website/full_javadoc/compbio/data/sequence/SequenceUtil.html

   1 <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">\r
   2 <!--NewPage-->\r
   3 <HTML>\r
   4 <HEAD>\r
   5 <!-- Generated by javadoc (build 1.6.0_14) on Wed Feb 17 16:46:49 GMT 2010 -->\r
   6 <TITLE>\r
   7 SequenceUtil\r
   8 </TITLE>\r
   9 \r
  10 <META NAME="date" CONTENT="2010-02-17">\r
  11 \r
  12 <LINK REL ="stylesheet" TYPE="text/css" HREF="../../../stylesheet.css" TITLE="Style">\r
  13 \r
  14 <SCRIPT type="text/javascript">\r
  15 function windowTitle()\r
  16 {\r
  17     if (location.href.indexOf('is-external=true') == -1) {\r
  18         parent.document.title="SequenceUtil";\r
  19     }\r
  20 }\r
  21 </SCRIPT>\r
  22 <NOSCRIPT>\r
  23 </NOSCRIPT>\r
  24 \r
  25 </HEAD>\r
  26 \r
  27 <BODY BGCOLOR="white" onload="windowTitle();">\r
  28 <HR>\r
  29 \r
  30 \r
  31 <!-- ========= START OF TOP NAVBAR ======= -->\r
  32 <A NAME="navbar_top"><!-- --></A>\r
  33 <A HREF="#skip-navbar_top" title="Skip navigation links"></A>\r
  34 <TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">\r
  35 <TR>\r
  36 <TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">\r
  37 <A NAME="navbar_top_firstrow"><!-- --></A>\r
  38 <TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">\r
  39   <TR ALIGN="center" VALIGN="top">\r
  40   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>\r
  41   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>\r
  42   <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>\r
  43   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="class-use/SequenceUtil.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A>&nbsp;</TD>\r
  44   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>\r
  45   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>\r
  46   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../index-files/index-1.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A>&nbsp;</TD>\r
  47   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>\r
  48   </TR>\r
  49 </TABLE>\r
  50 </TD>\r
  51 <TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>\r
  52 </EM>\r
  53 </TD>\r
  54 </TR>\r
  55 \r
  56 <TR>\r
  57 <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">\r
  58 &nbsp;<A HREF="../../../compbio/data/sequence/Program.html" title="enum in compbio.data.sequence"><B>PREV CLASS</B></A>&nbsp;\r
  59 &nbsp;<A HREF="../../../compbio/data/sequence/UnknownFileFormatException.html" title="class in compbio.data.sequence"><B>NEXT CLASS</B></A></FONT></TD>\r
  60 <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">\r
  61   <A HREF="../../../index.html?compbio/data/sequence/SequenceUtil.html" target="_top"><B>FRAMES</B></A>  &nbsp;\r
  62 &nbsp;<A HREF="SequenceUtil.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;\r
  63 &nbsp;<SCRIPT type="text/javascript">\r
  64   <!--\r
  65   if(window==top) {\r
  66     document.writeln('<A HREF="../../../allclasses-noframe.html"><B>All Classes</B></A>');\r
  67   }\r
  68   //-->\r
  69 </SCRIPT>\r
  70 <NOSCRIPT>\r
  71   <A HREF="../../../allclasses-noframe.html"><B>All Classes</B></A>\r
  72 </NOSCRIPT>\r
  73 \r
  74 \r
  75 </FONT></TD>\r
  76 </TR>\r
  77 <TR>\r
  78 <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">\r
  79   SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;<A HREF="#field_summary">FIELD</A>&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>\r
  80 <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">\r
  81 DETAIL:&nbsp;<A HREF="#field_detail">FIELD</A>&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>\r
  82 </TR>\r
  83 </TABLE>\r
  84 <A NAME="skip-navbar_top"></A>\r
  85 <!-- ========= END OF TOP NAVBAR ========= -->\r
  86 \r
