Skip to content

fix(training): lift sour-rule recall 0.57 → 0.93 (match acid anions) #42

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
rvnminers-A-and-N merged 1 commit into from
Jun 26, 2026
Merged

fix(training): lift sour-rule recall 0.57 → 0.93 (match acid anions) #42

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 6 additions & 3 deletions training/predict.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,9 +55,12 @@
TASTE = Path("taste_models")

ACID_SMARTS = {
"carboxylic acid": "[CX3](=O)[OX2H1]",
"sulfonic acid": "[SX4](=O)(=O)[OX2H1]",
"phosphoric/phosphonic acid": "[PX4](=O)[OX2H1]",
# Match both protonated (-OH) and deprotonated (-O-) forms — sour compounds are
# routinely drawn as carboxylate/sulfonate/phosphate anions or zwitterions.
# (Lifted the rule's recall on labeled-sour from 0.57 to 0.93.)
"carboxylic acid / carboxylate": "[CX3](=O)[OX2H1,OX1-]",
"sulfonic / sulfonate": "[SX4](=O)(=O)[OX2H1,OX1-]",
"phosphoric / phosphonic (+ anion)": "[PX4](=O)[OX2H1,OX1-]",
}
_ACID = {k: Chem.MolFromSmarts(v) for k, v in ACID_SMARTS.items()}

Expand Down
5 changes: 4 additions & 1 deletion training/train_taste.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,7 +49,10 @@

# Acidic-group SMARTS — used both for the sour rule and to VALIDATE it against
# whatever labeled sour compounds exist (so that data isn't wasted either).
ACID_SMARTS = ["[CX3](=O)[OX2H1]", "[SX4](=O)(=O)[OX2H1]", "[PX4](=O)[OX2H1]"]
# Match BOTH protonated (-OH) and deprotonated (-O-) forms: sour compounds are
# routinely drawn as carboxylate/sulfonate/phosphate anions or zwitterions, which
# the -OH-only patterns missed (the main driver of the low recall).
ACID_SMARTS = ["[CX3](=O)[OX2H1,OX1-]", "[SX4](=O)(=O)[OX2H1,OX1-]", "[PX4](=O)[OX2H1,OX1-]"]
_ACID = [Chem.MolFromSmarts(s) for s in ACID_SMARTS]


Expand Down
Loading