Adopt ecoli-sources data bundle as the ParCa input source

README.md

@@ -18,10 +18,11 @@ Its main benefits over the original model are:
 4. **Google Cloud support:** workflows too large to run on a local machine
     can be easily run on Google Cloud
 
-As in wcEcoli, [raw experimental data](reconstruction/ecoli/flat) is first processed
-by the parameter calculator or [ParCa](reconstruction/ecoli/fit_sim_data_1.py) to calculate 
-model parameters (e.g. transcription probabilities). These parameters are used to configure
-[processes](ecoli/processes) that are linked together into a
+Raw experimental data lives in [`vivarium-collective/ecoli-sources`](https://github.com/vivarium-collective/ecoli-sources)
+as a curated reference bundle (see [doc/data_ingestion.rst](doc/data_ingestion.rst)). The
+parameter calculator or [ParCa](reconstruction/ecoli/fit_sim_data_1.py) reads from that
+bundle to calculate model parameters (e.g. transcription probabilities). These parameters
+are used to configure [processes](ecoli/processes) that are linked together into a
 [complete simulation](ecoli/experiments/ecoli_master_sim.py).
 
 ## Setup

configs/default.json

@@ -58,8 +58,7 @@
         "intermediates_directory": "",
         "variable_elongation_transcription": true,
         "variable_elongation_translation": false,
-        "rnaseq_manifest_path": null,
-        "rnaseq_basal_dataset_id": null,
+        "bundle_manifest_path": null,
         "basal_expression_condition": "M9 Glucose minus AAs",
         "rnaseq_fill_missing_genes_from_ref": true
     },

configs/templates/parca_standalone.json

@@ -21,13 +21,6 @@
         "variable_elongation_transcription": true,
         "variable_elongation_translation": false,
 
-        # RNA-seq input options (optional; omit or set to null for legacy behavior)
-        # rnaseq_manifest_path: path to manifest TSV listing available RNA-seq datasets
-        # rnaseq_basal_dataset_id: dataset_id from manifest to use as basal transcriptome
-        # If both are null/omitted, ParCa uses the legacy raw_data.rna_seq_data tables.
-        "rnaseq_manifest_path": null,
-        "rnaseq_basal_dataset_id": null,
-
         # basal_expression_condition: modeled condition name (must match a defined condition)
         # This is used throughout ParCa for the baseline growth state.
         "basal_expression_condition": "M9 Glucose minus AAs",

data/marA_binding/get_TU_ID.py

@@ -19,9 +19,7 @@
 import argparse
 import pandas as pd
 import pickle
-import json
 import numpy as np
-from ast import literal_eval
 
 
 def main():
@@ -36,17 +34,35 @@ def main():
     # Load complexation and TU index data from sim_data
     sim_data = pickle.load(open(args.sim_data_path, "rb"))
     bulk_names = sim_data.internal_state.bulk_molecules.bulk_data["id"].tolist()
+    cistron_data = sim_data.process.transcription.cistron_data
     cistron_id_to_index = {
-        cistron: idx
-        for idx, cistron in enumerate(sim_data.process.transcription.cistron_data["id"])
+        cistron: idx for idx, cistron in enumerate(cistron_data["id"])
     }
     cistron_tu_mapping = sim_data.process.transcription.cistron_tu_mapping_matrix
     comp_stoich = sim_data.process.complexation.stoich_matrix().astype(np.int64).T
     comp_molecules = [str(i) for i in sim_data.process.complexation.molecule_names]
 
-    rnas = pd.read_table("reconstruction/ecoli/flat/rnas.tsv", comment="#")
-    rnas["synonyms"] = rnas["synonyms"].apply(literal_eval)
-    rnas = rnas.explode("synonyms")
+    # Build a synonym -> cistron-row DataFrame from sim_data: explodes the
+    # cistron_id_to_synonyms mapping into one row per (cistron, synonym) pair,
+    # and joins back to the cistron's id, common_name, and monomer_ids.
+    cistron_id_to_common_name = dict(
+        zip(cistron_data["id"], cistron_data["common_name"])
+    )
+    cistron_id_to_monomer_ids = (
+        sim_data.process.transcription.cistron_id_to_monomer_ids
+    )
+    rnas = pd.DataFrame(
+        [
+            {
+                "id": cistron_id,
+                "common_name": cistron_id_to_common_name[cistron_id],
+                "synonyms": syn,
+                "monomer_ids": cistron_id_to_monomer_ids.get(cistron_id, []),
+            }
+            for cistron_id, syns in sim_data.process.transcription.cistron_id_to_synonyms.items()
+            for syn in syns
+        ]
+    )
 
     # Use fold change from exposure to 1.5 mg/L tetracycline
     tet_FC = pd.read_table("data/marA_binding/tet_FC.tsv")
@@ -100,7 +116,6 @@ def recursive_search(complex_name, monomers_used):
         return add_monomers_used, add_complex_names
 
     def get_IDs(monomer_id):
-        monomer_id = json.loads(monomer_id)
         # Noncoding RNAs
         if len(monomer_id) == 0:
             return [[], [], [], []]