add FeatureList IO support for TSV/CSV

Author: trichter

pyproject.toml

@@ -46,6 +46,8 @@ genbank = "sugar._io.genbank"
 blast = "sugar._io.tab.blast"
 mmseqs = "sugar._io.tab.mmseqs"
 infernal = "sugar._io.tab.infernal"
+tsv = "sugar._io.tab.tsv"
+csv = "sugar._io.tab.tsv"
 
 [build-system]
 requires = ["setuptools>=61.0"]

sugar/_io/fasta.py

@@ -8,7 +8,7 @@
 from sugar._io.util import _add_fmt_doc
 
 
-filename_extensions = ['fasta', 'fa']
+filename_extensions_fasta = ['fasta', 'fa']
 
 def is_fasta(f, **kw):
     content = f.read(50)

sugar/_io/gff.py

@@ -13,8 +13,8 @@
 from sugar._io.util import _add_fmt_doc
 
 
-filename_extensions = ['gff']
-filename_extensions_fts = ['gff']
+filename_extensions_gff = ['gff']
+filename_extensions_fts_gff = ['gff']
 
 
 def is_gff(f, **kw):

sugar/_io/main.py

@@ -93,8 +93,8 @@ def detect_ext(fname, what='seqs'):
         return
     for fmt in FMTS_ALL[what]:
         module = EPS[what][fmt].load()
-        if hasattr(module, 'filename_extensions' + suf):
-            if ext in getattr(module, 'filename_extensions' + suf):
+        if hasattr(module, f'filename_extensions{suf}_{fmt}'):
+            if ext in getattr(module, f'filename_extensions{suf}_{fmt}'):
                 return fmt
 
 

sugar/_io/sjson.py

@@ -18,7 +18,7 @@
          BioBasket, BioSeq
          )
 
-filename_extensions = ['sjson', 'json']
+filename_extensions_sjson = ['sjson', 'json']
 COMMENT = f'sugar JSON format written by sugar v{__version__}'
 
 

sugar/_io/stockholm.py

@@ -10,7 +10,7 @@
 from sugar._io.util import _add_fmt_doc
 
 
-filename_extensions = ['stk', 'sto', 'stockholm']
+filename_extensions_stockholm = ['stk', 'sto', 'stockholm']
 
 
 def is_stockholm(f, **kw):

sugar/_io/util.py

@@ -7,7 +7,7 @@
 
 
 FMTS = {'seqs': ['fasta', 'genbank', 'stockholm', 'gff', 'sjson'],
-        'fts': ['gff', 'genbank', 'infernal', 'mmseqs', 'blast']}
+        'fts': ['gff', 'genbank', 'infernal', 'mmseqs', 'blast', 'tsv', 'csv']}
 
 
 def _epsname_key(epsname, what='seqs'):

sugar/core/fts.py

@@ -418,6 +418,23 @@ def __init__(self, data=None):
             data = data.data
         super().__init__(data)
 
+    @classmethod
+    def frompandas(cls, df, ftype=None):
+        if ftype is not None and 'type' not in df:
+            if ftype in df:
+                df['type'] = df[ftype]
+            else:
+                df['type'] = ftype
+        fts = []
+        for rec in df.to_dict('records'):
+            loc = Location(rec.pop('start'),
+                           rec.pop('stop'),
+                           strand=rec.pop('strand', '+'),
+                           defect=rec.pop('defect', Defect.NONE))
+            ft = Feature(locs=[loc], meta=rec)
+            fts.append(ft)
+        return cls(fts)
+
     def __str__(self):
         return self.tostr()
 

sugar/tests/data/fts_example.csv

@@ -0,0 +1,20 @@
+type,start,stop,strand
+region,0,108689991,+
+pseudogene,43129,43626,-
+exon,43129,43626,-
+gene,61869,98682,+
+mRNA,61869,98682,+
+exon,61869,62065,+
+exon,75477,75526,+
+exon,76998,77025,+
+exon,80391,80417,+
+exon,82620,82717,+
+exon,83974,84123,+
+exon,86529,86621,+
+exon,88006,88135,+
+exon,96921,98682,+
+CDS,61943,97199,+
+cDNA_match,101888622,101892867,-
+cDNA_match,103140200,103170945,-
+cDNA_match,103944892,103952028,-
+cDNA_match,107859806,107862198,-

sugar/tests/data/fts_example.tsv

@@ -0,0 +1,20 @@
+type	start	stop	strand
+region	0	108689991	+
+pseudogene	43129	43626	-
+exon	43129	43626	-
+gene	61869	98682	+
+mRNA	61869	98682	+
+exon	61869	62065	+
+exon	75477	75526	+
+exon	76998	77025	+
+exon	80391	80417	+
+exon	82620	82717	+
+exon	83974	84123	+
+exon	86529	86621	+
+exon	88006	88135	+
+exon	96921	98682	+
+CDS	61943	97199	+
+cDNA_match	101888622	101892867	-
+cDNA_match	103140200	103170945	-
+cDNA_match	103944892	103952028	-
+cDNA_match	107859806	107862198	-