Skip to content

Commit

Permalink
BiblioSpec pepXML check base_name parent path (#2809)
Browse files Browse the repository at this point in the history 
* - fixed BiblioSpec pepXML reader to check for spectrum files in the base_name's parent path (if present)
  • Loading branch information
@chambm
chambm authored Dec 12, 2023
1 parent eb399e3 commit c25fa15
Show file tree
Hide file tree
Showing 7 changed files with 1,878 additions and 14 deletions.
23 changes: 17 additions & 6 deletions pwiz_tools/BiblioSpec/src/BuildParser.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -92,15 +92,26 @@ void BuildParser::setSpecFileName(

curSpecFileName_.clear();

string fileroot = specfileroot;
Verbosity::debug("checking for basename: %s", fileroot);
auto localDirectories = directories;
bal::replace_all(specfileroot, "\\", "/"); // attempt to make Windows paths parseable on POSIX

// if specfileroot has a parent path, try that directory first
bfs::path specfilepath(specfileroot);
if (specfilepath.has_parent_path() && bfs::exists(bfs::complete(specfilepath.parent_path(), filepath_)))
localDirectories.insert(localDirectories.begin(), specfilepath.parent_path().string());

string fileroot = specfilepath.filename().string();
Verbosity::debug("checking for basename: %s", fileroot.c_str());
do {
// try the location of the result file, then all dirs in the list
for(int i=-1; i<(int)directories.size(); i++) {
for(int i=-1; i<(int)localDirectories.size(); i++) {

string path = filepath_.c_str();
if( i >= 0 ) {
path += directories.at(i);
if (bfs::path(localDirectories[i]).is_absolute())
path = localDirectories[i];
else
path += localDirectories[i];
}
if (path.empty())
path = ".";
Expand Down Expand Up @@ -151,7 +162,7 @@ void BuildParser::setSpecFileName(

if( curSpecFileName_.empty() ) {
string extString = fileNotFoundMessage(specfileroot,
extensions, directories);
extensions, localDirectories);
throw BlibException(true, extString.c_str());
}// else we found a file and set the name

Expand Down Expand Up @@ -223,7 +234,7 @@ string BuildParser::filesNotFoundMessage(
messageString += "\n\nIn any of the following directories:\n" + bfs::canonical(deepestPath).make_preferred().string();
set<string> parentPaths;
for (const auto& dir : directories)
parentPaths.insert(bfs::canonical(deepestPath / dir).make_preferred().string());
parentPaths.insert((bfs::path(dir).is_absolute() ? dir : bfs::canonical(deepestPath / dir)).make_preferred().string());
for (const auto& dir : boost::make_iterator_range(parentPaths.rbegin(), parentPaths.rend()))
messageString += "\n" + dir;

Expand Down
8 changes: 0 additions & 8 deletions pwiz_tools/BiblioSpec/src/PepXMLreader.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -146,14 +146,6 @@ void PepXMLreader::startElement(const XML_Char* name, const XML_Char** attr)
} else if(isElement("msms_run_summary",name)) {
fileroot_ = getRequiredAttrValue("base_name",attr);
Verbosity::comment(V_DEBUG, "PepXML base_name is %s", fileroot_.c_str());
// Because Mascot2XML uses the full path for the base_name,
// only the part beyond the last "\" or "/" is taken.
size_t slash = fileroot_.rfind('/');
size_t bslash = fileroot_.rfind('\\');
if (slash == string::npos || (bslash != string::npos && bslash > slash))
slash = bslash;
if (slash != string::npos)
fileroot_.erase(0, slash + 1);

// Check if this pepXML file is from Proteome Discoverer
string rawType = getAttrValue("raw_data_type", attr);
Expand Down
4 changes: 4 additions & 0 deletions pwiz_tools/BiblioSpec/tests/Jamfile.jam
View file
Original file line number Diff line number Diff line change
Expand Up @@ -183,10 +183,12 @@ rule blib-test-search ( name : args * : output-name : reference-names + : inputs
if NT = $(.os)
{
.percent = "%%" ;
.slash = "\\" ;
}
else
{
.percent = "%" ;
.slash = "/" ;
}