  87 <HR>\r
  88 <!-- ======== START OF CLASS DATA ======== -->\r
  89 <H2>\r
  90 <FONT SIZE="-1">\r
  91 compbio.data.sequence</FONT>\r
  92 <BR>\r
  93 Class SequenceUtil</H2>\r
  94 <PRE>\r
  95 java.lang.Object\r
  96   <IMG SRC="../../../resources/inherit.gif" ALT="extended by "><B>compbio.data.sequence.SequenceUtil</B>\r
  97 </PRE>\r
  98 <HR>\r
  99 <DL>\r
 100 <DT><PRE>public final class <B>SequenceUtil</B><DT>extends java.lang.Object</DL>\r
 101 </PRE>\r
 102 \r
 103 <P>\r
 104 Utility class for operations on sequences\r
 105 <P>\r
 106 \r
 107 <P>\r
 108 <DL>\r
 109 <DT><B>Author:</B></DT>\r
 110   <DD>pvtroshin
 111
 112          Date September 2009</DD>\r
 113 </DL>\r
 114 <HR>\r
 115 \r
 116 <P>\r
 117 <!-- =========== FIELD SUMMARY =========== -->\r
 118 \r
 119 <A NAME="field_summary"><!-- --></A>\r
 120 <TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">\r
 121 <TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">\r
 122 <TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">\r
 123 <B>Field Summary</B></FONT></TH>\r
 124 </TR>\r
 125 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 126 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 127 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 128 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#AA">AA</A></B></CODE>\r
 129 \r
 130 <BR>\r
 131 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Valid Amino acids</TD>\r
 132 </TR>\r
 133 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 134 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 135 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 136 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#AMBIGUOUS_AA">AMBIGUOUS_AA</A></B></CODE>\r
 137 \r
 138 <BR>\r
 139 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Same as AA pattern but with two additional letters - XU</TD>\r
 140 </TR>\r
 141 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 142 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 143 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 144 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#AMBIGUOUS_NUCLEOTIDE">AMBIGUOUS_NUCLEOTIDE</A></B></CODE>\r
 145 \r
 146 <BR>\r
 147 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Ambiguous nucleotide</TD>\r
 148 </TR>\r
 149 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 150 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 151 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 152 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#DIGIT">DIGIT</A></B></CODE>\r
 153 \r
 154 <BR>\r
 155 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;A digit</TD>\r
 156 </TR>\r
 157 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 158 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 159 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 160 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#NON_AA">NON_AA</A></B></CODE>\r
 161 \r
 162 <BR>\r
 163 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;inversion of AA pattern</TD>\r
 164 </TR>\r
 165 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 166 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 167 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 168 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#NON_NUCLEOTIDE">NON_NUCLEOTIDE</A></B></CODE>\r
 169 \r
 170 <BR>\r
 171 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Non nucleotide</TD>\r
 172 </TR>\r
 173 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 174 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 175 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 176 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#NONWORD">NONWORD</A></B></CODE>\r
 177 \r
 178 <BR>\r
