# HG changeset patch # User lain # Date 1606244108 0 # Node ID a174cbbb12dd70fa994c95e2eddca9bf819c10bb " master branch Updating" diff -r 000000000000 -r a174cbbb12dd Dockerfile --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Dockerfile Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,56 @@ + +FROM python:3.8-buster + +# set author +MAINTAINER Lain Pavot + +# set encoding +ENV LC_ALL en_US.UTF-8 +ENV LANG en_US.UTF-8 +ENV R_BASE_VERSION 4.0.3 + +ENV PLANEMO_VENV_LOCATION /planemo-venv +ENV CONDA /tmp/conda + +RUN \ + apt-get update \ + && apt-get install -y --no-install-recommends \ + ed \ + less \ + locales \ + vim-tiny \ + wget \ + ca-certificates \ + fonts-texgyre \ + && echo "en_US.UTF-8 UTF-8" >> /etc/locale.gen \ + && locale-gen en_US.utf8 \ + && /usr/sbin/update-locale LANG=en_US.UTF-8 \ + && echo "deb http://http.debian.net/debian buster main" > /etc/apt/sources.list.d/debian-unstable.list \ + && echo 'APT::Default-Release "stable";' > /etc/apt/apt.conf.d/default \ + && echo 'APT::Install-Recommends "false";' > /etc/apt/apt.conf.d/90local-no-recommends \ + && apt-get update \ + && apt-get upgrade -y \ + && apt-get install -y --no-install-recommends \ + git \ + littler \ + libhdf5-dev \ + r-cran-littler \ + r-base \ + r-base-dev \ + r-recommended \ + python-virtualenv \ + && R -e 'install.packages("batch", repos="http://cran.us.r-project.org")' \ + && pip install virtualenv \ + && python -m virtualenv "$PLANEMO_VENV_LOCATION" \ + && . "$PLANEMO_VENV_LOCATION"/bin/activate \ + && pip install --upgrade pip setuptools \ + && pip install planemo numpy \ + && planemo conda_init --conda_prefix "$CONDA" \ + && apt-get clean autoclean \ + && apt-get autoremove --yes \ + && rm -rf /var/lib/{apt,dpkg,cache,log}/ \ + && rm -rf /usr/bin/X11 \ + && rm -rf /tmp/* ; + +CMD [] + diff -r 000000000000 -r a174cbbb12dd README.md --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README.md Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,115 @@ +INTRODUCTION +============ + +This tool is part of the xcms/camera/XSeeker workflow, and it inserts +between camera and XSeeker. It takes in input a rdata producd by camera, +gather some data from mzxml original files, and create a database +containing all these informations organized in such a way that XSeeker +has just to display the data without manipulating them anymore, which +makes it a lot faster and easier to use. + + +PREREQUISITES +============= +There is not real preriquesite to understand how this tool works +and to modify it. There is a single R script - XSeekerPreparator.R - that do +all the work. + +You can make this tool work alone, but you can integrate it with galaxy. +In this case, you need to have a galaxy instance you can configure. +It is also recomended to have access to the datatypes definitions (in +the python files) to make the outputs recognized by galaxy as XSeeker's +database files. + + +DESIGN +====== +This tool is very simple and does a little number of things, so there is +only a single file: XSeekerPreparator.R . +There is a test/test.sh file that can be used as an example to know how +to use this tool. + +You will find the galaxy patches in the galaxy/ directory. These files +are not meant to be copy/paste-ed. The content of these files must be +added to the existing files of your galaxy instance + + +REQUIREMENT +===== + + - R-4.0.0 + - optparse + - xcms + - blob + - fst + - DBModelR + - stringr + - optparse + - galaxy (optional) + +#### R 4.0.0 + - `export R_MAJOR=4 R_VERSION=4.0.0 BUILD_TARGET_DIR=~/R/` + - `wget https://cran.rstudio.com/src/base/R-${R_MAJOR}/R-${R_VERSION}.tar.gz` + - `tar -xf "R-${R_VERSION}.tar.gz"` + - `cd ./R-${R_VERSION}/` + - `./configure --prefix="${BUILD_TARGET_DIR}" --with-readline="no" --with-x="no"` + - `export CC="gcc -fPIC"` + - `make` + - `make install` + +#### Packages +```bash +~/R/bin/R -e " +install.packages( + c( + 'optparse', + 'blob', + 'fst', + 'stringr', + 'optparse', + 'RSQLite', + 'remotes', + 'BiocManager' + ), repos='https://cloud.r-project.org' +)" && \ +~/R/bin/R -e ' + remotes::install_github("LainPavot/DBModelR", force=TRUE) +' && \ +~/R/bin/R -e ' + BiocManager::install("xcms") +' +``` + +#### galaxy +```bash +git clone https://github.com/galaxyproject/galaxy +``` + +DEPLOY +===== + +Install the tool in galaxy: +Open each file in the galaxy/ directory and copy their content to their +respective files in your galaxy instance. +Copy XSeekerPreparator.R in galaxy/tool/tools/LC-MSMS/ + +METADATA +-------- + + - **@name**: XSeekerPreparator + - **@version**: 1.1.2 + - **@authors**: Lain Pavot + - **@date creation**: 15/09/2020 + +NOTES +----- +Developed and tested using: + + - R 4.0.0 + - optparse 1.6.6 + - xcms 3.10.2 + - blob 1.2.1 + - fst 0.9.4 + - DBModelR + - stringr 1.4.0 + - galaxy 21.01 \ No newline at end of file diff -r 000000000000 -r a174cbbb12dd XSeekerPreparator.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/XSeekerPreparator.R Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,919 @@ + + +TOOL_NAME <- "XSeekerPreparator" +VERSION <- "1.1.2" + +OUTPUT_SPECIFIC_TOOL <- "XSeeker_Galaxy" + +ENRICHED_RDATA_VERSION <- paste("1.1.2", OUTPUT_SPECIFIC_TOOL, sep="-") +ENRICHED_RDATA_DOC <- sprintf(" +Welcome to the enriched of the output of CAMERA/xcms. +This doc was generated by the tool: %s - Version %s +To show the different variables contained in this rdata, type: + - `load('this_rdata.rdata', rdata_env <- new.env())` + - `names(rdata_env)` + +Sections +###### + + +This tools helpers +------ + The version number is somewhat special because the evolution of the + rdata's format is non-linear. + There may be different branches, each evolving separatly. + To reflect these branches's diversions, there may be a prepended + branch name following this format: + major.minor.patch-branch_name + Like this, we can process rdata with the same tool, and output + rdata formated differently, for each tool. + + + - enriched_rdata: + - Description: flag created by that tool to tell it was enriched. + - Retrieval method: enriched_rdata <- TRUE + + - enriched_rdata_version: + - Description: A flag created by that tool to tell which version of + this tool has enriched the rdata. + - Retrieval method: enriched_rdata_version <- sprintf(\"%s\", ENRICHED_RDATA_VERSION) + + - enriched_rdata_doc: + - Description: Contains the documentation string. + +Data from original mzxml file +------ + - tic: + - Description: Those are the tic values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@tic + - xcms version: 2.0 + + - mz: + - Description: Those are the m/z values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@env$mz + - xcms version: 2.0 + + - scanindex: + - Description: Those are the scanindex values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@scanindex + - xcms version: 2.0 + + - scantime: + - Description: Those are the scantime values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@scantime + - xcms version: 2.0 + + - intensity: + - Description: Those are the intensity values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@env$intensity + - xcms version: 2.0 + + - polarity: + - Description: Those are the polarity values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: as.character(xcms::xcmsRaw('original_file.mzxml')@polarity[[1]]) + - xcms version: 2.0 + +Data taken from incoming rdata +------ + - variableMetadata: + - Description: Unmodified copy of variableMetadata from incoming rdata. + - Retrieval method: rdata_file$variableMetadata + + - process_params: + - Description: Those are the processing parameters values from the + curent rdata. They have been simplified to allow easy access like: + for (params in process_params) { + if (params[[\"xfunction\"]] == \"annotatediff\") { + process_peak_picking_params(params) + } + } + - Retrieval method: + ## just he same list, but simplified + process_params <- list() + for (list_name in names(rdata_file$listOFlistArguments)) { + param_list <- list() + for (param_name in names(rdata_file$listOFlistArguments[[list_name]])) { + param_list[[param_name]] <- rdata_file$listOFlistArguments[[list_name]][[param_name]] + } + process_params[[length(process_params)+1]] <- param_list + } +", ENRICHED_RDATA_VERSION, TOOL_NAME, VERSION, ENRICHED_RDATA_VERSION) + + + +get_models <- function(path) { + if (is.null(path)) { + stop("No models to define the database schema") + } else { + message(sprintf("Loading models from %s", path)) + } + ## galaxy mangles the "@" to a "__at__" + if (substr(path, 1, 9) == "git__at__") { + path <- sub("^git__at__", "git@", path, perl=TRUE) + } + if ( + substr(path, 1, 4) == "git@" + || substr(path, length(path)-4, 4) == ".git" + ) { + return (get_models_from_git(path)) + } + if (substr(path, 1, 4) == "http") { + return (get_models_from_url(path)) + } + return (source(path)$value) +} + +get_models_from_git <- function (url, target_file="models.R", rm=TRUE) { + tmp <- tempdir() + message(sprintf("Cloning %s", url)) + system2("git", c("clone", url, tmp)) + result <- search_tree(file.path(tmp, dir), target_file) + if (!is.null(result)) { + models <- source(result)$value + if (rm) { + unlink(tmp, recursive=TRUE) + } + return (models) + } + if (rm) { + unlink(tmp, recursive=TRUE) + } + stop(sprintf( + "Could not find any file named \"%s\" in this repo", + target_file + )) +} + +get_models_from_url <- function (url, target_file="models.R", rm=TRUE) { + tmp <- tempdir() + message(sprintf("Downloading %s", url)) + result <- file.path(tmp, target_file) + if (download.file(url, destfile=result) == 0) { + models <- source(result)$value + if (rm) { + unlink(tmp, recursive=TRUE) + } + return (models) + } + if (rm) { + unlink(tmp, recursive=TRUE) + } + stop("Could not download any file at this adress.") +} + +search_tree <- function(path, target) { + target <- tolower(target) + for (file in list.files(path)) { + if (is.dir(file)) { + result <- search_tree(file.path(path, file), target) + if (!is.null(result)) { + return (result) + } + } else if (tolower(file) == target) { + return (file.path(path, file)) + } + } + return (NULL) +} + +create_database <- function(orm) { + orm$recreate_database(no_exists=FALSE) + set_database_version(orm, "created") +} + +insert_adducts <- function(orm) { + message("Creating adducts...") + adducts <- list( + list("[M-H2O-H]-",1,-1,-48.992020312000001069,1,0,0.5,"H0","H1O3"), + list("[M-H-Cl+O]-",1,-1,-19.981214542000000022,2,0,0.5,"O1","H1Cl1"), + list("[M-Cl+O]-",1,-1,-18.973389510000000512,3,0,0.5,"O1","Cl1"), + list("[M-3H]3-",1,-3,-3.0218293560000000219,4,0,1.0,"H0","H3"), + list("[2M-3H]3-",2,-3,-3.0218293560000000219,4,0,0.5,"H0","H3"), + list("[3M-3H]3-",3,-3,-3.0218293560000000219,4,0,0.5,"H0","H3"), + list("[M-2H]2-",1,-2,-2.0145529039999998666,5,0,1.0,"H0","H2"), + list("[2M-2H]2-",2,-2,-2.0145529039999998666,5,0,0.5,"H0","H2"), + list("[3M-2H]2-",3,-2,-2.0145529039999998666,5,0,0.5,"H0","H2"), + list("[M-H]-",1,-1,-1.0072764519999999333,6,1,1.0,"H0","H1"), + list("[2M-H]-",2,-1,-1.0072764519999999333,6,0,0.5,"H0","H1"), + list("[3M-H]-",3,-1,-1.0072764519999999333,6,0,0.5,"H0","H1"), + list("[M]+",1,1,-0.00054858000000000000945,7,1,1.0,"H0","H0"), + list("[M]-",1,-1,0.00054858000000000000945,8,1,1.0,"H0","H0"), + list("[M+H]+",1,1,1.0072764519999999333,9,1,1.0,"H1","H0"), + list("[2M+H]+",2,1,1.0072764519999999333,9,0,0.5,"H1","H0"), + list("[3M+H]+",3,1,1.0072764519999999333,9,0,0.25,"H1","H0"), + list("[M+2H]2+",1,2,2.0145529039999998666,10,0,0.75,"H2","H0"), + list("[2M+2H]2+",2,2,2.0145529039999998666,10,0,0.5,"H2","H0"), + list("[3M+2H]2+",3,2,2.0145529039999998666,10,0,0.25,"H2","H0"), + list("[M+3H]3+",1,3,3.0218293560000000219,11,0,0.75,"H3","H0"), + list("[2M+3H]3+",2,3,3.0218293560000000219,11,0,0.5,"H3","H0"), + list("[3M+3H]3+",3,3,3.0218293560000000219,11,0,0.25,"H3","H0"), + list("[M-2H+NH4]-",1,-1,16.019272654000001665,12,0,0.25,"N1H4","H2"), + list("[2M-2H+NH4]-",2,-1,16.019272654000001665,12,0,0.0,"N1H4","H2"), + list("[3M-2H+NH4]-",3,-1,16.019272654000001665,12,0,0.25,"N1H4","H2"), + list("[M+NH4]+",1,1,18.033825558000000199,13,1,1.0,"N1H4","H0"), + list("[2M+NH4]+",2,1,18.033825558000000199,13,0,0.5,"N1H4","H0"), + list("[3M+NH4]+",3,1,18.033825558000000199,13,0,0.25,"N1H4","H0"), + list("[M+H+NH4]2+",1,2,19.041102009999999467,14,0,0.5,"N1H5","H0"), + list("[2M+H+NH4]2+",2,2,19.041102009999999467,14,0,0.5,"N1H5","H0"), + list("[3M+H+NH4]2+",3,2,19.041102009999999467,14,0,0.25,"N1H5","H0"), + list("[M+Na-2H]-",1,-1,20.974668176000001551,15,0,0.75,"Na1","H2"), + list("[2M-2H+Na]-",2,-1,20.974668176000001551,15,0,0.25,"Na1","H2"), + list("[3M-2H+Na]-",3,-1,20.974668176000001551,15,0,0.25,"Na1","H2"), + list("[M+Na]+",1,1,22.989221080000000086,16,1,1.0,"Na1","H0"), + list("[2M+Na]+",2,1,22.989221080000000086,16,0,0.5,"Na1","H0"), + list("[3M+Na]+",3,1,22.989221080000000086,16,0,0.25,"Na1","H0"), + list("[M+H+Na]2+",1,2,23.996497531999999353,17,0,0.5,"Na1H1","H0"), + list("[2M+H+Na]2+",2,2,23.996497531999999353,17,0,0.5,"Na1H1","H0"), + list("[3M+H+Na]2+",3,2,23.996497531999999353,17,0,0.25,"Na1H1","H0"), + list("[M+2H+Na]3+",1,3,25.003773983999998619,18,0,0.25,"H2Na1","H0"), + list("[M+CH3OH+H]+",1,1,33.033491200000000276,19,0,0.25,"C1O1H5","H0"), + list("[M-H+Cl]2-",1,-2,33.962124838000001148,20,0,1.0,"Cl1","H1"), + list("[2M-H+Cl]2-",2,-2,33.962124838000001148,20,0,0.5,"Cl1","H1"), + list("[3M-H+Cl]2-",3,-2,33.962124838000001148,20,0,0.5,"Cl1","H1"), + list("[M+Cl]-",1,-1,34.969401290000000416,21,1,1.0,"Cl1","H0"), + list("[2M+Cl]-",2,-1,34.969401290000