Start updating BaseSpace version to include HCV reports for #412.

Dockerfile

@@ -10,11 +10,6 @@ RUN apt-get update -qq --fix-missing && apt-get install -qq -y \
   libpython3.4-dev \
   && rm -rf /var/lib/apt/lists/*
 
-## Python packages, plus trigger matplotlib to build its font cache
-RUN pip install python-Levenshtein matplotlib requests reportlab pyyaml cutadapt==1.11 && \
-  ln -s /usr/local/bin/cutadapt /usr/local/bin/cutadapt-1.11 && \
-  python -c 'import matplotlib; matplotlib.use("Agg"); import matplotlib.pyplot'
-
 ## bowtie2
 RUN wget -q -O bowtie2.zip https://github.com/BenLangmead/bowtie2/releases/download/v2.2.8/bowtie2-2.2.8-linux-x86_64.zip && \
   unzip bowtie2.zip -d /opt/ && \
@@ -24,11 +19,14 @@ RUN wget -q -O bowtie2.zip https://github.com/BenLangmead/bowtie2/releases/downl
 ENV PATH $PATH:/opt/bowtie2
 
 ## Gotoh
-COPY micall/alignment /opt/alignment
-WORKDIR /opt/alignment
-RUN python setup.py install
-WORKDIR /
-RUN rm -r /opt/alignment && python -c 'import gotoh'
+COPY micall/alignment /opt/micall/alignment
+COPY requirements.txt requirements-basespace.txt /opt/micall/
+
+## Python packages, plus trigger matplotlib to build its font cache
+WORKDIR /opt
+RUN pip install -r /opt/micall/requirements-basespace.txt && \
+  ln -s /usr/local/bin/cutadapt /usr/local/bin/cutadapt-1.11 && \
+  python -c 'import matplotlib; matplotlib.use("Agg"); import matplotlib.pyplot'
 
 ## MiCall
 COPY micall_basespace.py version.txt /opt/micall/

basespace/form.json

@@ -21,15 +21,29 @@
             "helpText": "A run does not have to be provided, however run quality information can only be produced if the selected samples were from the provided run"
         },
         {
-            "$type": "SampleChooser",
-            "size": 300,
-            "valueType": "Input",
-            "allowedPermissions": "read",
-            "label": "Sample",
-            "multiselect": true,
-            "required": true,
-            "id": "sample-ids",
-            "rules": "sample-reader"
+            "$type": "ResourceMatcher",
+        	"required": true,
+        	"id": "sample-ids",
+        	"label": "Sample Pairs",
+        	"buttonText": "Select Pairs",
+        	"maxRows": 100,
+        	"columns": [
+        		{
+        			"id": "main",
+        			"label": "Main Samples",
+        			"resourceType": "Sample",
+        			"rules": null
+        		},
+        		{
+        			"id": "midi",
+        			"label": "NS5b-MIDI Samples",
+        			"resourceType": "Sample",
+        			"rules": null
+        		}
+        	],
+            "allowunpairedcells": true,
+        	"rules": null,
+            "helpText": "MiCall expects Hepatitis C samples to come in two sections: the main section, and the NS5b-MIDI section (amino acids 336 to 560 in NS5b)."
         },
         {
             "$type": "CheckBox",

docker_build.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-from argparse import ArgumentParser
+from argparse import ArgumentParser, ArgumentDefaultsHelpFormatter
 import os
 from subprocess import check_call, CalledProcessError
 
@@ -8,7 +8,8 @@
 
 def parse_args():
     parser = ArgumentParser(
-        description="Build docker image from local source code or a tag.")
+        description="Build docker image from local source code or a tag.",
+        formatter_class=ArgumentDefaultsHelpFormatter)
 
     parser.add_argument('-a',
                         '--agent_id',

micall/core/prelim_map.py

@@ -76,7 +76,7 @@ def prelim_map(fastq1,
     ref_path = os.path.join(work_path, 'micall.fasta')
     all_excluded_seeds = {project_config.G2P_SEED_NAME}
     if excluded_seeds:
-        all_excluded_seeds |= excluded_seeds
+        all_excluded_seeds.update(excluded_seeds)
     with open(ref_path, 'w') as ref:
         projects.writeSeedFasta(ref, all_excluded_seeds)
     reffile_template = os.path.join(work_path, 'reference')

micall_basespace.py

@@ -211,7 +211,7 @@ def parse_json(json_file):
         args.read_length2 = run_content['SequencingStats']['NumCyclesRead2']
         args.index_length1 = run_content['SequencingStats']['NumCyclesIndex1']
         args.index_length2 = run_content['SequencingStats']['NumCyclesIndex2']
-    args.samples = sorted(arg_map['Input.sample-ids']['Items'],
+    args.samples = sorted(arg_map['Input.sample-ids.main']['Items'],
                           key=itemgetter('Name'))
     args.project_id = arg_map['Input.project-id']['Content']['Id']
     args.reports = arg_map['Input.reports']['Items']
@@ -334,7 +334,7 @@ def try_sample(sample_index, run_info, args, pssm):
     """
     try:
         process_sample(sample_index, run_info, args, pssm)
-    except:
+    except Exception:
         message = 'Failed to process sample {}.'.format(sample_index+1)
         logger.error(message, exc_info=True)
         raise RuntimeError(message)
@@ -508,8 +508,14 @@ def process_sample(sample_index, run_info, args, pssm):
     logger.info('Running hivdb (%d of %d).', sample_index+1, len(run_info.samples))
     with open(os.path.join(sample_scratch_path, 'amino.csv')) as amino_csv, \
             open(os.path.join(sample_scratch_path, 'resistance.csv'), 'w') as resistance_csv, \
-            open(os.path.join(sample_scratch_path, 'mutations.csv'), 'w') as mutations_csv:
-        hivdb(amino_csv, resistance_csv, mutations_csv, run_info.reports)
+            open(os.path.join(sample_scratch_path, 'mutations.csv'), 'w') as mutations_csv, \
+            open(os.path.join(sample_scratch_path, 'resistance_fail.csv'), 'w') as fail_csv:
+        hivdb(amino_csv,
+              amino_csv,  # TODO: match with MIDI sample
+              resistance_csv,
+              mutations_csv,
+              fail_csv,
+              run_info.reports)
 
     logger.info('Running resistance report (%d of %d).', sample_index+1, len(run_info.samples))
     source_path = os.path.dirname(__file__)
@@ -715,7 +721,7 @@ def main():
         try:
             with open(json_path, 'r') as json_file:
                 run_json = parse_json(json_file)
-        except:
+        except IOError:
             if os.path.exists(json_path):
                 # copy the input file to the output dir for postmortem analysis
                 logger.error("Error occurred while parsing '%s'" % json_path)
@@ -768,5 +774,6 @@ def main():
         summarize_samples(args, run_json, run_summary)
     logger.info('Done.')
 
+
 if __name__ == '__main__':
     main()

requirements-basespace.txt

@@ -0,0 +1,3 @@
+# Requirements for running the micall_basespace.py script
+-r requirements.txt
+requests==2.13.0

requirements.txt

@@ -3,6 +3,7 @@ micall/alignment
 git+https://github.com/cfe-lab/pyvdrm.git@v0.3.1
 numpy==1.12.0
 matplotlib==2.0.0
+cutadapt==1.11
 python-Levenshtein==0.12.0
 PyYAML==3.12
 reportlab==3.4.0