|
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 "CALCULATEPHYSICOCHEMICALPROPERTIES 1"
|
|
|
127 .TH CALCULATEPHYSICOCHEMICALPROPERTIES 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 CalculatePhysicochemicalProperties.pl \- Calculate physicochemical properties for SD files
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 CalculatePhysicochemicalProperties.pl SDFile(s)...
|
|
|
137 .PP
|
|
|
138 PhysicochemicalProperties.pl [\fB\-\-AromaticityModel\fR \fIAromaticityModelType\fR]
|
|
|
139 [\fB\-\-CompoundID\fR DataFieldName or LabelPrefixString]
|
|
|
140 [\fB\-\-CompoundIDLabel\fR text] [\fB\-\-CompoundIDMode\fR] [\fB\-\-DataFields\fR \*(L"FieldLabel1, FieldLabel2,...\*(R"]
|
|
|
141 [\fB\-d, \-\-DataFieldsMode\fR All | Common | Specify | CompoundID] [\fB\-f, \-\-Filter\fR Yes | No] [\fB\-h, \-\-help\fR]
|
|
|
142 [\fB\-\-HydrogenBonds\fR HBondsType1 | HBondsType2] [\fB\-k, \-\-KeepLargestComponent\fR Yes | No]
|
|
|
143 [\fB\-m, \-\-mode\fR All | RuleOf5 | RuleOf3 | \*(L"name1, [name2,...]\*(R"]
|
|
|
144 [\fB\-\-MolecularComplexity\fR \fIName,Value, [Name,Value,...]\fR]
|
|
|
145 [\fB\-\-OutDelim\fR comma | tab | semicolon] [\fB\-\-output\fR \s-1SD\s0 | text | both] [\fB\-o, \-\-overwrite\fR]
|
|
|
146 [\fB\-\-Precision\fR Name,Number,[Name,Number,..]] [\fB\-\-RotatableBonds\fR Name,Value, [Name,Value,...]]
|
|
|
147 [\fB\-\-RuleOf3Violations\fR Yes | No] [\fB\-\-RuleOf5Violations\fR Yes | No]
|
|
|
148 [\fB\-q, \-\-quote\fR Yes | No] [\fB\-r, \-\-root\fR RootName]
|
|
|
149 [\fB\-w, \-\-WorkingDir\fR dirname] SDFile(s)...
|
|
|
150 .SH "DESCRIPTION"
|
|
|
151 .IX Header "DESCRIPTION"
|
|
|
152 Calculate physicochemical properties for \fISDFile(s)\fR and create appropriate \s-1SD\s0 or \s-1CSV/TSV\s0
|
|
|
153 text file(s) containing calculated properties.
|
|
|
154 .PP
|
|
|
155 The current release of MayaChemTools supports the calculation of these physicochemical
|
|
|
156 properties:
|
|
|
157 .PP
|
|
|
158 .Vb 7
|
|
|
159 \& MolecularWeight, ExactMass, HeavyAtoms, Rings, AromaticRings,
|
|
|
160 \& van der Waals MolecularVolume [ Ref 93 ], RotatableBonds,
|
|
|
161 \& HydrogenBondDonors, HydrogenBondAcceptors, LogP and
|
|
|
162 \& Molar Refractivity (SLogP and SMR) [ Ref 89 ], Topological Polar
|
|
|
163 \& Surface Area (TPSA) [ Ref 90 ], Fraction of SP3 carbons (Fsp3Carbons)
|
|
|
164 \& and SP3 carbons (Sp3Carbons) [ Ref 115\-116, Ref 119 ],
|
|
|
165 \& MolecularComplexity [ Ref 117\-119 ]
|
|
|
166 .Ve
|
|
|
167 .PP
|
|
|
168 Multiple SDFile names are separated by spaces. The valid file extensions are \fI.sdf\fR
|
|
|
169 and \fI.sd\fR. All other file names are ignored. All the \s-1SD\s0 files in a current directory
|
|
|
170 can be specified either by \fI*.sdf\fR or the current directory name.
|
|
|
171 .PP
|
|
|
172 The calculation of molecular complexity using \fIMolecularComplexityType\fR parameter
|
|
|
173 corresponds to the number of bits-set or unique keys [ Ref 117\-119 ] in molecular fingerprints.
|
|
|
174 Default value for \fIMolecularComplexityType\fR: \fIMACCSKeys\fR of size 166. The calculation
|
|
|
175 of MACCSKeys is relatively expensive and can take rather substantial amount of time.
|
|
|
176 .SH "OPTIONS"
|
|
|
177 .IX Header "OPTIONS"
|
|
|
178 .IP "\fB\-\-AromaticityModel\fR \fIMDLAromaticityModel | TriposAromaticityModel | MMFFAromaticityModel | ChemAxonBasicAromaticityModel | ChemAxonGeneralAromaticityModel | DaylightAromaticityModel | MayaChemToolsAromaticityModel\fR" 4
|
|
|
179 .IX Item "--AromaticityModel MDLAromaticityModel | TriposAromaticityModel | MMFFAromaticityModel | ChemAxonBasicAromaticityModel | ChemAxonGeneralAromaticityModel | DaylightAromaticityModel | MayaChemToolsAromaticityModel"
|
|
|
180 Specify aromaticity model to use during detection of aromaticity. Possible values in the current
|
|
|
181 release are: \fIMDLAromaticityModel, TriposAromaticityModel, MMFFAromaticityModel,
|
|
|
182 ChemAxonBasicAromaticityModel, ChemAxonGeneralAromaticityModel, DaylightAromaticityModel
|
|
|
183 or MayaChemToolsAromaticityModel\fR. Default value: \fIMayaChemToolsAromaticityModel\fR.
|
|
|
184 .Sp
|
|
|
185 The supported aromaticity model names along with model specific control parameters
|
|
|
186 are defined in \fBAromaticityModelsData.csv\fR, which is distributed with the current release
|
|
|
187 and is available under \fBlib/data\fR directory. \fBMolecule.pm\fR module retrieves data from
|
|
|
188 this file during class instantiation and makes it available to method \fBDetectAromaticity\fR
|
|
|
189 for detecting aromaticity corresponding to a specific model.
|
|
|
190 .IP "\fB\-\-CompoundID\fR \fIDataFieldName or LabelPrefixString\fR" 4
|
|
|
191 .IX Item "--CompoundID DataFieldName or LabelPrefixString"
|
|
|
192 This value is \fB\-\-CompoundIDMode\fR specific and indicates how compound \s-1ID\s0 is generated.
|
|
|
193 .Sp
|
|
|
194 For \fIDataField\fR value of \fB\-\-CompoundIDMode\fR option, it corresponds to datafield label name
|
|
|
195 whose value is used as compound \s-1ID\s0; otherwise, it's a prefix string used for generating compound
|
|
|
196 IDs like LabelPrefixString<Number>. Default value, \fICmpd\fR, generates compound IDs which
|
|
|
197 look like Cmpd<Number>.