 179 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Non word</TD>\r
 180 </TR>\r
 181 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 182 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 183 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 184 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#NUCLEOTIDE">NUCLEOTIDE</A></B></CODE>\r
 185 \r
 186 <BR>\r
 187 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Nucleotides a, t, g, c, u</TD>\r
 188 </TR>\r
 189 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 190 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 191 <CODE>static&nbsp;java.util.regex.Pattern</CODE></FONT></TD>\r
 192 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#WHITE_SPACE">WHITE_SPACE</A></B></CODE>\r
 193 \r
 194 <BR>\r
 195 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;A whitespace character: [\t\n\x0B\f\r]</TD>\r
 196 </TR>\r
 197 </TABLE>\r
 198 &nbsp;\r
 199 <!-- ========== METHOD SUMMARY =========== -->\r
 200 \r
 201 <A NAME="method_summary"><!-- --></A>\r
 202 <TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">\r
 203 <TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">\r
 204 <TH ALIGN="left" COLSPAN="2"><FONT SIZE="+2">\r
 205 <B>Method Summary</B></FONT></TH>\r
 206 </TR>\r
 207 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 208 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 209 <CODE>static&nbsp;java.lang.String</CODE></FONT></TD>\r
 210 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#cleanSequence(java.lang.String)">cleanSequence</A></B>(java.lang.String&nbsp;sequence)</CODE>\r
 211 \r
 212 <BR>\r
 213 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Removes all whitespace chars in the sequence string</TD>\r
 214 </TR>\r
 215 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 216 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 217 <CODE>static&nbsp;java.lang.String</CODE></FONT></TD>\r
 218 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#deepCleanSequence(java.lang.String)">deepCleanSequence</A></B>(java.lang.String&nbsp;sequence)</CODE>\r
 219 \r
 220 <BR>\r
 221 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Removes all special characters and digits as well as whitespace chars
 222  from the sequence</TD>\r
 223 </TR>\r
 224 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 225 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 226 <CODE>static&nbsp;boolean</CODE></FONT></TD>\r
 227 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#isAmbiguosProtein(java.lang.String)">isAmbiguosProtein</A></B>(java.lang.String&nbsp;sequence)</CODE>\r
 228 \r
 229 <BR>\r
 230 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Check whether the sequence confirms to amboguous protein sequence</TD>\r
 231 </TR>\r
 232 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 233 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 234 <CODE>static&nbsp;boolean</CODE></FONT></TD>\r
 235 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#isNonAmbNucleotideSequence(java.lang.String)">isNonAmbNucleotideSequence</A></B>(java.lang.String&nbsp;sequence)</CODE>\r
 236 \r
 237 <BR>\r
 238 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Ambiguous DNA chars : AGTCRYMKSWHBVDN // differs from protein in only one
 239  (!) - B char</TD>\r
 240 </TR>\r
 241 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 242 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 243 <CODE>static&nbsp;boolean</CODE></FONT></TD>\r
 244 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#isNucleotideSequence(compbio.data.sequence.FastaSequence)">isNucleotideSequence</A></B>(<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&nbsp;s)</CODE>\r
 245 \r
