|
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 "EXTRACTFROMPDBFILES 1"
|
|
|
127 .TH EXTRACTFROMPDBFILES 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 ExtractFromPDBFiles.pl \- Extract specific data from PDBFile(s)
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 ExtractFromPDBFiles.pl PDBFile(s)...
|
|
|
137 .PP
|
|
|
138 ExtractFromPDBFiles.pl [\fB\-a, \-\-Atoms\fR \*(L"AtomNum, [AtomNum...]\*(R" | \*(L"StartAtomNum, EndAtomNum\*(R" |
|
|
|
139 \&\*(L"AtomName, [AtomName...]\*(R"] [\fB\-c, \-\-chains\fR First | All | \*(L"ChainID, [ChainID,...]\*(R"]
|
|
|
140 [<\-\-CombineChains> yes | no] [\fB\-d, \-\-distance\fR number] [\fB\-\-DistanceMode\fR Atom | Hetatm | Residue | \s-1XYZ\s0]
|
|
|
141 [\fB\-\-DistanceOrigin\fR \*(L"AtomNumber, AtomName\*(R" | \*(L"HetatmNumber, HetAtmName\*(R" | \*(L"ResidueNumber, ResidueName, [ChainID]\*(R" | \*(L"X,Y,Z\*(R">]
|
|
|
142 [<\-\-DistanceSelectionMode> ByAtom | ByResidue] [\fB\-h, \-\-help\fR] [\fB\-k, \-\-KeepOldRecords\fR yes | no]
|
|
|
143 [\fB\-m, \-\-mode \fR Chains | Sequences | Atoms | CAlphas | AtomNums | AtomsRange | AtomNames |
|
|
|
144 ResidueNums | ResiduesRange | ResidueNames | Distance | NonWater | NonHydrogens]
|
|
|
145 [\fB\-\-ModifyHeader\fR yes | no] [\fB\-\-NonStandardKeep\fR yes | no] [\fB\-\-NonStandardCode\fR character]
|
|
|
146 [\fB\-o, \-\-overwrite\fR] [\fB\-r, \-\-root\fR rootname] \fB\-\-RecordMode\fR \fIAtom | Hetatm | AtomAndHetatm\fR]
|
|
|
147 [\fB\-\-Residues\fR \*(L"ResidueNum,[ResidueNum...]\*(R" | StartResidueNum,EndResiduNum ]
|
|
|
148 [\fB\-\-SequenceLength\fR number] [\fB\-\-SequenceRecords\fR Atom | SeqRes]
|
|
|
149 [\fB\-\-SequenceIDPrefix\fR FileName | HeaderRecord | Automatic]
|
|
|
150 [\fB\-\-WaterResidueNames\fR Automatic | \*(L"ResidueName, [ResidueName,...]\*(R"]
|
|
|
151 [\fB\-w, \-\-WorkingDir\fR dirname] PDBFile(s)...
|
|
|
152 .SH "DESCRIPTION"
|
|
|
153 .IX Header "DESCRIPTION"
|
|
|
154 Extract specific data from \fIPDBFile(s)\fR and generate appropriate \s-1PDB\s0 or sequence file(s).
|
|
|
155 Multiple PDBFile names are separated by spaces. The valid file extension is \fI.pdb\fR.
|
|
|
156 All other file name extensions are ignored during the wild card expansion. All the \s-1PDB\s0 files
|
|
|
157 in a current directory can be specified either by \fI*.pdb\fR or the current directory name.
|
|
|
158 .PP
|
|
|
159 During \fIChains\fR and \fISequences\fR values of \fB\-m, \-\-mode\fR option, all \s-1ATOM/HETAM\s0 records
|
|
|
160 for chains after the first model in \s-1PDB\s0 fils containing data for multiple models are ignored.
|
|
|
161 .SH "OPTIONS"
|
|
|
162 .IX Header "OPTIONS"
|
|
|
163 .ie n .IP "\fB\-a, \-\-Atoms\fR \fI""AtomNum,[AtomNum...]"" | ""StartAtomNum,EndAtomNum"" | ""AtomName,[AtomName...]""\fR" 4
|
|
|
164 .el .IP "\fB\-a, \-\-Atoms\fR \fI``AtomNum,[AtomNum...]'' | ``StartAtomNum,EndAtomNum'' | ``AtomName,[AtomName...]''\fR" 4
|
|
|
165 .IX Item "-a, --Atoms AtomNum,[AtomNum...] | StartAtomNum,EndAtomNum | AtomName,[AtomName...]"
