| Previous changeset 17:2952bae8a1ea (2020-01-24) |
|
Commit message:
"planemo upload commit 7afd4b3ee25f024257ccbac6e51076d25b2a04e7" |
|
modified:
add_protein_features.R add_protein_features.xml proteore_nextprot_ref.loc.sample tool-data/nextprot_ref_07-05-2019.tsv tool-data/nextprot_ref_08-10-2018.tsv |
|
added:
tool-data/nextprot_ref_31-07-2020.tsv |
| b |
| diff -r 2952bae8a1ea -r 0a9ae3d7dbf2 add_protein_features.R --- a/add_protein_features.R Fri Jan 24 05:04:15 2020 -0500 +++ b/add_protein_features.R Thu Aug 20 03:09:52 2020 -0400 |
| [ |
| @@ -48,9 +48,7 @@ --column: the column number which you would like to apply... --header: true/false if your file contains a header --type: the type of input IDs (Uniprot_AC/EntrezID) - --pc_features: IsoPoint,SeqLength,MW - --localization: Chr,SubcellLocations - --diseases_info: Diseases + --pc_features: IsoPoint,SeqLength,MW,Chr,SubcellLocations,Diseases,protein_name,function,post_trans_mod,protein_family,pathway --output: text output filename \n") q(save="no") @@ -122,14 +120,9 @@ # Get information from neXtProt get_nextprot_info <- function(nextprot,input,pc_features,localization,diseases_info){ - if(diseases_info){ - cols = c("NextprotID",pc_features,localization,"Diseases") - } else { - cols = c("NextprotID",pc_features,localization) - } - + cols = c("NextprotID",pc_features) cols=cols[cols!="None"] - info = nextprot[match(input,nextprot$NextprotID),cols] + info = nextprot[match(input,nextprot$NextprotID),intersect(colnames(nextprot),cols)] return(info) } @@ -172,8 +165,6 @@ # Parse arguments id_type = args$type pc_features = strsplit(args$pc_features, ",")[[1]] - localization = strsplit(args$localization, ",")[[1]] - diseases_info = str2bool(args$diseases_info) output = args$output # Change the sample ids if they are Uniprot_AC ids to be able to match them with @@ -191,7 +182,7 @@ if (all(!NextprotID %in% nextprot[,1])){ write.table("None of the input ids can be found in Nextprot",file=output,sep="\t",quote=FALSE,col.names=TRUE,row.names=FALSE) } else { - res <- get_nextprot_info(nextprot,NextprotID,pc_features,localization,diseases_info) + res <- get_nextprot_info(nextprot,NextprotID,pc_features) res = res[!duplicated(res$NextprotID),] output_content = merge(file, res,by.x=ncol,by.y="NextprotID",incomparables = NA,all.x=T) output_content = order_columns(output_content,ncol,id_type,file) |
| b |
| diff -r 2952bae8a1ea -r 0a9ae3d7dbf2 add_protein_features.xml --- a/add_protein_features.xml Fri Jan 24 05:04:15 2020 -0500 +++ b/add_protein_features.xml Thu Aug 20 03:09:52 2020 -0400 |
| [ |
| @@ -1,4 +1,4 @@ -<tool id="prot_features" name="Add protein features" version="2020.01.23"> +<tool id="prot_features" name="Add protein features" version="2020.08.17"> <description>[neXtProt, Human] </description> <requirements> @@ -19,9 +19,7 @@ #end if --type='$idtype' - --pc_features='$Nextprot_params.pc_features' - --localization='$Nextprot_params.localization' - --diseases_info='$Nextprot_params.diseases_info' + --pc_features='$pc_features' --output='$output' #if 'proteore_nextprot_ref' in str($ref_file).split("/") @@ -63,32 +61,31 @@ </when> </conditional> - <param name="idtype" type="select" label="Type of IDs" multiple="false" optional="false"> - <option value="NextprotID" selected="true">neXtProt IDs</option> - <option value="Uniprot_AC" selected="false">UniProt accession number</option> - </param> - <section name="Nextprot_params" title="Select features (Physico-chemical, localization, disease infiormation)" expanded="True"> - <param name="pc_features" type="select" label="Select information to add to your list" multiple="true" help="" display="checkboxes" optional="false"> - <option value="SeqLength" selected="false">Sequence Length</option> - <option value="MW" selected="false">Molecular Weight</option> - <option value="IsoPoint" selected="false">Isoelectric point</option> - <option value="TMDomains" selected="false">Number of transmembrane domains</option> - <option value="ProteinExistence" selected="false">Protein Existence (evidence score from 1 to 5)</option> - </param> + <param name="idtype" type="select" label="Type of IDs" multiple="false" optional="false"> + <option value="NextprotID" selected="true">neXtProt IDs</option> + <option value="Uniprot_AC" selected="false">UniProt accession number</option> + </param> + <param name="pc_features" type="select" label="Features/Annotation" multiple="true" help="" display="checkboxes" optional="false"> + <option