Merge pull request #38 from Illumina/develop

Release 1.3.4

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.9-slim
+
+WORKDIR /opt/BeadArrayFiles/
+
+# Installing ps to support usage in Nextflow ICA pipelines
+RUN apt-get update && apt-get install -y --no-install-recommends procps
+
+COPY . /opt/BeadArrayFiles/
+
+RUN python setup.py install
+RUN pip install --no-cache-dir numpy pandas scipy

README.md

@@ -25,14 +25,21 @@ The library depends on the availability of the numpy package in the python insta
 
 ## Example usage
 
-> from IlluminaBeadArrayFiles import GenotypeCalls, BeadPoolManifest, code2genotype
-> import sys
-> gtc_file = "path_to_genotypes.gtc"
-> manifest_file = "path_to_manifest.bpm"
-> names = BeadPoolManifest( manifest_file ).names
-> genotypes = GenotypeCalls( gtc_file ).get_genotypes()
-> for (locus, genotype) in zip( names, genotypes ):
->   sys.stdout.write( locus + "," + code2genotype[genotype] + "\n" )
+```python
+from IlluminaBeadArrayFiles import GenotypeCalls, BeadPoolManifest, code2genotype
+
+gtc_file = "path_to_genotypes.gtc"
+manifest_file = "path_to_manifest.bpm"
+names = BeadPoolManifest( manifest_file ).names
+genotypes = GenotypeCalls( gtc_file ).get_genotypes()
+
+c = 0  # a counter to only show the first 10 genotypes
+for (locus, genotype) in zip( names, genotypes ):
+    print( locus + "," + code2genotype[genotype] )
+    if c >= 10:
+        break
+    c += 1
+```
 
 Also, see examples/* for additional examples of usage.
 These scripts are based on common Genome Studio (https://support.illumina.com/array/array_software/genomestudio.html) reports.

change_log.txt

@@ -1,3 +1,8 @@
+1.3.4
+  -Fix for empty LocusAggregates. See issue #31 (https://github.com/Illumina/BeadArrayFiles/issues/31)
+  -Added Dockerfile to be used with ICA pipelines
+  -Added more support to read clusterfiles of different versions
+
 1.3.3
   -Updated to python3
   -Added GenomeStudio-style dna_report to examples

module/ClusterFile.py

@@ -113,9 +113,6 @@ def read_cluster_file(handle):
         result = ClusterFile(gencall_version, cluster_version, call_version,
                              normalization_version, date_created, manifest_name)
         data_block_version = read_int(handle)
-        if data_block_version not in [8, 9]:
-            raise Exception("Data block version in cluster file " +
-                            str(data_block_version) + " not  supported")
         # opa
         _ = read_string(handle)
 
@@ -211,17 +208,26 @@ def read_record(handle, version):
 
         if version == 9:
             intensity_threshold = read_float(handle)
-        elif version == 8:
-            _ = read_float(handle)
+
+            # read through unused fields
+            for idx in range(14):
+                _ = read_float(handle)
+        elif version >= 6:
             intensity_threshold = 0
+
+            # read through unused fields
+            for idx in range(15):
+                _ = read_float(handle)
+        elif version < 5:
+            intensity_threshold = 0
+
+            # read through unused fields
+            _ = read_float(handle)
+            _ = read_float(handle)
         else:
             raise Exception(
                 "Unsupported cluster record version " + str(version))
 
-        # read through unused fields
-        for idx in range(14):
-            _ = read_float(handle)
-
         aa_cluster_stats = ClusterStats(
             aa_theta_mean, aa_theta_dev, aa_r_mean, aa_r_dev, aa_n)
         ab_cluster_stats = ClusterStats(

module/LocusAggregate.py

@@ -193,8 +193,8 @@ def aggregate_samples(samples, loci, callback, normalization_lookups, bin_size=1
         for loci_group in LocusAggregate.group_loci(loci, loci_batch_size):
 
             # read in the buffer for this group of loci
-            buffer = LocusAggregate.load_buffer(
-                samples, loci_group[0], loci_group[-1] - loci_group[0] + 1, normalization_lookups)
+            buffer = list(LocusAggregate.load_buffer(
+                samples, loci_group[0], loci_group[-1] - loci_group[0] + 1, normalization_lookups))
 
             # generate corresponding locus aggregates
             aggregates = map(GenerateLocusAggregate(

module/__init__.py

@@ -25,7 +25,7 @@
 # of the authors and should not be interpreted as representing official policies,
 # either expressed or implied, of the FreeBSD Project.
 
-__version__ = "1.3.3"
+__version__ = "1.3.4"
 from .GenotypeCalls import code2genotype, NC, AA, AB, BB, GenotypeCalls, NormalizationTransform, ScannerData
 from .BeadPoolManifest import RefStrand, SourceStrand, BeadPoolManifest
 from .LocusAggregate import LocusAggregate

setup.py

@@ -6,5 +6,5 @@
     author_email='[email protected]',
     packages=['IlluminaBeadArrayFiles'],
     package_dir={'IlluminaBeadArrayFiles' : 'module'},
-    version='1.3.3'
+    version='1.3.4'
 )