RECETOX · martenson · Sep 30, 2020 · Sep 7, 2020 · Sep 21, 2020 · Sep 22, 2020
diff --git a/tools/retip/.shed.yml b/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.
diff --git a/tools/retip/macros.xml b/tools/retip/macros.xml
@@ -0,0 +1,37 @@
+<macros>
+    <token name="@TOOL_VERSION@">0.5.4</token>
+    <xml name="requirements">
+        <requirements>
+            <container type="docker">recetox/retip:@TOOL_VERSION@-recetox0</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>
diff --git a/tools/retip/retip_apply.xml b/tools/retip/retip_apply.xml
@@ -0,0 +1,37 @@
+<tool id="retip_apply" name="Retip prediction" version="@TOOL_VERSION@+galaxy0">
+    <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' '$input_smiles' 'output.tsv'
+      ]]>
+    </command>
+    <inputs>
+        <param name="descr_train" label="Select Descriptors.Feather Dataset" type="data" format="h5"
+               optional="false"/>
+        <param name="model_hdf5" label="Select Model.hdf5 Dataset" type="data" format="h5" optional="false"/>
+        <param name="input_smiles" label="Select Input Dataset" type="data" format="tabular" optional="false"/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="output1" label="Predicted RT" from_work_dir="output.tsv"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="descr_train" value="descriptors.feather"/>
+            <param name="model_hdf5" value="model.hdf5"/>
+            <param name="input_smiles" value="input.tsv"/>
+            <output name="output1" file="output.tsv" ftype="tabular"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+.. class:: infomark
+
+This tool is used for **Retention Time Prediction** on a whole database.
+
+@HELP@
+        ]]>
+    </help>
+    <expand macro="citations"/>
+</tool>
diff --git a/tools/retip/retip_descriptors.xml b/tools/retip/retip_descriptors.xml
@@ -0,0 +1,33 @@
+<tool id="retip_descriptors" name="Retip chemical descriptors" version="@TOOL_VERSION@+galaxy0">
+    <description>for retention time prediction</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+          /run.sh chemdesc.R '$compounds' 'descriptors.feather'
+      ]]>
+    </command>
+    <inputs>
+        <param name="compounds" label="Select Compounds Dataset" type="data" format="tabular" optional="false"/>
+    </inputs>
+    <outputs>
+        <data format="h5" name="output1" label="Descriptors.Feather Dataset"
+              from_work_dir="descriptors.feather"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="compounds" value="compounds-small.tsv"/>
+            <output name="output1" file="descriptors.feather" ftype="h5"/>
+        </test>
+    </tests>
+    <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>
diff --git a/tools/retip/retip_train.xml b/tools/retip/retip_train.xml
@@ -0,0 +1,33 @@
+<tool id="retip_train" name="Retip training" version="@TOOL_VERSION@+galaxy0">
+    <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="h5"
+               optional="false"/>
+    </inputs>
+    <outputs>
+        <data format="h5" name="output1" label="Model.hdf5 Dataset" from_work_dir="model.hdf5"/>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="descr_train" value="descriptors.feather"/>
+            <output name="output1" file="model.hdf5" ftype="h5" lines_diff="2"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+.. class:: infomark
+
+This tool uses ALMA mater: Advanced Learning Machine Algorithms to **train models**.