value="ProteinName" selected="false">Protein name</option> + <option value="SeqLength" selected="false">Sequence Length</option> + <option value="MW" selected="false">Molecular Weight</option> + <option value="IsoPoint" selected="false">Isoelectric point</option> + <option value="TMDomains" selected="false">Number of transmembrane domains</option> + <option value="SubcellLocations" selected="false">Subcellular Location</option> + <option value="Diseases" selected="false">Disease information</option> + <option value="Function" selected="false">Protein function</option> + <option value="PostTranslationalModifications" selected="false">Post translational modifications</option> + <option value="ProteinFamily" selected="false">Protein family</option> + <option value="Pathway" selected="false">Pathway(s)</option> + <option value="ProteinExistence" selected="false">Protein Existence (evidence score from 1 to 5)</option> + <option value="Chr" selected="false">Chromosome</option> + </param> - <param name="localization" type="select" label="Localization" multiple="true" help="" display="checkboxes" optional="true"> - <option value="Chr" selected="false">Chromosome</option> - <option value="SubcellLocations" selected="false">Subcellular Location</option> - </param> - - <param name="diseases_info" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Disease information" /> - - </section> - <param name="ref_file" type="select" label="Release of neXtProt reference file to use"> + <param name="ref_file" type="select" label="Release of neXtProt reference file to use"> <options from_data_table="proteore_nextprot_ref"> <filter type="sort_by" column="0"/> </options> - </param> + </param> </inputs> @@ -110,12 +107,7 @@ </conditional> <param name="idtype" value="Uniprot_AC"/> - - <section name="Nextprot_params"> - <param name="pc_features" value="SeqLength,MW,IsoPoint,TMDomains,ProteinExistence"/> - <param name="localization" value="Chr,SubcellLocations"/> - <param name="diseases_info" value="true"/> - </section> + <param name="pc_features" value="SeqLength,MW,IsoPoint,TMDomains,ProteinExistence"/> <param name="ref_file" value="test-data/cached_locally/nextprot_ref_07-05-2019.tsv"/> <output name="output" file="Add_information_from_neXtProt.tsv"/> @@ -126,7 +118,7 @@ **Description** -This tool retrieves annotation (protein features) from the neXtProt database (knowledgebase on human proteins) to enrich your protein IDs list. +This tool retrieves annotation (protein features) from the neXtProt database (knowledgebase on human proteins) to enrich and better inform your protein IDs list. ----- @@ -148,7 +140,11 @@ **Output** -Output is a tabular file containing both original columns and new columns including the annotation requested. +Output is a tabular file containing both original columns and new columns including the annotation requested. Only features/annotations assigned with a "GOLD" quality criterion are considered, otherwise a "NA" value is returned. + +.. class:: warningmark + +"Protein name","Protein function","Post translational modifications","Protein family","Pathway(s)" options will not work will releases older than 08/2020. ----- @@ -158,16 +154,21 @@ neXtProt releases : -- nextProt release 07-05-2019 (release Feb 13, 2019) -- neXtProt release 08-10-2018 (release Feb 21, 2018) +- nextProt release 31-07-2020 (release Feb, 2020) +- nextProt release 07-05-2019 (release Feb, 2019) +- neXtProt release 08-10-2018 (release Feb, 2018) +.. class:: warningmark + +For "Protein function", "Post translational modifications" and "Pathway(s)", only results with gold quality are returned. + ----- .. class:: infomark **Authors** -David Christiany, Lisa Peru, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR +David Christiany, Lisa Perus, T.P. Lien Nguyen, 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 |
| b |
| diff -r 2952bae8a1ea -r 0a9ae3d7dbf2 proteore_nextprot_ref.loc.sample --- a/proteore_nextprot_ref.loc.sample Fri Jan 24 05:04:15 2020 -0500 +++ b/proteore_nextprot_ref.loc.sample Thu Aug 20 03:09:52 2020 -0400 |
| b |
| @@ -1,3 +1,4 @@ #<id> <release> <name> <value> 9979818992 nextprot_ref_08-10-2018 neXtProt release 08-10-2018 tool-data/nextprot_ref_08-10-2018.tsv 9979809493 nextprot_ref_07-05-2019 neXtProt release 07-05-2019 tool-data/nextprot_ref_07-05-2019.tsv +9979799269 nextprot_ref_31-07-2020 neXtProt release 31-07-2020 tool-data/nextprot_ref_31-07-2020.tsv |
| b |
