Merge branch 'master' of https://github.com/kundajelab/simdna

kundajelab · Apr 23, 2018 · 65b0d59 · 65b0d59
2 parents 64eecf6 + a6f0bd0
commit 65b0d59
Show file tree

Hide file tree

Showing 12 changed files with 29 additions and 9 deletions.
diff --git a/.gitignore b/.gitignore
@@ -2,3 +2,5 @@
 **/*.bat
 **/*.DS_Store
 simdna.egg-info/*
+build
+dist
diff --git a/.travis.yml b/.travis.yml
@@ -24,4 +24,10 @@ install:
   - pip install .
 
 # run a simulation from simulations.py
-script: python -c 'from simdna.simulations import simulate_single_motif_detection; sequences, labels, embedding_arr = simulate_single_motif_detection("SPI1_disc1", 20, 500, 500, 0.4)'
+script: python -c 'from simdna.simulations import simulate_single_motif_detection; sequences, labels, embedding_arr = simulate_single_motif_detection("SPI1_disc1", 20, 500, 500, 0.4)' || true
+
+deploy:
+  provider: pypi
+  user: "lilleswing"
+  password:
+    secure: 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
diff --git a/MANIFEST.in b/MANIFEST.in
@@ -0,0 +1,2 @@
+include simdna/resources/*.gz
+LICENSE
diff --git a/README.md b/README.md
@@ -1,5 +1,5 @@
-# [simdna: simulations of DNA](https://kundajelab.github.io/simdna/)
-[![license](https://img.shields.io/github/license/mashape/apistatus.svg?maxAge=2592000)](https://github.com/kundajelab/simdna/blob/master/LICENSE)
+# [simdna: simulated datasets of DNA](https://kundajelab.github.io/simdna/)
+[![license](https://img.shields.io/github/license/mashape/apistatus.svg?maxAge=2592000)](https://github.com/kundajelab/simdna/blob/master/LICENSE)[![PyPI version](https://badge.fury.io/py/simdna.svg)](https://badge.fury.io/py/simdna)
 
 ## Installation
 ```

diff --git a/scripts/emptyBackground.py b/scripts/emptyBackground.py
@@ -7,6 +7,7 @@
 
 def do(options):
     outputFileName_core = util.addArguments("EmptyBackground", [
+                                                 util.ArgumentToAdd(options.prefix, "prefix"),
                                                  util.ArgumentToAdd(options.seqLength, "seqLength")
                                                  ,util.ArgumentToAdd(options.numSeqs, "numSeqs")
                                                  ])
@@ -15,10 +16,12 @@ def do(options):
         , embedders=[]
     );
     sequenceSet = sn.GenerateSequenceNTimes(embedInBackground, options.numSeqs)
-    sn.printSequences(outputFileName_core+".simdata", sequenceSet, includeFasta=True, includeEmbeddings=True)
+    sn.printSequences(outputFileName_core+".simdata", sequenceSet, includeFasta=True, includeEmbeddings=True,
+                      prefix=options.prefix)
 
 if __name__=="__main__":
     parser = argparse.ArgumentParser();
+    parser.add_argument("--prefix")
     parser.add_argument("--seqLength", type=int, required=True)
     parser.add_argument("--numSeqs", type=int, required=True)
     options = parser.parse_args()

diff --git a/scripts/motifGrammarSimulation.py b/scripts/motifGrammarSimulation.py
@@ -25,7 +25,7 @@ def motifGrammarSimulation(options):
     seqLength = options.seqLength
     numSeq = options.numSeq
     generationSetting = options.generationSetting
-    outputFileName = "motifGrammarSimulation_"+generationSetting+("_bestHit" if bestHit else "")
+    outputFileName = "motifGrammarSimulation_"+("prefix-"+options.prefix+"_" if options.prefix is not None else "")+generationSetting+("_bestHit" if bestHit else "")
     if (generationSetting is not generationSettings.singleMotif2):
         outputFileName+="_motif1-"+motifName1
     if (generationSetting is not generationSettings.singleMotif1):
@@ -89,11 +89,13 @@ def motifGrammarSimulation(options):
 
     sequenceSet = synthetic.GenerateSequenceNTimes(embedInBackground, numSeq)
     synthetic.printSequences(outputFileName, sequenceSet,
-                             includeFasta=True, includeEmbeddings=True)
+                             includeFasta=True, includeEmbeddings=True,
+                             prefix=options.prefix)
 
 if __name__ == "__main__":
     import argparse
     parser = argparse.ArgumentParser()
+    parser.add_argument("--prefix")
     parser.add_argument("--pathToMotifs",
         default=simdna.ENCODE_MOTIFS_PATH)
     parser.add_argument("--motifName1", required=True)

diff --git a/scripts_test/test_empty_background_script.sh b/scripts_test/test_empty_background_script.sh
@@ -1,3 +1,3 @@
 #!/usr/bin/env bash
 
-emptyBackground.py --seqLength 200 --numSeqs 10
+emptyBackground.py --prefix empty --seqLength 200 --numSeqs 10
diff --git a/scripts_test/test_motif_grammar_simulation_script.sh b/scripts_test/test_motif_grammar_simulation_script.sh
@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 
 #variable spacing
-motifGrammarSimulation.py --motifName1 TAL1_known1 --motifName2 GATA_disc2 --seqLength 200 --numSeq 10 --generationSetting twoMotifsVariableSpacing --fixedSpacingOrMinSpacing 1 --maxSpacing 5
+motifGrammarSimulation.py --prefix testprefix --motifName1 TAL1_known1 --motifName2 GATA_disc2 --seqLength 200 --numSeq 10 --generationSetting twoMotifsVariableSpacing --fixedSpacingOrMinSpacing 1 --maxSpacing 5
 
 #variable spacing best hit
 motifGrammarSimulation.py --motifName1 TAL1_known1 --motifName2 GATA_disc2 --bestHit --seqLength 200 --numSeq 100 --generationSetting twoMotifsVariableSpacing --fixedSpacingOrMinSpacing 1 --maxSpacing 5

diff --git a/setup.cfg b/setup.cfg
@@ -0,0 +1,3 @@
+[metadata]
+description-file = README.md
+license-file = LICENSE
diff --git a/setup.py b/setup.py
@@ -2,7 +2,7 @@
 
 config = {
     'include_package_data': True,
-    'description': 'Simulations of DNA',
+    'description': 'Simulated datasets of DNA',
     'download_url': 'https://github.com/kundajelab/simdna',
     'version': '0.4.2',
     'packages': ['simdna', 'simdna.resources', 'simdna.synthetic'],

diff --git a/simdna/synthetic/core.py b/simdna/synthetic/core.py
@@ -3,6 +3,7 @@
 from collections import OrderedDict
 import numpy as np
 import re
+import itertools
 
 
 class DefaultNameMixin(object):

diff --git a/simdna/util.py b/simdna/util.py
@@ -98,6 +98,7 @@ def perform_action_on_each_line_of_file(
     i = 0;
     for line in file_handle:
         i += 1;
+        line = line.decode("utf-8")
         process_line(line, i, ignore_input_title,
                      transformation, action, progress_update)
         print_progress(progress_update, i, progress_update_file_name)