Repository 'proteore_get_unique_peptide_srm_method'
hg clone https://toolshed.g2.bx.psu.edu/repos/proteore/proteore_get_unique_peptide_srm_method

Changeset 0:a2b06836de90 (2019-07-12)
Next changeset 1:b72ece649392 (2020-01-30)
Commit message:
planemo upload commit f9de6f4e3302c41e64c39d639bee780e5eafd84d-dirty
added:
README.rst
get_unique_srm.py
proteore_get_unique_peptide_SRM-MRM_method.xml
test-data/Lacombe_et_al_2017_modified.tsv
test-data/proteore_human_srm_atlas.loc
test-data/srm_results.tsv
tool-data/Human_SRM_atlas_2016-04.csv
tool-data/proteore_human_srm_atlas.loc.sample
tool_data_table_conf.xml.sample
tool_data_table_conf.xml.test
b
diff -r 000000000000 -r a2b06836de90 README.rst
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/README.rst Fri Jul 12 07:49:45 2019 -0400
b
@@ -0,0 +1,64 @@
+**Description**
+
+This tool allows to retrieve unique proteotypic peptide and related information (from SRMAtlas) 
+for building Selected Reaction Monitoring (SRM) method using a list of Uniprot accession number as input. 
+The SRMAtlas is a compendium of targeted proteomics assays resulting from high-quality measurements of natural 
+and synthetic peptides conducted on a triple quadrupole mass spectrometer, and is intended as a resource 
+for building selected/multiple reaction monitoring (SRM/MRM)-based proteomic methods.
+
+-----
+
+**Input**
+
+A list of IDs (entered in a copy/paste mode) or a single-column file, the tool will then return a file containing 
+the selected information (peptide sequence/features). If your input is a multiple-column file, the column(s) 
+containing the selected information will be added at the end of the input file. Only Uniprot accession number (e.g. P31946) are allowed. 
+If your list of IDs is not in this form, please use the ID_Converter tool of ProteoRE.
+
+.. class:: warningmark
+
+Accession numbers with an hyphen ("-") that normally correspond to isoform are not considered as similar to its canonical form.
+
+.. class:: warningmark
+
+In copy/paste mode, the number of IDs considered in input is limited to 5000.
+
+-----
+
+**Parameters**
+
+Release: choose the release you want to use for retrieving peptide sequences/features
+Peptide sequence/features: select peptide features you want to retrieve; Peptide sequence 
+(amino acid sequence of detected peptide, including any mass modifications); 
+SSRT (Sequence Specific Retention Time provides a hydrophobicity measure for each peptide using 
+the algorithm of Krohkin et al. SSRCalc); Length (peptide sequence length); MW (molecular weight); 
+PeptideAtlas Accession (PA_Acc).
+
+-----
+
+**Output**
+
+A text file containing the selected peptide features (in addition to the original column(s) provided). 
+Please, note that a "NA" is returned when there is no match between a source ID and SRM/MRM source file.
+
+-----
+
+**Data sources (release date)**
+
+This tool is using the following source file:
+
+- `HumanSRMAtlasPeptidesFinalAnnotated (2016-04) (Kusebauch et al., 2016, PMID: 27453469) <http://www.srmatlas.org/downloads/HumanSRMAtlasPeptidesFinalAnnotated.xlsx>`_.
+
+-----
+
+.. class:: infomark
+
+**Authors**
+
+David Christiany, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
+
+Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR
+
+This work has been partially funded through the French National Agency for Research (ANR) IFB project.
+
+Help: contact@proteore.org for any questions or concerns about this tool.
\ No newline at end of file
b
diff -r 000000000000 -r a2b06836de90 get_unique_srm.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/get_unique_srm.py Fri Jul 12 07:49:45 2019 -0400
[
@@ -0,0 +1,192 @@
+import argparse, csv, re
+
+def get_args():
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--input_type", help="type of input (list of id or filename)", required=True)
+    parser.add_argument("-i", "--input", help="list of IDs (text or filename)", required=True)
+    parser.add_argument("--header", help="true/false if your file contains a header")
+    parser.add_argument("-c", "--column_number", help="list of IDs (text or filename)")
+    parser.add_argument("-f", "--features", help="Protein features to return from SRM Atlas", required=True)
+    parser.add_argument("-d", "--ref_file", help="path to reference file", required=True)
+    parser.add_argument("-o", "--output", help="output filename", required=True)
+    args = parser.parse_args()
+    return args
+
+#return the column number in int format
+def nb_col_to_int(nb_col):
+    try :
+        nb_col = int(nb_col.replace("c", "")) - 1
+        return nb_col
+    except :
+        sys.exit("Please specify the column where you would like to apply the filter with valid format")
+
+#replace all blank cells to NA
+def blank_to_NA(csv_file) :
+    tmp=[]
+    for line in csv_file :
+        line = ["NA" if cell=="" or cell==" " or cell=="NaN" else cell for cell in line]
+        tmp.append(line)
+    
+    return tmp
+
+#convert string to boolean
+def str2bool(v):
+    if v.lower() in ('yes', 'true', 't', 'y', '1'):
+        return True
+    elif v.lower() in ('no', 'false', 'f', 'n', '0'):
+        return False
+    else:
+        raise argparse.ArgumentTypeError('Boolean value expected.')
+
+#return list of (unique) ids from string
+def get_input_ids_from_string(input) :
+
+    ids_list = list(set(re.split(r'\s+',input.replace("_SNP","").replace("d_","").replace("\r","").replace("\n"," ").replace("\t"," "))))
+    if "" in ids_list : ids_list.remove("")
+
+    return ids_list
+
+#return input_file and list of unique ids from input file path
+def get_input_ids_from_file(input,nb_col,header) :
+    with open(input, "r") as csv_file :
+        input_file= list(csv.reader(csv_file, delimiter='\t'))
+
+    input_file, ids_list = one_id_one_line(input_file,nb_col,header)
+    if "" in ids_list : ids_list.remove("")
+
+    return input_file, ids_list
+
+#function to check if an id is an uniprot accession number : return True or False-
+def check_uniprot (id):
+    uniprot_pattern = re.compile("[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}")
+    if uniprot_pattern.match(id) :
+        return True
+    else :
+        return False
+
+#return input file by adding lines when there are more than one id per line
+def one_id_one_line(input_file,nb_col,header) :
+
+    if header : 
+        new_file = [input_file[0]]
+        input_file = input_file[1:]
+    else : 
+        new_file=[]
+    ids_list=[]
+
+    for line in input_file :
+        if line != [] and set(line) != {''}: 
+            line[nb_col] = re.sub(r"\s+","",line[nb_col])
+            if line[nb_col] == "" : line[nb_col]='NA'
+            if ";" in line[nb_col] :
+                ids = line[nb_col].split(";")
+                for id in ids :
+                    new_file.append(line[:nb_col]+[id]+line[nb_col+1:])
+                    ids_list.append(id)
+            else : 
+                new_file.append(line)
+                ids_list.append(line[nb_col])
+
+    ids_list=[e.replace("_SNP","").replace("d_","") for e in ids_list]
+    ids_list= list(set(ids_list))
+
+    return new_file, ids_list
+
+def create_srm_atlas_dictionary(features,srm_atlas_csv):
+
+    srm_atlas={}
+    features_index = {"PeptideSeq" : 0, "SSRT" : 1 , "Length" : 2 , "type": 3 , "PA_AccNum" : 4, "MW" : 5 }
+    features_to_get = [features_index[feature] for feature in features]
+    for line in srm_atlas_csv[1:]:
+        id = line[9].replace("_SNP","").replace("d_","")
+        if id not in srm_atlas:
+            srm_atlas[id]=[[line[i] for i in features_to_get]]
+        else: 
+            srm_atlas[id].append([line[i] for i in features_to_get])
+    return srm_atlas
+
+def retrieve_srm_features(srm_atlas,ids):
+
+    result_dict = {}
+    for id in ids:
+        if id in srm_atlas:
+            res = srm_atlas[id]
+        else :
+            res=""
+        result_dict[id]=res
+    return result_dict
+
+def create_header(input_file,ncol,features):
+    col_names = list(range(1,len(input_file[0])+1))
+    col_names = ["col"+str(e) for e in col_names]
+    col_names[ncol]="Uniprot-AC"
+    col_names = col_names+features