 246 <BR>\r
 247 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>\r
 248 </TR>\r
 249 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 250 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 251 <CODE>static&nbsp;boolean</CODE></FONT></TD>\r
 252 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#isProteinSequence(java.lang.String)">isProteinSequence</A></B>(java.lang.String&nbsp;sequence)</CODE>\r
 253 \r
 254 <BR>\r
 255 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>\r
 256 </TR>\r
 257 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 258 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 259 <CODE>static&nbsp;java.util.List&lt;<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&gt;</CODE></FONT></TD>\r
 260 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#readFasta(java.io.InputStream)">readFasta</A></B>(java.io.InputStream&nbsp;inStream)</CODE>\r
 261 \r
 262 <BR>\r
 263 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Reads fasta sequences from inStream into the list of FastaSequence
 264  objects</TD>\r
 265 </TR>\r
 266 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 267 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 268 <CODE>static&nbsp;void</CODE></FONT></TD>\r
 269 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#writeFasta(java.io.OutputStream, java.util.List)">writeFasta</A></B>(java.io.OutputStream&nbsp;os,\r
 270            java.util.List&lt;<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&gt;&nbsp;sequences)</CODE>\r
 271 \r
 272 <BR>\r
 273 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Writes FastaSequence in the file, each sequence will take one line only</TD>\r
 274 </TR>\r
 275 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 276 <TD ALIGN="right" VALIGN="top" WIDTH="1%"><FONT SIZE="-1">\r
 277 <CODE>static&nbsp;void</CODE></FONT></TD>\r
 278 <TD><CODE><B><A HREF="../../../compbio/data/sequence/SequenceUtil.html#writeFasta(java.io.OutputStream, java.util.List, int)">writeFasta</A></B>(java.io.OutputStream&nbsp;outstream,\r
 279            java.util.List&lt;<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&gt;&nbsp;sequences,\r
 280            int&nbsp;width)</CODE>\r
 281 \r
 282 <BR>\r
 283 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Writes list of FastaSequeces into the outstream formatting the sequence
 284  so that it contains width chars on each line</TD>\r
 285 </TR>\r
 286 </TABLE>\r
 287 &nbsp;<A NAME="methods_inherited_from_class_java.lang.Object"><!-- --></A>\r
 288 <TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">\r
 289 <TR BGCOLOR="#EEEEFF" CLASS="TableSubHeadingColor">\r
 290 <TH ALIGN="left"><B>Methods inherited from class java.lang.Object</B></TH>\r
 291 </TR>\r
 292 <TR BGCOLOR="white" CLASS="TableRowColor">\r
 293 <TD><CODE>equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait</CODE></TD>\r
 294 </TR>\r
 295 </TABLE>\r
 296 &nbsp;\r
 297 <P>\r
 298 \r
 299 <!-- ============ FIELD DETAIL =========== -->\r
 300 \r
 301 <A NAME="field_detail"><!-- --></A>\r
 302 <TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">\r
 303 <TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">\r
 304 <TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">\r
 305 <B>Field Detail</B></FONT></TH>\r
 306 </TR>\r
 307 </TABLE>\r
 308 \r
 309 <A NAME="WHITE_SPACE"><!-- --></A><H3>\r
 310 WHITE_SPACE</H3>\r
 311 <PRE>\r
 312 public static final java.util.regex.Pattern <B>WHITE_SPACE</B></PRE>\r
 313 <DL>\r
 314 <DD>A whitespace character: [\t\n\x0B\f\r]\r
 315 <P>\r
 316 <DL>\r
 317 </DL>\r
 318 </DL>\r
 319 <HR>\r
 320 \r
 321 <A NAME="DIGIT"><!-- --></A><H3>\r
 322 DIGIT</H3>\r
 323 <PRE>\r
 324 public static final java.util.regex.Pattern <B>DIGIT</B></PRE>\r
