Skip sequences shorter than 4 nucleotides

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "rnasamba"
-version = "0.2.3"
+version = "0.2.4"
 authors = ["Antonio Camargo <[email protected]>"]
 edition = "2018"
 

Dockerfile

@@ -5,7 +5,7 @@ RUN pip install --no-cache-dir \
     'biopython==1.74' \
     'keras==2.2.5' \
     'numpy==1.16.5' \
-    'rnasamba==0.2.3' \
+    'rnasamba==0.2.4' \
     'tensorflow==1.14.0'
 
 VOLUME ["/app"]

rnasamba/cli.py

@@ -48,7 +48,7 @@ def train(args):
 
 
 def classify_cli(parser):
-    parser.add_argument('--version', action='version', version='%(prog)s 0.2.3')
+    parser.add_argument('--version', action='version', version='%(prog)s 0.2.4')
     parser.set_defaults(func=classify)
     parser.add_argument(
         'output_file',
@@ -79,7 +79,7 @@ def classify_cli(parser):
 
 def train_cli(parser):
     parser.set_defaults(func=train)
-    parser.add_argument('--version', action='version', version='%(prog)s 0.2.3')
+    parser.add_argument('--version', action='version', version='%(prog)s 0.2.4')
     parser.add_argument(
         'output_file',
         help='output HDF5 file containing weights of the newly trained RNAsamba network.',
@@ -128,7 +128,7 @@ def cli():
         description='Coding potential calculation using deep learning.',
         formatter_class=argparse.ArgumentDefaultsHelpFormatter,
     )
-    parser.add_argument('--version', action='version', version='%(prog)s 0.2.3')
+    parser.add_argument('--version', action='version', version='%(prog)s 0.2.4')
     subparsers = parser.add_subparsers()
     classify_parser = subparsers.add_parser(
         'classify',

rnasamba/core/sequences.py

@@ -33,10 +33,13 @@ def read_fasta(filename):
     with open(filename) as handle:
         for record in SeqIO.parse(handle, 'fasta'):
             sequence_str = str(record.seq).upper().replace('U', 'T')
-            sequence_name = record.description
-            seqs.append(sequence_str)
-            seqs_tokenized.append(tokenize_dna(sequence_str))
-            seqs_names.append(sequence_name)
+            if len(sequence_str) < 4:
+                continue
+            else:
+                sequence_name = record.description
+                seqs.append(sequence_str)
+                seqs_tokenized.append(tokenize_dna(sequence_str))
+                seqs_names.append(sequence_name)
     return seqs, seqs_tokenized, seqs_names
 
 

setup.py

@@ -24,7 +24,7 @@
 
 setup(
     name='rnasamba',
-    version='0.2.3',
+    version='0.2.4',
     packages=find_packages(),
     rust_extensions=[
         RustExtension('rnasamba.core.kmer', debug=False),