|
0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
|
2 .\"
|
|
|
3 .\" Standard preamble:
|
|
|
4 .\" ========================================================================
|
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
|
6 .if t .sp .5v
|
|
|
7 .if n .sp
|
|
|
8 ..
|
|
|
9 .de Vb \" Begin verbatim text
|
|
|
10 .ft CW
|
|
|
11 .nf
|
|
|
12 .ne \\$1
|
|
|
13 ..
|
|
|
14 .de Ve \" End verbatim text
|
|
|
15 .ft R
|
|
|
16 .fi
|
|
|
17 ..
|
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
|
23 .\" nothing in troff, for use with C<>.
|
|
|
24 .tr \(*W-
|
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
|
26 .ie n \{\
|
|
|
27 . ds -- \(*W-
|
|
|
28 . ds PI pi
|
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
|
31 . ds L" ""
|
|
|
32 . ds R" ""
|
|
|
33 . ds C` ""
|
|
|
34 . ds C' ""
|
|
|
35 'br\}
|
|
|
36 .el\{\
|
|
|
37 . ds -- \|\(em\|
|
|
|
38 . ds PI \(*p
|
|
|
39 . ds L" ``
|
|
|
40 . ds R" ''
|
|
|
41 'br\}
|
|
|
42 .\"
|
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
|
45 .el .ds Aq '
|
|
|
46 .\"
|
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
|
50 .\" output yourself in some meaningful fashion.
|
|
|
51 .ie \nF \{\
|
|
|
52 . de IX
|
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
|
54 ..
|
|
|
55 . nr % 0
|
|
|
56 . rr F
|
|
|
57 .\}
|
|
|
58 .el \{\
|
|
|
59 . de IX
|
|
|
60 ..
|
|
|
61 .\}
|
|
|
62 .\"
|
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
|
65 . \" fudge factors for nroff and troff
|
|
|
66 .if n \{\
|
|
|
67 . ds #H 0
|
|
|
68 . ds #V .8m
|
|
|
69 . ds #F .3m
|
|
|
70 . ds #[ \f1
|
|
|
71 . ds #] \fP
|
|
|
72 .\}
|
|
|
73 .if t \{\
|
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
|
75 . ds #V .6m
|
|
|
76 . ds #F 0
|
|
|
77 . ds #[ \&
|
|
|
78 . ds #] \&
|
|
|
79 .\}
|
|
|
80 . \" simple accents for nroff and troff
|
|
|
81 .if n \{\
|
|
|
82 . ds ' \&
|
|
|
83 . ds ` \&
|
|
|
84 . ds ^ \&
|
|
|
85 . ds , \&
|
|
|
86 . ds ~ ~
|
|
|
87 . ds /
|
|
|
88 .\}
|
|
|
89 .if t \{\
|
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
|
96 .\}
|
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
|
107 . \" corrections for vroff
|
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
|
112 \{\
|
|
|
113 . ds : e
|
|
|
114 . ds 8 ss
|
|
|
115 . ds o a
|
|
|
116 . ds d- d\h'-1'\(ga
|
|
|
117 . ds D- D\h'-1'\(hy
|
|
|
118 . ds th \o'bp'
|
|
|
119 . ds Th \o'LP'
|
|
|
120 . ds ae ae
|
|
|
121 . ds Ae AE
|
|
|
122 .\}
|
|
|
123 .rm #[ #] #H #V #F C
|
|
|
124 .\" ========================================================================
|
|
|
125 .\"
|
|
|
126 .IX Title "EXTRACTFROMSDFILES 1"
|
|
|
127 .TH EXTRACTFROMSDFILES 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
|
129 .\" way too many mistakes in technical documents.
|
|
|
130 .if n .ad l
|
|
|
131 .nh
|
|
|
132 .SH "NAME"
|
|
|
133 ExtractFromSDFiles.pl \- Extract specific data from SDFile(s)
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 ExtractFromSDFiles.pl SDFile(s)...
