Estimate kcats from the EC tree; make brenda_ec_tree the default preset

docs/migrating_from_gecko_matlab.md

@@ -252,7 +252,10 @@ Each row maps a MATLAB function to its geckopy equivalent. The
 | `kcatsFromOKP`                      | `kcats_from_okp`                     | One OpenKineticsPredictor method, kept as `data/kcats/okp_<method>.tsv`; submits a job when there is none, writes the file once it is done. Returns `(kcat_list, done)`. |
 | `saveKcatSource`, `loadKcatSource` | `save_kcat_source`, `load_kcat_source`, `read_kcat_source` | Kcat source files: one per source, keyed by conventional reaction and enzyme set, the same file format in both tools. `load_kcat_source` maps a file to the current model and reports rows that fit no reaction. **`[Py]`** `read_kcat_source` reads a file without a model; GECKO gives the same in `loadKcatSource`'s `report.header` and `report.records`. |
 | `getEcRxnKeys`                      | `ec_rxn_keys`                        | Conventional reaction and enzyme set per `ec.rxns` entry. |
-| `collectKcats`                      | `collect_kcats`                      | Decides one kcat per reaction from the source files, as `[kcat_assignment]` in model_adapter.toml sets (preset `gecko_median`, the default, or `gecko_classic`, or stages), without changing the model. Writes `output/<model id>_kcatDecisions.tsv`. |
+| `kcatsFromECTree`                   | `kcats_from_ec_tree`                 | EC median of the BRENDA measurement table, shrunk toward the EC's 3- and 2-digit classes (weight n / (n + k)), kept as `data/kcats/ec_tree.tsv`. |
+| `ecTreeEstimate`                    | `ECTree.estimate` (`geckopy.gather_kcats.ec_tree`) | The EC-tree value for one or more EC numbers. |
+| `loadBrendaMeasurements`            | `load_brenda_measurements`           | The BRENDA measurement table (`measurements.tsv`): wild-type kcats with an EC number, after the outlier screen. |
+| `collectKcats`                      | `collect_kcats`                      | Decides one kcat per reaction from the source files, as `[kcat_assignment]` in model_adapter.toml sets (preset `brenda_ec_tree`, the default, `gecko_median` or `gecko_classic`, or stages), without changing the model. Writes `output/<model id>_kcatDecisions.tsv`. |
 | `assignKcats`                       | `assign_kcats`                       | `collect_kcats`, then sets `ec.kcat` and `ec.source` and applies the kcat constraints; replaces `merge_kcats` → `apply_kcat_list` → `apply_custom_kcats` → `fill_kcats_from_isozymes` → `assign_standard_kcat` → `apply_kcat_constraints`. In place. |
 | `updateKcatSources`                 | `update_kcat_sources`                | Gathers the source files the configuration needs that are missing, or outdated against `[kcat_sources.<name>]`; `dry_run` only reports. |
 

hatch_build.py

@@ -15,7 +15,7 @@
 
 from hatchling.builders.hooks.plugin.interface import BuildHookInterface
 
-_BRENDA_FILES = ("kcat.tsv", "sa.tsv", "mw.tsv")
+_BRENDA_FILES = ("kcat.tsv", "sa.tsv", "mw.tsv", "measurements.tsv")
 
 
 class BrendaCompressHook(BuildHookInterface):

pyproject.toml

@@ -79,12 +79,13 @@ geckopy = "geckopy.cli:main"
 
 [tool.hatch.build.targets.wheel]
 packages = ["src/geckopy"]
-# kcat.tsv/sa.tsv/mw.tsv are shipped xz-compressed instead -- see
+# kcat.tsv/sa.tsv/mw.tsv/measurements.tsv are shipped xz-compressed instead -- see
 # hatch_build.py and src/geckopy/databases/brenda_loader.py.
 exclude = [
     "src/geckopy/data/brenda/kcat.tsv",
     "src/geckopy/data/brenda/sa.tsv",
     "src/geckopy/data/brenda/mw.tsv",
+    "src/geckopy/data/brenda/measurements.tsv",
 ]
 
 [tool.hatch.build.targets.wheel.hooks.custom]

src/geckopy/__init__.py

@@ -82,6 +82,7 @@
     get_standard_kcat,  # deprecated; alias of assign_standard_kcat
     kcats_from_brenda,
     kcats_from_dlkcat,
+    kcats_from_ec_tree,
     kcats_from_okp,
     load_kcat_source,
     merge_dlkcat_and_fuzzy_kcats,  # deprecated; alias of merge_kcats
@@ -205,6 +206,7 @@
     "fuzzy_kcat_matching",
     "kcats_from_brenda",
     "kcats_from_dlkcat",
+    "kcats_from_ec_tree",
     "kcats_from_okp",
     "load_kcat_source",
     "merge_dlkcat_and_fuzzy_kcats",  # deprecated; alias of merge_kcats

src/geckopy/adapter/adapterParameters.tsv

@@ -32,7 +32,7 @@ okp.method	okp.method	"CataPro"	OpenKineticsPredictor method
 okp.handle_long_sequences	okp.handleLongSequences	"truncate"	How OpenKineticsPredictor handles sequences that are too long
 okp.include_similarity_columns	okp.includeSimilarityColumns	true	Return similarity to the method's training data
 okp.canonicalize_substrates	okp.canonicalizeSubstrates	true	Canonicalize substrate SMILES before prediction
-kcat_assignment.preset			Kcat assignment preset: gecko_median (used when neither preset nor stages are given) or gecko_classic
+kcat_assignment.preset			Kcat assignment preset: brenda_ec_tree (used when neither preset nor stages are given), gecko_median or gecko_classic
 kcat_assignment.isozymes		true	Fill reactions without a kcat from their isozymes after the stages
 kcat_assignment.standard		true	Give the remaining reactions the standard kcat
 kcat_assignment.stage			Stages instead of a preset: action, sources, criteria and BRENDA limits ([[kcat_assignment.stage]])

src/geckopy/adapter/params.py

@@ -126,10 +126,10 @@ class KcatAssignmentParams(BaseModel):
     """How kcats are assigned from the kcat source files (``collect_kcats``)."""
     model_config = ConfigDict(extra="forbid")
 
-    preset: Optional[Literal["gecko_classic", "gecko_median"]] = Field(
+    preset: Optional[Literal["gecko_classic", "gecko_median", "brenda_ec_tree"]] = Field(
         default=None,
         description=(
-            "Kcat assignment preset; gecko_median is used when neither a preset nor "
+            "Kcat assignment preset; brenda_ec_tree is used when neither a preset nor "
             "stages are given."
         ),
     )