Merge branch 'main' into use-metadata-params-for-submission

proteobench/io/params/alphapept.py

@@ -0,0 +1,49 @@
+"""Alphapept uses the yaml format to save configuration."""
+import pathlib
+
+import pandas as pd
+import yaml
+
+from proteobench.io.params import ProteoBenchParameters
+
+
+def extract_params(fname) -> ProteoBenchParameters:
+    with open(fname) as f:
+        record = yaml.safe_load(f)
+    summary = record["summary"]
+    params = ProteoBenchParameters()
+    params.software_name = "AlphaPept"
+    params.software_version = summary["version"]
+    params.search_engine = params.software_name
+    params.search_engine_version = params.software_version
+    fasta = record["fasta"]
+    params.enzyme = fasta["protease"]
+    params.allowed_miscleavages = fasta["n_missed_cleavages"]
+    params.fixed_mods = ",".join(fasta["mods_fixed"])
+    params.variable_mods = ",".join(fasta["mods_variable"])
+    params.max_mods = fasta["n_modifications_max"]
+    params.min_peptide_length = fasta["pep_length_min"]
+    params.max_peptide_length = fasta["pep_length_max"]
+    search = record["search"]
+    params.precursor_mass_tolerance = search["prec_tol"]
+    params.fragment_mass_tolerance = search["frag_tol"]
+    params.ident_fdr_protein = search["protein_fdr"]
+    params.ident_fdr_peptide = search["peptide_fdr"]
+    # params.ident_fdr_psm = search
+    params.min_precursor_charge = record["features"]["iso_charge_min"]
+    params.max_precursor_charge = record["features"]["iso_charge_max"]
+    params.enable_match_between_runs = record["workflow"]["match"]  # ! check
+
+    return params
+
+
+if __name__ == "__main__":
+    for fname in [
+        "../../../test/params/alphapept_0.4.9.yaml",
+        "../../../test/params/alphapept_0.4.9_unnormalized.yaml",
+    ]:
+        file = pathlib.Path(fname)
+        params = extract_params(file)
+        data_dict = params.__dict__
+        series = pd.Series(data_dict)
+        series.to_csv(file.with_suffix(".csv"))

proteobench/io/params/proline.py

@@ -87,7 +87,15 @@ def extract_params(fname) -> ProteoBenchParameters:
 
 
 if __name__ == "__main__":
-    file = pathlib.Path("test/params/Proline_example_w_Mascot_wo_proteinSets.xlsx")
+    file = pathlib.Path(
+        "../../../test/params/Proline_example_w_Mascot_wo_proteinSets.xlsx"
+    )
+    params = extract_params(file)
+    data_dict = params.__dict__
+    series = pd.Series(data_dict)
+    series.to_csv(file.with_suffix(".csv"))
+
+    file = pathlib.Path("../../../test/params/Proline_example_2.xlsx")
     params = extract_params(file)
     data_dict = params.__dict__
     series = pd.Series(data_dict)

test/params/Proline_example_2.csv

@@ -0,0 +1,20 @@
+,0
+software_name,Proline
+software_version,X! Tandem Vengeance (2015.12.15.2)
+search_engine,XTandem
+search_engine_version,
+ident_fdr_psm,1
+ident_fdr_peptide,
+ident_fdr_protein,
+enable_match_between_runs,False
+precursor_mass_tolerance,10.0 ppm
+fragment_mass_tolerance,0.02 Da
+enzyme,Trypsin
+allowed_miscleavages,2
+min_peptide_length,7
+max_peptide_length,
+fixed_mods,Carbamidomethyl (C)
+variable_mods,Acetyl (Protein N-term); Gln->pyro-Glu (Any N-term Q); Ammonia-loss (Any N-term C); Glu->pyro-Glu (Any N-term E); Oxidation (M)
+max_mods,
+min_precursor_charge,
+max_precursor_charge,

test/params/alphapept_0.4.9.csv

@@ -0,0 +1,20 @@
+,0
+software_name,AlphaPept
+software_version,0.4.9
+search_engine,AlphaPept
+search_engine_version,0.4.9
+ident_fdr_psm,
+ident_fdr_peptide,0.01
+ident_fdr_protein,0.01
+enable_match_between_runs,False
+precursor_mass_tolerance,20
+fragment_mass_tolerance,50
+enzyme,trypsin
+allowed_miscleavages,2
+min_peptide_length,7
+max_peptide_length,27
+fixed_mods,cC
+variable_mods,oxM
+max_mods,3
+min_precursor_charge,1
+max_precursor_charge,6