From 3c9ee037cef12813ed9d2c810a154855b8a67bf3 Mon Sep 17 00:00:00 2001 From: Jim Johnson Date: Mon, 1 Jun 2015 14:10:44 -0500 Subject: [PATCH] Initial upload. --- LICENSE | 340 ++++++++ README.md | 8 +- dependency-reduced-pom.xml | 51 ++ nb-configuration.xml | 18 + nbactions.xml | 46 ++ pom.xml | 180 ++++ schema.txt | 122 +++ .../umn/msi/gx/mztosqlite/MzIdentParser.java | 584 +++++++++++++ .../msi/gx/mztosqlite/MzParserHandler.java | 31 + .../edu/umn/msi/gx/mztosqlite/MzSQLiteDB.java | 314 +++++++ .../msi/gx/mztosqlite/MzSpectrumParser.java | 216 +++++ .../edu/umn/msi/gx/mztosqlite/MzToSQLite.java | 169 ++++ .../msi/gx/mztosqlite/ProteomicsFormat.java | 109 +++ .../edu/umn/msi/gx/mztosqlite/PsmUtils.java | 234 ++++++ src/main/resources/MzIdentMLElement.cfg.xml | 771 ++++++++++++++++++ 15 files changed, 3191 insertions(+), 2 deletions(-) create mode 100644 LICENSE create mode 100644 dependency-reduced-pom.xml create mode 100644 nb-configuration.xml create mode 100644 nbactions.xml create mode 100644 pom.xml create mode 100644 schema.txt create mode 100644 src/main/java/edu/umn/msi/gx/mztosqlite/MzIdentParser.java create mode 100644 src/main/java/edu/umn/msi/gx/mztosqlite/MzParserHandler.java create mode 100644 src/main/java/edu/umn/msi/gx/mztosqlite/MzSQLiteDB.java create mode 100644 src/main/java/edu/umn/msi/gx/mztosqlite/MzSpectrumParser.java create mode 100644 src/main/java/edu/umn/msi/gx/mztosqlite/MzToSQLite.java create mode 100644 src/main/java/edu/umn/msi/gx/mztosqlite/ProteomicsFormat.java create mode 100644 src/main/java/edu/umn/msi/gx/mztosqlite/PsmUtils.java create mode 100644 src/main/resources/MzIdentMLElement.cfg.xml diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..8cdb845 --- /dev/null +++ b/LICENSE @@ -0,0 +1,340 @@ + GNU GENERAL PUBLIC LICENSE + Version 2, June 1991 + + Copyright (C) 1989, 1991 Free Software Foundation, Inc., + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The licenses for most software are designed to take away your +freedom to share and change it. By contrast, the GNU General Public +License is intended to guarantee your freedom to share and change free +software--to make sure the software is free for all its users. This +General Public License applies to most of the Free Software +Foundation's software and to any other program whose authors commit to +using it. (Some other Free Software Foundation software is covered by +the GNU Lesser General Public License instead.) You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +this service if you wish), that you receive source code or can get it +if you want it, that you can change the software or use pieces of it +in new free programs; and that you know you can do these things. + + To protect your rights, we need to make restrictions that forbid +anyone to deny you these rights or to ask you to surrender the rights. +These restrictions translate to certain responsibilities for you if you +distribute copies of the software, or if you modify it. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must give the recipients all the rights that +you have. You must make sure that they, too, receive or can get the +source code. And you must show them these terms so they know their +rights. + + We protect your rights with two steps: (1) copyright the software, and +(2) offer you this license which gives you legal permission to copy, +distribute and/or modify the software. + + Also, for each author's protection and ours, we want to make certain +that everyone understands that there is no warranty for this free +software. If the software is modified by someone else and passed on, we +want its recipients to know that what they have is not the original, so +that any problems introduced by others will not reflect on the original +authors' reputations. + + Finally, any free program is threatened constantly by software +patents. We wish to avoid the danger that redistributors of a free +program will individually obtain patent licenses, in effect making the +program proprietary. To prevent this, we have made it clear that any +patent must be licensed for everyone's free use or not licensed at all. + + The precise terms and conditions for copying, distribution and +modification follow. + + GNU GENERAL PUBLIC LICENSE + TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION + + 0. This License applies to any program or other work which contains +a notice placed by the copyright holder saying it may be distributed +under the terms of this General Public License. The "Program", below, +refers to any such program or work, and a "work based on the Program" +means either the Program or any derivative work under copyright law: +that is to say, a work containing the Program or a portion of it, +either verbatim or with modifications and/or translated into another +language. (Hereinafter, translation is included without limitation in +the term "modification".) Each licensee is addressed as "you". + +Activities other than copying, distribution and modification are not +covered by this License; they are outside its scope. The act of +running the Program is not restricted, and the output from the Program +is covered only if its contents constitute a work based on the +Program (independent of having been made by running the Program). +Whether that is true depends on what the Program does. + + 1. You may copy and distribute verbatim copies of the Program's +source code as you receive it, in any medium, provided that you +conspicuously and appropriately publish on each copy an appropriate +copyright notice and disclaimer of warranty; keep intact all the +notices that refer to this License and to the absence of any warranty; +and give any other recipients of the Program a copy of this License +along with the Program. + +You may charge a fee for the physical act of transferring a copy, and +you may at your option offer warranty protection in exchange for a fee. + + 2. You may modify your copy or copies of the Program or any portion +of it, thus forming a work based on the Program, and copy and +distribute such modifications or work under the terms of Section 1 +above, provided that you also meet all of these conditions: + + a) You must cause the modified files to carry prominent notices + stating that you changed the files and the date of any change. + + b) You must cause any work that you distribute or publish, that in + whole or in part contains or is derived from the Program or any + part thereof, to be licensed as a whole at no charge to all third + parties under the terms of this License. + + c) If the modified program normally reads commands interactively + when run, you must cause it, when started running for such + interactive use in the most ordinary way, to print or display an + announcement including an appropriate copyright notice and a + notice that there is no warranty (or else, saying that you provide + a warranty) and that users may redistribute the program under + these conditions, and telling the user how to view a copy of this + License. (Exception: if the Program itself is interactive but + does not normally print such an announcement, your work based on + the Program is not required to print an announcement.) + +These requirements apply to the modified work as a whole. If +identifiable sections of that work are not derived from the Program, +and can be reasonably considered independent and separate works in +themselves, then this License, and its terms, do not apply to those +sections when you distribute them as separate works. But when you +distribute the same sections as part of a whole which is a work based +on the Program, the distribution of the whole must be on the terms of +this License, whose permissions for other licensees extend to the +entire whole, and thus to each and every part regardless of who wrote it. + +Thus, it is not the intent of this section to claim rights or contest +your rights to work written entirely by you; rather, the intent is to +exercise the right to control the distribution of derivative or +collective works based on the Program. + +In addition, mere aggregation of another work not based on the Program +with the Program (or with a work based on the Program) on a volume of +a storage or distribution medium does not bring the other work under +the scope of this License. + + 3. You may copy and distribute the Program (or a work based on it, +under Section 2) in object code or executable form under the terms of +Sections 1 and 2 above provided that you also do one of the following: + + a) Accompany it with the complete corresponding machine-readable + source code, which must be distributed under the terms of Sections + 1 and 2 above on a medium customarily used for software interchange; or, + + b) Accompany it with a written offer, valid for at least three + years, to give any third party, for a charge no more than your + cost of physically performing source distribution, a complete + machine-readable copy of the corresponding source code, to be + distributed under the terms of Sections 1 and 2 above on a medium + customarily used for software interchange; or, + + c) Accompany it with the information you received as to the offer + to distribute corresponding source code. (This alternative is + allowed only for noncommercial distribution and only if you + received the program in object code or executable form with such + an offer, in accord with Subsection b above.) + +The source code for a work means the preferred form of the work for +making modifications to it. For an executable work, complete source +code means all the source code for all modules it contains, plus any +associated interface definition files, plus the scripts used to +control compilation and installation of the executable. However, as a +special exception, the source code distributed need not include +anything that is normally distributed (in either source or binary +form) with the major components (compiler, kernel, and so on) of the +operating system on which the executable runs, unless that component +itself accompanies the executable. + +If distribution of executable or object code is made by offering +access to copy from a designated place, then offering equivalent +access to copy the source code from the same place counts as +distribution of the source code, even though third parties are not +compelled to copy the source along with the object code. + + 4. You may not copy, modify, sublicense, or distribute the Program +except as expressly provided under this License. Any attempt +otherwise to copy, modify, sublicense or distribute the Program is +void, and will automatically terminate your rights under this License. +However, parties who have received copies, or rights, from you under +this License will not have their licenses terminated so long as such +parties remain in full compliance. + + 5. You are not required to accept this License, since you have not +signed it. However, nothing else grants you permission to modify or +distribute the Program or its derivative works. These actions are +prohibited by law if you do not accept this License. Therefore, by +modifying or distributing the Program (or any work based on the +Program), you indicate your acceptance of this License to do so, and +all its terms and conditions for copying, distributing or modifying +the Program or works based on it. + + 6. Each time you redistribute the Program (or any work based on the +Program), the recipient automatically receives a license from the +original licensor to copy, distribute or modify the Program subject to +these terms and conditions. You may not impose any further +restrictions on the recipients' exercise of the rights granted herein. +You are not responsible for enforcing compliance by third parties to +this License. + + 7. If, as a consequence of a court judgment or allegation of patent +infringement or for any other reason (not limited to patent issues), +conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot +distribute so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you +may not distribute the Program at all. For example, if a patent +license would not permit royalty-free redistribution of the Program by +all those who receive copies directly or indirectly through you, then +the only way you could satisfy both it and this License would be to +refrain entirely from distribution of the Program. + +If any portion of this section is held invalid or unenforceable under +any particular circumstance, the balance of the section