added seed length

docs/api_reference.rst

@@ -39,7 +39,7 @@ pytrf.STRFinder
 
 	.. py:method:: as_list()
 
-		Put all SSRs in a list and return, each SSR in list has 7 columns including [sequence name, start position, end position, motif sequence, motif length, repeats, SSR length]
+		Put all SSRs in a list and return, each SSR in list has 7 columns including [sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length]
 
 		:return: all SSRs found
 
@@ -68,7 +68,7 @@ pytrf.GTRFinder
 
 	.. py:method:: as_list()
 
-		Put all GTRs in a list and return, each GTR in list has 7 columns including [sequence name, start position, end position, motif sequence, motif length, repeats, GTR length]
+		Put all GTRs in a list and return, each GTR in list has 7 columns including [sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length]
 
 		:return: all GTRs found
 
@@ -103,7 +103,7 @@ pytrf.ATRFinder
 
 	.. py:method:: as_list()
 
-		Put all ATRs in a list and return, each ATR in list has 14 columns including [sequence name, seed start position, seed end position, motif sequence, motif length, seed repeat, ATR start position, ATR end position, ATR repeat, ATR length, extend matches, extend substitutions, extend insertions, extend deletions, extend identity]
+		Put all ATRs in a list and return, each ATR in list has 16 columns including [sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length, seed start position, seed end position, seed repeat, seed length, extend matches, extend substitutions, extend insertions, extend deletions, extend identity]
 
 pytrf.ETR
 ---------
@@ -146,7 +146,7 @@ pytrf.ETR
 
 	.. py:method:: as_list()
 
-		convert ETR object to a list
+		convert ETR object to a list, [sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length]
 
 	.. py:method:: as_dict()
 
@@ -158,7 +158,7 @@ pytrf.ETR
 
 	.. py:method:: as_string(separator='\t', terminator='')
 
-		convert ETR object to a TSV or CSV string by using separator and terminator
+		convert ETR object to a TSV or CSV string by using separator and terminator, columns: sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length
 
 		:param str separator: a separator between columns
 
@@ -241,7 +241,7 @@ pytrf.ATR
 
 	.. py:method:: as_list()
 
-		convert ATR object to a list
+		convert ATR object to a list, [sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length, seed start position, seed end position, seed repeat, seed length, extend matches, extend substitutions, extend insertions, extend deletions, extend identity]
 
 	.. py:method:: as_dict()
 
@@ -253,7 +253,7 @@ pytrf.ATR
 
 	.. py:method:: as_string(separator='\t', terminator='')
 
-		convert ATR object to a TSV or CSV string by using separator and terminator
+		convert ATR object to a TSV or CSV string by using separator and terminator, columns: sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length, seed start position, seed end position, seed repeat, seed length, extend matches, extend substitutions, extend insertions, extend deletions, extend identity
 
 		:param str separator: a separator between columns
 

docs/changelog.rst

@@ -1,9 +1,11 @@
 Changelog
 =========
 
-Version 1.3.4 (2024-12-06)
+Version 1.4.0 (2024-12-06)
 --------------------------
 
+- Added seed length to ATR object
+- Changed the output column order of findatr
 - Fixed tandem repeat overlap
 - Fixed wraparound backtrace error
 

docs/usage.rst

@@ -269,10 +269,12 @@ Find exact microsatellites or simple sequence repeats (SSRs) from fasta/q file.
 	options:
 	  -h, --help            show this help message and exit
 	  -o , --out-file       output file (default: stdout)
-	  -f , --out-format     output format, tsv, csv or gff (default: tsv)
+	  -f , --out-format     output format, tsv, csv, bed or gff (default: tsv)
 	  -r mono di tri tetra penta hexa, --repeats mono di tri tetra penta hexa
 	                        minimum repeats for each STR type (default: 12 7 5 4 4 4)
 
+The columns in findstr tsv, csv, bed output file: sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length.
+
 Find exact generic tandem repeats (GTRs) from fasta/q file.
 
