Differences

This shows you the differences between two versions of the page.

--- gda [2008/06/18 10:20] – heidi
+++ gda [2011/07/13 16:54] (current) – heidi
@@ Line 11: / Line 11: @@
   * Windows
   * Mac OS 10.2.8 and 10.3 (Jaguar and Panther)
 ===== Data type handled =====
-  * AFLP........
+  * Microsat
+  * RFLP
+  * AFLP
+  * SNP
+  * Standard (multi-allelic marker)
@@ Line 22: / Line 29: @@
 ===== Input Files =====
   * uses [[NEXUS]] file format
 ==== GDADATA block ====
+  * If a token begins with a single or double quote character, then every character until the next, matching quote character will be treated as a single token. This is useful as a means of putting blank spaces insice poulation or locus lables.
+  * commands:
+    * begin
+    * dimensions:
+      * number of populations: ''npops=2''
+      * number of loci: ''nloci=5''
+    * format:
+      * ''tokens'' / ''notokens''
+      * ''labels'' / ''nolables''
+      * ''interleaved''
+      * ''haploid''
+      * ''missing=?''
+      * ''separator=/''
+      * ''datapoint=standard''
+    * locusallelelabels (optional):
+      * loci names
+      * allele names can be provided
+      * loci will be numbered beginning with 1 if this command is absent
+    * matrix:
+      * end of the data for one population is signified by either a comma or the semicolon indicating the end of the matrix command
+    * end
+  * not case-sensitive, except in the matrix command (allele named A is treated as being distinct form a)
+=== haploid data ===
+  * two ways:
+    * if all loci are haploid: include the keyword haploid in the format command
+    * mixture of haploid and diploid data: hapset command is used to specify which loci are haploid
 === example ===
-<code>
+  * diploid data: <code>
 #nexus
@@ Line 48: / Line 85: @@
   ;
 end;
+</code>
+  * haploid data: <code>
+#nexus
+begin gdadata;
+	dimensions nloci=5 npops=2;
+	format haploid tokens missing=? datapoint=standard;
+	locusallelelabels
+locus_1 [ / 1 2 3 4],
+locus_2 [ / 1 2 3 4],
+locus_3 [ / 1 2 3 4],
+locus_4 [ / 1 2 3 4],
+locus_5 [ / 1 2 3 4];
+	matrix
+	Pop_1:	_1_ 4 3 3 3 4
+		_2_ 4 4 3 3 4
+		_3_ 4 4 3 3 4
+		_4_ 4 4 ? 3 4
+		_5_ 4 4 2 4 4
+		_6_ 4 4 4 4 4
+		_7_ 4 4 3 4 4
+		_8_ 4 4 3 4 4
+		_9_ 4 4 ? 3 4
+_ 4 4 3 3 4,
+	Pop_2:	_1_ 4 4 2 2 4
+		_2_ 4 3 4 3 4
+		_3_ 4 4 3 3 4
+		_4_ 4 4 4 4 4
+		_5_ 4 3 4 4 4
+		_6_ 4 4 4 2 4
+		_7_ 4 4 3 3 4
+		_8_ 4 4 4 4 4
+;
+end;
+</code>
+  * mixed haploid/diploid data:<code>
+#NEXUS
+[Note: first 5 loci are diploid and last 3 are haploid]
+begin gdadata;
+  dimensions nloci=8 npops=6;
+  format tokens labels missing=? datapoint=standard;
+  hapset 6-8;
+  locusallelelabels
+'dip 1',
+'dip 2',
+'dip 3',
+'dip 4',
+'dip 5',
+'hap 1',
+'hap 2',
+'hap 3'
+  ;
+  matrix
+    Pop1:
+      indiv1 4/4 4/3 4/3 3/3 4/4 3 3 4
+      indiv2 4/4 4/4 4/3 3/3 4/4 3 3 4
+      ...
 </code>