From 71794dee855e242ebfc91a31379549527c187e79 Mon Sep 17 00:00:00 2001
From: cb-Hades <81743695+cb-Hades@users.noreply.github.com>
Date: Thu, 22 Aug 2024 15:00:58 +0200
Subject: [PATCH] Fixed CMPB workflow #8

---
 dev/CB_test_modules.ipynb                 | 89 ++++++-----------------
 src/specimen/cmpb/workflow.py             | 12 ++-
 src/specimen/data/config/cmpb_config.yaml | 11 ++-
 src/specimen/util/set_up.py               |  6 +-
 4 files changed, 39 insertions(+), 79 deletions(-)

diff --git a/dev/CB_test_modules.ipynb b/dev/CB_test_modules.ipynb
index 3999831..d0b0457 100644
--- a/dev/CB_test_modules.ipynb
+++ b/dev/CB_test_modules.ipynb
@@ -1549,13 +1549,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
+      "/Users/brune/miniconda3/envs/sprg/lib/python3.10/site-packages/pydantic/_internal/_config.py:322: UserWarning: Valid config keys have changed in V2:\n",
+      "* 'underscore_attrs_are_private' has been removed\n",
+      "  warnings.warn(message, UserWarning)\n",
       "WARNING:root:Keyword USER detected in config (gram). Either due to skipped options or missing required information.\n",
       "Reminder: This may lead to downstream problems.\n",
       "WARNING:root:Keyword USER detected in config (gene-table). Either due to skipped options or missing required information.\n",
@@ -1575,19 +1578,28 @@
      ]
     },
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Running in debugging mode.\n",
-      "fill_model: Running in debugging mode\n"
-     ]
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "571a86b91c4b4bfd97d7510cbf21dfc0",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/3 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "Trying to add missing reacs: 100%|██████████| 10/10 [00:10<00:00,  1.04s/it]\n",
-      "Adding genes to model: 100%|██████████| 3/3 [00:00<00:00, 5197.40it/s]\n",
+      "Adding genes to model: 100%|██████████| 5/5 [00:00<00:00, 5902.48it/s]\n",
+      "Trying to add missing reacs:   0%|          | 1/2581 [00:05<3:39:27,  5.10s/it]/Users/brune/Documents/10_Code/refinegems/build/__editable__.refineGEMs-1.4.2-py3-none-any/refinegems/utility/entities.py:630: UserWarning: HTTPError: G10554(n)\n",
+      "  warnings.warn(F'HTTPError: {kegg_id}')\n",
+      "Trying to add missing reacs: 100%|██████████| 2581/2581 [32:07<00:00,  1.34it/s]\n",
+      "Adding genes to model: 100%|██████████| 146/146 [00:00<00:00, 20753.33it/s]\n",
       "/Users/brune/Documents/10_Code/refinegems/build/__editable__.refineGEMs-1.4.2-py3-none-any/refinegems/classes/reports.py:234: UserWarning: Model is not able to grow sensible on any medium. Returning empty figure.\n",
       "  warnings.warn('Model is not able to grow sensible on any medium. Returning empty figure.')\n"
      ]
@@ -1607,7 +1619,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "100%|██████████| 1538/1538 [01:35<00:00, 16.11it/s]\n"
+      "100%|██████████| 1538/1538 [01:52<00:00, 13.65it/s]\n"
      ]
     },
     {
@@ -1615,7 +1627,7 @@
      "output_type": "stream",
      "text": [