# Add --unicode to optional arguments section to test that a format supports Unicode input paths
Expand Down Expand Up @@ -242,6 +244,8 @@ blib-test-build msfragger-tims : -o : output/msfragger-tims.blib : msfragger-tim
blib-test-build msfragger-thermo : -o : output/msfragger-thermo.blib : msfragger-thermo.check : $(TEST_INPUTS_PATH)/BSA_min_21.pepXML ;
blib-test-build peptideprophet-msfragger-thermo-mzml : -o : output/peptideprophet-msfragger-thermo-mzml.blib : peptideprophet-msfragger-thermo-mzml.check : $(TEST_INPUTS_PATH)/peptideprophet-msfragger-thermo-mzml.pep.xml ;
blib-test-build peptideprophet-msfragger-bruker-mgf : -o : output/peptideprophet-msfragger-bruker-mgf.blib : peptideprophet-msfragger-bruker-mgf.check : $(TEST_INPUTS_PATH)/peptideprophet-msfragger-bruker-mgf.pep.xml ;
blib-test-build-basic msfragger-check-parent-path-first : -o : $(TEST_INPUTS_PATH)/msfragger-check-parent-path-first.pepXML ;
blib-test-build-basic msfragger-check-parent-path-first-with-missing-file : -o -e@inputs$(.slash)msfragger-check-parent-path-first : $(TEST_INPUTS_PATH)/msfragger-check-parent-path-first-with-missing-file.pepXML ;