|
|
|
137 .PP
|
|
|
138 ExtractFromSDFiles.pl [\fB\-h, \-\-help\fR]
|
|
|
139 [\fB\-d, \-\-datafields\fR \*(L"fieldlabel,...\*(R" | \*(L"fieldlabel,value,criteria...\*(R" | \*(L"fieldlabel,value,value...\*(R"]
|
|
|
140 [\fB\-\-datafieldsfile\fR filename] [\fB\-\-indelim\fR comma | tab | semicolon] [\fB\-m, \-\-mode\fR alldatafields |
|
|
|
141 commondatafields | | datafieldnotbylist | datafields | datafieldsbyvalue | datafieldsbyregex | datafieldbylist |
|
|
|
142 datafielduniquebylist | molnames | randomcmpds | recordnum | recordnums | recordrange | 2dcmpdrecords |
|
|
|
143 3dcmpdrecords ] [\fB\-n, \-\-numofcmpds\fR number] [\fB\-\-outdelim\fR comma | tab | semicolon]
|
|
|
144 [\fB\-\-output\fR \s-1SD\s0 | text | both] [\fB\-o, \-\-overwrite\fR] [\fB\-q, \-\-quote\fR yes | no]
|
|
|
145 [\fB\-\-record\fR recnum | startrecnum,endrecnum] \fB\-\-RegexIgnoreCase\fR \fIyes or no\fR
|
|
|
146 [\fB\-r, \-\-root\fR rootname] [\fB\-s, \-\-seed\fR number] [\fB\-\-StrDataString\fR yes | no]
|
|
|
147 [\fB\-\-StrDataStringDelimiter\fR text] [\fB\-\-StrDataStringMode\fR StrOnly | StrAndDataFields]
|
|
|
148 [\fB\-\-ValueComparisonMode\fR \fINumeric | Alphanumeric\fR]
|
|
|
149 [\fB\-v, \-\-violations\-\fR number] [\fB\-w, \-\-workingdir\fR dirname] SDFile(s)...
|
|
|
150 .SH "DESCRIPTION"
|
|
|
151 .IX Header "DESCRIPTION"
|
|
|
152 Extract specific data from \fISDFile(s)\fR and generate appropriate \s-1SD\s0 or \s-1CSV/TSV\s0 text
|
|
|
153 file(s). The structure data from SDFile(s) is not transferred to \s-1CSV/TSV\s0 text file(s).
|
|
|
154 Multiple SDFile names are separated by spaces. The valid file extensions are \fI.sdf\fR
|
|
|
155 and \fI.sd\fR. All other file names are ignored. All the \s-1SD\s0 files in a current directory
|
|
|
156 can be specified either by \fI*.sdf\fR or the current directory name.
|
|
|
157 .SH "OPTIONS"
|
|
|
158 .IX Header "OPTIONS"
|
|
|
159 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
160 .IX Item "-h, --help"
|
|
|
161 Print this help message.
|
|
|
162 .ie n .IP "\fB\-d, \-\-datafields\fR \fI""fieldlabel,..."" | ""fieldlabel,value,criteria..."" | ""fieldlabel,value,value,...""\fR" 4
|
|
|
163 .el .IP "\fB\-d, \-\-datafields\fR \fI``fieldlabel,...'' | ``fieldlabel,value,criteria...'' | ``fieldlabel,value,value,...''\fR" 4
|
|
|
164 .IX Item "-d, --datafields fieldlabel,... | fieldlabel,value,criteria... | fieldlabel,value,value,..."
|
|
|
165 This value is mode specific. In general, it's a list of comma separated data field labels
|
|
|
166 and associated mode specific values.
|
|
|
167 .Sp
|
|
|
168 For \fIdatafields\fR mode, input value format is: \fIfieldlabel,...\fR. Examples:
|
|
|
169 .Sp
|
|
|
170 .Vb 2
|
|
|
171 \& Extreg
|
|
|
172 \& Extreg,CompoundName,ID
|
|
|
173 .Ve
|
|
|
174 .Sp
|
|
|
175 For \fIdatafieldsbyvalue\fR mode, input value format contains these triplets:
|
|
|
176 \&\fIfieldlabel,value, criteria...\fR. Possible values for criteria: \fIle, ge or eq\fR.
|
|
|
177 The values of \fB\-\-ValueComparisonMode\fR indicates whether values are
|
|
|
178 compared numerical or string comarison operators. Default is to consider
|
|
|
179 data field values as numerical values and use numerical comparison operators.