is intended to +apply and the section as a whole is intended to apply in other +circumstances. + +It is not the purpose of this section to induce you to infringe any +patents or other property right claims or to contest validity of any +such claims; this section has the sole purpose of protecting the +integrity of the free software distribution system, which is +implemented by public license practices. Many people have made +generous contributions to the wide range of software distributed +through that system in reliance on consistent application of that +system; it is up to the author/donor to decide if he or she is willing +to distribute software through any other system and a licensee cannot +impose that choice. + +This section is intended to make thoroughly clear what is believed to +be a consequence of the rest of this License. + + 8. If the distribution and/or use of the Program is restricted in +certain countries either by patents or by copyrighted interfaces, the +original copyright holder who places the Program under this License +may add an explicit geographical distribution limitation excluding +those countries, so that distribution is permitted only in or among +countries not thus excluded. In such case, this License incorporates +the limitation as if written in the body of this License. + + 9. The Free Software Foundation may publish revised and/or new versions +of the General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + +Each version is given a distinguishing version number. If the Program +specifies a version number of this License which applies to it and "any +later version", you have the option of following the terms and conditions +either of that version or of any later version published by the Free +Software Foundation. If the Program does not specify a version number of +this License, you may choose any version ever published by the Free Software +Foundation. + + 10. If you wish to incorporate parts of the Program into other free +programs whose distribution conditions are different, write to the author +to ask for permission. For software which is copyrighted by the Free +Software Foundation, write to the Free Software Foundation; we sometimes +make exceptions for this. Our decision will be guided by the two goals +of preserving the free status of all derivatives of our free software and +of promoting the sharing and reuse of software generally. + + NO WARRANTY + + 11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY +FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW. EXCEPT WHEN +OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES +PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED +OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF +MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS +TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU. SHOULD THE +PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING, +REPAIR OR CORRECTION. + + 12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR +REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, +INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING +OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED +TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY +YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER +PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE +POSSIBILITY OF SUCH DAMAGES. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +convey the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + {description} + Copyright (C) {year} {fullname} + + This program is free software; you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation; either version 2 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License along + with this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + +Also add information on how to contact you by electronic and paper mail. + +If the program is interactive, make it output a short notice like this +when it starts in an interactive mode: + + Gnomovision version 69, Copyright (C) year name of author + Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, the commands you use may +be called something other than `show w' and `show c'; they could even be +mouse-clicks or menu items--whatever suits your program. + +You should also get your employer (if you work as a programmer) or your +school, if any, to sign a "copyright disclaimer" for the program, if +necessary. Here is a sample; alter the names: + + Yoyodyne, Inc., hereby disclaims all copyright interest in the program + `Gnomovision' (which makes passes at compilers) written by James Hacker. + + {signature of Ty Coon}, 1 April 1989 + Ty Coon, President of Vice + +This General Public License does not permit incorporating your program into +proprietary programs. If your program is a subroutine library, you may +consider it more useful to permit linking proprietary applications with the +library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. + diff --git a/README.md b/README.md index 722197d..b1a77dd 100644 --- a/README.md +++ b/README.md @@ -1,2 +1,6 @@ -# mzToSQLite -Convert proteomics data files into a SQLite database +# mztosqlite +Convert proteomics data files into a SQLite database + +Extract data from proteomics mzIdentML and mass spec scan files: mzML, MGF, etc and store in a SQLite database. +The intended purpose is to provide a Galaxy dataset that can support an interactive Galaxy visualization plugin. + diff --git a/dependency-reduced-pom.xml b/dependency-reduced-pom.xml new file mode 100644 index 0000000..76d1a9c --- /dev/null +++ b/dependency-reduced-pom.xml @@ -0,0 +1,51 @@ + + + 4.0.0 + edu.umn.msi.gx + mzToSQLite + 1.0-SNAPSHOT + + + + maven-shade-plugin + 2.3 + + + package + + shade + + + + + edu.umn.msi.gx.mztosqlite.MzToSQLite + + + + + + + + + + + tmate + http://maven.tmatesoft.com/content/repositories/releases + + + + 1.4.4 + 0.1.21 + 1.1.4-SNAPSHOT + ${name}-${version} + 1.0.8 + 3.0.1 + 4.2.1 + 1.7 + 2.0.02 + UTF-8 + 1.5.0 + 1.7 + + + diff --git a/nb-configuration.xml b/nb-configuration.xml new file mode 100644 index 0000000..c2decf1 --- /dev/null +++ b/nb-configuration.xml @@ -0,0 +1,18 @@ + + + + + + JDK_1.7 + + diff --git a/nbactions.xml b/nbactions.xml new file mode 100644 index 0000000..e842d11 --- /dev/null +++ b/nbactions.xml @@ -0,0 +1,46 @@ + + + + run + + jar + + + process-classes + org.codehaus.mojo:exec-maven-plugin:1.2.1:exec + + + -Xms4g -classpath %classpath edu.umn.msi.gx.mztosqlite.MzToSQLite -s /Users/jj/Downloads/GCC2015.sqlite /Users/jj/gxt/gxt/database/files/006/dataset_6617.dat /Users/jj/gxt/gxt/database/files/006/dataset_6616.dat /Users/jj/gxt/gxt/database/files/006/dataset_6620.dat /Users/jj/gxt/gxt/database/files/006/dataset_6618.dat + java + + + + debug + + jar + + + process-classes + org.codehaus.mojo:exec-maven-plugin:1.2.1:exec + + + -Xdebug -Xrunjdwp:transport=dt_socket,server=n,address=${jpda.address} -Xms4g -classpath %classpath edu.umn.msi.gx.mztosqlite.MzToSQLite -s /Users/jj/Downloads/GCC2015.sqlite /Users/jj/gxt/gxt/database/files/006/dataset_6617.dat /Users/jj/gxt/gxt/database/files/006/dataset_6616.dat /Users/jj/gxt/gxt/database/files/006/dataset_6620.dat /Users/jj/gxt/gxt/database/files/006/dataset_6618.dat + java + true + + + + profile + + jar + + + process-classes + org.codehaus.mojo:exec-maven-plugin:1.2.1:exec + + + -Xms4g -classpath %classpath edu.umn.msi.gx.mztosqlite.MzToSQLite -s /Users/jj/Downloads/GCC2015.sqlite /Users/jj/gxt/gxt/database/files/006/dataset_6617.dat /Users/jj/gxt/gxt/database/files/006/dataset_6616.dat /Users/jj/gxt/gxt/database/files/006/dataset_6620.dat /Users/jj/gxt/gxt/database/files/006/dataset_6618.dat + java + + + diff --git a/pom.xml b/pom.xml new file mode 100644 index 0000000..5e6a705 --- /dev/null +++ b/pom.xml @@ -0,0 +1,180 @@ + + + 4.0.0 + edu.umn.msi.gx + mzToSQLite + 1.0-SNAPSHOT + jar + + UTF-8 + 1.7 + 1.7 + 1.1.4-SNAPSHOT + 1.0.8 + 0.1.21 + 3.0.1 + 4.2.1 + 1.4.4 + 1.5.0 + 2.0.02 + ${name}-${version} + + + + tmate + http://maven.tmatesoft.com/content/repositories/releases + + + + + uk.ac.ebi.jmzml + jmzml + 1.6.8 + + + xxindex + psidev.psi.tools + + + + + uk.ac.ebi.jmzidml + jmzidentml + 1.1.10-SNAPSHOT + + + commons-cli + commons-cli + 1.2 + + + uk.ac.ebi.pride.mzgraph + pride-mzgraph-browser + 1.0.4 + + + uk.ac.ebi.pride.tools + jmzreader + 1.2.0 + jar + + + uk.ac.ebi.pride.tools + pkl-parser + 1.2.1 + + + uk.ac.ebi.pride.tools + dta-parser + 1.2.1 + + + uk.ac.ebi.pride.tools + ms2-parser + 1.2.1 + + + uk.ac.ebi.pride.tools + mgf-parser + 1.2.4 + + + uk.ac.ebi.pride.tools + mzxml-parser + 1.3.2 + + + uk.ac.ebi.pride.tools + mzdata-parser + 1.2.1 + + + uk.ac.ebi.pride.tools + mzml-wrapper + 1.2 + + + uk.ac.ebi.pride.tools + pride-wrapper + 1.2.0 + + + com.github.samtools + htsjdk + 1.130 + + + org.tmatesoft.sqljet + sqljet + 1.1.10 + + + com.compomics + utilities + 3.47.2 + + + commons-math + commons-math + + + servlet-api + javax.servlet + + + swingx + org.swinglabs + + + swing-layout + org.swinglabs + + + batik-all + batik + + + pdf-transcoder + batik + + + jfreechart + jfree + + + xercesImpl + xerces + + + ssj + umontreal.iro.lecuyer.gof + + + + + + + + + org.apache.maven.plugins + maven-shade-plugin + 2.3 + + + package + + shade + + + + + edu.umn.msi.gx.mztosqlite.MzToSQLite + + + + + + + + + \ No newline at end of file diff --git a/schema.txt b/schema.txt new file mode 100644 index 0000000..02befcb --- /dev/null +++ b/schema.txt @@ -0,0 +1,122 @@ +CREATE TABLE Source ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + name TEXT, + format TEXT, + spectrumIDFormat TEXT, + location TEXT +); + +CREATE TABLE SpectraData ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + name TEXT, + format TEXT, + spectrumIDFormat TEXT, + location TEXT +); + +CREATE TABLE Spectrum ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + id TEXT, + acquisitionNum INTEGER, + msLevel INTEGER, + polarity INTEGER, + peaksCount INTEGER, + totIonCurrent REAL, + retentionTime REAL, + basePeakMZ REAL, + basePeakIntensity REAL, + collisionEnergy REAL, + ionisationEnergy REAL, + lowMZ REAL, + highMZ REAL, + precursorScanNum INTEGER, + precursorMZ REAL, + precursorCharge INTEGER, + precursorIntensity REAL, + title TEXT +); + +CREATE TABLE Peaks ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + Spectrum_pkid INT REFERENCES Spectrum(pkid), + acquisitionNum INTEGER, + moz TEXT, + intensity TEXT +); + +CREATE TABLE SearchDatabase ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + name TEXT, + format TEXT, + numDatabaseSequences INTEGER, + numResidues INTEGER, + releaseDate TEXT, + version TEXT, + location TEXT +); + +CREATE TABLE DBSequence ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + id INTEGER, + SearchDatabase_pkid INTEGER REFERENCES SearchDatabase(pkid), + accession TEXT, + description TEXT, + length INTEGER, + sequence TEXT +); + +CREATE TABLE Peptide ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + sequence TEXT, + modNum INTEGER +); + +CREATE TABLE Modification ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + Peptide_pkid INTEGER REFERENCES Peptide(pkid),location INTEGER, + residues TEXT, + replacementResidue TEXT, + name TEXT, + avgMassDelta REAL, + monoisotopicMassDelta REAL +); + +CREATE TABLE PeptideEvidence ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + SpectrumIdentification_pkid INTEGER REFERENCES SpectrumIdentification(pkid), + Peptide_pkid INTEGER REFERENCES Peptide(pkid), + DBSequence_pkid INTEGER REFERENCES DBSequence(pkid), + isDecoy INTEGER, + pre TEXT, + post TEXT, + start INTEGER, + end INTEGER +); + +CREATE TABLE SpectrumIdentification ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + Spectrum_pkid INTEGER, + spectrum_id TEXT, + acquisitionNum INTEGER, + chargeState INTEGER, + retentionTime REAL,rank INTEGER, + passThreshold INTEGER, + experimentalMassToCharge REAL, + calculatedMassToCharge REAL +); + +CREATE TABLE Score ( + pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, + spectrum_identification_id TEXT, + SpectrumIdentification_pkid INTEGER REFERENCES SpectrumIdentification ( + pkid), + [PeptideShaker PSM score] REAL, + [OMSSA:evalue] REAL, + [MS-GF:SpecEValue] REAL, + [theoretical mass] REAL, + [PeptideShaker PSM confidence] REAL +); + +CREATE INDEX DBSequence_acc_idx ON DBSequence(accession); +CREATE INDEX PeptideEvidence_fkey_idx on PeptideEvidence (spectrumidentification_pkid,dbsequence_pkid,peptide_pkid); +CREATE INDEX Peptide_sequence_idx ON Peptide(sequence); diff --git a/src/main/java/edu/umn/msi/gx/mztosqlite/MzIdentParser.java