 325 <DL>\r
 326 <DD>A digit\r
 327 <P>\r
 328 <DL>\r
 329 </DL>\r
 330 </DL>\r
 331 <HR>\r
 332 \r
 333 <A NAME="NONWORD"><!-- --></A><H3>\r
 334 NONWORD</H3>\r
 335 <PRE>\r
 336 public static final java.util.regex.Pattern <B>NONWORD</B></PRE>\r
 337 <DL>\r
 338 <DD>Non word\r
 339 <P>\r
 340 <DL>\r
 341 </DL>\r
 342 </DL>\r
 343 <HR>\r
 344 \r
 345 <A NAME="AA"><!-- --></A><H3>\r
 346 AA</H3>\r
 347 <PRE>\r
 348 public static final java.util.regex.Pattern <B>AA</B></PRE>\r
 349 <DL>\r
 350 <DD>Valid Amino acids\r
 351 <P>\r
 352 <DL>\r
 353 </DL>\r
 354 </DL>\r
 355 <HR>\r
 356 \r
 357 <A NAME="NON_AA"><!-- --></A><H3>\r
 358 NON_AA</H3>\r
 359 <PRE>\r
 360 public static final java.util.regex.Pattern <B>NON_AA</B></PRE>\r
 361 <DL>\r
 362 <DD>inversion of AA pattern\r
 363 <P>\r
 364 <DL>\r
 365 </DL>\r
 366 </DL>\r
 367 <HR>\r
 368 \r
 369 <A NAME="AMBIGUOUS_AA"><!-- --></A><H3>\r
 370 AMBIGUOUS_AA</H3>\r
 371 <PRE>\r
 372 public static final java.util.regex.Pattern <B>AMBIGUOUS_AA</B></PRE>\r
 373 <DL>\r
 374 <DD>Same as AA pattern but with two additional letters - XU\r
 375 <P>\r
 376 <DL>\r
 377 </DL>\r
 378 </DL>\r
 379 <HR>\r
 380 \r
 381 <A NAME="NUCLEOTIDE"><!-- --></A><H3>\r
 382 NUCLEOTIDE</H3>\r
 383 <PRE>\r
 384 public static final java.util.regex.Pattern <B>NUCLEOTIDE</B></PRE>\r
 385 <DL>\r
 386 <DD>Nucleotides a, t, g, c, u\r
 387 <P>\r
 388 <DL>\r
 389 </DL>\r
 390 </DL>\r
 391 <HR>\r
 392 \r
 393 <A NAME="AMBIGUOUS_NUCLEOTIDE"><!-- --></A><H3>\r
 394 AMBIGUOUS_NUCLEOTIDE</H3>\r
 395 <PRE>\r
 396 public static final java.util.regex.Pattern <B>AMBIGUOUS_NUCLEOTIDE</B></PRE>\r
 397 <DL>\r
 398 <DD>Ambiguous nucleotide\r
 399 <P>\r
 400 <DL>\r
 401 </DL>\r
 402 </DL>\r
 403 <HR>\r
 404 \r
 405 <A NAME="NON_NUCLEOTIDE"><!-- --></A><H3>\r
 406 NON_NUCLEOTIDE</H3>\r
 407 <PRE>\r
 408 public static final java.util.regex.Pattern <B>NON_NUCLEOTIDE</B></PRE>\r
 409 <DL>\r
 410 <DD>Non nucleotide\r
 411 <P>\r
 412 <DL>\r
 413 </DL>\r
 414 </DL>\r
 415 \r
 416 <!-- ============ METHOD DETAIL ========== -->\r
 417 \r
 418 <A NAME="method_detail"><!-- --></A>\r
 419 <TABLE BORDER="1" WIDTH="100%" CELLPADDING="3" CELLSPACING="0" SUMMARY="">\r
 420 <TR BGCOLOR="#CCCCFF" CLASS="TableHeadingColor">\r
 421 <TH ALIGN="left" COLSPAN="1"><FONT SIZE="+2">\r
 422 <B>Method Detail</B></FONT></TH>\r
 423 </TR>\r
 424 </TABLE>\r
 425 \r
 426 <A NAME="isNucleotideSequence(compbio.data.sequence.FastaSequence)"><!-- --></A><H3>\r
 427 isNucleotideSequence</H3>\r
 428 <PRE>\r
 429 public static boolean <B>isNucleotideSequence</B>(<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&nbsp;s)</PRE>\r
 430 <DL>\r
 431 <DD><DL>\r
 432 \r
 433 <DT><B>Returns:</B><DD>true is the sequence contains only letters a,c, t, g, u</DL>\r
 434 </DD>\r
 435 </DL>\r
 436 <HR>\r
 437 \r
 438 <A NAME="isNonAmbNucleotideSequence(java.lang.String)"><!-- --></A><H3>\r
 439 isNonAmbNucleotideSequence</H3>\r
 440 <PRE>\r
 441 public static boolean <B>isNonAmbNucleotideSequence</B>(java.lang.String&nbsp;sequence)</PRE>\r
 442 <DL>\r
 443 <DD>Ambiguous DNA chars : AGTCRYMKSWHBVDN // differs from protein in only one
 444  (!) - B char\r
 445 <P>\r
 446 <DD><DL>\r
 447 </DL>\r
 448 </DD>\r
 449 </DL>\r
 450 <HR>\r
 451 \r
 452 <A NAME="cleanSequence(java.lang.String)"><!-- --></A><H3>\r
 453 cleanSequence</H3>\r
 454 <PRE>\r
 455 public static java.lang.String <B>cleanSequence</B>(java.lang.String&nbsp;sequence)</PRE>\r
 456 <DL>\r
 457 <DD>Removes all whitespace chars in the sequence string\r
 458 <P>\r
 459 <DD><DL>\r
 460 <DT><B>Parameters:</B><DD><CODE>sequence</CODE> - \r
 461 <DT><B>Returns:</B><DD>cleaned up sequence</DL>\r
 462 </DD>\r
 463 </DL>\r
 464 <HR>\r
 465 \r