| diff -r 2952bae8a1ea -r 0a9ae3d7dbf2 tool-data/nextprot_ref_07-05-2019.tsv --- a/tool-data/nextprot_ref_07-05-2019.tsv Fri Jan 24 05:04:15 2020 -0500 +++ b/tool-data/nextprot_ref_07-05-2019.tsv Thu Aug 20 03:09:52 2020 -0400 |
| b |
| b'@@ -1,20400 +1,20400 @@\n-NextprotID\tMW\tSeqLength\tIsoPoint\tChr\tSubcellLocations\tDiseases\tTMDomains\tProteinExistence\r\n-NX_A0A024RBG1\t20434\t181\t5.99\t1\tCytoplasm\tNA\t0\tPE1\r\n-NX_A0A075B6H9\t12773\t119\t6.01\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6I0\t12814\t122\t4.33\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6I1\t12987\t120\t5.8\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6I4\t12395\t117\t7.85\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6I9\t12468\t117\t6.69\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6J1\t13277\t123\t4.75\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6J6\t12549\t115\t3.95\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6J9\t12412\t118\t4.66\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6K0\t12466\t115\t4.58\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6K2\t12387\t115\t5.34\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6K4\t12441\t115\t4.72\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6K5\t12332\t115\t6.81\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6K6\t13330\t122\t5.39\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6N1\t12769\t114\t6.53\t7\tCell membrane\tNA\t0\tPE1\r\n-NX_A0A075B6N2\t12175\t111\t8.52\t7\tCell membrane\tNA\t0\tPE1\r\n-NX_A0A075B6N3\t12929\t115\t7.68\t7\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6N4\t12983\t114\t5.91\t7\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6P5\t12957\t120\t5.61\t2\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6Q5\t12891\t118\t7.69\t14\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6R2\t12848\t117\t9.64\t14\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6S2\t13143\t120\t6.53\t2\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6S4\t12835\t117\t9.22\t2\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6S5\t12712\t117\t8.5\t2\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A075B6S6\t13215\t120\t7.79\t2\tCell membrane;Secreted\tNA\t0\tPE3\r\n-NX_A0A075B6T6\t12838\t113\t6.17\t14\tCell membrane\tNA\t0\tPE1\r\n-NX_A0A075B6T7\t15362\t132\t9.2\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6T8\t12354\t112\t4.83\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6U4\t12598\t112\t8.39\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6V5\t12697\t113\t6.57\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6W5\t13545\t121\t8.45\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6X5\t12414\t111\t5.26\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A075B6Y3\t2097\t20\t11\t14\tCell membrane\tNA\t0\tPE4\r\n-NX_A0A075B706\t1761\t16\t8.26\t14\tCell membrane\tNA\t0\tPE1\r\n-NX_A0A075B759\t18197\t164\t9.43\t1\tCytoplasm\tNA\t0\tPE3\r\n-NX_A0A075B767\t18208\t164\t9.19\t1\tCytoplasm\tNA\t0\tPE3\r\n-NX_A0A087WSX0\t13162\t123\t6.69\t22\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A087WSY4\t13025\t118\t9.7\t3\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A087WSY6\t12534\t115\t5.14\t2\tCell membrane;Secreted\tNA\t0\tPE3\r\n-NX_A0A087WSZ0\t12837\t117\t7.62\t2\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A087WSZ9\t12582\t112\t8.58\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A087WT01\t12043\t109\t5.7\t14\tCell membrane\tNA\t0\tPE1\r\n-NX_A0A087WT02\t12289\t112\t5.26\t14\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A087WT03\t12306\t109\t7.76\t14\tCell membrane\tNA\t0\tPE1\r\n-NX_A0A087WTH1\t11832\t108\t7.61\t16\tMembrane\tNA\t2\tPE2\r\n-NX_A0A087WTH5\t15028\t132\t8.73\t21\tMembrane\tNA\t1\tPE3\r\n-NX_A0A087WUL8\t440408\t3843\t4.53\t1\tCytoplasm\tNA\t0\tPE5\r\n-NX_A0A087WV62\t12845\t115\t6.7\t7\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A087WVF3\t62187\t549\t9.2\t17\tCell membrane\tNA\t0\tPE2\r\n-NX_A0A087WW87\t13310\t121\t4.43\t2\tCell membrane;Secreted\tNA\t0\tPE1\r\n-NX_A0A087WX78\t41674\t387\t8.87\t18\tNucleus\tNA\t0\tPE5\r\n-NX_A0A087WXM9\t40829\t373\t8.65\t5\tKinetochore;Centromere\tNA\t0\tPE1\r\n-NX_A0A087WXS9\t62205\t549\t9.2\t17\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A087X0M5\t13028\t115\t9.14\t7\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A087X179\t62131\t549\t9.18\t17\tCell membrane\tNA\t0\tPE2\r\n-NX_A0A087X1C5\t57489\t515\t8.7\t22\tMitochondrion;Cytoplasm;Membrane\tNA\t2\tPE5\r\n-NX_A0A087X1G2\t62171\t549\t9.23\t17\tCell