       "\n",
-      "Model with SBO annotations written to /var/folders/xd/zl0vk7sj60xcc0zmc4k4mxxc0000gr/T/tmphkr5txa_/dud.xml ...\n",
+      "Model with SBO annotations written to /var/folders/xd/zl0vk7sj60xcc0zmc4k4mxxc0000gr/T/tmpzhcgfxa0/dud.xml ...\n",
       "\n",
       "\tDuplicate metabolite(s) nh3_c, nh4_c found.\n",
       "\tDuplicate metabolite(s) fdxo_2_2_c, fdxox_c found.\n",
@@ -1721,61 +1733,6 @@
     "run(cfg)"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/brune/miniconda3/envs/sprg/lib/python3.10/site-packages/pydantic/_internal/_config.py:322: UserWarning: Valid config keys have changed in V2:\n",
-      "* 'underscore_attrs_are_private' has been removed\n",
-      "  warnings.warn(message, UserWarning)\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\tSpecial case -Duplicate NH4/NH3- detected.\n",
-      "\tTrying to solve by additionally removing reactions containing both metabolites.\n",
-      "\tDuplicate metabolite nh4_c found (duplicate to nh3_c based on annotation).\n",
-      "\t\tAutomated deletion not possible due to problems with consistency.\n",
-      "\tDuplicate metabolite fdxox_c found. Replaced with fdxo_2_2_c.\n",
-      "\tDuplicate metabolite metsox_S__L_c found. Replaced with metox_c.\n",
-      "\tDuplicate metabolite shcl_c found. Replaced with dscl_c.\n",
-      "\tDuplicate metabolite srch_c found (duplicate to scl_c based on annotation).\n",
-      "\t\tAutomated deletion not possible due to problems with consistency.\n",
-      "unknown metabolite 'acorn__L_c' created\n",
-      "\tDuplicate metabolite orn_c found (duplicate to orn__L_c based on annotation).\n",
-      "\t\tAutomated deletion not possible due to problems with consistency.\n",
-      "\tDuplicate metabolite metsox_S__L_e found. Replaced with metox_e.\n",
-      "\tDuplicate reaction OPTCCL found. Combined to OPETDC and deleted.\n",
-      "\tDuplicate reaction THZPSN_1 found. Combined to THZPSN and deleted.\n",
-      "\tDuplicate reaction METSR_S1 found. Combined to METSOXR1 and deleted.\n",
-      "\tDuplicate reaction METSabc found. Combined to METSOX1abc and deleted.\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/brune/miniconda3/envs/sprg/lib/python3.10/site-packages/cobra/core/group.py:147: UserWarning: need to pass in a list\n",
-      "  warn(\"need to pass in a list\")\n"
-     ]
-    }
-   ],
-   "source": [
-    "from refinegems.utility.io import load_model \n",
-    "from refinegems.curation.curate import resolve_duplicates\n",
-    "\n",
-    "testmodel = load_model('/Users/brune/Documents/11_Test_Data/test_SPECIMEN/cmpb/testrun/cmpb_out/model.xml','cobra')\n",
-    "\n",
-    "mod = resolve_duplicates(testmodel, replace_dupl_meta=True, check_reac=True)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
diff --git a/src/specimen/cmpb/workflow.py b/src/specimen/cmpb/workflow.py
index 7168564..ed1f664 100644
--- a/src/specimen/cmpb/workflow.py
+++ b/src/specimen/cmpb/workflow.py
@@ -123,8 +123,7 @@ def between_analysis(model: Model, cfg:dict, step:str):
 