# Test other xml formats (idpicker, xtandem)

Expand Down
202 changes: 202 additions & 0 deletions ..._tools/BiblioSpec/tests/inputs/msfragger-check-parent-path-first-with-missing-file.pepXML
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,202 @@
<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="pepXML_std.xsl"?>
<msms_pipeline_analysis date="2019-11-21T15:49:59" xmlns="http://regis-web.systemsbiology.net/pepXML" summary_xml="d:\test\bruker\tims\msfragger-check-parent-path-first.pepXML" xsi:schemaLocation="http://sashimi.sourceforge.net/schema_revision/pepXML/pepXML_v118.xsd" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<msms_run_summary base_name="C:\dev\pwiz\pwiz_tools\BiblioSpec\tests\inputs\msfragger-check-parent-path-first\Hela%20QC_PASEF_missing_file" raw_data_type="raw" raw_data="mzBIN">
<sample_enzyme name="trypsin">
<specificity cut="KR" no_cut="P" sense="C"/>
</sample_enzyme>
<search_summary base_name="C:\dev\pwiz\pwiz_tools\BiblioSpec\tests\inputs\msfragger-check-parent-path-first\Hela%20QC_PASEF_missing_file" precursor_mass_type="monoisotopic" search_engine="X! Tandem" search_engine_version="MSFragger-2.2" fragment_mass_type="monoisotopic" search_id="1">
<search_database local_path="D:\oldD\fasta\20150928-RefSeq-human.protein.revCat.fasta" type="AA"/>
<enzymatic_search_constraint enzyme="default" min_number_termini="2" max_num_internal_cleavages="1"/>
<aminoacid_modification aminoacid="C" massdiff="57.0215" mass="160.0307" variable="N"/>
<aminoacid_modification aminoacid="M" massdiff="15.9949" mass="147.0354" variable="Y"/>
<terminal_modification massdiff="42.0106" protein_terminus="Y" mass="43.0184" terminus="N" variable="Y"/>
<parameter name="# MSFragger.build" value="MSFragger-2.2"/>
<parameter name="database_name" value="D:\oldD\fasta\20150928-RefSeq-human.protein.revCat.fasta"/>
<parameter name="decoy_prefix" value="XXX_"/>
<parameter name="num_threads" value="15"/>
<parameter name="precursor_mass_lower" value="-50.0"/>
<parameter name="precursor_mass_upper" value="50.0"/>
<parameter name="precursor_mass_units" value="1"/>
<parameter name="precursor_true_tolerance" value="20.0"/>
<parameter name="precursor_true_units" value="1"/>
<parameter name="fragment_mass_tolerance" value="20.0"/>
<parameter name="fragment_mass_units" value="1"/>
<parameter name="calibrate_mass" value="2"/>
<parameter name="write_calibrated_mgf" value="1"/>
<parameter name="isotope_error" value="0/1/2"/>
<parameter name="mass_offsets" value="0"/>
<parameter name="precursor_mass_mode" value="SELECTED"/>
<parameter name="localize_delta_mass" value="0"/>
<parameter name="intensity_transform" value="0"/>
<parameter name="remove_precursor_peak" value="1"/>
<parameter name="remove_precursor_range" value="-1.50,1.50"/>
<parameter name="delta_mass_exclude_ranges" value="(-1.5,3.5)"/>
<parameter name="fragment_ion_series" value="b,y"/>
<parameter name="search_enzyme_name" value="trypsin"/>
<parameter name="search_enzyme_cutafter" value="KR"/>
<parameter name="search_enzyme_butnotafter" value="P"/>
<parameter name="num_enzyme_termini" value="2"/>
<parameter name="allowed_missed_cleavage" value="1"/>
<parameter name="clip_nTerm_M" value="1"/>
<parameter name="allow_multiple_variable_mods_on_residue" value="0"/>
<parameter name="max_variable_mods_per_mod" value="3"/>
<parameter name="max_variable_mods_combinations" value="5000"/>
<parameter name="output_file_extension" value="pepXML"/>
<parameter name="output_format" value="pepXML"/>
<parameter name="output_report_topN" value="1"/>
<parameter name="output_max_expect" value="50.0"/>
<parameter name="report_alternative_proteins" value="0"/>
<parameter name="override_charge" value="0"/>
<parameter name="precursor_charge" value="1 4"/>
<parameter name="digest_min_length" value="7"/>
<parameter name="digest_max_length" value="50"/>
<parameter name="digest_mass_range" value="500.0 5000.0"/>
<parameter name="max_fragment_charge" value="2"/>
<parameter name="track_zero_topN" value="0"/>
<parameter name="zero_bin_accept_expect" value="0.0"/>
<parameter name="zero_bin_mult_expect" value="1.0"/>
<parameter name="add_topN_complementary" value="0"/>
<parameter name="minimum_peaks" value="15"/>
<parameter name="use_topN_peaks" value="200"/>
<parameter name="min_fragments_modelling" value="2"/>
<parameter name="min_matched_fragments" value="4"/>
<parameter name="minimum_ratio" value="0.0"/>
