comparison macros.xml @ 0:baa7c8768036 draft

"planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/retip commit 931ccc430a2b20eebd174d29b45bf3fa18e85f58"
author recetox
date Wed, 30 Sep 2020 09:57:12 +0000
parents
children 6462a0ac9c29
comparison
equal deleted inserted replaced
-1:000000000000 0:baa7c8768036
1 <macros>
2 <token name="@TOOL_VERSION@">0.5.4</token>
3 <xml name="requirements">
4 <requirements>
5 <container type="docker">recetox/retip:@TOOL_VERSION@-recetox0</container>
6 </requirements>
7 </xml>
8 <xml name="citations">
9 <citations>
10 <citation type="doi">https://doi.org/10.1021/acs.analchem.9b05765</citation>
11 </citations>
12 </xml>
13 <token name="@HELP@"><![CDATA[
14 Retip is an R package for predicting Retention Time (RT) for small molecules in a high pressure liquid
15 chromatography (HPLC) Mass Spectrometry analysis. Retention time calculation can be useful in identifying
16 unknowns and removing false positive annotations. It uses five different machine learning algorithms to built a
17 stable, accurate and fast RT prediction model:
18
19 - Random Forest: a decision tree algorithms
20 - BRNN: Bayesian Regularized Neural Network
21 - XGBoost: an extreme Gradient Boosting for tree algorithms
22 - lightGBM: a gradient boosting framework that uses tree based learning algorithms.
23 - Keras: a high-level neural networks API for Tensorflow
24
25 Retip also includes useful biochemical databases like: BMDB, ChEBI, DrugBank, ECMDB, FooDB, HMDB, KNApSAcK,
26 PlantCyc, SMPDB, T3DB, UNPD, YMDB and STOFF.
27
28 **Get started**
29
30 To use Retip, a user needs to prepare a compound retention time library. The input file
31 needs compound Name, InChiKey, SMILES code and experimental retention time information for each compound.
32 The input must be a CSV file. Retip will use this input file to build a the model and will predict
33 retention times for other biochemical databases or an input query list of compounds. It is suggested that
34 the file has at least 300 compounds to build a good retention time prediction model.
35 ]]>
36 </token>
37 </macros>