Remove N channel (187c214b) · Commits · 钟慕尧 / deepchem

deepchem/data/data_loader.py

+3 −3

Original line number	Diff line number	Diff line
		@@ -905,12 +905,12 @@ class FASTALoader(DataLoader):
		'Y', 'Z', '*', '-'),
		"nucleic": ('A', 'C', 'G', 'T', 'U', '(i)', 'R', 'Y', 'K', 'M', 'S', 'W',
		'B', 'D', 'H', 'V', 'N', '-'),
		"ATCGN": ('A', 'T', 'C', 'G', 'N')
		"ATCGN": ('A', 'T', 'C', 'G')
		}
		try:
		self.charset = charsets[charset]
		except KeyError:
		if (featurizer == OneHotFeaturizer):
		if (featurizer == OneHotFeaturizer): # TODO EXPLICITLY CHECK IF FEATURIZER USES CHARSET
		logger.exception("charset is invalid. charset must be 'protein', 'nucleic', or 'ATCGN'.")
		else:
		logger.warning("charset is invalid, ignoring...")
		@@ -919,7 +919,7 @@ class FASTALoader(DataLoader):
		if isinstance(featurizer, UserDefinedFeaturizer):
		self.user_specified_features = featurizer.feature_fields

		featurizer = featurizer(charset = self.charset, max_length = max_length)
		featurizer = featurizer(charset = self.charset, max_length = max_length) # TODO EXPLICITLY CHECK IF MAX_LENGTH IS DESIRED
		self.featurizer = featurizer

		def create_dataset(self,

+1 −1

Original line number	Diff line number	Diff line
		@@ -30,4 +30,4 @@ class TestFASTALoader(unittest.TestCase):
		if legacy:
		assert sequences.X.shape == (3, 5, 58, 1)
		else:
		assert sequences.X.shape == (3, 58, 6)
		assert sequences.X.shape == (3, 58, 5)