|
|
|
166 Specify which atom records to extract from \fIPDBFiles(s)\fR during \fIAtomNums\fR,
|
|
|
167 \&\fIAtomsRange\fR, and \fIAtomNames\fR value of \fB\-m, \-\-mode\fR option: extract records
|
|
|
168 corresponding to atom numbers specified in a comma delimited list of atom numbers/names,
|
|
|
169 or with in the range of start and end atom numbers. Possible values: \fI\*(L"AtomNum[,AtomNum,..]\*(R"\fR,
|
|
|
170 \&\fIStartAtomNum,EndAtomNum\fR, or \fI\*(L"AtomName[,AtomName,..]\*(R"\fR. Default: \fINone\fR. Examples:
|
|
|
171 .Sp
|
|
|
172 .Vb 3
|
|
|
173 \& 10
|
|
|
174 \& 15,20
|
|
|
175 \& N,CA,C,O
|
|
|
176 .Ve
|
|
|
177 .IP "\fB\-c, \-\-chains\fR \fIFirst | All | ChainID,[ChainID,...]\fR" 4
|
|
|
178 .IX Item "-c, --chains First | All | ChainID,[ChainID,...]"
|
|
|
179 Specify which chains to extract from \fIPDBFile(s)\fR during \fIChains | Sequences\fR value of
|
|
|
180 \&\fB\-m, \-\-mode\fR option: first chain, all chains, or a specific list of comma delimited chain IDs.
|
|
|
181 Possible values: \fIFirst | All | ChainID,[ChainID,...]\fR. Default: \fIFirst\fR. Examples:
|
|
|
182 .Sp
|
|
|
183 .Vb 3
|
|
|
184 \& A
|
|
|
185 \& A,B
|
|
|
186 \& All
|
|
|
187 .Ve
|
|
|
188 .IP "\fB\-\-CombineChains\fR \fIyes | no\fR" 4
|
|
|
189 .IX Item "--CombineChains yes | no"
|
|
|
190 Specify whether to combine extracted chains data into a single file during \fIChains\fR or
|
|
|
191 \&\fISequences\fR value of \fB\-m, \-\-mode\fR option. Possible values: \fIyes | no\fR. Default: \fIno\fR.
|
|
|
192 .Sp
|
|
|
193 During \fIChains\fR value of <\-m, \-\-mode> option with \fIYes\fR value of <\-\-CombineChains>,
|
|
|
194 extracted data for specified chains is written into a single file instead of individual file for each
|
|
|
195 chain.
|
|
|
196 .Sp
|
|
|
197 During \fISequences\fR value of <\-m, \-\-mode> option with \fIYes\fR value of <\-\-CombineChains>,
|
|
|
198 residues sequences for specified chains are extracted and concatenated into a single sequence
|
|
|
199 file instead of individual file for each chain.
|
|
|
200 .IP "\fB\-d, \-\-distance\fR \fInumber\fR" 4
|
|
|
201 .IX Item "-d, --distance number"
|
|
|
202 Specify distance used to extract \s-1ATOM/HETATM\s0 recods during \fIDistance\fR value of
|
|
|
203 \&\fB\-m, \-\-mode\fR option. Default: \fI10.0\fR angstroms.
|
|
|
204 .Sp
|
|
|
205 \&\fB\-\-RecordMode\fR option controls type of record lines to extract from \fIPDBFile(s)\fR:
|
|
|
206 \&\s-1ATOM\s0, \s-1HETATM\s0 or both.
