Expose --subsample-seed parameter

CHANGES.md

@@ -1,11 +1,17 @@
 # Changes
 
-v1.1.3 (dev)
+v1.1.4 (dev)
 ------------
+* Exposed option to set PRNG seed when subsampling reads.
+
+v1.1.3 (2017.05.01)
+-------------------
 * Updated Dockerfile to use smaller, Alpine-based image.
 * Added Docker image for v1.1.2 to Docker Hub.
 * Updated Travis config to automatically build Docker images for each release.
 * Ported over improvements to adapter parsing (635eea9) from Cutadapt.
+* Fixed #12: tqdm progress bar not working.
+* Fixed #13: unnecessary differences in summary output between Cutadapt and Atropos.
 
 v1.1.2 (2017.04.12)
 -------------------

README.md

@@ -89,6 +89,7 @@ We welcome any contributions via GitHub issues and pull requests. See the  [docu
 * Migrate to xphyle (https://github.com/jdidion/xphyle) for file management.
 * Provide option for RNA-seq data that will trim polyA sequence.
 * Accept multiple input files.
+* Support SAM output.
 * Expand the list of contaminants that are detected by default.
 * Automate creation and sending of user statistics and crash reports using [pytattle](https://github.com/biologyguy/PyTattle).
 * Accessibility:

atropos/commands/base.py

@@ -194,6 +194,9 @@ def __init__(self, options, summary_class=Summary):
         # Wrap reader in subsampler
         if options.subsample:
             import random
+            if options.subsample_seed:
+                random.seed(options.subsample_seed)
+
             def subsample(reader, frac):
                 """Generator that yields a random subsample of records.
                 
@@ -204,6 +207,7 @@ def subsample(reader, frac):
                 for reads in reader:
                     if random.random() < frac:
                         yield reads
+
             reader = subsample(reader, options.subsample)
 
         self.iterable = enumerate(reader, 1)

atropos/commands/cli.py

@@ -183,6 +183,11 @@ def add_common_options(self):
             "--subsample",
             type=probability, default=None, metavar="PROB",
             help="Subsample a fraction of reads. (no)")
+        group.add_argument(
+            "--subsample-seed",
+            type=int, default=None, metavar="SEED",
+            help="The seed to use for the pseudorandom number generator. Using"
+                 "the same seed will result in the same subsampling of reads.")
         group.add_argument(
             "--batch-size",
             type=int_or_str, metavar="SIZE",