+    return(col_names)
+
+def main():
+    
+    #Get args from command line
+    args = get_args()
+    features=args.features.split(",")
+    header=False
+    if args.input_type=="file" :
+        column_number = nb_col_to_int(args.column_number)
+        header = str2bool(args.header)
+
+    #Get reference file (Human SRM Atlas)
+    with open(args.ref_file, "r") as csv_file :
+        srm_atlas_csv = csv.reader(csv_file, delimiter='\t')
+        srm_atlas_csv = [line for line in srm_atlas_csv]
+
+    #Create srm Atlas dictionary 
+    srm_atlas = create_srm_atlas_dictionary(features,srm_atlas_csv)
+        
+    #Get file and/or ids from input 
+    if args.input_type == "list" :
+        ids = get_input_ids_from_string(args.input)
+    elif args.input_type == "file" :
+        input_file, ids = get_input_ids_from_file(args.input,column_number,header)
+
+    #Check Uniprot-AC
+    if not any([check_uniprot(id) for id in ids]):
+        print ("No Uniprot-AC found, please check your input")
+        exit()
+
+    #retrieve features
+    result_dict = retrieve_srm_features(srm_atlas,ids)
+
+    #write output
+    with open(args.output,"w") as output :
+        writer = csv.writer(output,delimiter="\t")
+
+        #write header
+        if header : 
+            writer.writerow(input_file[0]+features)
+            input_file = input_file[1:]  
+        elif args.input_type=="file":
+            col_names = [create_header(input_file,column_number,features)]
+            writer.writerow(col_names)
+        else : 
+            writer.writerow(["Uniprot-AC"]+features)
+
+        #write lines 
+        previous_line=""
+        if args.input_type=="file" :
+            for line in input_file :
+                for res in result_dict[line[column_number]]:
+                    output_line = ["NA" if cell=="" or cell==" " or cell=="NaN" else cell for cell in line+res]
+                    if previous_line != output_line :
+                        writer.writerow(output_line)
+                        previous_line=output_line
+        elif args.input_type=="list" :
+            for id in ids :
+                for res in result_dict[id]:
+                    line = ["NA" if cell=="" or cell==" " or cell=="NaN" else cell for cell in [id]+res]
+                    if previous_line != line :
+                        writer.writerow(line)
+                        previous_line=line
+    
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
b
diff -r 000000000000 -r a2b06836de90 proteore_get_unique_peptide_SRM-MRM_method.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/proteore_get_unique_peptide_SRM-MRM_method.xml Fri Jul 12 07:49:45 2019 -0400
[
@@ -0,0 +1,154 @@
+<tool id="proteore_get_unique_peptide_srm_method" name="Get unique peptide SRM-MRM method" version="2019.07.11">
+    <description>[SRM Atlas]</description>
+    <requirements>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+
+        python $__tool_directory__/get_unique_srm.py 
+        
+        #if $input.ids == "text"
+            --input="$input.txt"
+            --input_type="list"
+        #else
+            --input="$input.input_file"
+            --column_number="$input.ncol"
+            --header="$input.header"
+            --input_type="file"
+        #end if
+
+        --features="$protein_features"
+        --output="$output"
+        
+        #if "SRM_atlas" in str($srm_file).split("/")
+            --ref_file="$srm_file"
+        #else 
+            --ref_file="$__tool_directory__/$srm_file"
+        #end if 
+
+    ]]></command>
+    <inputs>
+    <conditional name="input" >
+        <param name="ids" type="select" label="Enter IDs (Uniprot Accession number, e.g. P04746)" help="Copy/paste or from a file (e.g. table)" >
+            <option value="text">Copy/paste your Uniprot-AC identifiers</option>
+            <option value="file" selected="true">Input file containing Uniprot-AC identifiers</option>
+        </param>
+        <when value="text" >
+            <param name="txt" type="text" label="Copy/paste IDs" help='IDs must be separated by tab, space or carriage return into the form field, for example: P31946 P62258' >
+                <sanitizer invalid_char="">
+                    <valid initial="string.printable">
+                        <remove value="&apos;"/>
+                    </valid>
+                    <mapping initial="none">
+                        <add source="&apos;" target="__sq__"/>
+                        <add source="&#x20;" target=""/>
+                        <add source="&#xA;" target=""/>
+                        <add source="&#xD;" target=""/>
+                        <add source="&#x9;" target=""/>
+                    </mapping>
+                </sanitizer>
+            </param>
+        </when>
+        <when value="file" >
+            <param name="input_file" type="data" format="txt,tabular" label="Select your file" help="" />
+            <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" />
+            <param name="ncol" type="text" value="c1" label="Column number of IDs" help='For example, fill in "c1" if it is the first column, "c2" if it is the second column and so on'>
+                <validator type="regex" message="Please enter a column number, for example: 'c1' for the first column">[c]{0,1}[0-9]+</validator>
+            </param>
+        </when>
+    </conditional>
+    <param name="srm_file" type="select" label="Release" >
+        <options from_data_table="proteore_human_srm_atlas">
+            <filter type="sort_by" column="0"/>
+        </options>
+    </param>
+    <param name="protein_features" type="select" label="Peptide sequence/features" multiple="true" help="" display="checkboxes" optional="false">
+        <option value="PeptideSeq" selected="true">Peptide sequence</option>
+        <option value="SSRT" selected="false">SSRT (Sequence Specific Retention Time)</option>
+        <option value="Length" selected="false">Length (peptide sequence length)</option>
+        <option value="MW" selected="false">MW (Molecular weight)</option>
+        <option value="PA_AccNum" selected="false">PeptideAtlas Accession (PA_Acc)</option>
+    </param>
+    </inputs>
+    <outputs>
+        <data name="output" format="tsv"/>
+    </outputs>
+    <tests>
+        <test>
+            <conditional name="input" >
+                <param name="ids" value="file"/>
+                <param name="input_file" value="Lacombe_et_al_2017_modified.tsv" />
+                <param name="header" value="true" />
+                <param name="ncol" value="c1"/>
+            </conditional>
+            <param name="srm_file" value="tool-data/Human_SRM_atlas_2016-04.csv" />
+            <param name="protein_features" value="PeptideSeq,SSRT,Length,MW,PA_AccNum"/>
+            <output name="output" value="srm_results.tsv" />
+        </test>
+    </tests>
+    <help><![CDATA[
+        **Description**
+
+This tool allows to retrieve unique proteotypic peptide and related information (from SRMAtlas) 
+for building Selected Reaction Monitoring (SRM) method using a list of Uniprot accession number as input. 
+The SRMAtlas is a compendium of targeted proteomics assays resulting from high-quality measurements of natural 
+and synthetic peptides conducted on a triple quadrupole mass spectrometer, and is intended as a resource 
+for building selected/multiple reaction monitoring (SRM/MRM)-based proteomic methods.
+
+-----
+
+**Input**
+
+A list of IDs (entered in a copy/paste mode) or a single-column file, the tool will then return a file containing 
+the selected information (peptide sequence/features). If your input is a multiple-column file, the column(s) 
+containing the selected information will be added at the end of the input file. Only Uniprot accession number (e.g. P31946) are allowed. 
+If your list of IDs is not in this form, please use the ID_Converter tool of ProteoRE.
+
+.. class:: warningmark
+
+Accession numbers with an hyphen ("-") that normally correspond to isoform are not considered as similar to its canonical form.
+
+.. class:: warningmark
+
+In copy/paste mode, the number of IDs considered in input is limited to 5000.