|
|
|
207 .IP "\fB\-\-DistanceMode\fR \fIAtom | Hetatm | Residue | \s-1XYZ\s0\fR" 4
|
|
|
208 .IX Item "--DistanceMode Atom | Hetatm | Residue | XYZ"
|
|
|
209 Specify how to extract \s-1ATOM/HETATM\s0 records from \fIPDBFile(s)\fR during \fIDistance\fR value of
|
|
|
210 \&\fB\-m, \-\-mode\fR option: extract all the records within a certain distance specifed by \fB\-d, \-\-distance\fR
|
|
|
211 from an atom or hetro atom record, a residue, or any artbitrary point. Possible values: \fIAtom |
|
|
|
212 Hetatm | Residue | \s-1XYZ\s0\fR. Default: \fI\s-1XYZ\s0\fR.
|
|
|
213 .Sp
|
|
|
214 During \fIResidue\fR value of \fB\-\-distancemode\fR, distance of \s-1ATOM/HETATM\s0 records is calculated from
|
|
|
215 all the atoms in the residue and the records are selected as long as any atom of the residue lies with
|
|
|
216 in the distace specified using \fB\-d, \-\-distance\fR option.
|
|
|
217 .Sp
|
|
|
218 \&\fB\-\-RecordMode\fR option controls type of record lines to extract from \fIPDBFile(s)\fR:
|
|
|
219 \&\s-1ATOM\s0, \s-1HETATM\s0 or both.
|
|
|
220 .IP "\fB\-\-DistanceSelectionMode\fR \fIByAtom | ByResidue\fR" 4
|
|
|
221 .IX Item "--DistanceSelectionMode ByAtom | ByResidue"
|
|
|
222 Specify how how to extract \s-1ATOM/HETATM\s0 records from \fIPDBFile(s)\fR during \fIDistance\fR value of
|
|
|
223 \&\fB\-m, \-\-mode\fR option for all values of \fB\-\-DistanceMode\fR option: extract only those \s-1ATOM/HETATM\s0
|
|
|
224 records that meet specified distance criterion; extract all records corresponding to a residue as
|
|
|
225 long as one of the \s-1ATOM/HETATM\s0 record in the residue satisfies specified distance criterion. Possible
|
|
|
226 values: \fIByAtom, ByResidue\fR. Default value: \fIByAtom\fR.
|
|
|
227 .ie n .IP "\fB\-\-DistanceOrigin\fR \fI""AtomNumber,AtomName"" | ""HetatmNumber,HetAtmName"" | ""ResidueNumber,ResidueName[,ChainID]"" | ""X,Y,Z""\fR" 4
|
|
|
228 .el .IP "\fB\-\-DistanceOrigin\fR \fI``AtomNumber,AtomName'' | ``HetatmNumber,HetAtmName'' | ``ResidueNumber,ResidueName[,ChainID]'' | ``X,Y,Z''\fR" 4
|
|
|
229 .IX Item "--DistanceOrigin AtomNumber,AtomName | HetatmNumber,HetAtmName | ResidueNumber,ResidueName[,ChainID] | X,Y,Z"
|
|
|
230 This value is \fB\-\-distancemode\fR specific. In general, it identifies a point used to select
|
|
|
231 other \s-1ATOM/HETATMS\s0 with in a specific distance from this point.
|
|
|
232 .Sp
|
|
|
233 For \fIAtom\fR value of \fB\-\-distancemode\fR, this option corresponds to an atom specification.
|
|
|
234 Format: \fIAtomNumber,AtomName\fR. Example:
|
|
|
235 .Sp
|
|
|
236 .Vb 1
|
|
|
237 \& 455,CA
|
|
|
238 .Ve
|
|
|
239 .Sp
|
|
|
240 For \fIHetatm\fR value of \fB\-\-distancemode\fR, this option corresponds to a hetatm specification.
|
|
|
241 Format: \fIHetatmNumber,HetAtmName\fR. Example:
|
|
|
242 .Sp
|
|
|
243 .Vb 1
|
|
|
244 \& 5295,C1
|
|
|
245 .Ve
|
|
|
246 .Sp
|
|
|
247 For \fIResidue\fR value of \fB\-\-distancemode\fR, this option corresponds to a residue specification.
|
|
|
248 Format: \fIResidueNumber, ResidueName[,ChainID]\fR. Example:
|
|
|
249 .Sp
|
|
|
250 .Vb 3
|
|
|
251 \& 78,MSE
|
|
|
252 \& 977,RET,A
|
|
|
253 \& 978,RET,B
|
|
|
254 .Ve
|
|
|
255 .Sp
|
|
|
256 For \fI\s-1XYZ\s0\fR value of \fB\-\-distancemode\fR, this option corresponds to a coordinate of an
|
|
|
257 arbitrary point. Format: \fIX,Y,X\fR. Example:
|
|
|
258 .Sp
|
|
|
259 .Vb 1
|
|
|
260 \& 10.044,19.261,\-4.292
|
|
|
261 .Ve
|
|
|
262 .Sp
|
|
|
263 \&\fB\-\-RecordMode\fR option controls type of record lines to extract from \fIPDBFile(s)\fR:
|
|
|
264 \&\s-1ATOM\s0, \s-1HETATM\s0 or both.