+
+@HELP@
+        ]]>
+    </help>
+    <expand macro="citations"/>
+</tool>
diff --git a/tools/retip/test-data/compounds-small.tsv b/tools/retip/test-data/compounds-small.tsv
@@ -0,0 +1,80 @@
+Name	InChIKey	SMILES	RT
+Withanone	FAZIYUIDUNHZRG-UHFFFAOYNA-N	CC(C1CC(C)=C(C)C(=O)O1)C1(O)CCC2C3C4OC4C4(O)CC=CC(=O)C4(C)C3CCC12C	6.82
+Corosolic acid	HFGSQOYIOKBQOW-UHFFFAOYNA-N	CC1CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(C)C5CCC34C)C2C1C)C(O)=O	9.89
+Maslinic acid	MDZKJHQSJHYOHJ-UHFFFAOYNA-N	CC1(C)CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(C)C5CCC34C)C2C1)C(O)=O	9.77
+Soyasapogenol A	CDDWAYFUFNQLRZ-UHFFFAOYNA-N	CC1(C)CC2C3=CCC4C5(C)CCC(O)C(C)(CO)C5CCC4(C)C3(C)CCC2(C)C(O)C1O	8.94
+Ginsenoside Rh3	PHLXREOMFNVWOH-UHFFFAOYNA-N	CC(C)=CCC=C(C)C1CCC2(C)C1C(O)CC1C3(C)CCC(OC4OC(CO)C(O)C(O)C4O)C(C)(C)C3CCC21C	7.63
+Ginsenoside compound K	FVIZARNDLVOMSU-UHFFFAOYNA-N	CC(C)=CCCC(C)(OC1OC(CO)C(O)C(O)C1O)C1CCC2(C)C1C(O)CC1C3(C)CCC(O)C(C)(C)C3CCC21C	9.51
+Ginsenoside F1	XNGXWSFSJIQMNC-UHFFFAOYNA-N	CC(C)=CCCC(C)(OC1OC(CO)C(O)C(O)C1O)C1CCC2(C)C1C(O)CC1C3(C)CCC(O)C(C)(C)C3C(O)CC21C	6.59
+alpha-Hederin	KEOITPILCOILGM-UHFFFAOYNA-N	CC1OC(OC2C(O)C(O)COC2OC2CCC3(C)C(CCC4(C)C3CC=C3C5CC(C)(C)CCC5(CCC43C)C(O)=O)C2(C)CO)C(O)C(O)C1O	7.96
+Ginsenoside Rg5	NJUXRKMKOFXMRX-UHFFFAOYNA-N	CC(C)=CCC=C(C)C1CCC2(C)C1C(O)CC1C3(C)CCC(OC4OC(CO)C(O)C(O)C4OC4OC(CO)C(O)C(O)C4O)C(C)(C)C3CCC21C	9.63
+Ginsenoside F3	HJRVLGWTJSLQIG-UHFFFAOYNA-N	CC(C)=CCCC(C)(OC1OC(COC2OCC(O)C(O)C2O)C(O)C(O)C1O)C1CCC2(C)C1C(O)CC1C3(C)CCC(O)C(C)(C)C3C(O)CC21C	6.11
+Ginsenoside Rb2	NODILNFGTFIURN-UHFFFAOYNA-N	CC(C)=CCCC(C)(OC1OC(COC2OCC(O)C(O)C2O)C(O)C(O)C1O)C1CCC2(C)C1C(O)CC1C3(C)CCC(OC4OC(CO)C(O)C(O)C4OC4OC(CO)C(O)C(O)C4O)C(C)(C)C3CCC21C	6.14
+Ginsenoside Rb1	GZYPWOGIYAIIPV-UHFFFAOYNA-N	CC(C)=CCCC(C)(OC1OC(COC2OC(CO)C(O)C(O)C2O)C(O)C(O)C1O)C1CCC2(C)C1C(O)CC1C3(C)CCC(OC4OC(CO)C(O)C(O)C4OC4OC(CO)C(O)C(O)C4O)C(C)(C)C3CCC21C	5.88
