Merge pull request #437 from Proteobench/spectronaut_params

Spectronaut params

proteobench/io/params/spectronaut.py

@@ -0,0 +1,79 @@
+import re
+import pandas as pd
+from proteobench.io.params import ProteoBenchParameters
+from pathlib import Path
+
+
+def clean_text(text):
+    text = re.sub(r"^[\s:,\t]+|[\s:,\t]+$", "", text)
+    return text
+
+
+def extract_value(lines, search_term):
+    return next((clean_text(line.split(search_term)[1]) for line in lines if search_term in line), None)
+
+
+def extract_mass_tolerance(lines, search_term):
+    value = next((clean_text(line.split(search_term)[1]) for line in lines if search_term in line), None)
+    value = "40ppm" if value == "System Default" else value
+    return value
+
+
+def extract_value_regex(lines, search_term):
+    return next((clean_text(re.split(search_term, line)[1]) for line in lines if re.search(search_term, line)), None)
+
+
+def read_spectronaut_settings(file_path) -> ProteoBenchParameters:
+    # check if file exists
+    try:
+        # Read in the log file
+        with open(file_path) as f:
+            lines = f.readlines()
+    except:
+        lines = [l for l in file_path.read().decode("utf-8").splitlines()]
+
+    # Remove any trailing newline characters from each line
+    lines = [line.strip() for line in lines]
+
+    params = ProteoBenchParameters()
+    params.software_name = "Spectronaut"
+    params.software_version = lines[0].split()[1]
+    params.search_engine = "Spectronaut"
+    params.search_engine_version = params.software_version
+
+    lines = [re.sub(r"^[\s│├─└]*", "", line).strip() for line in lines]
+
+    params.ident_fdr_psm = extract_value(lines, "Precursor Qvalue Cutoff:")
+    params.ident_fdr_peptide = None
+    params.ident_fdr_protein = extract_value(lines, "Protein Qvalue Cutoff (Experiment):")
+    params.enable_match_between_runs = None
+    params.precursor_mass_tolerance = extract_mass_tolerance(lines, "MS1 Mass Tolerance Strategy:")
+    params.fragment_mass_tolerance = extract_mass_tolerance(lines, "MS2 Mass Tolerance Strategy:")
+    params.enzyme = extract_value(lines, "Enzymes / Cleavage Rules:")
+    params.allowed_miscleavages = extract_value(lines, "Missed Cleavages:")
+    params.max_peptide_length = extract_value(lines, "Max Peptide Length:")
+    params.min_peptide_length = extract_value(lines, "Min Peptide Length:")
+    params.fixed_mods = extract_value(lines, "Fixed Modifications:")
+    params.variable_mods = extract_value_regex(lines, "^Variable Modifications:")
+    params.max_mods = extract_value(lines, "Max Variable Modifications:")
+    params.min_precursor_charge = extract_value(lines, "Peptide Charge:")
+    params.max_precursor_charge = extract_value(lines, "Peptide Charge:")
+    params.scan_window = extract_value(lines, "XIC IM Extraction Window:")
+    params.quantification_method = extract_value(
+        lines, "Quantity MS Level:"
+    )  # "Quantity MS Level:" or "Protein LFQ Method:" or "Quantity Type:"
+    params.second_pass = extract_value(lines, "directDIA Workflow:")
+    params.protein_inference = extract_value(lines, "Inference Algorithm:")  # or Protein Inference Workflow:
+    params.predictors_library = extract_value(lines, "Hybrid (DDA + DIA) Library").replace(":", "").strip()
+
+    return params
+
+
+if __name__ == "__main__":
+    fnames = ["../../../test/params/spectronaut_Experiment1_ExperimentSetupOverview_BGS_Factory_Settings.txt"]
+
+    for file in fnames:
+        parameters = read_spectronaut_settings(file)
+        actual = pd.Series(parameters.__dict__)
+        actual.to_csv(Path(file).with_suffix(".csv"))
+        print(parameters)

proteobench/modules/quant_base/quant_base_module.py

@@ -19,6 +19,7 @@
 from proteobench.io.params.alphadia import extract_params as extract_params_alphadia
 from proteobench.io.params.alphapept import extract_params as extract_params_alphapept
 from proteobench.io.params.diann import extract_params as extract_params_diann
+from proteobench.io.params.spectronaut import read_spectronaut_settings as extract_params_spectronaut
 from proteobench.io.params.fragger import extract_params as extract_params_fragger
 from proteobench.io.params.i2masschroq import (
     extract_params as extract_params_i2masschroq,
@@ -74,7 +75,7 @@ def __init__(self, token: str = None, proteobench_repo_name: str = "", proteobot
         "AlphaDIA": extract_params_alphadia,
         "FragPipe (DIA-NN quant)": extract_params_fragger,
         "MSAID": extract_params_msaid,
-        # "Spectronaut": extract_params_spectronaut
+        "Spectronaut": extract_params_spectronaut,
     }
 
     def is_implemented(self) -> bool:

test/params/spectronaut_Experiment1_ExperimentSetupOverview_BGS_Factory_Settings.csv

@@ -0,0 +1,25 @@
+,0
+software_name,Spectronaut
+software_version,19.2.240905.62635
+search_engine,Spectronaut
+search_engine_version,19.2.240905.62635
+ident_fdr_psm,0.01
+ident_fdr_peptide,
+ident_fdr_protein,0.01
+enable_match_between_runs,
+precursor_mass_tolerance,40ppm
+fragment_mass_tolerance,40ppm
+enzyme,Trypsin/P
+allowed_miscleavages,2
+min_peptide_length,7
+max_peptide_length,52
+fixed_mods,Carbamidomethyl (C)
+variable_mods,"Acetyl (Protein N-term), Oxidation (M)"
+max_mods,5
+min_precursor_charge,False
+max_precursor_charge,False
+scan_window,Dynamic
+quantification_method,MS2
+second_pass,directDIA+ (Deep)
+protein_inference,IDPicker
+predictors_library,False