Merge pull request #173 from bioexcel/master

New biobb_pytorch Molecular dynamics autoencoder wrapper
galaxycomputationalchemistry · Dec 5, 2024 · 891dd7d · 891dd7d
2 parents 3c6707a + aca822a
commit 891dd7d
Show file tree

Hide file tree

Showing 7 changed files with 207 additions and 0 deletions.
diff --git a/tools/biobb_pytorch/.shed.yml b/tools/biobb_pytorch/.shed.yml
@@ -0,0 +1,20 @@
+name: biobb_pytorch
+owner: chemteam
+description: "biobb_pytorch is the Biobb module collection to create and train ML & DL models using the popular [PyTorch](https://pytorch.org/) Python library."
+homepage_url: https://github.com/bioexcel/biobb_pytorch
+long_description: |
+    biobb_pytorch is the Biobb module collection to create and train ML & DL models using the popular [PyTorch](https://pytorch.org/) Python library.
+    Biobb (BioExcel building blocks) packages are Python building blocks that
+    create new layer of compatibility and interoperability over popular
+    bioinformatics tools.
+    The latest documentation of this package can be found in our readthedocs site:
+    [latest API documentation](http://biobb-pytorch.readthedocs.io/en/latest/).
+remote_repository_url: https://github.com/galaxycomputationalchemistry/galaxy-tools-compchem/tree/master/tools/biobb_pytorch
+type: unrestricted
+categories:
+- Molecular Dynamics
+- Computational chemistry
+maintainers:
+  - PauAndrio
+  - gbayarri
+  - adamhospital
diff --git a/tools/biobb_pytorch/biobb_apply_mdae.xml b/tools/biobb_pytorch/biobb_apply_mdae.xml
@@ -0,0 +1,84 @@
+<tool id="biobb_pytorch_apply_mdae" name="ApplyMdae" version="@TOOL_VERSION@" profile="22.05">
+    <description>Apply a Molecular Dynamics AutoEncoder (MDAE) PyTorch model.</description>
+    <macros>
+      <token name="@TOOL_VERSION@">4.2.1</token>
+    </macros>
+
+    <requirements>
+      <requirement type="package" version="@TOOL_VERSION@">biobb_pytorch</requirement>
+    </requirements>
+
+    <command detect_errors="exit_code"><![CDATA[
+
+      ln -s '$input_data_npy_path' ./input_data_npy_path.$input_data_npy_path.ext &&
+      ln -s '$input_model_pth_path' ./input_model_pth_path.pth &&
+
+      #if $config_json:
+        ln -s '$config_json' ./config_json.$config_json.ext &&
+      #end if
+
+      apply_mdae
+
+      #if $config_json:
+        --config ./config_json.$config_json.ext
+      #end if
+
+      --input_data_npy_path ./input_data_npy_path.$input_data_npy_path.ext
+      --input_model_pth_path ./input_model_pth_path.pth
+      #if $output_latent_space_npy_path:
+      --output_latent_space_npy_path ./output_latent_space_npy_path.npy
+      #end if
+      --output_reconstructed_data_npy_path ./output_reconstructed_data_npy_path.npy
+      ;
+      ]]>
+    </command>
+
+    <inputs>
+      <param name="input_data_npy_path"  type="data" format="npy"  optional="False" label="Input NPY file" help="Input data file"/>
+      <param name="input_model_pth_path" type="data" format="pth"  optional="False" label="Input PTH file" help="Input model file"/>
+      <param name="config_json" type="data" format="json" optional="True" label="Configuration file" help="File containing tool settings"/>
+    </inputs>
+
+    <outputs>
+      <data format="npy" name="output_reconstructed_data_npy_path" from_work_dir="output_reconstructed_data_npy_path.npy" label="output_reconstructed_data_npy_path" />
+      <data format="npy" name="output_latent_space_npy_path" from_work_dir="output_latent_space_npy_path.npy" label="output_latent_space_npy_path" />
+    </outputs>
+
+    <tests>
+        <test>
+          <param name="config_json" value="config_apply_mdae.json" ftype="json" />
+          <param name="input_data_npy_path"  value="train_mdae_traj.npy" ftype="npy" />
+          <param name="input_model_pth_path" value="ref_output_model.pth" />
+          <output name="output_reconstructed_data_npy_path" ftype="npy">
+            <assert_contents>
+              <has_size value="123k" delta="50k"/>
+            </assert_contents>
+          </output>
+          <output name="output_latent_space_npy_path" ftype="npy">
+            <assert_contents>
+              <has_size value="928" delta="200"/>
+            </assert_contents>
+          </output>
+        </test>
+    </tests>
+
+    <help>
+.. class:: infomark
+
+Check the syntax for the tool parameters at the original library documentation: https://biobb-pytorch.readthedocs.io/en/latest
+   </help>
+
+    <citations>
+        <citation type="bibtex">
+            @misc{githubbiobb,
+            author = {Andrio P, Bayarri, G., Hospital A, Gelpi JL},
+            year = {2019-21},
+            title = {biobb: BioExcel building blocks },
+            publisher = {GitHub},