|
|
|
180 Examples:
|
|
|
181 .Sp
|
|
|
182 .Vb 2
|
|
|
183 \& MolWt,450,le
|
|
|
184 \& MolWt,450,le,LogP,5,le,SumNumNO,10,le,SumNHOH,5,le
|
|
|
185 .Ve
|
|
|
186 .Sp
|
|
|
187 For \fIdatafieldsbyregex\fR mode, input value format contains these triplets:
|
|
|
188 \&\fIfieldlabel,regex, criteria...\fR. \fIregex\fR corresponds to any valid regular expression
|
|
|
189 and is used to match the values for specified \fIfieldlabel\fR. Possible values for criteria:
|
|
|
190 \fIeq or ne\fR. During \fIeq\fR and \fIne\fR values, data field label value is matched with
|
|
|
191 regular expression using =~ and !~ respectively. \fB\-\-RegexIgnoreCase\fR option
|
|
|
192 value is used to determine whether to ignore letter upper/lower case during
|
|
|
193 regular expression match. Examples:
|
|
|
194 .Sp
|
|
|
195 .Vb 2
|
|
|
196 \& Name,ol,eq
|
|
|
197 \& Name,\*(Aq^pat\*(Aq,ne
|
|
|
198 .Ve
|
|
|
199 .Sp
|
|
|
200 For \fIdatafieldbylist\fR and \fIdatafielduniquebylist\fR mode, input value format is:
|
|
|
201 \&\fIfieldlabel,value1,value2...\fR. This is equivalent to \fIdatafieldsbyvalue\fR mode with
|
|
|
202 this input value format:\fIfieldlabel,value1,eq,fieldlabel,value2,eq,...\fR. For
|
|
|
203 \&\fIdatafielduniquebylist\fR mode, only unique compounds identified by first occurrence
|
|
|
204 of \fIvalue\fR associated with \fIfieldlabel\fR in \fISDFile(s)\fR are kept; any subsequent compounds
|
|
|
205 are simply ignored.
|
|
|
206 .Sp
|
|
|
207 For \fIdatafieldnotbylist\fR mode, input value format is: \fIfieldlabel,value1,value2...\fR. In this
|
|
|
208 mode, the script behaves exactly opposite of \fIdatafieldbylist\fR mode, and only those compounds
|
|
|
209 are extracted whose data field values don't match any specified data field value.
|
|
|
210 .IP "\fB\-\-datafieldsfile\fR \fIfilename\fR" 4
|
|
|
211 .IX Item "--datafieldsfile filename"
|
|
|
212 Filename which contains various mode specific values. This option provides a way
|
|
|
213 to specify mode specific values in a file instead of entering them on the command
|
|
|
214 line using \fB\-d \-\-datafields\fR.
|
|
|
215 .Sp
|
|
|
216 For \fIdatafields\fR mode, input file lines contain comma delimited field labels:
|
|
|
217 \&\fIfieldlabel,...\fR. Example:
|
|
|
218 .Sp
|
|
|
219 .Vb 2
|
|
|
220 \& Line 1:MolId
|
|
|
221 \& Line 2:"Extreg",CompoundName,ID
|
|
|
222 .Ve
|
|
|
223 .Sp
|
|
|
224 For \fIdatafieldsbyvalue\fR mode, input file lines contains these comma separated triplets:
|
|
|
225 \&\fIfieldlabel,value, criteria\fR. Possible values for criteria: \fIle, ge or eq\fR. Examples:
|
|
|
226 .Sp
|
|
|
227 .Vb 1
|
|
|
228 \& Line 1:MolWt,450,le
|
|
|
229 \&
|
|
|
230 \& Line 1:"MolWt",450,le,"LogP",5,le,"SumNumNO",10,le,"SumNHOH",5,le
|
|
|
231 \&
|
|
|
232 \& Line 1:MolWt,450,le
|
|
|
233 \& Line 2:"LogP",5,le
|
|
|
234 \& Line 3:"SumNumNO",10,le
|
|
|
235 \& Line 4: SumNHOH,5,le
|
|
|
236 .Ve
|
|
|
237 .Sp
|
|
|
238 For \fIdatafieldbylist\fR and \fIdatafielduniquebylist\fR mode, input file line format is:
|
|
|
239 .Sp
|
|
|
240 .Vb 2
|
|
|
241 \& Line 1:fieldlabel;
|
|
|
242 \& Subsequent lines:value1,value2...