+Saikosaponin D	KYWSCMDFVARMPN-UHFFFAOYNA-N	CC1OC(OC2CCC3(C)C(CCC4(C)C3C=CC35OCC6(CCC(C)(C)CC36)C(O)CC45C)C2(C)CO)C(O)C(OC2OC(CO)C(O)C(O)C2O)C1O	8.25
+Licoricesaponin H2	LPLVUJXQOOQHMX-UHFFFAOYNA-N	CC1(C)C(CCC2(C)C1CCC1(C)C2C(=O)C=C2C3CC(C)(CCC3(C)CCC12C)C(O)=O)OC1OC(C(O)C(O)C1OC1OC(C(O)C(O)C1O)C(O)=O)C(O)=O	7.03
+Saikosaponin C	PYJMYPPFWASOJX-UHFFFAOYNA-N	CC1OC(OC2C(COC3OC(CO)C(O)C(O)C3O)OC(OC3CCC4(C)C(CCC5(C)C4C=CC4=C6CC(C)(C)CCC6(CO)C(O)CC54C)C3(C)C)C(O)C2O)C(O)C(O)C1O	6.29
+Ginsenoside Ro	NFZYDZXHKFHPGA-UHFFFAOYNA-N	CC1(C)CCC2(CCC3(C)C(=CCC4C5(C)CCC(OC6OC(C(O)C(O)C6OC6OC(CO)C(O)C(O)C6O)C(O)=O)C(C)(C)C5CCC34C)C2C1)C(=O)OC1OC(CO)C(O)C(O)C1O	6.18
+Asiaticoside	WYQVAPGDARQUBT-UHFFFAOYNA-N	CC1CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(CO)C5CCC34C)C2C1C)C(=O)OC1OC(COC2OC(CO)C(OC3OC(C)C(O)C(O)C3O)C(O)C2O)C(O)C(O)C1O	5.21
+Madecassoside	BNMGUJRJUUDLHW-UHFFFAOYNA-N	CC1CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(CO)C5C(O)CC34C)C2C1C)C(=O)OC1OC(COC2OC(CO)C(OC3OC(C)C(O)C(O)C3O)C(O)C2O)C(O)C(O)C1O	4.88
+Chrysanthellin B	WNGIVKPPGCCJNP-UHFFFAOYNA-N	CC1OC(OC2C(O)COC(OC3C(C)OC(OC4C(O)C(O)COC4OC(=O)C45CCC(C)(C)CC4C4=CCC6C7(C)CCC(OC8OC(CO)C(O)C(O)C8O)C(C)(CO)C7CCC6(C)C4(C)CC5O)C(O)C3O)C2O)C(O)C(O)C1O	5.79
+Hederacoside C	RYHDIBJJJRNDSX-UHFFFAOYNA-N	CC1OC(OC2C(O)C(O)C(OCC3OC(OC(=O)C45CCC(C)(C)CC4C4=CCC6C7(C)CCC(OC8OCC(O)C(O)C8OC8OC(C)C(O)C(O)C8O)C(C)(CO)C7CCC6(C)C4(C)CC5)C(O)C(O)C3O)OC2CO)C(O)C(O)C1O	5.38
+Lyalosidic acid	UZLBTLIRYSYTRG-UHFFFAOYNA-N	OCC1OC(OC2OC=C(C(CC3=NC=CC4=C3NC3=C4C=CC=C3)C2C=C)C(O)=O)C(O)C(O)C1O	3.72
+5(S)-5-carboxystrictosidine	LHKZIVMTXZLOTP-UHFFFAOYNA-N	COC(=O)C1=COC(OC2OC(CO)C(O)C(O)C2O)C(C=C)C1CC1NC(CC2=C1NC1=C2C=CC=C1)C(O)=O	4.13
+Thalsimine	YWNUNVSMOKMJMG-UHFFFAOYNA-N	COC1=CC=C2CC3N(C)CCC4=C3C(OC3=CC5=C(CCN=C5CC5=CC=C(OC1=C2)C=C5)C=C3OC)=C(OC)C(OC)=C4OC	4.25
