diff docs/scripts/man1/ExtractFromSDFiles.1 @ 0:4816e4a8ae95 draft default tip

Uploaded
author deepakjadmin
date Wed, 20 Jan 2016 09:23:18 -0500
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/docs/scripts/man1/ExtractFromSDFiles.1	Wed Jan 20 09:23:18 2016 -0500
@@ -0,0 +1,466 @@
+.\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
+.\"
+.\" Standard preamble:
+.\" ========================================================================
+.de Sp \" Vertical space (when we can't use .PP)
+.if t .sp .5v
+.if n .sp
+..
+.de Vb \" Begin verbatim text
+.ft CW
+.nf
+.ne \\$1
+..
+.de Ve \" End verbatim text
+.ft R
+.fi
+..
+.\" Set up some character translations and predefined strings.  \*(-- will
+.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
+.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
+.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
+.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
+.\" nothing in troff, for use with C<>.
+.tr \(*W-
+.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
+.ie n \{\
+.    ds -- \(*W-
+.    ds PI pi
+.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
+.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
+.    ds L" ""
+.    ds R" ""
+.    ds C` ""
+.    ds C' ""
+'br\}
+.el\{\
+.    ds -- \|\(em\|
+.    ds PI \(*p
+.    ds L" ``
+.    ds R" ''
+'br\}
+.\"
+.\" Escape single quotes in literal strings from groff's Unicode transform.
+.ie \n(.g .ds Aq \(aq
+.el       .ds Aq '
+.\"
+.\" If the F register is turned on, we'll generate index entries on stderr for
+.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
+.\" entries marked with X<> in POD.  Of course, you'll have to process the
+.\" output yourself in some meaningful fashion.
+.ie \nF \{\
+.    de IX
+.    tm Index:\\$1\t\\n%\t"\\$2"
+..
+.    nr % 0
+.    rr F
+.\}
+.el \{\
+.    de IX
+..
+.\}
+.\"
+.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
+.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
+.    \" fudge factors for nroff and troff
+.if n \{\
+.    ds #H 0
+.    ds #V .8m
+.    ds #F .3m
+.    ds #[ \f1
+.    ds #] \fP
+.\}
+.if t \{\
+.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
+.    ds #V .6m
+.    ds #F 0
+.    ds #[ \&
+.    ds #] \&
+.\}
+.    \" simple accents for nroff and troff
+.if n \{\
+.    ds ' \&
+.    ds ` \&
+.    ds ^ \&
+.    ds , \&
+.    ds ~ ~
+.    ds /
+.\}
+.if t \{\
+.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
+.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
+.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
+.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
+.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
+.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
+.\}
+.    \" troff and (daisy-wheel) nroff accents
+.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
+.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
+.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
+.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
+.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
+.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
+.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
+.ds ae a\h'-(\w'a'u*4/10)'e
+.ds Ae A\h'-(\w'A'u*4/10)'E
+.    \" corrections for vroff
+.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
+.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
+.    \" for low resolution devices (crt and lpr)
+.if \n(.H>23 .if \n(.V>19 \
+\{\
+.    ds : e
+.    ds 8 ss
+.    ds o a
+.    ds d- d\h'-1'\(ga
+.    ds D- D\h'-1'\(hy
+.    ds th \o'bp'
+.    ds Th \o'LP'
+.    ds ae ae
+.    ds Ae AE
+.\}
+.rm #[ #] #H #V #F C
+.\" ========================================================================
+.\"
+.IX Title "EXTRACTFROMSDFILES 1"
+.TH EXTRACTFROMSDFILES 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
+.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
+.\" way too many mistakes in technical documents.
+.if n .ad l
+.nh
+.SH "NAME"
+ExtractFromSDFiles.pl \- Extract specific data from SDFile(s)
+.SH "SYNOPSIS"
+.IX Header "SYNOPSIS"
+ExtractFromSDFiles.pl SDFile(s)...