 466 <A NAME="deepCleanSequence(java.lang.String)"><!-- --></A><H3>\r
 467 deepCleanSequence</H3>\r
 468 <PRE>\r
 469 public static java.lang.String <B>deepCleanSequence</B>(java.lang.String&nbsp;sequence)</PRE>\r
 470 <DL>\r
 471 <DD>Removes all special characters and digits as well as whitespace chars
 472  from the sequence\r
 473 <P>\r
 474 <DD><DL>\r
 475 <DT><B>Parameters:</B><DD><CODE>sequence</CODE> - \r
 476 <DT><B>Returns:</B><DD>cleaned up sequence</DL>\r
 477 </DD>\r
 478 </DL>\r
 479 <HR>\r
 480 \r
 481 <A NAME="isProteinSequence(java.lang.String)"><!-- --></A><H3>\r
 482 isProteinSequence</H3>\r
 483 <PRE>\r
 484 public static boolean <B>isProteinSequence</B>(java.lang.String&nbsp;sequence)</PRE>\r
 485 <DL>\r
 486 <DD><DL>\r
 487 <DT><B>Parameters:</B><DD><CODE>sequence</CODE> - \r
 488 <DT><B>Returns:</B><DD>true is the sequence is a protein sequence, false overwise</DL>\r
 489 </DD>\r
 490 </DL>\r
 491 <HR>\r
 492 \r
 493 <A NAME="isAmbiguosProtein(java.lang.String)"><!-- --></A><H3>\r
 494 isAmbiguosProtein</H3>\r
 495 <PRE>\r
 496 public static boolean <B>isAmbiguosProtein</B>(java.lang.String&nbsp;sequence)</PRE>\r
 497 <DL>\r
 498 <DD>Check whether the sequence confirms to amboguous protein sequence\r
 499 <P>\r
 500 <DD><DL>\r
 501 <DT><B>Parameters:</B><DD><CODE>sequence</CODE> - \r
 502 <DT><B>Returns:</B><DD>return true only if the sequence if ambiguous protein sequence
 503          Return false otherwise. e.g. if the sequence is non-ambiguous
 504          protein or DNA</DL>\r
 505 </DD>\r
 506 </DL>\r
 507 <HR>\r
 508 \r
 509 <A NAME="writeFasta(java.io.OutputStream, java.util.List, int)"><!-- --></A><H3>\r
 510 writeFasta</H3>\r
 511 <PRE>\r
 512 public static void <B>writeFasta</B>(java.io.OutputStream&nbsp;outstream,\r
 513                               java.util.List&lt;<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&gt;&nbsp;sequences,\r
 514                               int&nbsp;width)\r
 515                        throws java.io.IOException</PRE>\r
 516 <DL>\r
 517 <DD>Writes list of FastaSequeces into the outstream formatting the sequence
 518  so that it contains width chars on each line\r
 519 <P>\r
 520 <DD><DL>\r
 521 <DT><B>Parameters:</B><DD><CODE>outstream</CODE> - <DD><CODE>sequences</CODE> - <DD><CODE>width</CODE> - - the maximum number of characters to write in one line\r
 522 <DT><B>Throws:</B>\r
 523 <DD><CODE>java.io.IOException</CODE></DL>\r
 524 </DD>\r
 525 </DL>\r
 526 <HR>\r
 527 \r
 528 <A NAME="readFasta(java.io.InputStream)"><!-- --></A><H3>\r
 529 readFasta</H3>\r
 530 <PRE>\r
 531 public static java.util.List&lt;<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&gt; <B>readFasta</B>(java.io.InputStream&nbsp;inStream)\r
 532                                                throws java.io.IOException</PRE>\r
 533 <DL>\r
 534 <DD>Reads fasta sequences from inStream into the list of FastaSequence
 535  objects\r
 536 <P>\r
 537 <DD><DL>\r
 538 <DT><B>Parameters:</B><DD><CODE>inStream</CODE> - from\r
 539 <DT><B>Returns:</B><DD>list of FastaSequence objects\r
 540 <DT><B>Throws:</B>\r
 541 <DD><CODE>java.io.IOException</CODE></DL>\r
 542 </DD>\r
 543 </DL>\r
 544 <HR>\r
 545 \r
 546 <A NAME="writeFasta(java.io.OutputStream, java.util.List)"><!-- --></A><H3>\r
 547 writeFasta</H3>\r
 548 <PRE>\r
 549 public static void <B>writeFasta</B>(java.io.OutputStream&nbsp;os,\r
 550                               java.util.List&lt;<A HREF="../../../compbio/data/sequence/FastaSequence.html" title="class in compbio.data.sequence">FastaSequence</A>&gt;&nbsp;sequences)\r
 551                        throws java.io.IOException</PRE>\r
 552 <DL>\r
 553 <DD>Writes FastaSequence in the file, each sequence will take one line only\r