b/src/main/java/edu/umn/msi/gx/mztosqlite/MzIdentParser.java new file mode 100644 index 0000000..1db2aea --- /dev/null +++ b/src/main/java/edu/umn/msi/gx/mztosqlite/MzIdentParser.java @@ -0,0 +1,584 @@ +/* + * To change this license header, choose License Headers in Project Properties. + * To change this template file, choose Tools | Templates + * and open the template in the editor. + */ + +package edu.umn.msi.gx.mztosqlite; + +import com.compomics.util.protein.Header; +import java.io.BufferedReader; +import java.io.DataInputStream; +import java.io.File; +import java.io.FileInputStream; +import java.io.FileNotFoundException; +import java.io.IOException; +import java.io.InputStream; +import java.io.InputStreamReader; +import java.text.DateFormat; +import java.text.SimpleDateFormat; +import java.util.ArrayList; +import java.util.Date; +import java.util.HashMap; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.regex.Matcher; +import java.util.regex.Pattern; +import uk.ac.ebi.jmzidml.MzIdentMLElement; +import uk.ac.ebi.jmzidml.model.mzidml.AbstractParam; +import uk.ac.ebi.jmzidml.model.mzidml.AnalysisData; +import uk.ac.ebi.jmzidml.model.mzidml.AnalysisSoftware; +import uk.ac.ebi.jmzidml.model.mzidml.CvParam; +import uk.ac.ebi.jmzidml.model.mzidml.DBSequence; +import uk.ac.ebi.jmzidml.model.mzidml.DataCollection; +import uk.ac.ebi.jmzidml.model.mzidml.Modification; +import uk.ac.ebi.jmzidml.model.mzidml.Peptide; +import uk.ac.ebi.jmzidml.model.mzidml.PeptideEvidence; +import uk.ac.ebi.jmzidml.model.mzidml.PeptideEvidenceRef; +import uk.ac.ebi.jmzidml.model.mzidml.ProteinAmbiguityGroup; +import uk.ac.ebi.jmzidml.model.mzidml.ProteinDetectionHypothesis; +import uk.ac.ebi.jmzidml.model.mzidml.ProteinDetectionList; +import uk.ac.ebi.jmzidml.model.mzidml.SearchDatabase; +import uk.ac.ebi.jmzidml.model.mzidml.SourceFile; +import uk.ac.ebi.jmzidml.model.mzidml.SpectraData; +import uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentificationItem; +import uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentificationResult; +import uk.ac.ebi.jmzidml.model.mzidml.SubstitutionModification; +import uk.ac.ebi.jmzidml.model.mzidml.UserParam; +import uk.ac.ebi.jmzidml.xml.io.MzIdentMLUnmarshaller; + +/** + * + * @author James E Johnson jj@umn.edu + * @version + */ +public class MzIdentParser { + String[] FASTA_ID_PATTERNS = {"^(?:sp|tr|gi[|][^|]+[|]ref)[|]([a-zA-Z0-9]+[|]*(:[_.][a-zA-Z0-9]+)*).*$", + "^(\\w+)\\s*(.*)$"}; + + String filepath; + /* map of spectrum id to database primary key*/ + private Map spectrumIdPkidMap; + private Map accToSeq = new HashMap<>(); + private Map accToDefline = new HashMap<>(); + boolean verbose = false; + + public MzIdentParser() { + } + + public MzIdentParser(String filepath) { + this(filepath,null); + } + + public MzIdentParser(String filepath,Map spectrumIdPkidMap) { + this.filepath = filepath; + this.spectrumIdPkidMap = spectrumIdPkidMap; + } + + public boolean isVerbose() { + return verbose; + } + + public void setVerbose(boolean verbose) { + this.verbose = verbose; + } + + public void parseIdent(MzParserHandler handler) { + parseIdent(filepath,handler); + } + public void parseIdent(String filepath, MzParserHandler parseHandler) { + /* + TODO: Generate scores for: + DBSequence: %sequence_coverage + Spectral_identification: + */ + DateFormat dfmt = new SimpleDateFormat("yyyy-MM-dd' 'HH:mm:ss.SSS"); + File input = new File(filepath); + boolean aUseSpectrumCache = true; + Map sourceFileIdHashMap = new HashMap<>(); + Map analysisSoftwareIdHashMap = new HashMap<>(); + Map peptideEvidenceIdHashMap = new HashMap<>(); + Map peptideIdHashMap = new HashMap<>(); + Map spectraDataIdHashMap = new HashMap<>(); + Map siiIdHashMap = new HashMap<>(); + Map siiIdToSirHashMap = new HashMap<>(); + Map scoreNameToClassMap = new HashMap<>(); + Map columnToScoreMap = new HashMap<>(); + Map columnToProtScoreMap = new HashMap<>(); + Map dbSequenceIdHashMap = new HashMap<>(); + Map pdhIdHashMap = new HashMap<>(); + Map> peptide_pdh_HashMap = new HashMap<>(); + List proteinDetectionHypothesisList = new ArrayList<>(); + List proteinAmbiguityGroupList = new ArrayList<>(); + ProteinDetectionList proteinDetectionList = new ProteinDetectionList(); + boolean isAutoRefResolving = MzIdentMLElement.SpectrumIdentificationItem.isAutoRefResolving(); + // DB Maps for Foreign Keys + Map fkSearchDatabaseIdPkid = new HashMap<>(); + Map fkDBSequenceIdPkid = new HashMap<>(); + Map fkSpectrumIdentificationIdPkid = new HashMap<>(); + Map fkPeptideIdPkid = new HashMap<>(); + Map> spectrumIdentScores = new HashMap<>(); + Map scoreNameValueClass = new HashMap<>(); + // Read mzIdentML file + MzIdentMLUnmarshaller unmarshaller = new MzIdentMLUnmarshaller(input); + DataCollection dc = unmarshaller.unmarshal(DataCollection.class); + AnalysisData ad = dc.getAnalysisData(); + List spectraDataList = dc.getInputs().getSpectraData(); + for (SpectraData spectraData : dc.getInputs().getSpectraData()) { + Map sourceMap = new HashMap<>(); + sourceMap.put("name", spectraData.getName()); + sourceMap.put("location", spectraData.getLocation()); + sourceMap.put("format", spectraData.getFileFormat().getCvParam().getName()); + sourceMap.put("spectrumIDFormat", spectraData.getSpectrumIDFormat() == null ? null : spectraData.getSpectrumIDFormat().getCvParam().getName()); + Object pkid = parseHandler.handle("SpectraData", sourceMap); + } + for (SearchDatabase searchDatabase : dc.getInputs().getSearchDatabase()) { + Map sourceMap = new HashMap<>(); + sourceMap.put("name", searchDatabase.getName()); + sourceMap.put("location", searchDatabase.getLocation()); //required + sourceMap.put("format", searchDatabase.getFileFormat() == null ? null : searchDatabase.getFileFormat().getCvParam().getName()); + sourceMap.put("numDatabaseSequences", searchDatabase.getNumDatabaseSequences()); + sourceMap.put("numResidues", searchDatabase.getNumResidues()); + sourceMap.put("releaseDate", searchDatabase.getReleaseDate()); + sourceMap.put("version", searchDatabase.getVersion()); + Object pkid = parseHandler.handle("SearchDatabase", sourceMap); + fkSearchDatabaseIdPkid.put(searchDatabase.getId(), pkid); + } + // AnalysisSoftwareList AnalysisSoftware SoftwareName + if (verbose) { + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over SourceFile"); + } + Iterator iterSourceFile = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.SourceFile); + while (iterSourceFile.hasNext()) { + SourceFile sourceFile = iterSourceFile.next(); + sourceFileIdHashMap.put(sourceFile.getId(), sourceFile); + Map sourceMap = new HashMap<>(); + sourceMap.put("name", sourceFile.getName()); + sourceMap.put("location", sourceFile.getLocation()); + sourceMap.put("format", sourceFile.getFileFormat().getCvParam().getName()); + Object pkid = parseHandler.handle("Source", sourceMap); + } + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over AnalysisSoftware"); + } + Iterator iterAnalysisSoftware = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.AnalysisSoftware); + while (iterAnalysisSoftware.hasNext()) { + AnalysisSoftware analysisSoftware = iterAnalysisSoftware.next(); + analysisSoftwareIdHashMap.put(analysisSoftware.getId(), analysisSoftware); + } + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over DBsequence"); + } + Iterator iterDBSequence = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.DBSequence); + while (iterDBSequence.hasNext()) { + DBSequence dbSequence = iterDBSequence.next(); + dbSequenceIdHashMap.put(dbSequence.getId(), dbSequence); + Object SearchDatabase_pkid = fkSearchDatabaseIdPkid.get(dbSequence.getSearchDatabaseRef()); + if (dbSequence.getSeq() == null) { + String seq = accToSeq.get(dbSequence.getAccession()); + //System.out.println("seq: " + seq); + if(seq!=null){ + dbSequence.setSeq(seq); + if (dbSequence.getLength() == null) { + dbSequence.setLength(seq.length()); + } + } + } + Integer seqLen =dbSequence.getLength(); + Map dbMap = new HashMap<>(); + dbMap.put("SearchDatabase_pkid", SearchDatabase_pkid); + dbMap.put("accession", dbSequence.getAccession()); + dbMap.put("length", dbSequence.getLength()); + dbMap.put("sequence", dbSequence.getSeq()); + for (CvParam cv : dbSequence.getCvParam()) { + switch (cv.getAccession()) { + case "MS:1001088": + dbMap.put("description", cv.getValue()); // TEXT + break; + } + } + Object pkid = parseHandler.handle("DBSequence", dbMap); + fkDBSequenceIdPkid.put(dbSequence.getId(), pkid); + } + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over Peptide"); + } + Iterator iterPeptide = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.Peptide); + while (iterPeptide.hasNext()) { + Peptide peptide = iterPeptide.next(); + peptideIdHashMap.put(peptide.getId(), peptide); + Map peptideValues = new HashMap<>(); + List> modValueList = new ArrayList<>(); + String peptideId = peptide.getId(); + peptideValues.put("sequence", peptide.getPeptideSequence()); + int modNum = 0; + if (peptide.getModification() != null) { + for (Modification mod : peptide.getModification()) { + modNum++; + Map modValues = new HashMap<>(); + modValues.put("location", mod.getLocation()); + List residues = mod.getResidues(); + StringBuilder sb = new StringBuilder(); + for (String residue : residues) { + sb.append(residue); + } + modValues.put("residues", sb.length() > 0 ? sb.toString() : null); + modValues.put("replacementResidue", null); + modValues.put("avgMassDelta", mod.getAvgMassDelta()); + modValues.put("monoisotopicMassDelta", mod.getMonoisotopicMassDelta()); + String modNames = null; + for (CvParam cv : mod.getCvParam()) { + if (modNames == null) { + modNames = cv.getName(); + } else { + modNames += "," + cv.getName(); + } + } + modValues.put("name", modNames); + modValueList.add(modValues); + } + } + if (peptide.getSubstitutionModification() != null) { + for (SubstitutionModification subMod : peptide.getSubstitutionModification()) { + modNum++; + Map modValues = new HashMap<>(); + modValues.put("location", subMod.getLocation()); + modValues.put("residues", subMod.getOriginalResidue()); + modValues.put("replacementResidue", subMod.getReplacementResidue()); + modValues.put("avgMassDelta", subMod.getAvgMassDelta()); + modValues.put("monoisotopicMassDelta", subMod.getMonoisotopicMassDelta()); + modValues.put("name", "substitution"); + modValueList.add(modValues); + } + } + peptideValues.put("modNum", modNum); + Object Peptide_pkid = parseHandler.handle("Peptide", peptideValues); + fkPeptideIdPkid.put(peptideId, Peptide_pkid); + for (Map modValues : modValueList) { + modValues.put("Peptide_pkid", Peptide_pkid); + parseHandler.handle("Modification", modValues); + } + } + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over PepEvid"); + } + Iterator iterPeptideEvidence = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.PeptideEvidence); + while (iterPeptideEvidence.hasNext()) { + PeptideEvidence peptideEvidence = iterPeptideEvidence.next(); + peptideEvidenceIdHashMap.put(peptideEvidence.getId(), peptideEvidence); + } + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over Spectra Data"); + } + Iterator iterSpectraData = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.SpectraData); + while (iterSpectraData.hasNext()) { + SpectraData spectraData = iterSpectraData.next(); + spectraDataIdHashMap.put(spectraData.getId(), spectraData); + } + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over PDH"); + } + Iterator iterPDH = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.ProteinDetectionHypothesis); + Integer pCounter = 0; + while (iterPDH.hasNext()) { + ProteinDetectionHypothesis pdh = iterPDH.next(); + pdhIdHashMap.put(pdh.getId(), pdh); + + for (CvParam cvParam : pdh.getCvParam()) { + if (cvParam.getAccession().equals("MS:1001591") || cvParam.getAccession().equals("MS:1001592") || cvParam.getAccession().equals("MS:1001593") + || cvParam.getAccession().equals("MS:1001594") || cvParam.getAccession().equals("MS:1001595") || cvParam.getAccession().equals("MS:1001596") + || cvParam.getAccession().equals("MS:1001597") + || cvParam.getAccession().equals("MS:1001598") + || cvParam.getAccession().equals("MS:1001599")) { //do nothing - these are specifically handled + //ToDO this code could be improved using an array of values... + } else if (cvParam.getValue() != null) { + if (!columnToProtScoreMap.containsValue(cvParam.getName())) { + columnToProtScoreMap.put(pCounter, cvParam.getName()); + pCounter++; + } + } + } + for (UserParam userParam : pdh.getUserParam()) { + if (!columnToProtScoreMap.containsValue(userParam.getName())) { + columnToProtScoreMap.put(pCounter, userParam.getName()); + pCounter++; + } + + } + + } + Integer counter = 0; + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to iterate over SIR"); + } + Iterator iterSIR = unmarshaller.unmarshalCollectionFromXpath(MzIdentMLElement.SpectrumIdentificationResult); + List sirList = new ArrayList<>(); + while (iterSIR.hasNext()) { + SpectrumIdentificationResult sir = iterSIR.next(); + sirList.add(sir); + + List listSII = sir.getSpectrumIdentificationItem(); + + for (SpectrumIdentificationItem sii : listSII) { + siiIdHashMap.put(sii.getId(), sii); + siiIdToSirHashMap.put(sii.getId(), sir); + for (CvParam cvParam : sii.getCvParam()) { + String value = cvParam.getValue(); + if (value != null && !value.isEmpty()) { + if (!columnToScoreMap.containsValue(cvParam.getName())) { + columnToScoreMap.put(counter, cvParam.getName()); + Class colClass = String.class; + try { + int parseInt = Integer.parseInt(value); + colClass = Integer.class; + + } catch (NumberFormatException exi) { + try { + double parseDouble = Double.parseDouble(value); + colClass = Double.class; + } catch (NumberFormatException exd) { + + } + } + scoreNameToClassMap.put(cvParam.getName(), colClass); + counter++; + } + } + } + } + } + // Add new columns to score table + parseHandler.addTableColumns("Score", scoreNameToClassMap); + if (verbose) { + System.out.println("...done"); + System.out.print(dfmt.format(new Date())); + System.out.print("About to create output"); + } + for (SpectrumIdentificationResult sir : sirList) { + String spectrumID = sir.getSpectrumID(); + SpectraData spectraData = spectraDataIdHashMap.get(sir.getSpectraDataRef()); + //String spectrumID = sir.getSpectrumID(); + Double rtInSeconds = -1.0; + String spectrumTitle = null; + // + // + // + for (CvParam cvParam : sir.getCvParam()) { + // Updated by FG: checking for old CV param 1114 or newer correct CV term 16. + if (cvParam.getAccession().equals("MS:1001114") || cvParam.getAccession().equals("MS:1000016")) { + if (cvParam.getUnitAccession().equals("UO:0000010")) { + rtInSeconds = Double.parseDouble(cvParam.getValue()); + } else if (cvParam.getUnitAccession().equals("UO:0000031")) { + rtInSeconds = Double.parseDouble(cvParam.getValue()) / 60; //Convert minutes to seconds + } else { + System.out.println("Error parsing RT - unit not recognised"); + } + } + if (cvParam.getAccession().equals("MS:1000796")) { + spectrumTitle = cvParam.getValue(); + } + } + + List listSII = sir.getSpectrumIdentificationItem(); + for (SpectrumIdentificationItem sii : listSII) { + // SpectrumIdentification (pkid INTEGER PRIMARY KEY, id TEXT, acquisitionNum INTEGER, chargeState INTEGER, rank INTEGER, passThreshold INTEGER, experimentalMassToCharge REAL, calculatedMassToCharge REAL + //, sequence TEXT, modNum INTEGER, isDecoy INTEGER, post TEXT, pre TEXT, start INTEGER, end INTEGER, DatabaseAccess TEXT, DatabaseSeq TEXT, DatabaseDescription TEXT )"; + // SpectrumIdentification (pkid INTEGER PRIMARY KEY, id TEXT, acquisitionNum INTEGER, chargeState INTEGER, rank INTEGER, passThreshold INTEGER, experimentalMassToCharge REAL, calculatedMassToCharge REAL, sequence TEXT, modNum INTEGER, isDecoy INTEGER)"; + Map psmValues = new HashMap<>(); + Map scoreValues = new HashMap<>(); + String indentificationID = sii.getId(); + //psmValues.put("id", spectrumID); // TEXT + if (spectrumIdPkidMap != null) { + if ((spectrumTitle != null) && (spectrumIdPkidMap.get(spectrumTitle) != null)) { + psmValues.put("Spectrum_pkid", spectrumIdPkidMap.get(spectrumTitle)); + } else { + psmValues.put("Spectrum_pkid", spectrumIdPkidMap.get(spectrumID)); + } + } + psmValues.put("spectrum_id", spectrumID); + psmValues.put("acquisitionNum", null); // TEXT + psmValues.put("chargeState", sii.getChargeState()); // INTEGER + psmValues.put("retentionTime", rtInSeconds >= 0 ? rtInSeconds : null); // INTEGER + psmValues.put("rank", sii.getRank()); // INTEGER + psmValues.put("passThreshold", sii.isPassThreshold()); // INTEGER + psmValues.put("experimentalMassToCharge", sii.getCalculatedMassToCharge()); // REAL + psmValues.put("calculatedMassToCharge", sii.getCalculatedMassToCharge()); // REAL + +// Map mapNameToValue = new HashMap<>(); + //Handle scores + for (AbstractParam param : sii.getParamGroup()) { + String pname = param.getName(); + String pvalue = param.getValue(); + Object value = null; + if (pvalue != null && !pvalue.isEmpty()) { + Class colClass = scoreNameToClassMap.get(pname); + if (colClass == String.class) { + value = pvalue; + } else { + try { + if (colClass == Double.class) { + value = new Double(pvalue); + } else if (colClass == Integer.class) { + value = new Integer(pvalue); + } + } catch (NumberFormatException exd) { + + } + } + //System.out.println("test1" + param.getName() + "-> " + param.getValue()); + } + scoreValues.put(param.getName(), param.getValue()); + } +// for (int i = 0; i < columnToScoreMap.size(); i++) { +// String score = columnToScoreMap.get(i); +// Object scoreValue = mapNameToValue.containsKey(score) ? mapNameToValue.get(score) : null; +// scoreValues.put(score, scoreValue); +// } + + Object SpectrumIdentification_pkid = parseHandler.handle("SpectrumIdentification", psmValues); + List peptideEvidenceRefs = sii.getPeptideEvidenceRef(); + for (PeptideEvidenceRef peptideEvidenceRef : peptideEvidenceRefs) { + PeptideEvidence peptideEvidence = peptideEvidenceIdHashMap.get(peptideEvidenceRef.getPeptideEvidenceRef()); + Object Peptide_pkid = fkPeptideIdPkid.get(peptideEvidence.getPeptideRef()); + Object DBSequence_pkid = fkDBSequenceIdPkid.get(peptideEvidence.getDBSequenceRef()); + Map peptideValues = new HashMap<>(); + peptideValues.put("SpectrumIdentification_pkid", SpectrumIdentification_pkid); + peptideValues.put("DBSequence_pkid", DBSequence_pkid); + peptideValues.put("Peptide_pkid", Peptide_pkid); + peptideValues.put("pre", peptideEvidence.getPre()); + peptideValues.put("post", peptideEvidence.getPost()); + peptideValues.put("start", peptideEvidence.getStart()); + peptideValues.put("end", peptideEvidence.getEnd()); + peptideValues.put("isDecoy", peptideEvidence.isIsDecoy()); + Object PeptideEvidence_pkid = parseHandler.handle("PeptideEvidence", peptideValues); + } + + if (!scoreValues.isEmpty()) { + scoreValues.put("spectrum_identification_id",spectrumID); + scoreValues.put("SpectrumIdentification_pkid", SpectrumIdentification_pkid); + parseHandler.handle("Score", scoreValues); + } + } + + } + if (verbose) { + System.out.println("...done"); + System.out.println(dfmt.format(new Date())); + } + } + + public void readFasta(String inputFasta) { + List pats = new ArrayList<>(); + for (String pat : FASTA_ID_PATTERNS) { + pats.add(Pattern.compile(pat)); + } + InputStream fstream = null; + try { + fstream = new FileInputStream(inputFasta); + // Get the object of DataInputStream + InputStream in = new DataInputStream(fstream); + BufferedReader br = new BufferedReader(new InputStreamReader(in)); + String line; + String currSequence = ""; + String currProtAcc = null; + String currDefline = null; + int recordCounter = 0; + while ((line = br.readLine()) != null) { + line = line.replaceAll("\n",""); + + if(line.contains(">")){ + //Insert previous into hash and reset + if(recordCounter != 0){ + currSequence = currSequence.replaceAll(" ",""); + accToSeq.put(currProtAcc, currSequence); + //System.out.println("Inserting:" + currProtAcc + "_" + currSequence); + accToDefline.put(currProtAcc, currDefline); + //System.out.println("Inserting2:" + currProtAcc + "_" + currDefline); + + currSequence = ""; + } + + try { + Header header = Header.parseFromFASTA(line); + currProtAcc = header.getAccession(); + currDefline = header.getDescription(); + } catch (Exception ex) { + line = line.replaceAll(">", ""); + for (Pattern p : pats) { + Matcher m = p.matcher(line); + if (m.matches()) { + switch (m.groupCount()) { + case 2: + currDefline = m.group(2); + case 1: + currProtAcc = m.group(1); + break; + default: + currProtAcc = line; + } + break; + } + } + } + recordCounter++; + } else { + currSequence += line; + } + } + //handle last + accToSeq.put(currProtAcc, currSequence.replaceAll(" ","")); + accToDefline.put(currProtAcc, currDefline); + //Close the input stream + in.close(); + } catch (FileNotFoundException ex) { + String methodName =Thread.currentThread().getStackTrace()[1].getMethodName(); + String className = this.getClass().getName(); + String message= "The task \""+methodName + "\" in the class \""+ className + "\" was not completed because of "+ ex.getMessage()+"."+ + "\nPlease see the reference guide at 01 for more information on this error. https://code.google.com/p/mzidentml-lib/wiki/CommonErrors "; + System.out.println (message); + } catch (IOException ex) { + String methodName =Thread.currentThread().getStackTrace()[1].getMethodName(); + String className = this.getClass().getName(); + String message= "The task \""+methodName + "\" in the class \""+ className + "\" was not completed because of "+ ex.getMessage()+"."+ + "\nPlease see the reference guide at 02 for more information on this error. https://code.google.com/p/mzidentml-lib/wiki/CommonErrors "; + System.out.println (message); + } finally { + try { + fstream.close(); + } catch (IOException ex) { + String methodName =Thread.currentThread().getStackTrace()[1].getMethodName(); + String className = this.getClass().getName(); + String message= "The task \""+methodName + "\" in the class \""+ className + "\" was not completed because of "+ ex.getMessage()+"."+ + "\nPlease see the reference guide at 02 for more information on this error. https://code.google.com/p/mzidentml-lib/wiki/CommonErrors "; + System.out.println (message); + } + } + } + + public static void main(String[] args) { + + try { + MzIdentParser mzIdentParser = new MzIdentParser(); + } catch (Exception ex) { + System.err.println("ProteomeXchangeSubmission FAILED: " + ex.getMessage()); + System.exit(1); + } + } + +} diff --git a/src/main/java/edu/umn/msi/gx/mztosqlite/MzParserHandler.java b/src/main/java/edu/umn/msi/gx/mztosqlite/MzParserHandler.java new file mode 100644 index 0000000..d378c16 --- /dev/null +++ b/src/main/java/edu/umn/msi/gx/mztosqlite/MzParserHandler.java @@ -0,0 +1,31 @@ +/* + * To change this license header, choose License Headers in Project Properties. + * To change this template file, choose Tools | Templates + * and open the template in the editor. + */ + +package edu.umn.msi.gx.mztosqlite; + +import java.util.Map; + +/** + * + * @author James E Johnson jj@umn.edu + * @version + */ +public class MzParserHandler { + MzSQLiteDB mzSQLiteDB = null; + + public MzParserHandler(MzSQLiteDB mzSQLiteDB) { + this.mzSQLiteDB = mzSQLiteDB; + } + + public Object handle(String tableName, Map values) { + return this.mzSQLiteDB.insertOrReplace(tableName, values); + } + + public void addTableColumns(String table,Map colTypes) { + mzSQLiteDB.addTableColumns(table, colTypes); + } + +} diff --git a/src/main/java/edu/umn/msi/gx/mztosqlite/MzSQLiteDB.java b/src/main/java/edu/umn/msi/gx/mztosqlite/MzSQLiteDB.java new file mode 100644 index 0000000..f808f3f --- /dev/null +++ b/src/main/java/edu/umn/msi/gx/mztosqlite/MzSQLiteDB.java @@ -0,0 +1,314 @@ +/* + * To change this license header, choose License Headers in Project Properties. + * To change this template file, choose Tools | Templates + * and open the template in the editor. + */ + +package edu.umn.msi.gx.mztosqlite; + +import java.io.File; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.Set; +import java.util.logging.Level; +import java.util.logging.Logger; +import org.tmatesoft.sqljet.core.SqlJetException; +import org.tmatesoft.sqljet.core.SqlJetTransactionMode; +import org.tmatesoft.sqljet.core.schema.ISqlJetColumnDef; +import org.tmatesoft.sqljet.core.schema.SqlJetConflictAction; +import org.tmatesoft.sqljet.core.table.ISqlJetCursor; +import org.tmatesoft.sqljet.core.table.ISqlJetTable; +import org.tmatesoft.sqljet.core.table.SqlJetDb; + +/** + * + * @author James E Johnson jj@umn.edu + * @version + */ +public class MzSQLiteDB { + public static final String CREATE_Source_TABLE = "CREATE TABLE Source (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, name TEXT, format TEXT, spectrumIDFormat TEXT, location TEXT)"; + public static final String CREATE_SpectraData_TABLE = "CREATE TABLE SpectraData (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, name TEXT, format TEXT, spectrumIDFormat TEXT, location TEXT)"; + public static final String CREATE_SearchDatabase_TABLE = "CREATE TABLE SearchDatabase (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, name TEXT, format TEXT, numDatabaseSequences INTEGER, numResidues INTEGER, releaseDate TEXT, version TEXT, location TEXT)"; + public static final String CREATE_DBSequence_TABLE = "CREATE TABLE DBSequence ( pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, id INTEGER, SearchDatabase_pkid INTEGER REFERENCES SearchDatabase(pkid), accession TEXT, description TEXT, length INTEGER, sequence TEXT)"; + public static final String CREATE_PeptideEvidence_TABLE = "CREATE TABLE PeptideEvidence (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, SpectrumIdentification_pkid INTEGER REFERENCES SpectrumIdentification(pkid), Peptide_pkid INTEGER REFERENCES Peptide(pkid), DBSequence_pkid INTEGER REFERENCES DBSequence(pkid), isDecoy INTEGER, pre TEXT, post TEXT, start INTEGER, end INTEGER)"; + public static final String CREATE_Peptide_TABLE = "CREATE TABLE Peptide ( pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, sequence TEXT, modNum INTEGER)"; + public static final String CREATE_Modification_TABLE = "CREATE TABLE Modification (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, Peptide_pkid INTEGER REFERENCES Peptide(pkid),location INTEGER, residues TEXT, replacementResidue TEXT, name TEXT, avgMassDelta REAL, monoisotopicMassDelta REAL )"; + public static final String CREATE_Score_TABLE = "CREATE TABLE Score (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, spectrum_identification_id TEXT, SpectrumIdentification_pkid INTEGER REFERENCES SpectrumIdentification(pkid) )"; + public static final String CREATE_SpectrumIdentification_TABLE = "CREATE TABLE SpectrumIdentification (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, Spectrum_pkid INTEGER, spectrum_id TEXT, acquisitionNum INTEGER, chargeState INTEGER, retentionTime REAL,rank INTEGER, passThreshold INTEGER, experimentalMassToCharge REAL, calculatedMassToCharge REAL)"; +// public static final String CREATE_Fragmentation_TABLE = "CREATE TABLE Fragmentation (pkid INTEGER PRIMARY KEY, spectrum_identification_id TEXT, charge INTEGER, index TEXT)"; + public static final String CREATE_Spectrum_TABLE = "CREATE TABLE Spectrum (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, id TEXT, acquisitionNum INTEGER, msLevel INTEGER, polarity INTEGER, peaksCount INTEGER, totIonCurrent REAL, retentionTime REAL, basePeakMZ REAL, basePeakIntensity REAL, collisionEnergy REAL, ionisationEnergy REAL, lowMZ REAL, highMZ REAL, precursorScanNum INTEGER, precursorMZ REAL, precursorCharge INTEGER, precursorIntensity REAL )"; + public static final String CREATE_Peaks_TABLE = "CREATE TABLE Peaks (pkid INTEGER PRIMARY KEY ASC AUTOINCREMENT, Spectrum_pkid INT REFERENCES Spectrum(pkid), acquisitionNum INTEGER, moz TEXT, intensity TEXT)"; + public static final String[] TABLE_DEFS = {CREATE_Source_TABLE, CREATE_SpectraData_TABLE, CREATE_SearchDatabase_TABLE, CREATE_DBSequence_TABLE, CREATE_Peptide_TABLE, CREATE_PeptideEvidence_TABLE, CREATE_Modification_TABLE, CREATE_SpectrumIdentification_TABLE, CREATE_Score_TABLE, CREATE_Spectrum_TABLE,CREATE_Peaks_TABLE}; + // Indexes + public static final String CREATE_DBSequence_DB_Accession_INDEX = "CREATE INDEX DBSequence_db_accession_idx ON DBSequence(SearchDatabase_pkid,accession)"; + public static final String CREATE_DBSequence_Accession_INDEX = "CREATE INDEX DBSequence_acc_idx ON DBSequence(accession)"; + public static final String CREATE_Peptide_sequence_INDEX = "CREATE INDEX Peptide_sequence_idx ON Peptide(sequence)"; + public static final String CREATE_PeptideEvidence_FKEYs_INDEX = "CREATE INDEX PeptideEvidence_fkey_idx on PeptideEvidence (spectrumidentification_pkid,dbsequence_pkid,peptide_pkid)"; + + public static final String[] INDEX_DEFS = {CREATE_DBSequence_Accession_INDEX, CREATE_Peptide_sequence_INDEX, CREATE_PeptideEvidence_FKEYs_INDEX}; + /* Sample Protein query: + SELECT dbs.accession, dbs.description, count(si.pkid) AS ScanCount + FROM spectrum, peptide, DBSequence dbs, peptideevidence pe, spectrumidentification si, score + WHERE pe.dbsequence_pkid = dbs.pkid + AND pe.peptide_pkid = peptide.pkid + AND pe.spectrumidentification_pkid = si.pkid + AND si.spectrum_pkid = spectrum.pkid + AND score.spectrumidentification_pkid = si.pkid + GROUP BY dbs.accession + ORDER BY ScanCount DESC; + */ + /* Sample PeptideSpetralMatch query: + SELECT CAST(Score.'PeptideShaker PSM score' as Number) AS 'PeptideShaker PSM score', + CAST(Score.'OMSSA:evalue' as Number) AS 'OMSSA:evalue',CAST(Score.'MS-GF:SpecEValue' as Number) AS 'MS-GF:SpecEValue', + CAST(Score.'theoretical mass' as Number) AS 'theoretical mass', + CAST(Score.'PeptideShaker PSM confidence' as Number) AS 'PeptideShaker PSM confidence', + Spectrum.acquisitionNum,Spectrum.msLevel,Spectrum.polarity,Spectrum.peaksCount,Spectrum.totIonCurrent, + Spectrum.retentionTime,Spectrum.basePeakMZ,Spectrum.basePeakIntensity,Spectrum.collisionEnergy, + Spectrum.ionisationEnergy,Spectrum.lowMZ,Spectrum.highMZ,Spectrum.precursorScanNum,Spectrum.precursorMZ, + Spectrum.precursorCharge,Spectrum.precursorIntensity,Spectrum.title,Peptide.sequence,Peptide.modNum,dbs.accession, si.pkid + FROM spectrum, peptide, DBSequence dbs, peptideevidence pe, spectrumidentification si, score + WHERE pe.dbsequence_pkid = dbs.pkid + AND pe.peptide_pkid = peptide.pkid + AND pe.spectrumidentification_pkid = si.pkid + AND si.spectrum_pkid = spectrum.pkid + AND score.spectrumidentification_pkid = si.pkid; + */ + String dbFilePath = null; + File dbFile = null; + SqlJetDb sqlJetDb = null; + Map> schemaMap = null; + Map columnNameMap = new HashMap<>(); + + public String sanitizeColumnName(String name) { + if (!columnNameMap.containsKey(name)) { +// columnNameMap.put(name, name.replaceAll("[-:]", "_")); + columnNameMap.put(name, name.matches("[a-zA-Z_]\\w*") ? name : "[" + name + "]"); + } + return columnNameMap.get(name); + } + + public MzSQLiteDB(String dbFilePath) { + this.dbFilePath = dbFilePath; + this.dbFile = new File(dbFilePath); + dbFile.delete(); + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.FINE, "{0} writable {1}", new Object[]{dbFile.getAbsolutePath(), dbFile.canWrite()}); + } + + SqlJetDb getDB() throws SqlJetException { + if (sqlJetDb == null) { + sqlJetDb = SqlJetDb.open(dbFile, true); + } + if (!sqlJetDb.isOpen()) { + sqlJetDb.open(); + } + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.FINER, "getDB: {0}", sqlJetDb.toString()); + return sqlJetDb; + } + + public void createTables() throws SqlJetException { + SqlJetDb db = getDB(); + createTables(db); + db.close(); + } + + + public void createTables(SqlJetDb db) throws SqlJetException { + db.beginTransaction(SqlJetTransactionMode.WRITE); + try { + for (String createTableStmt : TABLE_DEFS) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.FINE, createTableStmt); + db.createTable(createTableStmt); + } + for (String indexStmt : INDEX_DEFS) { + db.createIndex(indexStmt); + } + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } finally { + db.commit(); + } + } + + public Map> getSchemaMap() { + if (this.schemaMap == null) { + Map> schema = new HashMap<>(); + try { + StringBuilder sb = new StringBuilder(); + SqlJetDb db = getDB(); + Set tableNames = db.getSchema().getTableNames(); + for (String tableName : tableNames) { + sb.append(tableName).append("_FIELDS = ["); + Map tableMap = new HashMap<>(); + schema.put(tableName, tableMap); + List columns = db.getTable(tableName).getDefinition().getColumns(); + for (ISqlJetColumnDef column : columns) { + String columnName = column.getName(); + sb.append("'").append(columnName).append("'").append(","); + tableMap.put(columnName, column); + columnNameMap.put(columnName, columnName); + } + sb.append("]").append(System.getProperty("line.separator")); + } + this.schemaMap = schema; + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.FINER,sb.toString()); + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + } + return this.schemaMap; + } + + public void checkColumns(String tableName, Map values) { + Map tableMap = getSchemaMap().get(tableName); + for (String field : values.keySet()) { + String columnName = sanitizeColumnName(field); + if (!tableMap.containsKey(columnName)) { + addColumns(tableName, values); + break; + } + } + } + + public void addTableColumns(String tableName,Map colTypes) { + try { + SqlJetDb db = getDB(); + db.getSchema().getTableNames(); + db.beginTransaction(SqlJetTransactionMode.WRITE); + try { + ISqlJetTable table = db.getTable(tableName); + for (String field : colTypes.keySet()) { + if (table.getDefinition().getColumn(field) == null) { + String columnName = sanitizeColumnName(field); + Class colClass = colTypes.get(field); + String fieldType = colClass.isAssignableFrom(Double.class) ? "REAL" : colClass.isAssignableFrom(Integer.class) ? "INTEGER" : "TEXT"; + String alterTable = "ALTER TABLE " + tableName + " ADD COLUMN " + columnName + " " + fieldType; + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.FINE, alterTable); + db.alterTable(alterTable); + ISqlJetColumnDef column = table.getDefinition().getColumn(columnName); + getSchemaMap().get(tableName).put(field, column); + } + } + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + db.commit(); + db.close(); + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + + } + + public void addColumns(String tableName,Map values) { + try { + SqlJetDb db = getDB(); + db.getSchema().getTableNames(); + db.beginTransaction(SqlJetTransactionMode.WRITE); + try { + ISqlJetTable table = db.getTable(tableName); + for (String field : values.keySet()) { + if (table.getDefinition().getColumn(field) == null) { + String columnName = sanitizeColumnName(field); + Object value = values.get(field); + if (value != null) { + String fieldType = value instanceof Integer ? "INTEGER" : value instanceof Number ? "REAL" : "TEXT"; + String alterTable = "ALTER TABLE " + tableName + " ADD COLUMN " + columnName + " " + fieldType; + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.FINE, alterTable); + db.alterTable(alterTable); + ISqlJetColumnDef column = table.getDefinition().getColumn(columnName); + getSchemaMap().get(tableName).put(field, column); + } + } + } + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + db.commit(); + db.close(); + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + } + + public Object insertOrReplace(String tableName, Map values) { + Object rowid = null; + try { + checkColumns(tableName,values); + Map tableMap = getSchemaMap().get(tableName); + Map insertValues = new HashMap<>(); + for (String field : tableMap.keySet()) { + insertValues.put(field, null); + } + for (String field : values.keySet()) { +// insertValues.put(sanitizeColumnName(field),values.get(field)); + insertValues.put(field,values.get(field)); + } + SqlJetDb db = getDB(); + db.beginTransaction(SqlJetTransactionMode.WRITE); + try { + ISqlJetTable table = db.getTable(tableName); + rowid = table.insertByFieldNamesOr(SqlJetConflictAction.REPLACE, insertValues); + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, insertValues.toString(), ex); + } + db.commit(); + db.close(); + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + return rowid; + } + + public Object update(String tableName, Object pkid, Map values) { + Object rowid = null; + try { + checkColumns(tableName,values); + SqlJetDb db = getDB(); + db.beginTransaction(SqlJetTransactionMode.WRITE); + try { + ISqlJetTable table = db.getTable(tableName); + ISqlJetCursor lookup = table.lookup(null, pkid); + lookup.updateByFieldNames(values); + rowid = lookup.getRowId(); + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, values.toString(), ex); + } + db.commit(); + db.close(); + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + return rowid; + } + + public Map getValues(String tableName, Object pkid, Map values) { + Map rowValues = values != null ? values : new HashMap(); + try { + SqlJetDb db = getDB(); + ISqlJetTable table = db.getTable(tableName); + Map tableMap = getSchemaMap().get(tableName); + ISqlJetCursor lookup = table.lookup(null, pkid); + for (String field : tableMap.keySet()) { + rowValues.put(field, lookup.getValue(field)); + } + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + return rowValues; + } + + public static void main(String[] args) { + String dbpath = new File(args.length > 0 ? args[0] : "/Users/jj/tmp/mzSQLiteDB.sqlite").getAbsolutePath(); + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.FINE, dbpath); + try { + MzSQLiteDB mzSQLiteDB = new MzSQLiteDB(dbpath); + mzSQLiteDB.createTables(); + if (mzSQLiteDB.sqlJetDb != null && mzSQLiteDB.sqlJetDb.isOpen()) { + mzSQLiteDB.sqlJetDb.close(); + } + } catch (SqlJetException ex) { + Logger.getLogger(MzSQLiteDB.class.getName()).log(Level.SEVERE, null, ex); + } + } +} diff --git a/src/main/java/edu/umn/msi/gx/mztosqlite/MzSpectrumParser.java b/src/main/java/edu/umn/msi/gx/mztosqlite/MzSpectrumParser.java new file mode 100644 index 0000000..f966bfd --- /dev/null +++ b/src/main/java/edu/umn/msi/gx/mztosqlite/MzSpectrumParser.java @@ -0,0 +1,216 @@ +/* + * To change this license header, choose License Headers in Project Properties. + * To change this template file, choose Tools | Templates + * and open the template in the editor. + */ + +package edu.umn.msi.gx.mztosqlite; + +import java.io.File; +import java.util.ArrayList; +import java.util.HashMap; +import java.util.Iterator; +import java.util.List; +import java.util.Map; +import java.util.TreeSet; +import uk.ac.ebi.pride.tools.dta_parser.DtaFile; +import uk.ac.ebi.pride.tools.jmzreader.JMzReader; +import uk.ac.ebi.pride.tools.jmzreader.JMzReaderException; +import uk.ac.ebi.pride.tools.jmzreader.model.Spectrum; +import uk.ac.ebi.pride.tools.jmzreader.model.impl.CvParam; +import uk.ac.ebi.pride.tools.mgf_parser.MgfFile; +import uk.ac.ebi.pride.tools.ms2_parser.Ms2File; +import uk.ac.ebi.pride.tools.mzdata_parser.MzDataFile; +import uk.ac.ebi.pride.tools.mzml_wrapper.MzMlWrapper; +import uk.ac.ebi.pride.tools.mzxml_parser.MzXMLFile; +import uk.ac.ebi.pride.tools.mzxml_parser.MzXMLParsingException; +import uk.ac.ebi.pride.tools.pkl_parser.PklFile; +import uk.ac.ebi.pride.tools.pride_wrapper.PRIDEXmlWrapper; + +/** + * + * @author James E Johnson jj@umn.edu + * @version + */ +public class MzSpectrumParser { + String filepath; + ProteomicsFormat format; + Map spectrumIdPkidMap; + + public MzSpectrumParser() { + } + + public MzSpectrumParser(String filepath, ProteomicsFormat format) { + this.format = format; + this.filepath = filepath; + } + + public MzSpectrumParser(String filepath, ProteomicsFormat format, Map spectrumIdPkidMap) { + this.filepath = filepath; + this.format = format; + this.spectrumIdPkidMap = spectrumIdPkidMap; + } + + public void parseSpectrum(MzParserHandler handler) throws Exception { + parseSpectrum(filepath,format,handler); + } + + public void parseSpectrum(String filepath, ProteomicsFormat format, MzParserHandler parseHandler) throws Exception { + File input = new File(filepath); + JMzReader inputParser; + if (format == null) { + format = ProteomicsFormat.getFormat(input); + } + inputParser = getSpectrumParser(input, format); + Iterator scanIterator = inputParser.getSpectrumIterator(); + int nCurrentSpec = 0; + while (scanIterator.hasNext()) { + Spectrum s = scanIterator.next(); + Integer acquisitionNum = ++nCurrentSpec; // Default to ordinal in file + try { + /* + MS:1000768 name: Thermo nativeID format def: "controller=xsd:nonNegativeInteger scan=xsd:positiveInteger." + MS:1000769 name: Waters nativeID format def: "function=xsd:positiveInteger process=xsd:nonNegativeInteger scan=xsd:nonNegativeInteger." + MS:1000770 name: WIFF nativeID format def: "sample=xsd:nonNegativeInteger period=xsd:nonNegativeInteger cycle=xsd:nonNegativeInteger experiment=xsd:nonNegativeInteger." + MS:1000771 name: Bruker/Agilent YEP nativeID format def: "scan=xsd:nonNegativeInteger." + MS:1000772 name: Bruker BAF nativeID format def: "scan=xsd:nonNegativeInteger." + MS:1000773 name: "Bruker FID nativeID format": def: "xsd:string" + MS:1000774 name: "multiple peak list nativeID format": def: "index=xsd:nonNegativeInteger" + MS:1000775 name: "single peak list nativeID format": def: "xsd:string" + MS:1000776 name: "scan number only nativeID format": def: "scan=xsd:nonNegativeInteger" + */ + Integer scanNum = Integer.parseInt(s.getId().replaceAll("^.*?(\\d+)$","$1" )); + acquisitionNum = scanNum; + } catch (Exception e) { + } + // make sure the spectrum isn't empty + if (s == null) { + continue; + } + String spectrumID = s.getId(); + Map spectrumValues = new HashMap<>(); + Map peakList = s.getPeakList(); + int peakListLen = peakList != null ? peakList.size() : 0; + spectrumValues.put("id", spectrumID); + spectrumValues.put("acquisitionNum", acquisitionNum); + spectrumValues.put("msLevel", s.getMsLevel()); + spectrumValues.put("polarity", null); + spectrumValues.put("peaksCount", peakListLen); + spectrumValues.put("totIonCurrent", null); + spectrumValues.put("retentionTime", null); + spectrumValues.put("basePeakMZ", null); + spectrumValues.put("basePeakIntensity", null); + spectrumValues.put("collisionEnergy", null); + spectrumValues.put("ionisationEnergy", null); + spectrumValues.put("lowMZ", null); + spectrumValues.put("highMZ", null); + spectrumValues.put("precursorScanNum", null); + spectrumValues.put("precursorMZ", s.getPrecursorMZ()); + spectrumValues.put("precursorCharge", s.getPrecursorCharge()); + spectrumValues.put("precursorIntensity", s.getPrecursorIntensity()); + List cvParams = s.getAdditional().getCvParams(); + Map cvMap = new HashMap<>(); + for (CvParam cv : cvParams) { + switch (cv.getAccession()) { + case "MS:1000285": + spectrumValues.put("totIonCurrent", cv.getValue()); + break; + case "MS:1000504": + spectrumValues.put("basePeakMZ", cv.getValue()); + break; + case "MS:1000505": + spectrumValues.put("basePeakIntensity",cv.getValue()); + break; + case "MS:1000528": + spectrumValues.put("lowMZ", cv.getValue()); + break; + case "MS:1000527": + spectrumValues.put("highMZ", cv.getValue()); + break; + case "MS:1000894": + spectrumValues.put("retentionTime", cv.getValue()); + break; + case "MS:1000796": + spectrumValues.put("title", cv.getValue()); + break; + /* Additional params + CvParam("peak list scans", scan, "MS", "MS:1000797") + CvParam("Fragment mass tolerance setting", tolerance.toString(), "PRIDE", "PRIDE:0000161") + */ + default: + break; + } + } + + Object spectrum_pkid = parseHandler.handle("Spectrum", spectrumValues); + if (spectrumIdPkidMap != null) { + spectrumIdPkidMap.put(spectrumID, spectrum_pkid); + if (spectrumValues.get("title") != null) { + spectrumIdPkidMap.put((String) spectrumValues.get("title"), spectrum_pkid); + } + } + List mozArray = new ArrayList<>(); + List intensityArray = new ArrayList<>(); + TreeSet keys = new TreeSet(peakList.keySet()); + for (Double moz : keys) { + mozArray.add(moz); + intensityArray.add(peakList.get(moz)); + } + String moz = mozArray.toString().replaceAll(" ", ""); + String intensity = intensityArray.toString().replaceAll(" ", ""); + Map peakValues = new HashMap<>(); + peakValues.put("acquisitionNum", acquisitionNum); + peakValues.put("Spectrum_pkid", spectrum_pkid); + peakValues.put("moz", moz); + peakValues.put("intensity", intensity); + Object peak_pkid = parseHandler.handle("Peaks", peakValues); + } + + } + + private JMzReader getSpectrumParser(File inputFile,ProteomicsFormat format) throws Exception { + //hrow new UnsupportedOperationException("Not supported yet."); //To change body of generated methods, choose Tools | Templates. + JMzReader jMzReader = null; + if (format == null) { + format = ProteomicsFormat.getFormat(inputFile.getName()); + } + if (format != null) { + try { + switch (format) { + case MZML: + return new MzMlWrapper(inputFile); + case MGF: + return new MgfFile(inputFile); + case MZXML: + return new MzXMLFile(inputFile); + case DTA: + return new DtaFile(inputFile); + case MS2: + return new Ms2File(inputFile); + case PKL: + return new PklFile(inputFile); + case MZDATA: + return new MzDataFile(inputFile); + case PRIDEXML: + return new PRIDEXmlWrapper(inputFile); + default: + return null; + } + } catch (JMzReaderException | MzXMLParsingException e) { + throw e; + } + } + return jMzReader; + } + + public static void main(String[] args) { + + try { + MzSpectrumParser mzSpectrumParser = new MzSpectrumParser(); + } catch (Exception ex) { + System.err.println(ex.getMessage()); + System.exit(1); + } + } + +} diff --git a/src/main/java/edu/umn/msi/gx/mztosqlite/MzToSQLite.java b/src/main/java/edu/umn/msi/gx/mztosqlite/MzToSQLite.java new file mode 100644 index 0000000..ff3aa5d --- /dev/null +++ b/src/main/java/edu/umn/msi/gx/mztosqlite/MzToSQLite.java @@ -0,0 +1,169 @@ +/* + * To change this license header, choose License Headers in Project Properties. + * To change this template file, choose Tools | Templates + * and open the template in the editor. + */ + +package edu.umn.msi.gx.mztosqlite; + +import java.io.File; +import java.io.IOException; +import static java.lang.System.exit; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import java.util.logging.Level; +import java.util.logging.Logger; +import org.apache.commons.cli.BasicParser; +import org.apache.commons.cli.CommandLine; +import org.apache.commons.cli.HelpFormatter; +import org.apache.commons.cli.Options; +import org.apache.commons.cli.ParseException; +import org.apache.commons.cli.Parser; +import org.tmatesoft.sqljet.core.SqlJetException; + +/** + * + * @author James E Johnson jj@umn.edu + * @version + */ +public class MzToSQLite { + Map scanFiles = new HashMap<>(); + Map identFiles = new HashMap<>(); + Map seqDbFiles = new HashMap<>(); + String dbPath = null; + String jsonPath = null; + String tsvPath = null; + boolean verbose = true; + MzSQLiteDB mzSQLiteDB = null; + + public final void parseOptions(String[] args) { + Integer MAX_INPUTS = 100; + Parser parser = new BasicParser(); + String dbOpt = "sqlite"; + String inputFileOpt = "input"; + String inputNameOpt = "name"; + String inputIdOpt = "encoded_id"; + String verboseOpt = "verbose"; + String helpOpt = "help"; + Options options = new Options(); + options.addOption("s", dbOpt, true, "SQLite output file"); + options.addOption("v", verboseOpt, false, "verbose"); + options.addOption("h", helpOpt, false, "help"); + options.addOption("i", inputFileOpt, verbose, "input file"); + options.addOption("n", inputNameOpt, verbose, "name for input file"); + options.addOption("e", inputIdOpt, verbose, "encoded id for input file"); + options.addOption("f", inputIdOpt, verbose, "FASTA Search Database files"); + options.getOption(inputFileOpt).setArgs(MAX_INPUTS); + options.getOption(inputNameOpt).setArgs(MAX_INPUTS); + options.getOption(inputIdOpt).setArgs(MAX_INPUTS); + // create the parser + try { + // parse the command line arguments + CommandLine cli = parser.parse(options, args); + if (cli.hasOption(helpOpt)) { + HelpFormatter formatter = new HelpFormatter(); + formatter.printHelp( "java -jar MzToSQLite.jar [options] [proteomics_data_file ...]", options ); + exit(0); + } + if (cli.hasOption(verboseOpt)) { + verbose = true; + } + if (cli.hasOption(dbOpt)) { + dbPath = cli.getOptionValue(dbOpt); + mzSQLiteDB = new MzSQLiteDB(dbPath); + try { + mzSQLiteDB.createTables(); + } catch (SqlJetException ex) { + Logger.getLogger(MzToSQLite.class.getName()).log(Level.SEVERE, null, ex); + } + } + List argList = cli.getArgList(); + if (argList != null) { + for (String filePath : argList) { + File inputFile = new File(filePath); + if (inputFile.canRead()) { + try { + ProteomicsFormat format = ProteomicsFormat.getFormat(inputFile); + switch (format) { + case MZID: + identFiles.put(filePath, format); + break; + case MZML: + case MGF: + case DTA: + case MS2: + case PKL: + case MZXML: + case XML_FILE: + case MZDATA: + case PRIDEXML: + scanFiles.put(filePath, format); + break; + case FASTA: + seqDbFiles.put(filePath, format); + break; + case PEPXML: + case UNSUPPORTED: + default: + Logger.getLogger(MzToSQLite.class.getName()).log(Level.WARNING, "Unknown or unsupported format: {0}", filePath); + break; + } + } catch (IOException ex) { + Logger.getLogger(MzToSQLite.class.getName()).log(Level.SEVERE, null, ex); + } + } else { + Logger.getLogger(MzToSQLite.class.getName()).log(Level.WARNING, "Unable to read {0}", filePath); + } + } + } + } catch (ParseException exp) { + Logger.getLogger(MzToSQLite.class.getName()).log(Level.SEVERE, null, exp); + } + + } + + public void processFiles() { + Map spectrumIdPkidMap = new HashMap<>(); + MzParserHandler handler = new MzParserHandler(this.mzSQLiteDB); + for (String filepath : scanFiles.keySet()) { + ProteomicsFormat format = scanFiles.get(filepath); + Map source = new HashMap<>(); + source.put("name", filepath); + source.put("location", filepath); + source.put("format", format.toString()); + handler.handle("Source", source); + try { + MzSpectrumParser mzSpectrum = new MzSpectrumParser(filepath, format, spectrumIdPkidMap); + mzSpectrum.parseSpectrum(handler); + } catch (Exception ex) { + Logger.getLogger(MzToSQLite.class.getName()).log(Level.SEVERE, null, ex); + } + } + for (String filepath : identFiles.keySet()) { + ProteomicsFormat format = identFiles.get(filepath); + Map source = new HashMap<>(); + source.put("name", filepath); + source.put("location", filepath); + source.put("format", format.toString()); + handler.handle("Source", source); + MzIdentParser mzIdentParser = new MzIdentParser(filepath,spectrumIdPkidMap); + for (String fastapath : seqDbFiles.keySet()) { + mzIdentParser.readFasta(fastapath); + } + mzIdentParser.parseIdent(handler); + } + } + + public static void main(String[] args) { + try { + MzToSQLite mzToSQLite = new MzToSQLite(); + mzToSQLite.parseOptions(args); + mzToSQLite.processFiles(); + } catch (Exception ex) { + Logger.getLogger(MzToSQLite.class.getName()).log(Level.SEVERE, null, ex); + System.exit(1); + } + } + +} diff --git a/src/main/java/edu/umn/msi/gx/mztosqlite/ProteomicsFormat.java b/src/main/java/edu/umn/msi/gx/mztosqlite/ProteomicsFormat.java new file mode 100644 index 0000000..4059020 --- /dev/null +++ b/src/main/java/edu/umn/msi/gx/mztosqlite/ProteomicsFormat.java @@ -0,0 +1,109 @@ +package edu.umn.msi.gx.mztosqlite; + +import java.io.File; +import java.io.FileReader; +import java.io.IOException; + +/** + * The supported peak list formats. + * @author jg + * + */ +public enum ProteomicsFormat { + + DTA(".dta"), + MGF(".mgf"), + MS2(".ms2"), + PKL(".pkl"), + MZXML(".mzXML"), + XML_FILE(".xml"), + MZML(".mzML"), + MZID(".mzid"), + MZDATA(".xml"), + PRIDEXML(".xml"), + PEPXML(".pep.xml"), + FASTA(".fasta"), + UNSUPPORTED("?"); + + private final String extension; + + private ProteomicsFormat(String extension) { + this.extension = extension; + } + + public String getExtension() { + return extension; + } + + /** + * Returns the expected file format based on the filename's extension. + * Returns null in case the file type is unknown. + * + * @param filename + * @return + */ + public static ProteomicsFormat getFormat(String filename) { + filename = filename.toLowerCase(); + + for (ProteomicsFormat f : values()) { + if (filename.endsWith(f.getExtension().toLowerCase())) { + return f; + } + } + return null; + } + + public static ProteomicsFormat getFormat(File inputFile) throws IOException { + ProteomicsFormat fmt = null; + FileReader fr = null; + try { + fr = new FileReader(inputFile); + // read the first 1000 bytes + char[] buffer = new char[1000]; + fr.read(buffer); + String header = new String(buffer); + String[] lines = header.split("\\r?\\n"); + //mzid + if (header.contains(" 0 && line.startsWith(">")) { + return FASTA; + } + } + } finally { + try { + if (fr != null) { + fr.close(); + } + } catch (IOException e) { + // ignore + } + } + return UNSUPPORTED; + } + +} diff --git a/src/main/java/edu/umn/msi/gx/mztosqlite/PsmUtils.java b/src/main/java/edu/umn/msi/gx/mztosqlite/PsmUtils.java new file mode 100644 index 0000000..f435a75 --- /dev/null +++ b/src/main/java/edu/umn/msi/gx/mztosqlite/PsmUtils.java @@ -0,0 +1,234 @@ +/* + * To change this license header, choose License Headers in Project Properties. + * To change this template file, choose Tools | Templates + * and open the template in the editor. + */ + +package edu.umn.msi.gx.mztosqlite; + +import java.util.ArrayList; +import java.util.HashMap; +import java.util.List; +import java.util.Map; +import uk.ac.ebi.pride.tools.jmzreader.model.Spectrum; + +/** + * + * @author James E Johnson jj@umn.edu + * @version + */ +public class PsmUtils { + /* + filters: + "percent_tic": PercentTicFilterFactory, + "percent_max_intensity": PercentMaxSpectrumIntensityFilterFactory, + "quantile": QuantileFilterFactory, + "mz_range_absolute": MzRangeFilterFactory, + "mz_range_percent_bp": MzRangePercentBpFilterFactory, + "intensity_range": IntensityRangeFilterFactory, + MatchesIon: + ions_matched + peaks_matched + def _setup_ion_matcher(self, settings, **options): + mass_tolerance = DEFAULT_MASS_TOLERANCE + # Could be defined for this column provider or whole evaluation + # process. + if 'mass_tolerance' in options: + mass_tolerance = float(options['mass_tolerance']) + elif 'mass_tolerance' in settings: + mass_tolerance = float(settings['mass_tolerance']) + self.ion_matcher = \ + lambda ion, peak: abs(peak[0] - ion.get_mz()) < mass_tolerance + + def _ions_matched(self, ions, peaks): + ion_matcher = self.ion_matcher + return [any([ion_matcher(ion, peak) for peak in peaks]) for ion in ions] + + def _peaks_matched(self, ions, peaks): + # Probably not expected behavior + ion_matcher = self.ion_matcher + return [any([ion_matcher(ion, peak) for ion in ions]) for peak in peaks] +class UsesIonSeries(object): + """ + >>> uses_ions = UsesIonSeries() + >>> uses_ions._setup_ion_series({}, **{"ions": {"series": ["m1"]}}) + >>> from psme.peptide import Peptide + >>> class TestPsm(): peptide = Peptide("AM") + >>> psm = TestPsm() + >>> ion = uses_ions._get_ions(psm)[0] + >>> round(ion.get_mz(), 4) + 221.0954 + >>> uses_ions._setup_ion_series({"mass_type": "average"}, **{"ions": {"series": ["y1"]}}) + >>> ion = uses_ions._get_ions(psm)[0] + >>> round(ion.get_mz(), 1) # Should be 150.2206 but average doesn't really work. + 150.2 + """ + + def _setup_ion_series(self, settings, **kwds): + ion_options = kwds.get('ions', {}) or {} + self.ion_options = ion_options + + if 'mass_type' in kwds: + mass_type = kwds['mass_type'] + else: + mass_type = settings.get('mass_type', DEFAULT_MASS_TYPE) + self.calc_args = {'average': mass_type.lower().startswith('av')} + + def _get_ions(self, psm): + return get_ions(psm.peptide, self.calc_args, **self.ion_options) + + AGGREGATE_ION_METHODS = ['count', 'count_longest_stretch', 'percent', 'count_missed', 'percent_missed', 'list_matches', 'list_misses'] + AGGREGATE_PEAKS_METHODS = ['count', 'percent', 'count_missed', 'percent_missed'] + + + Spectrum + totalIonCurrent + moz + intensity + Peptide + seq + modifications + ions + + ions_matched + + + class IonsMatched(ColumnProvider, AggregatesMatches, FiltersPeaks, MatchesIons): + + def __init__(self, settings, **kwds): + super(IonsMatched, self).__init__(**kwds) + self._setup_aggregate_by(aggregate_what='ions', **kwds) + self._setup_peak_filters(**kwds) + self._setup_ion_series(settings, **kwds) + self._setup_ion_matcher(settings, **kwds) + + def calculate(self, spectra, psm): + filtered_peaks = self._filtered_peaks(spectra) + ions = self._get_ions(psm) + matched = self._ions_matched(ions, filtered_peaks) + return self._aggregate(matched, ions) + + +@register_column_provider(name="num_peaks") +class NumPeaks(ColumnProvider, FiltersPeaks): + + def __init__(self, **kwds): + super(NumPeaks, self).__init__(**kwds) + self._setup_peak_filters(**kwds) + + def calculate(self, spectra, psm): + filtered_peaks = self._filtered_peaks(spectra) + return len(filtered_peaks) + + +@register_column_provider(name="peaks_matched") + stat: #|% (un) matched + ion_series [abcxyx][123],M1,M2,internal + losses: NH3,CO + filters: + %TIC, + % + IntensityQuantile, + q partitions + k partition + Intensity%Max, + mz AbsoluteRange, + mz %Range +class PeaksMatched(NumPeaks, MatchesIons, AggregatesMatches): + + def __init__(self, settings, **kwds): + super(PeaksMatched, self).__init__(**kwds) + self._setup_aggregate_by(aggregate_what='peaks', **kwds) + self._setup_ion_series(settings, **kwds) + self._setup_ion_matcher(settings, **kwds) + + def calculate(self, spectra, psm): + filtered_peaks = self._filtered_peaks(spectra) + ions = self._get_ions(psm) + peaks_matched = self._peaks_matched(ions, filtered_peaks) + return self._aggregate(peaks_matched) + + num_peaks + filters: + percent_tic + quantile + percent_max_intensity + mz_range_absolute + mz_range_percent_bp + peaks_matched + aggregate_by + count + count_missed + percent + percent_missed + ions + [abcxyx][123],M1,M2,internal + losses: + H2O,NH3,CO + peak_filters + percent_tic + quantile + percent_max_intensity + mz_range_absolute + mz_range_percent_bp + tolerance_conditional + 0.5 + ions_matched + aggregate_by + count + count_missed + percent + percent_missed + list_matches + list_misses + [abcxyx][123],M1,M2,internal + losses: + H2O,NH3,CO + peak_filters + percent_tic + quantile + percent_max_intensity + mz_range_absolute + mz_range_percent_bp + tolerance_conditional + 0.5 + + +*/ + + public static double totalIonCurrent(Spectrum s) { + return 0; + } + + + public void getFilteredPeaks(List mozArray,List intensityArray) { + + + } + public Map getFilteredPeaks(Map peakList) { + + return null; + } + + class IntensityThresholdFilterFactory { + + double min_inten; + double max_inten; + + public IntensityThresholdFilterFactory(double min_inten, double max_inten) { + this.min_inten = min_inten; + this.max_inten = max_inten; + } + + public Map getFilteredPeaks(Map peakList) { + Map filteredList = new HashMap<>(); + for (Double moz : peakList.keySet()) { + Double inten = peakList.get(moz); + if (min_inten <= inten && inten <= max_inten) { + filteredList.put(moz, inten); + } + } + return filteredList; + } + } +} diff --git a/src/main/resources/MzIdentMLElement.cfg.xml b/src/main/resources/MzIdentMLElement.cfg.xml new file mode 100644 index 0000000..df892d4 --- /dev/null +++ b/src/main/resources/MzIdentMLElement.cfg.xml @@ -0,0 +1,771 @@ + + + + + true + false + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AbstractContact + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AbstractParam + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.AbstractParamUnitCvRefResolver + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Affiliation + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.AffiliationRefResolver + Affiliation + /MzIdentML/AuditCollection/Person/Affiliation + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AmbiguousResidue + uk.ac.ebi.jmzidml.model.mzidml.params.AmbiguousResidueCvParam + false + false + AmbiguousResidue + uk.ac.ebi.jmzidml.model.mzidml.params.AmbiguousResidueUserParam + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/MassTable/AmbiguousResidue + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AnalysisCollection + false + true + AnalysisCollection + /MzIdentML/AnalysisCollection + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AnalysisData + false + true + AnalysisData + /MzIdentML/DataCollection/AnalysisData + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AnalysisProtocolCollection + false + true + AnalysisProtocolCollection + /MzIdentML/AnalysisProtocolCollection + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AnalysisSampleCollection + false + true + AnalysisSampleCollection + /MzIdentML/AnalysisSampleCollection + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SearchDatabase + uk.ac.ebi.jmzidml.model.mzidml.params.SearchDatabaseCvParam + true + true + SearchDatabase + /MzIdentML/DataCollection/Inputs/SearchDatabase + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AnalysisSoftware + true + true + AnalysisSoftware + /MzIdentML/AnalysisSoftwareList/AnalysisSoftware + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AnalysisSoftwareList + false + true + AnalysisSoftwareList + /MzIdentML/AnalysisSoftwareList + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.AuditCollection + false + true + AuditCollection + /MzIdentML/AuditCollection + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.BibliographicReference + false + true + BibliographicReference + /MzIdentML/BibliographicReference + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ContactRole + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.ContactRoleRefResolver + ContactRole + /MzIdentML/AnalysisSoftwareList/AnalysisSoftware/ContactRole + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Cv + true + true + cv + /MzIdentML/cvList/cv + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.CvList + false + true + cvList + /MzIdentML/cvList + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.CvParam + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.CvParamRefResolver + cvParam + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.DatabaseFilters + false + false + DatabaseFilters + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/DatabaseFilters + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.DatabaseTranslation + false + true + DatabaseTranslation + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/DatabaseTranslation + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.DataCollection + false + true + DataCollection + /MzIdentML/DataCollection + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.DBSequence + uk.ac.ebi.jmzidml.model.mzidml.params.DBSequenceCvParam + true + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.DBSequenceRefResolver + DBSequence + uk.ac.ebi.jmzidml.model.mzidml.params.DBSequenceUserParam + /MzIdentML/SequenceCollection/DBSequence + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Enzyme + false + false + Enzyme + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/Enzymes/Enzyme + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Enzymes + false + false + Enzymes + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/Enzymes + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ExternalData + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.FileFormat + uk.ac.ebi.jmzidml.model.mzidml.params.FileFormatCvParam + false + false + FileFormat + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Filter + false + false + Filter + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/DatabaseFilters/Filter + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.FragmentArray + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.FragmentArrayRefResolver + FragmentArray + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/SpectrumIdentificationResult/SpectrumIdentificationItem/Fragmentation/IonType/FragmentArray + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Fragmentation + false + false + Fragmentation + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/SpectrumIdentificationResult/SpectrumIdentificationItem/Fragmentation + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.FragmentationTable + false + true + FragmentationTable + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/FragmentationTable + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Identifiable + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Inputs + false + true + Inputs + /MzIdentML/DataCollection/Inputs + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.InputSpectra + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.InputSpectraRefResolver + InputSpectra + /MzIdentML/AnalysisCollection/SpectrumIdentification/InputSpectra + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.InputSpectrumIdentifications + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.InputSpectrumIdentificationsRefResolver + InputSpectrumIdentifications + /MzIdentML/AnalysisCollection/ProteinDetection/InputSpectrumIdentifications + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.IonType + uk.ac.ebi.jmzidml.model.mzidml.params.IonTypeCvParam + false + false + IonType + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/SpectrumIdentificationResult/SpectrumIdentificationItem/Fragmentation/IonType + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.MassTable + uk.ac.ebi.jmzidml.model.mzidml.params.MassTableCvParam + true + true + MassTable + uk.ac.ebi.jmzidml.model.mzidml.params.MassTableUserParam + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/MassTable + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Measure + uk.ac.ebi.jmzidml.model.mzidml.params.MeasureCvParam + true + true + Measure + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/FragmentationTable/Measure + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Modification + uk.ac.ebi.jmzidml.model.mzidml.params.ModificationCvParam + false + false + Modification + uk.ac.ebi.jmzidml.model.mzidml.params.ModificationUserParam + /MzIdentML/SequenceCollection/Peptide/Modification + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ModificationParams + false + false + ModificationParams + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/ModificationParams + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.MzIdentML + true + true + MzIdentML + /MzIdentML + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Organization + uk.ac.ebi.jmzidml.model.mzidml.params.OrganizationCvParam + true + true + Organization + uk.ac.ebi.jmzidml.model.mzidml.params.OrganizationUserParam + /MzIdentML/AuditCollection/Organization + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Param + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ParamList + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ParentOrganization + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.ParentOrganizationRefResolver + Parent + /MzIdentML/AuditCollection/Organization/Parent + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Peptide + uk.ac.ebi.jmzidml.model.mzidml.params.PeptideCvParam + true + true + Peptide + uk.ac.ebi.jmzidml.model.mzidml.params.PeptideUserParam + /MzIdentML/SequenceCollection/Peptide + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.PeptideEvidence + uk.ac.ebi.jmzidml.model.mzidml.params.PeptideEvidenceCvParam + true + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.PeptideEvidenceResolver + PeptideEvidence + uk.ac.ebi.jmzidml.model.mzidml.params.PeptideEvidenceUserParam + /MzIdentML/SequenceCollection/PeptideEvidence + + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.PeptideEvidenceRef + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.PeptideEvidenceRefResolver + PeptideEvidenceRef + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/SpectrumIdentificationResult/SpectrumIdentificationItem/PeptideEvidenceRef + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.PeptideHypothesis + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.PeptideHypothesisRefResolver + PeptideHypothesis + /MzIdentML/DataCollection/AnalysisData/ProteinDetectionList/ProteinAmbiguityGroup/ProteinDetectionHypothesis/PeptideHypothesis + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Person + uk.ac.ebi.jmzidml.model.mzidml.params.PersonCvParam + true + true + Person + uk.ac.ebi.jmzidml.model.mzidml.params.PersonUserParam + /MzIdentML/AuditCollection/Person + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ProteinAmbiguityGroup + uk.ac.ebi.jmzidml.model.mzidml.params.ProteinAmbiguityGroupCvParam + false + true + ProteinAmbiguityGroup + uk.ac.ebi.jmzidml.model.mzidml.params.ProteinAmbiguityGroupUserParam + /MzIdentML/DataCollection/AnalysisData/ProteinDetectionList/ProteinAmbiguityGroup + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ProteinDetection + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.ProteinDetectionRefResolver + ProteinDetection + /MzIdentML/AnalysisCollection/ProteinDetection + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ProteinDetectionHypothesis + uk.ac.ebi.jmzidml.model.mzidml.params.ProteinDetectionHypothesisCvParam + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.ProteinDetectionHypothesisRefResolver + ProteinDetectionHypothesis + uk.ac.ebi.jmzidml.model.mzidml.params.ProteinDetectionHypothesisUserParam + /MzIdentML/DataCollection/AnalysisData/ProteinDetectionList/ProteinAmbiguityGroup/ProteinDetectionHypothesis + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ProteinDetectionList + uk.ac.ebi.jmzidml.model.mzidml.params.ProteinDetectionListCvParam + true + true + ProteinDetectionList + uk.ac.ebi.jmzidml.model.mzidml.params.ProteinDetectionListUserParam + /MzIdentML/DataCollection/AnalysisData/ProteinDetectionList + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ProteinDetectionProtocol + true + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.ProteinDetectionProtocolRefResolver + ProteinDetectionProtocol + /MzIdentML/AnalysisProtocolCollection/ProteinDetectionProtocol + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.ProtocolApplication + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Provider + true + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.ProviderRefResolver + Provider + /MzIdentML/Provider + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Residue + false + false + Residue + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/MassTable/Residue + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Role + uk.ac.ebi.jmzidml.model.mzidml.params.RoleCvParam + false + false + Role + /MzIdentML/AnalysisSoftwareList/AnalysisSoftware/ContactRole/Role + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Sample + uk.ac.ebi.jmzidml.model.mzidml.params.SampleCvParam + true + true + Sample + uk.ac.ebi.jmzidml.model.mzidml.params.SampleUserParam + /MzIdentML/AnalysisSampleCollection/Sample + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SearchDatabaseRef + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.SearchDatabaseRefResolver + SearchDatabaseRef + /MzIdentML/AnalysisCollection/SpectrumIdentification/SearchDatabaseRef + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SearchModification + false + false + SearchModification + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/ModificationParams/SearchModification + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SequenceCollection + false + true + SequenceCollection + /MzIdentML/SequenceCollection + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SourceFile + uk.ac.ebi.jmzidml.model.mzidml.params.SourceFileCvParam + false + false + SourceFile + uk.ac.ebi.jmzidml.model.mzidml.params.SourceFileUserParam + /MzIdentML/DataCollection/Inputs/SourceFile + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpecificityRules + uk.ac.ebi.jmzidml.model.mzidml.params.SpecificityRulesCvParam + false + false + SpecificityRules + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/ModificationParams/SearchModification/SpecificityRules + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpectraData + true + true + SpectraData + /MzIdentML/DataCollection/Inputs/SpectraData + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentification + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.SpectrumIdentificationRefResolver + SpectrumIdentification + /MzIdentML/AnalysisCollection/SpectrumIdentification + + + true + false + uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentificationItem + uk.ac.ebi.jmzidml.model.mzidml.params.SpectrumIdentificationItemCvParam + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.SpectrumIdentificationItemRefResolver + SpectrumIdentificationItem + uk.ac.ebi.jmzidml.model.mzidml.params.SpectrumIdentificationItemUserParam + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/SpectrumIdentificationResult/SpectrumIdentificationItem + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentificationItemRef + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.SpectrumIdentificationItemRefRefResolver + SpectrumIdentificationItemRef + /MzIdentML/DataCollection/AnalysisData/ProteinDetectionList/ProteinAmbiguityGroup/ProteinDetectionHypothesis/PeptideHypothesis/SpectrumIdentificationItemRef + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentificationList + uk.ac.ebi.jmzidml.model.mzidml.params.SpectrumIdentificationListCvParam + true + true + SpectrumIdentificationList + uk.ac.ebi.jmzidml.model.mzidml.params.SpectrumIdentificationListUserParam + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentificationProtocol + true + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.SpectrumIdentificationProtocolRefResolver + SpectrumIdentificationProtocol + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpectrumIdentificationResult + uk.ac.ebi.jmzidml.model.mzidml.params.SpectrumIdentificationResultCvParam + false + true + uk.ac.ebi.jmzidml.xml.jaxb.resolver.SpectrumIdentificationResultRefResolver + SpectrumIdentificationResult + uk.ac.ebi.jmzidml.model.mzidml.params.SpectrumIdentificationResultUserParam + /MzIdentML/DataCollection/AnalysisData/SpectrumIdentificationList/SpectrumIdentificationResult + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SpectrumIDFormat + uk.ac.ebi.jmzidml.model.mzidml.params.SpectrumIDFormatCvParam + false + false + SpectrumIDFormat + /MzIdentML/DataCollection/Inputs/SpectraData/SpectrumIDFormat + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SubSample + false + false + uk.ac.ebi.jmzidml.xml.jaxb.resolver.SubSampleRefResolver + SubSample + /MzIdentML/AnalysisSampleCollection/Sample/SubSample + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.SubstitutionModification + false + false + SubstitutionModification + /MzIdentML/SequenceCollection/Peptide/SubstitutionModification + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.Tolerance + uk.ac.ebi.jmzidml.model.mzidml.params.ToleranceCvParam + false + false + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.TranslationTable + uk.ac.ebi.jmzidml.model.mzidml.params.TranslationTableCvParam + true + true + TranslationTable + /MzIdentML/AnalysisProtocolCollection/SpectrumIdentificationProtocol/DatabaseTranslation/TranslationTable + + + false + false + uk.ac.ebi.jmzidml.model.mzidml.UserParam + false + false + userParam + + +