+.PP
+ExtractFromSDFiles.pl [\fB\-h, \-\-help\fR]
+[\fB\-d, \-\-datafields\fR \*(L"fieldlabel,...\*(R" | \*(L"fieldlabel,value,criteria...\*(R" | \*(L"fieldlabel,value,value...\*(R"]
+[\fB\-\-datafieldsfile\fR filename] [\fB\-\-indelim\fR comma | tab | semicolon] [\fB\-m, \-\-mode\fR alldatafields |
+commondatafields | | datafieldnotbylist | datafields | datafieldsbyvalue | datafieldsbyregex | datafieldbylist |
+datafielduniquebylist | molnames | randomcmpds | recordnum | recordnums | recordrange | 2dcmpdrecords |
+3dcmpdrecords ] [\fB\-n, \-\-numofcmpds\fR number] [\fB\-\-outdelim\fR comma | tab | semicolon]
+[\fB\-\-output\fR \s-1SD\s0 | text | both] [\fB\-o, \-\-overwrite\fR] [\fB\-q, \-\-quote\fR yes | no]
+[\fB\-\-record\fR recnum | startrecnum,endrecnum] \fB\-\-RegexIgnoreCase\fR \fIyes or no\fR
+[\fB\-r, \-\-root\fR rootname] [\fB\-s, \-\-seed\fR number] [\fB\-\-StrDataString\fR yes | no]
+[\fB\-\-StrDataStringDelimiter\fR text] [\fB\-\-StrDataStringMode\fR StrOnly | StrAndDataFields]
+[\fB\-\-ValueComparisonMode\fR \fINumeric | Alphanumeric\fR]
+[\fB\-v, \-\-violations\-\fR number] [\fB\-w, \-\-workingdir\fR dirname] SDFile(s)...
+.SH "DESCRIPTION"
+.IX Header "DESCRIPTION"
+Extract specific data from \fISDFile(s)\fR and generate appropriate \s-1SD\s0 or \s-1CSV/TSV\s0 text
+file(s). The structure data from SDFile(s) is not transferred to \s-1CSV/TSV\s0 text file(s).
+Multiple SDFile names are separated by spaces. The valid file extensions are \fI.sdf\fR
+and \fI.sd\fR. All other file names are ignored. All the \s-1SD\s0 files in a current directory
+can be specified either by \fI*.sdf\fR or the current directory name.
+.SH "OPTIONS"
+.IX Header "OPTIONS"
+.IP "\fB\-h, \-\-help\fR" 4
+.IX Item "-h, --help"
+Print this help message.
+.ie n .IP "\fB\-d, \-\-datafields\fR \fI""fieldlabel,..."" | ""fieldlabel,value,criteria..."" | ""fieldlabel,value,value,...""\fR" 4
+.el .IP "\fB\-d, \-\-datafields\fR \fI``fieldlabel,...'' | ``fieldlabel,value,criteria...'' | ``fieldlabel,value,value,...''\fR" 4
+.IX Item "-d, --datafields fieldlabel,... | fieldlabel,value,criteria... | fieldlabel,value,value,..."
+This value is mode specific. In general, it's a list of comma separated data field labels
+and associated mode specific values.
+.Sp
+For \fIdatafields\fR mode, input value format is: \fIfieldlabel,...\fR. Examples:
+.Sp
+.Vb 2
+\&    Extreg
+\&    Extreg,CompoundName,ID
+.Ve
+.Sp
+For \fIdatafieldsbyvalue\fR mode, input value format contains these triplets:
+\&\fIfieldlabel,value, criteria...\fR. Possible values for criteria: \fIle, ge or eq\fR.
+The values of \fB\-\-ValueComparisonMode\fR indicates whether values are
+compared numerical or string comarison operators. Default is to consider
+data field values as numerical values and use numerical comparison operators.