+
+-----
+
+**Parameters**
+
+Release: choose the release you want to use for retrieving peptide sequences/features
+Peptide sequence/features: select peptide features you want to retrieve; Peptide sequence 
+(amino acid sequence of detected peptide, including any mass modifications); 
+SSRT (Sequence Specific Retention Time provides a hydrophobicity measure for each peptide using 
+the algorithm of Krohkin et al. SSRCalc); Length (peptide sequence length); MW (molecular weight); 
+PeptideAtlas Accession (PA_Acc).
+
+-----
+
+**Output**
+
+A text file containing the selected peptide features (in addition to the original column(s) provided). 
+Please, note that a "NA" is returned when there is no match between a source ID and SRM/MRM source file.
+
+-----
+
+**Data sources (release date)**
+
+This tool is using the following source file:
+
+- `HumanSRMAtlasPeptidesFinalAnnotated (2016-04) (Kusebauch et al., 2016, PMID: 27453469) <http://www.srmatlas.org/downloads/HumanSRMAtlasPeptidesFinalAnnotated.xlsx>`_.
+
+-----
+
+.. class:: infomark
+
+**Authors**
+
+David Christiany, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
+
+Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR
+
+This work has been partially funded through the French National Agency for Research (ANR) IFB project.
+
+Help: contact@proteore.org for any questions or concerns about this tool.
+    ]]></help>
+</tool>
\ No newline at end of file
b
diff -r 000000000000 -r a2b06836de90 test-data/Lacombe_et_al_2017_modified.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/Lacombe_et_al_2017_modified.tsv Fri Jul 12 07:49:45 2019 -0400
[
@@ -0,0 +1,160 @@
+#Protein accession number (UniProt) Protein name Number of peptides (razor + unique)
+P15924 Desmoplakin 69
+P02538 Keratin, type II cytoskeletal 6A 53
+P02768 Serum albumin 44
+P08779 Keratin, type I cytoskeletal 16 29
+Q02413 Desmoglein-1 24
+P07355 Annexin A2;Putative annexin A2-like protein 22
+P14923 Junction plakoglobin 22
+P02788;Q9HC84;P29508 Lactotransferrin 21
+P63261 Actin, cytoplasmic 2 19
+Q8N1N4 Keratin, type II cytoskeletal 78 18
+Q04695 Keratin, type I cytoskeletal 17 18
+P01876 Ig alpha-1 chain C region 16
+Q01469 Fatty acid-binding protein 5, epidermal 15
+ Caspase-14 15
+ Polymeric immunoglobulin receptor 15
+ Alpha-enolase 15
+ Zinc-alpha-2-glycoprotein 15
+ Plectin 15
+ Keratin, type II cytoskeletal 4 13
+ Keratin, type II cytoskeletal 80 13
+ Protein-glutamine gamma-glutamyltransferase E 12
+P13646 Keratin, type I cytoskeletal 13 11
+Q86YZ3 Hornerin 11
+P04259 Keratin, type II cytoskeletal 6B 10
+P02545 Prelamin-A/C;Lamin-A/C 10
+P04083 Annexin A1 10
+P11021 78 kDa glucose-regulated protein 10
+P02787 Serotransferrin 9
+P04040 Catalase 9
+P31151 Protein S100-A7 9
+P31947 14-3-3 protein sigma 9
+Q96P63 Serpin B12 9
+P14618 Pyruvate kinase PKM 9
+P60174 Triosephosphate isomerase 9
+Q06830 Peroxiredoxin-1 9
+P01040 Cystatin-A 8
+P05089 Arginase-1 8
+P01834 8
+P04406 8
+P0DMV9 8
+P13639 8
+P35579 8
+P68371 8
+Q8WVV4 8
+O75635 7
+P01857 7
+P61626 7
+P68363 7
+P01009 6
+P07900 Heat shock protein HSP 90-alpha 6
+Q9NZH8 Interleukin-36 gamma 6
+O43707 Alpha-actinin-4;Alpha-actinin-1 6
+O75223 Gamma-glutamylcyclotransferase 6
+P00338 L-lactate dehydrogenase A chain 6
+P07339 Cathepsin D 6
+P62987 Ubiquitin-60S ribosomal protein L40 6
+P10599 Thioredoxin 6
+Q9UGM3 Deleted in malignant brain tumors 1 protein 6
+Q9UI42 Carboxypeptidase A4 6
+P47929 Galectin-7 5
+Q13867 Bleomycin hydrolase 5
+Q6P4A8 Phospholipase B-like 1 5
+O75369 Filamin-B 5
+P00441 Superoxide dismutase [Cu-Zn] 5
+P04792 Heat shock protein beta-1 5
+P11142 Heat shock cognate 71 kDa protein 5
+P58107 Epiplakin 5
+P60842 Eukaryotic initiation factor 4A-I 5
+P62937 Peptidyl-prolyl cis-trans isomerase A 5
+P63104 14-3-3 protein zeta/delta 5
+Q92820 Gamma-glutamyl hydrolase 5
+O75342 Arachidonate 12-lipoxygenase, 12R-type 4
+P09211 Glutathione S-transferase P 4
+P31025 Lipocalin-1 4
+P48594 Serpin B4 4
+Q14574 Desmocollin-3 4
+Q5T750 Skin-specific protein 32 4
+Q6UWP8 Suprabasin 4
+O60911 Cathepsin L2 4
+P00558 Phosphoglycerate kinase 1 4
+P04075 Fructose-bisphosphate aldolase A 4
+P07384 Calpain-1 catalytic subunit 4
+P0CG05 Ig lambda-2 chain C regions 4
+P18206 Vinculin 4
+P62258 14-3-3 protein epsilon 4
+P68871 Hemoglobin subunit beta 4
+Q9C075 Keratin, type I cytoskeletal 23 4
+A8K2U0 Alpha-2-macroglobulin-like protein 1 3
+P00738 Haptoglobin 3
+P01011 Alpha-1-antichymotrypsin 3
+P02763 Alpha-1-acid glycoprotein 1 3
+P18510 Interleukin-1 receptor antagonist protein 3