membrane\tNA\t0\tPE3\r\n-NX_A0A096LNP1\t8156\t70\t8.26\t11\tSecreted\tNA\t0\tPE2\r\n-NX_A0A096LP01\t10908\t95\t6.24\t20\tNucleoplasm;Cytosol;Membrane\tNA\t1\tPE1\r\n-NX_A0A096LP49\t114856\t1063\t9.76\t9\tNA\tNA\t0\tPE1\r\n-NX_A0A096LP55\t10752\t91\t4.39\t1\tMitochondrion inner membrane\tNA\t0\tPE3\r\n-NX_A0A096LPI5\t11989\t108\t8.8\t6\tNA\tNA\t0\tPE4\r\n-NX_A0A0A0MRZ7\t13297\t120\t4.9\t2\tCell membrane;Secreted\tNA\t0\tPE3\r\n-NX_A0A0A0MRZ8\t12625\t115\t5.15\t2\tCell membrane;Secreted\tNA\t0\tPE3\r\n-NX_A0A0A0MRZ9\t13446\t124\t7.76\t22\tCe'..b'9961\t9.18\t0\tMitochondrion\tNA\tPE1\t15\n+NX_Q9Y6N6\t1575\t171227\t6.14\t0\tBasement membrane\tCortical malformations occipital\tPE1\t9\n+NX_Q9Y6N7\t1651\t180930\t5.7\t1\tAxon;Endoplasmic reticulum-Golgi intermediate compartment membrane;Cell membrane\tNA\tPE1\t3\n+NX_Q9Y6N8\t788\t88451\t4.83\t1\tCell membrane\tNA\tPE1\t5\n+NX_Q9Y6N9\t552\t62211\t5.36\t0\tCytosol;Microvillus;Cytoskeleton\tDeafness, autosomal recessive, 18A;Usher syndrome 1C\tPE1\t11\n+NX_Q9Y6P5\t492\t56557\t5.68\t0\tCytoplasm;Nucleolus;Nucleus\tNA\tPE1\t6\n+NX_Q9Y6Q1\t641\t74576\t6.62\t0\tCytosol;Perinuclear region;Spindle\tNA\tPE1\tX\n+NX_Q9Y6Q2\t735\t83141\t5.82\t0\tCytoplasm;Membrane\tNA\tPE1\t2\n+NX_Q9Y6Q3\t630\t71209\t9.26\t0\tCytoplasmic vesicle;Nucleus\tNA\tPE1\t9\n+NX_Q9Y6Q5\t423\t48108\t8.23\t0\tCytoplasmic vesicle;Clathrin-coated vesicle membrane;Golgi apparatus\tNA\tPE1\t19\n+NX_Q9Y6Q6\t616\t66034\t5.21\t1\tCytosol;Cell membrane\tPaget disease of bone 2, early-onset;Osteopetrosis, autosomal recessive 7;Familial expansile osteolysis\tPE1\t18\n+NX_Q9Y6Q9\t1424\t155293\t7.16\t0\tCytosol;Nucleoplasm;Nucleus;Cytoplasm\tNA\tPE1\t20\n+NX_Q9Y6R0\t609\t64891\t9.1\t0\tCytoplasm\tNA\tPE1\t19\n+NX_Q9Y6R1\t1079\t121461\t6.35\t12\tBasolateral cell membrane\tRenal tubular acidosis, proximal, with ocular abnormalities and mental retardation\tPE1\t4\n+NX_Q9Y6R4\t1608\t181685\t5.94\t0\tCytosol;Perinuclear region\tNA\tPE1\t6\n+NX_Q9Y6R6\t833\t96807\t9.17\t0\tNucleus\tNA\tPE1\t19\n+NX_Q9Y6R7\t5405\t572017\t5.14\t0\tCytoskeleton;Golgi apparatus;Cell membrane;Secreted\tNA\tPE1\t19\n+NX_Q9Y6R9\t512\t57368\t10.27\t0\tNucleus\tNA\tPE1\t19\n+NX_Q9Y6S9\t549\t60036\t7.06\t0\tNucleoplasm\tNA\tPE1\t14\n+NX_Q9Y6T7\t804\t90595\t8.11\t0\tCytoplasm\tNA\tPE1\t7\n+NX_Q9Y6U3\t715\t80489\t5.5\t0\tCytoskeleton;Podosome;Cell membrane\tNA\tPE1\t7\n+NX_Q9Y6U7\t377\t41101\t8.98\t2\tCytoskeleton;Nucleolus;Membrane\tNA\tPE2\t22\n+NX_Q9Y6V0\t5142\t560699\t6.07\t0\tNucleus speckle;Synapse;Cell membrane\tPontocerebellar hypoplasia 3\tPE1\t7\n+NX_Q9Y6V7\t483\t54226\t9.21\t0\tMitochondrion;Nucleolus\tNA\tPE1\t19\n+NX_Q9Y6W3\t813\t92652\t7.55\t0\tNucleus\tNA\tPE1\t3\n+NX_Q9Y6W5\t498\t54284\t5.38\t0\tCytosol;Cytoplasm;Cytoskeleton;Cell membrane;Lamellipodium\tNA\tPE1\t1\n+NX_Q9Y6W6\t482\t52642\t7.87\t0\tCytosol;Nucleoplasm;Nucleus;Golgi apparatus;Cytoplasm\tNA\tPE1\t1\n+NX_Q9Y6W8\t199\t22625\t9.01\t1\tCell membrane;Secreted\tImmunodeficiency, common variable, 1\tPE1\t2\n+NX_Q9Y6X0\t1596\t175008\t9.76\t0\tCytosol;Nucleus\tSchinzel-Giedion midface retraction syndrome;Leukemia, acute myelogenous;Leukemia, juvenile myelomonocytic;Myelodysplastic syndrome;Mental retardation, autosomal dominant 29;Leukemia, chronic myeloid, atypical\tPE1\t18\n+NX_Q9Y6X1\t66\t7374\t11.01\t1\tEndoplasmic reticulum membrane;Endoplasmic reticulum;Cell membrane;Membrane\tNA\tPE1\t3\n+NX_Q9Y6X2\t628\t68017\t7.81\t0\tNucleoplasm;Nucleus speckle;Nucleus;Cytoplasm\tNA\tPE1\t1\n+NX_Q9Y6X3\t613\t69082\t6.84\t0\tNucleoplasm;Nucleus;Chromosome\tNA\tPE1\t19\n+NX_Q9Y6X4\t670\t74955\t4.52\t0\tCytosol;Nucleus inner membrane;Nucleus envelope;Nucleus membrane\tNA\tPE1\t5\n+NX_Q9Y6X5\t453\t51641\t5.71\t1\tCell membrane\tNA\tPE1\t6\n+NX_Q9Y6X6\t1858\t206129\t6.37\t0\tCytoplasmic vesicle;Cytoplasm\tNA\tPE1\t13\n+NX_Q9Y6X8\t837\t92307\t6.42\t0\tNucleoplasm;Nucleus\tNA\tPE1\t8\n+NX_Q9Y6X9\t1032\t117823\t8.6\t0\tCytosol;Nucleus\tCharcot-Marie-Tooth disease 2Z\tPE1\t22\n+NX_Q9Y6Y0\t642\t71729\t5.33\t0\tNucleoplasm;Cytoplasm;Cytoskeleton;Cytosol\tNA\tPE1\t1\n+NX_Q9Y6Y1\t1673\t183672\t7.29\t0\tCytosol;Cytoplasm;Nucleolus;Nucleus\tCerebellar ataxia, non-progressive, with mental retardation\tPE1\t1\n+NX_Q9Y6Y8\t1000\t111076\t5.35\t0\tCytoplasmic vesicle;COPII-coated vesicle membrane;Endoplasmic reticulum\tNA\tPE1\t10\n+NX_Q9Y6Y9\t160\t18546\t8.8\t0\tCytoplasmic vesicle;Extracellular space;Secreted\tNA\tPE1\t8\n+NX_Q9Y6Z2\t57\t6189\t5.98\t0\tNA\tNA\tPE4\t6\n+NX_Q9Y6Z4\t181\t19411\t9.48\t0\tNA\tNA\tPE5\t6\n+NX_Q9Y6Z5\t254\t26128\t11.81\t0\tNA\tNA\tPE5\t6\n+NX_Q9Y6Z7\t277\t30705\t6.96\t0\tCytoplasm;Golgi apparatus;Secreted\t3MC syndrome 3\tPE1\t8\n+NX_Q9YNA8\t666\t74183\t9.05\t0\tCell membrane\tNA\tPE1\t19\n+NX_S4R3P1\t24\t2751\t5.87\t0\tCytoplasm;Secreted\tNA\tPE3\t4\n+NX_S4R3Y5\t24\t2737\t7.98\t0\tCytoplasm;Secreted\tNA\tPE2\t1\n+NX_U3KPV4\t340\t38754\t9.39\t1\tGolgi stack membrane\tNA\tPE2\t1\n+NX_W5XKT8\t324\t36333\t6.15\t1\tMembrane\tNA\tPE1\t19\n+NX_W6CW81\t113\t12732\t5.57\t0\tNA\tNA\tPE1\t1\n' |
