Merge pull request #43 from jfennick/weekly_ci

Weekly ci

examples/config_ci.json

@@ -6,7 +6,11 @@
     // need to manually exclude large workflows.
     // See https://en.wikipedia.org/wiki/Graph_isomorphism_problem
     "large_workflows": [
-        "dsb", "dsb1", "elm", "vs_demo_2", "vs_demo_3", "vs_demo_4"
+        "dsb", "dsb1", "elm", "vs_demo_2", "vs_demo_3", "vs_demo_4",
+        "vs_demo_2_weekly",
+        "vs_demo_3_weekly",
+        "vs_demo_4_weekly",
+        "docking_rescoring_weekly"
     ],
     // NOTE: Most of the workflows in this list have free variables because they are subworkflows
     // i.e. if you try to run them, you will get "Missing required input parameter"
@@ -68,5 +72,13 @@
         "cwl_watcher_protein",
         // Skip vs_demo_4 so we don't accidentally DOS pdbbind.org.cn
         "vs_demo_4"
+    ],
+    // Run computationally intensive stress tests weekly.
+    // e.g. these workflows should scatter over much larger input arrays.
+    "run_weekly": [
+        "vs_demo_2_weekly",
+        "vs_demo_3_weekly",
+        "vs_demo_4_weekly",
+        "docking_rescoring_weekly"
     ]
 }

examples/docking/vs_demo_2_weekly.yml

@@ -0,0 +1,15 @@
+steps:
+- vs_demo_2.yml:
+
+wic:
+  steps:
+    (1, vs_demo_2.yml):
+      wic:
+        steps:
+          (3, download_smiles_ligand_db.yml):
+            in:
+              max_row: 16 # Override default 1
+          (8, autodock_vina_filter):
+            in:
+              max_num_poses_per_ligand: 2 # Override default 1
+              max_num_poses_total: 16 # Override default 1

examples/docking/vs_demo_3_weekly.yml

@@ -0,0 +1,15 @@
+steps:
+- vs_demo_3.yml:
+
+wic:
+  steps:
+    (1, vs_demo_3.yml):
+      wic:
+        steps:
+          (3, download_smiles_ligand_db.yml):
+            in:
+              max_row: 16 # Override default 1
+          (6, autodock_vina_filter):
+            in:
+              max_num_poses_per_ligand: 2 # Override default 1
+              max_num_poses_total: 16 # Override default 1

examples/docking/vs_demo_4.yml

@@ -2,11 +2,11 @@ steps:
 - extract_pdbbind_refined:
     in:
       # https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.query.html
-      # The query() method uses a slightly modified Python syntax by default. 
-      # For example, the & and | (bitwise) operators have the precedence of their 
-      # boolean cousins, and and or. This is syntactically valid Python, however 
+      # The query() method uses a slightly modified Python syntax by default.
+      # For example, the & and | (bitwise) operators have the precedence of their
+      # boolean cousins, and and or. This is syntactically valid Python, however
       # the semantics are different.
-      query: '(Kd_Ki == "Kd") and (value < 0.000002)'
+      query: '(Kd_Ki == "Kd") and (value < 0.001)'
       max_row: 1 #25 # Use 1 for CI
       convert_Kd_dG: 'True'
       output_txt_path: '&binding_data.txt'

examples/docking/vs_demo_4_weekly.yml

@@ -0,0 +1,15 @@
+steps:
+- vs_demo_4.yml:
+
+wic:
+  steps:
+    (1, vs_demo_4.yml):
+      wic:
+        steps:
+          (1, extract_pdbbind_refined):
+            in:
+              max_row: 16 # Override default 1
+          (6, autodock_vina_filter):
+            in:
+              max_num_poses_per_ligand: 2 # Override default 1
+              max_num_poses_total: 16 # Override default 1

examples/gromacs/npt_gromacs.yml

@@ -31,18 +31,18 @@ steps:
         config:
           terms: [Density]
         output_xvg_path: 'density.xvg'
-  - cwl_watcher:
-      in:
-        #cachedir_path: /absolute/path/to/cachedir/ (automatically filled in by wic)
-        file_pattern: '*npt.edr' # This * is a glob wildcard, NOT an explicit edge!
-        cwl_tool: gmx_energy
-        max_times: '5'
-        config:
-          in:
-            input_energy_path: npt.edr
-            config:
-              terms: [Density]
-            output_xvg_path: density.xvg
+  # - cwl_watcher:
+  #     in:
+  #       #cachedir_path: /absolute/path/to/cachedir/ (automatically filled in by wic)
+  #       file_pattern: '*npt.edr' # This * is a glob wildcard, NOT an explicit edge!
+  #       cwl_tool: gmx_energy
+  #       max_times: '5'
+  #       config:
+  #         in:
+  #           input_energy_path: npt.edr
+  #           config:
+  #             terms: [Density]
+  #           output_xvg_path: density.xvg
 
 wic:
   graphviz:

examples/gromacs/nvt.yml

@@ -30,18 +30,18 @@ steps:
         output_xvg_path: temperature.xvg
 # NOTE: explicit edges are not supported with cwl_watcher, and all filenames
 # must be globally unique!
-  - cwl_watcher:
-      in:
-        #cachedir_path: /absolute/path/to/cachedir/ (automatically filled in by wic)
-        file_pattern: '*nvt.edr' # This * is a glob wildcard, NOT an explicit edge!
-        cwl_tool: gmx_energy
-        max_times: '5'
-        config:
-          in:
-            input_energy_path: '*nvt.edr' # This * is automatically removed.
-            config:
-              terms: [Temperature]
-            output_xvg_path: temperature.xvg
+  # - cwl_watcher:
+  #     in:
+  #       #cachedir_path: /absolute/path/to/cachedir/ (automatically filled in by wic)
+  #       file_pattern: '*nvt.edr' # This * is a glob wildcard, NOT an explicit edge!
+  #       cwl_tool: gmx_energy
+  #       max_times: '5'
+  #       config:
+  #         in:
+  #           input_energy_path: '*nvt.edr' # This * is automatically removed.
+  #           config:
+  #             terms: [Temperature]
+  #           output_xvg_path: temperature.xvg
 
 wic:
   graphviz:

examples/gromacs/prod.yml

@@ -46,7 +46,7 @@ steps:
         output_crd_path: '&prod.gro'
         output_trr_path: '&prod.trr' # Explicitly specify for cwl_watcher
         output_edr_path: '&prod.edr'
-  - cwl_watcher_analysis.yml:
+  # - cwl_watcher_analysis.yml:
 
 wic:
   graphviz:

examples/rescoring/docking_rescoring_weekly.yml

@@ -0,0 +1,14 @@
+steps:
+- docking_rescoring.yml:
+
+wic:
+  steps:
+    (1, docking_rescoring.yml):
+      wic:
+        steps:
+          (1, extract_pdbbind_refined):
+            in:
+              max_row: 1000  # Default 500
+          (2, random_subset_rows):
+            in:
+              num_of_samples: 32