000416,21,0,0.5,"Cl1","H0"), + list("[3M+Cl]-",3,-1,34.969401290000000416,21,0,0.5,"Cl1","H0"), + list("[M+K-2H]-",1,-1,36.948605415999999479,22,0,0.5,"K1","H2"), + list("[2M-2H+K]-",2,-1,36.948605415999999479,22,0,0.0,"K1","H2"), + list("[3M-2H+K]-",3,-1,36.948605415999999479,22,0,0.0,"K1","H2"), + list("[M+K]+",1,1,38.963158319999998013,23,1,1.0,"K1","H0"), + list("[2M+K]+",2,1,38.963158319999998013,23,0,0.5,"K1","H0"), + list("[3M+K]+",3,1,38.963158319999998013,23,0,0.25,"K1","H0"), + list("[M+H+K]2+",1,2,39.970434771999997281,24,0,0.5,"K1H1","H0"), + list("[2M+H+K]2+",2,2,39.970434771999997281,24,0,0.5,"K1H1","H0"), + list("[3M+H+K]2+",3,2,39.970434771999997281,24,0,0.25,"K1H1","H0"), + list("[M+ACN+H]+",1,1,42.033825557999996646,25,0,0.25,"C2H4N1","H0"), + list("[2M+ACN+H]+",2,1,42.033825557999996646,25,0,0.25,"C2H4N1","H0"), + list("[M+2Na-H]+",1,1,44.971165708000000902,26,0,0.5,"Na2","H1"), + list("[2M+2Na-H]+",2,1,44.971165708000000902,26,0,0.25,"Na2","H1"), + list("[3M+2Na-H]+",3,1,44.971165708000000902,26,0,0.25,"Na2","H1"), + list("[2M+FA-H]-",2,-1,44.998202851999998586,27,0,0.25,"C1O2H2","H1"), + list("[M+FA-H]-",1,-1,44.998202851999998586,27,0,0.5,"C1O2H2","H1"), + list("[M+2Na]2+",1,2,45.978442160000000172,28,0,0.5,"Na2","H0"), + list("[2M+2Na]2+",2,2,45.978442160000000172,28,0,0.5,"Na2","H0"), + list("[3M+2Na]2+",3,2,45.978442160000000172,28,0,0.25,"Na2","H0"), + list("[M+H+2Na]3+",1,3,46.985718611999999438,29,0,0.25,"H1Na2","H0"), + list("[M+H+FA]+",1,1,47.012755755999997122,30,0,0.25,"C1O2H3","H0"), + list("[M+Hac-H]-",1,-1,59.013852915999997607,31,0,0.25,"C2O2H4","H1"), + list("[2M+Hac-H]-",2,-1,59.013852915999997607,31,0,0.25,"C2O2H4","H1"), + list("[M+IsoProp+H]+",1,1,61.064791327999998317,32,0,0.25,"C3H9O1","H0"), + list("[M+Na+K]2+",1,2,61.9523793999999981,33,0,0.5,"Na1K1","H0"), + list("[2M+Na+K]2+",2,2,61.9523793999999981,33,0,0.5,"Na1K1","H0"), + list("[3M+Na+K]2+",3,2,61.9523793999999981,33,0,0.25,"Na1K1","H0"), + list("[M+NO3]-",1,-1,61.988366450000000895,34,0,0.5,"N1O3","H0"), + list("[M+ACN+Na]+",1,1,64.015770185999997464,35,0,0.25,"C2H3N1Na1","H0"), + list("[2M+ACN+Na]+",2,1,64.015770185999997464,35,0,0.25,"C2H3N1Na1","H0"), + list("[M+NH4+FA]+",1,1,64.039304861999994502,36,0,0.25,"N1C1O2H6","H0"), + list("[M-2H+Na+FA]-",1,-1,66.980147479999999405,37,0,0.5,"NaC1O2H2","H2"), + list("[M+3Na]3+",1,3,68.967663239999993153,38,0,0.25,"Na3","H0"), + list("[M+Na+FA]+",1,1,68.99470038399999794,39,0,0.25,"Na1C1O2H2","H0"), + list("[M+2Cl]2-",1,-2,69.938802580000000832,40,0,1.0,"Cl2","H0"), + list("[2M+2Cl]2-",2,-2,69.938802580000000832,40,0,0.5,"Cl2","H0"), + list("[3M+2Cl]2-",3,-2,69.938802580000000832,40,0,0.5,"Cl2","H0"), + list("[M+2K-H]+",1,1,76.919040187999996758,41,0,0.5,"K2","H1"), + list("[2M+2K-H]+",2,1,76.919040187999996758,41,0,0.25,"K2","H1"), + list("[3M+2K-H]+",3,1,76.919040187999996758,41,0,0.25,"K2","H1"), + list("[M+2K]2+",1,2,77.926316639999996028,42,0,0.5,"K2","H0"), + list("[2M+2K]2+",2,2,77.926316639999996028,42,0,0.5,"K2","H0"), + list("[3M+2K]2+",3,2,77.926316639999996028,42,0,0.25,"K2","H0"), + list("[M+Br]-",1,-1,78.918886479999997619,43,1,1.0,"Br1","H0"), + list("[M+Cl+FA]-",1,-1,80.974880593999998268,44,0,0.5,"Cl1C1O2H2","H0"), + list("[M+AcNa-H]-",1,-1,80.995797543999998426,45,0,0.25,"C2H3Na1O2","H1"), + list("[M+2ACN+2H]2+",1,2,84.067651115999993292,46,0,0.25,"C4H8N2","H0"), + list("[M+K+FA]+",1,1,84.968637623999995868,47,0,0.25,"K1C1O2H2","H0"), + list("[M+Cl+Na+FA-H]-",1,-1,102.95682522200000619,48,0,0.5,"Cl1Na1C1O2H2","H1"), + list("[2M+3H2O+2H]+",2,1,104.03153939599999944,49,0,0.25,"H8O6","H0"), + list("[M+TFA-H]-",1,-1,112.98558742000000165,50,0,0.5,"C2F3O2H1","H1"), + list("[M+H+TFA]+",1,1,115.00014032400000019,51,0,0.25,"C2F3O2H2","H0"), + list("[M+3ACN+2H]2+",1,2,125.09420022199999778,52,0,0.25,"C6H11N3","H0"), + list("[M+NH4+TFA]+",1,1,132.02668943000000468,53,0,0.25,"N1C2F3O2H5","H0"), + list("[M+Na+TFA]+",1,1,136.98208495200000811,54,0,0.25,"Na1C2F3O2H1","H0"), + list("[M+Cl+TFA]-",1,-1,148.96226516199999423,55,0,0.5,"Cl1C2F3O2H1","H0"), + list("[M+K+TFA]+",1,1,152.95602219200000604,56,0,0.25,"K1C2F3O2H1","H0") + ) + dummy_adduct <- orm$adduct() + for (adduct in adducts) { + i <- 0 + dummy_adduct$set_name(adduct[[i <- i+1]]) + dummy_adduct$set_multi(adduct[[i <- i+1]]) + dummy_adduct$set_charge(adduct[[i <- i+1]]) + dummy_adduct$set_mass(adduct[[i <- i+1]]) + dummy_adduct$set_oidscore(adduct[[i <- i+1]]) + dummy_adduct$set_quasi(adduct[[i <- i+1]]) + dummy_adduct$set_ips(adduct[[i <- i+1]]) + dummy_adduct$set_formula_add(adduct[[i <- i+1]]) + dummy_adduct$set_formula_ded(adduct[[i <- i+1]]) + dummy_adduct$save() + dummy_adduct$clear(unset_id=TRUE) + } + message("Adducts created") +} + +insert_base_data <- function(orm, path, archetype=FALSE) { + if (archetype) { + ## not implemented yet + return () + } + base_data <- readLines(path) + for (sql in strsplit(paste(base_data, collapse=" "), ";")[[1]]) { + orm$execute(sql) + } + set_database_version(orm, "enriched") +} + +insert_compounds <- function(orm, compounds_path) { + compounds <- read.csv(file=compounds_path, sep="\t") + if (is.null(compounds <- translate_compounds(compounds))) { + stop("Could not find asked compound's attributes in csv file.") + } + dummy_compound <- orm$compound() + compound_list <- list() + for (i in seq_len(nrow(compounds))) { + dummy_compound$set_mz(compounds[i, "mz"]) + dummy_compound$set_name(compounds[i, "name"]) + dummy_compound$set_common_name(compounds[i, "common_name"]) + dummy_compound$set_formula(compounds[i, "formula"]) + # dummy_compound$set_mz(compounds[i, "mz"]) + # dummy_compound$set_mz(compounds[i, "mz"]) + compound_list[[length(compound_list)+1]] <- as.list( + dummy_compound, + c("mz", "name", "common_name", "formula") + ) + dummy_compound$clear(unset_id=TRUE) + } + dummy_compound$save(bulk=compound_list) +} + +translate_compounds <- function(compounds) { + recognized_headers <- list( + c("HMDB_ID", "MzBank", "X.M.H..", "X.M.H...1", "MetName", "ChemFormula", "INChIkey") + ) + header_translators <- list( + hmdb_header_translator + ) + for (index in seq_along(recognized_headers)) { + headers <- recognized_headers[[index]] + if (identical(colnames(compounds), headers)) { + return (header_translators[[index]](compounds)) + } + } + if (is.null(translator <- guess_translator(colnames(compounds)))) { + return (NULL) + } + return (csv_header_translator(translator, compounds)) +} + +guess_translator <- function(header) { + result <- list( + # HMDB_ID=NULL,< + mz=NULL, + name=NULL, + common_name=NULL, + formula=NULL, + # inchi_key=NULL + ) + asked_cols <- names(result) + for (asked_col in asked_cols) { + for (col in header) { + if ((twisted <- tolower(col)) == asked_col + || gsub("-", "_", twisted) == asked_col + || gsub(" ", "_", twisted) == asked_col + || tolower(gsub("(.)([A-Z])", "\\1_\\2", col)) == asked_col + ) { + result[[asked_col]] <- col + next + } + } + } + if (any(mapply(is.null, result))) { + return (NULL) + } + return (result) +} + +hmdb_header_translator <- function(compounds) { + return (csv_header_translator( + list( + HMDB_ID="HMDB_ID", + mz="MzBank", + name="MetName", + common_name="MetName", + formula="ChemFormula", + inchi_key="INChIkey" + ), compounds + )) +} + +csv_header_translator <- function(translation_table, csv) { + header_names <- names(translation_table) + result <- data.frame(1:nrow(csv)) + # colnames(result) <- header_names + for (i in seq_along(header_names)) { + result[, header_names[[i]]] <- csv[, translation_table[[i]]] + } + print(result[, "mz"]) + result[, "mz"] <- as.numeric(result[, "mz"]) + print(result[, "mz"]) + return (result) +} + +set_database_version <- function(orm, version) { + orm$set_tag( + version, + tag_name="database_version", + tag_table_name="XSeeker_tagging_table" + ) +} + +process_rdata <- function(orm, rdata, options) { + mzml_tmp_dir <- gather_mzml_files(rdata) + samples <- names(rdata$singlefile) + if (!is.null(options$samples)) { + samples <- samples[options$samples %in% samples] + } + show_percent <- ( + is.null(options$`not-show-percent`) + || options$`not-show-percent` == FALSE + ) + error <- tryCatch({ + process_sample_list( + orm, rdata, samples, + show_percent=show_percent + ) + NULL + }, error=function(e) { + message(e) + e + }) + if (!is.null(mzml_tmp_dir)) { + unlink(mzml_tmp_dir, recursive=TRUE) + } + if (!is.null(error)) { + stop(error) + } +} + +gather_mzml_files <- function(rdata) { + if (is.null(rdata$singlefile)) { + message("Extracting mxml files") + tmp <- tempdir() + rdata$singlefile <- utils::unzip(rdata$zipfile, exdir=tmp) + names(rdata$singlefile) <- tools::file_path_sans_ext(basename(rdata$singlefile)) + message("Extracted") + return (tmp) + } else { + message(sprintf("Not a zip file, loading files directly from path: %s", paste(rdata$singlefile, collapse=" ; "))) + } + return (NULL) +} + +process_sample_list <- function(orm, radta, sample_names, show_percent) { + file_grouping_var <- find_grouping_var(rdata$variableMetadata) + message("Processing samples.") + message(sprintf("File grouping variable: %s", file_grouping_var)) + if(is.null(file_grouping_var)) { + stop("Malformed variableMetada.") + } + + process_arg_list <- rdata$listOFlistArguments + process_params <- list() + for (list_name in names(process_arg_list)) { + param_list <- list() + for (param_name in names(process_arg_list[[list_name]])) { + param_list[[param_name]] <- process_arg_list[[list_name]][[param_name]] + } + process_params[[length(process_params)+1]] <- param_list + } + message("Parameters from previous processes extracted.") + + var_meta <- rdata$variableMetadata + align_group <- rep(0, nrow(var_meta)) + var_meta <- cbind(var_meta, align_group) + context <- new.env() + context$clusters <- list() + context$groupidx <- rdata$xa@xcmsSet@groupidx + context$peaks <- rdata$xa@xcmsSet@peaks + context$show_percent <- show_percent + + indices <- as.numeric(unique(var_meta[, file_grouping_var])) + smol_xcms_set <- orm$smol_xcms_set() + mz_tab_info <- new.env() + xcms_set <- rdata$xa@xcmsSet + g <- xcms::groups(xcms_set) + mz_tab_info$group_length <- nrow(g) + mz_tab_info$dataset_path <- xcms::filepaths(xcms_set) + mz_tab_info$sampnames <- xcms::sampnames(xcms_set) + mz_tab_info$sampclass <- xcms::sampclass(xcms_set) + mz_tab_info$rtmed <- g[,"rtmed"] + mz_tab_info$mzmed <- g[,"mzmed"] + mz_tab_info$smallmolecule_abundance_assay <- xcms::groupval(xcms_set, value="into") + blogified <- blob::blob(fst::compress_fst(serialize(mz_tab_info, NULL), compression=100)) + smol_xcms_set$set_raw(blogified)$save() + for (no in indices) { + sample_name <- names(rdata$singlefile)[[no]] + sample_path <- rdata$singlefile[[no]] + if ( + is.na(no) + || is.null(sample_path) + || !(sample_name %in% sample_names) + ) { + next + } + ms_file=xcms::xcmsRaw(sample_path) + env <- new.env() + env$variableMetadata <- var_meta[var_meta[, file_grouping_var]==no,] + env$tic <- ms_file@tic + env$mz <- ms_file@env$mz + env$scanindex <- ms_file@scanindex + env$scantime <- ms_file@scantime + env$intensity <- ms_file@env$intensity + env$polarity <- as.character(ms_file@polarity[[1]]) + env$sample_name <- sample_name + env$dataset_path <- sample_path + env$process_params <- process_params + env$enriched_rdata <- TRUE + env$enriched_rdata_version <- ENRICHED_RDATA_VERSION + env$tool_name <- TOOL_NAME + env$enriched_rdata_doc <- ENRICHED_RDATA_DOC + context$sample_no <- no + add_sample_to_database(orm, env, context, smol_xcms_set) + } + message("Features enrichment") + complete_features(orm, context) + message("Features enrichment done.") + return (NULL) +} + +find_grouping_var <- function(var_meta) { + for (grouping_var in c(".", "Bio")) { + if (!is.null(rdata$variableMetadata[[grouping_var]])) { + return (grouping_var) + } + } + return (NULL) +} + +add_sample_to_database <- function(orm, env, context, smol_xcms_set) { + message(sprintf("Processing sample %s", env$sample_name)) + sample <- ( + orm$sample() + $set_name(env$sample_name) + $set_path(env$dataset_path) + $set_kind("enriched_rdata") + $set_polarity( + if (is.null(env$polarity) || identical(env$polarity, character(0))) "" + else env$polarity + ) + $set_smol_xcms_set(smol_xcms_set) + $set_raw(blob::blob(fst::compress_fst( + serialize(env, NULL), + compression=100 + ))) + $save() + ) + load_variable_metadata(orm, sample, env$variableMetadata, context) + load_process_params(orm, sample, env$process_params) + message(sprintf("Sample %s inserted.", env$sample_name)) + return (sample) +} + + +load_variable_metadata <- function(orm, sample, var_meta, context) { + all_clusters <- orm$cluster()$all() + + next_feature_id <- get_next_id(orm$feature()$all(), "featureID") + next_cluster_id <- get_next_id(all_clusters, "clusterID") + next_pc_group <- get_next_id(all_clusters, "pc_group") + next_align_group <- get_next_id(all_clusters, "align_group") + message("Extracting features") + invisible(create_features( + orm, sample, var_meta, context, + next_feature_id, next_cluster_id, + next_pc_group, next_align_group + )) + message("Extracting features done.") + return (NULL) +} + +get_next_id <- function(models, attribute) { + if ((id <- models$max(attribute)) == Inf || id == -Inf) { + return (1) + } + return (id + 1) +} + +create_features <- function( + orm, sample, var_meta, context, + next_feature_id, next_cluster_id, + next_pc_group, next_align_group +) { + field_names <- as.list(names(orm$feature()$fields__)) + field_names[field_names=="id"] <- NULL + + features <- list() + dummy_feature <- orm$feature() + + if (show_percent <- context$show_percent) { + percent <- -1 + total <- nrow(var_meta) + } + for (row in seq_len(nrow(var_meta))) { + if (show_percent && (row / total) * 100 > percent) { + percent <- percent + 1 + message("\r", sprintf("\r%d %%", percent), appendLF=FALSE) + } + + curent_var_meta <- var_meta[row, ] + + peak_list <- context$peaks[context$groupidx[[row]], ] + sample_peak_list <- peak_list[peak_list[, "sample"] == context$sample_no, , drop=FALSE] + if (!identical(sample_peak_list, numeric(0)) && !is.null(nrow(sample_peak_list)) && nrow(sample_peak_list) != 0) { + if (!is.na(int_o <- extract_peak_var(sample_peak_list, "into"))) { + dummy_feature$set_int_o(int_o) + } + if (!is.na(int_b <- extract_peak_var(sample_peak_list, "intb"))) { + dummy_feature$set_int_b(int_b) + } + if (!is.na(max_o <- extract_peak_var(sample_peak_list, "maxo"))) { + dummy_feature$set_max_o(max_o) + } + } + + set_feature_fields_from_var_meta(dummy_feature, curent_var_meta) + + dummy_feature$set_featureID(next_feature_id) + next_feature_id <- next_feature_id + 1 + fake_iso <- dummy_feature$get_iso() + iso <- extract_iso(fake_iso) + clusterID <- extract_clusterID(fake_iso, next_cluster_id) + context$clusterID <- clusterID + dummy_feature$set_iso(iso) + create_associated_cluster( + sample, dummy_feature, clusterID, + context, curent_var_meta, next_pc_group, + next_align_group + ) + next_align_group <- next_align_group + 1 + features[[length(features)+1]] <- as.list(dummy_feature, field_names) + dummy_feature$clear() + } + message("")## +\n for previous message + message("Saving features") + dummy_feature$save(bulk=features) + message("Saved.") + return (context$clusters) +} + +extract_peak_var <- function(peak_list, var_name, selector=max) { + value <- peak_list[, var_name] + names(value) <- NULL + return (selector(value)) +} + +set_feature_fields_from_var_meta <- function(feature, var_meta) { + if (!is.null(mz <- var_meta[["mz"]]) && !is.na(mz)) { + feature$set_mz(mz) + } + if (!is.null(mzmin <- var_meta[["mzmin"]]) && !is.na(mzmin)) { + feature$set_mz_min(mzmin) + } + if (!is.null(mzmax <- var_meta[["mzmax"]]) && !is.na(mzmax)) { + feature$set_mz_max(mzmax) + } + if (!is.null(rt <- var_meta[["rt"]]) && !is.na(rt)) { + feature$set_rt(rt) + } + if (!is.null(rtmin <- var_meta[["rtmin"]]) && !is.na(rtmin)) { + feature$set_rt_min(rtmin) + } + if (!is.null(rtmax <- var_meta[["rtmax"]]) && !is.na(rtmax)) { + feature$set_rt_max(rtmax) + } + if (!is.null(isotopes <- var_meta[["isotopes"]]) && !is.na(isotopes)) { + feature$set_iso(isotopes) + } + return (feature) +} + +extract_iso <- function(weird_data) { + if (grepl("^\\[\\d+\\]", weird_data)[[1]]) { + return (sub("^\\[\\d+\\]", "", weird_data, perl=TRUE)) + } + return (weird_data) +} + +extract_clusterID <- function(weird_data, next_cluster_id){ + if (grepl("^\\[\\d+\\]", weird_data)[[1]]) { + clusterID <- stringr::str_extract(weird_data, "^\\[\\d+\\]") + clusterID <- as.numeric(stringr::str_extract(clusterID, "\\d+")) + } else { + clusterID <- 0 + } + return (clusterID + next_cluster_id) +} + +create_associated_cluster <- function( + sample, feature, grouping_variable, + context, curent_var_meta, next_pc_group, next_align_group +) { + pcgroup <- as.numeric(curent_var_meta[["pcgroup"]]) + adduct <- as.character(curent_var_meta[["adduct"]]) + annotation <- curent_var_meta[["isotopes"]] + grouping_variable <- as.character(grouping_variable) + if (is.null(cluster <- context$clusters[[grouping_variable]])) { + cluster <- context$clusters[[grouping_variable]] <- orm$cluster( + pc_group=pcgroup + next_pc_group, + adduct=adduct, + align_group=next_align_group, + # curent_group=curent_group, + clusterID=context$clusterID, + annotation=annotation + )$set_sample(sample) + } else { + if (context$clusterID != 0 && cluster$get_clusterID() == 0) { + cluster$set_clusterID(context$clusterID) + } + } + cluster$save() + feature$set_cluster(cluster) + return (feature) +} + +complete_features <- function(orm, context) { + for (cluster in context$clusters) { + features <- orm$feature()$load_by(cluster_id=cluster$get_id()) + if (features$any()) { + if (!is.null(rt <- features$mean("rt"))) { + cluster$set_mean_rt(rt)$save() + } + features_df <- as.data.frame(features) + central_feature <- features_df[grepl("^\\[M\\]", features_df[, "iso"]), ] + central_feature_into <- central_feature[["int_o"]] + if (!identical(central_feature_into, numeric(0)) && central_feature_into != 0) { + for (feature in as.vector(features)) { + feature$set_abundance( + feature$get_int_o() / central_feature_into * 100 + )$save() + } + } + } + } + return (NULL) +} + +load_process_params <- function(orm, sample, params) { + for (param_list in params) { + if (is.null(param_list[["xfunction"]])) { + next + } + if (param_list[["xfunction"]] == "annotatediff") { + load_process_params_peak_picking(orm, sample, param_list) + } + } + return (sample) +} + +load_process_params_peak_picking <- function(orm, sample, peak_picking_params) { + return (add_sample_process_parameters( + params=peak_picking_params, + params_translation=list( + ppm="ppm", + maxcharge="maxCharge", + maxiso="maxIso" + ), + param_model_generator=orm$peak_picking_parameters, + sample_param_setter=sample$set_peak_picking_parameters + )) +} + +add_sample_process_parameters <- function( + params, + params_translation, + param_model_generator, + sample_param_setter +) { + model_params <- list() + for (rdata_param_name in names(params_translation)) { + database_param_name <- params_translation[[rdata_param_name]] + if (is.null(rdata_param <- params[[rdata_param_name]])) { + next + } + model_params[[database_param_name]] <- rdata_param + } + params_models <- do.call(param_model_generator()$load_by, model_params) + if (params_models$any()) { + params_model <- params_models$first() + } else { + params_model <- do.call(param_model_generator, model_params) + params_model$save() + } + return (sample_param_setter(params_model)$save()) +} + + +library(optparse) + +option_list <- list( + optparse::make_option( + c("-v", "--version"), + action="store_true", + help="Display this tool's version and exits" + ), + optparse::make_option( + c("-i", "--input"), + type="character", + help="The rdata path to import in XSeeker" + ), + optparse::make_option( + c("-s", "--samples"), + type="character", + help="Samples to visualise in XSeeker" + ), + optparse::make_option( + c("-B", "--archetype"), + type="character", + help="The name of the base database" + ), + optparse::make_option( + c("-b", "--database"), + type="character", + help="The base database's path" + ), + optparse::make_option( + c("-c", "--compounds-csv"), + type="character", + help="The csv containing compounds" + ), + optparse::make_option( + c("-m", "--models"), + type="character", + help="The path or url (must begin with http[s]:// or git@) to the database's models" + ), + optparse::make_option( + c("-o", "--output"), + type="character", + help="The path where to output sqlite" + ), + optparse::make_option( + c("-P", "--not-show-percent"), + action="store_true", + help="Flag not to show the percents", + default=FALSE + ) +) + +options(error=function(){traceback(3)}) + +parser <- OptionParser(usage="%prog [options] file", option_list=option_list) +args <- parse_args(parser, positional_arguments=0) + +err_code <- 0 + +if (!is.null(args$options$version)) { + message(sprintf("%s %s", TOOL_NAME, VERSION)) + quit() +} + +models <- get_models(args$options$models) +orm <- DBModelR::ORM( + connection_params=list(dbname=args$options$output), + dbms="SQLite" +) + +invisible(orm$models(models)) +invisible(create_database(orm)) + +message("Database model created") + +insert_adducts(orm) + +if (!is.null(args$options$database)) { + insert_base_data(orm, args$options$database) +} +message(sprintf("Base data inserted using %s.", args$options$database)) + +if (!is.null(args$options$archetype)) { + insert_base_data(orm, args$options$archetype, archetype=TRUE) +} +if (!is.null(args$options$`compounds-csv`)) { + insert_compounds(orm, args$options$`compounds-csv`) +} + +# if (!is.null(args$options$rdata)) { +# load_rdata_in_base(args$options$rdata, args$options$samples, args$options$`not-show-percent`) +# } + + +load(args$options$input, rdata <- new.env()) + +process_rdata(orm, rdata, args$options) + +quit(status=err_code) + + diff -r 000000000000 -r a174cbbb12dd data/SERUM_v2019Jan17.tabular --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data/SERUM_v2019Jan17.tabular Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,253 @@ +HMDB_ID MzBank [M+H]+ [M-H]- MetName ChemFormula INChIkey +HMDB0000001 169.085126611 170.092403011 168.077850211 1-Methylhistidine C7H11N3O2 BRMWTNUJHUMWMS-LURJTMIESA-N +HMDB0000002 74.08439833 75.09167473 73.07712193 1,3-Diaminopropane C3H10N2 XFNJVJPLKCPIBV-UHFFFAOYSA-N +HMDB0000005 102.031694058 103.038970458 101.024417658 "2-Ketobutyric acid" C4H6O3 TYEYBOSBBBHJIV-UHFFFAOYSA-N +HMDB0000008 104.047344122 105.054620522 103.040067722 "2-Hydroxybutyric acid" C4H8O3 AFENDNXGAFYKQO-UHFFFAOYSA-N +HMDB0000010 300.172544634 301.179821034 299.165268234 2-Methoxyestrone C19H24O3 WHEUWNKSCXYKBU-QPWUGHHJSA-N +HMDB0000011 104.047344122 105.054620522 103.040067722 "(R)-3-Hydroxybutyric acid" C4H8O3 WHBMMWSBFZVSSR-GSVOUGTGSA-N +HMDB0000012 228.074621504 229.081897904 227.067345104 Deoxyuridine C9H12N2O5 MXHRCPNRJAMMIM-SHYZEUOFSA-N +HMDB0000014 227.090605919 228.097882319 226.083329519 Deoxycytidine C9H13N3O4 CKTSBUTUHBMZGZ-SHYZEUOFSA-N +HMDB0000015 346.214409448 347.221685848 345.207133048 Cortexolone C21H30O4 WHBHBVVOGNECLV-OBQKJFGGSA-N +HMDB0000016 330.219494826 331.226771226 329.212218426 Deoxycorticosterone C21H30O3 ZESRJSPZRDMNHY-YFWFAHHUSA-N +HMDB0000017 183.053157781 184.060434181 182.045881381 "4-Pyridoxic acid" C8H9NO4 HXACOUQIXZGNBF-UHFFFAOYSA-N +HMDB0000019 116.047344122 117.054620522 115.040067722 "alpha-Ketoisovaleric acid" C5H8O3 QHKABHOOEWYVLI-UHFFFAOYSA-N +HMDB0000020 152.047344122 153.054620522 151.040067722 "p-Hydroxyphenylacetic acid" C8H8O3 XQXPVVBIMDBYFF-UHFFFAOYSA-N +HMDB0000021 306.970536611 307.977813011 305.963260211 Iodotyrosine C9H10INO3 UQTZMGFTRHFAAM-ZETCQYMHSA-N +HMDB0000022 167.094628665 168.101905065 166.087352265 3-Methoxytyramine C9H13NO2 DIVQKHQLANKJQO-UHFFFAOYSA-N +HMDB0000023 104.047344122 105.054620522 103.040067722 "(S)-3-Hydroxyisobutyric acid" C4H8O3 DBXBTMSZEOQQDU-VKHMYHEASA-N +HMDB0000026 132.053492132 133.060768532 131.046215732 "Ureidopropionic acid" C4H8N2O3 JSJWCHRYRHKBBW-UHFFFAOYSA-N +HMDB0000027 241.117489371 242.124765771 240.110212971 Tetrahydrobiopterin C9H15N5O3 FNKQXYHWGSIFBK-UHFFFAOYSA-N +HMDB0000030 244.088163078 245.095439478 243.080886678 Biotin C10H16N2O3S YBJHBAHKTGYVGT-ZKWXMUAHSA-N +HMDB0000031 290.224580204 291.231856604 289.217303804 Androsterone C19H30O2 QGXBDMJGAMFCBF-HLUDHZFRSA-N +HMDB0000032 384.33921603 385.34649243 383.33193963 7-Dehydrocholesterol C27H44O UCTLRSWJYQTBFZ-DDPQNLDTSA-N +HMDB0000033 226.106590334 227.113866734 225.099313934 Carnosine C9H14N4O3 CQOVPNPJLQNMDC-ZETCQYMHSA-N +HMDB0000034 135.054495185 136.061771585 134.047218785 Adenine C5H5N5 GFFGJBXGBJISGV-UHFFFAOYSA-N +HMDB0000036 515.291673489 516.298949889 514.284397089 "Taurocholic acid" C26H45NO7S WBWWGRHZICKQGZ-HZAMXZRMSA-N +HMDB0000037 360.193674006 361.200950406 359.186397606 Aldosterone C21H28O5 PQSUYGKTWSAVDQ-SRPWZAMTSA-N +HMDB0000038 239.101839307 240.109115707 238.094562907 Dihydrobiopterin C9H13N5O3 FEMXZDUTFRTWPE-UHFFFAOYSA-N +HMDB0000039 88.0524295 89.0597059 87.0451531 "Butyric acid" C4H8O2 FERIUCNNQQJTOY-UHFFFAOYSA-N +HMDB0000042 60.021129372 61.028405772 59.013852972 "Acetic acid" C2H4O2 QTBSBXVTEAMEQO-UHFFFAOYSA-N +HMDB0000043 117.078978601 118.086255001 116.071702201 Betaine C5H11NO2 KWIUHFFTVRNATP-UHFFFAOYSA-N +HMDB0000044 176.032087988 177.039364388 175.024811588 "Ascorbic acid" C6H8O6 CIWBSHSKHKDKBQ-JLAZNSOCSA-N +HMDB0000045 347.063084339 348.070360739 346.055807939 "Adenosine monophosphate" C10H14N5O7P UDMBCSSLTHHNCD-KQYNXXCUSA-N +HMDB0000050 267.096753929 268.104030329 266.089477529 Adenosine C10H13N5O4 OIRDTQYFTABQOQ-KQYNXXCUSA-N +HMDB0000051 17.026549101 18.033825501 16.019272701 Ammonia H3N QGZKDVFQNNGYKY-UHFFFAOYSA-N +HMDB0000052 290.122634328 291.129910728 289.115357928 "Argininosuccinic acid" C10H18N4O6 KDZOASGQNOPSCU-WDSKDSINSA-N +HMDB0000053 286.193280076 287.200556476 285.186003676 Androstenedione C19H26O2 AEMFNILZOJDQLW-QAGGRKNESA-N +HMDB0000054 584.263484904 585.270761304 583.256208504 Bilirubin C33H36N4O6 BPYKTIZUTYGOLE-IFADSCNNSA-N +HMDB0000056 89.047678473 90.054954873 88.040402073 beta-Alanine C3H7NO2 UCMIRNVEIXFBKS-UHFFFAOYSA-N +HMDB0000058 329.052519653 330.059796053 328.045243253 "Cyclic AMP" C10H12N5O6P IVOMOUWHDPKRLL-KQYNXXCUSA-N +HMDB0000060 102.031694058 103.038970458 101.024417658 "Acetoacetic acid" C4H6O3 WDJHALXBUFZDSR-UHFFFAOYSA-N +HMDB0000062 161.105193351 162.112469751 160.097916951 L-Carnitine C7H15NO3 PHIQHXFUZVPYII-ZCFIWIBFSA-N +HMDB0000063 362.20932407 363.21660047 361.20204767 Cortisol C21H30O5 JYGXADMDTFJGBT-VWUMJDOOSA-N +HMDB0000064 131.069476547 132.076752947 130.062200147 Creatine C4H9N3O2 CVSVTCORWBXHQV-UHFFFAOYSA-N +HMDB0000067 386.354866094 387.362142494 385.347589694 Cholesterol C27H46O HVYWMOMLDIMFJA-DPAQBDIFSA-N +HMDB0000068 183.089543287 184.096819687 182.082266887 Epinephrine C9H13NO3 UCTWMZQNUQWSLP-VIFPVBQESA-N +HMDB0000070 129.078978601 130.086255001 128.071702201 "Pipecolic acid" C6H11NO2 HXEACLLIILLPRG-UHFFFAOYSA-N +HMDB0000071 252.085854882 253.093131282 251.078578482 Deoxyinosine C10H12N4O4 VGONTNSXDCQUGY-RRKCRQDMSA-N +HMDB0000073 