| b |
| diff -r 2952bae8a1ea -r 0a9ae3d7dbf2 tool-data/nextprot_ref_08-10-2018.tsv --- a/tool-data/nextprot_ref_08-10-2018.tsv Fri Jan 24 05:04:15 2020 -0500 +++ b/tool-data/nextprot_ref_08-10-2018.tsv Thu Aug 20 03:09:52 2020 -0400 |
| b |
| b'@@ -1,20231 +1,20231 @@\n-NextprotID\tMW\tSeqLength\tIsoPoint\tChr\tSubcellLocations\tDiseases\tTMDomains\tProteinExistence\n-NX_Q7RTS7\t57865\t529\t7.59\t12\tNA\tEctodermal dysplasia 7, hair/nail type;Woolly hair autosomal dominant;Hypotrichosis 3\t0\tPE1\n-NX_Q7RTS9\t75935\t669\t5.56\t18\tGolgi apparatus;Cytoplasm;Golgi apparatus;Membrane\tSmith-McCort dysplasia 1;Dyggve-Melchior-Clausen syndrome\t0\tPE1\n-NX_Q7RTT3\t21553\t188\t9.19\tX\tNA\tNA\t0\tPE2\n-NX_Q7RTT4\t21859\t187\t9.46\tX\tNA\tNA\t0\tPE2\n-NX_Q7RTT5\t21591\t188\t9.19\tX\tNA\tNA\t0\tPE2\n-NX_Q7RTT6\t21688\t188\t9.32\tX\tNA\tNA\t0\tPE5\n-NX_Q7RTT9\t58059\t530\t7.64\t7\tCytoskeleton;Cytoskeleton;Apical cell membrane;Cell membrane\tNA\t10\tPE1\n-NX_Q7RTU0\t17516\t167\t10.24\t8\tNucleus\tNA\t0\tPE3\n-NX_Q7RTU1\t23309\t214\t11.33\t2\tNucleus\tNA\t0\tPE2\n-NX_Q7RTU3\t29358\t272\t9.54\t6\tNucleus\tNA\t0\tPE1\n-NX_Q7RTU4\t24132\t235\t11.21\t17\tNucleus;Cytoplasm\tCamptosynpolydactyly, complex;Syndactyly, mesoaxial synostotic, with phalangeal reduction;Split-hand/foot malformation with long bone deficiency 3\t0\tPE1\n-NX_Q7RTU5\t29462\t278\t8.71\t1\tNucleus\tNA\t0\tPE3\n-NX_Q7RTU7\t21596\t201\t10.17\t8\tNucleus\tNA\t0\tPE3\n-NX_Q7RTU9\t192967\t1775\t5.27\t15\tKinocilium;Stereocilium;Cell surface\tDeafness, autosomal recessive, 16;Deafness-infertility syndrome\t0\tPE2\n-NX_Q7RTV0\t12405\t110\t8.79\t22\tNucleoplasm;Nucleus;Nucleus speckle\tNA\t0\tPE1\n-NX_Q7RTV2\t25722\t222\t7.74\t6\tCytoplasm\tNA\t0\tPE1\n-NX_Q7RTV3\t38411\t350\t8.07\t9\tNucleus;Nucleoplasm\tNA\t0\tPE1\n-NX_Q7RTV5\t24857\t226\t9.07\t9\tNA\tNA\t0\tPE1\n-NX_Q7RTW8\t128533\t1153\t5.53\t16\tExtracellular matrix;Apical cell membrane\tDeafness, autosomal recessive, 22\t0\tPE1\n-NX_Q7RTX0\t93386\t852\t6.75\t1\tCell membrane\tNA\t7\tPE1\n-NX_Q7RTX1\t93074\t841\t8.32\t1\tCell membrane\tNA\t7\tPE2\n-NX_Q7RTX7\t54092\t472\t5.15\t1\tFlagellum membrane\tNA\t6\tPE1\n-NX_Q7RTX9\t56254\t510\t6.45\t2\tCytosol;Cell membrane\tNA\t12\tPE2\n-NX_Q7RTY0\t44992\t426\t6.44\t17\tGolgi apparatus;Golgi apparatus membrane;Cell membrane\tDiabetes mellitus, non-insulin-dependent\t12\tPE1\n-NX_Q7RTY1\t55794\t509\t8.25\t10\tCell membrane;Cell junction;Nucleus\tNA\t12\tPE1\n-NX_Q7RTY3\t29329\t260\t8.42\t3\tNA\tNA\t0\tPE2\n-NX_Q7RTY5\t35970\t328\t7.49\t4\tSecreted\tNA\t0\tPE2\n-NX_Q7RTY7\t125066\t1134\t8.67\t12\tSecreted\tNA\t0\tPE1\n-NX_Q7RTY8\t94415\t843\t8.84\t3\tCell membrane\tNA\t1\tPE2\n-NX_Q7RTY9\t35078\t318\t9.36\t16\tCell membrane\tNA\t0\tPE1\n-NX_Q7RTZ1\t62642\t564\t7.22\t11\tSecreted\tNA\t0\tPE1\n-NX_Q7RTZ2\t59590\t530\t7.81\t8\tEndoplasmic reticulum;Nucleus\tNA\t0\tPE3\n-NX_Q7Z2D5\t82983\t763\t9\t1\tMembrane\tNA\t6\tPE1\n-NX_Q7Z2E3\t40740\t356\t9.27\t9\tCytoplasm;Nucleolus;Nucleus;Nucleoplasm;Nucleolus\tAtaxia-oculomotor apraxia syndrome\t0\tPE1\n-NX_Q7Z2F6\t14454\t126\t4.9\t16\tNucleoplasm;Cytosol\tNA\t0\tPE2\n-NX_Q7Z2G1\t19618\t175\t10.69\tX\tNucleus membrane;Chromosome\tNA\t0\tPE1\n-NX_Q7Z2H8\t53076\t476\t6.54\t5\tEndoplasmic reticulum;Cell membrane;Lysosome membrane\tNA\t11\tPE1\n-NX_Q7Z2K6\t100231\t904\t7.2\t9\tNucleus;Nucleolus;Endoplasmic reticulum membrane\tNA\t9\tPE1\n-NX_Q7Z2K8\t102399\t1008\t8.33\t5\tCell membrane;Cytoplasmic vesicle;Cell membrane;Growth cone\tNA\t0\tPE1\n-NX_Q7Z2Q7\t70301\t622\t9.02\t5\tMembrane\tNA\t1\tPE2\n-NX_Q7Z2R9\t10995\t100\t12.15\t1\tSecreted\tNA\t0\tPE5\n-NX_Q7Z2T5\t81747\t733\t8.11\t1\tNucleolus;Nucleus\tNA\t0\tPE1\n-NX_Q7Z2V1\t23111\t217\t6.41\t16\tNA\tNA\t0\tPE1\n-NX_Q7Z2W4\t101431\t902\t8.72\t7\tCytosol;Nucleus;Golgi apparatus;Cytoplasm\tNA\t0\tPE1\n-NX_Q7Z2W7\t127685\t1104\t6.91\t2\tCell membrane;Membrane raft;Endoplasmic reticulum membrane\tNA\t6\tPE1\n-NX_Q7Z2W9\t22815\t205\t9.91\t11\tNucleoplasm;Mitochondrion;Mitochondrion\tNA\t0\tPE1\n-NX_Q7Z2X4\t28272\t250\t6.53\t2\tEndoplasmic