|
|
|
198 .Sp
|
|
|
199 Examples for \fIDataField\fR value of \fB\-\-CompoundIDMode\fR:
|
|
|
200 .Sp
|
|
|
201 .Vb 2
|
|
|
202 \& MolID
|
|
|
203 \& ExtReg
|
|
|
204 .Ve
|
|
|
205 .Sp
|
|
|
206 Examples for \fILabelPrefix\fR or \fIMolNameOrLabelPrefix\fR value of \fB\-\-CompoundIDMode\fR:
|
|
|
207 .Sp
|
|
|
208 .Vb 1
|
|
|
209 \& Compound
|
|
|
210 .Ve
|
|
|
211 .Sp
|
|
|
212 The value specified above generates compound IDs which correspond to Compound<Number>
|
|
|
213 instead of default value of Cmpd<Number>.
|
|
|
214 .IP "\fB\-\-CompoundIDLabel\fR \fItext\fR" 4
|
|
|
215 .IX Item "--CompoundIDLabel text"
|
|
|
216 Specify compound \s-1ID\s0 column label for \s-1CSV/TSV\s0 text file(s) used during \fICompoundID\fR value
|
|
|
217 of \fB\-\-DataFieldsMode\fR option. Default value: \fICompoundID\fR.
|
|
|
218 .IP "\fB\-\-CompoundIDMode\fR \fIDataField | MolName | LabelPrefix | MolNameOrLabelPrefix\fR" 4
|
|
|
219 .IX Item "--CompoundIDMode DataField | MolName | LabelPrefix | MolNameOrLabelPrefix"
|
|
|
220 Specify how to generate compound IDs and write to \s-1CSV/TSV\s0 text file(s) along with calculated
|
|
|
221 physicochemical properties for \fItext | both\fR values of \fB\-\-output\fR option: use a \fISDFile(s)\fR
|
|
|
222 datafield value; use molname line from \fISDFile(s)\fR; generate a sequential \s-1ID\s0 with specific prefix;
|
|
|
223 use combination of both MolName and LabelPrefix with usage of LabelPrefix values for empty
|
|
|
224 molname lines.
|
|
|
225 .Sp
|
|
|
226 Possible values: \fIDataField | MolName | LabelPrefix | MolNameOrLabelPrefix\fR.
|
|
|
227 Default value: \fILabelPrefix\fR.
|
|
|
228 .Sp
|
|
|
229 For \fIMolNameAndLabelPrefix\fR value of \fB\-\-CompoundIDMode\fR, molname line in \fISDFile(s)\fR takes
|
|
|
230 precedence over sequential compound IDs generated using \fILabelPrefix\fR and only empty molname
|
|
|
231 values are replaced with sequential compound IDs.
|
|
|
232 .Sp
|
|
|
233 This is only used for \fICompoundID\fR value of \fB\-\-DataFieldsMode\fR option.
|
|
|
234 .ie n .IP "\fB\-\-DataFields\fR \fI""FieldLabel1,FieldLabel2,...""\fR" 4
|
|
|
235 .el .IP "\fB\-\-DataFields\fR \fI``FieldLabel1,FieldLabel2,...''\fR" 4
|
|
|
236 .IX Item "--DataFields FieldLabel1,FieldLabel2,..."
|
|
|
237 Comma delimited list of \fISDFiles(s)\fR data fields to extract and write to \s-1CSV/TSV\s0 text file(s) along
|
|
|
238 with calculated physicochemical properties for \fItext | both\fR values of \fB\-\-output\fR option.
|
|
|
239 .Sp
|
|
|
240 This is only used for \fISpecify\fR value of \fB\-\-DataFieldsMode\fR option.
|
|
|
241 .Sp
|
|
|
242 Examples:
|
|
|
243 .Sp
|
|
|
244 .Vb 2
|
|
|
245 \& Extreg
|
|
|
246 \& MolID,CompoundName
|
|
|
247 .Ve
|
|
|
248 .IP "\fB\-d, \-\-DataFieldsMode\fR \fIAll | Common | Specify | CompoundID\fR" 4
|
|
|
249 .IX Item "-d, --DataFieldsMode All | Common | Specify | CompoundID"
|
|
|
250 Specify how data fields in \fISDFile(s)\fR are transferred to output \s-1CSV/TSV\s0 text file(s) along
|
|
|
251 with calculated physicochemical properties for \fItext | both\fR values of \fB\-\-output\fR option:
|
|
|
252 transfer all \s-1SD\s0 data field; transfer \s-1SD\s0 data files common to all compounds; extract specified
|
|
|
253 data fields; generate a compound \s-1ID\s0 using molname line, a compound prefix, or a combination
|
|
|
254 of both. Possible values: \fIAll | Common | specify | CompoundID\fR. Default value: \fICompoundID\fR.
|
|
|
255 .IP "\fB\-f, \-\-Filter\fR \fIYes | No\fR" 4
|
|
|
256 .IX Item "-f, --Filter Yes | No"
|
|
|
257 Specify whether to check and filter compound data in SDFile(s). Possible values: \fIYes or No\fR.
|
|
|
258 Default value: \fIYes\fR.
|
|
|
259 .Sp
|
|
|
260 By default, compound data is checked before calculating physiochemical properties and compounds
|
|
|
261 containing atom data corresponding to non-element symbols or no atom data are ignored.
|
|
|
262 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
263 .IX Item "-h, --help"
|
|
|
264 Print this help message.
|
|
|
265 .IP "\fB\-\-HydrogenBonds\fR \fIHBondsType1 | HBondsType2\fR" 4
|
|
|
266 .IX Item "--HydrogenBonds HBondsType1 | HBondsType2"
|
|
|
267 Parameters to control calculation of hydrogen bond donors and acceptors. Possible values:
|
|
|
268 \&\fIHBondsType1, HydrogenBondsType1, HBondsType2, HydrogenBondsType2\fR. Default value:
|
|
|
269 \&\fIHBondsType2\fR which corresponds to \fBRuleOf5\fR definition for number of hydrogen bond
|
|
|
270 donors and acceptors.