+Isohernandezine	FUZMQNZACIFDBL-UHFFFAOYNA-N	COC1=CC=C2CC3N(C)CCC4=C3C(OC3=CC5=C(CCN(C)C5CC5=CC=C(OC1=C2)C=C5)C=C3OC)=C(OC)C(OC)=C4OC	4.41
+3.4,5-Trihydroxystilbene	LUKBXSAWLPMMSZ-UHFFFAOYSA-N	OC1=CC=C(C=CC2=CC(O)=CC(O)=C2)C=C1	5
+trans-pterostilbene	VLEUZFDZJKSGMX-UHFFFAOYSA-N	COC1=CC(C=CC2=CC=C(O)C=C2)=CC(OC)=C1	8.02
+E-Resveratrol trimethyl ether	GDHNBPHYVRHYCC-UHFFFAOYSA-N	COC1=CC=C(C=CC2=CC(OC)=CC(OC)=C2)C=C1	9.6
+Triacetyl resveratrol	PDAYUJSOJIMKIS-UHFFFAOYSA-N	CC(=O)OC1=CC=C(C=CC2=CC(OC(C)=O)=CC(OC(C)=O)=C2)C=C1	8.46
+trans-piceid	HSTZMXCBWJGKHG-UHFFFAOYNA-N	OCC1OC(OC2=CC(C=CC3=CC=C(O)C=C3)=CC(O)=C2)C(O)C(O)C1O	4.05
+Pseudojervine	HYDDDNUKNMMWBD-UHFFFAOYNA-N	CC1C2NCC(C)CC2OC11CCC2C3CC=C4CC(CCC4(C)C3C(=O)C2=C1C)OC1OC(CO)C(O)C(O)C1O	4.01
+Digitonin	UVYVLBIGDKGWPX-UHFFFAOYNA-N	CC1C2C(OC11CCC(C)CO1)C(O)C1C3CCC4CC(OC5OC(CO)C(OC6OC(CO)C(O)C(OC7OCC(O)C(O)C7O)C6OC6OC(CO)C(O)C(OC7OC(CO)C(O)C(O)C7O)C6O)C(O)C5O)C(O)CC4(C)C3CCC21C	6.99
+N-Acetylsolasodine	JXAZKNVJWYDQJY-UHFFFAOYNA-N	CC1C2C(CC3C4CC=C5CC(O)CCC5(C)C4CCC23C)OC11CCC(C)CN1C(C)=O	7.36
+O-Acetylsolasodine	MCQNPWNREVNWDQ-UHFFFAOYNA-N	CC1C2C(CC3C4CC=C5CC(CCC5(C)C4CCC23C)OC(C)=O)OC11CCC(C)CN1	8.16
+Bergenin	YWJXCIXBAKGUKZ-UHFFFAOYNA-N	COC1=C(O)C2=C(C=C1O)C(=O)OC1C(O)C(O)C(CO)OC21	2.86
+Hydrocotarnine	XXANNZJIZQTCBP-UHFFFAOYSA-N	COC1=C2CN(C)CCC2=CC2=C1OCO2	3.33
+(-)-B-Hydrastine	JZUTXVTYJDCMDU-UHFFFAOYNA-N	COC1=C(OC)C2=C(C=C1)C(OC2=O)C1N(C)CCC2=C1C=C1OCOC1=C2	4.21
+4-Aminoantipyrin	RLFWWDJHLFCNIJ-UHFFFAOYSA-N	CN1N(C(=O)C(N)=C1C)C1=CC=CC=C1	2.76
+Vanillin acetate	PZSJOBKRSVRODF-UHFFFAOYSA-N	COC1=C(OC(C)=O)C=CC(C=O)=C1	5.59
+4-Hydroxyquinoline	PMZDQRJGMBOQBF-UHFFFAOYSA-N	OC1=CC=NC2=C1C=CC=C2	2.93
+Schizandrin	YEFOAORQXAOVJQ-UHFFFAOYNA-N	COC1=CC2=C(C(OC)=C1OC)C1=C(OC)C(OC)=C(OC)C=C1CC(C)(O)C(C)C2	7.59
+Iso-gamma-fagarine	VNBUMBNLPGLBML-UHFFFAOYSA-N	COC1=CC=CC2=C1N(C)C1=C(C=CO1)C2=O	5.59
+Atractylenolide III	FBMORZZOJSDNRQ-UHFFFAOYNA-N	CC1=C2CC3C(=C)CCCC3(C)CC2(O)OC1=O	7.91
