Added doc + test

evolbioinfo · Sep 26, 2024 · a631422 · a631422
1 parent bdbd8f1
commit a631422
Show file tree

Hide file tree

Showing 4 changed files with 87 additions and 1 deletion.
diff --git a/cmd/cutdate.go b/cmd/cutdate.go
@@ -21,7 +21,9 @@ var pruneDateCmd = &cobra.Command{
 This command will extract part of the tree corresponding to >= min-date and <= max-date.
 
 If min-date falls on an internal branch, it will create a new root node and will extract a tree starting at this node.
-If max-date falls on an internal branch, we do not take this part of the tree, and we remove branches that end into these cases.
+If max-date is specified (>0) : It additionally removes all tips that are > maxdate
+
+This command considers the input tree as rooted
 
 `,
 	RunE: func(cmd *cobra.Command, args []string) (err error) {

diff --git a/docs/commands/cut.md b/docs/commands/cut.md
@@ -0,0 +1,66 @@
+# Gotree: toolkit and api for phylogenetic tree manipulation
+
+## Commands
+
+### cut
+Cut the input tree by keeping only parts in date window.
+
+It extracts parts of the tree corresponding to >= min-date and <= max-date.
+
+If min-date falls on an internal branch, it will create a new root node and will extract a tree starting at this node.
+If max-date is specified (>0) : It removes all tips that are > maxdate
+
+This command considers the input tree as rooted.
+
+Dates are taken from the field [&date=] of the Nexus format.
+
+#### Usage
+
+```
+Usage:
+  gotree cut date [flags]
+
+Flags:
+  -h, --help             help for date
+  -i, --input string     Input tree(s) file (default "stdin")
+      --max-date float   Maximum date to cut the tree (0=no max date)
+      --min-date float   Minimum date to cut the tree
+  -o, --output string    Forest output file (default "stdout")
+
+Global Flags:
+      --format string   Input tree format (newick, nexus, phyloxml, or nextstrain) (default "newick")
+```
+
+#### Example
+
+
+Initial tree:
+```
++-------------------- A[&date="2000"]
+[&date="1990"]
+|                        +------------ B[&date="2008"]
++------------------------|[&date="2002"]
+                         |          +----- C[&date="2010"]
+                         +----------|[&date="2007"]
+                                    +------- D[&date="2011"]
+```
+
+If we cut it between 2003 and 2009:
+```
+echo '(A[&date="2000"]:10,(B[&date="2008"]:6,(C[&date="2010"]:3,D[&date="2011"]:4)[&date="2007"]:5)[&date="2002"]:12)[&date="1990"];' | ./gotree cut date --min-date 2003 --max-date 2009
+
+(B[&date="2008"]:5)[&date="2003.000000"];
+```
+
+- There is only one hanging branch left
+
+If we cut it between 2003 and 2020:
+
+```
+echo '(A[&date="2000"]:10,(B[&date="2008"]:6,(C[&date="2010"]:3,D[&date="2011"]:4)[&date="2007"]:5)[&date="2002"]:12)[&date="1990"];' | ./gotree cut date --min-date 2003 --max-date 2020
+
+(B[&date="2008"]:5)[&date="2003.000000"];
+((C[&date="2010"]:3,D[&date="2011"]:4)[&date="2007"]:4)[&date="2003.000000"];
+```
+
+- There are two trees: 1) only one hanging branch, and 2) two tips left
diff --git a/docs/index.md b/docs/index.md
@@ -64,6 +64,7 @@ Command                                                            | Subcommand
 --                                                                 | edgetrees         | Writes one output tree per branch of the input tree, with only one branch
 --                                                                 | support classical | Computes classical bootstrap supports
 --                                                                 | support booster   | Computes booster bootstrap supports
+[cut](commands/cut.md)                                             | date              | Cut the tree into specific time windows trees (if dated tree)
 [divide](commands/divide.md)                                       |                   | Divides an input tree file into several tree files
 [download](commands/download.md) ([api](api/download.md))          |                   | Downloads trees from a server
 --                                                                 | itol              | Downloads a tree image from iTOL, with given image options

diff --git a/test.sh b/test.sh
@@ -2251,3 +2251,20 @@ EOF
 echo '(((A[&date="2024"]:1,B[&date="2024"]:1)[&date="2023"]:1,C[&date="2024"]:2)[&date="2022"]:3,(D[&date="2024"]:4,(E[&date="2024"]:3,((F[&date="2024"]:1.5,G[&date="2024"]:1.5)[&date="2022.5"]:0.5,H[&date="2024"]:2)[&date="2022"]:1)[&date="2021"]:1)[&date="2020"]:1)[&date="2019"];' | $GOTREE ltt > result
 diff -q -b expected result
 rm -f expected result
+
+
+echo "->gotree cut date"
+cat > expected <<EOF
+(B[&date="2008"]:5)[&date="2003.000000"];
+((C[&date="2010"]:3,D[&date="2011"]:4)[&date="2007"]:4)[&date="2003.000000"];
+EOF
+echo '(A[&date="2000"]:10,(B[&date="2008"]:6,(C[&date="2010"]:3,D[&date="2011"]:4)[&date="2007"]:5)[&date="2002"]:12)[&date="1990"];' | $GOTREE cut date --min-date 2003 --max-date 2020 > result
+diff -q -b expected result
+rm -f expected result
+
+cat > expected <<EOF
+(B[&date="2008"]:5)[&date="2003.000000"];
+EOF
+echo '(A[&date="2000"]:10,(B[&date="2008"]:6,(C[&date="2010"]:3,D[&date="2011"]:4)[&date="2007"]:5)[&date="2002"]:12)[&date="1990"];' | $GOTREE cut date --min-date 2003 --max-date 2009 > result
+diff -q -b expected result
+rm -f expected result