|
|
|
265 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
266 .IX Item "-h, --help"
|
|
|
267 Print this help message.
|
|
|
268 .IP "\fB\-k, \-\-KeepOldRecords\fR \fIyes | no\fR" 4
|
|
|
269 .IX Item "-k, --KeepOldRecords yes | no"
|
|
|
270 Specify whether to transfer old non \s-1ATOM\s0 and \s-1HETATM\s0 records from input PDBFile(s) to new
|
|
|
271 PDBFile(s) during \fIChains | Atoms | HetAtms | CAlphas | Distance| NonWater | NonHydrogens\fR
|
|
|
272 value of \fB\-m \-\-mode\fR option. By default, except for the \s-1HEADER\s0 record, all
|
|
|
273 other unnecessary non \s-1ATOM/HETATM\s0 records are dropped during the
|
|
|
274 generation of new \s-1PDB\s0 files. Possible values: \fIyes | no\fR. Default: \fIno\fR.
|
|
|
275 .IP "\fB\-m, \-\-mode \fR \fIChains | Sequences | Atoms | CAlphas | AtomNums | AtomsRange | AtomNames | ResidueNums | ResiduesRange | ResidueNames | Distance | NonWater | NonHydrogens\fR" 4
|
|
|
276 .IX Item "-m, --mode Chains | Sequences | Atoms | CAlphas | AtomNums | AtomsRange | AtomNames | ResidueNums | ResiduesRange | ResidueNames | Distance | NonWater | NonHydrogens"
|
|
|
277 Specify what to extract from \fIPDBFile(s)\fR: \fIChains\fR \- retrieve records for
|
|
|
278 specified chains; \fISequences\fR \- generate sequence files for specific chains;
|
|
|
279 \&\fIAtoms\fR \- extract atom records; \fICAlphas\fR \- extract atom records for alpha
|
|
|
280 carbon atoms; \fIAtomNums\fR \- extract atom records for specified atom numbers;
|
|
|
281 \&\fIAtomsRange\fR \- extract atom records between specified atom number range;
|
|
|
282 \&\fIAtomNames\fR \- extract atom records for specified atom names; \fIResidueNums\fR
|
|
|
283 \&\- extract records for specified residue numbers; \fIResiduesRange\fR \- extract records
|
|
|
284 for residues between specified residue number range; \fIResidueNames\fR \- extract
|
|
|
285 records for specified residue names; \fIDistance\fR \- extract records with in a
|
|
|
286 certain distance from a specific position; \fINonWater\fR \- extract records corresponding
|
|
|
287 to residues other than water; \fINonHydrogens\fR \- extract non-hydrogen records.
|
|
|
288 .Sp
|
|
|
289 Possible values: \fIChains, Sequences Atoms, CAlphas, AtomNums, AtomsRange,
|
|
|
290 AtomNames, ResidueNums, ResiduesRange, ResidueNames, Distance, NonWater,
|
|
|
291 NonHydrogens\fR. Default value: \fINonWater\fR
|
|
|
292 .Sp
|
|
|
293 During the generation of new \s-1PDB\s0 files, unnecessay \s-1CONECT\s0 records are dropped.
|
|
|
294 .Sp
|
|
|
295 For \fIChains\fR mode, data for appropriate chains specified by \fB\-\-c \-\-chains\fR option
|
|
|
296 is extracted from \fIPDBFile(s)\fR and placed into new \s-1PDB\s0 file(s).
|
|
|
297 .Sp
|
|
|
298 For \fISequences\fR mode, residues names using various sequence related options are
|
|
|
299 extracted for chains specified by \fB\-\-c \-\-chains\fR option from \fIPDBFile(s)\fR and
|
|
|
300 \&\s-1FASTA\s0 sequence file(s) are generated.