+Amygdalin	XUCIJNAGGSZNQT-UHFFFAOYNA-N	OCC1OC(OCC2OC(OC(C#N)C3=CC=CC=C3)C(O)C(O)C2O)C(O)C(O)C1O	3.32
+Procaine	MFDFERRIHVXMIY-UHFFFAOYSA-N	CCN(CC)CCOC(=O)C1=CC=C(N)C=C1	2.75
+Aristolochic acid B	MEEXETVZNQYRSP-UHFFFAOYSA-N	OC(=O)C1=CC2=C(OCO2)C2=C1C(=CC1=CC=CC=C21)[N+]([O-])=O	7.55
+Aristolochic acid C	NBFGYDJKTHENDP-UHFFFAOYSA-N	OC(=O)C1=CC2=C(OCO2)C2=C1C(=CC1=CC=C(O)C=C21)[N+]([O-])=O	5.96
+Gallic acid	LNTHITQWFMADLM-UHFFFAOYSA-N	OC(=O)C1=CC(O)=C(O)C(O)=C1	2.04
+Paeonol	UILPJVPSNHJFIK-UHFFFAOYSA-N	COC1=CC=C(C(C)=O)C(O)=C1	6.57
+Oxyacanthine	HGNHIFJNOKGSKI-UHFFFAOYNA-N	COC1=CC2=C3C(CC4=CC=C(OC5=CC(CC6N(C)CCC7=CC(OC)=C(OC3=C1OC)C=C67)=CC=C5O)C=C4)N(C)CC2	3.76
+Thalsimidine	CLDCTFPNFRITPI-UHFFFAOYNA-N	COC1=CC=C2CC3N(C)CCC4=C(O)C(OC)=C(OC)C(OC5=C(OC)C=C6CCN=C(CC7=CC=C(OC1=C2)C=C7)C6=C5)=C34	3.96
+(S.S)-(+)-Tetrandrine	WVTKBKWTSCPRNU-UHFFFAOYNA-N	COC1=CC=C2CC3N(C)CCC4=C3C(OC3=CC5=C(CCN(C)C5CC5=CC=C(OC1=C2)C=C5)C=C3OC)=C(OC)C(OC)=C4	4,19
+Seco-isolariciresinol diglucoside	SBVBJPHMDABKJV-UHFFFAOYNA-N	COC1=C(O)C=CC(CC(COC2OC(CO)C(O)C(O)C2O)C(COC2OC(CO)C(O)C(O)C2O)CC2=CC(OC)=C(O)C=C2)=C1	3.67
+Enterolactone	HVDGDHBAMCBBLR-UHFFFAOYNA-N	OC1=CC(CC2COC(=O)C2CC2=CC(O)=CC=C2)=CC=C1	6.18
+Matairesinol	MATGKVZWFZHCLI-UHFFFAOYNA-N	COC1=CC(CC2COC(=O)C2CC2=CC=C(O)C(OC)=C2)=CC=C1O	5.96
+Arctigenin	NQWVSMVXKMHKTF-UHFFFAOYNA-N	COC1=CC=C(CC2COC(=O)C2CC2=CC=C(O)C(OC)=C2)C=C1OC	6.63
+Enterodiol	DWONJCNDULPHLV-UHFFFAOYNA-N	OCC(CC1=CC(O)=CC=C1)C(CO)CC1=CC(O)=CC=C1	5.26
+Secoisolariciresinol	PUETUDUXMCLALY-UHFFFAOYNA-N	COC1=CC(CC(CO)C(CO)CC2=CC=C(O)C(OC)=C2)=CC=C1O	4.76
+Justicidin G	VINGQMQXGDIELG-UHFFFAOYSA-N	COC1=C2OCOC2=CC2=C(C3=C(C=C12)C(=O)OC3)C1=CC2=C(OCO2)C=C1	8.93
+Jusmicranthin ethyl ether	JJXCEOLNFSCNNE-UHFFFAOYNA-N	CCOC1OC(=O)C2=C1C(C1=CC3=C(OCO3)C=C1)=C1C3=C(OCO3)C=CC1=C2	8.82
+Carbazochrome sulfonate	OZCACMPSTYQSMM-UHFFFAOYNA-N	CN1C(CC2=CC(=NNC(O)=N)C(=O)C=C12)S(O)(=O)=O	2.69
