Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@

## Unreleased

* `sensitivity_tuning` selects the first enzyme or reaction of the model when two have equal flux (within a relative 1e-9), as `sensitivityTuning` does. It took the first reaction of an unordered set, so a tie could give a different kcat than MATLAB.
* `kcat_evidence` shows, for selected reactions, the kcat of every source file next to the kcat of the model and, for a tuned kcat, the kcat before tuning. The reactions are selected by name (`rxns`), by enzyme (`enzymes`, for example the enzymes that `flexibilize_enz_concs` relaxed) or by the result of `sensitivity_tuning` (`tuned`); `compute=["ec_tree"]` adds the EC-tree estimate without a source file. `kcats_for_reactions` gets the kcats of every source for a few reactions, computes the EC-tree estimate and, with `okp`, predicts them with one, several or all OpenKineticsPredictor methods. `kcats_from_okp` has `job_tag`, which keeps a job for a few reactions apart from the job of all reactions: it has its own job, input and result files. GECKO has `kcatEvidence`, `kcatsForReactions` and the `jobTag` option of `kcatsFromOKP`.
* `kcats_from_ec_tree` marks a reverse direction (`_REV`) in `detail` with `direction=reverse`. The estimate depends on the EC number only, as BRENDA measurements have no direction, so the reverse direction has the value of the forward direction. GECKO's `kcatsFromECTree` does the same.
* `load_uniprot_tsv` always splits a gene cell of uniprot.tsv with several gene names, separated by semicolons and/or whitespace (`YPR080W; YBR118W`), into one row per gene name; the other columns are repeated on every row and an empty cell stays one row. A model gene that is any of the names finds the entry. The `split_gene_cells` option is removed. GECKO's `loadDatabases` does the same.
Expand Down
57 changes: 28 additions & 29 deletions src/geckopy/kcat_tuning/sensitivity_tuning.py
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@
# Growth is considered stalled when an iteration improves it by no more
# than this (absolute, 1/h). Using a tolerance instead of exact equality
# avoids spinning on sub-numerical-noise increases.
_TIE_TOL = 1e-9
_GROWTH_STALL_TOL = 1e-9


Expand Down Expand Up @@ -303,17 +304,15 @@ def sensitivity_tuning(
tuned_ec_indices.append(ec_rows[0])
continue

# Pick usage rxn with max flux (= most produced enzyme),
# excluding any in prot_to_ignore.
# Pick the usage rxn with the largest flux (the most produced enzyme),
# excluding any in prot_to_ignore. Ties go to the first rxn of the model.
usage_ids = [uid for uid in usage_rxn_ids if uid not in ignore_usage_ids]
usage_fluxes = [float(sol.fluxes.get(uid, 0.0)) for uid in usage_ids]
best_usage_id: Optional[str] = None
best_usage_flux = -np.inf
for uid in usage_rxn_ids:
if uid in ignore_usage_ids:
continue
f = float(sol.fluxes.get(uid, 0.0))
if f > best_usage_flux:
best_usage_flux = f
best_usage_id = uid
if usage_ids:
k = _first_tied(usage_fluxes, largest=True)
best_usage_id, best_usage_flux = usage_ids[k], usage_fluxes[k]

if best_usage_id is None or best_usage_flux <= 0:
logger.warning(
Expand All @@ -337,17 +336,13 @@ def sensitivity_tuning(
# Find the catalysed rxn consuming the most of this protein.
# Consumption: S[prot, rxn] < 0 with positive flux -> negative product.
# The rxn with the most-negative S[prot] * flux is selected.
# Ties go to the first rxn of the model.
position = {r.id: i for i, r in enumerate(model.reactions)}
consumers = sorted((r for r in prot_met.reactions if r.id != best_usage_id), key=lambda r: position[r.id])
values = [r.metabolites[prot_met] * float(sol.fluxes.get(r.id, 0.0)) for r in consumers]
target_rxn = None
target_value = 0.0
for rxn in prot_met.reactions:
if rxn.id == best_usage_id:
continue
coeff = rxn.metabolites[prot_met]
flux = float(sol.fluxes.get(rxn.id, 0.0))
value = coeff * flux
if value < target_value:
target_value = value
target_rxn = rxn
if values and min(values) < 0:
target_rxn = consumers[_first_tied(values, largest=False)]

if target_rxn is None:
logger.warning(
Expand Down Expand Up @@ -391,6 +386,16 @@ def sensitivity_tuning(
return result


def _first_tied(values: list[float], *, largest: bool) -> int:
"""Index of the first value that ties with the extreme value, that is,
that differs from it by less than a relative ``_TIE_TOL``."""
arr = np.asarray(values, dtype=float)
best = arr.max() if largest else arr.min()
tol = _TIE_TOL * max(1.0, abs(best))
hits = np.flatnonzero(arr >= best - tol if largest else arr <= best + tol)
return int(hits[0])


def _mark_tuned(model: "EcModel", ec_idx: int) -> None:
"""Add the tuning method to the source of one ec row.