     dir = config['general']['dir']
     if not config['general']['save_all_models']:
-        only_modelpath = Path(dir,'cmpb_out','model.xml') # @TODO Use model ID here...
-                                                          # model might not exist here ...
+        only_modelpath = Path(dir,'cmpb_out','model.xml') 
 
     # create directory structure
     # --------------------------
@@ -377,8 +376,6 @@ def between_analysis(model: Model, cfg:dict, step:str):
     
     # in-between testing
     between_growth_test(current_model,config,step='after_duplicate_removal')
-    import sys
-    sys.exit(0) # ------------------ issue above ------------------------
     between_analysis(current_model,config,step='after_duplicate_removal')
 
     # BOF
@@ -469,10 +466,11 @@ def between_analysis(model: Model, cfg:dict, step:str):
 
 ####### IDEAS below ####
 
-# @TODO / @IDEAS Add option to have specific colour list per model for plots
+# @TODO 
+# - Add option to have specific colour list per model for plots
     # for the comparison when runnin this on multiple models
-# @TODO Maybe get models at first and then add model IDs to every save filename?
-# @TODO Add optional FROG report at end of pipeline
+# - Maybe get models at first and then add model IDs to every save filename?
+# - Add optional FROG report at end of pipeline
 
 # run for multiple models
 def wrapper():
diff --git a/src/specimen/data/config/cmpb_config.yaml b/src/specimen/data/config/cmpb_config.yaml
index 2906e47..f12e91a 100644
--- a/src/specimen/data/config/cmpb_config.yaml
+++ b/src/specimen/data/config/cmpb_config.yaml
@@ -3,6 +3,7 @@
 # Meaning of the default parameters:
 #    The value __USER__ indicates parameters required to be specified by the user
 #    The value USER indicates parameters required only in specific cases
+#    To avoid warnings, set parameters you do not use to null or NULL
 
 # Meta info:
 #    model:     USER
@@ -14,8 +15,7 @@
 # ----------------------
 input:
   modelpath: NULL            # Optional, path to a model.
-                             # If not given, runs CarveMe -> Future update!
-  # annotated_genome: USER # Some alternative input if not model is given
+                             # If not given, runs CarveMe 
   mediapath: __USER__        # Path to a media config to test growth with
 
 # General options
@@ -50,10 +50,11 @@ tech-resources:
 # Build a model using CarveMe
 # ---------------------------
 carveme:
-  # requires protein_fasta under general to be set
+  # CarveMe requires protein_fasta under general to be set instead of modelpath
   # if CarveMe should be run, 
   # fill out the params below
-  gram: USER           # grampos or gramneg?
+  gram: USER           # Choose either grampos or gramneg, depending on the Gram-test
+                       # resilts of your organism
 
 # Polish a CarveMe model
 #    Only neccessary, if the model will or has been build with CarveMe
@@ -67,6 +68,7 @@ cm-polish:
 # Filling gaps, optional
 # ----------------------
 gapfilling:
+
   ########### general options ###########
   # parameters, that apply to all the gap filling algorithmns
   idprefix: 'CMPB'            # prefix to use for fantasy IDs, if IDs for 
@@ -79,6 +81,7 @@ gapfilling:
                               # from being added to the model.
   exclude-rna: True           # Exclude reactions containing 'RNA' in their name
                               # from being added to the model.
+
   ########## enable algorithms ##########
   # via KEGG ...................
   # requires KEGG organism ID to be set
diff --git a/src/specimen/util/set_up.py b/src/specimen/util/set_up.py
index 7cd1e26..44614e0 100644
--- a/src/specimen/util/set_up.py
+++ b/src/specimen/util/set_up.py
@@ -33,8 +33,10 @@
 HQTB_CONFIG_PATH_REQUIRED = ['annotated_genome','full_sequence','model','diamond',
                              'mnx_chem_prop', 'mnx_chem_xref','mnx_reac_prop','mnx_reac_xref',
                              'media_analysis'] #: :meta: 
-CMPB_CONFIG_PATHS_REQUIRED = ['mediapath','protein_fasta','refseq_gff','annotated_genome'] #: :meta:
-CMPB_CONFIG_PATHS_OPTIONAL = ['modelpath','biocyc_files','full_genome_sequence'] # :meta:
+CMPB_CONFIG_PATHS_REQUIRED = ['mediapath'] #: :meta:
+CMPB_CONFIG_PATHS_OPTIONAL = ['modelpath','full_genome_sequence','refseq_gff', 'protein_fasta',
+                              'gene-table','reacs-table','gff','swissprot-dmnd',
+                              'swissprot-mapping'] # :meta:
 PIPELINE_PATHS_OPTIONAL = {'hqtb':HQTB_CONFIG_PATH_OPTIONAL,
                   'cmpb':CMPB_CONFIG_PATHS_OPTIONAL} #: :meta: 
 PIPELINE_PATHS_REQUIRED = {'hqtb':HQTB_CONFIG_PATH_REQUIRED,