|
2
|
1 <?xml version='1.0' encoding='UTF-8'?>
|
|
|
2 <!--This is a configuration file for the integration of a tools into Galaxy (https://galaxyproject.org/). This file was automatically generated using CTD2Galaxy.-->
|
|
|
3 <!--Proposed Tool Section: [Chemoinformatics]-->
|
|
|
4 <tool id="FingerprintSimilaritySearch" name="FingerprintSimilaritySearch" version="1.1.0">
|
|
|
5 <description>calculate similar molecules in a library</description>
|
|
|
6 <macros>
|
|
|
7 <token name="@EXECUTABLE@">FingerprintSimilaritySearch</token>
|
|
|
8 <import>macros.xml</import>
|
|
|
9 </macros>
|
|
|
10 <expand macro="stdio"/>
|
|
|
11 <expand macro="requirements"/>
|
|
|
12 <command>FingerprintSimilaritySearch
|
|
|
13
|
|
|
14 #if $param_t:
|
|
|
15 -t $param_t
|
|
|
16 #end if
|
|
|
17 #if $param_q:
|
|
|
18 -q $param_q
|
|
|
19 #end if
|
|
|
20 #if $param_o:
|
|
|
21 -o $param_o
|
|
|
22 #end if
|
|
|
23 #if $param_f:
|
|
|
24 -f $param_f
|
|
|
25 #end if
|
|
|
26 #if $param_fp_col:
|
|
|
27 -fp_col $param_fp_col
|
|
|
28 #end if
|
|
|
29 #if $param_id_col:
|
|
|
30 -id_col $param_id_col
|
|
|
31 #end if
|
|
|
32 #if $param_fp_tag:
|
|
|
33 -fp_tag "$param_fp_tag"
|
|
|
34 #end if
|
|
|
35 #if $param_id_tag:
|
|
|
36 -id_tag "$param_id_tag"
|
|
|
37 #end if
|
|
|
38 #if $param_tc:
|
|
|
39 -tc $param_tc
|
|
|
40 #end if
|
|
|
41 #if $param_nt:
|
|
|
42 -nt "$param_nt"
|
|
|
43 #end if
|
|
|
44 #if $param_bs:
|
|
|
45 -bs $param_bs
|
|
|
46 #end if
|
|
|
47 #if $param_sdf_out:
|
|
|
48 -sdf_out $param_sdf_out
|
|
|
49 #end if
|
|
|
50 </command>
|
|
|
51 <inputs>
|
|
|
52 <param name="param_t" type="data" format="smi.gz,csv,sdf.gz,sdf,txt.gz,smi,txt,csv.gz" optional="False" value="<class 'CTDopts.CTDopts._Null'>" label="Target library input file" help="(-t) "/>
|
|
|
53 <param name="param_q" type="data" format="smi.gz,csv,sdf.gz,sdf,txt.gz,smi,txt,csv.gz" optional="False" value="<class 'CTDopts.CTDopts._Null'>" label="Query library input file" help="(-q) "/>
|
|
|
54 <param name="param_f" type="integer" min="1" max="2" optional="False" value="0" label="Fingerprint format [1 = binary bitstring, 2 = comma separated feature list]" help="(-f) "/>
|
|
|
55 <param name="param_fp_col" type="integer" value="-1" label="Column number for comma separated smiles input which contains the fingerprint" help="(-fp_col) "/>
|
|
|
56 <param name="param_id_col" type="integer" value="-1" label="Column number for comma separated smiles input which contains the molecule identifie" help="(-id_col) "/>
|
|
|
57 <param name="param_fp_tag" type="text" size="30" value=" " label="Tag name for SDF input which contains the fingerprint" help="(-fp_tag) ">
|
|
|
58 <sanitizer>
|
|
|
59 <valid initial="string.printable">
|
|
|
60 <remove value="'"/>
|
|
|
61 <remove value="""/>
|
|
|
62 </valid>
|
|
|
63 </sanitizer>
|
|
|
64 </param>
|
|
|
65 <param name="param_id_tag" type="text" size="30" value=" " label="Tag name for SDF input which contains the molecule identifie" help="(-id_tag) ">
|
|
|
66 <sanitizer>
|
|
|
67 <valid initial="string.printable">
|
|
|
68 <remove value="'"/>
|
|
|
69 <remove value="""/>
|
|
|
70 </valid>
|
|
|
71 </sanitizer>
|
|
|
72 </param>
|
|
|
73 <param name="param_tc" type="float" value="0.7" label="Tanimoto cutoff [default: 0.7]" help="(-tc) "/>
|
|
|