|
|
|
271 .Sp
|
|
|
272 The current release of MayaChemTools supports identification of two types of hydrogen bond
|
|
|
273 donor and acceptor atoms with these names:
|
|
|
274 .Sp
|
|
|
275 .Vb 2
|
|
|
276 \& HBondsType1 or HydrogenBondsType1
|
|
|
277 \& HBondsType2 or HydrogenBondsType2
|
|
|
278 .Ve
|
|
|
279 .Sp
|
|
|
280 The names of these hydrogen bond types are rather arbitrary. However, their definitions have
|
|
|
281 specific meaning and are as follows:
|
|
|
282 .Sp
|
|
|
283 .Vb 1
|
|
|
284 \& HydrogenBondsType1 [ Ref 60\-61, Ref 65\-66 ]:
|
|
|
285 \&
|
|
|
286 \& Donor: NH, NH2, OH \- Any N and O with available H
|
|
|
287 \& Acceptor: N[!H], O \- Any N without available H and any O
|
|
|
288 \&
|
|
|
289 \& HydrogenBondsType2 [ Ref 91 ]:
|
|
|
290 \&
|
|
|
291 \& Donor: NH, NH2, OH \- N and O with available H
|
|
|
292 \& Acceptor: N, O \- And N and O
|
|
|
293 .Ve
|
|
|
294 .IP "\fB\-k, \-\-KeepLargestComponent\fR \fIYes | No\fR" 4
|
|
|
295 .IX Item "-k, --KeepLargestComponent Yes | No"
|
|
|
296 Calculate physicochemical properties for only the largest component in molecule. Possible values:
|
|
|
297 \&\fIYes or No\fR. Default value: \fIYes\fR.
|
|
|
298 .Sp
|
|
|
299 For molecules containing multiple connected components, physicochemical properties can be
|
|
|
300 calculated in two different ways: use all connected components or just the largest connected
|
|
|
301 component. By default, all atoms except for the largest connected component are
|
|
|
302 deleted before calculation of physicochemical properties.
|
|
|
303 .ie n .IP "\fB\-m, \-\-mode\fR \fIAll | RuleOf5 | RuleOf3 | ""name1, [name2,...]""\fR" 4
|
|
|
304 .el .IP "\fB\-m, \-\-mode\fR \fIAll | RuleOf5 | RuleOf3 | ``name1, [name2,...]''\fR" 4
|
|
|
305 .IX Item "-m, --mode All | RuleOf5 | RuleOf3 | name1, [name2,...]"
|
|
|
306 Specify physicochemical properties to calculate for SDFile(s): calculate all available physical
|
|
|
307 chemical properties; calculate properties corresponding to Rule of 5; or use a comma delimited
|
|
|
308 list of supported physicochemical properties. Possible values: \fIAll | RuleOf5 | RuleOf3 |
|
|
|
309 \&\*(L"name1, [name2,...]\*(R"\fR.
|
|
|
310 .Sp
|
|
|
311 Default value: \fIMolecularWeight, HeavyAtoms, MolecularVolume, RotatableBonds, HydrogenBondDonors,
|
|
|
312 HydrogenBondAcceptors, SLogP, \s-1TPSA\s0\fR. These properties are calculated by default.
|
|
|
313 .Sp
|
|
|
314 \&\fIRuleOf5\fR [ Ref 91 ] includes these properties: \fIMolecularWeight, HydrogenBondDonors, HydrogenBondAcceptors,
|
|
|
315 SLogP\fR. \fIRuleOf5\fR states: MolecularWeight <= 500, HydrogenBondDonors <= 5, HydrogenBondAcceptors <= 10, and
|
|
|
316 logP <= 5.
|
|
|
317 .Sp
|
|
|
318 \&\fIRuleOf3\fR [ Ref 92 ] includes these properties: \fIMolecularWeight, RotatableBonds, HydrogenBondDonors,
|
|
|
319 HydrogenBondAcceptors, SLogP, \s-1TPSA\s0\fR. \fIRuleOf3\fR states: MolecularWeight <= 300, RotatableBonds <= 3,
|
|
|
320 HydrogenBondDonors <= 3, HydrogenBondAcceptors <= 3, logP <= 3, and \s-1TPSA\s0 <= 60.
|
|
|
321 .Sp
|
|
|
322 \&\fIAll\fR calculates all supported physicochemical properties: \fIMolecularWeight, ExactMass,
|
|
|
323 HeavyAtoms, Rings, AromaticRings, MolecularVolume, RotatableBonds, HydrogenBondDonors,
|
|
|
324 HydrogenBondAcceptors, SLogP, \s-1SMR\s0, \s-1TPSA\s0, Fsp3Carbons, Sp3Carbons, MolecularComplexity\fR.
|
|
|
325 .IP "\fB\-\-MolecularComplexity\fR \fIName,Value, [Name,Value,...]\fR" 4
|
|
|
326 .IX Item "--MolecularComplexity Name,Value, [Name,Value,...]"
|
|
|
327 Parameters to control calculation of molecular complexity: it's a comma delimited list of parameter
|
|
|
328 name and value pairs.
|
|
|
329 .Sp
|
|
|
330 Possible parameter names: \fIMolecularComplexityType, AtomIdentifierType,
|
|
|
331 AtomicInvariantsToUse, FunctionalClassesToUse, MACCSKeysSize, NeighborhoodRadius,
|
|
|
332 MinPathLength, MaxPathLength, UseBondSymbols, MinDistance, MaxDistance,
|
|
|
333 UseTriangleInequality, DistanceBinSize, NormalizationMethodology\fR.
|
|
|
334 .Sp
|
|
|
335 The valid paramater valuse for each parameter name are described in the following sections.
|
|
|
336 .Sp
|
|
|
337 The current release of MayaChemTools supports calculation of molecular complexity using
|
|
|
338 \&\fIMolecularComplexityType\fR parameter corresponding to the number of bits-set or unique
|
|
|
339 keys [ Ref 117\-119 ] in molecular fingerprints. The valid values for \fIMolecularComplexityType\fR
|
|
|
340 are:
|
|
|
341 .Sp
|
|
|
342 .Vb 9
|
|
|
343 \& AtomTypesFingerprints
|
|
|
344 \& ExtendedConnectivityFingerprints
|
|
|
345 \& MACCSKeys
|
|
|
346 \& PathLengthFingerprints
|
|
|
347 \& TopologicalAtomPairsFingerprints
|
|
|
348 \& TopologicalAtomTripletsFingerprints
|
|
|
349 \& TopologicalAtomTorsionsFingerprints
|
|
|
350 \& TopologicalPharmacophoreAtomPairsFingerprints
|
|
|
351 \& TopologicalPharmacophoreAtomTripletsFingerprints
|
|
|
352 .Ve
|
|
|
353 .Sp
|
|
|
354 Default value for \fIMolecularComplexityType\fR: \fIMACCSKeys\fR.
|
|
|
355 .Sp
|
|
|
356 \&\fIAtomIdentifierType\fR parameter name correspods to atom types used during generation of
|
|
|
357 fingerprints. The valid values for \fIAtomIdentifierType\fR are: \fIAtomicInvariantsAtomTypes,
|
|
|
358 DREIDINGAtomTypes, EStateAtomTypes, FunctionalClassAtomTypes, MMFF94AtomTypes,
|
|
|
359 SLogPAtomTypes, SYBYLAtomTypes, TPSAAtomTypes, UFFAtomTypes\fR. \fIAtomicInvariantsAtomTypes\fR
|
|
|
360 is not supported for during the following values of \fIMolecularComplexityType\fR: \fIMACCSKeys,
|
|
|
361 TopologicalPharmacophoreAtomPairsFingerprints, TopologicalPharmacophoreAtomTripletsFingerprints\fR.
|
|
|
362 \&\fIFunctionalClassAtomTypes\fR is the only valid value for \fIAtomIdentifierType\fR for topological
|
|
|
363 pharmacophore fingerprints.