|
|
|
301 .Sp
|
|
|
302 For \fIDistance\fR mode, all \s-1ATOM/HETATM\s0 records with in a distance specified
|
|
|
303 by \fB\-d \-\-distance\fR option from a specific atom, residue or a point indicated by
|
|
|
304 \&\fB\-\-distancemode\fR are extracted and placed into new \s-1PDB\s0 file(s).
|
|
|
305 .Sp
|
|
|
306 For \fINonWater\fR mode, non water \s-1ATOM/HETATM\s0 record lines, identified using value of
|
|
|
307 \&\fB\-\-WaterResidueNames\fR, are extracted and written to new \s-1PDB\s0 file(s).
|
|
|
308 .Sp
|
|
|
309 For \fINonHydrogens\fR mode, \s-1ATOM/HETATOM\s0 record lines containing element symbol
|
|
|
310 other than \fIH\fR are extracted and written to new \s-1PDB\s0 file(s).
|
|
|
311 .Sp
|
|
|
312 For all other options, appropriate \s-1ATOM/HETATM\s0 records are extracted to generate new
|
|
|
313 \&\s-1PDB\s0 file(s).
|
|
|
314 .Sp
|
|
|
315 \&\fB\-\-RecordMode\fR option controls type of record lines to extract and process from
|
|
|
316 \&\fIPDBFile(s)\fR: \s-1ATOM\s0, \s-1HETATM\s0 or both.
|
|
|
317 .IP "\fB\-\-ModifyHeader\fR \fIyes | no\fR" 4
|
|
|
318 .IX Item "--ModifyHeader yes | no"
|
|
|
319 Specify whether to modify \s-1HEADER\s0 record during the generation of new \s-1PDB\s0 files
|
|
|
320 for \fB\-m, \-\-mode\fR values of \fIChains | Atoms | CAlphas | Distance\fR. Possible values:
|
|
|
321 \&\fIyes | no\fR. Default: \fIyes\fR. By default, Classification data is replaced by \fIData extracted
|
|
|
322 using MayaChemTools\fR before writing out \s-1HEADER\s0 record.
|
|
|
323 .IP "\fB\-\-NonStandardKeep\fR \fIyes | no\fR" 4
|
|
|
324 .IX Item "--NonStandardKeep yes | no"
|
|
|
325 Specify whether to include and convert non-standard three letter residue codes into
|
|
|
326 a code specified using \fB\-\-nonstandardcode\fR option and include them into sequence file(s)
|
|
|
327 generated during \fISequences\fR value of \fB\-m, \-\-mode\fR option. Possible values: \fIyes | no\fR.
|
|
|
328 Default: \fIyes\fR.
|
|
|
329 .Sp
|
|
|
330 A warning is also printed about the presence of non-standard residues. Any residue other
|
|
|
331 than standard 20 amino acids and 5 nucleic acid is considered non-standard; additionally,
|
|
|
332 \&\s-1HETATM\s0 residues in chains also tagged as non-standard.
|
|
|
333 .IP "\fB\-\-NonStandardCode\fR \fIcharacter\fR" 4
|
|
|
334 .IX Item "--NonStandardCode character"
|
|
|
335 A single character code to use for non-standard residues. Default: \fIX\fR. Possible values:
|
|
|
336 \&\fI?, \-, or X\fR.
|
|
|
337 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
|
338 .IX Item "-o, --overwrite"
|
|
|
339 Overwrite existing files.
|
|
|
340 .IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
|
|
|
341 .IX Item "-r, --root rootname"
|
|
|
342 New \s-1PDB\s0 and sequence file name is generated using the root: <Root><Mode>.<Ext>.
|
|
|
343 Default new file name: <PDBFileName>Chain<ChainID>.pdb for \fIChains\fR \fBmode\fR;
|
|
|
344 <PDBFileName>SequenceChain<ChainID>.fasta for \fISequences\fR \fBmode\fR;
|
|
|
345 <PDBFileName>DistanceBy<DistanceMode>.pdb for \fIDistance\fR \fB\-m, \-\-mode\fR
|
|
|
346 <PDBFileName><Mode>.pdb for \fIAtoms | CAlphas | NonWater | NonHydrogens\fR \fB\-m, \-\-mode\fR
|
|
|
347 values. This option is ignored for multiple input files.
