Release sage 2.0.0 torsion #419
Open
Conversation
This file contains 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
QCSubmit Validation Report
QC Specification Report
QCSubmit version information(click to expand)
|
lilyminium
requested changes
Dec 19, 2024
...024-12-17-OpenFF-Sage-2.0.0-Torsion-Drive-Training-Dataset-v1.0/generate-combined-dataset.py
Outdated
Show resolved
Hide resolved
...024-12-17-OpenFF-Sage-2.0.0-Torsion-Drive-Training-Dataset-v1.0/generate-combined-dataset.py
Outdated
Show resolved
Hide resolved
| rec_ids_cmiles = {} | ||
| for _, results in Opt.entries.items(): | ||
| tmp_rec_ids_cmiles = {result.record_id: result.cmiles for result in results} | ||
| # TODO: Check if updating dic would change the number of records |
Comment on lines
5
to
8
| A quantum chemical (QC) dataset curated to train the OpenFF 2.0.0 Sage torsion potentials. This QC dataset with the OpenFF default level of theory, B3LYP-D3BJ/DZVP, is used to benchmark Sage geometries and energetics. These optimized conformer geometries where used to train one dimensional torsional profiles. This Generation 2 dataset increases chemical diversity when compared to Generation 1, which are of value to our industry partners. Large molecules (>20 heavy atoms) were also included, including more flexible molecules and a greater degree of conformational variation which provide intramolecular interactions. This is the complete optimization dataset used for training OpenFF 2.0.0 Sage, consisting of the following datasets: | ||
|
|
||
| 'OpenFF Gen 2 Torsion Set 1 Roche', | ||
| 'OpenFF Gen 2 Torsion Set 2 Coverage', 'OpenFF Gen 2 Torsion Set 3 Pfizer Discrepancy', 'OpenFF Gen 2 Torsion Set 4 eMolecules - Discrepancy', 'OpenFF Gen 2 Torsion Set 5 Bayer' and 'OpenFF Gen 2 Torsion Set 6 supplemental 2'. The `HydrogenBondFilter(method='baker-hubbard')` filter was applied, and the following record IDs were dropped due to issues with ForceBalance: 6098580, 2703504, 2703505, 18045478. Further information can be found in the curation scripts for the linked repositories. |
There was a problem hiding this comment.
In the optimization training set PR you linked the OpenFF Sage repo, as well as the directories of each of the source torsion drive sets. That was quite nice, could you please do that here as well?
submissions/2024-12-17-OpenFF-Sage-2.0.0-Torsion-Drive-Training-Dataset-v1.0/README.md
Show resolved
Hide resolved
submissions/2024-12-17-OpenFF-Sage-2.0.0-Torsion-Drive-Training-Dataset-v1.0/README.md
Show resolved
Hide resolved
| { | ||
| "dataset_name": "OpenFF Sage 2.0.0 Torsion Drive Training Dataset v1.0", | ||
| "dataset_tagline": "B3LYP-D3BJ/DZVP conformers applicable to drug-like molecules for OpenFF 2.0.0 Sage", | ||
| "description": "A quantum chemical (QC) dataset curated to train the OpenFF 2.0.0 Sage torsion potentials. This QC dataset with the OpenFF default level of theory, B3LYP-D3BJ/DZVP, is used to benchmark Sage geometries and energetics. These optimized conformer geometries where used to train one dimensional torsional profiles. This Generation 2 dataset increases chemical diversity when compared to Generation 1, which are of value to our industry partners. Large molecules (>20 heavy atoms) were also included, including more flexible molecules and a greater degree of conformational variation which provide intramolecular interactions. This is the complete optimization dataset used for training OpenFF 2.0.0 Sage, consisting of the following datasets: 'OpenFF Gen 2 Torsion Set 1 Roche', 'OpenFF Gen 2 Torsion Set 2 Coverage', 'OpenFF Gen 2 Torsion Set 3 Pfizer Discrepancy', 'OpenFF Gen 2 Torsion Set 4 eMolecules - Discrepancy', 'OpenFF Gen 2 Torsion Set 5 Bayer' and 'OpenFF Gen 2 Torsion Set 6 supplemental 2'. The `HydrogenBondFilter(method='baker-hubbard')` filter was applied, and the following record IDs were dropped due to issues with ForceBalance: 6098580, 2703504, 2703505, 18045478. Further information can be found in the curation scripts for the linked repositories.", |
There was a problem hiding this comment.
