Add Parsley 1.3.1

.github/workflows/run.yaml

@@ -152,13 +152,30 @@ jobs:
 
           echo input_dir="${input_dir}" >> $GITHUB_ENV
 
+      - name: tar results
+        shell: bash -l {0}
+        run: |
+          bzip2 tmp.sqlite
+          micromamba env export > env.yaml
+          input_files=$(python get_files.py ${{ inputs.path }})
+          tar cf results.tar \
+            tmp.sqlite.bz2 $input_dir/output/{dde,icrmsd,rmsd,tfd}.csv \
+            $input_dir/output/{dde,rmsd,rmsd_cdf,tfd,tfd_cdf,bonds,angles,dihedrals,impropers}.png \
+            env.yaml main.py $input_files
+
+      - name: Archive results
+        uses: actions/upload-artifact@v4
+        with:
+          name: results
+          path: results.tar
+          retention-days: 14
+
       - name: Upload to zenodo
         env:
             ZENODO_TOKEN: ${{ secrets.ZENODO_TOKEN }}
+            ZENODO_URL:  "https://zenodo.org"
         shell: bash -l {0}
         run: |
-          bzip2 tmp.sqlite
-          micromamba env export > env.yaml
           input_files=$(python get_files.py ${{ inputs.path }})
           python zenodo_upload.py --title "YDS Upload ${{ inputs.pr_number }}" \
             tmp.sqlite.bz2 $input_dir/output/{dde,icrmsd,rmsd,tfd}.csv \

README.md

@@ -48,13 +48,15 @@ See [datasets/README.md](datasets/README.md)
 
 ## Benchmark Results
 
-| Submission                 | Description                       | DOI                                                                |
-|----------------------------|-----------------------------------|--------------------------------------------------------------------|
-| [Sage-2.1.0]               | Constrained openff-2.1.0.offxml   | [10.5281/zenodo.14053221](https://doi.org/10.5281/zenodo.14053221) |
-| [Sage-2.1.0-unconstrained] | Unconstrained openff-2.1.0.offxml | [10.5281/zenodo.14058464](https://doi.org/10.5281/zenodo.14058464) |
+| Submission                    | Description                       | DOI                                                                |
+|-------------------------------|-----------------------------------|--------------------------------------------------------------------|
+| [Sage-2.1.0]                  | Constrained openff-2.1.0.offxml   | [10.5281/zenodo.14053221](https://doi.org/10.5281/zenodo.14053221) |
+| [Sage-2.1.0-unconstrained]    | Unconstrained openff-2.1.0.offxml | [10.5281/zenodo.14058464](https://doi.org/10.5281/zenodo.14058464) |
+| [Parsley-1.3.1-unconstrained] | Unconstrained openff-1.3.1.offxml | [10.5281/zenodo.14172472](https://doi.org/10.5281/zenodo.14172472) |
 
 [Sage-2.1.0]: submissions/2024-11-07-Sage-2.1.0
 [Sage-2.1.0-unconstrained]: submissions/2024-11-08-Sage-2.1.0-unconstrained
+[Parsley-1.3.1-unconstrained]: submissions/2024-11-13-Parsley-1.3.1
 
 
 <!-- References -->

datasets/OpenFF-Industry-Benchmark-Season-1-v1.1/README.md

@@ -5,3 +5,12 @@ Namely, the dataset name and `chunksize` are now passed via the command line
 rather than being part of a config file (`industry.yaml` in this case). For that
 reason, a copy of the version of `download_and_filter_dataset.py` (previously
 called `new_dataset.py`) is also included here.
+
+Additionally, the cache file `first100.json` contains the first 100 entries in
+from `cache.json` for testing purposes. This file was produced by manipulating
+`cache.json` with `jq`:
+
+``` shell
+jq '{qm_molecules: .qm_molecules[:100], tag: .tag, version: .version}' cache.json > first100.json
+```
+

devtools/env.yaml

@@ -22,4 +22,4 @@ dependencies:
   - tqdm
 
   - pip:
-    - git+https://github.com/openforcefield/[email protected].0beta1
+    - git+https://github.com/openforcefield/[email protected].0

get_files.py

@@ -1,11 +1,24 @@
 # read the config file supplied as the first argument and write the associated
-# files to stdout
+# files to stdout, if they exist
 
+import logging
 import sys
+from pathlib import Path
 
 from config import Config
 
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger("get_files.py")
+
+
+def maybe_print(path):
+    if Path(path).exists():
+        print(path)
+    else:
+        logger.warning(f"skipping non-existent file: {path}")
+
+
 conf = Config.from_file(sys.argv[1])
-print(conf.forcefield)
+maybe_print(conf.forcefield)
 for ds in conf.datasets:
-    print(ds)
+    maybe_print(ds)