+Gelsenicine	BIGABVPVCRHEES-UHFFFAOYNA-N	CCC1=NC2CC3(C4CC1C2CO4)C(=O)N(OC)C1=C3C=CC=C1	3.99
+Gramine	OCDGBSUVYYVKQZ-UHFFFAOYSA-N	CN(C)CC1=CNC2=CC=CC=C12	3.06
+Koumine	VTLYEMHGPMGUOT-UHFFFAOYNA-N	CN1CC2(C=C)C3CC4OCC3C1CC21C4=NC2=CC=CC=C12	3.58
+Gardneramine	RIMDDIPKIZTBHU-UHFFFAOYNA-N	COCC=C1CN2C3CC45C2CC1C3COC4=NC1=C5C(OC)=C(OC)C=C1OC	3.82
+Gentiopicroside	DUAGQYUORDTXOR-UHFFFAOYNA-N	OCC1OC(OC2OC=C3C(=O)OCC=C3C2C=C)C(O)C(O)C1O	3.44
+Swertiamarin	HEYZWPRKKUGDCR-UHFFFAOYNA-N	OCC1OC(OC2OC=C3C(=O)OCCC3(O)C2C=C)C(O)C(O)C1O	3.2
+1-Isothiocyanato-4-(methylsulfinyl)-butane	SUVMJBTUFCVSAD-UHFFFAOYNA-N	CS(=O)CCCCN=C=S	3.69
+1-Methylsulfinylbutenyl isothiocyante	QKGJFQMGPDVOQE-UHFFFAOYNA-N	CS(=O)C=CCCN=C=S	3.77
+7-Methylsulfenylheptyl isothiocyanate	LDIRGNDMTOGVRB-UHFFFAOYSA-N	CSCCCCCCCN=C=S	9.19
+Ginkgolide B	SQOJOAFXDQDRGF-UHFFFAOYNA-N	CC1C(=O)OC2C(O)C34C5CC(C(C)(C)C)C33C(O)C(=O)OC3OC4(C(=O)O5)C12O	5.36
+Ginkgolide C	AMOGMTLMADGEOQ-UHFFFAOYNA-N	CC1C(=O)OC2C(O)C34C5OC(=O)C3(OC3OC(=O)C(O)C43C(C5O)C(C)(C)C)C12O	4.33
+Gossypetin-8-C-glucoside	SJRXVLUZMMDCNG-UHFFFAOYNA-N	OCC1OC(OC2=C(O)C=C(O)C3=C2OC(=C(O)C3=O)C2=CC=C(O)C(O)=C2)C(O)C(O)C1O	4.64
+isosakuranetin-7-O-neohesperidoside	NLAWPKPYBMEWIR-UHFFFAOYNA-N	COC1=CC=C(C=C1)C1CC(=O)C2=C(O1)C=C(OC1OC(CO)C(O)C(O)C1OC1OC(C)C(O)C(O)C1O)C=C2O	5.42
+isosakuranetin-7-O-rutinoside	RMCRQBAILCLJGU-UHFFFAOYNA-N	COC1=CC=C(C=C1)C1CC(=O)C2=C(O)C=C(OC3OC(COC4OC(C)C(O)C(O)C4O)C(O)C(O)C3O)C=C2O1	5.33
+Icariin	TZJALUIVHRYQQB-UHFFFAOYNA-N	COC1=CC=C(C=C1)C1=C(OC2OC(C)C(O)C(O)C2O)C(=O)C2=C(O1)C(CC=C(C)C)=C(OC1OC(CO)C(O)C(O)C1O)C=C2O	5.43
+Kaempferol-3-O-robinoside-7-O-rhamnoside	PEFASEPMJYRQBW-UHFFFAOYNA-N	CC1OC(OCC2OC(OC3=C(OC4=C(C(O)=CC(OC5OC(C)C(O)C(O)C5O)=C4)C3=O)C3=CC=C(O)C=C3)C(O)C(O)C2O)C(O)C(O)C1O	3.55
+Myricetin-3-O-xyloside	SBEOEJNITMVWLK-UHFFFAOYNA-N	OC1COC(OC2=C(OC3=CC(O)=CC(O)=C3C2=O)C2=CC(O)=C(O)C(O)=C2)C(O)C1O	3.9
