From a88cf5716ae0e1f4768be5b9c8ccd7abfc602615 Mon Sep 17 00:00:00 2001 From: Xirtid Nepla Date: Tue, 25 Mar 2025 10:38:14 +0000 Subject: [PATCH] Add support for lower/mixed case FASTA --- deepsp_predictor.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/deepsp_predictor.py b/deepsp_predictor.py index 913609b..a9d98b5 100644 --- a/deepsp_predictor.py +++ b/deepsp_predictor.py @@ -165,6 +165,7 @@ def load_input_data(filename): # One Hot Encoding of Aligned Sequence def one_hot_encoder(s): + s = s.upper() d = {'A': 0, 'C': 1, 'D': 2, 'E': 3, 'F': 4, 'G': 5, 'H': 6, 'I': 7, 'K': 8, 'L': 9, 'M': 10, 'N': 11, 'P': 12, 'Q': 13, 'R': 14, 'S': 15, 'T': 16, 'V': 17, 'W': 18, 'Y': 19, '-': 20} x = np.zeros((len(d), len(s))) @@ -212,4 +213,4 @@ def one_hot_encoder(s): 'SCM_neg_CDRH1','SCM_neg_CDRH2','SCM_neg_CDRH3','SCM_neg_CDRL1','SCM_neg_CDRL2','SCM_neg_CDRL3','SCM_neg_CDR','SCM_neg_Hv','SCM_neg_Lv','SCM_neg_Fv', 'SCM_pos_CDRH1','SCM_pos_CDRH2','SCM_pos_CDRH3','SCM_pos_CDRL1','SCM_pos_CDRL2','SCM_pos_CDRL3','SCM_pos_CDR','SCM_pos_Hv','SCM_pos_Lv','SCM_pos_Fv'] df = pd.concat([pd.DataFrame(name_list), pd.DataFrame(sap_pos), pd.DataFrame(scm_neg), pd.DataFrame(scm_pos)], ignore_index=True, axis=1,); df.columns = features -df.to_csv('DeepSP_descriptors.csv', index=False) \ No newline at end of file +df.to_csv('DeepSP_descriptors.csv', index=False)