+            journal = {GitHub repository},
+            url = {https://github.com/bioexcel/biobb_pytorch},
+            }
+        </citation>
+        <citation type="doi">10.1038/s41597-019-0177-4</citation>
+    </citations>
+</tool>
diff --git a/tools/biobb_pytorch/biobb_train_mdae.xml b/tools/biobb_pytorch/biobb_train_mdae.xml
@@ -0,0 +1,92 @@
+<tool id="biobb_pytorch_train_mdae" name="TrainMdae" version="@TOOL_VERSION@" profile="22.05">
+    <description>Train a Molecular Dynamics AutoEncoder (MDAE) PyTorch model</description>
+    <macros>
+      <token name="@TOOL_VERSION@">4.2.1</token>
+    </macros>
+
+    <requirements>
+      <requirement type="package" version="@TOOL_VERSION@">biobb_pytorch</requirement>
+    </requirements>
+
+    <command detect_errors="exit_code"><![CDATA[
+
+      ln -s '$input_train_npy_path' ./input_train_npy_path.$input_train_npy_path.ext &&
+
+      #if $input_model_pth_path:
+        ln -s '$input_model_pth_path' ./input_model_pth_path.$input_model_pth_path.ext &&
+      #end if
+      #if $config_json:
+        ln -s '$config_json' ./config_json.$config_json.ext &&
+      #end if
+
+      train_mdae
+
+      #if $config_json:
+        --config ./config_json.$config_json.ext
+      #end if
+
+      --input_train_npy_path ./input_train_npy_path.$input_train_npy_path.ext
+      #if $input_model_pth_path:
+        --input_model_pth_path ./input_model_pth_path.$input_model_pth_path.ext
+      #end if
+      --output_model_pth_path ./output_model_pth_path.pth
+      #if $output_train_data_npz_path:
+        --output_train_data_npz_path ./output_train_data_npz_path.npz
+      #end if
+      #if $output_performance_npz_path:
+        --output_performance_npz_path ./output_performance_npz_path.npz
+      #end if
+      ;
+      ]]>
+    </command>
+
+    <inputs>
+      <param name="input_train_npy_path" type="data" format="npy"  optional="False" label="Input NPY file" help="Input train NPY data file"/>
+      <param name="input_model_pth_path" type="data" format="pth"  optional="True" label="Input PTH file" help="Input model PTH file"/>
+      <param name="config_json" type="data" format="json" optional="True" label="Configuration file" help="File containing tool settings"/>
+    </inputs>
+
+    <outputs>
+      <data format="pth" name="output_model_pth_path" from_work_dir="output_model_pth_path.pth" label="output_model_pth_path" />
+      <data format="npz" name="output_train_data_npz_path" from_work_dir="output_train_data_npz_path.npz" label="output_train_data_npz_path" />
+      <data format="npz" name="output_performance_npz_path" from_work_dir="output_performance_npz_path.npz" label="output_performance_npz_path" />
+    </outputs>
+
+    <tests>
+      <test>
+        <param name="config_json" value="config_train_mdae.json" ftype="json" />
+        <param name="input_train_npy_path" value="train_mdae_traj.npy" ftype="npy" />
+        <output name="output_model_pth_path"       file="ref_output_model.pth" compare="sim_size" />
+        <output name="output_train_data_npz_path">
+          <assert_contents>
+            <has_size value="1k" delta="500"/>
+          </assert_contents>
+        </output>
+        <output name="output_performance_npz_path">
+          <assert_contents>
+            <has_size value="124k" delta="50k"/>
+          </assert_contents>
+        </output>
+      </test>
+    </tests>
+
+    <help>
+.. class:: infomark
+
+Check the syntax for the tool parameters at the original library documentation: https://biobb-pytorch.readthedocs.io/en/latest
+   </help>
+
+    <citations>
+        <citation type="bibtex">
+            @misc{githubbiobb,
+            author = {Andrio P, Bayarri, G., Hospital A, Gelpi JL},
+            year = {2019-21},
+            title = {biobb: BioExcel building blocks },
+            publisher = {GitHub},
+            journal = {GitHub repository},
+            url = {https://github.com/bioexcel/biobb_pytorch},
+            }
+        </citation>
+        <citation type="doi">10.1038/s41597-019-0177-4</citation>
+    </citations>
+</tool>
diff --git a/tools/biobb_pytorch/test-data/config_apply_mdae.json b/tools/biobb_pytorch/test-data/config_apply_mdae.json
@@ -0,0 +1,5 @@
+{
+  "properties": {
+    "batch_size": 1
+  }
+}
diff --git a/tools/biobb_pytorch/test-data/config_train_mdae.json b/tools/biobb_pytorch/test-data/config_train_mdae.json
@@ -0,0 +1,6 @@
+{
+  "properties": {
+    "num_epochs": 50,
+    "seed": 1
+  }
+}
diff --git a/tools/biobb_pytorch/test-data/ref_output_model.pth b/tools/biobb_pytorch/test-data/ref_output_model.pth
diff --git a/tools/biobb_pytorch/test-data/train_mdae_traj.npy b/tools/biobb_pytorch/test-data/train_mdae_traj.npy