 .. code:: sh
@@ -293,6 +295,8 @@ Find exact generic tandem repeats (GTRs) from fasta/q file.
 	  -r , --min-repeat   minimum repeat number (default: 3)
 	  -l , --min-length   minimum repeat length (default: 10)
 
+The columns in findgtr tsv, csv, bed output file: sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length.
+
 Find imperfect or approximate tandem repeats (ATRs)
 
 .. code:: sh
@@ -322,6 +326,8 @@ Find imperfect or approximate tandem repeats (ATRs)
 	  -x , --max-extend-length
 	                        maximum length allowed to extend (default: 2000)
 
+The columns in findatr tsv, csv, bed output file: sequence or chromosome name, start position, end position, motif sequence, motif length, repeat number, repeat length, seed start position, seed end position, seed repeat number, seed length, number of matches, number of substitutions, number of insertions, number of deletions, extend alignment identity between imperfect repeat and its perfect counterpart.
+
 Extract tandem repeat sequence and flanking sequence according results of findatr, findgtr or findstr.
 
 .. code:: sh

pytrfcli.py

@@ -242,7 +242,7 @@ def main():
 		default = 70,
 		metavar = '',
 		type = float,
-		help = "minimum identity from 0 to 100 (default: 70)"
+		help = "minimum identity for extending, 0 to 100 (default: 70)"
 	)
 
 	parser_atrfinder.add_argument('-x', '--max-extend',

src/atr.c

@@ -18,17 +18,18 @@ static PyObject* pytrf_atr_repr(pytrf_ATR *self) {
 }
 
 static PyObject* pytrf_atr_as_list(pytrf_ATR *self) {
-	return Py_BuildValue("OnnOiinnfiiiiif", self->seqid, self->sstart, self->send, self->motif,
-						self->mlen, self->srepeat, self->start, self->end, self->repeat,
-						self->length, self->matches, self->substitutions, self->insertions,
+	return Py_BuildValue("OnnOiiinnfiiiiif", self->seqid, self->start, self->end, self->motif,
+						self->mlen, self->repeat, self->length, self->sstart, self->send,
+						self->srepeat, self->slen, self->matches, self->substitutions, self->insertions,
 						self->deletions, self->identity);
 }
 
 static PyObject* pytrf_atr_as_dict(pytrf_ATR *self) {
-	return Py_BuildValue("{s:O,s:n,s:n,s:O,s:i,s:n,s:n,s:i,s:f,s:i,s:i,s:i,s:i,s:i,s:f}", "chrom", self->seqid,
-						"start", self->start, "end", self->end, "motif", self->motif, "type", self->mlen,
-						"seed_start", self->sstart, "seed_end", self->send, "seed_repeat", self->srepeat,
-						"repeat", self->repeat, "length", self->length, "matches", self->matches,
+	return Py_BuildValue("{s:O,s:n,s:n,s:O,s:i,s:f,s:i,s:n,s:n,s:i,s:i,s:i,s:i,s:i,s:i,s:f}",
+						"chrom", self->seqid, "start", self->start, "end", self->end,
+						"motif", self->motif, "type", self->mlen, "repeat", self->repeat,
+						"length", self->length, "seed_start", self->sstart, "seed_end", self->send,
+						"seed_repeat", self->srepeat, "seed_length", self->slen ,"matches", self->matches,
 						"substitutions", self->substitutions, "insertions", self->insertions,
 						"deletions", self->deletions, "identity", self->identity);
 }
@@ -72,12 +73,13 @@ static PyObject* pytrf_atr_as_string(pytrf_ATR *self, PyObject *args, PyObject *
 