reticulum;Cytoplasm\tNA\t0\tPE1\n-NX_Q7Z2X7\t12090\t111\t4\tX\tNA\tNA\t0\tPE1\n-NX_Q7Z2Y5\t178479\t1582\t5.93\tX\tCytoplasm;Cytosol;Nucleoplasm\tNA\t0\tPE1\n-NX_Q7Z2Y8\t279048\t2422\t6.12\t11\tCytosol;Nucleus\tNA\t0\tPE2\n-NX_Q7Z2Z1\t210857\t1910\t9\t15\tNucleus;Nucleoplasm\tNA\t0\tPE1\n-NX_Q7Z2Z2\t125430\t1120\t5.66\t15\tCytosol\tNA\t0\tPE1\n-NX_Q7Z304\t77556\t686\t5.05\t9\tEndoplasmic reticulum;Extracellular matrix\tNA\t0\tPE1\n-NX_Q7Z309\t26928\t247\t5.98\tX\tNucleus;Nucleoplasm\tNA\t0\tPE1\n-NX_Q7Z333\t302880\t2677\t6.83\t9\tCytoskeleton;Nucleus;Nucleolus;Nucleus;Nucleoplasm;Cytoplasm;Chromosome;Telomere;Axon;Growth cone\tSpinocerebellar ataxia, autosomal recessive, 1;Amyotrophic lateral scleros'..b'3\t318\t36596\t8.13\t2\tCytoskeleton;Membrane;Cytosol;Nucleoplasm;Perinuclear region;Endoplasmic reticulum\tNA\tPE1\t16\n+NX_Q7L5N1\t327\t36163\t5.47\t0\tNucleus;Nucleoplasm;Nucleus;Cytoplasm\tNA\tPE1\t7\n+NX_Q7L5N7\t544\t60208\t6.14\t1\tLipid droplet;Golgi apparatus membrane;Endoplasmic reticulum membrane;Lipid droplet;Endoplasmic reticulum\tNA\tPE1\t16\n+NX_Q7L5Y1\t443\t49786\t6.03\t0\tMitochondrion\tNA\tPE1\t18\n+NX_Q7L5Y6\t550\t63848\t7.32\t0\tNucleoplasm;Cytoskeleton;Nucleus\tNA\tPE1\t15\n+NX_Q7L5Y9\t396\t45287\t8.95\t0\tNucleoplasm;Nucleus matrix;Cell membrane;Cytoskeleton\tNA\tPE1\t4\n+NX_Q7L622\t706\t80504\t7.9\t0\tCytoplasm;Nucleolus\tNA\tPE1\t14\n+NX_Q7L775\t607\t70370\t5.77\t0\tEndoplasmic reticulum\tNA\tPE1\t3\n+NX_Q7L7L0\t130\t14121\t11.05\t0\tNucleus;Chromosome\tNA\tPE1\t1\n+NX_Q7L7V1\t743\t84419\t4.88\t0\tNucleus;Mitochondrion\tNA\tPE1\t10\n+NX_Q7L7X3\t1001\t116070\t7.3\t0\tCytoplasm\tNA\tPE1\t17\n+NX_Q7L804\t512\t58279\t9.33\t0\tCytoplasmic vesicle;Nucleoplasm;Cell membrane;Recycling endosome membrane\tNA\tPE1\t10\n+NX_Q7L8A9\t365\t40957\t9.5\t0\tSecreted\tNA\tPE1\t14\n+NX_Q7L8C5\t426\t46885\t7.6\t1\tGolgi apparatus;Cytoplasmic vesicle;Membrane\tNA\tPE1\t11\n+NX_Q7L8J4\t393\t43499\t5.57\t0\tGolgi apparatus;Cytoplasmic vesicle;Nucleoplasm\tNA\tPE1\t1\n+NX_Q7L8L6\t764\t86574\t8.41\t0\tMitochondrion nucleoid\tNA\tPE1\t20\n+NX_Q7L8S5\t288\t33300\t6.29\t0\tNA\tNA\tPE1\tX\n+NX_Q7L8W6\t267\t30307\t5.24\t0\tNucleus;Nucleolus\tNA\tPE1\t15\n+NX_Q7L945\t461\t52853\t9.18\t0\tNucleolus;Nucleus;Nucleus\tNA\tPE1\t19\n+NX_Q7L985\t606\t68066\t8.44\t1\tMembrane\tNA\tPE1\t9\n+NX_Q7L9B9\t569\t62403\t8.64\t0\tNucleus speckle;Cytoplasmic vesicle;Cell membrane\tNA\tPE1\t7\n+NX_Q7L9L4\t216\t25091\t6.24\t0\tCytoplasm;Nucleus\tNA\tPE1\t4\n+NX_Q7LBC6\t1761\t191581\t6.78\t0\tNucleus;Nucleoplasm\tNA\tPE1\t5\n+NX_Q7LBE3\t791\t86988\t8.47\t13\tMembrane;Nucleus;Cell junction\tNA\tPE1\t1\n+NX_Q7LBR1\t199\t22109\t7.81\t0\tNucleus;Late endosome membrane;Midbody;Cytosol;Endosome\tNA\tPE1\t18\n+NX_Q7LC44\t396\t45316\t5.45\t0\tCytoskeleton;Synapse;Cytoplasmic vesicle;Cytoskeleton;Endosome;Acrosome;Postsynaptic density;Dendrite;Dendritic spine\tNA\tPE1\t8\n+NX_Q7LDG7\t609\t69248\t7.89\t0\tSynaptosome;Ruffle membrane;Cell membrane;Cytosol\tBleeding disorder, platelet-type 18\tPE1\t11\n+NX_Q7LDI9\t666\t74079\t9.11\t0\tCell membrane\tNA\tPE1\t7\n+NX_Q7LFL8\t322\t32977\t9.27\t0\tCytosol;Nucleoplasm;Nucleus;Cytoplasm\tNA\tPE1\t5\n+NX_Q7LFX5\t561\t64926\t8.56\t1\tCentrosome;Cytosol;Golgi apparatus membrane\tNA\tPE1\t10\n+NX_Q7LG56\t351\t40737\t4.89\t0\tNucleus;Nucleoplasm;Cytoplasm;Cytosol\tProgressive external ophthalmoplegia with mitochondrial DNA deletions, autosomal dominant, 5;Mitochondrial DNA depletion syndrome 8A;Mitochondrial DNA depletion syndrome 8B\tPE1\t8\n+NX_Q7LGA3\t356\t41881\t8.83\t1\tMitochondrion;Golgi apparatus membrane\tNA\tPE1\t1\n+NX_Q7LGC8\t479\t54706\t8.84\t1\tCytosol;Golgi apparatus;Golgi apparatus membrane\tSpondyloepiphyseal dysplasia with congenital joint dislocations\tPE1\t10\n+NX_Q7M4L6\t423\t46768\t6.01\t0\tNucleus\tNA\tPE1\t15\n+NX_Q7RTM1\t612\t67353\t8.71\t10\tExtracellular space;Membrane\tNA\tPE2\t4\n+NX_Q7RTN6\t431\t48369\t6.02\t0\tCytosol;Nucleoplasm;Cytoplasm;Nucleus\tNA\tPE1\t17\n+NX_Q7RTP0\t329\t34562\t8.7\t9\tCell membrane;Early endosome\tSpastic paraplegia 6, autosomal dominant\tPE1\t15\n+NX_Q7RTP6\t2002\t224295\t5.43\t0\tCytosol;Cytoplasm;Cell membrane;Nucleoplasm;Cell cortex;Cilium basal body;Spindle;Midbody;Nucleus;Cytoskeleton\tNA\tPE1\t22\n+NX_Q7RTR0\t991\t113312\t6.08\t0\tCytoplasm;Inflammasome\tNA\tPE1\t19\n+NX_Q7RTR2\t1065\t114658\t8.64\t0\tCytosol;Microtubule organizing center;Cytoplasm\tNA\tPE1\t16\n+NX_Q7RTR8\t314\t36195\t9.64\t7\tMembrane;Focal adhesion;Nucleoplasm;Cytoskeleton\tNA\tPE2\t12\n+NX_Q7RTS1\t189\t20818\t11.26\t0\tNucleoplasm;Nucleus;Golgi apparatus\tNA\tPE1\t7\n+NX_Q7RTS3\t328\t34970\t5.1\t0\tNucleus;Nucleoplasm;Cytoplasm\tPancreatic agenesis 2;Pancreatic and cerebellar agenesis\tPE1\t10\n+NX_Q7RTS5\t596\t66296\t8.96\t12\tMembrane\tNA\tPE1\t17\n+NX_Q7RTS6\t562\t62236\t7.04\t10\tMembrane\tNA\tPE1\t17\n+NX_Q8WZ42\t34350\t3816030\t6.02\t0\tCytoplasm;Nucleus Early-onset myopathy with fatal cardiomyopathy;Cardiomyopathy, familial hypertrophic 9;Cardiomyopathy, dilated 1G;Tardive tibial muscular dystrophy;Hereditary myopathy with early respiratory failure;Limb-girdle muscular dystrophy\t2J\tPE1\t2\n' |