Suggested change
| "description": "A quantum chemical (QC) dataset curated to train the OpenFF 2.0.0 Sage torsion potentials. This QC dataset with the OpenFF default level of theory, B3LYP-D3BJ/DZVP, is used to benchmark Sage geometries and energetics. These optimized conformer geometries where used to train one dimensional torsional profiles. This Generation 2 dataset increases chemical diversity when compared to Generation 1, which are of value to our industry partners. Large molecules (>20 heavy atoms) were also included, including more flexible molecules and a greater degree of conformational variation which provide intramolecular interactions. This is the complete optimization dataset used for training OpenFF 2.0.0 Sage, consisting of the following datasets: 'OpenFF Gen 2 Torsion Set 1 Roche', 'OpenFF Gen 2 Torsion Set 2 Coverage', 'OpenFF Gen 2 Torsion Set 3 Pfizer Discrepancy', 'OpenFF Gen 2 Torsion Set 4 eMolecules - Discrepancy', 'OpenFF Gen 2 Torsion Set 5 Bayer' and 'OpenFF Gen 2 Torsion Set 6 supplemental 2'. The `HydrogenBondFilter(method='baker-hubbard')` filter was applied, and the following record IDs were dropped due to issues with ForceBalance: 6098580, 2703504, 2703505, 18045478. Further information can be found in the curation scripts for the linked repositories.", | |
| "description": "A quantum chemical (QC) dataset curated to train the OpenFF 2.0.0 Sage torsion potentials. This QC dataset with the OpenFF default level of theory, B3LYP-D3BJ/DZVP, is used to benchmark Sage geometries and energetics. These optimized conformer geometries were used to train one dimensional torsional profiles. This Generation 2 dataset increases chemical diversity when compared to Generation 1, which are of value to our industry partners. Large molecules (>20 heavy atoms) were also included, including more flexible molecules and a greater degree of conformational variation which provide intramolecular interactions. This is the complete TorsionDrive dataset used for training OpenFF 2.0.0 Sage, consisting of the following datasets: 'OpenFF Gen 2 Torsion Set 1 Roche', 'OpenFF Gen 2 Torsion Set 2 Coverage', 'OpenFF Gen 2 Torsion Set 3 Pfizer Discrepancy', 'OpenFF Gen 2 Torsion Set 4 eMolecules - Discrepancy', 'OpenFF Gen 2 Torsion Set 5 Bayer' and 'OpenFF Gen 2 Torsion Set 6 supplemental 2'. The `HydrogenBondFilter(method='baker-hubbard')` filter was applied, and the following record IDs were dropped due to issues with ForceBalance: 6098580, 2703504, 2703505, 18045478. Further information can be found in the curation scripts for the linked repositories.", |
Some typos and suggestions.
QCSubmit Validation Report
QC Specification Report
QCSubmit version information(click to expand)
|
QCSubmit Validation Report
QC Specification Report
QCSubmit version information(click to expand)
|
QCSubmit Validation Report
QC Specification Report
QCSubmit version information(click to expand)
|
QCSubmit Validation Report
QC Specification Report
QCSubmit version information(click to expand)
|
…g-Dataset-v1.0/generate-combined-dataset.py Co-authored-by: Lily Wang <31115101+lilyminium@users.noreply.github.com>
QCSubmit Validation Report
QC Specification Report
QCSubmit version information(click to expand)
|
QCSubmit Validation Report
QC Specification Report
QCSubmit version information(click to expand)
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
New Submission Checklist
README.mddescribing the dataset see here for examplesdataset*.json; may feature a compression extension, such as.bz2README.md