 554 <P>\r
 555 <DD><DL>\r
 556 <DT><B>Parameters:</B><DD><CODE>os</CODE> - <DD><CODE>sequences</CODE> - \r
 557 <DT><B>Throws:</B>\r
 558 <DD><CODE>java.io.IOException</CODE></DL>\r
 559 </DD>\r
 560 </DL>\r
 561 <!-- ========= END OF CLASS DATA ========= -->\r
 562 <HR>\r
 563 \r
 564 \r
 565 <!-- ======= START OF BOTTOM NAVBAR ====== -->\r
 566 <A NAME="navbar_bottom"><!-- --></A>\r
 567 <A HREF="#skip-navbar_bottom" title="Skip navigation links"></A>\r
 568 <TABLE BORDER="0" WIDTH="100%" CELLPADDING="1" CELLSPACING="0" SUMMARY="">\r
 569 <TR>\r
 570 <TD COLSPAN=2 BGCOLOR="#EEEEFF" CLASS="NavBarCell1">\r
 571 <A NAME="navbar_bottom_firstrow"><!-- --></A>\r
 572 <TABLE BORDER="0" CELLPADDING="0" CELLSPACING="3" SUMMARY="">\r
 573   <TR ALIGN="center" VALIGN="top">\r
 574   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../overview-summary.html"><FONT CLASS="NavBarFont1"><B>Overview</B></FONT></A>&nbsp;</TD>\r
 575   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-summary.html"><FONT CLASS="NavBarFont1"><B>Package</B></FONT></A>&nbsp;</TD>\r
 576   <TD BGCOLOR="#FFFFFF" CLASS="NavBarCell1Rev"> &nbsp;<FONT CLASS="NavBarFont1Rev"><B>Class</B></FONT>&nbsp;</TD>\r
 577   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="class-use/SequenceUtil.html"><FONT CLASS="NavBarFont1"><B>Use</B></FONT></A>&nbsp;</TD>\r
 578   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="package-tree.html"><FONT CLASS="NavBarFont1"><B>Tree</B></FONT></A>&nbsp;</TD>\r
 579   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../deprecated-list.html"><FONT CLASS="NavBarFont1"><B>Deprecated</B></FONT></A>&nbsp;</TD>\r
 580   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../index-files/index-1.html"><FONT CLASS="NavBarFont1"><B>Index</B></FONT></A>&nbsp;</TD>\r
 581   <TD BGCOLOR="#EEEEFF" CLASS="NavBarCell1">    <A HREF="../../../help-doc.html"><FONT CLASS="NavBarFont1"><B>Help</B></FONT></A>&nbsp;</TD>\r
 582   </TR>\r
 583 </TABLE>\r
 584 </TD>\r
 585 <TD ALIGN="right" VALIGN="top" ROWSPAN=3><EM>\r
 586 </EM>\r
 587 </TD>\r
 588 </TR>\r
 589 \r
 590 <TR>\r
 591 <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">\r
 592 &nbsp;<A HREF="../../../compbio/data/sequence/Program.html" title="enum in compbio.data.sequence"><B>PREV CLASS</B></A>&nbsp;\r
 593 &nbsp;<A HREF="../../../compbio/data/sequence/UnknownFileFormatException.html" title="class in compbio.data.sequence"><B>NEXT CLASS</B></A></FONT></TD>\r
 594 <TD BGCOLOR="white" CLASS="NavBarCell2"><FONT SIZE="-2">\r
 595   <A HREF="../../../index.html?compbio/data/sequence/SequenceUtil.html" target="_top"><B>FRAMES</B></A>  &nbsp;\r
 596 &nbsp;<A HREF="SequenceUtil.html" target="_top"><B>NO FRAMES</B></A>  &nbsp;\r
 597 &nbsp;<SCRIPT type="text/javascript">\r
 598   <!--\r
 599   if(window==top) {\r
 600     document.writeln('<A HREF="../../../allclasses-noframe.html"><B>All Classes</B></A>');\r
 601   }\r
 602   //-->\r
 603 </SCRIPT>\r
 604 <NOSCRIPT>\r
 605   <A HREF="../../../allclasses-noframe.html"><B>All Classes</B></A>\r
 606 </NOSCRIPT>\r
 607 \r
 608 \r
 609 </FONT></TD>\r
 610 </TR>\r
 611 <TR>\r
 612 <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">\r
 613   SUMMARY:&nbsp;NESTED&nbsp;|&nbsp;<A HREF="#field_summary">FIELD</A>&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_summary">METHOD</A></FONT></TD>\r
 614 <TD VALIGN="top" CLASS="NavBarCell3"><FONT SIZE="-2">\r
 615 DETAIL:&nbsp;<A HREF="#field_detail">FIELD</A>&nbsp;|&nbsp;CONSTR&nbsp;|&nbsp;<A HREF="#method_detail">METHOD</A></FONT></TD>\r
 616 </TR>\r
 617 </TABLE>\r
 618 <A NAME="skip-navbar_bottom"></A>\r
 619 <!-- ======== END OF BOTTOM NAVBAR ======= -->\r
 620 \r
 621 <HR>\r
 622 \r
 623 </BODY>\r
 624 </HTML>\r