| b |
| diff -r 2952bae8a1ea -r 0a9ae3d7dbf2 tool-data/nextprot_ref_31-07-2020.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/nextprot_ref_31-07-2020.tsv Thu Aug 20 03:09:52 2020 -0400 |
| [ |
| b'@@ -0,0 +1,20338 @@\n+NextprotID\tProteinName\tSeqLength\tMW\tIsoPoint\tTMDomains\tSubcellLocations\tDiseases\tFunction\tPostTranslationalModifications\tProteinFamily\tPathway\tProteinExistence\tChr\n+NX_A0A024RBG1\tDiphosphoinositol polyphosphate phosphohydrolase NUDT4B\t181\t20434\t5.99\t0\tCytoplasm\tNA\tCleaves a beta-phosphate from the diphosphate groups in PP-InsP5 (diphosphoinositol pentakisphosphate), PP-InsP4 and [PP]2-InsP4 (bisdiphosphoinositol tetrakisphosphate), suggesting that it may play a role in signal transduction. Also able to catalyze the hydrolysis of dinucleoside oligophosphate Ap6A, but not Ap5A. The major reaction products are ADP and p4a from Ap6A. Also able to hydrolyze 5-phosphoribose 1-diphosphate. Does not play a role in U8 snoRNA decapping activity. Binds U8 snoRNA.\tNA\tBelongs to the Nudix hydrolase family. DIPP subfamily.\tNA\tPE1\t1\n+NX_A0A075B6H9\tImmunoglobulin lambda variable 4-69\t119\t12773\t6.01\t0\tSecreted;Cell membrane\tNA\tV region of the variable domain of immunoglobulin light chains that participates in the antigen recognition (PubMed:24600447). Immunoglobulins, also known as antibodies, are membrane-bound or secreted glycoproteins produced by B lymphocytes. In the recognition phase of humoral immunity, the membrane-bound immunoglobulins serve as receptors which, upon binding of a specific antigen, trigger the clonal expansion and differentiation of B lymphocytes into immunoglobulins-secreting plasma cells. Secreted immunoglobulins mediate the effector phase of humoral immunity, which results in the elimination of bound antigens (PubMed:20176268, PubMed:22158414). The antigen binding site is formed by the variable domain of one heavy chain, together with that of its associated light chain. Thus, each immunoglobulin has two antigen binding sites with remarkable affinity for a particular antigen. The variable domains are assembled by a process called V-(D)-J rearrangement and can then be subjected to somatic hypermutations which, after exposure to antigen and selection, allow affinity maturation for a particular antigen (PubMed:17576170, PubMed:20176268).\tNA\tNA\tNA\tPE1\t22\n+NX_A0A075B6I0\tImmunoglobulin lambda variable 8-61\t122\t12814\t4.33\t0\tSecreted;Cell membrane\tNA\tV region of the variable domain of immunoglobulin light chains that participates in the antigen recognition (PubMed:24600447). Immunoglobulins, also known as antibodies, are membrane-bound or secreted glycoproteins produced by B lymphocytes. In the recognition phase of humoral immunity, the membrane-bound immunoglobulins serve as receptors which, upon binding of a specific antigen, trigger the clonal expansion and differentiation of B lymphocytes into immunoglobulins-secreting plasma cells. Secreted immunoglobulins mediate the effector phase of humoral immunity, which results in the elimination of bound antigens (PubMed:20176268, PubMed:22158414). The antigen binding site is formed by the variable domain of one heavy chain, together with that of its associated light chain. Thus, each immunoglobulin has two antigen binding sites with remarkable affinity for a particular antigen. The variable domains are assembled by a process called V-(D)-J rearrangement and can then be subjected to somatic hypermutations which, after exposure to antigen and selection, allow affinity maturation for a particular antigen (PubMed:17576170, PubMed:20176268).