153.078978601 154.086255001 152.071702201 Dopamine C8H11NO2 VYFYYTLLBUKUHU-UHFFFAOYSA-N +HMDB0000076 114.042927446 115.050203846 113.035651046 Dihydrouracil C4H6N2O2 OIVLITBTBDPEFK-UHFFFAOYSA-N +HMDB0000077 288.20893014 289.21620654 287.20165374 Dehydroepiandrosterone C19H28O2 FMGSKLZLMKYGDP-USOAJAOKSA-N +HMDB0000078 178.041212886 179.048489286 177.033936486 Cysteinylglycine C5H10N2O3S ZUKPVRWZDMRIEO-VKHMYHEASA-N +HMDB0000079 128.05857751 129.06585391 127.05130111 Dihydrothymine C5H8N2O2 NBAKTGXDIBVZOO-UHFFFAOYSA-N +HMDB0000085 267.096753929 268.104030329 266.089477529 Deoxyguanosine C10H13N5O4 YKBGVTZYEHREMT-KVQBGUIXSA-N +HMDB0000086 257.102823889 258.110100289 256.095547489 Glycerophosphocholine C8H20NO6P SUHOQUVVVLNYQR-QMMMGPOBSA-N +HMDB0000087 45.057849229 46.065125629 44.050572829 Dimethylamine C2H7N ROSDSFDQCJNGOL-UHFFFAOYSA-N +HMDB0000089 243.085520541 244.092796941 242.078244141 Cytidine C9H13N3O5 UHDGCWIWMRVCDJ-XVFCMESISA-N +HMDB0000092 103.063328537 104.070604937 102.056052137 Dimethylglycine C4H9NO2 FFDGPVCHZBVARC-UHFFFAOYSA-N +HMDB0000094 192.02700261 193.03427901 191.01972621 "Citric acid" C6H8O7 KRKNYBCHXYNGOX-UHFFFAOYSA-N +HMDB0000097 104.107539075 105.114815475 103.100262675 Choline C5H14NO OEYIOHPDSNJKLS-UHFFFAOYSA-N +HMDB0000098 150.05282343 151.06009983 149.04554703 D-Xylose C5H10O5 SRBFZHDQGSBBOR-IOVATXLUSA-N +HMDB0000099 222.067427636 223.074704036 221.060151236 L-Cystathionine C7H14N2O4S ILRYLPWNYFXEMH-WHFBIAKZSA-N +HMDB0000101 251.101839307 252.109115707 250.094562907 Deoxyadenosine C10H13N5O3 OLXZPDWKRNYJJZ-RRKCRQDMSA-N +HMDB0000107 182.07903818 183.08631458 181.07176178 Galactitol C6H14O6 FBPFZTCFMRRESA-GUCUJZIJSA-N +HMDB0000108 46.041864814 47.049141214 45.034588414 Ethanol C2H6O LFQSCWFLJHTTHZ-UHFFFAOYSA-N +HMDB0000112 103.063328537 104.070604937 102.056052137 "gamma-Aminobutyric acid" C4H9NO2 BTCSSZJGUNDROE-UHFFFAOYSA-N +HMDB0000115 76.016043994 77.023320394 75.008767594 "Glycolic acid" C2H4O3 AEMRFAOFKBGASW-UHFFFAOYSA-N +HMDB0000118 182.057908808 183.065185208 181.050632408 "Homovanillic acid" C9H10O4 QRMZSPFSDQBLIX-UHFFFAOYSA-N +HMDB0000119 74.00039393 75.00767033 72.99311753 "Glyoxylic acid" C2H2O3 HHLFWLYXYJOTON-UHFFFAOYSA-N +HMDB0000121 441.139681375 442.146957775 440.132404975 "Folic acid" C19H19N7O6 OVBPIULPVIDEAO-LBPRGKRZSA-N +HMDB0000122 180.063388116 181.070664516 179.056111716 D-Glucose C6H12O6 WQZGKKKJIJFFOK-GASJEMHNSA-N +HMDB0000123 75.032028409 76.039304809 74.024752009 Glycine C2H5NO2 DHMQDGOQFOQNFH-UHFFFAOYSA-N +HMDB0000124 260.029718526 261.036994926 259.022442126 "Fructose 6-phosphate" C6H13O9P GSXOAOHZAIYLCY-HSUXUTPPSA-N +HMDB0000125 307.083805981 308.091082381 306.076529581 Glutathione C10H17N3O6S RWSXRVCMGQZWBV-WDSKDSINSA-N +HMDB0000126 172.013674532 173.020950932 171.006398132 "Glycerol 3-phosphate" C3H9O6P AWUCVROLDVIAJX-GSVOUGTGSA-N +HMDB0000127 194.042652674 195.049929074 193.035376274 "D-Glucuronic acid" C6H10O7 AEMOLEFTQBMNLQ-WAXACMCWSA-N +HMDB0000128 117.053826483 118.061102883 116.046550083 "Guanidoacetic acid" C3H7N3O2 BPMFZUMJYQTVII-UHFFFAOYSA-N +HMDB0000130 168.042258744 169.049535144 167.034982344 "Homogentisic acid" C8H8O4 IGMNYECMUMZDDF-UHFFFAOYSA-N +HMDB0000131 92.047344122 93.054620522 91.040067722 Glycerol C3H8O3 PEDCQBHIVMGVHV-UHFFFAOYSA-N +HMDB0000133 283.091668551 284.098944951 282.084392151 Guanosine C10H13N5O5 NYHBQMYGNKIUIF-UUOKFMHZSA-N +HMDB0000134 116.010958616 117.018235016 115.003682216 "Fumaric acid" C4H4O4 VZCYOOQTPOCHFL-OWOJBTEDSA-N +HMDB0000138 465.309038113 466.316314513 464.301761713 "Glycocholic acid" C26H43NO6 RFDAIACWWDREDC-MZMBZMQMSA-N +HMDB0000139 106.02660868 107.03388508 105.01933228 "Glyceric acid" C3H6O4 RBNPOMFGQQGHHO-UWTATZPHSA-N +HMDB0000140 811.690118957 812.697395357 810.682842557 Glucosylceramide C48H93NO8 POQRWMRXUOPCLD-XNWFPASESA-N +HMDB0000142 46.005479308 47.012755708 44.998202908 "Formic acid" CH2O2 BDAGIHXWWSANSR-UHFFFAOYSA-N +HMDB0000143 180.063388116 181.070664516 179.056111716 D-Galactose C6H12O6 WQZGKKKJIJFFOK-PHYPRBDBSA-N +HMDB0000145 270.161979948 271.169256348 269.154703548 Estrone C18H22O2 DNXHEGUUPJUMQT-CBZIJGRNSA-N +HMDB0000148 147.053157781 148.060434181 146.045881381 "L-Glutamic acid" C5H9NO4 WHUUTDBJXJRKMK-VKHMYHEASA-N +HMDB0000149 61.052763851 62.060040251 60.045487451 Ethanolamine C2H7NO HZAXFHJVJLSVMW-UHFFFAOYSA-N +HMDB0000150 178.047738052 179.055014452 177.040461652 Gluconolactone C6H10O6 PHOQVHQSTUBQQK-SQOUGZDYSA-N +HMDB0000151 272.177630012 273.184906412 271.170353612 Estradiol C18H24O2 VOXZDWNPVJITMN-ZBRFXRBCSA-N +HMDB0000152 154.026608673 155.033885073 153.019332273 "Gentisic acid" C7H6O4 WXTMDXOMEHJXQO-UHFFFAOYSA-N +HMDB0000153 288.172544634 289.179821034 287.165268234 Estriol C18H24O3 PROQIPRRNZUXQM-ZXXIGWHRSA-N +HMDB0000156 134.021523302 135.028799702 133.014246902 "L-Malic acid" C4H6O5 BJEPYKJPYRNKOW-REOHCLBHSA-N +HMDB0000157 136.03851077 137.04578717 135.03123437 Hypoxanthine C5H4N4O FDGQSTZJBFJUBT-UHFFFAOYSA-N +HMDB0000158 181.073893223 182.081169623 180.066616823 L-Tyrosine C9H11NO3 OUYCCCASQSFEME-QMMMGPOBSA-N +HMDB0000159 165.078978601 166.086255001 164.071702201 L-Phenylalanine C9H11NO2 COLNVLDHVKWLRT-QMMMGPOBSA-N +HMDB0000161 89.047678473 90.054954873 88.040402073 L-Alanine C3H7NO2 QNAYBMKLOCPYGJ-REOHCLBHSA-N +HMDB0000162 115.063328537 116.070604937 114.056052137 L-Proline C5H9NO2 ONIBWKKTOPOVIA-BYPYZUCNSA-N +HMDB0000163 342.116211546 343.123487946 341.108935146 D-Maltose C12H22O11 GUBGYTABKSRVRQ-DKBJLJRDSA-N +HMDB0000164 31.042199165 32.049475565 30.034922765 Methylamine CH5N BAVYZALUXZFZLV-UHFFFAOYSA-N +HMDB0000167 119.058243159 120.065519559 118.050966759 L-Threonine C4H9NO3 AYFVYJQAPQTCCC-GBXIJSLDSA-N +HMDB0000168 132.053492132 133.060768532 131.046215732 L-Asparagine C4H8N2O3 DCXYFEDJOCDNAF-REOHCLBHSA-N +HMDB0000169 180.063388116 181.070664516 179.056111716 D-Mannose C6H12O6 WQZGKKKJIJFFOK-QTVWNMPRSA-N +HMDB0000172 131.094628665 132.101905065 130.087352265 L-Isoleucine C6H13NO2 AGPKZVBTJJNPAG-WHFBIAKZSA-N +HMDB0000174 164.068473494 165.075749894 163.061197094 L-Fucose C6H12O5 SHZGCJCMOBCMKK-DHVFOXMCSA-N +HMDB0000175 348.047099924 349.054376324 347.039823524 "Inosinic acid" C10H13N4O8P GRSZFWQUAKGDAV-KQYNXXCUSA-N +HMDB0000176 116.010958616 117.018235016 115.003682216 "Maleic acid" C4H4O4 VZCYOOQTPOCHFL-UPHRSURJSA-N +HMDB0000177 155.069476547 156.076752947 154.062200147 L-Histidine C6H9N3O2 HNDVDQJCIGZPNO-YFKPBYRVSA-N +HMDB0000181 197.068807845 198.076084245 196.061531445 L-Dopa C9H11NO4 WTDRDQBEARUVNC-LURJTMIESA-N +HMDB0000182 146.105527702 147.112804102 145.098251302 L-Lysine C6H14N2O2 KDXKERNSBIXSRK-YFKPBYRVSA-N +HMDB0000186 342.116211546 343.123487946 341.108935146 Alpha-Lactose C12H22O11 GUBGYTABKSRVRQ-XLOQQCSPSA-N +HMDB0000187 105.042593095 106.049869495 104.035316695 L-Serine C3H7NO3 MTCFGRXMJLQNBG-REOHCLBHSA-N +HMDB0000190 90.031694058 91.038970458 89.024417658 "L-Lactic acid" C3H6O3 JVTAAEKCZFNVCJ-REOHCLBHSA-N +HMDB0000191 133.037507717 134.044784117 132.030231317 "L-Aspartic acid" C4H7NO4 CKLJMWTZIZZHCS-REOHCLBHSA-N +HMDB0000192 240.023848262 241.031124662 239.016571862 L-Cystine C6H12N2O4S2 LEVWYRKDKASIDU-IMJSIDKUSA-N +HMDB0000193 192.02700261 193.03427901 191.01972621 "Isocitric acid" C6H8O7 ODBLHEXUDAPZAU-UHFFFAOYSA-N +HMDB0000194 240.122240398 241.129516798 239.114963998 Anserine C10H16N4O3 MYYIAHXIVFADCU-QMMMGPOBSA-N +HMDB0000195 268.080769514 269.088045914 267.073493114 Inosine C10H12N4O5 UGQMRVRMYYASKQ-KQYNXXCUSA-N +HMDB0000197 175.063328537 176.070604937 174.056052137 "Indoleacetic acid" C10H9NO2 SEOVTRFCIGRIMH-UHFFFAOYSA-N +HMDB0000201 203.115758031 204.123034431 202.108481631 L-Acetylcarnitine C9H17NO4 RDHQFKQIGNGIED-MRVPVSSYSA-N +HMDB0000202 118.02660868 119.03388508 117.01933228 "Methylmalonic acid" C4H6O4 ZIYVHBGGAOATLY-UHFFFAOYSA-N +HMDB0000205 164.047344122 165.054620522 163.040067722 "Phenylpyruvic acid" C9H8O3 BTNMPGBKDVTSJY-UHFFFAOYSA-N +HMDB0000206 188.116092388 189.123368788 187.108815988 N6-Acetyl-L-lysine C8H16N2O3 DTERQYGMUDWYAZ-ZETCQYMHSA-N +HMDB0000207 282.255880332 283.263156732 281.248603932 "Oleic acid" C18H34O2 ZQPPMHVWECSIRJ-KTKRTIGZSA-N +HMDB0000208 146.021523302 147.028799702 145.014246902 "Oxoglutaric acid" C5H6O5 KPGXRSRHYNQIFN-UHFFFAOYSA-N +HMDB0000209 136.0524295 137.0597059 135.0451531 "Phenylacetic acid" C8H8O2 WLJVXDMOQOGPHL-UHFFFAOYSA-N +HMDB0000210 219.110672659 220.117949059 218.103396259 "Pantothenic acid" C9H17NO5 GHOKWGTUZJEAQD-ZETCQYMHSA-N +HMDB0000211 180.063388116 181.070664516 179.056111716 myo-Inositol C6H12O6 CDAISMWEOUEBRE-GPIVLXJGSA-N +HMDB0000214 132.089877638 133.097154038 131.082601238 Ornithine C5H12N2O2 AHLPHDHHMVZTML-BYPYZUCNSA-N +HMDB0000215 221.089937217 222.097213617 220.082660817 N-Acetyl-D-glucosamine C8H15NO6 OVRNDRQMDRJTHS-RTRLPJTCSA-N +HMDB0000216 169.073893223 170.081169623 168.066616823 Norepinephrine C8H11NO3 SFLSHLFXELFNJZ-QMMMGPOBSA-N +HMDB0000217 744.083277073 745.090553473 743.076000673 NADP C21H29N7O17P3 XJLXINKUBYWONI-NNYOXOHSSA-O +HMDB0000220 256.240230268 257.247506668 255.232953868 "Palmitic acid" C16H32O2 IPCSVZSSVZVIGE-UHFFFAOYSA-N +HMDB0000221 745.091102105 746.098378505 744.083825705 NADPH C21H30N7O17P3 ACFIXJIJDZMPPO-NCHANQSKSA-N +HMDB0000222 399.334858933 400.342135333 398.327582533 L-Palmitoylcarnitine C23H45NO4 XOMRRQXKHMYMOC-OAQYLSRUSA-N +HMDB0000224 141.019094261 142.026370661 140.011817861 O-Phosphoethanolamine C2H8NO4P SUHOOTKUPISOBE-UHFFFAOYSA-N +HMDB0000225 160.037173366 161.044449766 159.029896966 "Oxoadipic acid" C6H8O5 FGSBNBBHOZHUBO-UHFFFAOYSA-N +HMDB0000226 156.017106626 157.024383026 155.009830226 "Orotic acid" C5H4N2O4 PXQPEWDEAKTCGB-UHFFFAOYSA-N +HMDB0000227 148.073558872 149.080835272 147.066282472 "Mevalonic acid" C6H12O4 KJTLQQUUPVSXIM-UHFFFAOYSA-N +HMDB0000228 94.041864814 95.049141214 93.034588414 Phenol C6H6O ISWSIDIOOBJBQZ-UHFFFAOYSA-N +HMDB0000229 334.056601978 335.063878378 333.049325578 "Nicotinamide ribotide" C11H15N2O8P DAYLJWODMCOQEW-TURQNECASA-N +HMDB0000230 309.105981211 310.113257611 308.098704811 "N-Acetylneuraminic acid" C11H19NO9 SQVRNKJHWKZAKO-PFQGKNLYSA-N +HMDB0000232 167.021857653 168.029134053 166.014581253 "Quinolinic acid" C7H5NO4 GJAWHXHKYYXBSV-UHFFFAOYSA-N +HMDB0000234 288.20893014 289.21620654 287.20165374 Testosterone C19H28O2 MUMGGOZAMZWBJJ-DYKIIFRCSA-N +HMDB0000235 265.112306876 266.119583276 264.105030476 Thiamine C12H17N4OS JZRWCGZRTZMZEH-UHFFFAOYSA-N +HMDB0000237 74.036779436 75.044055836 73.029503036 "Propionic acid" C3H6O2 XBDQKXXYIPTUBI-UHFFFAOYSA-N +HMDB0000239 169.073893223 170.081169623 168.066616823 Pyridoxine C8H11NO3 LXNHXLLTXMVWPM-UHFFFAOYSA-N +HMDB0000240 81.97246462 82.97974102 80.96518822 Sulfite H2O3S LSNNMFCWUKXFEE-UHFFFAOYSA-N +HMDB0000241 562.258005596 563.265281996 561.250729196 "Protoporphyrin IX" C34H34N4O4 KSFOVUSSGSKXFI-UJJXFSCMSA-N +HMDB0000243 88.016043994 89.023320394 87.008767594 "Pyruvic acid" C3H4O3 LCTONWCANYUPML-UHFFFAOYSA-N +HMDB0000244 376.138284392 377.145560792 375.131007992 Riboflavin C17H20N4O6 AUNGANRZJHBGPY-SCRDCRAPSA-N +HMDB0000245 226.095356946 227.102633346 225.088080546 Porphobilinogen C10H14N2O4 QSHWIQZFGQKFMA-UHFFFAOYSA-N +HMDB0000246 72.057514878 73.064791278 71.050238478 Tetrahydrofuran C4H8O WYURNTSHIVDZCO-UHFFFAOYSA-N +HMDB0000247 182.07903818 183.08631458 181.07176178 Sorbitol C6H14O6 FBPFZTCFMRRESA-JGWLITMVSA-N +HMDB0000248 776.686681525 777.693957925 775.679405125 Thyroxine C15H11I4NO4 XUIIKFGFIJCVMT-LBPRGKRZSA-N +HMDB0000250 177.943225506 178.950501906 176.935949106 Pyrophosphate H4O7P2 XPPKVPWEQAFLFU-UHFFFAOYSA-N +HMDB0000251 125.014663785 126.021940185 124.007387385 Taurine C2H7NO3S XOAAWQZATWQOTB-UHFFFAOYSA-N +HMDB0000252 299.282429433 300.289705833 298.275153033 Sphingosine C18H37NO2 WWUZIQQURGPMPG-CCEZHUSRSA-N +HMDB0000253 316.240230268 317.247506668 315.232953868 Pregnenolone C21H32O2 ORNBQBCIOKFOEO-QGVNFLHTSA-N +HMDB0000254 118.02660868 119.03388508 117.01933228 "Succinic acid" C4H6O4 KDYFGRWQOYBRFD-UHFFFAOYSA-N +HMDB0000256 410.3912516 411.398528 409.3839752 Squalene C30H50 YYGNTYWPHWGJRM-FLHYQJCXSA-N +HMDB0000257 113.94453531 114.95181171 112.93725891 Thiosulfate H2O3S2 DHCDFWKWKRSZHF-UHFFFAOYSA-N +HMDB0000258 342.116211546 343.123487946 341.108935146 Sucrose C12H22O11 CZMRCDWAGMRECN-UGDNZRGBSA-N +HMDB0000259 176.094963016 177.102239416 175.087686616 Serotonin C10H12N2O QZAYGJVTTNCVMB-UHFFFAOYSA-N +HMDB0000262 126.042927446 127.050203846 125.035651046 Thymine C5H6N2O2 RWQNBRDOKXIBIV-UHFFFAOYSA-N +HMDB0000263 167.982374404 168.989650804 166.975098004 "Phosphoenolpyruvic acid" C3H5O6P DTBNBXWJWCWCIK-UHFFFAOYSA-N +HMDB0000265 650.790038137 651.797314537 649.782761737 Liothyronine C15H12I3NO4 AUYYCJSJGJYCDS-LBPRGKRZSA-N +HMDB0000267 129.042593095 130.049869495 128.035316695 "Pyroglutamic acid" C5H7NO3 ODHCTXKNWHHXJC-VKHMYHEASA-N +HMDB0000268 350.245709576 351.252985976 349.238433176 Tetrahydrocorticosterone C21H34O4 RHQQHZQUAMFINJ-DSCSGEDNSA-N +HMDB0000269 301.298079497 302.305355897 300.290803097 Sphinganine C18H39NO2 OTKJDMGTUTTYMP-ZWKOTPCHSA-N +HMDB0000271 89.047678473 90.054954873 88.040402073 Sarcosine C3H7NO2 FSYKKLYZXJSNPZ-UHFFFAOYSA-N +HMDB0000272 185.008923505 186.016199905 184.001647105 Phosphoserine C3H8NO6P BZQFBWGGLXLEPQ-REOHCLBHSA-N +HMDB0000273 242.090271568 243.097547968 241.082995168 Thymidine C10H14N2O5 IQFYYKKMVGJFEH-XLPZGREQSA-N +HMDB0000277 379.248759843 380.256036243 378.241483443 "Sphingosine 1-phosphate" C18H38NO5P DUYSYHSSBDVJSM-KRWOKUGFSA-N +HMDB0000279 276.132136382 277.139412782 275.124859982 Saccharopine C11H20N2O6 ZDGJAHTZVHVLOT-YUMQZZPRSA-N +HMDB0000280 389.95181466 390.95909106 388.94453826 "Phosphoribosyl pyrophosphate" C5H13O14P3 PQGCEDQWHSBAJP-TXICZTDVSA-N +HMDB0000283 150.05282343 151.06009983 149.04554703 D-Ribose C5H10O5 HMFHBZSHGGEWLO-SOOFDHNKSA-N +HMDB0000286 566.055020376 567.062296776 565.047743976 "Uridine diphosphate glucose" C15H24N2O17P2 HSCJRCZFDFQWRP-LPTOLDDLSA-N +HMDB0000288 324.035866536 325.043142936 323.028590136 "Uridine 5'-monophosphate" C9H13N2O9P DJJCXFVJDGTHFX-XVFCMESISA-N +HMDB0000289 168.028340014 169.035616414 167.021063614 "Uric acid" C5H4N4O3 LEHOTFFKMJEONL-UHFFFAOYSA-N +HMDB0000291 198.05282343 199.06009983 197.04554703 "Vanillylmandelic acid" C9H10O5 CGQCWMIAEPEHNQ-QMMMGPOBSA-N +HMDB0000292 152.033425392 153.040701792 151.026148992 Xanthine C5H4N4O2 LRFVTYWOQMYALW-UHFFFAOYSA-N +HMDB0000294 60.03236276 61.03963916 59.02508636 Urea CH4N2O XSQUKJJJFZCRTK-UHFFFAOYSA-N +HMDB0000295 404.002196946 405.009473346 402.994920546 "Uridine 5'-diphosphate" C9H14N2O12P2 XCCTYIAWTASOJW-XVFCMESISA-N +HMDB0000296 244.069536126 245.076812526 243.062259726 Uridine C9H12N2O6 DRTQHJPVMGBUCF-XVFCMESISA-N +HMDB0000299 284.075684136 285.082960536 283.068407736 Xanthosine C10H12N4O6 UBORTCNDUKBEOP-UUOKFMHZSA-N +HMDB0000300 112.027277382 113.034553782 111.020000982 Uracil C4H4N2O2 ISAKRJDGNUQOIC-UHFFFAOYSA-N +HMDB0000301 138.042927446 139.050203846 137.035651046 "Urocanic acid" C6H6N2O2 LOIYMIARKYCTBW-OWOJBTEDSA-N +HMDB0000303 160.100048394 161.107324794 159.092771994 Tryptamine C10H12N2 APJYDQYYACXCRM-UHFFFAOYSA-N +HMDB0000305 286.229665582 287.236941982 285.222389182 "Vitamin A" C20H30O FPIPGXGPPPQFEQ-OVSJKPMPSA-N +HMDB0000306 137.084063979 138.091340379 136.076787579 Tyramine C8H11NO DZGWFCGJZKJUFP-UHFFFAOYSA-N +HMDB0000308 374.282095082 375.289371482 373.274818682 "3b-Hydroxy-5-cholenoic acid" C24H38O3 HIAJCGFYHIANNA-QIZZZRFXSA-N +HMDB0000315 332.23514489 333.24242129 331.22786849 16-a-Hydroxypregnenolone C21H32O3 ZAKJZPQDUPCXSD-YRWKUUEZSA-N +HMDB0000317 132.07864425 133.08592065 131.07136785 "2-Hydroxy-3-methylpentanoic acid" C6H12O3 RILPIWOPNGRASR-RFZPGFLSSA-N +HMDB0000318 170.057908808 171.065185208 169.050632408 3,4-Dihydroxyphenylglycol C8H10O4 MTVWFVDWRVYDOR-UHFFFAOYSA-N +HMDB0000319 362.20932407 363.21660047 361.20204767 18-Hydroxycorticosterone C21H30O5 HFSXHZZDNDGLQN-ZVIOFETBSA-N +HMDB0000321 162.05282343 163.06009983 161.04554703 "2-Hydroxyadipic acid" C6H10O5 OTTXIFWBPRRYOG-UHFFFAOYSA-N +HMDB0000325 190.084123558 191.091399958 189.076847158 "3-Hydroxysuberic acid" C8H14O5 ARJZZFJXSNJKGR-UHFFFAOYSA-N +HMDB0000326 408.28757439 409.29485079 407.28029799 "1b,3a,12a-Trihydroxy-5b-cholanoic acid" C24H40O5 DAKYVYUAVGJDRK-LFMRMFNLSA-N +HMDB0000332 376.188588628 377.195865028 375.181312228 18-Oxocortisol C21H28O6 XUQWWIFROYJHCU-FJNAKSJRSA-N +HMDB0000335 286.15689457 287.16417097 285.14961817 16a-Hydroxyestrone C18H22O3 WPOCIZJTELRQMF-QFXBJFAPSA-N +HMDB0000336 104.047344122 105.054620522 103.040067722 "(R)-3-Hydroxyisobutyric acid" C4H8O3 DBXBTMSZEOQQDU-GSVOUGTGSA-N +HMDB0000337 120.042258744 121.049535144 119.034982344 "(S)-3,4-Dihydroxybutyric acid" C4H8O4 DZAIOXUZHHTJKN-UHFFFAOYSA-N +HMDB0000343 286.15689457 287.16417097 285.14961817 2-Hydroxyestrone C18H22O3 SWINWPBPEKHUOD-JPVZDGGYSA-N +HMDB0000345 162.05282343 163.06009983 161.04554703 "3-Hydroxyadipic acid" C6H10O5 YVOMYDHIQVMMTA-UHFFFAOYSA-N +HMDB0000347 288.172544634 289.179821034 287.165268234 16b-Hydroxyestradiol C18H24O3 PROQIPRRNZUXQM-ZMSHIADSSA-N +HMDB0000350 218.115423686 219.122700086 217.108147286 "3-Hydroxysebacic acid" C10H18O5 OQYZCCKCJQWHIE-UHFFFAOYSA-N +HMDB0000352 304.203844762 305.211121162 303.196568362 16a-Hydroxydehydroisoandrosterone C19H28O3 QQIVKFZWLZJXJT-DNKQKWOHSA-N +HMDB0000357 104.047344122 105.054620522 103.040067722 "3-Hydroxybutyric acid" C4H8O3 WHBMMWSBFZVSSR-UHFFFAOYSA-N +HMDB0000359 434.339609961 435.346886361 433.332333561 "3alpha,7alpha-Dihydroxycoprostanic acid" C27H46O4 ITZYGDKGRKKBSN-HKFUITGCSA-N +HMDB0000360 120.042258744 121.049535144 119.034982344 "2,4-Dihydroxybutanoic acid" C4H8O4 UFYGCFHQAXXBCF-UHFFFAOYSA-N +HMDB0000362 185.99293909 187.00021549 184.98566269 "2-Phosphoglyceric acid" C3H7O7P GXIURPTVHJPJLF-UHFFFAOYSA-N +HMDB0000363 332.23514489 333.24242129 331.22786849 17a-Hydroxypregnenolone C21H32O3 JERGUCIJOXJXHF-TVWVXWENSA-N +HMDB0000365 290.224580204 291.231856604 289.217303804 Epiandrosterone C19H30O2 QGXBDMJGAMFCBF-QRIARFFBSA-N +HMDB0000369 292.240230268 293.247506668 291.232953868 3b,17b-Dihydroxyetiocholane C19H32O2 CBMYJHIOYJEBSB-WTVXNACZSA-N +HMDB0000374 330.219494826 331.226771226 329.212218426 17-Hydroxyprogesterone C21H30O3 DBPWSSGDRRHUNT-CEGNMAFCSA-N +HMDB0000375 166.062994186 167.070270586 165.055717786 "3-(3-Hydroxyphenyl)propanoic acid" C9H10O3 QVWAEZJXDYOKEH-UHFFFAOYSA-N +HMDB0000379 206.042652674 207.049929074 205.035376274 "2-Methylcitric acid" C7H10O7 YNOXCRMFGMSKIJ-UHFFFAOYSA-N +HMDB0000380 302.188194698 303.195471098 301.180918298 "2-Hydroxyestradiol-3-methyl ether" C19H26O3 MMKYSUOJWFKECQ-SSTWWWIQSA-N +HMDB0000387 216.172544634 217.179821034 215.165268234 "3-Hydroxydodecanoic acid" C12H24O3 MUCMKTPAZLSKTL-UHFFFAOYSA-N +HMDB0000394 274.178023942 275.185300342 273.170747542 "3-Hydroxytetradecanedioic acid" C14H26O5 CEDZIURHISELSQ-UHFFFAOYSA-N +HMDB0000396 118.062994186 119.070270586 117.055717786 "2-Ethylhydracrylic acid" C5H10O3 ZMZQVAUJTDKQGE-UHFFFAOYSA-N +HMDB0000397 154.026608673 155.033885073 153.019332273 "2-Pyrocatechuic acid" C7H6O4 GLDQAMYCGOIJDV-UHFFFAOYSA-N +HMDB0000405 302.188194698 303.195471098 301.180918298 2-Methoxyestradiol C19H26O3 CQOQDQWUFQDJMK-SSTWWWIQSA-N +HMDB0000407 118.062994186 119.070270586 117.055717786 "2-Hydroxy-3-methylbutyric acid" C5H10O3 NGEWQZIDQIYUNV-UHFFFAOYSA-N +HMDB0000413 246.146723814 247.154000214 245.139447414 "3-Hydroxydodecanedioic acid" C12H22O5 FYVQCLGZFXHEGL-UHFFFAOYSA-N +HMDB0000416 412.191959446 413.199235846 411.184683046 "17-Hydroxypregnenolone sulfate" C21H32O6S OMOKWYAQVYBHMG-QUPIPBJSSA-N +HMDB0000418 378.204238692 379.211515092 377.196962292 18-Hydroxycortisol C21H30O6 HESFZGWRDUVOMS-FJNAKSJRSA-N +HMDB0000422 146.057908808 147.065185208 145.050632408 "2-Methylglutaric acid" C6H10O4 AQYCMVICBNBXNA-UHFFFAOYSA-N +HMDB0000423 182.057908808 183.065185208 181.050632408 "3,4-Dihydroxyhydrocinnamic acid" C9H10O4 DZAUWHJDUNRCTF-UHFFFAOYSA-N +HMDB0000424 218.115423686 219.122700086 217.108147286 "2-Hydroxydecanedioic acid" C10H18O5 LPIOYESQKJFWPQ-UHFFFAOYSA-N +HMDB0000426 148.037173366 149.044449766 147.029896966 "Citramalic acid" C5H8O5 XFTRTWQBIOMVPK-UHFFFAOYSA-N +HMDB0000428 148.037173366 149.044449766 147.029896966 "3-Hydroxyglutaric acid" C5H8O5 ZQHYXNSQOIDNTL-UHFFFAOYSA-N +HMDB0000429 272.177630012 273.184906412 271.170353612 17a-Estradiol C18H24O2 VOXZDWNPVJITMN-SFFUCWETSA-N +HMDB0000430 416.329045274 417.336321674 415.321768874 "24,25-Dihydroxyvitamin D" C27H44O3 FCKJYANJHNLEEP-OIMXRAFZSA-N +HMDB0000434 196.073558872 197.080835272 195.066282472 "Homoveratric acid" C10H12O4 WUAXWQRULBZETB-UHFFFAOYSA-N +HMDB0000439 169.037507717 170.044784117 168.030231317 2-Furoylglycine C7H7NO4 KSPQDMRTZZYQLM-UHFFFAOYSA-N +HMDB0000440 152.047344122 153.054620522 151.040067722 "3-Hydroxyphenylacetic acid" C8H8O3 FVMDYYGIDFPZAX-UHFFFAOYSA-N +HMDB0000442 104.047344122 105.054620522 103.040067722 "(S)-3-Hydroxybutyric acid" C4H8O3 WHBMMWSBFZVSSR-VKHMYHEASA-N +HMDB0000448 146.057908808 147.065185208 145.050632408 "Adipic acid" C6H10O4 WNLRTRBMVRJNCN-UHFFFAOYSA-N +HMDB0000449 350.245709576 351.252985976 349.238433176 5a-Tetrahydrocorticosterone C21H34O4 RHQQHZQUAMFINJ-NZTKVECHSA-N +HMDB0000450 162.100442324 163.107718724 161.093165924 5-Hydroxylysine C6H14N2O3 YSMODUONRAFBET-UHNVWZDZSA-N +HMDB0000452 103.063328537 104.070604937 102.056052137 "L-alpha-Aminobutyric acid" C4H9NO2 QWCKQJZIFLGMSD-VKHMYHEASA-N +HMDB0000459 157.073893223 158.081169623 156.066616823 3-Methylcrotonylglycine C7H11NO3 PFWQSHXPNKRLIV-UHFFFAOYSA-N +HMDB0000462 158.043990078 159.051266478 157.036713678 Allantoin C4H6N4O3 POJWUDADGALRAB-UHFFFAOYSA-N +HMDB0000464 39.962591155 40.969867555 38.955314755 Calcium Ca BHPQYMZQTOCNFJ-UHFFFAOYSA-N +HMDB0000468 237.086189243 238.093465643 236.078912843 Biopterin C9H11N5O3 LHQIJBMDNUYRAM-DZSWIPIPSA-N +HMDB0000469 142.037842068 143.045118468 141.030565668 5-Hydroxymethyluracil C5H6N2O3 JDBGXEHEIRGOBU-UHFFFAOYSA-N +HMDB0000472 220.08479226 221.09206866 219.07751586 5-Hydroxy-L-tryptophan C11H12N2O3 LDCYZAJDBXYCGN-VIFPVBQESA-N +HMDB0000473 163.085795313 164.093071713 162.078518913 6-Dimethylaminopurine C7H9N5 BVIAOQMSVZHOJM-UHFFFAOYSA-N +HMDB0000474 72.057514878 73.064791278 71.050238478 Butanone C4H8O ZWEHNKRNPOVVGH-UHFFFAOYSA-N +HMDB0000479 169.085126611 170.092403011 168.077850211 3-Methylhistidine C7H11N3O2 JDHILDINMRGULE-LURJTMIESA-N +HMDB0000481 268.080769514 269.088045914 267.073493114 "Allopurinol riboside" C10H12N4O5 KFQUAMTWOJHPEJ-DAGMQNCNSA-N diff -r 000000000000 -r a174cbbb12dd data/models.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/data/models.R Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,183 @@ + +tryCatch({ + DBModelR::ModelDefinition(table="yui", fields=list(yui="INTEGER")) +}, error=function(e) { + stop("Please, install DBModelR before you source this file.") +}) + +list( + adduct=DBModelR::ModelDefinition( + table="adduct", + fields=list( + name="TEXT", + mass="FLOAT", + charge="INTEGER", + multi="INTEGER", + formula_add="TEXT", + formula_ded="TEXT", + sign="TEXT", + oidscore="INTEGER", + quasi="INTEGER", + ips="FLOAT" + ) + ), + cluster=DBModelR::ModelDefinition( + table="cluster", + fields=list( + clusterID="INTEGER", + formula="TEXT", + annotation="TEXT", + coeff="FLOAT", + r_squared="FLOAT", + charge="INTEGER", + mean_rt="FLOAT", + score="FLOAT", + deviation="FLOAT", + status="TEXT", + adduct="TEXT", + curent_group="INTEGER", + pc_group="INTEGER", + align_group="INTEGER", + xcms_group="INTEGER" + ), + one=list("sample", "compound") + ), + compound=DBModelR::ModelDefinition( + table="compound", + fields=list( + name="TEXT", + common_name="TEXT", + formula="TEXT", + charge="INTEGER", + date="TEXT", + mz="FLOAT" + ) + ), + feature=DBModelR::ModelDefinition( + table="feature", + fields=list( + featureID="INTEGER", + mz="FLOAT", + mz_min="FLOAT", + mz_max="FLOAT", + rt="FLOAT", + rt_min="FLOAT", + rt_max="FLOAT", + int_o="FLOAT", + int_b="FLOAT", + max_o="FLOAT", + iso="TEXT", + abundance="FLOAT" + ), + one=list("cluster") + ), + instrument=DBModelR::ModelDefinition( + table="instrument", + fields=list( + model="TEXT", + manufacturer="TEXT", + analyzer="TEXT", + detector_type="TEXT", + ion_source="TEXT" + ) + ), + instrument_config=DBModelR::ModelDefinition( + table="instrument_config", + fields=list( + resolution="TEXT", + agc_target="TEXT", + maximum_IT="TEXT", + number_of_scan_range="TEXT", + scan_range="TEXT", + version="TEXT" + ) + ), + project=DBModelR::ModelDefinition( + table="project", + fields=list( + name="TEXT", + comment="TEXT" + ), + one=list("sample") + ), + sample=DBModelR::ModelDefinition( + table="sample", + fields=list( + name="TEXT", + path="TEXT", + polarity="TEXT", + kind="TEXT", ## rdata or mxml or enriched_rdata + raw="BLOB" + ), + one=list( + "peak_picking_parameters", + "pairing_parameters", + "alignmenmt_parameters", + "camera_parameters", + "instrument", + "instrument_config", + "software", + "smol_xcms_set" + ) + ), + smol_xcms_set=DBModelR::ModelDefinition( + table="smol_xcms_set", + fields=list( + raw="BLOB" + ) + ), + software=DBModelR::ModelDefinition( + table="software", + fields=list( + name="TEXT", + version="TEXT" + ) + ), + # camera_parameters=DBModelR::ModelDefinition( + # table="camera_parameters", + # fields=list() + # ), + # pairing_parameters=DBModelR::ModelDefinition( + # table="pairing_parameters", + # fields=list() + # ), + peak_picking_parameters=DBModelR::ModelDefinition( + table="peak_picking_parameters", + fields=list( + ppm="FLOAT", + peakwidth="TEXT", + snthresh="TEXT", + prefilterStep="TEXT", + prefilterLevel="TEXT", + mzdiff="TEXT", + fitgauss="TEXT", + noise="TEXT", + mzCenterFun="TEXT", + integrate="INTEGER", + firstBaselineCheck="TEXT", + snthreshIsoROIs="TEXT", + maxCharge="INTEGER", + maxIso="INTEGER", + mzIntervalExtension="TEXT" + ) + ), + alignmenmt_parameters=DBModelR::ModelDefinition( + table="alignmenmt_parameters", + fields=list( + binSize="TEXT", + centerSample="TEXT", + response="TEXT", + distFun="TEXT", + gapInit="TEXT", + gapExtend="TEXT", + factorDiag="TEXT", + factorGap="TEXT", + localAlignment="INTEGER", + initPenalty="TEXT", + bw="TEXT", + minFraction="TEXT", + minSamples="TEXT", + maxFeatures="TEXT" + ) + ) +) diff -r 000000000000 -r a174cbbb12dd format_versionning.MD --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/format_versionning.MD Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,91 @@ + +INTRODUCTION +===== +This file describes the format of the database generated by XSeeker +Preprocessor. This format will evolve in the future to fit users +wanted features. That's why there is a history of versions numbers, +describing what they brought to the sqlite file, and how it was usefull. + +The first version (the older one) is at the bottom of this file, and the +modifications provided by the newest versions are on top of the file. + + +VERSION 1.1.2 +===== +add missing mz_tab_info$group_length field to produce mzTab + +VERSION 1.1.1 +===== +add missing mz_tab_info$dataset_path field to produce mzTab + + +VERSION 1.1.0 +===== +Summary: + - The field `mz_tab_info` was added in new table smol_xcms_set. + +smol_xcms_set table added +----- +This table contains a subset of the original ms file. + +mz_tab_info field added to smol_xcms_set +----- +This field contains five subfields: + - sampclass ; + - sampnames ; + - rtmed ; + - mzmed ; + - smallmolecule_abundance_assay . + +These fields were added after users asked to export data from XSeeker +in mzTab files. +XCMS has some functions to extract sampclass, sampnames, rtmed, mzmed +and smallmolecule_abundance_assay from xcms set. Then, they are used +in the mz tab creation process, but we didn't want to keep the whole +xcmsset object. So we used the original code from XCMS and modified it +a little bit, justifying the extraction of these new fields. + + +VERSION 1.0.0 +===== + + +DATABASE +----- + +### SAMPLE + +#### RAW +This structure is an epurated and enriched version of the original +rdata, saved as a compressed env: +`blob::blob(fst::compress_fst(serialize(raw, NULL), compression=100))` + +The fields contained in the env are as follow: + +##### variableMetadata + +##### tic + +##### mz + +##### scanindex + +##### scantime + +##### intensity + +##### polarity + +##### sample_name + +##### dataset_path + +##### process_params + +##### enriched_rdata + +##### enriched_rdata_version + +##### tool_name + +##### enriched_rdata_doc \ No newline at end of file diff -r 000000000000 -r a174cbbb12dd galaxy/config/datatype_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy/config/datatype_conf.xml Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,6 @@ + + + + + + diff -r 000000000000 -r a174cbbb12dd galaxy/config/tool_conf.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy/config/tool_conf.xml Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,6 @@ + + +
+ +