|
|
|
364 .Sp
|
|
|
365 Default value for \fIAtomIdentifierType\fR: \fIAtomicInvariantsAtomTypes\fR
|
|
|
366 for all except topological pharmacophore fingerprints where it is \fIFunctionalClassAtomTypes\fR.
|
|
|
367 .Sp
|
|
|
368 \&\fIAtomicInvariantsToUse\fR parameter name and values are used during \fIAtomicInvariantsAtomTypes\fR
|
|
|
369 value of parameter \fIAtomIdentifierType\fR. It's a list of space separated valid atomic invariant atom types.
|
|
|
370 .Sp
|
|
|
371 Possible values for atomic invariants are: \fI\s-1AS\s0, X, \s-1BO\s0, \s-1LBO\s0, \s-1SB\s0, \s-1DB\s0, \s-1TB\s0, H, Ar, \s-1RA\s0, \s-1FC\s0, \s-1MN\s0, \s-1SM\s0\fR.
|
|
|
372 Default value for \fIAtomicInvariantsToUse\fR parameter are set differently for different fingerprints
|
|
|
373 using \fIMolecularComplexityType\fR parameter as shown below:
|
|
|
374 .Sp
|
|
|
375 .Vb 1
|
|
|
376 \& MolecularComplexityType AtomicInvariantsToUse
|
|
|
377 \&
|
|
|
378 \& AtomTypesFingerprints AS X BO H FC
|
|
|
379 \& TopologicalAtomPairsFingerprints AS X BO H FC
|
|
|
380 \& TopologicalAtomTripletsFingerprints AS X BO H FC
|
|
|
381 \& TopologicalAtomTorsionsFingerprints AS X BO H FC
|
|
|
382 \&
|
|
|
383 \& ExtendedConnectivityFingerprints AS X BO H FC MN
|
|
|
384 \& PathLengthFingerprints AS
|
|
|
385 .Ve
|
|
|
386 .Sp
|
|
|
387 The atomic invariants abbreviations correspond to:
|
|
|
388 .Sp
|
|
|
389 .Vb 1
|
|
|
390 \& AS = Atom symbol corresponding to element symbol
|
|
|
391 \&
|
|
|
392 \& X<n> = Number of non\-hydrogen atom neighbors or heavy atoms
|
|
|
393 \& BO<n> = Sum of bond orders to non\-hydrogen atom neighbors or heavy atoms
|
|
|
394 \& LBO<n> = Largest bond order of non\-hydrogen atom neighbors or heavy atoms
|
|
|
395 \& SB<n> = Number of single bonds to non\-hydrogen atom neighbors or heavy atoms
|
|
|
396 \& DB<n> = Number of double bonds to non\-hydrogen atom neighbors or heavy atoms
|
|
|
397 \& TB<n> = Number of triple bonds to non\-hydrogen atom neighbors or heavy atoms
|
|
|
398 \& H<n> = Number of implicit and explicit hydrogens for atom
|
|
|
399 \& Ar = Aromatic annotation indicating whether atom is aromatic
|
|
|
400 \& RA = Ring atom annotation indicating whether atom is a ring
|
|
|
401 \& FC<+n/\-n> = Formal charge assigned to atom
|
|
|
402 \& MN<n> = Mass number indicating isotope other than most abundant isotope
|
|
|
403 \& SM<n> = Spin multiplicity of atom. Possible values: 1 (singlet), 2 (doublet) or
|
|
|
404 \& 3 (triplet)
|
|
|
405 .Ve
|
|
|
406 .Sp
|
|
|
407 Atom type generated by AtomTypes::AtomicInvariantsAtomTypes class corresponds to:
|
|
|
408 .Sp
|
|
|
409 .Vb 1
|
|
|
410 \& AS.X<n>.BO<n>.LBO<n>.<SB><n>.<DB><n>.<TB><n>.H<n>.Ar.RA.FC<+n/\-n>.MN<n>.SM<n>
|
|
|
411 .Ve
|
|
|
412 .Sp
|
|
|
413 Except for \s-1AS\s0 which is a required atomic invariant in atom types, all other atomic invariants are
|
|
|
414 optional. Atom type specification doesn't include atomic invariants with zero or undefined values.
|
|
|
415 .Sp
|
|
|
416 In addition to usage of abbreviations for specifying atomic invariants, the following descriptive words
|
|
|
417 are also allowed:
|
|
|
418 .Sp
|
|
|
419 .Vb 12
|
|
|
420 \& X : NumOfNonHydrogenAtomNeighbors or NumOfHeavyAtomNeighbors
|
|
|
421 \& BO : SumOfBondOrdersToNonHydrogenAtoms or SumOfBondOrdersToHeavyAtoms
|
|
|
422 \& LBO : LargestBondOrderToNonHydrogenAtoms or LargestBondOrderToHeavyAtoms
|
|
|
423 \& SB : NumOfSingleBondsToNonHydrogenAtoms or NumOfSingleBondsToHeavyAtoms
|
|
|
424 \& DB : NumOfDoubleBondsToNonHydrogenAtoms or NumOfDoubleBondsToHeavyAtoms
|
|
|
425 \& TB : NumOfTripleBondsToNonHydrogenAtoms or NumOfTripleBondsToHeavyAtoms
|
|
|
426 \& H : NumOfImplicitAndExplicitHydrogens
|
|
|
427 \& Ar : Aromatic
|
|
|
428 \& RA : RingAtom
|
|
|
429 \& FC : FormalCharge
|
|
|
430 \& MN : MassNumber
|
|
|
431 \& SM : SpinMultiplicity
|
|
|
432 .Ve
|
|
|
433 .Sp
|
|
|
434 \&\fIAtomTypes::AtomicInvariantsAtomTypes\fR module is used to assign atomic invariant
|
|
|
435 atom types.
|
|
|
436 .Sp
|
|
|
437 \&\fIFunctionalClassesToUse\fR parameter name and values are used during \fIFunctionalClassAtomTypes\fR
|
|
|
438 value of parameter \fIAtomIdentifierType\fR. It's a list of space separated valid atomic invariant atom types.
|
|
|
439 .Sp
|
|
|
440 Possible values for atom functional classes are: \fIAr, \s-1CA\s0, H, \s-1HBA\s0, \s-1HBD\s0, Hal, \s-1NI\s0, \s-1PI\s0, \s-1RA\s0\fR.