+Quercetin-3-O-vicianoside	YNMFDPCLPIMRFD-UHFFFAOYNA-N	OC1COC(OCC2OC(OC3=C(OC4=CC(O)=CC(O)=C4C3=O)C3=CC(O)=C(O)C=C3)C(O)C(O)C2O)C(O)C1O	3.7
+Kaempferol-3-O-galactoside-6''-rhamnoside-3'''-rha	UYVBMGULWGRDQT-UHFFFAOYNA-N	CC1OC(OC2C(O)C(C)OC(OCC3OC(OC4=C(OC5=CC(O)=CC(O)=C5C4=O)C4=CC=C(O)C=C4)C(O)C(O)C3O)C2O)C(O)C(O)C1O	3.98
diff --git a/tools/retip/test-data/descriptors.feather b/tools/retip/test-data/descriptors.feather
diff --git a/tools/retip/test-data/input.tsv b/tools/retip/test-data/input.tsv
@@ -0,0 +1,6 @@
+Name	InChIKey	SMILES
+Withanone	FAZIYUIDUNHZRG-UHFFFAOYNA-N	CC(C1CC(C)=C(C)C(=O)O1)C1(O)CCC2C3C4OC4C4(O)CC=CC(=O)C4(C)C3CCC12C
+Corosolic acid	HFGSQOYIOKBQOW-UHFFFAOYNA-N	CC1CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(C)C5CCC34C)C2C1C)C(O)=O
+Maslinic acid	MDZKJHQSJHYOHJ-UHFFFAOYNA-N	CC1(C)CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(C)C5CCC34C)C2C1)C(O)=O
+Soyasapogenol A	CDDWAYFUFNQLRZ-UHFFFAOYNA-N	CC1(C)CC2C3=CCC4C5(C)CCC(O)C(C)(CO)C5CCC4(C)C3(C)CCC2(C)C(O)C1O
+Ginsenoside Rh3	PHLXREOMFNVWOH-UHFFFAOYNA-N	CC(C)=CCC=C(C)C1CCC2(C)C1C(O)CC1C3(C)CCC(OC4OC(CO)C(O)C(O)C4O)C(C)(C)C3CCC21C
diff --git a/tools/retip/test-data/model.hdf5 b/tools/retip/test-data/model.hdf5
diff --git a/tools/retip/test-data/output.tsv b/tools/retip/test-data/output.tsv
@@ -0,0 +1,6 @@
+Name	InChIKey	SMILES	RTP
+Withanone	FAZIYUIDUNHZRG-UHFFFAOYNA-N	CC(C1CC(C)=C(C)C(=O)O1)C2(O)CCC3C4C5OC5C6(O)CC=CC(=O)C6(C)C4CCC23C	5.61
+Corosolic acid	HFGSQOYIOKBQOW-UHFFFAOYNA-N	CC1CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(C)C5CCC34C)C2C1C)C(O)=O	8.24
+Maslinic acid	MDZKJHQSJHYOHJ-UHFFFAOYNA-N	CC1(C)CCC2(CCC3(C)C(=CCC4C5(C)CC(O)C(O)C(C)(C)C5CCC34C)C2C1)C(O)=O	8.31
+Soyasapogenol A	CDDWAYFUFNQLRZ-UHFFFAOYNA-N	CC1(C)CC2C3=CCC4C5(C)CCC(O)C(C)(CO)C5CCC4(C)C3(C)CCC2(C)C(O)C1O	7.23
+Ginsenoside Rh3	PHLXREOMFNVWOH-UHFFFAOYNA-N	CC(C)=CCC=C(C)C1CCC2(C)C1C(O)CC3C4(C)CCC(OC5OC(CO)C(O)C(O)C5O)C(C)(C)C4CCC23C	7.57