+P22528 Cornifin-B 3
+P30740 Leukocyte elastase inhibitor 3
+P80188 Neutrophil gelatinase-associated lipocalin 3
+Q15828 Cystatin-M 3
+Q9HCY8 Protein S100-A14 3
+P01623 Ig kappa chain V-III region 3
+P01877 Ig alpha-2 chain C region 3
+P06396 Gelsolin 3
+P14735 Insulin-degrading enzyme 3
+P20933 N(4)-(beta-N-acetylglucosaminyl)-L-asparaginase 3
+P25788 Proteasome subunit alpha type-3 3
+P26641 Elongation factor 1-gamma 3
+P36952 Serpin B5 3
+P40926 Malate dehydrogenase, mitochondrial 3
+Q9Y6R7 IgGFc-binding protein 3
+O95274 Ly6/PLAUR domain-containing protein 3 2
+P00491 Purine nucleoside phosphorylase 2
+P04080 Cystatin-B 2
+P09972 Fructose-bisphosphate aldolase C 2
+P19012 Keratin, type I cytoskeletal 15 2
+P20930 Filaggrin 2
+Q96FX8 p53 apoptosis effector related to PMP-22 2
+Q9UIV8 Serpin B13 2
+P01625 Ig kappa chain V-IV region Len 2
+P01765 Ig heavy chain V-III region TIL 2
+P01766 Ig heavy chain V-III region BRO 2
+P01860 Ig gamma-3 chain C region 2
+P01871 Ig mu chain C region 2
+P05090 Apolipoprotein D 2
+P06870 Kallikrein-1 2
+P07858 Cathepsin B 2
+P08865 40S ribosomal protein SA 2
+P11279 Lysosome-associated membrane glycoprotein 1 2
+P13473 Lysosome-associated membrane glycoprotein 2 2
+P19971 Thymidine phosphorylase 2
+P23284 Peptidyl-prolyl cis-trans isomerase B 2
+P23396 40S ribosomal protein S3 2
+P25705 ATP synthase subunit alpha, mitochondrial 2
+P27482 Calmodulin-like protein 3 2
+P31949 Protein S100-A11 2
+P40121 Macrophage-capping protein 2
+P42357 Histidine ammonia-lyase 2
+P47756 F-actin-capping protein subunit beta 2
+P48637 Glutathione synthetase 2
+P49720 Proteasome subunit beta type-3 2
+P50395 Rab GDP dissociation inhibitor beta 2
+P59998 Actin-related protein 2/3 complex subunit 4 2
+P61160 Actin-related protein 2 2
+P61916 Epididymal secretory protein E1 2
+P04745 Alpha-amylase 1 23
+Q9NZT1 Calmodulin-like protein 5 8
+P12273 Prolactin-inducible protein 6
+Q96DA0 Zymogen granule protein 16 homolog B 5
+P01036 Cystatin-S 5
+Q8TAX7 Mucin-7 2
+P01037 Cystatin-SN 2
+P09228 Cystatin-SA 2
+P04264 Keratin, type II cytoskeletal 1 61
+P35908 Keratin, type II cytoskeletal 2 epidermal 40
+P13645 Keratin, type I cytoskeletal 10 40
+Q5D862 Filaggrin-2 14
+Q5T749 Keratinocyte proline-rich protein 13
+Q8IW75 Serpin A12 3
+P81605 Dermcidin 3
+P22531 Small proline-rich protein 2E 3
+P59666 Neutrophil defensin 3 2
+P78386 Keratin, type II cuticular Hb5 2
b
diff -r 000000000000 -r a2b06836de90 test-data/proteore_human_srm_atlas.loc
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/proteore_human_srm_atlas.loc Fri Jul 12 07:49:45 2019 -0400
b
@@ -0,0 +1,2 @@
+#<id> <release> <name> <value>
+9979839599 2016-04 Human SRM atlas (2016-04) tool-data/Human_SRM_atlas_2016-04.csv
b
diff -r 000000000000 -r a2b06836de90 test-data/srm_results.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/srm_results.tsv Fri Jul 12 07:49:45 2019 -0400
b
b'@@ -0,0 +1,1129 @@\n+#Protein accession number (UniProt)\tProtein name\tNumber of peptides (razor + unique)\tPeptideSeq\tSSRT\tLength\tMW\tPA_AccNum\r\n+P15924\tDesmoplakin\t69\tLQSLTEDLTK\t22,6\t10\t1146,6132\tPAp01640065\r\n+P15924\tDesmoplakin\t69\tYETEIDITK\t19,1\t9\t1110,5445\tPAp01640060\r\n+P15924\tDesmoplakin\t69\tADSSATETINK\t8,6\t11\t1135,5357\tPAp01884047\r\n+P15924\tDesmoplakin\t69\tNQFETEIDITK\t28,1\t11\t1336,651\tPAp01640117\r\n+P15924\tDesmoplakin\t69\tITDLTQQLEQASIVK\t32\t15\t1685,9199\tPAp01640175\r\n+P15924\tDesmoplakin\t69\tAQIDDLTR\t15,9\t8\t930,477\tPAp01884148\r\n+P15924\tDesmoplakin\t69\tDATILELR\t25,6\t8\t929,5182\tPAp01884332\r\n+P15924\tDesmoplakin\t69\tLDDSILQATEQR\t21,8\t12\t1387,6943\tPAp01885875\r\n+P15924\tDesmoplakin\t69\tGFFDPNTEENLTYLQLK\t40,2\t17\t2027,984\tPAp00044234\r\n+P15924\tDesmoplakin\t69\tITNLTQQLEQASIVK\t31\t15\t1684,9359\tPAp00044505\r\n+P15924\tDesmoplakin\t69\tALLQAILQTEDMLK\t40\t14\t1585,8749\tPAp00374731\r\n+P15924\tDesmoplakin\t69\tIEVLEEELR\t27\t9\t1128,6026\tPAp00092953\r\n+P15924\tDesmoplakin\t69\tSMVEDITGLR\t28,3\t10\t1119,5594\tPAp00374719\r\n+P15924\tDesmoplakin\t69\tSAIYQLEEEYENLLK\t39,1\t15\t1840,9094\tPAp00045295\r\n+P15924\tDesmoplakin\t69\tLLEAQACTGGIIHPTTGQK\t26,7\t19\t1937,004\tPAp00005080\r\n+P15924\tDesmoplakin\t69\tGSFDATGNSSYSYSYSFSSSSIGH\t31,2\t24\t2494,0197\tPAp01748200\r\n+P15924\tDesmoplakin\t69\tIQSQFTDAQK\t14,4\t10\t1164,5775\tPAp00527111\r\n+P15924\tDesmoplakin\t69\tVTAMQLYECQLIDK\t36,6\t14\t1653,8106\tPAp00400165\r\n+P15924\tDesmoplakin\t69\tFGDSNTVMR\t17,5\t9\t1025,46\tPAp00404146\r\n+P02538\tKeratin, type II cytoskeletal 