\tNA\tNA\tNA\tPE1\t22\n+NX_A0A075B6I1\tImmunoglobulin lambda variable 4-60\t120\t12987\t5.8\t0\tSecreted;Cell membrane\tNA\tV region of the variable domain of immunoglobulin light chains that participates in the antigen recognition (PubMed:24600447). Immunoglobulins, also known as antibodies, are membrane-bound or secreted glycoproteins produced by B lymphocytes. In the recognition phase of humoral immunity, the membrane-bound immunoglobulins serve as receptors which, upon binding of a specific antigen, trigger the clonal expansion and differentiation of B lymphocytes into immunoglobulins-secreting plasma cells. Secreted immunoglobulins medi'..b'otor molecules with ATPase activity. Unconventional myosins serve in intracellular movements. Their highly divergent tails are presumed to bind to membranous compartments, which would be moved relative to actin filaments. May be involved in targeting of the catalytic subunit of protein phosphatase 1 during brain development. Activates PI3K and concomitantly recruits the WAVE1 complex to the close vicinity of PI3K and regulates neuronal morphogenesis (By similarity).\tPhosphorylated on tyrosine residues by FYN upon stimulation with CNTN5.\tIn the N-terminal section; belongs to the TRAFAC class myosin-kinesin ATPase superfamily. Myosin family.;In the C-terminal section; belongs to the NYAP family.\tNA\tPE1\t13\n+NX_Q9Y6X8\tZinc fingers and homeoboxes protein 2\t837\t92307\t6.42\t0\tNucleoplasm;Nucleus\tNA\tActs as a transcriptional repressor (PubMed:12741956). Represses the promoter activity of the CDC25C gene stimulated by NFYA (PubMed:12741956). May play a role in retinal development where it regulates the composition of bipolar cell populations, by promoting differentiation of bipolar OFF-type cells (By similarity). In the brain, may promote maintenance and suppress differentiation of neural progenitor cells in the developing cortex (By similarity).\tNA\tBelongs to the ZHX family.\tNA\tPE1\t8\n+NX_Q9Y6X9\tATPase MORC2\t1032\t117823\t8.6\t0\tNucleus matrix;Chromosome;Nucleoplasm;Cytosol;Nucleus\tCharcot-Marie-Tooth disease 2Z\tEssential for epigenetic silencing by the HUSH (human silencing hub) complex. Recruited by HUSH to target site in heterochromatin, the ATPase activity and homodimerization are critical for HUSH-mediated silencing (PubMed:28581500, PubMed:29440755). Represses germ cell-related genes and L1 retrotransposons in collaboration with SETDB1 and the HUSH complex, the silencing is dependent of repressive epigenetic modifications, such as H3K9me3 mark. Silencing events often occur within introns of transcriptionally active genes, and lead to the down-regulation of host gene expression (PubMed:29211708). During DNA damage response, regulates chromatin remodeling through ATP hydrolysis. Upon DNA damage, is phosphorylated by PAK1, both colocalize to chromatin and induce H2AFX expression. ATPase activity is required and dependent of phosphorylation by PAK1 and presence of DNA (PubMed:23260667). Recruits histone deacetylases, such as HDAC4, to promoter regions, causing local histone H3 deacetylation and transcriptional repression of genes such as CA9 (PubMed:20225202, PubMed:20110259). Exhibits a cytosolic function in lipogenesis, adipogenic differentiation, and lipid homeostasis by increasing the activity of ACLY, possibly preventing its dephosphorylation (PubMed:24286864).\tPhosphorylated by PAK1 at Ser-739 upon DNA damage. Phosphorylation is required for ATPase activity and recruitment to damaged chromatin.\tNA\tFatty acyl-CoA biosynthesis\tPE1\t22\n+NX_Q9Y6Y0\tInfluenza virus NS1A-binding protein\t642\t71729\t5.33\t0\tNucleoplasm;Cytosol;Cytoplasm;Cytoskeleton\tNA\tInvolved in many cell functions, including pre-mRNA splicing, the aryl hydrocarbon receptor (AHR) pathway, F-actin organization and protein ubiquitination. Plays a role in the dynamic organization of the actin skeleton as a stabilizer of actin filaments by association with F-actin through Kelch repeats (By similarity). Protects cells from cell death induced by actin destabilization (By similarity). Functions as modifier of the AHR/Aryl hydrocarbon receptor pathway increasing the concentration of AHR available to activate transcription (PubMed:16582008). In addition, functions as a negative regulator of BCR(KLHL20) E3 ubiquitin ligase complex to prevent ubiquitin-mediated proteolysis of PML and DAPK1, two tumor suppressors (PubMed:25619834). Inhibits pre-mRNA splicing (in vitro) (PubMed:9696811).;(Microbial infection) Involved in the alternative splicing of influenza A virus M1 mRNA through interaction with HNRNPK, thereby facilitating the generation of viral M2 protein.\tNA\tNA\tInfluenza A\tPE1\t1\n' |