diff --git a/proteobench/io/parsing/io_parse_settings/parse_settings_fragpipe.toml b/proteobench/io/parsing/io_parse_settings/parse_settings_fragpipe.toml index 38e64e5e..883d52e4 100644 --- a/proteobench/io/parsing/io_parse_settings/parse_settings_fragpipe.toml +++ b/proteobench/io/parsing/io_parse_settings/parse_settings_fragpipe.toml @@ -29,7 +29,7 @@ "before_aa" = false "isalpha" = true "isupper" = true -"pattern"="\\[([^]]+)\\]" +"pattern"="(?<=\\[).+?(?=\\])" "modification_dict" = {"57.0215" = "Carbamidomethyl", "57.0216" = "Carbamidomethyl", "15.9949" = "Oxidation", "-17.026548" = "Gln->pyro-Glu", "-18.010565" = "Glu->pyro-Glu", "42.0106" = "Acetyl"} [general] diff --git a/proteobench/io/parsing/io_parse_settings/parse_settings_sage.toml b/proteobench/io/parsing/io_parse_settings/parse_settings_sage.toml index 1ca587cd..cdd48c4a 100644 --- a/proteobench/io/parsing/io_parse_settings/parse_settings_sage.toml +++ b/proteobench/io/parsing/io_parse_settings/parse_settings_sage.toml @@ -29,7 +29,7 @@ "before_aa" = false "isalpha" = true "isupper" = true -"pattern"="\\[([^]]+)\\]" +"pattern"="(?<=\\[).+?(?=\\])" "modification_dict" = {"+57.0215" = "Carbamidomethyl", "+15.9949" = "Oxidation", "-17.026548" = "Gln->pyro-Glu", "-18.010565" = "Glu->pyro-Glu", "+42" = "Acetyl"} [general] diff --git a/proteobench/io/parsing/parse_ion.py b/proteobench/io/parsing/parse_ion.py index 52835edc..80dfcabd 100644 --- a/proteobench/io/parsing/parse_ion.py +++ b/proteobench/io/parsing/parse_ion.py @@ -13,7 +13,7 @@ def load_input_file(input_csv: str, input_format: str) -> pd.DataFrame: if input_format == "MaxQuant": input_data_frame = pd.read_csv(input_csv, sep="\t", low_memory=False) elif input_format == "AlphaPept": - input_data_frame = pd.read_csv(input_csv, low_memory=False) + input_data_frame = pd.read_csv(input_csv, low_memory=False, dtype={"charge": int}) elif input_format == "Sage": input_data_frame = pd.read_csv(input_csv, sep="\t", low_memory=False) elif input_format == "FragPipe":