|
|
|
243 .Ve
|
|
|
244 .Sp
|
|
|
245 For \fIdatafieldbylist\fR, \fIdatafielduniquebylist\fR, and \fIdatafieldnotbylist\fR mode, input file
|
|
|
246 line format is:
|
|
|
247 .Sp
|
|
|
248 .Vb 2
|
|
|
249 \& Line 1:fieldlabel;
|
|
|
250 \& Subsequent lines:value1,value2...
|
|
|
251 .Ve
|
|
|
252 .Sp
|
|
|
253 For \fIdatafielduniquebylist\fR mode, only unique compounds identified by first occurrence
|
|
|
254 of \fIvalue\fR associated with \fIfieldlabel\fR in \fISDFile(s)\fR are kept; any subsequent compounds
|
|
|
255 are simply ignored. Example:
|
|
|
256 .Sp
|
|
|
257 .Vb 5
|
|
|
258 \& Line 1: MolID
|
|
|
259 \& Subsequent Lines:
|
|
|
260 \& 907508
|
|
|
261 \& 832291,4642
|
|
|
262 \& "1254","907303"
|
|
|
263 .Ve
|
|
|
264 .IP "\fB\-\-indelim\fR \fIcomma | tab | semicolon\fR" 4
|
|
|
265 .IX Item "--indelim comma | tab | semicolon"
|
|
|
266 Delimiter used to specify text values for \fB\-d \-\-datafields\fR and \fB\-\-datafieldsfile\fR options.
|
|
|
267 Possible values: \fIcomma, tab, or semicolon\fR. Default value: \fIcomma\fR.
|
|
|
268 .IP "\fB\-m, \-\-mode\fR \fIalldatafields | commondatafields | datafields | datafieldsbyvalue | datafieldsbyregex | datafieldbylist | datafielduniquebylist | datafieldnotbylist | molnames | randomcmpds | recordnum | recordnums | recordrange | 2dcmpdrecords | 3dcmpdrecords\fR" 4
|
|
|
269 .IX Item "-m, --mode alldatafields | commondatafields | datafields | datafieldsbyvalue | datafieldsbyregex | datafieldbylist | datafielduniquebylist | datafieldnotbylist | molnames | randomcmpds | recordnum | recordnums | recordrange | 2dcmpdrecords | 3dcmpdrecords"
|
|
|
270 Specify what to extract from \fISDFile(s)\fR. Possible values: \fIalldatafields, commondatafields,
|
|
|
271 datafields, datafieldsbyvalue, datafieldsbyregex, datafieldbylist, datafielduniquebylist, datafieldnotbylist,
|
|
|
272 molnames, randomcmpds, recordnum, recordnums, recordrange, 2dcmpdrecords, 3dcmpdrecords\fR.
|
|
|
273 Default value: \fIalldatafields\fR.
|
|
|
274 .Sp
|
|
|
275 For \fIalldatafields\fR and \fImolnames\fR mode, only a \s-1CSV/TSV\s0 text file is generated; for all
|
|
|
276 other modes, however, a \s-1SD\s0 file is generated by default \- you can change the behavior to genereate
|
|
|
277 text file using \fI\-\-output\fR option.
|
|
|
278 .Sp
|
|
|
279 For \fI3DCmpdRecords\fR mode, only those compounds with at least one non-zero value for Z atomic coordinates
|
|
|
280 are retrieved; however, during retrieval of compounds in \fI2DCmpdRecords\fR mode, all Z atomic coordinates must
|
|
|
281 be zero.
|
|
|
282 .IP "\fB\-n, \-\-numofcmpds\fR \fInumber\fR" 4
|
|
|
283 .IX Item "-n, --numofcmpds number"
|
|
|
284 Number of compouds to extract during \fIrandomcmpds\fR mode.
|
|
|
285 .IP "\fB\-\-outdelim\fR \fIcomma | tab | semicolon\fR" 4
|
|
|
286 .IX Item "--outdelim comma | tab | semicolon"
|
|
|
287 Delimiter for output \s-1CSV/TSV\s0 text file(s). Possible values: \fIcomma, tab, or semicolon\fR
|
|
|
288 Default value: \fIcomma\fR
|
|
|
289 .IP "\fB\-\-output\fR \fI\s-1SD\s0 | text | both\fR" 4
|
|
|
290 .IX Item "--output SD | text | both"
|
|
|
291 Type of output files to generate. Possible values: \fI\s-1SD\s0, text, or both\fR. Default value: \fI\s-1SD\s0\fR. For
|
|
|
292 \&\fIalldatafields\fR and \fImolnames\fR mode, this option is ingored and only a \s-1CSV/TSV\s0 text file is generated.