6A\t53\tGMQDLVEDFK\t29,1\t10\t1180,5434\tPAp00044284\r\n+P02538\tKeratin, type II cytoskeletal 6A\t53\tSGFSSVSVSR\t18,9\t10\t1011,4985\tPAp00045352\r\n+P02768\tSerum albumin\t44\tLVDEVTEFAK\t25,7\t10\t1149,5917\tPAp01639378\r\n+P02768\tSerum albumin\t44\tLVNEVTEFAK\t24,5\t10\t1148,6077\tPAp00026771\r\n+P02768\tSerum albumin\t44\tEFNAETFTFHADICTLSEK\t39,3\t19\t2201,9939\tPAp00001996\r\n+P02768\tSerum albumin\t44\tLVTDLTK\t17\t7\t788,4644\tPAp00044857\r\n+P02768\tSerum albumin\t44\tSLHTLFGDK\t23,3\t9\t1016,5291\tPAp00031453\r\n+P02768\tSerum albumin\t44\tLVAASQAALGL\t27,8\t11\t1012,5917\tPAp00044845\r\n+P02768\tSerum albumin\t44\tCCTESLVNR\t12,7\t9\t1023,4478\tPAp00000881\r\n+P02768\tSerum albumin\t44\tYICENQDSISSK\t14,8\t12\t1385,6133\tPAp00008936\r\n+P02768\tSerum albumin\t44\tRPCFSALEVDETYVPK\t34,1\t16\t1852,9029\tPAp00006780\r\n+P08779\tKeratin, type I cytoskeletal 16\t29\tAPSTYGGGLSVSSR\t18,3\t14\t1337,6575\tPAp00091920\r\n+P08779\tKeratin, type I cytoskeletal 16\t29\tIIAATIENAQPILQIDNAR\t40,9\t19\t2063,1375\tPAp00044452\r\n+P08779\tKeratin, type I cytoskeletal 16\t29\tEQSSSSFSQGQSS\t8,4\t13\t1344,543\tPAp00742754\r\n+P08779\tKeratin, type I cytoskeletal 16\t29\tDAETWFLSK\t28,5\t9\t1095,5237\tPAp00043800\r\n+P08779\tKeratin, type I cytoskeletal 16\t29\tEVASNSELVQSSR\t16,2\t13\t1404,6845\tPAp00092329\r\n+Q02413\tDesmoglein-1\t24\tTGEIDITSIVDR\t31\t12\t1317,6776\tPAp01700982\r\n+Q02413\tDesmoglein-1\t24\tESSNVVVTER\t13,7\t10\t1118,5568\tPAp00620220\r\n+Q02413\tDesmoglein-1\t24\tIHSDCAANQQVTYR\t14,5\t14\t1604,7365\tPAp00803601\r\n+Q02413\tDesmoglein-1\t24\tMTGFELTEGVK\t26,6\t11\t1210,5904\tPAp00374345\r\n+Q02413\tDesmoglein-1\t24\tEGGLNMNFMESYFCQK\t39\t16\t1896,7845\tPAp00432530\r\n+Q02413\tDesmoglein-1\t24\tDGGADGMSAECECNIK\t15,9\t16\t1598,6011\tPAp01522270\r\n+Q02413\tDesmoglein-1\t24\tSSSDHHFNQTIGSASPSTAR\t18,4\t20\t2085,9464\tPAp00626608\r\n+Q02413\tDesmoglein-1\t24\tALNSMGQDLERPLELR\t33,2\t16\t1840,9465\tPAp00491147\r\n+Q02413\tDesmoglein-1\t24\tEQYGQYALAVR\t23,2\t11\t1296,6462\tPAp00148323\r\n+Q02413\tDesmoglein-1\t24\tYSTVQYSK\t11,3\t8\t974,4709\tPAp01673050\r\n+Q02413\tDesmoglein-1\t24\tTGEINITSIVDR\t28,7\t12\t1316,6936\tPAp01700983\r\n+Q02413\tDesmoglein-1\t24\tYVMGNNPADLLAVDSR\t31,4\t16\t1733,8406\tPAp00045975\r\n+Q02413\tDesmoglein-1\t24\tVGDFVATDLDTGRPSTTVR\t31,4\t19\t2006,0068\tPAp00045748\r\n+P07355\tAnnexin A2;Putative annexin A2-like protein\t22\tGVDEVTIVNILTDR\t40,2\t14\t1542,8253\tPAp01698614\r\n+P07355\tAnnexin A2;Putative annexin A2-like protein\t22\tPLYFADR\t22,7\t7\t880,4443\tPAp00394780\r\n+P07355\tAnnexin A2;Putative annexin A2-like protein\t22\tAEDGSVIDYELIDQDAR\t34,3\t17\t1907,8748\tPAp00063109\r\n+P07355\tAnnexin A2;Putative annexin A2-like protein\t22\tDLYDAGVK\t16,4\t8\t879,4338\tPAp00065217\r\n+P07355\tAnnexin A2;Putative annexin A2-like protein\t22\tQDIAFAYQR\t21,5\t9\t1110,54'..b'tal 2 epidermal\t40\tVDLLNQEIEFLK\t40\t12\t1459,7922\tPAp00045714\r\n+P35908\tKeratin, type II cytoskeletal 2 epidermal\t40\tYEELQVTVGR\t21,1\t10\t1192,6088\tPAp00045909\r\n+P35908\tKeratin, type II cytoskeletal 2 epidermal\t40\tGSSGEAFGSSVTFSFR\t30,9\t16\t1621,7372\tPAp00092756\r\n+P35908\tKeratin, type II cytoskeletal 2 epidermal\t40\tHGGGGGGFGGGGFGSR\t15,9\t16\t1319,5755\tPAp00034510\r\n+P35908\tKeratin, type II cytoskeletal 2 epidermal\t40\tGFSSGSAVVSGGSR\t16,4\t14\t1253,6\tPAp00044239\r\n+P13645\tKeratin, type I cytoskeletal 10\t40\tNQILDLTTDNANILLQIDNAR\t46,9\t21\t2367,2394\tPAp01886410\r\n+P13645\tKeratin, type I cytoskeletal 10\t40\tVLDELTLTK\t27,2\t9\t1030,591\tPAp00045773\r\n+P13645\tKeratin, type I cytoskeletal 10\t40\tADLEMQIESLTEELAYLK\t44,3\t18\t2095,0395\tPAp00039328\r\n+P13645\tKeratin, type I cytoskeletal 10\t40\tALEESNYELEGK\t20,9\t12\t1380,6409\tPAp00032393\r\n+P13645\tKeratin, type I cytoskeletal 10\t40\tSLLEGEGSSGGGGR\t14,6\t14\t1261,5898\tPAp00045412\r\n+P13645\tKeratin, type I cytoskeletal 10\t40\tGSLGGGFSSGGFSGGSFSR\t30,4\t19\t1706,7648\tPAp00040588\r\n+Q5D862\tFilaggrin-2\t14\tSVVTVIDVFYK\t42,4\t11\t1268,7016\tPAp00045500\r\n+Q5D862\tFilaggrin-2\t14\tFSNSSSSNEFSK\t14\t12\t1319,563\tPAp00374343\r\n+Q5D862\tFilaggrin-2\t14\tHQEEESETEEDEEDTPGHK\t8,5\t19\t2253,8781\tPAp00517702\r\n+Q5D862\tFilaggrin-2\t14\tNPDDPDTVDVIMHMLDR\t36,1\t17\t1981,8873\tPAp00618232\r\n+Q5D862\tFilaggrin-2\t14\tSQHGESESIVHER\t10,9\t13\t1493,6859\tPAp01668429\r\n+Q5D862\tFilaggrin-2\t14\tLETTHGQTGDTTR\t6,2\t13\t1415,6641\tPAp01667284\r\n+Q5D862\tFilaggrin-2\t14\tESGEEYESGSGSNSWER\t16,9\t17\t1888,7347\tPAp00626610\r\n+Q5D862\tFilaggrin-2\t14\tSISNSHLSWSTDSTANK\t23,2\t17\t1833,8493\tPAp01643746\r\n+Q5D862\tFilaggrin-2\t14\tFGGQGNQFSYIQSGCQSGIK\t29\t20\t2104,9636\tPAp01649403\r\n+Q5D862\tFilaggrin-2\t14\tSSGFAQHEYR\t14,6\t10\t1180,5261\tPAp01645800\r\n+Q5D862\tFilaggrin-2\t14\tENGQPQNCGGQWR\t11,2\t13\t1472,6215\tPAp01522213\r\n+Q5D862\tFilaggrin-2\t14\tSQHGESGSAIHGR\t6,3\t13\t1321,6123\tPAp00160539\r\n+Q5D862\tFilaggrin-2\t14\tELHPVLK\t20\t7\t834,4963\tPAp01693963\r\n+Q5D862\tFilaggrin-2\t14\tEFHPVLK\t21,8\t7\t868,4807\tPAp01693904\r\n+Q5T749\tKeratinocyte