+Examples:
+.Sp
+.Vb 2
+\&    MolWt,450,le
+\&    MolWt,450,le,LogP,5,le,SumNumNO,10,le,SumNHOH,5,le
+.Ve
+.Sp
+For \fIdatafieldsbyregex\fR mode, input value format contains these triplets:
+\&\fIfieldlabel,regex, criteria...\fR. \fIregex\fR corresponds to any valid regular expression
+and is used to match the values for specified \fIfieldlabel\fR. Possible values for criteria:
+ \fIeq or ne\fR. During \fIeq\fR and \fIne\fR values, data field label value is matched with
+regular expression using =~ and !~ respectively. \fB\-\-RegexIgnoreCase\fR option
+value is used to determine whether to ignore letter upper/lower case during
+regular expression match. Examples:
+.Sp
+.Vb 2
+\&    Name,ol,eq
+\&    Name,\*(Aq^pat\*(Aq,ne
+.Ve
+.Sp
+For \fIdatafieldbylist\fR and \fIdatafielduniquebylist\fR mode, input value format is:
+\&\fIfieldlabel,value1,value2...\fR. This is equivalent to \fIdatafieldsbyvalue\fR mode with
+this input value format:\fIfieldlabel,value1,eq,fieldlabel,value2,eq,...\fR. For
+\&\fIdatafielduniquebylist\fR mode, only unique compounds identified by first occurrence
+of \fIvalue\fR associated with \fIfieldlabel\fR in \fISDFile(s)\fR are kept; any subsequent compounds
+are simply ignored.
+.Sp
+For \fIdatafieldnotbylist\fR mode, input value format is: \fIfieldlabel,value1,value2...\fR. In this
+mode, the script behaves exactly opposite of \fIdatafieldbylist\fR mode, and only those compounds
+are extracted whose data field values don't match any specified data field value.
+.IP "\fB\-\-datafieldsfile\fR \fIfilename\fR" 4
+.IX Item "--datafieldsfile filename"
+Filename which contains various mode specific values. This option provides a way
+to specify mode specific values in a file instead of entering them on the command
+line using \fB\-d \-\-datafields\fR.
+.Sp
+For \fIdatafields\fR mode, input file lines contain comma delimited field labels:
+\&\fIfieldlabel,...\fR. Example:
+.Sp
+.Vb 2
+\&    Line 1:MolId
+\&    Line 2:"Extreg",CompoundName,ID
+.Ve
+.Sp
+For \fIdatafieldsbyvalue\fR mode, input file lines contains these comma separated triplets:
+\&\fIfieldlabel,value, criteria\fR. Possible values for criteria: \fIle, ge or eq\fR. Examples:
+.Sp
+.Vb 1
+\&    Line 1:MolWt,450,le
+\&
+\&    Line 1:"MolWt",450,le,"LogP",5,le,"SumNumNO",10,le,"SumNHOH",5,le
+\&
+\&    Line 1:MolWt,450,le
+\&    Line 2:"LogP",5,le
+\&    Line 3:"SumNumNO",10,le
+\&    Line 4: SumNHOH,5,le
+.Ve
+.Sp
+For \fIdatafieldbylist\fR and \fIdatafielduniquebylist\fR mode, input file line format is:
+.Sp
+.Vb 2
+\&    Line 1:fieldlabel;
+\&    Subsequent lines:value1,value2...
+.Ve
+.Sp
+For \fIdatafieldbylist\fR, \fIdatafielduniquebylist\fR, and \fIdatafieldnotbylist\fR mode, input file
+line format is:
+.Sp
+.Vb 2
+\&    Line 1:fieldlabel;
+\&    Subsequent lines:value1,value2...
+.Ve
+.Sp
+For \fIdatafielduniquebylist\fR mode, only unique compounds identified by first occurrence
+of \fIvalue\fR associated with \fIfieldlabel\fR in \fISDFile(s)\fR are kept; any subsequent compounds
+are simply ignored. Example:
+.Sp
+.Vb 5
+\&    Line 1: MolID
+\&    Subsequent Lines:
+\&    907508
+\&    832291,4642
+\&    "1254","907303"
+.Ve
+.IP "\fB\-\-indelim\fR \fIcomma | tab | semicolon\fR" 4
+.IX Item "--indelim comma | tab | semicolon"
+Delimiter used to specify text values for \fB\-d \-\-datafields\fR and \fB\-\-datafieldsfile\fR options.