|
|
|
441 .Sp
|
|
|
442 Default value for \fIFunctionalClassesToUse\fR parameter is set to:
|
|
|
443 .Sp
|
|
|
444 .Vb 1
|
|
|
445 \& HBD HBA PI NI Ar Hal
|
|
|
446 .Ve
|
|
|
447 .Sp
|
|
|
448 for all fingerprints except for the following two \fIMolecularComplexityType\fR fingerints:
|
|
|
449 .Sp
|
|
|
450 .Vb 1
|
|
|
451 \& MolecularComplexityType FunctionalClassesToUse
|
|
|
452 \&
|
|
|
453 \& TopologicalPharmacophoreAtomPairsFingerprints HBD HBA P, NI H
|
|
|
454 \& TopologicalPharmacophoreAtomTripletsFingerprints HBD HBA PI NI H Ar
|
|
|
455 .Ve
|
|
|
456 .Sp
|
|
|
457 The functional class abbreviations correspond to:
|
|
|
458 .Sp
|
|
|
459 .Vb 9
|
|
|
460 \& HBD: HydrogenBondDonor
|
|
|
461 \& HBA: HydrogenBondAcceptor
|
|
|
462 \& PI : PositivelyIonizable
|
|
|
463 \& NI : NegativelyIonizable
|
|
|
464 \& Ar : Aromatic
|
|
|
465 \& Hal : Halogen
|
|
|
466 \& H : Hydrophobic
|
|
|
467 \& RA : RingAtom
|
|
|
468 \& CA : ChainAtom
|
|
|
469 \&
|
|
|
470 \& Functional class atom type specification for an atom corresponds to:
|
|
|
471 \&
|
|
|
472 \& Ar.CA.H.HBA.HBD.Hal.NI.PI.RA
|
|
|
473 .Ve
|
|
|
474 .Sp
|
|
|
475 \&\fIAtomTypes::FunctionalClassAtomTypes\fR module is used to assign functional class atom
|
|
|
476 types. It uses following definitions [ Ref 60\-61, Ref 65\-66 ]:
|
|
|
477 .Sp
|
|
|
478 .Vb 4
|
|
|
479 \& HydrogenBondDonor: NH, NH2, OH
|
|
|
480 \& HydrogenBondAcceptor: N[!H], O
|
|
|
481 \& PositivelyIonizable: +, NH2
|
|
|
482 \& NegativelyIonizable: \-, C(=O)OH, S(=O)OH, P(=O)OH
|
|
|
483 .Ve
|
|
|
484 .Sp
|
|
|
485 \&\fIMACCSKeysSize\fR parameter name is only used during \fIMACCSKeys\fR value of
|
|
|
486 \&\fIMolecularComplexityType\fR and corresponds to the size of \s-1MACCS\s0 key set. Possible
|
|
|
487 values: \fI166 or 322\fR. Default value: \fI166\fR.
|
|
|
488 .Sp
|
|
|
489 \&\fINeighborhoodRadius\fR parameter name is only used during \fIExtendedConnectivityFingerprints\fR
|
|
|
490 value of \fIMolecularComplexityType\fR and corresponds to atomic neighborhoods radius for
|
|
|
491 generating extended connectivity fingerprints. Possible values: positive integer. Default value:
|
|
|
492 \&\fI2\fR.
|
|
|
493 .Sp
|
|
|
494 \&\fIMinPathLength\fR and \fIMaxPathLength\fR parameters are only used during \fIPathLengthFingerprints\fR
|
|
|
495 value of \fIMolecularComplexityType\fR and correspond to minimum and maximum path lengths to use
|
|
|
496 for generating path length fingerprints. Possible values: positive integers. Default value: \fIMinPathLength \- 1\fR;
|
|
|
497 \&\fIMaxPathLength \- 8\fR.
|
|
|
498 .Sp
|
|
|
499 \&\fIUseBondSymbols\fR parameter is only used during \fIPathLengthFingerprints\fR value of
|
|
|
500 \&\fIMolecularComplexityType\fR and indicates whether bond symbols are included in atom path
|
|
|
501 strings used to generate path length fingerprints. Possible value: \fIYes or No\fR. Default value:
|
|
|
502 \&\fIYes\fR.
|
|
|
503 .Sp
|
|
|
504 \&\fIMinDistance\fR and \fIMaxDistance\fR parameters are only used during \fITopologicalAtomPairsFingerprints\fR
|
|
|
505 and \fITopologicalAtomTripletsFingerprints\fR values of \fIMolecularComplexityType\fR and correspond to
|
|
|
506 minimum and maximum bond distance between atom pairs during topological pharmacophore fingerprints.
|
|
|
507 Possible values: positive integers. Default value: \fIMinDistance \- 1\fR; \fIMaxDistance \- 10\fR.
|
|
|
508 .Sp
|
|
|
509 \&\fIUseTriangleInequality\fR parameter is used during these values for \fIMolecularComplexityType\fR:
|
|
|
510 \&\fITopologicalAtomTripletsFingerprints\fR and \fITopologicalPharmacophoreAtomTripletsFingerprints\fR.
|
|
|
511 Possible values: \fIYes or No\fR. It determines wheter to apply triangle inequality to distance triplets.
|
|
|
512 Default value: \fITopologicalAtomTripletsFingerprints \- No\fR;
|
|
|
513 \&\fITopologicalPharmacophoreAtomTripletsFingerprints \- Yes\fR.
|
|
|
514 .Sp
|
|
|
515 \&\fIDistanceBinSize\fR parameter is used during \fITopologicalPharmacophoreAtomTripletsFingerprints\fR
|
|
|
516 value of \fIMolecularComplexityType\fR and correspons to distance bin size used for binning
|
|
|
517 distances during generation of topological pharmacophore atom triplets fingerprints. Possible
|
|
|
518 value: positive integer. Default value: \fI2\fR.
|
|
|
519 .Sp
|
|
|
520 \&\fINormalizationMethodology\fR is only used for these values for \fIMolecularComplexityType\fR:
|
|
|
521 \&\fIExtendedConnectivityFingerprints\fR, \fITopologicalPharmacophoreAtomPairsFingerprints\fR
|
|
|
522 and \fITopologicalPharmacophoreAtomTripletsFingerprints\fR. It corresponds to normalization
|
|
|
523 methodology to use for scaling the number of bits-set or unique keys during generation of
|
|
|
524 fingerprints. Possible values during \fIExtendedConnectivityFingerprints\fR: \fINone or
|
|
|
525 ByHeavyAtomsCount\fR; Default value: \fINone\fR. Possible values during topological
|
|
|
526 pharmacophore atom pairs and tripletes fingerprints: \fINone or ByPossibleKeysCount\fR;
|
|
|
527 Default value: \fINone\fR. \fIByPossibleKeysCount\fR corresponds to total number of
|
|
|
528 possible topological pharmacophore atom pairs or triplets in a molecule.
