fix problem with moved fragment method. Added instructions for runnin…

…g tests with conda.

README.md

@@ -203,6 +203,34 @@ playbooks.
     `Posting Squonk pipelines` section of Squonk's OpenShift Ansible
     [README](https://github.com/InformaticsMatters/squonk/blob/master/openshift/ansible/README.md).
 
+## Running tests
+
+The test running is in the pipelines-utils repo and tests are run from there.
+For full details consult that repo.
+
+But as a quick start you should be able to run the the tests in a conda environment like this:
+
+Create a conda environment containing RDKit:
+```
+conda env create -f environment-rdkit.yml
+```
+
+Move into the `pipelines-utils` repo (this should be alongside `pipelines` and `pipelines-utils-rdkit`):
+```
+cd ../pipleines-utils
+```
+
+Set your `PYTHONPATH` environment variable to include the `pipelines-utils` and `pipelines-utils-rdkit` sources
+(adjusting `/path/to/` to whatever is needed):
+```
+export PYTHONPATH=/path/to/pipelines-utils/src/python:/path/to/pipelines-utils-rdkit/src/python
+``` 
+
+Run tests:
+```
+./gradlew runPipelineTester -Pptargs=-opipelines
+```
+
 ## Contact
 
 Any questions contact: 

environment-rdkit.yml

@@ -0,0 +1,11 @@
+name: pipelines
+channels:
+    - conda-forge
+dependencies:
+    - python=3.6
+    - pip=20.0.2
+    - rdkit=2019.09.2
+    - pip:
+        - matplotlib==2.2.*
+        - molvs==0.1.1
+        - standardiser==0.1.9

src/python/pipelines/dimorphite/enumerate_charges.py

@@ -55,6 +55,7 @@ def add_src_mol_ref(src_mol, target_mol, index):
     :param index:
     :return:
     """
+    parent = None
     if src_mol.HasProp('uuid'):
         parent = src_mol.GetProp('uuid')
     elif src_mol.HasProp('_name_'):

src/python/pipelines/dimorphite/enumerate_charges.test

@@ -5,7 +5,7 @@
     version = 1,
 
     // Testing cluster_butina.py reading from STDIN and writing to STDOUT
-    test_raw_cluster_butina_from_sdf_to_default = [
+    test_dimorphite_simple = [
 
         command: '''gunzip -c ${PIN}Kinase_inhibs.sdf.gz |
                  python -m pipelines.dimorphite.enumerate_charges -if sdf''',

src/python/pipelines/rdkit/screen.py

@@ -22,7 +22,7 @@
 from rdkit.Chem import MACCSkeys
 from rdkit.Chem.Fingerprints import FingerprintMols
 
-from pipelines_utils_rdkit import filter, rdkit_utils
+from pipelines_utils_rdkit import filter, rdkit_utils, mol_utils
 from pipelines_utils import parameter_utils, utils
 
 ### start field name defintions #########################################
@@ -99,7 +99,7 @@ def main():
         i +=1
         if mol is None: continue
         if args.fragment:
-            mol = filter.fragment(mol, args.fragment, quiet=args.quiet)
+            mol = mol_utils.fragment(mol, args.fragment, quiet=args.quiet)
         if not filter.filter(mol, minHac=args.hacmin, maxHac=args.hacmax, minMw=args.mwmin, maxMw=args.mwmax, quiet=args.quiet):
             continue
         target_fp = descriptor(mol)

src/python/pipelines/rdkit/screen.test

@@ -48,6 +48,25 @@
 
     ],
 
+    // Testing screen.py reading and writing files using sdf with --fragment argument
+        test_screen_fragment = [
+
+            command: '''python -m pipelines.rdkit.screen
+                     -i ${PIN}dhfr_3d.sdf.gz -o ${POUT}output -of sdf
+                     --qsmiles 'C1N=C(C2=CC=CC=C2)C2=CC=CC=C2C2=C1C=NC(NC1=CC=CC=C1)=N2'
+                     --simmin 0.45 -if sdf --meta --fragment hac''',
+
+            stderr: [ 'Found [1-9]\\d+ similar molecules' ],
+
+            creates: [ 'output.sdf.gz',
+                       'output_metrics.txt' ],
+
+            metrics: [ 'RDKitScreen': '756',
+                       '__InputCount__': '756',
+                       '__OutputCount__': '[1-9]\\d+' ],
+
+        ],
+
     // Testing screen.py reading and writing files using json
     test_nci100_data_json = [
 

src/python/pipelines/rdkit/screen_multi.py

@@ -21,7 +21,7 @@
 from rdkit.Chem import MACCSkeys
 from rdkit.Chem.Fingerprints import FingerprintMols
 
-from pipelines_utils_rdkit import filter, rdkit_utils
+from pipelines_utils_rdkit import filter, rdkit_utils, mol_utils
 from pipelines_utils import parameter_utils, utils
 
 ### start field name defintions #########################################
@@ -131,7 +131,7 @@ def main():
         i +=1
         if mol is None: continue
         if args.fragment:
-            mol = filter.fragment(mol, args.fragment, quiet=args.quiet)
+            mol = mol_utils.fragment(mol, args.fragment, quiet=args.quiet)
         if not filter.filter(mol, minHac=args.hacmin, maxHac=args.hacmax, minMw=args.mwmin, maxMw=args.mwmax, quiet=args.quiet):
             continue
         targetFp = descriptor(mol)