Expand Down Expand Up @@ -446,17 +451,11 @@ def _light_step(
"""The ec rows of the reaction with the most flux through the protein
pool (gecko-light), or ``None`` when no reaction draws on it."""
pool = model.metabolites.get_by_id(POOL_ID)
best_id: Optional[str] = None
best_value = 0.0
for rxn in model.reactions:
if rxn.id in ignore_rxn_ids or pool not in rxn.metabolites:
continue
value = rxn.metabolites[pool] * float(sol.fluxes.get(rxn.id, 0.0))
if value < best_value:
best_value = value
best_id = rxn.id
if best_id is None:
candidates = [r for r in model.reactions if r.id not in ignore_rxn_ids and pool in r.metabolites]
values = [r.metabolites[pool] * float(sol.fluxes.get(r.id, 0.0)) for r in candidates]
if not values or min(values) >= 0:
return None
best_id = candidates[_first_tied(values, largest=False)].id
rows = [
i for i, ec_id in enumerate(model.ec.rxns)
if split_light_rxn_id(ec_id)[1] == best_id
Expand Down
52 changes: 52 additions & 0 deletions tests/test_sensitivity_tuning.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
"""Tests for sensitivity_tuning."""
import importlib
from pathlib import Path

import cobra
Expand Down Expand Up @@ -319,3 +320,54 @@ def test_docstrings_name_the_standard_and_advanced_tuning():

assert "standard kcat tuning" in sensitivity_tuning.__doc__
assert "advanced kcat tuning" in cmaes_kcat_tuning.__doc__


# --------------------------------------------------------------------------- #
# Ties
# --------------------------------------------------------------------------- #

class _Solution:
status = "optimal"

def __init__(self, objective_value, fluxes):
self.objective_value = objective_value
self.fluxes = fluxes


@pytest.mark.parametrize("first", ["R", "R2"])
def test_a_tie_between_reactions_of_an_enzyme_goes_to_the_first_in_the_model(tmp_path, monkeypatch, first):
"""R and R2 consume the same amount of prot_E: the first one in the model is tuned."""
adapter = _adapter(tmp_path, gr_exp=50.0)
model = _build_toy(adapter)
r2 = cobra.Reaction("R2")
r2.add_metabolites({
model.metabolites.get_by_id("A_c"): -1.0,
model.metabolites.get_by_id("prot_E"): model.reactions.get_by_id("R").metabolites[model.metabolites.get_by_id("prot_E")],
model.metabolites.get_by_id("bio_met"): 1.0,
})
r2.bounds = (0.0, 1000.0)
model.add_reactions([r2])
if first == "R2":
r = model.reactions.get_by_id("R")
model.remove_reactions([r])
model.add_reactions([r])
model.ec.rxns = ["R", "R2"]
model.ec.kcat = np.array([1.0, 1.0])
model.ec.source = ["initial", "initial"]
model.ec.notes = ["", ""]
model.ec.eccodes = ["", ""]
model.ec.rxn_enz_mat = sparse.csr_matrix([[1.0], [1.0]])
consumption = {"usage_prot_E": 2.0, "R": 1.0, "R2": 1.0}
answers = iter([_Solution(1.0, consumption), _Solution(100.0, consumption)])
monkeypatch.setattr(importlib.import_module("geckopy.kcat_tuning.sensitivity_tuning"), "optimize_model", lambda m: next(answers))
result = sensitivity_tuning(model, fold_change=10.0, verbose=False)
assert list(result.rxns) == [first]


def test_first_tied_takes_the_first_value_within_the_tolerance():
from geckopy.kcat_tuning.sensitivity_tuning import _first_tied

assert _first_tied([1.0, 3.0, 3.0 - 1e-12, 2.0], largest=True) == 1
assert _first_tied([3.0 - 1e-12, 3.0, 1.0], largest=True) == 0
assert _first_tied([-1.0, -3.0, -3.0, -2.0], largest=False) == 1
assert _first_tied([-2.0, -3.0], largest=False) == 1
Loading