+Possible values: \fIcomma, tab, or semicolon\fR. Default value: \fIcomma\fR.
+.IP "\fB\-m, \-\-mode\fR \fIalldatafields | commondatafields | datafields | datafieldsbyvalue | datafieldsbyregex | datafieldbylist | datafielduniquebylist |  datafieldnotbylist | molnames | randomcmpds | recordnum | recordnums | recordrange | 2dcmpdrecords | 3dcmpdrecords\fR" 4
+.IX Item "-m, --mode alldatafields | commondatafields | datafields | datafieldsbyvalue | datafieldsbyregex | datafieldbylist | datafielduniquebylist |  datafieldnotbylist | molnames | randomcmpds | recordnum | recordnums | recordrange | 2dcmpdrecords | 3dcmpdrecords"
+Specify what to extract from \fISDFile(s)\fR. Possible values: \fIalldatafields, commondatafields,
+datafields, datafieldsbyvalue, datafieldsbyregex, datafieldbylist, datafielduniquebylist, datafieldnotbylist,
+molnames, randomcmpds, recordnum, recordnums, recordrange, 2dcmpdrecords, 3dcmpdrecords\fR.
+Default value: \fIalldatafields\fR.
+.Sp
+For \fIalldatafields\fR and \fImolnames\fR mode, only a \s-1CSV/TSV\s0 text file is generated; for all
+other modes, however, a \s-1SD\s0 file is generated by default \- you can change the behavior to genereate
+text file using \fI\-\-output\fR option.
+.Sp
+For \fI3DCmpdRecords\fR mode, only those compounds with at least one non-zero value for Z atomic coordinates
+are retrieved; however, during retrieval of compounds in \fI2DCmpdRecords\fR mode, all Z atomic coordinates must
+be zero.
+.IP "\fB\-n, \-\-numofcmpds\fR \fInumber\fR" 4
+.IX Item "-n, --numofcmpds number"
+Number of compouds to extract during \fIrandomcmpds\fR mode.
+.IP "\fB\-\-outdelim\fR \fIcomma | tab | semicolon\fR" 4
+.IX Item "--outdelim comma | tab | semicolon"
+Delimiter for output \s-1CSV/TSV\s0 text file(s). Possible values: \fIcomma, tab, or semicolon\fR
+Default value: \fIcomma\fR
+.IP "\fB\-\-output\fR \fI\s-1SD\s0 | text | both\fR" 4
+.IX Item "--output SD | text | both"
+Type of output files to generate. Possible values: \fI\s-1SD\s0, text, or both\fR. Default value: \fI\s-1SD\s0\fR. For
+\&\fIalldatafields\fR and \fImolnames\fR mode, this option is ingored and only a \s-1CSV/TSV\s0 text file is generated.
+.IP "\fB\-o, \-\-overwrite\fR" 4
+.IX Item "-o, --overwrite"
+Overwrite existing files.
+.IP "\fB\-q, \-\-quote\fR \fIyes | no\fR" 4
+.IX Item "-q, --quote yes | no"
+Put quote around column values in output \s-1CSV/TSV\s0 text file(s). Possible values:
+\&\fIyes or no\fR. Default value: \fIyes\fR.
+.IP "\fB\-\-record\fR \fIrecnum | recnums | startrecnum,endrecnum\fR" 4
+.IX Item "--record recnum | recnums | startrecnum,endrecnum"
+Record number, record numbers or range of records to extract during \fIrecordnum\fR, \fIrecordnums\fR
+and \fIrecordrange\fR mode. Input value format is: <num>, <num1,num2,...> and <startnum, endnum>
+for \fIrecordnum\fR, \fIrecordnums\fR and \fIrecordrange\fR modes recpectively. Default value: none.
+.IP "\fB\-\-RegexIgnoreCase\fR \fIyes or no\fR" 4
+.IX Item "--RegexIgnoreCase yes or no"
+Specify whether to ingnore case during \fIdatafieldsbyregex\fR value of \fB\-m, \-\-mode\fR option.