|
|
|
529 .Sp
|
|
|
530 Examples of \fIMolecularComplexity\fR name and value parameters:
|
|
|
531 .Sp
|
|
|
532 .Vb 2
|
|
|
533 \& MolecularComplexityType,AtomTypesFingerprints,AtomIdentifierType,
|
|
|
534 \& AtomicInvariantsAtomTypes,AtomicInvariantsToUse,AS X BO H FC
|
|
|
535 \&
|
|
|
536 \& MolecularComplexityType,ExtendedConnectivityFingerprints,
|
|
|
537 \& AtomIdentifierType,AtomicInvariantsAtomTypes,
|
|
|
538 \& AtomicInvariantsToUse,AS X BO H FC MN,NeighborhoodRadius,2,
|
|
|
539 \& NormalizationMethodology,None
|
|
|
540 \&
|
|
|
541 \& MolecularComplexityType,MACCSKeys,MACCSKeysSize,166
|
|
|
542 \&
|
|
|
543 \& MolecularComplexityType,PathLengthFingerprints,AtomIdentifierType,
|
|
|
544 \& AtomicInvariantsAtomTypes,AtomicInvariantsToUse,AS,MinPathLength,
|
|
|
545 \& 1,MaxPathLength,8,UseBondSymbols,Yes
|
|
|
546 \&
|
|
|
547 \& MolecularComplexityType,TopologicalAtomPairsFingerprints,
|
|
|
548 \& AtomIdentifierType,AtomicInvariantsAtomTypes,AtomicInvariantsToUse,
|
|
|
549 \& AS X BO H FC,MinDistance,1,MaxDistance,10
|
|
|
550 \&
|
|
|
551 \& MolecularComplexityType,TopologicalAtomTripletsFingerprints,
|
|
|
552 \& AtomIdentifierType,AtomicInvariantsAtomTypes,AtomicInvariantsToUse,
|
|
|
553 \& AS X BO H FC,MinDistance,1,MaxDistance,10,UseTriangleInequality,No
|
|
|
554 \&
|
|
|
555 \& MolecularComplexityType,TopologicalAtomTorsionsFingerprints,
|
|
|
556 \& AtomIdentifierType,AtomicInvariantsAtomTypes,AtomicInvariantsToUse,
|
|
|
557 \& AS X BO H FC
|
|
|
558 \&
|
|
|
559 \& MolecularComplexityType,TopologicalPharmacophoreAtomPairsFingerprints,
|
|
|
560 \& AtomIdentifierType,FunctionalClassAtomTypes,FunctionalClassesToUse,
|
|
|
561 \& HBD HBA PI NI H,MinDistance,1,MaxDistance,10,NormalizationMethodology,
|
|
|
562 \& None
|
|
|
563 \&
|
|
|
564 \& MolecularComplexityType,TopologicalPharmacophoreAtomTripletsFingerprints,
|
|
|
565 \& AtomIdentifierType,FunctionalClassAtomTypes,FunctionalClassesToUse,
|
|
|
566 \& HBD HBA PI NI H Ar,MinDistance,1,MaxDistance,10,NormalizationMethodology,
|
|
|
567 \& None,UseTriangleInequality,Yes,NormalizationMethodology,None,
|
|
|
568 \& DistanceBinSize,2
|
|
|
569 .Ve
|
|
|
570 .IP "\fB\-\-OutDelim\fR \fIcomma | tab | semicolon\fR" 4
|
|
|
571 .IX Item "--OutDelim comma | tab | semicolon"
|
|
|
572 Delimiter for output \s-1CSV/TSV\s0 text file(s). Possible values: \fIcomma, tab, or semicolon\fR
|
|
|
573 Default value: \fIcomma\fR.
|
|
|
574 .IP "\fB\-\-output\fR \fI\s-1SD\s0 | text | both\fR" 4
|
|
|
575 .IX Item "--output SD | text | both"
|
|
|
576 Type of output files to generate. Possible values: \fI\s-1SD\s0, text, or both\fR. Default value: \fItext\fR.
|
|
|
577 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
|
578 .IX Item "-o, --overwrite"
|
|
|
579 Overwrite existing files.
|
|
|
580 .IP "\fB\-\-Precision\fR \fIName,Number,[Name,Number,..]\fR" 4
|
|
|
581 .IX Item "--Precision Name,Number,[Name,Number,..]"
|
|
|
582 Precision of calculated property values in the output file: it's a comma delimited list of
|
|
|
583 property name and precision value pairs. Possible property names: \fIMolecularWeight,
|
|
|
584 ExactMass\fR. Possible values: positive intergers. Default value: \fIMolecularWeight,2,
|
|
|
585 ExactMass,4\fR.
|
|
|
586 .Sp
|
|
|
587 Examples:
|
|
|
588 .Sp
|
|
|
589 .Vb 2
|
|
|
590 \& ExactMass,3
|
|
|
591 \& MolecularWeight,1,ExactMass,2
|
|
|
592 .Ve
|
|
|
593 .IP "\fB\-q, \-\-quote\fR \fIYes | No\fR" 4
|
|
|
594 .IX Item "-q, --quote Yes | No"
|
|
|
595 Put quote around column values in output \s-1CSV/TSV\s0 text file(s). Possible values:
|
|
|
596 \&\fIYes or No\fR. Default value: \fIYes\fR.
|
|
|
597 .IP "\fB\-r, \-\-root\fR \fIRootName\fR" 4
|
|
|
598 .IX Item "-r, --root RootName"
|
|
|
599 New file name is generated using the root: <Root>.<Ext>. Default for new file names:
|
|
|
600 <SDFileName><PhysicochemicalProperties>.<Ext>. The file type determines <Ext> value.
|
|
|
601 The sdf, csv, and tsv <Ext> values are used for \s-1SD\s0, comma/semicolon, and tab
|
|
|
602 delimited text files, respectively.This option is ignored for multiple input files.
|
|
|
603 .IP "\fB\-\-RotatableBonds\fR \fIName,Value, [Name,Value,...]\fR" 4
|
|
|
604 .IX Item "--RotatableBonds Name,Value, [Name,Value,...]"
|
|
|
605 Parameters to control calculation of rotatable bonds [ Ref 92 ]: it's a comma delimited list of parameter
|
|
|
606 name and value pairs. Possible parameter names: \fIIgnoreTerminalBonds, IgnoreBondsToTripleBonds,
|
|
|
607 IgnoreAmideBonds, IgnoreThioamideBonds, IgnoreSulfonamideBonds\fR. Possible parameter values:
|
|
|
608 \&\fIYes or No\fR. By default, value of all parameters is set to \fIYes\fR.
|
|
|
609 .IP "\fB\-\-RuleOf3Violations\fR \fIYes | No\fR" 4
|
|
|
610 .IX Item "--RuleOf3Violations Yes | No"
|
|
|
611 Specify whether to calculate \fBRuleOf3Violations\fR for SDFile(s). Possible values: \fIYes or No\fR.
|
|
|
612 Default value: \fINo\fR.
|
|
|
613 .Sp
|
|
|
614 For \fIYes\fR value of \fBRuleOf3Violations\fR, in addition to calculating total number of \fBRuleOf3\fR violations,
|
|
|
615 individual violations for compounds are also written to output files.
|
|
|
616 .Sp
|
|
|
617 \&\fBRuleOf3\fR [ Ref 92 ] states: MolecularWeight <= 300, RotatableBonds <= 3, HydrogenBondDonors <= 3,
|
|
|
618 HydrogenBondAcceptors <= 3, logP <= 3, and \s-1TPSA\s0 <= 60.
|
|
|
619 .IP "\fB\-\-RuleOf5Violations\fR \fIYes | No\fR" 4
|
|
|
620 .IX Item "--RuleOf5Violations Yes | No"
|
|
|
621 Specify whether to calculate \fBRuleOf5Violations\fR for SDFile(s). Possible values: \fIYes or No\fR.
|
|
|
622 Default value: \fINo\fR.
|
|
|
623 .Sp
|
|
|
624 For \fIYes\fR value of \fBRuleOf5Violations\fR, in addition to calculating total number of \fBRuleOf5\fR violations,
|
|
|
625 individual violations for compounds are also written to output files.
|
|
|
626 .Sp
|
|
|
627 \&\fBRuleOf5\fR [ Ref 91 ] states: MolecularWeight <= 500, HydrogenBondDonors <= 5, HydrogenBondAcceptors <= 10,
|
|
|
628 and logP <= 5.
|
|
|
629 .IP "\fB\-\-TPSA\fR \fIName,Value, [Name,Value,...]\fR" 4
|
|
|
630 .IX Item "--TPSA Name,Value, [Name,Value,...]"
|
|
|
631 Parameters to control calculation of \s-1TPSA:\s0 it's a comma delimited list of parameter name and value
|
|
|
632 pairs. Possible parameter names: \fIIgnorePhosphorus, IgnoreSulfur\fR. Possible parameter values:
|
|
|
633 \&\fIYes or No\fR. By default, value of all parameters is set to \fIYes\fR.
|
|
|
634 .Sp
|
|
|
635 By default, \s-1TPSA\s0 atom contributions from Phosphorus and Sulfur atoms are not included during
|
|
|
636 \&\s-1TPSA\s0 calculations. [ Ref 91 ]
|
|
|
637 .IP "\fB\-w, \-\-WorkingDir\fR \fIDirName\fR" 4
|
|
|
638 .IX Item "-w, --WorkingDir DirName"
|
|
|
639 Location of working directory. Default value: current directory.
|
|
|
640 .SH "EXAMPLES"
|
|
|
641 .IX Header "EXAMPLES"
|
|
|
642 To calculate default set of physicochemical properties \- MolecularWeight, HeavyAtoms,
|
|
|
643 MolecularVolume, RotatableBonds, HydrogenBondDonor, HydrogenBondAcceptors, SLogP,
|
|
|
644 \&\s-1TPSA\s0 \- and generate a SamplePhysicochemicalProperties.csv file containing sequential
|
|
|
645 compound IDs along with properties data, type:
|
|
|
646 .PP
|
|
|
647 .Vb 1
|
|
|
648 \& % CalculatePhysicochemicalProperties.pl \-o Sample.sdf
|
|
|
649 .Ve
|
|
|
650 .PP
|
|
|
651 To calculate all available physicochemical properties and generate both SampleAllProperties.csv
|
|
|
652 and SampleAllProperties.sdf files containing sequential compound IDs in \s-1CSV\s0 file along with
|
|
|
653 properties data, type:
|
|
|
654 .PP
|
|
|
655 .Vb 2
|
|
|
656 \& % CalculatePhysicochemicalProperties.pl \-m All \-\-output both
|
|
|
657 \& \-r SampleAllProperties \-o Sample.sdf
|
|
|
658 .Ve
|
|
|
659 .PP
|
|
|
660 To calculate RuleOf5 physicochemical properties and generate a SampleRuleOf5Properties.csv file
|
|
|
661 containing sequential compound IDs along with properties data, type:
|
|
|
662 .PP
|
|
|
663 .Vb 2
|
|
|
664 \& % CalculatePhysicochemicalProperties.pl \-m RuleOf5
|
|
|
665 \& \-r SampleRuleOf5Properties \-o Sample.sdf
|
|
|
666 .Ve
|
|
|
667 .PP
|
|
|
668 To calculate RuleOf5 physicochemical properties along with counting RuleOf5 violations and generate
|
|
|
669 a SampleRuleOf5Properties.csv file containing sequential compound IDs along with properties data, type:
|
|
|
670 .PP
|
|
|
671 .Vb 2
|
|
|
672 \& % CalculatePhysicochemicalProperties.pl \-m RuleOf5 \-\-RuleOf5Violations Yes
|
|
|
673 \& \-r SampleRuleOf5Properties \-o Sample.sdf
|
|
|
674 .Ve
|
|
|
675 .PP
|
|
|
676 To calculate RuleOf3 physicochemical properties and generate a SampleRuleOf3Properties.csv file
|
|
|
677 containing sequential compound IDs along with properties data, type:
|
|
|
678 .PP
|
|
|
679 .Vb 2
|
|
|
680 \& % CalculatePhysicochemicalProperties.pl \-m RuleOf3
|
|
|
681 \& \-r SampleRuleOf3Properties \-o Sample.sdf
|
|
|
682 .Ve
|
|
|
683 .PP
|
|
|
684 To calculate RuleOf3 physicochemical properties along with counting RuleOf3 violations and generate
|
|
|
685 a SampleRuleOf3Properties.csv file containing sequential compound IDs along with properties data, type:
|
|
|
686 .PP
|
|
|
687 .Vb 2
|
|
|
688 \& % CalculatePhysicochemicalProperties.pl \-m RuleOf3 \-\-RuleOf3Violations Yes
|
|
|
689 \& \-r SampleRuleOf3Properties \-o Sample.sdf
|
|
|
690 .Ve
|
|
|
691 .PP
|
|
|
692 To calculate a specific set of physicochemical properties and generate a SampleProperties.csv file
|
|
|
693 containing sequential compound IDs along with properties data, type:
|
|
|
694 .PP
|
|
|
695 .Vb 2
|
|
|
696 \& % CalculatePhysicochemicalProperties.pl \-m "Rings,AromaticRings"
|
|
|
697 \& \-r SampleProperties \-o Sample.sdf
|
|
|
698 .Ve
|
|
|
699 .PP
|
|
|
700 To calculate HydrogenBondDonors and HydrogenBondAcceptors using HydrogenBondsType1 definition
