Merge pull request #6 from volkamerlab/v2_updates

V2 release updates
volkamerlab · Apr 8, 2024 · 53ae033 · 53ae033
2 parents 85ab654 + 49f80cf
commit 53ae033
Show file tree

Hide file tree

Showing 5 changed files with 6 additions and 6 deletions.
diff --git a/README.md b/README.md
@@ -18,7 +18,7 @@ and install this package in editable/develop mode
 pip install -e .
 ```
 ### (3) Obtain raw data
-The raw data, docked poses and kinase pdb files, can be obtained [from Zenodo](https://zenodo.org/records/10410259). 
+The raw data, docked poses and kinase pdb files, can be obtained [from Zenodo](https://zenodo.org/records/10852507). 
 After downloading the archives, extract them in the root directory of this repository.
 ```
 cd PATH_TO_REPO
@@ -33,7 +33,7 @@ See the [Kinodata-3D repo](https://github.com/volkamerlab/kinodata-3D) for more
 
 ## Reproducing results
 ### (1) Acquire exact dataset and data split versions
-If you intend to reproduce our results, we strongly recommend that you use [our preprocessed version of the dataset and corresponding data splits](https://zenodo.org/records/10410594).
+If you intend to reproduce our results, we strongly recommend that you use [our preprocessed version of the dataset and corresponding data splits](https://zenodo.org/records/10886085).
 
 ### (2) Model training and evaluation
 You can use the shell script `condor/train_generic.sh` to train and test a model in one run, on one particular split.

diff --git a/condor/train_generic.sh b/condor/train_generic.sh
@@ -1,3 +1,3 @@
-cd /home/jgross/kinodata-docked-rescore
+cd ${HOME}/kinodata-3D-affinity-prediction
 export WANDB_API_KEY=$(cat wandb_api_key)
 python3 scripts/$1.py --split_type $2 --split_index $5 --config $4 --filter_rmsd_max_value $3
diff --git a/examples/data_splits.ipynb b/examples/data_splits.ipynb
@@ -98,7 +98,7 @@
    "metadata": {},
    "source": [
     "### Pre-computed splits and preprocessed dataset\n",
-    "The splits used in [the Kinodata-3D publication](https://chemrxiv.org/engage/chemrxiv/article-details/658441f7e9ebbb4db96d98e8) are [available on Zenodo](https://zenodo.org/records/10410594) and\n",
+    "The splits used in [the Kinodata-3D publication](https://chemrxiv.org/engage/chemrxiv/article-details/658441f7e9ebbb4db96d98e8) are [available on Zenodo](https://zenodo.org/records/10886085) and\n",
     "are guaranteed to be compatible with the preprocessed version of the dataset available through the same Zenodo record.\n",
     "\n",
     "The following code snippet briefly demonstrates how to recreate the data modules we used to train the published models."

diff --git a/examples/dataset.ipynb b/examples/dataset.ipynb
@@ -115,7 +115,7 @@
     "Instantiating the dataset for the first time will trigger the data preprocessing, which creates the PyG data objects.\n",
     "This process takes a while (~ 1 hour on a 2021 MacBook Pro), but the result is cached on disk to accelerate future instantiations.\n",
     "\n",
-    "**Note**: you may also obtain our [preprocessed version of the dataset](https://zenodo.org/records/10410594)."
+    "**Note**: you may also obtain our [preprocessed version of the dataset](https://zenodo.org/records/10886085)."
    ]
   },
   {

diff --git a/examples/models.ipynb b/examples/models.ipynb
@@ -6,7 +6,7 @@
    "source": [
     "## Validating pre-trained models\n",
     "This code demonstrates how to load our trained models and one way of doing using them for inference.\n",
-    "It requires that you downloaded and extracted the [pretrained models and the corresponding preprocessed version of kinodata-3D](https://zenodo.org/records/10410594)\n",
+    "It requires that you downloaded and extracted the [pretrained models and the corresponding preprocessed version of kinodata-3D](https://zenodo.org/records/10886085)\n",
     "in the root directory of this repository."
    ]
   },