74 <param name="param_nt" type="text" size="30" value="1" label="Number of parallel threads to use" help="(-nt) To use all possible threads enter <max> [default: 1]">
|
|
|
75 <sanitizer>
|
|
|
76 <valid initial="string.printable">
|
|
|
77 <remove value="'"/>
|
|
|
78 <remove value="""/>
|
|
|
79 </valid>
|
|
|
80 </sanitizer>
|
|
|
81 </param>
|
|
|
82 <param name="param_bs" type="integer" value="500" label="Block size [default: 500]" help="(-bs) "/>
|
|
|
83 <param name="param_sdf_out" type="integer" min="0" max="1" optional="True" value="0" label="If query file has SD format, this flag activates writing of nearest neighbours as a new CSV tag in a copy of the query SD file" help="(-sdf_out) "/>
|
|
|
84 </inputs>
|
|
|
85 <expand macro="advanced_options"/>
|
|
|
86 <outputs>
|
|
|
87 <data name="param_o" metadata_source="param_t" format="input"/>
|
|
|
88 </outputs>
|
|
|
89 <help>This tool calculates all nearest neighbours above a similarity cutoff for given query molecules in a compound library on the basis of 2D binary fingerprints.
|
|
|
90 The first library to specify (i1) is the compound library to be searched, the second library (i2) is conseiderd as the query compounds.
|
|
|
91 Both files have to be comma separated values (csv) files and the binary fingerprints have to be encoded as feature lists or as binary bit strings.
|
|
|
92
|
|
|
93 WARNING: If similarity cutoff is chosen to be 0.0, the output will be the entire similarity matrix and has a size of n*m with n=|i1| and m=|i2|.
|
|
|
94
|
|
|
95 ======================================================================================================================================================
|
|
|
96
|
|
|
97 Examples:
|
|
|
98
|
|
|
99 $ FingerprintSimilaritySearch -t target.sdf -q query.sdf -o results -fp_tag FPRINT -f 1 -id_tag NAME
|
|
|
100 tries to extract fingerprints as binary bitstrings (-f 1) from tag <FPRINT> and compound IDs from tag <NAME> of target.sdf and query.sdf.
|
|
|
101 A similarity search is performed for all query molecules against all target molecules and pairs with similarity above Tanimoto cutoff 0.7 are written to outfile (results).
|
|
|
102
|
|
|
103 $ FingerprintSimilaritySearch -t target.sdf -q query.sdf -o results -fp_tag FPRINT -f 1 -id_tag NAME -sdf_out
|
|
|
104 tries to extract fingerprints as binary bitstrings (-f 1) from tag <FPRINT> and compound IDs from tag <NAME> of target.sdf and query.sdf.
|
|
|
105 A similarity search is performed for all query molecules against all target molecules and pairs with similarity above Tanimoto cutoff 0.7
|
|
|
106 are added as a new SD tag to output file 'NN_TAGGED_query.sdf' as a list of TargetID:Similarity pairs.
|
|
|
107
|
|
|
108 $ FingerprintSimilaritySearch -t target.sdf -q query.smi -o results -fp_tag FPRINT -f 1 -id_tag NAME -fp_col 2
|
|
|
109 tries to extract fingerprints as binary bitstrings (-f 1) from tag <FPRINT> and compound IDs from tag <NAME> of target.sdf
|
|
|
110 and fingerprints as binary bitstrings of space separated query file from column 2 (-fp_col 2).
|
|
|
111 A similarity search is performed for all query molecules against all target molecules and pairs with similarity above Tanimoto cutoff 0.7 are written to outfile (results).
|
|
|
112
|
|
|
113 </help>
|
|
|
114 </tool>
|