|
|
|
701 and generate a SampleProperties.csv file containing sequential compound IDs along with properties
|
|
|
702 data, type:
|
|
|
703 .PP
|
|
|
704 .Vb 2
|
|
|
705 \& % CalculatePhysicochemicalProperties.pl \-m "HydrogenBondDonors,HydrogenBondAcceptors"
|
|
|
706 \& \-\-HydrogenBonds HBondsType1 \-r SampleProperties \-o Sample.sdf
|
|
|
707 .Ve
|
|
|
708 .PP
|
|
|
709 To calculate \s-1TPSA\s0 using sulfur and phosphorus atoms along with nitrogen and oxygen atoms and
|
|
|
710 generate a SampleProperties.csv file containing sequential compound IDs along with properties
|
|
|
711 data, type:
|
|
|
712 .PP
|
|
|
713 .Vb 2
|
|
|
714 \& % CalculatePhysicochemicalProperties.pl \-m "TPSA" \-\-TPSA "IgnorePhosphorus,No,
|
|
|
715 \& IgnoreSulfur,No" \-r SampleProperties \-o Sample.sdf
|
|
|
716 .Ve
|
|
|
717 .PP
|
|
|
718 To calculate MolecularComplexity using extendend connectivity fingerprints corresponding
|
|
|
719 to atom neighborhood radius of 2 with atomic invariant atom types without any scaling and
|
|
|
720 generate a SampleProperties.csv file containing sequential compound IDs along with properties
|
|
|
721 data, type:
|
|
|
722 .PP
|
|
|
723 .Vb 5
|
|
|
724 \& % CalculatePhysicochemicalProperties.pl \-m MolecularComplexity \-\-MolecularComplexity
|
|
|
725 \& "MolecularComplexityType,ExtendedConnectivityFingerprints,NeighborhoodRadius,2,
|
|
|
726 \& AtomIdentifierType, AtomicInvariantsAtomTypes,
|
|
|
727 \& AtomicInvariantsToUse,AS X BO H FC MN,NormalizationMethodology,None"
|
|
|
728 \& \-r SampleProperties \-o Sample.sdf
|
|
|
729 .Ve
|
|
|
730 .PP
|
|
|
731 To calculate RuleOf5 physicochemical properties along with counting RuleOf5 violations and generate
|
|
|
732 a SampleRuleOf5Properties.csv file containing compound IDs from molecule name line along with
|
|
|
733 properties data, type:
|
|
|
734 .PP
|
|
|
735 .Vb 3
|
|
|
736 \& % CalculatePhysicochemicalProperties.pl \-m RuleOf5 \-\-RuleOf5Violations Yes
|
|
|
737 \& \-\-DataFieldsMode CompoundID \-\-CompoundIDMode MolName
|
|
|
738 \& \-r SampleRuleOf5Properties \-o Sample.sdf
|
|
|
739 .Ve
|
|
|
740 .PP
|
|
|
741 To calculate all available physicochemical properties and generate a SampleAllProperties.csv
|
|
|
742 file containing compound \s-1ID\s0 using specified data field along with along with properties data,
|
|
|
743 type:
|
|
|
744 .PP
|
|
|
745 .Vb 3
|
|
|
746 \& % CalculatePhysicochemicalProperties.pl \-m All
|
|
|
747 \& \-\-DataFieldsMode CompoundID \-\-CompoundIDMode DataField \-\-CompoundID Mol_ID
|
|
|
748 \& \-r SampleAllProperties \-o Sample.sdf
|
|
|
749 .Ve
|
|
|
750 .PP
|
|
|
751 To calculate all available physicochemical properties and generate a SampleAllProperties.csv
|
|
|
752 file containing compound \s-1ID\s0 using combination of molecule name line and an explicit compound
|
|
|
753 prefix along with properties data, type:
|
|
|
754 .PP
|
|
|
755 .Vb 4
|
|
|
756 \& % CalculatePhysicochemicalProperties.pl \-m All
|
|
|
757 \& \-\-DataFieldsMode CompoundID \-\-CompoundIDMode MolnameOrLabelPrefix
|
|
|
758 \& \-\-CompoundID Cmpd \-\-CompoundIDLabel MolID \-r SampleAllProperties
|
|
|
759 \& \-o Sample.sdf
|
|
|
760 .Ve
|
|
|
761 .PP
|
|
|
762 To calculate all available physicochemical properties and generate a SampleAllProperties.csv
|
|
|
763 file containing specific data fields columns along with with properties data, type:
|
|
|
764 .PP
|
|
|
765 .Vb 3
|
|
|
766 \& % CalculatePhysicochemicalProperties.pl \-m All
|
|
|
767 \& \-\-DataFieldsMode Specify \-\-DataFields Mol_ID \-r SampleAllProperties
|
|
|
768 \& \-o Sample.sdf
|
|
|
769 .Ve
|
|
|
770 .PP
|
|
|
771 To calculate all available physicochemical properties and generate a SampleAllProperties.csv
|
|
|
772 file containing common data fields columns along with with properties data, type:
|
|
|
773 .PP
|
|
|
774 .Vb 2
|
|
|
775 \& % CalculatePhysicochemicalProperties.pl \-m All
|
|
|
776 \& \-\-DataFieldsMode Common \-r SampleAllProperties \-o Sample.sdf
|
|
|
777 .Ve
|
|
|
778 .PP
|
|
|
779 To calculate all available physicochemical properties and generate both SampleAllProperties.csv
|
|
|
780 and \s-1CSV\s0 files containing all data fields columns in \s-1CSV\s0 files along with with properties data, type:
|
|
|
781 .PP
|
|
|
782 .Vb 3
|
|
|
783 \& % CalculatePhysicochemicalProperties.pl \-m All
|
|
|
784 \& \-\-DataFieldsMode All \-\-output both \-r SampleAllProperties
|
|
|
785 \& \-o Sample.sdf
|
|
|
786 .Ve
|
|
|
787 .SH "AUTHOR"
|
|
|
788 .IX Header "AUTHOR"
|
|
|
789 Manish Sud <msud@san.rr.com>
|
|
|
790 .SH "SEE ALSO"
|
|
|
791 .IX Header "SEE ALSO"
|
|
|
792 ExtractFromSDtFiles.pl, ExtractFromTextFiles.pl, InfoSDFiles.pl, InfoTextFiles.pl
|
|
|
793 .SH "COPYRIGHT"
|
|
|
794 .IX Header "COPYRIGHT"
|
|
|
795 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
796 .PP
|
|
|
797 This file is part of MayaChemTools.
|
|
|
798 .PP
|
|
|
799 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
800 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
801 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
802 any later version.
|