|
|
|
293 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
|
294 .IX Item "-o, --overwrite"
|
|
|
295 Overwrite existing files.
|
|
|
296 .IP "\fB\-q, \-\-quote\fR \fIyes | no\fR" 4
|
|
|
297 .IX Item "-q, --quote yes | no"
|
|
|
298 Put quote around column values in output \s-1CSV/TSV\s0 text file(s). Possible values:
|
|
|
299 \&\fIyes or no\fR. Default value: \fIyes\fR.
|
|
|
300 .IP "\fB\-\-record\fR \fIrecnum | recnums | startrecnum,endrecnum\fR" 4
|
|
|
301 .IX Item "--record recnum | recnums | startrecnum,endrecnum"
|
|
|
302 Record number, record numbers or range of records to extract during \fIrecordnum\fR, \fIrecordnums\fR
|
|
|
303 and \fIrecordrange\fR mode. Input value format is: <num>, <num1,num2,...> and <startnum, endnum>
|
|
|
304 for \fIrecordnum\fR, \fIrecordnums\fR and \fIrecordrange\fR modes recpectively. Default value: none.
|
|
|
305 .IP "\fB\-\-RegexIgnoreCase\fR \fIyes or no\fR" 4
|
|
|
306 .IX Item "--RegexIgnoreCase yes or no"
|
|
|
307 Specify whether to ingnore case during \fIdatafieldsbyregex\fR value of \fB\-m, \-\-mode\fR option.
|
|
|
308 Possible values: \fIyes or no\fR. Default value: \fIyes\fR.
|
|
|
309 .IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
|
|
|
310 .IX Item "-r, --root rootname"
|
|
|
311 New file name is generated using the root: <Root>.<Ext>. Default for new file
|
|
|
312 names: <SDFileName><mode>.<Ext>. The file type determines <Ext> value.
|
|
|
313 The sdf, csv, and tsv <Ext> values are used for \s-1SD\s0, comma/semicolon, and tab
|
|
|
314 delimited text files respectively.This option is ignored for multiple input files.
|
|
|
315 .IP "\fB\-s, \-\-seed\fR \fInumber\fR" 4
|
|
|
316 .IX Item "-s, --seed number"
|
|
|
317 Random number seed used for \fIrandomcmpds\fR mode. Default:123456789.
|
|
|
318 .IP "\fB\-\-StrDataString\fR \fIyes | no\fR" 4
|
|
|
319 .IX Item "--StrDataString yes | no"
|
|
|
320 Specify whether to write out structure data string to \s-1CSV/TSV\s0 text file(s). Possible values:
|
|
|
321 \&\fIyes or no\fR. Default value: \fIno\fR.
|
|
|
322 .Sp
|
|
|
323 The value of \fBStrDataStringDelimiter\fR option is used as a delimiter to join structure
|
|
|
324 data lines into a structure data string.
|
|
|
325 .Sp
|
|
|
326 This option is ignored during generation of \s-1SD\s0 file(s).
|
|
|
327 .IP "\fB\-\-StrDataStringDelimiter\fR \fItext\fR" 4
|
|
|
328 .IX Item "--StrDataStringDelimiter text"
|
|
|
329 Delimiter for joining multiple stucture data lines into a string before writing to \s-1CSV/TSV\s0 text
|
|
|
330 file(s). Possible values: \fIany alphanumeric text\fR. Default value: \fI|\fR.
|
|
|
331 .Sp
|
|
|
332 This option is ignored during generation of \s-1SD\s0 file(s).
|
|
|
333 .IP "\fB\-\-StrDataStringMode\fR \fIStrOnly | StrAndDataFields\fR" 4
|
|
|
334 .IX Item "--StrDataStringMode StrOnly | StrAndDataFields"
|
|
|
335 Specify whether to include \s-1SD\s0 data fields and values along with the structure data into structure
|
|
|
336 data string before writing it out to \s-1CSV/TSV\s0 text file(s). Possible values: \fIStrOnly or StrAndDataFields\fR.