+Possible values: \fIyes or no\fR. Default value: \fIyes\fR.
+.IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
+.IX Item "-r, --root rootname"
+New file name is generated using the root: <Root>.<Ext>. Default for new file
+names: <SDFileName><mode>.<Ext>. The file type determines <Ext> value.
+The sdf, csv, and tsv <Ext> values are used for \s-1SD\s0, comma/semicolon, and tab
+delimited text files respectively.This option is ignored for multiple input files.
+.IP "\fB\-s, \-\-seed\fR \fInumber\fR" 4
+.IX Item "-s, --seed number"
+Random number seed used for \fIrandomcmpds\fR mode. Default:123456789.
+.IP "\fB\-\-StrDataString\fR \fIyes | no\fR" 4
+.IX Item "--StrDataString yes | no"
+Specify whether to write out structure data string to \s-1CSV/TSV\s0 text file(s). Possible values:
+\&\fIyes or no\fR. Default value: \fIno\fR.
+.Sp
+The value of \fBStrDataStringDelimiter\fR option is used as a delimiter to join structure
+data lines into a structure data string.
+.Sp
+This option is ignored during generation of \s-1SD\s0 file(s).
+.IP "\fB\-\-StrDataStringDelimiter\fR \fItext\fR" 4
+.IX Item "--StrDataStringDelimiter text"
+Delimiter for joining multiple stucture data lines into a string before writing to \s-1CSV/TSV\s0 text
+file(s). Possible values: \fIany alphanumeric text\fR. Default value: \fI|\fR.
+.Sp
+This option is ignored during generation of \s-1SD\s0 file(s).
+.IP "\fB\-\-StrDataStringMode\fR \fIStrOnly | StrAndDataFields\fR" 4
+.IX Item "--StrDataStringMode StrOnly | StrAndDataFields"
+Specify whether to include \s-1SD\s0 data fields and values along with the structure data into structure
+data string before writing it out to \s-1CSV/TSV\s0 text file(s). Possible values: \fIStrOnly or StrAndDataFields\fR.
+Default value: \fIStrOnly\fR.
+.Sp
+The value of \fBStrDataStringDelimiter\fR option is used as a delimiter to join structure
+data lines into a structure data string.
+.Sp
+This option is ignored during generation of \s-1SD\s0 file(s).
+.IP "\fB\-\-ValueComparisonMode\fR \fINumeric | Alphanumeric\fR" 4
+.IX Item "--ValueComparisonMode Numeric | Alphanumeric"
+Specify how to compare data field values during \fIdatafieldsbyvalue\fR mode: Compare
+values using either numeric or string ((eq, le, ge) comparison operators. Possible values:
+\&\fINumeric or Alphanumeric\fR. Defaule value: \fINumeric\fR.
+.IP "\fB\-v, \-\-violations\fR \fInumber\fR" 4
+.IX Item "-v, --violations number"
+Number of criterion violations allowed for values specified during \fIdatafieldsbyvalue\fR
+and \fIdatafieldsbyregex\fR mode. Default value: \fI0\fR.
+.IP "\fB\-w, \-\-workingdir\fR \fIdirname\fR" 4
+.IX Item "-w, --workingdir dirname"
+Location of working directory. Default: current directory.