|
|
|
348 .IP "\fB\-\-RecordMode\fR \fIAtom | Hetatm | AtomAndHetatm\fR" 4
|
|
|
349 .IX Item "--RecordMode Atom | Hetatm | AtomAndHetatm"
|
|
|
350 Specify type of record lines to extract and process from \fIPDBFile(s)\fR during various
|
|
|
351 values of \fB\-m, \-\-mode\fR option: extract only \s-1ATOM\s0 record lines; extract only \s-1HETATM\s0
|
|
|
352 record lines; extract both \s-1ATOM\s0 and \s-1HETATM\s0 lines. Possible values: \fIAtom | Hetatm
|
|
|
353 | AtomAndHetatm | \s-1XYZ\s0\fR. Default during \fIAtoms, CAlphas, AtomNums, AtomsRange,
|
|
|
354 AtomNames\fR values of \fB\-m, \-\-mode\fR option: \fIAtom\fR; otherwise: \fIAtomAndHetatm\fR.
|
|
|
355 .Sp
|
|
|
356 This option is ignored during \fIChains, Sequences\fR values of \fB\-m, \-\-mode\fR option.
|
|
|
357 .ie n .IP "\fB\-\-Residues\fR \fI""ResidueNum,[ResidueNum...]"" | ""StartResidueNum,EndResiduNum"" | ""ResidueName,[ResidueName...]""\fR" 4
|
|
|
358 .el .IP "\fB\-\-Residues\fR \fI``ResidueNum,[ResidueNum...]'' | ``StartResidueNum,EndResiduNum'' | ``ResidueName,[ResidueName...]''\fR" 4
|
|
|
359 .IX Item "--Residues ResidueNum,[ResidueNum...] | StartResidueNum,EndResiduNum | ResidueName,[ResidueName...]"
|
|
|
360 Specify which resiude records to extract from \fIPDBFiles(s)\fR during \fIResidueNums\fR,
|
|
|
361 \&\fIResiduesRange\fR,and \fIResidueNames\fR value of \fB\-m, \-\-mode\fR option: extract records
|
|
|
362 corresponding to residue numbers specified in a comma delimited list of residue numbers/names,
|
|
|
363 or with in the range of start and end residue numbers. Possible values: \fI\*(L"ResidueNum[,ResidueNum,..]\*(R"\fR,
|
|
|
364 \&\fIStartResidueNum,EndResiduNum\fR, or \fI<\*(L"ResidueName[,ResidueName,..]\*(R"\fR. Default: \fINone\fR. Examples:
|
|
|
365 .Sp
|
|
|
366 .Vb 3
|
|
|
367 \& 20
|
|
|
368 \& 5,10
|
|
|
369 \& TYR,SER,THR
|
|
|
370 .Ve
|
|
|
371 .Sp
|
|
|
372 \&\fB\-\-RecordMode\fR option controls type of record lines to extract from \fIPDBFile(s)\fR:
|
|
|
373 \&\s-1ATOM\s0, \s-1HETATM\s0 or both.
|
|
|
374 .IP "\fB\-\-SequenceLength\fR \fInumber\fR" 4
|
|
|
375 .IX Item "--SequenceLength number"
|
|
|
376 Maximum sequence length per line in sequence file(s). Default: \fI80\fR.
|
|
|
377 .IP "\fB\-\-SequenceRecords\fR \fIAtom | SeqRes\fR" 4
|
|
|
378 .IX Item "--SequenceRecords Atom | SeqRes"
|
|
|
379 Specify which records to use for extracting residue names from \fIPDBFiles(s)\fR during
|
|
|
380 \&\fISequences\fR value of \fB\-m, \-\-mode\fR option: use \s-1ATOM\s0 records to compile a list
|
|
|
381 of residues in a chain or parse \s-1SEQRES\s0 record to get a list of residues. Possible values:
|
|
|
382 \&\fIAtom | SeqRes\fR. Default: \fIAtom\fR.