+ \ No newline at end of file diff -r 000000000000 -r a174cbbb12dd galaxy/lib/galaxy/datatypes/binary.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy/lib/galaxy/datatypes/binary.py Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,52 @@ + + +class XSeekerDatabase(SQlite): + """Class describing an XSeeker Sqlite database """ + MetadataElement( + name="xseeker_version", + default="1.0.0", + param=MetadataParameter, + desc="XSeeker Version", + readonly=True, + visible=True, + no_value="1.0.0" + ) + file_ext = "xseeker.sqlite" + edam_format = "format_3622" + edam_data = "data_3498" + + def set_meta(self, dataset, overwrite=True, **kwd): + super(XSeekerDatabase, self).set_meta(dataset, overwrite=overwrite, **kwd) + try: + conn = sqlite.connect(dataset.file_name) + c = conn.cursor() + tables_query = "SELECT database_version FROM XSeeker_tagging_table" + result = c.execute(tables_query).fetchall() + for version, in result: + dataset.metadata.xseeker_vesrion = version + # TODO: Can/should we detect even more attributes, such as use of PED file, what was input annotation type, etc. + except Exception as e: + log.warning('%s, set_meta Exception: %s', self, e) + + def sniff(self, filename): + if super(XSeekerDatabase, self).sniff(filename): + table_names = [ + "XSeeker_tagging_table" + ] + return self.sniff_table_names(filename, table_names) + return False + + def set_peek(self, dataset, is_multi_byte=False): + if not dataset.dataset.purged: + dataset.peek = "XSeeker SQLite Database, version %s" % (dataset.metadata.xseeker_version or 'unknown') + dataset.blurb = nice_size(dataset.get_size()) + else: + dataset.peek = 'file does not exist' + dataset.blurb = 'file purged from disk' + + def display_peek(self, dataset): + try: + return dataset.peek + except Exception: + return "XSeeker SQLite Database, version %s" % (dataset.metadata.xseeker_version or 'unknown') + diff -r 000000000000 -r a174cbbb12dd galaxy/lib/galaxy/datatypes/text.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy/lib/galaxy/datatypes/text.py Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,35 @@ + + +@build_sniff_from_prefix +class SQL(Text): + """Class describing an html file""" + file_ext = "sql" + + def set_peek(self, dataset, is_multi_byte=False): + if not dataset.dataset.purged: + dataset.peek = "SQL file" + dataset.blurb = nice_size(dataset.get_size()) + else: + dataset.peek = "file does not exist" + dataset.blurb = "file purged from disk" + + def get_mime(self): + """Returns the mime type of the datatype""" + return "application/sql" + + def sniff_prefix(self, file_prefix): + """ + Uses some patterns usualy encountered in sql files to guess + it's type + """ + start = file_prefix.string_io().read(42).strip() + return any( + header in start + for header in ( + "CREATE DATABASE", + "INSERT INTO", + "CREATE TABLE", + "BEGIN TRANSACTION" + ) + ) + diff -r 000000000000 -r a174cbbb12dd galaxy/tools/LC-MSMS/XSeekerPreparator.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy/tools/LC-MSMS/XSeekerPreparator.R Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,919 @@ + + +TOOL_NAME <- "XSeekerPreparator" +VERSION <- "1.1.2" + +OUTPUT_SPECIFIC_TOOL <- "XSeeker_Galaxy" + +ENRICHED_RDATA_VERSION <- paste("1.1.2", OUTPUT_SPECIFIC_TOOL, sep="-") +ENRICHED_RDATA_DOC <- sprintf(" +Welcome to the enriched of the output of CAMERA/xcms. +This doc was generated by the tool: %s - Version %s +To show the different variables contained in this rdata, type: + - `load('this_rdata.rdata', rdata_env <- new.env())` + - `names(rdata_env)` + +Sections +###### + + +This tools helpers +------ + The version number is somewhat special because the evolution of the + rdata's format is non-linear. + There may be different branches, each evolving separatly. + To reflect these branches's diversions, there may be a prepended + branch name following this format: + major.minor.patch-branch_name + Like this, we can process rdata with the same tool, and output + rdata formated differently, for each tool. + + + - enriched_rdata: + - Description: flag created by that tool to tell it was enriched. + - Retrieval method: enriched_rdata <- TRUE + + - enriched_rdata_version: + - Description: A flag created by that tool to tell which version of + this tool has enriched the rdata. + - Retrieval method: enriched_rdata_version <- sprintf(\"%s\", ENRICHED_RDATA_VERSION) + + - enriched_rdata_doc: + - Description: Contains the documentation string. + +Data from original mzxml file +------ + - tic: + - Description: Those are the tic values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@tic + - xcms version: 2.0 + + - mz: + - Description: Those are the m/z values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@env$mz + - xcms version: 2.0 + + - scanindex: + - Description: Those are the scanindex values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@scanindex + - xcms version: 2.0 + + - scantime: + - Description: Those are the scantime values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@scantime + - xcms version: 2.0 + + - intensity: + - Description: Those are the intensity values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: xcms::xcmsRaw('original_file.mzxml')@env$intensity + - xcms version: 2.0 + + - polarity: + - Description: Those are the polarity values from the original mzxml + file, extracted using xcms 2. + - Retrieval method: as.character(xcms::xcmsRaw('original_file.mzxml')@polarity[[1]]) + - xcms version: 2.0 + +Data taken from incoming rdata +------ + - variableMetadata: + - Description: Unmodified copy of variableMetadata from incoming rdata. + - Retrieval method: rdata_file$variableMetadata + + - process_params: + - Description: Those are the processing parameters values from the + curent rdata. They have been simplified to allow easy access like: + for (params in process_params) { + if (params[[\"xfunction\"]] == \"annotatediff\") { + process_peak_picking_params(params) + } + } + - Retrieval method: + ## just he same list, but simplified + process_params <- list() + for (list_name in names(rdata_file$listOFlistArguments)) { + param_list <- list() + for (param_name in names(rdata_file$listOFlistArguments[[list_name]])) { + param_list[[param_name]] <- rdata_file$listOFlistArguments[[list_name]][[param_name]] + } + process_params[[length(process_params)+1]] <- param_list + } +", ENRICHED_RDATA_VERSION, TOOL_NAME, VERSION, ENRICHED_RDATA_VERSION) + + + +get_models <- function(path) { + if (is.null(path)) { + stop("No models to define the database schema") + } else { + message(sprintf("Loading models from %s", path)) + } + ## galaxy mangles the "@" to a "__at__" + if (substr(path, 1, 9) == "git__at__") { + path <- sub("^git__at__", "git@", path, perl=TRUE) + } + if ( + substr(path, 1, 4) == "git@" + || substr(path, length(path)-4, 4) == ".git" + ) { + return (get_models_from_git(path)) + } + if (substr(path, 1, 4) == "http") { + return (get_models_from_url(path)) + } + return (source(path)$value) +} + +get_models_from_git <- function (url, target_file="models.R", rm=TRUE) { + tmp <- tempdir() + message(sprintf("Cloning %s", url)) + system2("git", c("clone", url, tmp)) + result <- search_tree(file.path(tmp, dir), target_file) + if (!is.null(result)) { + models <- source(result)$value + if (rm) { + unlink(tmp, recursive=TRUE) + } + return (models) + } + if (rm) { + unlink(tmp, recursive=TRUE) + } + stop(sprintf( + "Could not find any file named \"%s\" in this repo", + target_file + )) +} + +get_models_from_url <- function (url, target_file="models.R", rm=TRUE) { + tmp <- tempdir() + message(sprintf("Downloading %s", url)) + result <- file.path(tmp, target_file) + if (download.file(url, destfile=result) == 0) { + models <- source(result)$value + if (rm) { + unlink(tmp, recursive=TRUE) + } + return (models) + } + if (rm) { + unlink(tmp, recursive=TRUE) + } + stop("Could not download any file at this adress.") +} + +search_tree <- function(path, target) { + target <- tolower(target) + for (file in list.files(path)) { + if (is.dir(file)) { + result <- search_tree(file.path(path, file), target) + if (!is.null(result)) { + return (result) + } + } else if (tolower(file) == target) { + return (file.path(path, file)) + } + } + return (NULL) +} + +create_database <- function(orm) { + orm$recreate_database(no_exists=FALSE) + set_database_version(orm, "created") +} + +insert_adducts <- function(orm) { + message("Creating adducts...") + adducts <- list( + list("[M-H2O-H]-",1,-1,-48.992020312000001069,1,0,0.5,"H0","H1O3"), + list("[M-H-Cl+O]-",1,-1,-19.981214542000000022,2,0,0.5,"O1","H1Cl1"), + list("[M-Cl+O]-",1,-1,-18.973389510000000512,3,0,0.5,"O1","Cl1"), + list("[M-3H]3-",1,-3,-3.0218293560000000219,4,0,1.0,"H0","H3"), + list("[2M-3H]3-",2,-3,-3.0218293560000000219,4,0,0.5,"H0","H3"), + list("[3M-3H]3-",3,-3,-3.0218293560000000219,4,0,0.5,"H0","H3"), + list("[M-2H]2-",1,-2,-2.0145529039999998666,5,0,1.0,"H0","H2"), + list("[2M-2H]2-",2,-2,-2.0145529039999998666,5,0,0.5,"H0","H2"), + list("[3M-2H]2-",3,-2,-2.0145529039999998666,5,0,0.5,"H0","H2"), + list("[M-H]-",1,-1,-1.0072764519999999333,6,1,1.0,"H0","H1"), + list("[2M-H]-",2,-1,-1.0072764519999999333,6,0,0.5,"H0","H1"), + list("[3M-H]-",3,-1,-1.0072764519999999333,6,0,0.5,"H0","H1"), + list("[M]+",1,1,-0.00054858000000000000945,7,1,1.0,"H0","H0"), + list("[M]-",1,-1,0.00054858000000000000945,8,1,1.0,"H0","H0"), + list("[M+H]+",1,1,1.0072764519999999333,9,1,1.0,"H1","H0"), + list("[2M+H]+",2,1,1.0072764519999999333,9,0,0.5,"H1","H0"), + list("[3M+H]+",3,1,1.0072764519999999333,9,0,0.25,"H1","H0"), + list("[M+2H]2+",1,2,2.0145529039999998666,10,0,0.75,"H2","H0"), + list("[2M+2H]2+",2,2,2.0145529039999998666,10,0,0.5,"H2","H0"), + list("[3M+2H]2+",3,2,2.0145529039999998666,10,0,0.25,"H2","H0"), + list("[M+3H]3+",1,3,3.0218293560000000219,11,0,0.75,"H3","H0"), + list("[2M+3H]3+",2,3,3.0218293560000000219,11,0,0.5,"H3","H0"), + list("[3M+3H]3+",3,3,3.0218293560000000219,11,0,0.25,"H3","H0"), + list("[M-2H+NH4]-",1,-1,16.019272654000001665,12,0,0.25,"N1H4","H2"), + list("[2M-2H+NH4]-",2,-1,16.019272654000001665,12,0,0.0,"N1H4","H2"), + list("[3M-2H+NH4]-",3,-1,16.019272654000001665,12,0,0.25,"N1H4","H2"), + list("[M+NH4]+",1,1,18.033825558000000199,13,1,1.0,"N1H4","H0"), + list("[2M+NH4]+",2,1,18.033825558000000199,13,0,0.5,"N1H4","H0"), + list("[3M+NH4]+",3,1,18.033825558000000199,13,0,0.25,"N1H4","H0"), + list("[M+H+NH4]2+",1,2,19.041102009999999467,14,0,0.5,"N1H5","H0"), + list("[2M+H+NH4]2+",2,2,19.041102009999999467,14,0,0.5,"N1H5","H0"), + list("[3M+H+NH4]2+",3,2,19.041102009999999467,14,0,0.25,"N1H5","H0"), + list("[M+Na-2H]-",1,-1,20.974668176000001551,15,0,0.75,"Na1","H2"), + list("[2M-2H+Na]-",2,-1,20.974668176000001551,15,0,0.25,"Na1","H2"), + list("[3M-2H+Na]-",3,-1,20.974668176000001551,15,0,0.25,"Na1","H2"), + list("[M+Na]+",1,1,22.989221080000000086,16,1,1.0,"Na1","H0"), + list("[2M+Na]+",2,1,22.989221080000000086,16,0,0.5,"Na1","H0"), + list("[3M+Na]+",3,1,22.989221080000000086,16,0,0.25,"Na1","H0"), + list("[M+H+Na]2+",1,2,23.996497531999999353,17,0,0.5,"Na1H1","H0"), + list("[2M+H+Na]2+",2,2,23.996497531999999353,17,0,0.5,"Na1H1","H0"), + list("[3M+H+Na]2+",3,2,23.996497531999999353,17,0,0.25,"Na1H1","H0"), + list("[M+2H+Na]3+",1,3,25.003773983999998619,18,0,0.25,"H2Na1","H0"), + list("[M+CH3OH+H]+",1,1,33.033491200000000276,19,0,0.25,"C1O1H5","H0"), + list("[M-H+Cl]2-",1,-2,33.962124838000001148,20,0,1.0,"Cl1","H1"), + list("[2M-H+Cl]2-",2,-2,33.962124838000001148,20,0,0.5,"Cl1","H1"), + list("[3M-H+Cl]2-",3,-2,33.962124838000001148,20,0,0.5,"Cl1","H1"), + list("[M+Cl]-",1,-1,34.969401290000000416,21,1,1.0,"Cl1","H0"), + list("[2M+Cl]-",2,-1,34.969401290000000416,21,0,0.5,"Cl1","H0"), + list("[3M+Cl]-",3,-1,34.969401290000000416,21,0,0.5,"Cl1","H0"), + list("[M+K-2H]-",1,-1,36.948605415999999479,22,0,0.5,"K1","H2"), + list("[2M-2H+K]-",2,-1,36.948605415999999479,22,0,0.0,"K1","H2"), + list("[3M-2H+K]-",3,-1,36.948605415999999479,22,0,0.0,"K1","