+.SH "EXAMPLES"
+.IX Header "EXAMPLES"
+To retrieve all data fields from \s-1SD\s0 files and generate \s-1CSV\s0 text files, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-o Sample.sdf
+\&    % ExtractFromSDFiles.pl \-o *.sdf
+.Ve
+.PP
+To retrieve all data fields from \s-1SD\s0 file and generate \s-1CSV\s0 text files containing
+a column with structure data as a string with | as line delimiter, type:
+.PP
+.Vb 1
+\&    % ExtractFromSDFiles.pl \-\-StrDataString Yes \-o Sample.sdf
+.Ve
+.PP
+To retrieve \s-1MOL_ID\s0 data fileld from \s-1SD\s0 file and generate \s-1CSV\s0 text files containing
+a column with structure data along with all data fields as a string with | as line
+delimiter, type:
+.PP
+.Vb 3
+\&    % ExtractFromSDFiles.pl \-m datafields \-d "Mol_ID" \-\-StrDataString Yes
+\&      \-\-StrDataStringMode StrAndDataFields \-\-StrDataStringDelimiter "|"
+\&      \-\-output text \-o Sample.sdf
+.Ve
+.PP
+To retrieve common data fields which exists for all the compounds in
+a \s-1SD\s0 file and generate a \s-1TSV\s0 text file NewSample.tsv, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m commondatafields \-\-outdelim tab \-r NewSample
+\&      \-\-output Text \-o Sample.sdf
+.Ve
+.PP
+To retrieve MolId, ExtReg, and CompoundName data field from a \s-1SD\s0 file and generate a
+\&\s-1CSV\s0 text file NewSample.csv, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m datafields \-d "Mol_ID,MolWeight,
+\&      CompoundName" \-r NewSample \-\-output Text \-o Sample.sdf
+.Ve
+.PP
+To retrieve compounds from a \s-1SD\s0 which meet a specific set of criteria \- MolWt <= 450,
+LogP <= 5 and SumNO < 10 \- from a \s-1SD\s0 file and generate a new \s-1SD\s0 file NewSample.sdf,
+type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m datafieldsbyvalue \-d "MolWt,450,le,LogP
+\&      ,5,le,SumNO,10" \-r NewSample \-o Sample.sdf
+.Ve
+.PP
+To retrive compounds from a \s-1SD\s0 file with a specific set of values for MolID and
+generate a new \s-1SD\s0 file NewSample.sdf, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m datafieldbylist \-d "Mol_ID,159,4509,4619"
+\&      \-r NewSample \-o Sample.sdf
+.Ve
+.PP
+To retrive compounds from a \s-1SD\s0 file with values for MolID not on a list of specified
+values and generate a new \s-1SD\s0 file NewSample.sdf, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m datafieldnotbylist \-d "Mol_ID,159,4509,4619"
+\&      \-r NewSample \-o Sample.sdf
+.Ve
+.PP
+To retrive 10 random compounds from a \s-1SD\s0 file and generate a new \s-1SD\s0 file RandomSample.sdf, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m randomcmpds \-n 10 \-r RandomSample
+\&      \-o Sample.sdf
+.Ve
+.PP
+To retrive compound record number 10 from a \s-1SD\s0 file and generate a new \s-1SD\s0 file NewSample.sdf, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m recordnum \-\-record 10 \-r NewSample
+\&      \-o Sample.sdf
+.Ve
+.PP
+To retrive compound record numbers 10, 20 and 30  from a \s-1SD\s0 file and generate a new \s-1SD\s0 file
+NewSample.sdf, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m recordnums \-\-record 10,20,30 \-r NewSample
+\&      \-o Sample.sdf
+.Ve
+.PP
+To retrive compound records between 10 to 20 from  \s-1SD\s0 file and generate a new \s-1SD\s0
+file NewSample.sdf, type:
+.PP
+.Vb 2
+\&    % ExtractFromSDFiles.pl \-m recordrange \-\-record 10,20 \-r NewSample
+\&      \-o Sample.sdf
+.Ve
+.SH "AUTHOR"
+.IX Header "AUTHOR"
+Manish Sud <msud@san.rr.com>
+.SH "SEE ALSO"
+.IX Header "SEE ALSO"
+FilterSDFiles.pl, InfoSDFiles.pl, SplitSDFiles.pl, MergeTextFilesWithSD.pl
+.SH "COPYRIGHT"
+.IX Header "COPYRIGHT"
+Copyright (C) 2015 Manish Sud. All rights reserved.
+.PP
+This file is part of MayaChemTools.
+.PP
+MayaChemTools is free software; you can redistribute it and/or modify it under
+the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
+Software Foundation; either version 3 of the License, or (at your option)
+any later version.