|
|
|
383 .IP "\fB\-\-SequenceIDPrefix\fR \fIFileName | HeaderRecord | Automatic\fR" 4
|
|
|
384 .IX Item "--SequenceIDPrefix FileName | HeaderRecord | Automatic"
|
|
|
385 Specify how to generate a prefix for sequence IDs during \fISequences\fR value
|
|
|
386 of \fB\-m, \-\-mode\fR option: use input file name prefix; retrieve \s-1PDB\s0 \s-1ID\s0 from \s-1HEADER\s0 record;
|
|
|
387 or automatically decide the method for generating the prefix. The chain IDs are also
|
|
|
388 appended to the prefix. Possible values: \fIFileName | HeaderRecord | Automatic\fR.
|
|
|
389 Default: \fIAutomatic\fR
|
|
|
390 .ie n .IP "\fB\-\-WaterResidueNames\fR \fIAutomatic | ""ResidueName,[ResidueName,...]""\fR" 4
|
|
|
391 .el .IP "\fB\-\-WaterResidueNames\fR \fIAutomatic | ``ResidueName,[ResidueName,...]''\fR" 4
|
|
|
392 .IX Item "--WaterResidueNames Automatic | ResidueName,[ResidueName,...]"
|
|
|
393 Identification of water residues during \fINonWater\fR value of \fB\-m, \-\-mode\fR option. Possible values:
|
|
|
394 \&\fIAutomatic | \*(L"ResidueName,[ResidueName,...]\*(R"\fR. Default: \fIAutomatic\fR \- corresponds
|
|
|
395 to \*(L"\s-1HOH\s0,WAT,H20\*(R". You can also specify a different comma delimited list of residue names
|
|
|
396 to use for water.
|
|
|
397 .IP "\fB\-w, \-\-WorkingDir\fR \fIdirname\fR" 4
|
|
|
398 .IX Item "-w, --WorkingDir dirname"
|
|
|
399 Location of working directory. Default: current directory.
|
|
|
400 .SH "EXAMPLES"
|
|
|
401 .IX Header "EXAMPLES"
|
|
|
402 To extract non-water records from Sample2.pdb file and generate Sample2NonWater.pdb
|
|
|
403 file, type:
|
|
|
404 .PP
|
|
|
405 .Vb 1
|
|
|
406 \& % ExtractFromPDBFiles.pl Sample2.pdb
|
|
|
407 .Ve
|
|
|
408 .PP
|
|
|
409 To extract non-water records corresponding to only \s-1ATOM\s0 records from Sample2.pdb file
|
|
|
410 and generate Sample2NonWater.pdb file, type:
|
|
|
411 .PP
|
|
|
412 .Vb 1
|
|
|
413 \& % ExtractFromPDBFiles.pl \-\-RecordMode Atom Sample2.pdb
|
|
|
414 .Ve
|
|
|
415 .PP
|
|
|
416 To extract non-water records from Sample2.pdb file using \s-1HOH\s0 or \s-1WAT\s0 residue name for water along
|
|
|
417 with all old non-coordinate records and generate Sample2NewNonWater.pdb file, type:
|
|
|
418 .PP
|
|
|
419 .Vb 2
|
|
|
420 \& % ExtractFromPDBFiles.pl \-m NonWater \-\-WaterResidueNames "HOH,WAT"
|
|
|
421 \& \-KeepOldRecords Yes \-r Sample2New \-o Sample2.pdb
|
|
|
422 .Ve
|
|
|
423 .PP
|
|
|
424 To extract non-hydrogens records from Sample2.pdb file and generate Sample2NonHydrogen.pdb
|
|
|
425 file, type:
|
|
|
426 .PP
|
|
|
427 .Vb 1
|
|
|
428 \& % ExtractFromPDBFiles.pl \-m NonHydrogens Sample2.pdb
|
|
|
429 .Ve
|
|
|
430 .PP
|
|
|
431 To extract data for first chain in Sample2.pdb and generate Sample2ChainA.pdb, type
|
|
|
432 file, type:
|
|
|
433 .PP
|
|
|
434 .Vb 1
|
|
|
435 \& % ExtractFromPDBFiles.pl \-m chains \-o Sample2.pdb
|
|
|
436 .Ve
|
|
|
437 .PP
|
|
|
438 To extract data for both chains in Sample2.pdb and generate Sample2ChainA.pdb and
|