<parameter name="clear_mz_range" value="0.0 0.0"/>
<parameter name="excluded_scan_list_file" value=""/>
<parameter name="variable_mod_01" value="15.99490 M"/>
<parameter name="variable_mod_02" value="42.01060 [^"/>
<parameter name="add_A_alanine" value="0.000000"/>
<parameter name="add_B_user_amino_acid" value="0.000000"/>
<parameter name="add_C_cysteine" value="57.021464"/>
<parameter name="add_Cterm_peptide" value="0.0"/>
<parameter name="add_Cterm_protein" value="0.0"/>
<parameter name="add_D_aspartic_acid" value="0.000000"/>
<parameter name="add_E_glutamic_acid" value="0.000000"/>
<parameter name="add_F_phenylalanine" value="0.000000"/>
<parameter name="add_G_glycine" value="0.000000"/>
<parameter name="add_H_histidine" value="0.000000"/>
<parameter name="add_I_isoleucine" value="0.000000"/>
<parameter name="add_J_user_amino_acid" value="0.000000"/>
<parameter name="add_K_lysine" value="0.000000"/>
<parameter name="add_L_leucine" value="0.000000"/>
<parameter name="add_M_methionine" value="0.000000"/>
<parameter name="add_N_asparagine" value="0.000000"/>
<parameter name="add_Nterm_peptide" value="0.0"/>
<parameter name="add_Nterm_protein" value="0.0"/>
<parameter name="add_O_user_amino_acid" value="0.000000"/>
<parameter name="add_P_proline" value="0.000000"/>
<parameter name="add_Q_glutamine" value="0.000000"/>
<parameter name="add_R_arginine" value="0.000000"/>
<parameter name="add_S_serine" value="0.000000"/>
<parameter name="add_T_threonine" value="0.000000"/>
<parameter name="add_U_user_amino_acid" value="0.000000"/>
<parameter name="add_V_valine" value="0.000000"/>
<parameter name="add_W_tryptophan" value="0.000000"/>
<parameter name="add_X_user_amino_acid" value="0.000000"/>
<parameter name="add_Y_tyrosine" value="0.000000"/>
<parameter name="add_Z_user_amino_acid" value="0.000000"/>
</search_summary>
<spectrum_query start_scan="1" ion_mobility="1.2009081" assumed_charge="2" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.1.1.2" end_scan="1" index="1" precursor_neutral_mass="2317.9421" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="NTAAMVCSLENRDECLMCGS" massdiff="1.0156" calc_neutral_pep_mass="2316.9265" peptide_next_aa="-" num_missed_cleavages="1" num_tol_term="2" num_tot_proteins="1" tot_num_ions="38" hit_rank="1" num_matched_ions="12" protein="NP_001024.1" peptide_prev_aa="R" is_rejected="0">
<modification_info>
<mod_aminoacid_mass mass="160.0307" position="7"/>
<mod_aminoacid_mass mass="160.0307" position="15"/>
<mod_aminoacid_mass mass="160.0307" position="18"/>
</modification_info>
<search_score name="hyperscore" value="23.270"/>
<search_score name="nextscore" value="8.785"/>
<search_score name="expect" value="3.610e-04"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="2" ion_mobility="1.0267171" assumed_charge="2" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.2.2.2" end_scan="2" index="2" precursor_neutral_mass="1533.6818" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="EYTACELMNIYK" massdiff="-0.0026" calc_neutral_pep_mass="1533.6843" peptide_next_aa="T" num_missed_cleavages="0" num_tol_term="2" num_tot_proteins="1" tot_num_ions="22" hit_rank="1" num_matched_ions="8" protein="XP_006712233.1" peptide_prev_aa="K" is_rejected="0">
<modification_info>
<mod_aminoacid_mass mass="160.0307" position="5"/>
</modification_info>
<search_score name="hyperscore" value="16.791"/>
<search_score name="nextscore" value="8.503"/>
<search_score name="expect" value="1.690e-03"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="3" ion_mobility="0.85685045" assumed_charge="3" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.3.3.3" end_scan="3" index="3" precursor_neutral_mass="1776.8328" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="MLHFLTAVVGSTCDVK" massdiff="-0.0575" calc_neutral_pep_mass="1776.8903" peptide_next_aa="V" num_missed_cleavages="0" num_tol_term="2" num_tot_proteins="1" tot_num_ions="60" hit_rank="1" num_matched_ions="9" protein="NP_663760.1" peptide_prev_aa="R" is_rejected="0">
<modification_info>
<mod_aminoacid_mass mass="160.0307" position="13"/>
</modification_info>
<search_score name="hyperscore" value="18.616"/>
<search_score name="nextscore" value="18.616"/>