|
|
|
337 Default value: \fIStrOnly\fR.
|
|
|
338 .Sp
|
|
|
339 The value of \fBStrDataStringDelimiter\fR option is used as a delimiter to join structure
|
|
|
340 data lines into a structure data string.
|
|
|
341 .Sp
|
|
|
342 This option is ignored during generation of \s-1SD\s0 file(s).
|
|
|
343 .IP "\fB\-\-ValueComparisonMode\fR \fINumeric | Alphanumeric\fR" 4
|
|
|
344 .IX Item "--ValueComparisonMode Numeric | Alphanumeric"
|
|
|
345 Specify how to compare data field values during \fIdatafieldsbyvalue\fR mode: Compare
|
|
|
346 values using either numeric or string ((eq, le, ge) comparison operators. Possible values:
|
|
|
347 \&\fINumeric or Alphanumeric\fR. Defaule value: \fINumeric\fR.
|
|
|
348 .IP "\fB\-v, \-\-violations\fR \fInumber\fR" 4
|
|
|
349 .IX Item "-v, --violations number"
|
|
|
350 Number of criterion violations allowed for values specified during \fIdatafieldsbyvalue\fR
|
|
|
351 and \fIdatafieldsbyregex\fR mode. Default value: \fI0\fR.
|
|
|
352 .IP "\fB\-w, \-\-workingdir\fR \fIdirname\fR" 4
|
|
|
353 .IX Item "-w, --workingdir dirname"
|
|
|
354 Location of working directory. Default: current directory.
|
|
|
355 .SH "EXAMPLES"
|
|
|
356 .IX Header "EXAMPLES"
|
|
|
357 To retrieve all data fields from \s-1SD\s0 files and generate \s-1CSV\s0 text files, type:
|
|
|
358 .PP
|
|
|
359 .Vb 2
|
|
|
360 \& % ExtractFromSDFiles.pl \-o Sample.sdf
|
|
|
361 \& % ExtractFromSDFiles.pl \-o *.sdf
|
|
|
362 .Ve
|
|
|
363 .PP
|
|
|
364 To retrieve all data fields from \s-1SD\s0 file and generate \s-1CSV\s0 text files containing
|
|
|
365 a column with structure data as a string with | as line delimiter, type:
|
|
|
366 .PP
|
|
|
367 .Vb 1
|
|
|
368 \& % ExtractFromSDFiles.pl \-\-StrDataString Yes \-o Sample.sdf
|
|
|
369 .Ve
|
|
|
370 .PP
|
|
|
371 To retrieve \s-1MOL_ID\s0 data fileld from \s-1SD\s0 file and generate \s-1CSV\s0 text files containing
|
|
|
372 a column with structure data along with all data fields as a string with | as line
|
|
|
373 delimiter, type:
|
|
|
374 .PP
|
|
|
375 .Vb 3
|
|
|
376 \& % ExtractFromSDFiles.pl \-m datafields \-d "Mol_ID" \-\-StrDataString Yes
|
|
|
377 \& \-\-StrDataStringMode StrAndDataFields \-\-StrDataStringDelimiter "|"
|
|
|
378 \& \-\-output text \-o Sample.sdf
|
|
|
379 .Ve
|
|
|
380 .PP
|
|
|
381 To retrieve common data fields which exists for all the compounds in
|
|
|
382 a \s-1SD\s0 file and generate a \s-1TSV\s0 text file NewSample.tsv, type:
|
|
|
383 .PP
|
|
|
384 .Vb 2
|
|
|
385 \& % ExtractFromSDFiles.pl \-m commondatafields \-\-outdelim tab \-r NewSample
|
|
|
386 \& \-\-output Text \-o Sample.sdf
|
|
|
387 .Ve
|
|
|
388 .PP
|
|
|
389 To retrieve MolId, ExtReg, and CompoundName data field from a \s-1SD\s0 file and generate a
|
|
|
390 \&\s-1CSV\s0 text file NewSample.csv, type:
|
|
|
391 .PP
|
|
|
392 .Vb 2
|
|
|
393 \& % ExtractFromSDFiles.pl \-m datafields \-d "Mol_ID,MolWeight,
|
|
|
394 \& CompoundName" \-r NewSample \-\-output Text \-o Sample.sdf
