Merge branch 'main' of https://github.com/compomics/psm_utils into di…

…ann-io

CHANGELOG.md

@@ -5,6 +5,48 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.1.1] - 2024-10-01
+
+### Fixed
+
+- `io`: Fix Sage filename pattern for automatic file type inference
+- `io.flashlfq`: Fix writing PSMs without protein accession
+- `io.flashlfq`: Fix column names `Peptide Monoisotopic Mass` and `Protein Accession`.
+- `io.idxml`: Fix parsing if spectra file name not present [#92](https://github.com/compomics/psm_utils/issues/92)
+
+## [1.1.0] - 2024-09-05
+
+### Added
+
+- `Peptidoform`: Add `modified_sequence` property to return the modified sequence in ProForma format, but without charge state.
+- `io`: Add support for reading and writing FlashLFQ generic TSV files.
+
+
+## [1.0.1] - 2024-08-28
+
+### Fixed
+
+- `io.percolator`: Fix and improve ScanNr inferring and writing
+- `io.percolator`: Infer style from file extension if not provided (enables dynamic style determination in, for instance, `convert` function).
+
+## [1.0.0] - 2024-08-14
+
+### Added
+
+- Peptidoform: Allow comparison between a peptidoform and a peptidoform string; allow direct indexing with square brackets, which indexes or slices parsed_sequence (in #89)
+
+### Fixed
+
+- TSV: Avoid flooding logs when reading a different file format by raising exception when three consecutive rows could not be parsed (in #88)
+
+## [0.9.1] - 2024-07-17
+
+### Fixed
+
+- `io.xtandem`: Fix parsing PSMs and complete protein names in XTandem (by @julianu in #83)
+- `io.tsv`: Fix warning formatting when parsing TSV (by @paretje in #85)
+- `io`: Fix support for mzIdentML and pepXML files from Comet (by @paretje in #87)
+
 ## [0.9.0] - 2024-05-01
 
 ### Added

README.rst

@@ -91,6 +91,7 @@ Supported file formats
 ===================================================================================================================== ======================== =============== ===============
  `AlphaDIA precursors TSV <https://alphadia.readthedocs.io/en/latest/quickstart.html#output-files>`_                   ``alphadia``             ✅              ❌
  `DIA-NN TSV <https://github.com/vdemichev/DiaNN#output>`_                                                             ``diann``                ✅              ❌
+ `FlashLFQ generic TSV <https://github.com/smith-chem-wisc/FlashLFQ/wiki/Identification-Input-Formats>`_               ``flashlfq``             ✅              ✅
  `FragPipe PSM TSV <https://fragpipe.nesvilab.org/docs/tutorial_fragpipe_outputs.html#psmtsv/>`_                       ``fragpipe``             ✅              ❌
  `ionbot CSV <https://ionbot.cloud/>`_                                                                                 ``ionbot``               ✅              ❌
  `OpenMS idXML <https://www.openms.de/>`_                                                                              ``idxml``                ✅              ✅

docs/source/api/psm_utils.io.rst

@@ -23,6 +23,14 @@ psm_utils.io.diann
    :inherited-members:
 
 
+psm_utils.io.flashlfq
+#####################
+
+.. automodule:: psm_utils.io.flashlfq
+   :members:
+   :inherited-members:
+
+
 psm_utils.io.fragpipe
 ##################
 
@@ -76,7 +84,7 @@ psm_utils.io.mzid
 
 
 psm_utils.io.parquet
-#################
+####################
 
 .. automodule:: psm_utils.io.parquet
    :members:

example_files/PXD053286-G1_PTMiprophet.slice.pep.xml

@@ -0,0 +1,90 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<msms_pipeline_analysis date="2022-05-17T22:37:25"
+    xmlns="http://regis-web.systemsbiology.net/pepXML"
+    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+    xsi:schemaLocation="http://regis-web.systemsbiology.net/pepXML /tools/bin/TPP/tpp/schema/pepXML_v122.xsd"
+    summary_xml="/mnt/nfs/DataPool/Projects/Lumos/2022/22_2_Apr_Jun/20220510_VC/Pipe_Mferi_M/G1_iprophet.pep.xml">
+    <analysis_summary analysis="ptmprophet" time="2022-05-17T23:41:43">
+        <ptmprophet_summary version="TPP v5.1.0 Syzygy, Build 202012091755-8315 (Linux-x86_64)"
+            options="M:15.994915,n:42.010565 MZTOL=0.4 G1_iprophet.pep.xml G1_PTMiprophet.pep.xml">
+            <inputfile name="G1_iprophet.pep.xml" />
+            <inputfile name="20220511_M1_Mferi_0535_VC_i01_comet.pep.xml"
+                directory="/mnt/nfs/DataPool/Projects/Lumos/2022/22_2_Apr_Jun/20220510_VC/Data" />
+            <inputfile name="20220511_M1_Mferi_0535_VC_i02_comet.pep.xml"
+                directory="/mnt/nfs/DataPool/Projects/Lumos/2022/22_2_Apr_Jun/20220510_VC/Data" />
+        </ptmprophet_summary>
+    </analysis_summary>
+    <msms_run_summary
+        base_name="/mnt/nfs/DataPool/Projects/Lumos/2022/22_2_Apr_Jun/20220510_VC/Data/20220511_M1_Mferi_0535_VC_i01"
+        msManufacturer="UNKNOWN" msModel="UNKNOWN" raw_data_type="raw" raw_data=".mzXML">
+        <sample_enzyme name="trypsin">
+            <specificity cut="KR" no_cut="P" sense="C" />
+        </sample_enzyme>
+        <search_summary
+            base_name="/mnt/nfs/DataPool/Projects/Lumos/2022/22_2_Apr_Jun/20220510_VC/Data/20220511_M1_Mferi_0535_VC_i01"
+            search_engine="Comet" search_engine_version="2019.01 rev. 5"
+            precursor_mass_type="monoisotopic" fragment_mass_type="monoisotopic" search_id="1">
+            <search_database
+                local_path="/mnt/nfs/DataPool/FastaDataBases/Mferi_G5847_GCF_000327395.faa_REV.fasta"
+                type="AA" />
+            <enzymatic_search_constraint enzyme="Trypsin" max_num_internal_cleavages="3"
+                min_number_termini="2" />
+            <aminoacid_modification aminoacid="M" massdiff="15.994900" mass="147.035385"
+                variable="Y" symbol="*" />
+            <terminal_modification terminus="N" massdiff="42.010565" mass="43.018390" variable="Y"
+                protein_terminus="Y" symbol="#" />
+            <aminoacid_modification aminoacid="C" massdiff="57.021464" mass="160.030649"
+                variable="N" />
+        </search_summary>
+        <spectrum_query spectrum="20220511_M1_Mferi_0535_VC_i01.05387.05387.2" start_scan="5387"
+            end_scan="5387" precursor_neutral_mass="1006.560276" assumed_charge="2" index="143"
+            retention_time_sec="1413.1" experiment_label="Mferi_M1">
+            <search_result>
+                <search_hit hit_rank="1" peptide="SNLFLMLK" peptide_prev_aa="M" peptide_next_aa="Q"
+                    protein="WP_008364460.1" num_tot_proteins="1" num_matched_ions="11"
+                    tot_num_ions="14" calc_neutral_pep_mass="1006.552139" massdiff="0.008137"
+                    num_tol_term="2" num_missed_cleavages="0" num_matched_peptides="55"
+                    protein_descr="ABC transporter permease [Mycoplasma feriruminatoris]">
+                    <modification_info modified_peptide="n[43]SNLFLMLK" mod_nterm_mass="43.01839"></modification_info>
+                    <search_score name="xcorr" value="1.214" />
+                    <search_score name="deltacn" value="1.000" />
+                    <search_score name="deltacnstar" value="0.000" />
+                    <search_score name="spscore" value="453.5" />
+                    <search_score name="sprank" value="1" />
+                    <search_score name="expect" value="1.17E+00" />
+                    <analysis_result analysis="peptideprophet">
+                        <peptideprophet_result probability="0.5131"
+                            all_ntt_prob="(0.0000,0.0000,0.5131)">
+                            <search_score_summary>
+                                <parameter name="fval" value="-0.3767" />
+                                <parameter name="ntt" value="2" />
+                                <parameter name="nmc" value="0" />
+                                <parameter name="massd" value="8.084" />
+                                <parameter name="isomassd" value="0" />
+                            </search_score_summary>
+                        </peptideprophet_result>
+                    </analysis_result>
+                    <analysis_result analysis="interprophet">
+                        <interprophet_result probability="0.00133535"
+                            all_ntt_prob="(0,0,0.00133535)">
+                            <search_score_summary>
+                                <parameter name="nss" value="0.1289" />
+                                <parameter name="nrs" value="-0.7221" />
+                                <parameter name="nse" value="-0.5741" />
+                                <parameter name="nsi" value="0" />
+                                <parameter name="nsm" value="0.9838" />
+                                <parameter name="nsp" value="20" />
+                            </search_score_summary>
+                        </interprophet_result>
+                    </analysis_result>
+                    <analysis_result analysis="ptmprophet">
+                        <ptmprophet_result prior="1" ptm="PTMProphet_n42.0106"
+                            ptm_peptide="n(1.000)SNLFLMLK">
+                            <mod_terminal_probability terminus="n" probability="1.000" />
+                        </ptmprophet_result>
+                    </analysis_result>
+                </search_hit>
+            </search_result>
+        </spectrum_query>
+    </msms_run_summary>
+</msms_pipeline_analysis>