proline-rich protein\t13\tIEISSPCCPR\t16,7\t10\t1103,5103\tPAp00446039\r\n+Q5T749\tKeratinocyte proline-rich protein\t13\tLDQCPESPLQR\t17,8\t11\t1284,6132\tPAp01533921\r\n+Q5T749\tKeratinocyte proline-rich protein\t13\tFSTQCQYQGSYSSCGPQFQSR\t23,3\t21\t2387,9899\tPAp00803679\r\n+Q5T749\tKeratinocyte proline-rich protein\t13\tGQDGHGDQGNAFAGVK\t12,3\t16\t1556,6967\tPAp00937968\r\n+Q5T749\tKeratinocyte proline-rich protein\t13\tCPVEIPPIR\t24,8\t9\t1022,5583\tPAp01526978\r\n+Q5T749\tKeratinocyte proline-rich protein\t13\tSEPIYNSR\t12,7\t8\t964,4614\tPAp01675510\r\n+Q5T749\tKeratinocyte proline-rich protein\t13\tMCDQQQIQCR\t9,2\t10\t1251,5159\tPAp01675007\r\n+Q8IW75\tSerpin A12\t3\tHEFDPDVTK\t17,8\t9\t1086,4982\tPAp01698675\r\n+Q8IW75\tSerpin A12\t3\tDITAIFILPDEGK\t36,7\t13\t1430,7657\tPAp01697390\r\n+Q8IW75\tSerpin A12\t3\tIFEEHGDLTK\t21,6\t10\t1187,5822\tPAp01562397\r\n+Q8IW75\tSerpin A12\t3\tGLQVDTFSR\t21,1\t9\t1021,5192\tPAp01568902\r\n+Q8IW75\tSerpin A12\t3\tSGIYQVGYDDK\t20,1\t11\t1243,5721\tPAp01572711\r\n+Q8IW75\tSerpin A12\t3\tNITAIFILPDEGK\t36,5\t13\t1429,7816\tPAp01571789\r\n+Q8IW75\tSerpin A12\t3\tLHMTGTFDLK\t27\t10\t1161,5852\tPAp01570464\r\n+Q8IW75\tSerpin A12\t3\tIVNPIGK\t14,4\t7\t739,4592\tPAp01672748\r\n+Q8IW75\tSerpin A12\t3\tHEFDPNVTK\t16,4\t9\t1085,5142\tPAp01698676\r\n+P81605\tDermcidin\t3\tYDPEAASAPGSGNPCHEASAAQK\t12,2\t23\t2256,9705\tPAp00008846\r\n+P81605\tDermcidin\t3\tAVGGLGK\t9,2\t7\t600,3595\tPAp01037828\r\n+P81605\tDermcidin\t3\tGAVHDVK\t6,1\t7\t724,3868\tPAp01568544\r\n+P81605\tDermcidin\t3\tDVLDSVL\t27,1\t7\t759,4014\tPAp01747140\r\n+P81605\tDermcidin\t3\tDAVEDLESVGK\t21,5\t11\t1160,5561\tPAp00043805\r\n+P81605\tDermcidin\t3\tENAGEDPGLAR\t11,8\t11\t1127,5207\tPAp00092279\r\n+P59666\tNeutrophil defensin 3\t2\tNMDCYCR\t9,3\t7\t903,3037\tPAp01532701\r\n+P78386\tKeratin, type II cuticular Hb5\t2\tWQFYQNQR\t22,9\t8\t1168,5414\tPAp00150342\r\n+P78386\tKeratin, type II cuticular Hb5\t2\tSDLEANVEALVEESSFLR\t39,3\t18\t2006,9796\tPAp00429303\r\n+P78386\tKeratin, type II cuticular Hb5\t2\tCCESNLEPLFSGYIETLR\t42,7\t18\t2072,9547\tPAp00429337\r\n+P78386\tKeratin, type II cuticular Hb5\t2\tVLQAHISDTSVIVK\t28\t14\t1508,8562\tPAp00061772\r\n+P78386\tKeratin, type II cuticular Hb5\t2\tLEAAVAEAEQQGEAALSDAR\t25,6\t20\t2027,9759\tPAp00093270\r\n'
b
diff -r 000000000000 -r a2b06836de90 tool-data/Human_SRM_atlas_2016-04.csv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/Human_SRM_atlas_2016-04.csv Fri Jul 12 07:49:45 2019 -0400
b
b'@@ -0,0 +1,166175 @@\n+PeptideSeq\tSSRT\tLength\ttype\tPA_AccNum\tMW\te_charge\tn_map_core\tn_map_all\tProt_acc\n+GTTYHCK\t4,3\t7\tK\tPAp01561636\t808,3538\t3\t1\t1\tA0A183\n+QQSWKPPNVPK\t16,3\t11\tK\tPAp01592044\t1307,6986\t3\t1\t1\tA0A183\n+NVFPPEVAVFEPSEAEISHTQK\t36,6\t22\tK\tPAp00537499\t2454,2067\t3\t1\t1\tA0A5B9\n+ATLVCLATGFYPDHVELSWWVNGK\t55,8\t24\tK\tPAp02018443\t2705,3311\t3\t1\t1\tA0A5B9\n+ADCGFTSESYQQGVLSATILYEILLGK\t54,8\t27\tK\tPAp02018292\t2905,4419\t2\t1\t1\tA0A5B9\n+CQVQFYGLSENDEWTQDR\t34,4\t18\tR\tPAp00001326\t2216,9433\t2\t2\t2\tA0A5B9.P01850\n+AKPVTQIVSAEAWGR\t31,4\t15\tR\tPAp00039435\t1611,8733\t3\t2\t2\tA0A5B9.P01850\n+VSATFWQNPR\t25,3\t10\tR\tPAp00491254\t1204,5989\t2\t2\t2\tA0A5B9.P01850\n+TFHEPTTILGNSLPK\t31,6\t15\tK\tPAp01531757\t1653,8726\t3\t1\t1\tA0AUZ9\n+CTEIKPEVNTLTAENK\t23,2\t16\tK\tPAp01530703\t1788,8927\t3\t1\t1\tA0AUZ9\n+IVPGHSNVPVSSSAAEK\t19,5\t17\tK\tPAp00161090\t1677,8686\t3\t1\t1\tA0AUZ9\n+MVVLQPLDEYNLGK\t36,3\t14\tK\tPAp01537489\t1617,8436\t2\t1\t1\tA0AUZ9\n+NVEGQDLLLK\t26,6\t10\tK\tPAp01667991\t1127,6186\t2\t1\t1\tA0AUZ9\n+GISFSSLPSTMESDK\t28,9\t15\tK\tPAp01666612\t1584,7341\t2\t1\t1\tA0AUZ9\n+DVQIILDSNITK\t31,7\t12\tK\tPAp01539542\t1357,7453\t2\t1\t1\tA0AUZ9\n+TFGLGLTNVK\t26,6\t10\tK\tPAp01644016\t1048,5917\t2\t1\t1\tA0AUZ9\n+LSPTFYWTPQTLPSK\t36,2\t15\tK\tPAp01644702\t1764,9087\t2\t1\t1\tA0AUZ9\n+HLSETALGER\t16,9\t10\tR\tPAp01645887\t1111,5622\t3\t1\t1\tA0AUZ9\n+SPQEQIILAPSLAK\t31\t14\tK\tPAp01563570\t1493,8453\t2\t1\t1\tA0AV02\n+EGAEGLHCSEHLLLEK\t29,3\t16\tK\tPAp01567618\t1763,8512\t4\t1\t1\tA0AV02\n+SPPSFPVEISDR\t26\t12\tR\tPAp01558558\t1329,6565\t2\t1\t1\tA0AV02\n+ASPGLHLGSASNFSFFR\t38,3\t17\tR\tPAp01560305\t1793,8849\t3\t1\t1\tA0AV02\n+YDFLIAEK\t29,1\t8\tK\tPAp01669272\t997,512\t2\t1\t1\tA0AV02\n+VLEGTLLEFTK\t34,1\t11\tK\tPAp01574156\t1248,6965\t2\t1\t1\tA0AV02\n+VIPALACLGQGK\t27,2\t12\tK\tPAp01644069\t1168,6638\t2\t1\t1\tA0AV02\n+VDMEMTQLTQENADFATR\t32,5\t18\tR\tPAp01650546\t2098,9299\t2\t1\t1\tA0AV02\n+EQLMPHY\t19,9\t7\tY\tPAp01747555\t916,4113\t2\t1\t1\tA0AV02\n+TQMSQVQELFHEAAQQDALAQPQPWWK\t42,9\t27\tK\tPAp02019700\t3194,5243\t3\t1\t1\tA0AV02\n+FILDALAQPQPWWK\t45,9\t14\tK\tPAp01607909\t1711,9086\t2\t0\t1\tA0AV02-2\n+DMSSFIQVK\t24,2\t9\tK\tPAp01604481\t1053,5165\t2\t0\t1\tA0AV02-2\n+NHFNVVNVTCVSYR\t29,8\t14\tR\tPAp00075318\t1650,7937\t3\t0\t1\tA0AV02-2\n+AAAGGLAVGQLPGEGPAGEEGAALGK\t32,2\t26\tK\tPAp01052468\t2247,1494\t2\t0\t1\tA0AV02-3\n+MAGFNMGGDLR\t25,5\t11\tR\tPAp01379365\t1167,5165\t2\t0\t1\tA0AV02-4\n+MCSCSLTPVPEPVLR\t32,6\t15\tR\tPAp01606401\t1630,7881\t2\t0\t1\tA0AV02-5\n+SFGQFNPGCVER\t23,4\t12\tR\tPAp00027695\t1339,5979\t2\t1\t1\tA0AV96\n+VPEGVAGAPNEAALLALMER\t38,7\t20\tR\tPAp00495387\t2007,0459\t2\t1\t1\tA0AV96\n+GSYLGGYSAGR\t18,2\t11\tR\tPAp01645934\t1086,5094\t2\t1\t1\tA0AV96\n+DYAFVHFTSR\t26,2\t10\tR\tPAp01439648\t1241,5829\t3\t1\t1\tA0AV96\n+YGGPPPGWEGPHPQR\t19,1\t15\tR\tPAp00477765\t1630,764\t3\t1\t1\tA0AV96\n+LLGVCCSVDNCR\t19,8\t12\tR\tPAp01445737\t1280,5675\t2\t1\t1\tA0AV96\n+GFAFVEYESHR\t27,2\t11\tR\tPAp00399000\t1340,6149\t3\t3\t3\tA0AV96.Q8TBY0.Q9NQ94\n+VAIPAIGAQYSMFPAAPAPK\t37,4\t20\tK\tPAp00810166\t1999,0601\t2\t0\t1\tA0AV96-2\n+SHYQEAIDIYK\t30,6\t11\tK\tPAp00531563\t1365,6565\t3\t1\t1\tA0AVF1\n+LDPNPEYWEGK\t23,7\t11\tK\tPAp01562620\t1346,6143\t2\t1\t1\tA0AVF1\n+GVVNAALGQEMGSR\t22,2\t14\tR\tPAp01569253\t1387,6878\t2\t1\t1\tA0AVF1\n+DFTGAITLLEFK\t43,8\t12\tK\tPAp01564603\t1353,718\t2\t1\t1\tA0AVF1\n+STGNTQVEYMIR\t22,4\t12\tR\tPAp01650336\t1397,6609\t2\t1\t1\tA0AVF1\n+GGEGALQVLPPLVDVIPEAR\t47,5\t20\tR\tPAp00504051\t2029,1207\t2\t1\t1\tA0AVF1\n+SLLLQELAQK\t34,4\t10\tK\tPAp01572840\t1141,6707\t2\t1\t1\tA0AVI2\n+HQDFLGYLYR\t38,1\t10\tR\tPAp01560275\t1310,6408\t3\t1\t1\tA0AVI2\n+TGAEDHLGITAR\t17,5\t12\tR\tPAp00494375\t1239,6207\t3\t1\t1\tA0AVI2\n+TANVDLVDDNLSR\t25,8\t13\tR\tPAp01558517\t1430,7001\t2\t1\t1\tA0AVI2\n+ELIHFEVSIGHYGNK\t34\t15\tK\tPAp01666094\t1741,8787\t4\t1\t1\tA0AVI2\n+IQTLFLQYPEGEGQK\t33,8\t15\tK\tPAp01667082\t1749,8937\t2\t1\t1\tA0AVI2\n+LLYGTDDTDIQIFK\t35\t14\tK\tPAp01649820\t1640,8297\t2\t1\t1\tA0AVI2\n+IGTTVIDLENR\t26,3\t11\tR\tPAp01646518\t1229,6615\t2\t1\t1\tA0AVI2\n+SQVLEEVYENQGR\t25,1\t13\tR\tPAp01641395\t1549,7372\t2\t1\t1\tA0AVI2\n+LHPGPTNHLSDIFPELPAPGD\t38,3\t21\tD\tPAp01749058\t2223,096\t3\t1\t1\tA0AVI2\n+MIPCGMR\t19\t7\tR\tPAp01603090\t806,3601\t2\t0\t1\tA0AVI2-3\n+MGNNPFFNEVG\t27,4\t11\tG\tPAp01749539\t1224,5233\t1\t0\t1\tA0AVI2-3\n+VIVTDTWVMK\t32,3\t10\tK\tPAp01574135\t1190,6369\t2\t1\t1\tA0AVI4\n+FATGAPGAR\t11,3\t9\tR\tPAp01556990\t846,4348\t2\t1\t1\tA0AVI4\n+VHVAQQQDVHLTVTESR\t23,7\t17\tR\tPAp01574109\t1945,997\t4\t1\t1\tA0AVI4\n+QDPLRPDTWLASR\t27,1\t13\tR\tPAp0157'..b'NVAR\t37,4\t18\tR\tPAp00513003\t2103,0207\t2\t1\t1\tQ9Y6Y0\n+SGLGTAEMNGK\t15,3\t11\tK\tPAp01461081\t1063,4968\t2\t1\t1\tQ9Y6Y0\n+LEVMLEDNVCLPSNGK\t33,5\t16\tK\tPAp01642927\t1759,8484\t2\t1\t1\tQ9Y6Y0\n+LYIVGGSDPYGQK\t23,2\t13\tK\tPAp00747706\t1395,7034\t2\t1\t1\tQ9Y6Y0\n+AVLACCSPYLFEIFNSDSDPHGISHVK\t46,5\t27\tK\tPAp01450117\t2948,3837\t4\t1\t1\tQ9Y6Y0\n+QISSSSTGCLSSPNATVQSPK\t21\t21\tK\tPAp00510363\t2077,995\t2\t1\t1\tQ9Y6Y0\n+NFASCMGDSR\t15,5\t10\tR\tPAp01525485\t1086,4223\t2\t1\t1\tQ9Y6Y0\n+WNTNEEIAAYLITFEK\t42\t16\tK\tPAp01540323\t1940,952\t2\t1\t1\tQ9Y6Y1\n+DLYIGVSTVQVTGNPK\t29,2\t16\tK\tPAp01531502\t1689,8937\t2\t1\t1\tQ9Y6Y1\n+AISIPDSLGR\t22,7\t10\tR\tPAp01534500\t1027,5662\t2\t1\t1\tQ9Y6Y1\n+TRPQNGSMILYNR\t23,6\t13\tR\tPAp01540618\t1548,7831\t3\t1\t1\tQ9Y6Y1\n+TGGYGSHSEVQHNDVSEGK\t11,2\t19\tK\tPAp01668672\t1986,8667\t4\t1\t1\tQ9Y6Y1\n+TEDTSFEQQMAK\t16,4\t12\tK\tPAp01647764\t1413,6082\t2\t1\t1\tQ9Y6Y1\n+EELIGQLKPMFHGIK\t38,2\t15\tK\tPAp01643026\t1738,944\t4\t1\t1\tQ9Y6Y1\n+VENEFAQLTLSDHEQR\t29,1\t16\tR\tPAp00157119\t1914,9071\t3\t1\t1\tQ9Y6Y1\n+VFMVTDYSPEWSYPEGGVK\t39,4\t19\tK\tPAp01537565\t2189,9979\t2\t1\t1\tQ9Y6Y1\n+EVVNTELGSYR\t20,9\t11\tR\tPAp00162611\t1265,6252\t2\t1\t1\tQ9Y6Y1\n+ELEDIQQHPLAM\t27,7\t12\tM\tPAp01747421\t1422,6813\t2\t0\t1\tQ9Y6Y1-2\n+AAYWEEEPAEVR\t25,2\t12\tR\tPAp00146864\t1448,6572\t2\t1\t1\tQ9Y6Y8\n+AHTSSTQLQEELEK\t19,2\t14\tK\tPAp00063415\t1599,774\t3\t1\t1\tQ9Y6Y8\n+LEFPSGETIVMHNPK\t30,5\t15\tK\tPAp00499440\t1697,8447\t3\t1\t1\tQ9Y6Y8\n+IANFVEHK\t17,3\t8\tK\tPAp01458691\t956,5079\t3\t1\t1\tQ9Y6Y8\n+SIIECVDDFR\t28,8\t10\tR\tPAp00495182\t1195,5543\t2\t1\t1\tQ9Y6Y8\n+CPGPLAVANGVVK\t25,3\t13\tK\tPAp00029301\t1223,6696\t2\t1\t1\tQ9Y6Y8\n+VGMLNGGR\t15,4\t8\tR\tPAp01676025\t802,4119\t2\t1\t1\tQ9Y6Y8\n+VGMEINHLHALFMSR\t38,6\t15\tR\tPAp01136511\t1753,8756\t4\t1\t1\tQ9Y6Y8\n+TMNISPEQPQH\t15,8\t11\tH\tPAp00381062\t1280,5819\t2\t1\t1\tQ9Y6Y8\n+GFFNIYHPLDPVAYR\t40,7\t15\tR\tPAp00132532\t1807,9046\t3\t1\t1\tQ9Y6Y8\n+SAWQTLNEFAR\t32,2\t11\tR\tPAp00411790\t1321,6415\t2\t1\t1\tQ9Y6Y8\n+GETVNTTISFSFK\t29\t13\tK\tPAp01531474\t1429,7089\t2\t1\t1\tQ9Y6Y9\n+MQYPISINVNPCIELK\t37,3\t16\tK\tPAp01529729\t1860,9478\t2\t1\t1\tQ9Y6Y9\n+GLLHIFYIPR\t36,8\t10\tR\tPAp01528546\t1227,7128\t3\t1\t1\tQ9Y6Y9\n+GSDDDYSFCR\t14\t10\tR\tPAp01557133\t1163,4189\t2\t1\t1\tQ9Y6Y9\n+QLYFNLYITVNTMNLPK\t45,5\t17\tK\tPAp01572280\t2071,0812\t2\t1\t1\tQ9Y6Y9\n+QYWVCNSSDASISYTYCDK\t32\t19\tK\tPAp01700480\t2231,914\t2\t1\t1\tQ9Y6Y9\n+CVVEAISGSPEEMLFCLEFVILHQPNSN\t52,6\t28\tN\tPAp02019352\t3104,4657\t2\t1\t1\tQ9Y6Y9\n+LLTSDFPYGR\t26,3\t10\tR\tPAp01558625\t1167,5924\t2\t1\t1\tQ9Y6Z2\n+MGTAVGPHHSPAPHDSALPAR\t22,6\t21\tR\tPAp01571354\t2105,0224\t5\t1\t1\tQ9Y6Z2\n+SCQIEQVK\t9,8\t8\tK\tPAp01592150\t933,459\t2\t1\t1\tQ9Y6Z2\n+YSVPDTGLFQHWEGSIPT\t37,5\t18\tT\tPAp01751905\t2032,953\t2\t1\t1\tQ9Y6Z2\n+ECCSIVCMAAK\t22\t11\tK\tPAp01560913\t1156,4749\t2\t1\t1\tQ9Y6Z4\n+GCSPAWGFLPQAR\t35,9\t13\tR\tPAp01560039\t1388,6659\t2\t1\t1\tQ9Y6Z4\n+GGSVSVTWSSVSCCR\t23,9\t15\tR\tPAp01558234\t1513,6653\t2\t1\t1\tQ9Y6Z4\n+APGSPWMVPGDVAMSGHR\t31,2\t18\tR\tPAp01566390\t1850,8556\t3\t1\t1\tQ9Y6Z4\n+NNGVLQGR\t11,8\t8\tR\tPAp00566877\t856,4515\t2\t1\t1\tQ9Y6Z4\n+HQPQMPSAR\t9,5\t9\tR\tPAp01055386\t1050,5029\t3\t1\t1\tQ9Y6Z4\n+HQPEMPSAR\t10,4\t9\tR\tPAp01694524\t1051,4869\t3\t0\t1\tQ9Y6Z4_SNP\n+CHQPVNAAPSSAWQPR\t22,7\t16\tR\tPAp01604145\t1747,8213\t3\t0\t1\tQ9Y6Z4-2\n+MVPGDVAMSGHR\t18,2\t12\tR\tPAp01602925\t1255,5801\t3\t0\t1\tQ9Y6Z4-2\n+DSQSSPGGPGPTVTPSVISLK\t28,3\t21\tK\tPAp01110313\t2010,0269\t2\t0\t1\tQ9Y6Z4-2\n+AGCVLWPVLLTALDPGCAVSTTTK\t51\t24\tK\tPAp01669595\t2415,2541\t2\t0\t1\tQ9Y6Z4-2\n+WAVLGSAGDR\t23\t10\tR\tPAp01558079\t1030,5196\t2\t1\t1\tQ9Y6Z5\n+WVPWAVLGSVR\t38,2\t11\tR\tPAp01560286\t1268,7029\t2\t1\t1\tQ9Y6Z5\n+WAALGPMGGTGSGR\t24,2\t14\tR\tPAp01043947\t1316,6295\t2\t1\t1\tQ9Y6Z5\n+WAAPDPMGGAGFGPDWR\t36,3\t17\tR\tPAp01574536\t1786,7885\t2\t1\t1\tQ9Y6Z5\n+WVVMDLWTGGAGSR\t39,7\t14\tR\tPAp01574665\t1533,7398\t2\t1\t1\tQ9Y6Z5\n+GLLGIPGEK\t23,8\t9\tK\tPAp00899347\t882,5174\t2\t1\t1\tQ9Y6Z7\n+DEAANTLIADYVAK\t31,6\t14\tK\tPAp00976976\t1492,7409\t2\t1\t1\tQ9Y6Z7\n+FYYIVQEEK\t26,2\t9\tK\tPAp00092536\t1217,5968\t2\t1\t1\tQ9Y6Z7\n+GELGDMGDQGNIGK\t19,1\t14\tK\tPAp01560848\t1389,6194\t2\t1\t1\tQ9Y6Z7\n+WNDTECHLTMYFVCEFIK\t48,8\t18\tK\tPAp01651843\t2277,9897\t3\t1\t1\tQ9Y6Z7\n+VFIGVNDLER\t29,2\t10\tR\tPAp00094672\t1160,6189\t2\t1\t1\tQ9Y6Z7\n+LPAGQVPVTLQPQTQVK\t28,7\t17\tK\tPAp01531426\t1803,0254\t2\t1\t1\tQ9YNA8\n+GSELHEIIDK\t21,4\t10\tK\tPAp01538252\t1139,5822\t3\t1\t1\tQ9YNA8\n+VPELVGPSESKPR\t20,4\t13\tR\tPAp01574269\t1393,7565\t3\t1\t1\tQ9YNA8\n+VIVELMAYENPNPECQSAIKPLK\t39,1\t23\tK\tPAp00968484\t2585,3233\t3\t1\t1\tQ9YNA8\n'
b
diff -r 000000000000 -r a2b06836de90 tool-data/proteore_human_srm_atlas.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/proteore_human_srm_atlas.loc.sample Fri Jul 12 07:49:45 2019 -0400
b
@@ -0,0 +1,2 @@
+#<id> <release> <name> <value>
+9979839599 2016-04 Human SRM atlas (2016-04) tool-data/Human_SRM_atlas_2016-04.csv
b
diff -r 000000000000 -r a2b06836de90 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Fri Jul 12 07:49:45 2019 -0400
b
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Location of ID Mapping files for id_converter-->
+    <table name="proteore_human_srm_atlas" comment_char="#">
+      <columns>id, release, name, value</columns>
+      <file path="tool-data/proteore_human_srm_atlas.loc" />
+    </table>
+</tables>
\ No newline at end of file
b
diff -r 000000000000 -r a2b06836de90 tool_data_table_conf.xml.test
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.test Fri Jul 12 07:49:45 2019 -0400
b
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Location of ID Mapping files for id_converter-->
+    <table name="proteore_human_srm_atlas" comment_char="#">
+      <columns>id, release, name, value</columns>
+      <file path="${__HERE__}/test-data/proteore_human_srm_atlas.loc" />
+    </table>
+</tables>
\ No newline at end of file