|
|
|
395 .Ve
|
|
|
396 .PP
|
|
|
397 To retrieve compounds from a \s-1SD\s0 which meet a specific set of criteria \- MolWt <= 450,
|
|
|
398 LogP <= 5 and SumNO < 10 \- from a \s-1SD\s0 file and generate a new \s-1SD\s0 file NewSample.sdf,
|
|
|
399 type:
|
|
|
400 .PP
|
|
|
401 .Vb 2
|
|
|
402 \& % ExtractFromSDFiles.pl \-m datafieldsbyvalue \-d "MolWt,450,le,LogP
|
|
|
403 \& ,5,le,SumNO,10" \-r NewSample \-o Sample.sdf
|
|
|
404 .Ve
|
|
|
405 .PP
|
|
|
406 To retrive compounds from a \s-1SD\s0 file with a specific set of values for MolID and
|
|
|
407 generate a new \s-1SD\s0 file NewSample.sdf, type:
|
|
|
408 .PP
|
|
|
409 .Vb 2
|
|
|
410 \& % ExtractFromSDFiles.pl \-m datafieldbylist \-d "Mol_ID,159,4509,4619"
|
|
|
411 \& \-r NewSample \-o Sample.sdf
|
|
|
412 .Ve
|
|
|
413 .PP
|
|
|
414 To retrive compounds from a \s-1SD\s0 file with values for MolID not on a list of specified
|
|
|
415 values and generate a new \s-1SD\s0 file NewSample.sdf, type:
|
|
|
416 .PP
|
|
|
417 .Vb 2
|
|
|
418 \& % ExtractFromSDFiles.pl \-m datafieldnotbylist \-d "Mol_ID,159,4509,4619"
|
|
|
419 \& \-r NewSample \-o Sample.sdf
|
|
|
420 .Ve
|
|
|
421 .PP
|
|
|
422 To retrive 10 random compounds from a \s-1SD\s0 file and generate a new \s-1SD\s0 file RandomSample.sdf, type:
|
|
|
423 .PP
|
|
|
424 .Vb 2
|
|
|
425 \& % ExtractFromSDFiles.pl \-m randomcmpds \-n 10 \-r RandomSample
|
|
|
426 \& \-o Sample.sdf
|
|
|
427 .Ve
|
|
|
428 .PP
|
|
|
429 To retrive compound record number 10 from a \s-1SD\s0 file and generate a new \s-1SD\s0 file NewSample.sdf, type:
|
|
|
430 .PP
|
|
|
431 .Vb 2
|
|
|
432 \& % ExtractFromSDFiles.pl \-m recordnum \-\-record 10 \-r NewSample
|
|
|
433 \& \-o Sample.sdf
|
|
|
434 .Ve
|
|
|
435 .PP
|
|
|
436 To retrive compound record numbers 10, 20 and 30 from a \s-1SD\s0 file and generate a new \s-1SD\s0 file
|
|
|
437 NewSample.sdf, type:
|
|
|
438 .PP
|
|
|
439 .Vb 2
|
|
|
440 \& % ExtractFromSDFiles.pl \-m recordnums \-\-record 10,20,30 \-r NewSample
|
|
|
441 \& \-o Sample.sdf
|
|
|
442 .Ve
|
|
|
443 .PP
|
|
|
444 To retrive compound records between 10 to 20 from \s-1SD\s0 file and generate a new \s-1SD\s0
|
|
|
445 file NewSample.sdf, type:
|
|
|
446 .PP
|
|
|
447 .Vb 2
|
|
|
448 \& % ExtractFromSDFiles.pl \-m recordrange \-\-record 10,20 \-r NewSample
|
|
|
449 \& \-o Sample.sdf
|
|
|
450 .Ve
|
|
|
451 .SH "AUTHOR"
|
|
|
452 .IX Header "AUTHOR"
|
|
|
453 Manish Sud <msud@san.rr.com>
|
|
|
454 .SH "SEE ALSO"
|
|
|
455 .IX Header "SEE ALSO"
|
|
|
456 FilterSDFiles.pl, InfoSDFiles.pl, SplitSDFiles.pl, MergeTextFilesWithSD.pl
|
|
|
457 .SH "COPYRIGHT"
|
|
|
458 .IX Header "COPYRIGHT"
|
|
|
459 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
460 .PP
|
|
|
461 This file is part of MayaChemTools.
|
|
|
462 .PP
|
|
|
463 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
464 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
465 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
466 any later version.
|