example_files/example.flashlfq.tsv

@@ -0,0 +1,18 @@
+File Name	Scan Retention Time	Precursor Charge	Base Sequence	Full Sequence	Peptide Monoisotopic Mass	Protein Accession
+SmallCalibratible_Yeast	24.80555	2	KAPAGGAADAAAK	KAPAGGAADAAAK		
+SmallCalibratible_Yeast	24.95372	2	KAPAAAPAASK	KAPAAAPAASK		
+SmallCalibratible_Yeast	24.77032	2	KQAIETANK	KQAIETANK		
+SmallCalibratible_Yeast	24.17319	2	RVDEGGAQDK	RVDEGGAQDK		
+SmallCalibratible_Yeast	24.26695	2	KDAEPQSDSTTSK	KDAEPQSDSTTSK		
+SmallCalibratible_Yeast	24.10798	2	EKAEAEAEK	EKAEAEAEK		
+SmallCalibratible_Yeast	24.06874	2	EKAEAEAEK	EKAEAEAEK		
+SmallCalibratible_Yeast	24.77398	2	FKEEDEKESQR	FKEEDEKESQR		
+SmallCalibratible_Yeast	24.90638	2	YDHEASSSYK	YDHEASSSYK		
+SmallCalibratible_Yeast	24.40345	3	SKDVTDSATTKK	SKDVTDSATTKK		
+SmallCalibratible_Yeast	24.71679	2	FKEEDEKESQR	FKEEDEKESQR		
+SmallCalibratible_Yeast	24.39968	2	ALKQEGAANK	ALKQEGAANK		
+SmallCalibratible_Yeast	24.67303	2	SKDVTDSATTK	SKDVTDSATTK		
+SmallCalibratible_Yeast	24.45053	2	KLEDHPK	KLEDHPK		
+SmallCalibratible_Yeast	24.77398	1	HIDAGAK	HIDAGAK		
+SmallCalibratible_Yeast	24.9022	2	YLAKEEEKK	YLAKEEEKK		
+SmallCalibratible_Yeast	24.76278	2	YAGEVSHDDK	YAGEVSHDDK		

psm_utils/__init__.py

@@ -1,6 +1,6 @@
 """Common utilities for parsing and handling PSMs, and search engine results."""
 
-__version__ = "0.9.0"
+__version__ = "1.1.1"
 __all__ = ["Peptidoform", "PSM", "PSMList"]
 
 from warnings import filterwarnings

psm_utils/io/__init__.py

@@ -10,6 +10,7 @@
 
 import psm_utils.io.alphadia as alphadia
 import psm_utils.io.diann as diann
+import psm_utils.io.flashlfq as flashlfq
 import psm_utils.io.fragpipe as fragpipe
 import psm_utils.io.idxml as idxml
 import psm_utils.io.ionbot as ionbot
@@ -31,6 +32,12 @@
 from psm_utils.psm_list import PSMList
 
 FILETYPES = {
+    "flashlfq": {
+        "reader": flashlfq.FlashLFQReader,
+        "writer": flashlfq.FlashLFQWriter,
+        "extension": ".tsv",
+        "filename_pattern": r"^.*\.flashlfq\.tsv$",
+    },
     "ionbot": {
         "reader": ionbot.IonbotReader,
         "writer": None,
@@ -65,7 +72,7 @@
         "reader": pepxml.PepXMLReader,
         "writer": None,
         "extension": ".pepxml",
-        "filename_pattern": r"^.*\.pepxml$",
+        "filename_pattern": r"^.*\.pep\.?xml$",
     },
     "percolator": {
         "reader": percolator.PercolatorTabReader,
@@ -101,13 +108,13 @@
         "reader": sage.SageTSVReader,
         "writer": None,
         "extension": ".tsv",
-        "filename_pattern": r"^.*(?:_|\.).sage.tsv$",
+        "filename_pattern": r"^.*(?:_|\.)sage.tsv$",
     },
     "sage_parquet": {
         "reader": sage.SageParquetReader,
         "writer": None,
         "extension": ".parquet",
-        "filename_pattern": r"^.*(?:_|\.).sage.parquet$",
+        "filename_pattern": r"^.*(?:_|\.)sage.parquet$",
     },
     "fragpipe": {
         "reader": fragpipe.FragPipeReader,