feat(training): generalize build_properties.py + curated volatile list - #62
Merged
Merged
Conversation
…volatile list - build_properties.py now takes --molecules <csv|parquet> (a 'smiles' or 'inchikey' column) instead of being hardcoded to taste_master, and MERGES into properties.parquet so sets accumulate (taste, aroma/GS-LF, a customer's list — point it at each in turn). PubChem physical properties are public domain, so this is clean even for GS-LF molecules in the academic edition (only the GS-LF odor labels are NonCommercial). - flavor_volatiles.csv: a curated list of 105 common flavor volatiles (esters, terpenes, aldehydes, phenolics, lactones, pyrazines, sulfur notes, acids). These are VOLATILE — unlike the taste set — so PubChem BP/VP coverage is high, giving the demo measured values for the compounds people actually type (vanillin, limonene, ethyl acetate, …). Signed-off-by: Austin L. <86896075+rvnminers-A-and-N@users.noreply.github.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Answers the academic/GS-LF + customer-data question, and fixes the sparse-coverage problem.
Generalized builder
build_properties.pynow takes--molecules <csv|parquet>(asmilesorinchikeycolumn) instead of being hardcoded totaste_master, and merges intoproperties.parquetso you accumulate sets — taste molecules, aroma/GS-LF molecules, a customer's list — by pointing--moleculesat each.Curated volatile list
flavor_volatiles.csv— 105 common flavor volatiles (esters, terpenes, aldehydes, phenolics, lactones, pyrazines, sulfur, acids), all SMILES validated. Unlike tastants, these boil — so PubChem BP/VP coverage is high, giving the demo measured values for the compounds people actually type. Build running now; counts to follow.