|
|
439 Sample2ChainB.pdb, type:
|
|
|
440 .PP
|
|
|
441 .Vb 1
|
|
|
442 \& % ExtractFromPDBFiles.pl \-m chains \-c All \-o Sample2.pdb
|
|
|
443 .Ve
|
|
|
444 .PP
|
|
|
445 To extract data for alpha carbons in Sample2.pdb and generate Sample2CAlphas.pdb, type:
|
|
|
446 .PP
|
|
|
447 .Vb 1
|
|
|
448 \& % ExtractFromPDBFiles.pl \-m CAlphas \-o Sample2.pdb
|
|
|
449 .Ve
|
|
|
450 .PP
|
|
|
451 To extract records for specific residue numbers in all chains from Sample2.pdb file and generate
|
|
|
452 Sample2ResidueNums.pdb file, type:
|
|
|
453 .PP
|
|
|
454 .Vb 2
|
|
|
455 \& % ExtractFromPDBFiles.pl \-m ResidueNums \-\-Residues "3,6"
|
|
|
456 \& Sample2.pdb
|
|
|
457 .Ve
|
|
|
458 .PP
|
|
|
459 To extract records for a specific range of residue number in all chains from Sample2.pdb
|
|
|
460 file and generate Sample2ResiduesRange.pdb file, type:
|
|
|
461 .PP
|
|
|
462 .Vb 2
|
|
|
463 \& % ExtractFromPDBFiles.pl \-m ResiduesRange \-\-Residues "10,30"
|
|
|
464 \& Sample2.pdb
|
|
|
465 .Ve
|
|
|
466 .PP
|
|
|
467 To extract data for all \s-1ATOM\s0 and \s-1HETATM\s0 records with in 10 angstrom of an atom specifed by
|
|
|
468 atom serial number and name \*(L"1,N\*(R" in Sample2.pdb file and generate Sample2DistanceByAtom.pdb,
|
|
|
469 type:
|
|
|
470 .PP
|
|
|
471 .Vb 2
|
|
|
472 \& % ExtractFromPDBFiles.pl \-m Distance \-\-DistanceMode Atom
|
|
|
473 \& \-\-DistanceOrigin "1,N" \-k No \-\-distance 10 \-o Sample2.pdb
|
|
|
474 .Ve
|
|
|
475 .PP
|
|
|
476 To extract data for all \s-1ATOM\s0 and \s-1HETATM\s0 records for complete residues with any atom or hetatm
|
|
|
477 less than 10 angstrom of an atom specifed by atom serial number and name \*(L"1,N\*(R" in Sample2.pdb
|
|
|
478 file and generate Sample2DistanceByAtom.pdb, type:
|
|
|
479 .PP
|
|
|
480 .Vb 3
|
|
|
481 \& % ExtractFromPDBFiles.pl \-m Distance \-\-DistanceMode Atom
|
|
|
482 \& \-\-DistanceOrigin "1,N" \-\-DistanceSelectionMode ByResidue
|
|
|
483 \& \-k No \-\-distance 10 \-o Sample2.pdb
|
|
|
484 .Ve
|
|
|
485 .PP
|
|
|
486 To extract data for all \s-1ATOM\s0 and \s-1HETATM\s0 records with in 25 angstrom of an arbitrary point \*(L"0,0,0\*(R"
|
|
|
487 in Sample2.pdb file and generate Sample2DistanceByXYZ.pdb, type:
|
|
|
488 .PP
|
|
|
489 .Vb 2
|
|
|
490 \& % ExtractFromPDBFiles.pl \-m Distance \-\-DistanceMode XYZ
|
|
|
491 \& \-\-DistanceOrigin "0,0,0" \-k No \-\-distance 25 \-o Sample2.pdb
|
|
|
492 .Ve
|
|
|
493 .SH "AUTHOR"
|
|
|
494 .IX Header "AUTHOR"
|
|
|
495 Manish Sud <msud@san.rr.com>
|
|
|
496 .SH "SEE ALSO"
|
|
|
497 .IX Header "SEE ALSO"
|
|
|
498 InfoPDBFiles.pl, ModifyPDBFiles.pl
|
|
|
499 .SH "COPYRIGHT"
|
|
|
500 .IX Header "COPYRIGHT"
|
|
|
501 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
502 .PP
|
|
|
503 This file is part of MayaChemTools.
|
|
|
504 .PP
|
|
|
505 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
506 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
507 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
508 any later version.
|