<search_score name="expect" value="9.354e-03"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="4" ion_mobility="0.79972166" assumed_charge="3" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.4.4.3" end_scan="4" index="4" precursor_neutral_mass="1668.8376" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="LFPLIQTMHSNLAGK" massdiff="-0.0645" calc_neutral_pep_mass="1668.9021" peptide_next_aa="I" num_missed_cleavages="0" num_tol_term="2" num_tot_proteins="1" tot_num_ions="56" hit_rank="1" num_matched_ions="4" protein="NP_001129125.1" peptide_prev_aa="R" is_rejected="0">
<search_score name="hyperscore" value="8.473"/>
<search_score name="nextscore" value="8.473"/>
<search_score name="expect" value="3.212e+00"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="6" ion_mobility="0.90289825" assumed_charge="3" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.6.6.3" end_scan="6" index="6" precursor_neutral_mass="2062.8899" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="EFHDVTLGNPWAGTKMDK" massdiff="1.9275" calc_neutral_pep_mass="2060.9624" peptide_next_aa="Y" num_missed_cleavages="1" num_tol_term="2" num_tot_proteins="1" tot_num_ions="68" hit_rank="1" num_matched_ions="6" protein="XXX_XP_011509654.1" peptide_prev_aa="K" is_rejected="0">
<modification_info>
<mod_aminoacid_mass mass="147.0354" position="16"/>
</modification_info>
<search_score name="hyperscore" value="10.267"/>
<search_score name="nextscore" value="9.823"/>
<search_score name="expect" value="2.481e+00"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="7" ion_mobility="1.0246093" assumed_charge="2" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.7.7.2" end_scan="7" index="7" precursor_neutral_mass="1509.7432" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="YQLEIPENFTTR" massdiff="-0.0031" calc_neutral_pep_mass="1509.7462" peptide_next_aa="N" num_missed_cleavages="0" num_tol_term="2" num_tot_proteins="1" tot_num_ions="22" hit_rank="1" num_matched_ions="10" protein="XP_011531100.1" peptide_prev_aa="R" is_rejected="0">
<search_score name="hyperscore" value="18.993"/>
<search_score name="nextscore" value="8.168"/>
<search_score name="expect" value="4.377e-05"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="8" ion_mobility="1.1342232" assumed_charge="2" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.8.8.2" end_scan="8" index="8" precursor_neutral_mass="1914.9641" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="LQQTQNQVDEVVDIMR" massdiff="0.0172" calc_neutral_pep_mass="1914.9469" peptide_next_aa="V" num_missed_cleavages="0" num_tol_term="2" num_tot_proteins="1" tot_num_ions="30" hit_rank="1" num_matched_ions="13" protein="NP_004772.1" peptide_prev_aa="R" is_rejected="0">
<search_score name="hyperscore" value="26.288"/>
<search_score name="nextscore" value="9.657"/>
<search_score name="expect" value="8.699e-07"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="9" ion_mobility="1.086622" assumed_charge="2" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.9.9.2" end_scan="9" index="9" precursor_neutral_mass="1672.8044" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="LQLVTQKMQYFEK" massdiff="1.9344" calc_neutral_pep_mass="1670.8700" peptide_next_aa="C" num_missed_cleavages="1" num_tol_term="2" num_tot_proteins="1" tot_num_ions="24" hit_rank="1" num_matched_ions="5" protein="XXX_NP_597716.1" peptide_prev_aa="K" is_rejected="0">
<modification_info>
<mod_aminoacid_mass mass="147.0354" position="8"/>
</modification_info>
<search_score name="hyperscore" value="11.396"/>
<search_score name="nextscore" value="10.214"/>
<search_score name="expect" value="2.535e+00"/>
</search_hit>
</search_result>
</spectrum_query>
<spectrum_query start_scan="10" ion_mobility="1.1805618" assumed_charge="2" spectrum="Hela_QC_PASEF_Slot1-5_01_57_cutout_2min.10.10.2" end_scan="10" index="10" precursor_neutral_mass="2062.9375" retention_time_sec="3600.674">
<search_result>
<search_hit peptide="SPNAYSGGHNSSSRNDPCR" massdiff="1.0703" calc_neutral_pep_mass="2061.8672" peptide_next_aa="G" num_missed_cleavages="1" num_tol_term="2" num_tot_proteins="1" tot_num_ions="36" hit_rank="1" num_matched_ions="4" protein="NP_001138818.1" peptide_prev_aa="R" is_rejected="0">
<modification_info>
<mod_aminoacid_mass mass="160.0307" position="18"/>
</modification_info>
<search_score name="hyperscore" value="4.825"/>
<search_score name="nextscore" value="4.646"/>
<search_score name="expect" value="2.623e+00"/>
</search_hit>
</search_result>
</spectrum_query>
</msms_run_summary>
</msms_pipeline_analysis>
Loading

0 comments on commit c25fa15

Please sign in to comment.