 	percent = PyFloat_FromDouble(self->identity);
 	repeat = PyFloat_FromDouble(self->repeat);
-	retval = PyUnicode_FromFormat("%S%s%zd%s%zd%s%S%s%d%s%d%s%zd%s%zd%s%S%s%d%s%d%s%d%s%d%s%d%s%S%s",
-								self->seqid, separator, self->sstart, separator, self->send, separator,
-								self->motif, separator, self->mlen, separator, self->srepeat, separator,
-								self->start, separator, self->end, separator, repeat, separator, 
-								self->length, separator, self->matches, separator, self->substitutions, separator,
-								self->insertions, separator, self->deletions, separator, percent, terminator);
+	retval = PyUnicode_FromFormat("%S%s%zd%s%zd%s%S%s%d%s%S%s%d%s%zd%s%zd%s%d%s%d%s%d%s%d%s%d%s%d%s%S%s",
+								self->seqid, separator, self->start, separator, self->end, separator,
+								self->motif, separator, self->mlen, separator, repeat, separator,
+								self->length, separator, self->sstart, separator, self->send, separator,
+								self->srepeat, separator, self->slen, separator, self->matches, separator,
+								self->substitutions, separator, self->insertions, separator, self->deletions,
+								separator, percent, terminator);
 	Py_DECREF(percent);
 	Py_DECREF(repeat);
 	return retval;
@@ -108,7 +110,8 @@ static PyMemberDef pytrf_atr_members[] = {
 	{"type", T_INT, offsetof(pytrf_ATR, mlen), READONLY},
 	{"seed_start", T_PYSSIZET, offsetof(pytrf_ATR, sstart), READONLY},
 	{"seed_end", T_PYSSIZET, offsetof(pytrf_ATR, send), READONLY},
-	{"seed_repeat", T_PYSSIZET, offsetof(pytrf_ATR, repeat), READONLY},
+	{"seed_repeat", T_INT, offsetof(pytrf_ATR, repeat), READONLY},
+	{"seed_length", T_INT, offsetof(pytrf_ATR, slen), READONLY},
 	{"repeat", T_FLOAT, offsetof(pytrf_ATR, repeat), READONLY},
 	{"length", T_INT, offsetof(pytrf_ATR, length), READONLY},
 	{"matches", T_INT, offsetof(pytrf_ATR, matches), READONLY},

src/atr.h

@@ -35,6 +35,9 @@ typedef struct {
 	//seed repeats
 	int srepeat;
 
+	//seed length
+	int slen;
+
 	//motif length
 	int mlen;
 

src/itr.c

@@ -491,6 +491,7 @@ static PyObject* pytrf_itrfinder_next(pytrf_ITRFinder *self) {
 					atr->sstart = seed_start + 1;
 					atr->send = seed_end + 1;
 					atr->srepeat = seed_repeat;
+					atr->slen = seed_length;
 					atr->repeat = tandem_length * 1.0 / j;
 					atr->length = tandem_length;
 					atr->matches = tandem_match;
@@ -612,9 +613,10 @@ static PyObject* pytrf_itrfinder_as_list(pytrf_ITRFinder *self) {
 				tandem_repeat = tandem_length * 1.0 / j;
 
 				if (tandem_identity >= self->min_identity) {
-					tmp = Py_BuildValue("Onnsiinnfiiiiif", self->seqname, seed_start + 1, seed_end + 1, self->motif,
-										j, seed_repeat, tandem_start, tandem_end, tandem_repeat, tandem_length, tandem_match,
-										tandem_substitute, tandem_insert, tandem_delete, tandem_identity);
+					tmp = Py_BuildValue("Onnsifinniiiiiif", self->seqname, tandem_start, tandem_end, self->motif, j,
+										tandem_repeat, tandem_length, seed_start + 1, seed_end + 1, seed_repeat,
+										seed_length, tandem_match, tandem_substitute, tandem_insert, tandem_delete,
+										tandem_identity);
 
 					PyList_Append(itrs, tmp);
 					Py_DECREF(tmp);