNA
+ENSMUSG00000073294.4	AU022751	X	6081219	6083419	protein_coding
+ENSMUSG00000075918.1	n-R5s2	X	6106891	6107009	rRNA
+ENSMUSG00000073293.4	Nudt10	X	6168696	6173015	protein_coding
+ENSMUSG00000023279.7	Bmp15	X	6314107	6320721	protein_coding
+ENSMUSG00000068270.15	Shroom4	X	6399854	6637448	protein_coding
+ENSMUSG00000062393.13	Dgkk	X	6779306	6948363	protein_coding
+ENSMUSG00000051592.14	Ccnb3	X	6979652	7041619	protein_coding
+ENSMUSG00000101796.1	Gm29277	Y	206151	207788	lncRNA
+ENSMUSG00000101492.1	Gm29089	Y	321659	323295	lncRNA
+ENSMUSG00000100968.1	Gm2098	Y	670179	695777	unprocessed_pseudogene
+ENSMUSG00000053211.10	Zfy1	Y	725128	797409	protein_coding
+ENSMUSG00000069053.11	Uba1y	Y	818649	844224	protein_coding
+ENSMUSG00000101036.1	Gm28588	Y	841783	847750	lncRNA
+ENSMUSG00000101107.1	Gm28587	Y	869709	873309	lncRNA
+ENSMUSG00000101666.1	Rhoay-ps3	Y	873640	874215	processed_pseudogene
+ENSMUSG00000056673.14	Kdm5d	Y	897788	956786	protein_coding
+ENSMUSG00000075874.1	n-R5s1	Y	991630	991748	rRNA
+ENSMUSG00000106618.1	Gm47281	Y	991657	991716	miRNA
+ENSMUSG00000069049.11	Eif2s3y	Y	1010543	1028847	protein_coding
+ENSMUSG00000099876.1	Gm29650	Y	1048393	1049134	lncRNA
+ENSMUSG00000091749.7	Tspy-ps	Y	1055764	1058868	transcribed_unprocessed_pseudogene
+ENSMUSG00000068457.14	Uty	Y	1096861	1245759	protein_coding