H2"), + list("[M+K]+",1,1,38.963158319999998013,23,1,1.0,"K1","H0"), + list("[2M+K]+",2,1,38.963158319999998013,23,0,0.5,"K1","H0"), + list("[3M+K]+",3,1,38.963158319999998013,23,0,0.25,"K1","H0"), + list("[M+H+K]2+",1,2,39.970434771999997281,24,0,0.5,"K1H1","H0"), + list("[2M+H+K]2+",2,2,39.970434771999997281,24,0,0.5,"K1H1","H0"), + list("[3M+H+K]2+",3,2,39.970434771999997281,24,0,0.25,"K1H1","H0"), + list("[M+ACN+H]+",1,1,42.033825557999996646,25,0,0.25,"C2H4N1","H0"), + list("[2M+ACN+H]+",2,1,42.033825557999996646,25,0,0.25,"C2H4N1","H0"), + list("[M+2Na-H]+",1,1,44.971165708000000902,26,0,0.5,"Na2","H1"), + list("[2M+2Na-H]+",2,1,44.971165708000000902,26,0,0.25,"Na2","H1"), + list("[3M+2Na-H]+",3,1,44.971165708000000902,26,0,0.25,"Na2","H1"), + list("[2M+FA-H]-",2,-1,44.998202851999998586,27,0,0.25,"C1O2H2","H1"), + list("[M+FA-H]-",1,-1,44.998202851999998586,27,0,0.5,"C1O2H2","H1"), + list("[M+2Na]2+",1,2,45.978442160000000172,28,0,0.5,"Na2","H0"), + list("[2M+2Na]2+",2,2,45.978442160000000172,28,0,0.5,"Na2","H0"), + list("[3M+2Na]2+",3,2,45.978442160000000172,28,0,0.25,"Na2","H0"), + list("[M+H+2Na]3+",1,3,46.985718611999999438,29,0,0.25,"H1Na2","H0"), + list("[M+H+FA]+",1,1,47.012755755999997122,30,0,0.25,"C1O2H3","H0"), + list("[M+Hac-H]-",1,-1,59.013852915999997607,31,0,0.25,"C2O2H4","H1"), + list("[2M+Hac-H]-",2,-1,59.013852915999997607,31,0,0.25,"C2O2H4","H1"), + list("[M+IsoProp+H]+",1,1,61.064791327999998317,32,0,0.25,"C3H9O1","H0"), + list("[M+Na+K]2+",1,2,61.9523793999999981,33,0,0.5,"Na1K1","H0"), + list("[2M+Na+K]2+",2,2,61.9523793999999981,33,0,0.5,"Na1K1","H0"), + list("[3M+Na+K]2+",3,2,61.9523793999999981,33,0,0.25,"Na1K1","H0"), + list("[M+NO3]-",1,-1,61.988366450000000895,34,0,0.5,"N1O3","H0"), + list("[M+ACN+Na]+",1,1,64.015770185999997464,35,0,0.25,"C2H3N1Na1","H0"), + list("[2M+ACN+Na]+",2,1,64.015770185999997464,35,0,0.25,"C2H3N1Na1","H0"), + list("[M+NH4+FA]+",1,1,64.039304861999994502,36,0,0.25,"N1C1O2H6","H0"), + list("[M-2H+Na+FA]-",1,-1,66.980147479999999405,37,0,0.5,"NaC1O2H2","H2"), + list("[M+3Na]3+",1,3,68.967663239999993153,38,0,0.25,"Na3","H0"), + list("[M+Na+FA]+",1,1,68.99470038399999794,39,0,0.25,"Na1C1O2H2","H0"), + list("[M+2Cl]2-",1,-2,69.938802580000000832,40,0,1.0,"Cl2","H0"), + list("[2M+2Cl]2-",2,-2,69.938802580000000832,40,0,0.5,"Cl2","H0"), + list("[3M+2Cl]2-",3,-2,69.938802580000000832,40,0,0.5,"Cl2","H0"), + list("[M+2K-H]+",1,1,76.919040187999996758,41,0,0.5,"K2","H1"), + list("[2M+2K-H]+",2,1,76.919040187999996758,41,0,0.25,"K2","H1"), + list("[3M+2K-H]+",3,1,76.919040187999996758,41,0,0.25,"K2","H1"), + list("[M+2K]2+",1,2,77.926316639999996028,42,0,0.5,"K2","H0"), + list("[2M+2K]2+",2,2,77.926316639999996028,42,0,0.5,"K2","H0"), + list("[3M+2K]2+",3,2,77.926316639999996028,42,0,0.25,"K2","H0"), + list("[M+Br]-",1,-1,78.918886479999997619,43,1,1.0,"Br1","H0"), + list("[M+Cl+FA]-",1,-1,80.974880593999998268,44,0,0.5,"Cl1C1O2H2","H0"), + list("[M+AcNa-H]-",1,-1,80.995797543999998426,45,0,0.25,"C2H3Na1O2","H1"), + list("[M+2ACN+2H]2+",1,2,84.067651115999993292,46,0,0.25,"C4H8N2","H0"), + list("[M+K+FA]+",1,1,84.968637623999995868,47,0,0.25,"K1C1O2H2","H0"), + list("[M+Cl+Na+FA-H]-",1,-1,102.95682522200000619,48,0,0.5,"Cl1Na1C1O2H2","H1"), + list("[2M+3H2O+2H]+",2,1,104.03153939599999944,49,0,0.25,"H8O6","H0"), + list("[M+TFA-H]-",1,-1,112.98558742000000165,50,0,0.5,"C2F3O2H1","H1"), + list("[M+H+TFA]+",1,1,115.00014032400000019,51,0,0.25,"C2F3O2H2","H0"), + list("[M+3ACN+2H]2+",1,2,125.09420022199999778,52,0,0.25,"C6H11N3","H0"), + list("[M+NH4+TFA]+",1,1,132.02668943000000468,53,0,0.25,"N1C2F3O2H5","H0"), + list("[M+Na+TFA]+",1,1,136.98208495200000811,54,0,0.25,"Na1C2F3O2H1","H0"), + list("[M+Cl+TFA]-",1,-1,148.96226516199999423,55,0,0.5,"Cl1C2F3O2H1","H0"), + list("[M+K+TFA]+",1,1,152.95602219200000604,56,0,0.25,"K1C2F3O2H1","H0") + ) + dummy_adduct <- orm$adduct() + for (adduct in adducts) { + i <- 0 + dummy_adduct$set_name(adduct[[i <- i+1]]) + dummy_adduct$set_multi(adduct[[i <- i+1]]) + dummy_adduct$set_charge(adduct[[i <- i+1]]) + dummy_adduct$set_mass(adduct[[i <- i+1]]) + dummy_adduct$set_oidscore(adduct[[i <- i+1]]) + dummy_adduct$set_quasi(adduct[[i <- i+1]]) + dummy_adduct$set_ips(adduct[[i <- i+1]]) + dummy_adduct$set_formula_add(adduct[[i <- i+1]]) + dummy_adduct$set_formula_ded(adduct[[i <- i+1]]) + dummy_adduct$save() + dummy_adduct$clear(unset_id=TRUE) + } + message("Adducts created") +} + +insert_base_data <- function(orm, path, archetype=FALSE) { + if (archetype) { + ## not implemented yet + return () + } + base_data <- readLines(path) + for (sql in strsplit(paste(base_data, collapse=" "), ";")[[1]]) { + orm$execute(sql) + } + set_database_version(orm, "enriched") +} + +insert_compounds <- function(orm, compounds_path) { + compounds <- read.csv(file=compounds_path, sep="\t") + if (is.null(compounds <- translate_compounds(compounds))) { + stop("Could not find asked compound's attributes in csv file.") + } + dummy_compound <- orm$compound() + compound_list <- list() + for (i in seq_len(nrow(compounds))) { + dummy_compound$set_mz(compounds[i, "mz"]) + dummy_compound$set_name(compounds[i, "name"]) + dummy_compound$set_common_name(compounds[i, "common_name"]) + dummy_compound$set_formula(compounds[i, "formula"]) + # dummy_compound$set_mz(compounds[i, "mz"]) + # dummy_compound$set_mz(compounds[i, "mz"]) + compound_list[[length(compound_list)+1]] <- as.list( + dummy_compound, + c("mz", "name", "common_name", "formula") + ) + dummy_compound$clear(unset_id=TRUE) + } + dummy_compound$save(bulk=compound_list) +} + +translate_compounds <- function(compounds) { + recognized_headers <- list( + c("HMDB_ID", "MzBank", "X.M.H..", "X.M.H...1", "MetName", "ChemFormula", "INChIkey") + ) + header_translators <- list( + hmdb_header_translator + ) + for (index in seq_along(recognized_headers)) { + headers <- recognized_headers[[index]] + if (identical(colnames(compounds), headers)) { + return (header_translators[[index]](compounds)) + } + } + if (is.null(translator <- guess_translator(colnames(compounds)))) { + return (NULL) + } + return (csv_header_translator(translator, compounds)) +} + +guess_translator <- function(header) { + result <- list( + # HMDB_ID=NULL,< + mz=NULL, + name=NULL, + common_name=NULL, + formula=NULL, + # inchi_key=NULL + ) + asked_cols <- names(result) + for (asked_col in asked_cols) { + for (col in header) { + if ((twisted <- tolower(col)) == asked_col + || gsub("-", "_", twisted) == asked_col + || gsub(" ", "_", twisted) == asked_col + || tolower(gsub("(.)([A-Z])", "\\1_\\2", col)) == asked_col + ) { + result[[asked_col]] <- col + next + } + } + } + if (any(mapply(is.null, result))) { + return (NULL) + } + return (result) +} + +hmdb_header_translator <- function(compounds) { + return (csv_header_translator( + list( + HMDB_ID="HMDB_ID", + mz="MzBank", + name="MetName", + common_name="MetName", + formula="ChemFormula", + inchi_key="INChIkey" + ), compounds + )) +} + +csv_header_translator <- function(translation_table, csv) { + header_names <- names(translation_table) + result <- data.frame(1:nrow(csv)) + # colnames(result) <- header_names + for (i in seq_along(header_names)) { + result[, header_names[[i]]] <- csv[, translation_table[[i]]] + } + print(result[, "mz"]) + result[, "mz"] <- as.numeric(result[, "mz"]) + print(result[, "mz"]) + return (result) +} + +set_database_version <- function(orm, version) { + orm$set_tag( + version, + tag_name="database_version", + tag_table_name="XSeeker_tagging_table" + ) +} + +process_rdata <- function(orm, rdata, options) { + mzml_tmp_dir <- gather_mzml_files(rdata) + samples <- names(rdata$singlefile) + if (!is.null(options$samples)) { + samples <- samples[options$samples %in% samples] + } + show_percent <- ( + is.null(options$`not-show-percent`) + || options$`not-show-percent` == FALSE + ) + error <- tryCatch({ + process_sample_list( + orm, rdata, samples, + show_percent=show_percent + ) + NULL + }, error=function(e) { + message(e) + e + }) + if (!is.null(mzml_tmp_dir)) { + unlink(mzml_tmp_dir, recursive=TRUE) + } + if (!is.null(error)) { + stop(error) + } +} + +gather_mzml_files <- function(rdata) { + if (is.null(rdata$singlefile)) { + message("Extracting mxml files") + tmp <- tempdir() + rdata$singlefile <- utils::unzip(rdata$zipfile, exdir=tmp) + names(rdata$singlefile) <- tools::file_path_sans_ext(basename(rdata$singlefile)) + message("Extracted") + return (tmp) + } else { + message(sprintf("Not a zip file, loading files directly from path: %s", paste(rdata$singlefile, collapse=" ; "))) + } + return (NULL) +} + +process_sample_list <- function(orm, radta, sample_names, show_percent) { + file_grouping_var <- find_grouping_var(rdata$variableMetadata) + message("Processing samples.") + message(sprintf("File grouping variable: %s", file_grouping_var)) + if(is.null(file_grouping_var)) { + stop("Malformed variableMetada.") + } + + process_arg_list <- rdata$listOFlistArguments + process_params <- list() + for (list_name in names(process_arg_list)) { + param_list <- list() + for (param_name in names(process_arg_list[[list_name]])) { + param_list[[param_name]] <- process_arg_list[[list_name]][[param_name]] + } + process_params[[length(process_params)+1]] <- param_list + } + message("Parameters from previous processes extracted.") + + var_meta <- rdata$variableMetadata + align_group <- rep(0, nrow(var_meta)) + var_meta <- cbind(var_meta, align_group) + context <- new.env() + context$clusters <- list() + context$groupidx <- rdata$xa@xcmsSet@groupidx + context$peaks <- rdata$xa@xcmsSet@peaks + context$show_percent <- show_percent + + indices <- as.numeric(unique(var_meta[, file_grouping_var])) + smol_xcms_set <- orm$smol_xcms_set() + mz_tab_info <- new.env() + xcms_set <- rdata$xa@xcmsSet + g <- xcms::groups(xcms_set) + mz_tab_info$group_length <- nrow(g) + mz_tab_info$dataset_path <- xcms::filepaths(xcms_set) + mz_tab_info$sampnames <- xcms::sampnames(xcms_set) + mz_tab_info$sampclass <- xcms::sampclass(xcms_set) + mz_tab_info$rtmed <- g[,"rtmed"] + mz_tab_info$mzmed <- g[,"mzmed"] + mz_tab_info$smallmolecule_abundance_assay <- xcms::groupval(xcms_set, value="into") + blogified <- blob::blob(fst::compress_fst(serialize(mz_tab_info, NULL), compression=100)) + smol_xcms_set$set_raw(blogified)$save() + for (no in indices) { + sample_name <- names(rdata$singlefile)[[no]] + sample_path <- rdata$singlefile[[no]] + if ( + is.na(no) + || is.null(sample_path) + || !(sample_name %in% sample_names) + ) { + next + } + ms_file=xcms::xcmsRaw(sample_path) + env <- new.env() + env$variableMetadata <- var_meta[var_meta[, file_grouping_var]==no,] + env$tic <- ms_file@tic + env$mz <- ms_file@env$mz + env$scanindex <- ms_file@scanindex + env$scantime <- ms_file@scantime + env$intensity <- ms_file@env$intensity + env$polarity <- as.character(ms_file@polarity[[1]]) + env$sample_name <- sample_name + env$dataset_path <- sample_path + env$process_params <- process_params + env$enriched_rdata <- TRUE + env$enriched_rdata_version <- ENRICHED_RDATA_VERSION + env$tool_name <- TOOL_NAME + env$enriched_rdata_doc <- ENRICHED_RDATA_DOC + context$sample_no <- no + add_sample_to_database(orm, env, context, smol_xcms_set) + } + message("Features enrichment") + complete_features(orm, context) + message("Features enrichment done.") + return (NULL) +} + +find_grouping_var <- function(var_meta) { + for (grouping_var in c(".", "Bio")) { + if (!is.null(rdata$variableMetadata[[grouping_var]])) { + return (grouping_var) + } + } + return (NULL) +} + +add_sample_to_database <- function(orm, env, context, smol_xcms_set) { + message(sprintf("Processing sample %s", env$sample_name)) + sample <- ( + orm$sample() + $set_name(env$sample_name) + $set_path(env$dataset_path) + $set_kind("enriched_rdata") + $set_polarity( + if (is.null(env$polarity) || identical(env$polarity, character(0))) "" + else env$polarity + ) + $set_smol_xcms_set(smol_xcms_set) + $set_raw(blob::blob(fst::compress_fst( + serialize(env, NULL), + compression=100 + ))) + $save() + ) + load_variable_metadata(orm, sample, env$variableMetadata, context) + load_process_params(orm, sample, env$process_params) + message(sprintf("Sample %s inserted.", env$sample_name)) + return (sample) +} + + +load_variable_metadata <- function(orm, sample, var_meta, context) { + all_clusters <- orm$cluster()$all() + + next_feature_id <- get_next_id(orm$feature()$all(), "featureID") + next_cluster_id <- get_next_id(all_clusters, "clusterID") + next_pc_group <- get_next_id(all_clusters, "pc_group") + next_align_group <- get_next_id(all_clusters, "align_group") + message("Extracting features") + invisible(create_features( + orm, sample, var_meta, context, + next_feature_id, next_cluster_id, + next_pc_group, next_align_group + )) + message("Extracting features done.") + return (NULL) +} + +get_next_id <- function(models, attribute) { + if ((id <- models$max(attribute)) == Inf || id == -Inf) { + return (1) + } + return (id + 1) +} + +create_features <- function( + orm, sample, var_meta, context, + next_feature_id, next_cluster_id, + next_pc_group, next_align_group +) { + field_names <- as.list(names(orm$feature()$fields__)) + field_names[field_names=="id"] <- NULL + + features <- list() + dummy_feature <- orm$feature() + + if (show_percent <- context$show_percent) { + percent <- -1 + total <- nrow(var_meta) + } + for (row in seq_len(nrow(var_meta))) { + if (show_percent && (row / total) * 100 > percent) { + percent <- percent + 1 + message("\r", sprintf("\r%d %%", percent), appendLF=FALSE) + } + + curent_var_meta <- var_meta[row, ] + + peak_list <- context$peaks[context$groupidx[[row]], ] + sample_peak_list <- peak_list[peak_list[, "sample"] == context$sample_no, , drop=FALSE] + if (!identical(sample_peak_list, numeric(0)) && !is.null(nrow(sample_peak_list)) && nrow(sample_peak_list) != 0) { + if (!is.na(int_o <- extract_peak_var(sample_peak_list, "into"))) { + dummy_feature$set_int_o(int_o) + } + if (!is.na(int_b <- extract_peak_var(sample_peak_list, "intb"))) { + dummy_feature$set_int_b(int_b) + } + if (!is.na(max_o <- extract_peak_var(sample_peak_list, "maxo"))) { + dummy_feature$set_max_o(max_o) + } + } + + set_feature_fields_from_var_meta(dummy_feature, curent_var_meta) + + dummy_feature$set_featureID(next_feature_id) + next_feature_id <- next_feature_id + 1 + fake_iso <- dummy_feature$get_iso() + iso <- extract_iso(fake_iso) + clusterID <- extract_clusterID(fake_iso, next_cluster_id) + context$clusterID <- clusterID + dummy_feature$set_iso(iso) + create_associated_cluster( + sample, dummy_feature, clusterID, + context, curent_var_meta, next_pc_group, + next_align_group + ) + next_align_group <- next_align_group + 1 + features[[length(features)+1]] <- as.list(dummy_feature, field_names) + dummy_feature$clear() + } + message("")## +\n for previous message + message("Saving features") + dummy_feature$save(bulk=features) + message("Saved.") + return (context$clusters) +} + +extract_peak_var <- function(peak_list, var_name, selector=max) { + value <- peak_list[, var_name] + names(value) <- NULL + return (selector(value)) +} + +set_feature_fields_from_var_meta <- function(feature, var_meta) { + if (!is.null(mz <- var_meta[["mz"]]) && !is.na(mz)) { + feature$set_mz(mz) + } + if (!is.null(mzmin <- var_meta[["mzmin"]]) && !is.na(mzmin)) { + feature$set_mz_min(mzmin) + } + if (!is.null(mzmax <- var_meta[["mzmax"]]) && !is.na(mzmax)) { + feature$set_mz_max(mzmax) + } + if (!is.null(rt <- var_meta[["rt"]]) && !is.na(rt)) { + feature$set_rt(rt) + } + if (!is.null(rtmin <- var_meta[["rtmin"]]) && !is.na(rtmin)) { + feature$set_rt_min(rtmin) + } + if (!is.null(rtmax <- var_meta[["rtmax"]]) && !is.na(rtmax)) { + feature$set_rt_max(rtmax) + } + if (!is.null(isotopes <- var_meta[["isotopes"]]) && !is.na(isotopes)) { + feature$set_iso(isotopes) + } + return (feature) +} + +extract_iso <- function(weird_data) { + if (grepl("^\\[\\d+\\]", weird_data)[[1]]) { + return (sub("^\\[\\d+\\]", "", weird_data, perl=TRUE)) + } + return (weird_data) +} + +extract_clusterID <- function(weird_data, next_cluster_id){ + if (grepl("^\\[\\d+\\]", weird_data)[[1]]) { + clusterID <- stringr::str_extract(weird_data, "^\\[\\d+\\]") + clusterID <- as.numeric(stringr::str_extract(clusterID, "\\d+")) + } else { + clusterID <- 0 + } + return (clusterID + next_cluster_id) +} + +create_associated_cluster <- function( + sample, feature, grouping_variable, + context, curent_var_meta, next_pc_group, next_align_group +) { + pcgroup <- as.numeric(curent_var_meta[["pcgroup"]]) + adduct <- as.character(curent_var_meta[["adduct"]]) + annotation <- curent_var_meta[["isotopes"]] + grouping_variable <- as.character(grouping_variable) + if (is.null(cluster <- context$clusters[[grouping_variable]])) { + cluster <- context$clusters[[grouping_variable]] <- orm$cluster( + pc_group=pcgroup + next_pc_group, + adduct=adduct, + align_group=next_align_group, + # curent_group=curent_group, + clusterID=context$clusterID, + annotation=annotation + )$set_sample(sample) + } else { + if (context$clusterID != 0 && cluster$get_clusterID() == 0) { + cluster$set_clusterID(context$clusterID) + } + } + cluster$save() + feature$set_cluster(cluster) + return (feature) +} + +complete_features <- function(orm, context) { + for (cluster in context$clusters) { + features <- orm$feature()$load_by(cluster_id=cluster$get_id()) + if (features$any()) { + if (!is.null(rt <- features$mean("rt"))) { + cluster$set_mean_rt(rt)$save() + } + features_df <- as.data.frame(features) + central_feature <- features_df[grepl("^\\[M\\]", features_df[, "iso"]), ] + central_feature_into <- central_feature[["int_o"]] + if (!identical(central_feature_into, numeric(0)) && central_feature_into != 0) { + for (feature in as.vector(features)) { + feature$set_abundance( + feature$get_int_o() / central_feature_into * 100 + )$save() + } + } + } + } + return (NULL) +} + +load_process_params <- function(orm, sample, params) { + for (param_list in params) { + if (is.null(param_list[["xfunction"]])) { + next + } + if (param_list[["xfunction"]] == "annotatediff") { + load_process_params_peak_picking(orm, sample, param_list) + } + } + return (sample) +} + +load_process_params_peak_picking <- function(orm, sample, peak_picking_params) { + return (add_sample_process_parameters( + params=peak_picking_params, + params_translation=list( + ppm="ppm", + maxcharge="maxCharge", + maxiso="maxIso" + ), + param_model_generator=orm$peak_picking_parameters, + sample_param_setter=sample$set_peak_picking_parameters + )) +} + +add_sample_process_parameters <- function( + params, + params_translation, + param_model_generator, + sample_param_setter +) { + model_params <- list() + for (rdata_param_name in names(params_translation)) { + database_param_name <- params_translation[[rdata_param_name]] + if (is.null(rdata_param <- params[[rdata_param_name]])) { + next + } + model_params[[database_param_name]] <- rdata_param + } + params_models <- do.call(param_model_generator()$load_by, model_params) + if (params_models$any()) { + params_model <- params_models$first() + } else { + params_model <- do.call(param_model_generator, model_params) + params_model$save() + } + return (sample_param_setter(params_model)$save()) +} + + +library(optparse) + +option_list <- list( + optparse::make_option( + c("-v", "--version"), + action="store_true", + help="Display this tool's version and exits" + ), + optparse::make_option( + c("-i", "--input"), + type="character", + help="The rdata path to import in XSeeker" + ), + optparse::make_option( + c("-s", "--samples"), + type="character", + help="Samples to visualise in XSeeker" + ), + optparse::make_option( + c("-B", "--archetype"), + type="character", + help="The name of the base database" + ), + optparse::make_option( + c("-b", "--database"), + type="character", + help="The base database's path" + ), + optparse::make_option( + c("-c", "--compounds-csv"), + type="character", + help="The csv containing compounds" + ), + optparse::make_option( + c("-m", "--models"), + type="character", + help="The path or url (must begin with http[s]:// or git@) to the database's models" + ), + optparse::make_option( + c("-o", "--output"), + type="character", + help="The path where to output sqlite" + ), + optparse::make_option( + c("-P", "--not-show-percent"), + action="store_true", + help="Flag not to show the percents", + default=FALSE + ) +) + +options(error=function(){traceback(3)}) + +parser <- OptionParser(usage="%prog [options] file", option_list=option_list) +args <- parse_args(parser, positional_arguments=0) + +err_code <- 0 + +if (!is.null(args$options$version)) { + message(sprintf("%s %s", TOOL_NAME, VERSION)) + quit() +} + +models <- get_models(args$options$models) +orm <- DBModelR::ORM( + connection_params=list(dbname=args$options$output), + dbms="SQLite" +) + +invisible(orm$models(models)) +invisible(create_database(orm)) + +message("Database model created") + +insert_adducts(orm) + +if (!is.null(args$options$database)) { + insert_base_data(orm, args$options$database) +} +message(sprintf("Base data inserted using %s.", args$options$database)) + +if (!is.null(args$options$archetype)) { + insert_base_data(orm, args$options$archetype, archetype=TRUE) +} +if (!is.null(args$options$`compounds-csv`)) { + insert_compounds(orm, args$options$`compounds-csv`) +} + +# if (!is.null(args$options$rdata)) { +# load_rdata_in_base(args$options$rdata, args$options$samples, args$options$`not-show-percent`) +# } + + +load(args$options$input, rdata <- new.env()) + +process_rdata(orm, rdata, args$options) + +quit(status=err_code) + + diff -r 000000000000 -r a174cbbb12dd galaxy/tools/LC-MSMS/XSeekerPreparator.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/galaxy/tools/LC-MSMS/XSeekerPreparator.xml Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,343 @@ + + Prepare RData file from CAMERA to be visualized in XSeeker + + + operation_1812 + operation_0335 + + + + R_SCRIPT_PATH + + R + optparse + xcms + blob + fst + stringr + DBModelR + + + + + + + + + + + + R_SCRIPT_PATH '$__tool_directory__/XSeekerPreparator.R' -v + + + + + + + + + + +
+ + +
+ +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ + + + + + + + + +tryCatch({ + DBModelR::ModelDefinition(table="yui", fields=list(yui="INTEGER")) +}, error=function(e) { + stop("Please, install DBModelR before you source this file.") +}) + +list( + adduct=DBModelR::ModelDefinition( + table="adduct", + fields=list( + name="TEXT", + mass="FLOAT", + charge="INTEGER", + multi="INTEGER", + formula_add="TEXT", + formula_ded="TEXT", + sign="TEXT", + oidscore="INTEGER", + quasi="INTEGER", + ips="FLOAT" + ) + ), + cluster=DBModelR::ModelDefinition( + table="cluster", + fields=list( + clusterID="INTEGER", + formula="TEXT", + annotation="TEXT", + coeff="FLOAT", + r_squared="FLOAT", + charge="INTEGER", + mean_rt="FLOAT", + score="FLOAT", + deviation="FLOAT", + status="TEXT", + adduct="TEXT", + curent_group="INTEGER", + pc_group="INTEGER", + align_group="INTEGER", + xcms_group="INTEGER" + ), + one=list("sample", "compound") + ), + compound=DBModelR::ModelDefinition( + table="compound", + fields=list( + name="TEXT", + common_name="TEXT", + formula="TEXT", + charge="INTEGER", + date="TEXT", + mz="FLOAT" + ) + ), + feature=DBModelR::ModelDefinition( + table="feature", + fields=list( + featureID="INTEGER", + mz="FLOAT", + mz_min="FLOAT", + mz_max="FLOAT", + rt="FLOAT", + rt_min="FLOAT", + rt_max="FLOAT", + int_o="FLOAT", + int_b="FLOAT", + max_o="FLOAT", + iso="TEXT", + abundance="FLOAT" + ), + one=list("cluster") + ), + instrument=DBModelR::ModelDefinition( + table="instrument", + fields=list( + model="TEXT", + manufacturer="TEXT", + analyzer="TEXT", + detector_type="TEXT", + ion_source="TEXT" + ) + ), + instrument_config=DBModelR::ModelDefinition( + table="instrument_config", + fields=list( + resolution="TEXT", + agc_target="TEXT", + maximum_IT="TEXT", + number_of_scan_range="TEXT", + scan_range="TEXT", + version="TEXT" + ) + ), + project=DBModelR::ModelDefinition( + table="project", + fields=list( + name="TEXT", + comment="TEXT" + ), + one=list("sample") + ), + sample=DBModelR::ModelDefinition( + table="sample", + fields=list( + name="TEXT", + path="TEXT", + polarity="TEXT", + kind="TEXT", ## rdata or mxml or enriched_rdata + raw="BLOB" + ), + one=list( + "peak_picking_parameters", + "pairing_parameters", + "alignmenmt_parameters", + "camera_parameters", + "instrument", + "instrument_config", + "software", + "smol_xcms_set" + ) + ), + smol_xcms_set=DBModelR::ModelDefinition( + table="smol_xcms_set", + fields=list( + raw="BLOB" + ) + ), + software=DBModelR::ModelDefinition( + table="software", + fields=list( + name="TEXT", + version="TEXT" + ) + ), + peak_picking_parameters=DBModelR::ModelDefinition( + table="peak_picking_parameters", + fields=list( + ppm="FLOAT", + peakwidth="TEXT", + snthresh="TEXT", + prefilterStep="TEXT", + prefilterLevel="TEXT", + mzdiff="TEXT", + fitgauss="TEXT", + noise="TEXT", + mzCenterFun="TEXT", + integrate="INTEGER", + firstBaselineCheck="TEXT", + snthreshIsoROIs="TEXT", + maxCharge="INTEGER", + maxIso="INTEGER", + mzIntervalExtension="TEXT" + ) + ), + alignmenmt_parameters=DBModelR::ModelDefinition( + table="alignmenmt_parameters", + fields=list( + binSize="TEXT", + centerSample="TEXT", + response="TEXT", + distFun="TEXT", + gapInit="TEXT", + gapExtend="TEXT", + factorDiag="TEXT", + factorGap="TEXT", + localAlignment="INTEGER", + initPenalty="TEXT", + bw="TEXT", + minFraction="TEXT", + minSamples="TEXT", + maxFeatures="TEXT" + ) + ) +) + + + diff -r 000000000000 -r a174cbbb12dd test/recreate_full.R --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test/recreate_full.R Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,35 @@ +#!/home/lain/R/bin/Rscript + +ZIP <- FALSE + +file.copy("../convert/yann.rdata", "../convert/yann.rdata.old") +load("../convert/yann.rdata", rdata <- new.env()) + +listOFlistArguments <- rdata$listOFlistArguments +diffrep <- rdata$diffrep +variableMetadata <- rdata$variableMetadata +xa <- rdata$xa +if (ZIP) { + zipfile <- normalizePath("../convert/yann.zip", mustWork=TRUE) + singlefile <- rdata$singlefile +} else { + singles <- list.files("../convert/") + singles <- singles[singles != "yann.rdata"] + singlefile <- list() + for (single in singles) { + singlefile[tools::file_path_sans_ext(single)] <- normalizePath(paste0("../convert/", single)) + } + zipfile <- NULL + print(singlefile) +} + +save( + zipfile, + listOFlistArguments, + diffrep, + variableMetadata, + xa, + singlefile, + file="../convert/yann.rdata" + ,version=2 +) \ No newline at end of file diff -r 000000000000 -r a174cbbb12dd test/test.sh --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test/test.sh Tue Nov 24 18:55:08 2020 +0000 @@ -0,0 +1,18 @@ +#!/bin/sh + +currdir=`pwd` +cd `dirname $(readlink -f $0)` + +ln -s ../data/ ./data + +~/R/bin/Rscript $(realpath ../XSeekerPreparator.R) \ + -i $(realpath ../data/full.rdata) \ + -m $(realpath ../data/models.R) \ + -c $(realpath ../data/SERUM_v2019Jan17.tabular) \ + -o $(realpath ../test.sqlite) \ +|| true + + + +rm -rf "./data" +cd "${currdir}"