[WIP] Add retip tool suit wrapper(s)

tools/retip/.shed.yml

@@ -0,0 +1,16 @@
+categories:
+  - Metabolomics
+owner: "recetox"
+remote_repository_url: "https://github.com/RECETOX/galaxytools/tree/master/tools/retip"
+homepage_url: "https://github.com/PaoloBnn/Retip"
+type: unrestricted
+auto_tool_repositories:
+  name_template: "{{ tool_id }}"
+  description_template: "The tool {{ tool_name }} from the Retip tool suite."
+suite:
+  name: "suite_retip"
+  description: "A suite of Retip (Retention Time Prediction for metabolomics) tools."
+  long_description: |
+    "Retip is an R package for predicting Retention Time (RT) for small molecules in a
+    high pressure liquid chromatography (HPLC) Mass Spectrometry analysis. Retention
+    time calculation can be useful in identifying unknowns and removing false positive annotations.

tools/retip/macros.xml

@@ -0,0 +1,37 @@
+<macros>
+    <token name="@VERSION@">1.0.0</token>
+    <xml name="requirements">
+        <requirements>
+            <container type="docker">registry.gitlab.ics.muni.cz:443/recetox/mass-spectrometry/retip:@VERSION@</container>
+        </requirements>
+    </xml>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">https://doi.org/10.1021/acs.analchem.9b05765</citation>
+        </citations>
+    </xml>
+    <token name="@HELP@"><![CDATA[
+Retip is an R package for predicting Retention Time (RT) for small molecules in a high pressure liquid
+chromatography (HPLC) Mass Spectrometry analysis. Retention time calculation can be useful in identifying
+unknowns and removing false positive annotations. It uses five different machine learning algorithms to built a
+stable, accurate and fast RT prediction model:
+
+- Random Forest: a decision tree algorithms
+- BRNN: Bayesian Regularized Neural Network
+- XGBoost: an extreme Gradient Boosting for tree algorithms
+- lightGBM: a gradient boosting framework that uses tree based learning algorithms.
+- Keras: a high-level neural networks API for Tensorflow
+
+Retip also includes useful biochemical databases like: BMDB, ChEBI, DrugBank, ECMDB, FooDB, HMDB, KNApSAcK,
+PlantCyc, SMPDB, T3DB, UNPD, YMDB and STOFF.
+
+**Get started**
+
+To use Retip, a user needs to prepare a compound retention time library. The input file
+needs compound Name, InChiKey, SMILES code and experimental retention time information for each compound.
+The input must be a CSV file. Retip will use this input file to build a the model and will predict
+retention times for other biochemical databases or an input query list of compounds. It is suggested that
+the file has at least 300 compounds to build a good retention time prediction model.
+    ]]>
+    </token>
+</macros>

tools/retip/retip_apply.xml

@@ -0,0 +1,31 @@
+<tool id="retip_apply" name="Retip prediction" version="@VERSION@">
+    <description>is retention time predictor for Metabolomics</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+           /run.sh spell.R '$descr_train' '$model_hdf5' '$input' 'SMILES'
+      ]]>
+    </command>
+
+    <inputs>
+        <param name="descr_train" label="Select Descriptors.Feather Dataset" type="data" format="feather"
+               optional="false"/>
+        <param name="model_hdf5" label="Select Model.hdf5 Dataset" type="data" format="h5" optional="false"/>
+        <param name="input" label="Select Input Dataset" type="data" format="tabular" optional="false"/>
+    </inputs>
+
+    <outputs>
+        <data format="tabular" name="output" label="Predicted RT" from_work_dir="SMILES"/>
+    </outputs>
+    <help><![CDATA[
+.. class:: infomark
+
+This tool is used for **Retention Time Prediction** on a whole database.
+
+@HELP@
+        ]]>
+    </help>
+    <expand macro="citations"/>
+</tool>

tools/retip/retip_descriptors.xml

@@ -0,0 +1,29 @@
+<tool id="retip_descriptors" name="Retip chemical descriptors" version="@VERSION@">
+    <description>for retention time prediction</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+          /run.sh chemdesc.R '$compounds' 'descriptors.feather'
+      ]]>
+    </command>
+
+    <inputs>
+        <param name="compounds" label="Select Compounds Dataset" type="data" format="tabular" optional="false"/>
+    </inputs>
+
+    <outputs>
+        <data format="feather" name="output_file1" label="Descriptors.Feather Dataset"
+              from_work_dir="descriptors.feather"/>
+    </outputs>
+    <help><![CDATA[
+.. class:: infomark
+
+This tool **computes chemical descriptors** with CDK a JAVA based open source project aimed at cheminformatics.
+
+@HELP@
+        ]]>
+    </help>
+    <expand macro="citations"/>
+</tool>

tools/retip/retip_train.xml

@@ -0,0 +1,29 @@
+<tool id="retip_train" name="Retip training" version="@VERSION@">
+    <description>the Keras model to predict retention times</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+            /run.sh trainKeras.R '$descr_train' 'model.hdf5'
+      ]]>
+    </command>
+
+    <inputs>
+        <param name="descr_train" label="Select Descriptors.Feather Dataset" type="data" format="feather"
+               optional="false"/>
+    </inputs>
+
+    <outputs>
+        <data format="h5" name="output_file2" label="Model.hdf5 Dataset" from_work_dir="model.hdf5"/>
+    </outputs>
+    <help><![CDATA[
+.. class:: infomark
+
+This tool uses ALMA mater: Advanced Learning Machine Algorithms to **train models**.
+
+@HELP@
+        ]]>
+    </help>
+    <expand macro="citations"/>
+</tool>