Skip to content
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

updated bioavailability_ma_et_al #366

Closed
wants to merge 3 commits into from
Closed

updated bioavailability_ma_et_al #366

Changes from 2 commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
4d58c0e
updated bioavailability_ma_et_al
bethanyconnolly Jul 20, 2023
6e5d829
corrected templated to say if smiles is valid or not
bethanyconnolly Jul 20, 2023
6c64765
Update data/tabular/bioavailability_ma_et_al/transform.py
MicPie Jul 26, 2023
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
15 changes: 8 additions & 7 deletions data/tabular/bioavailability_ma_et_al/transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,7 @@ def get_and_transform_data():
"type": "boolean",
"names": [ # names for the property (to sample from for building the prompts)
{"noun": "oral bioavailability"},
{"noun": "bioavailability"},
{"adjective": "bioavailable"},
{"adjective": "orally bioavailable"},
],
"uris": [
"http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#C70913",
Expand Down Expand Up @@ -99,6 +98,8 @@ def get_and_transform_data():
{
"url": "https://tdcommons.ai/single_pred_tasks/adme/#bioavailability-ma-et-al",
"description": "data source",
# note: this is not the original data, it is their modified version
# original larger dataset: http://modem.ucsd.edu/adme/databases/databases_bioavailability.htm
},
],
"num_points": len(df), # number of datapoints in this dataset
Expand All @@ -118,19 +119,19 @@ def get_and_transform_data():
journal = {Journal of Pharmaceutical and Biomedical Analysis}""",
],
"templates": [
"The molecule with the {SMILES__description} representation of {SMILES#} is {bioavailable#not &NULL}{bioavailable__names__adjective}.", # noqa: E501
"The molecule with the {SMILES__description} representation {SMILES#} is {bioavailable#not &NULL}{bioavailable__names__adjective}.", # noqa: E501
"Based on the {SMILES__description} representation {SMILES#}, the molecule is {bioavailable#not &NULL}{bioavailable__names__adjective}.", # noqa: E501
"The {SMILES__description} {SMILES#} represents a molecule that is {bioavailable#not &NULL}identified as {bioavailable__names__adjective}.", # noqa: E501
"The {SMILES__description} {SMILES#} is {bioavailable#not &NULL}{bioavailable__names__adjective}.",
"The molecule {SMILES#} is {bioavailable__names__adjective}.",
"Is the {SMILES__description} {SMILES#} {bioavailable__names__adjective}:<EOI> {bioavailable#yes&no}", # noqa: E501 for the benchmarking setup <EOI> separates input and output
"The molecule {SMILES#} is {bioavailable#not &NULL}{bioavailable__names__adjective}.",
"Is the {SMILES__description} {SMILES#} {bioavailable__names__adjective}?:<EOI> {bioavailable#yes&no}", # noqa: E501 for the benchmarking setup <EOI> separates input and output
MicPie marked this conversation as resolved.
Show resolved Hide resolved
"""Task: Please answer the multiple choice question below with {%multiple_choice_enum%2%aA1}.
Question: Is the molecule with the {SMILES__description} representation of {SMILES#} {bioavailable__names__adjective}?
Question: Is the molecule with the {SMILES__description} representation {SMILES#} {bioavailable__names__adjective}?
Options:
{bioavailable%}
Answer: {%multiple_choice_result}""",
"""Task: Please answer the multiple choice question below with {%multiple_choice_enum%2%aA1}.
Question: Is the molecule with the {SMILES__description} representation of {SMILES#} {bioavailable__names__adjective}?
Question: Is the molecule with the {SMILES__description} representation {SMILES#} {bioavailable__names__adjective}?
Options:
{bioavailable%}
Answer:<EOI> {%multiple_choice_result}""",
Expand Down