autoimmune

Read in data

autoimmune <- fread(
  input = "data_raw/2019_05_29_ICD/ICD10.autoimmune.txt",
  header = TRUE,
  stringsAsFactors = F,
  data.table = F)

colnames(autoimmune)
##    [1] "IID"    "D590m"  "D590s"  "IID"    "D591m"  "D591s"  "IID"   
##    [8] "D613m"  "IID"    "D686m"  "D686s"  "IID"    "D690m"  "D690s" 
##   [15] "IID"    "D693m"  "D693s"  "IID"    "D70m"   "D70s"   "IID"   
##   [22] "D721m"  "D721s"  "IID"    "D730s"  "IID"    "D731m"  "D731s" 
##   [29] "IID"    "D732m"  "D732s"  "IID"    "D760m"  "D760s"  "IID"   
##   [36] "D761m"  "D761s"  "IID"    "D860m"  "D860s"  "IID"    "D861m" 
##   [43] "D861s"  "IID"    "D862m"  "D862s"  "IID"    "D863m"  "D863s" 
##   [50] "IID"    "D868m"  "D868s"  "IID"    "D869m"  "D869s"  "IID"   
##   [57] "D890m"  "D890s"  "IID"    "D891m"  "D891s"  "IID"    "D892m" 
##   [64] "D892s"  "IID"    "E05s"   "IID"    "E050m"  "E050s"  "IID"   
##   [71] "E063m"  "E063s"  "IID"    "E100m"  "E100s"  "IID"    "E101m" 
##   [78] "E101s"  "IID"    "E102m"  "E102s"  "IID"    "E103m"  "E103s" 
##   [85] "IID"    "E104m"  "E104s"  "IID"    "E105m"  "E105s"  "IID"   
##   [92] "E106m"  "E106s"  "IID"    "E107m"  "E107s"  "IID"    "E108m" 
##   [99] "E108s"  "IID"    "E109m"  "E109s"  "IID"    "E121s"  "IID"   
##  [106] "E128s"  "IID"    "E129s"  "IID"    "E208s"  "IID"    "E271m" 
##  [113] "E271s"  "IID"    "E283m"  "E283s"  "IID"    "E310m"  "E310s" 
##  [120] "IID"    "E318m"  "IID"    "E319s"  "IID"    "E351s"  "IID"   
##  [127] "G122m"  "G122s"  "IID"    "G35m"   "G35s"   "IID"    "G360m" 
##  [134] "G360s"  "IID"    "G368s"  "IID"    "G369m"  "G369s"  "IID"   
##  [141] "G370s"  "IID"    "G373m"  "G373s"  "IID"    "G378m"  "G378s" 
##  [148] "IID"    "G379m"  "G379s"  "IID"    "G610m"  "G610s"  "IID"   
##  [155] "G618m"  "G618s"  "IID"    "G619m"  "G619s"  "IID"    "G700m" 
##  [162] "G700s"  "IID"    "G724m"  "G724s"  "IID"    "G731m"  "G731s" 
##  [169] "IID"    "H150m"  "H150s"  "IID"    "H151m"  "H151s"  "IID"   
##  [176] "H201m"  "H201s"  "IID"    "H208m"  "H208s"  "IID"    "H209m" 
##  [183] "H209s"  "IID"    "H353m"  "H353s"  "IID"    "I241m"  "I241s" 
##  [190] "IID"    "I730m"  "I730s"  "IID"    "I731m"  "I731s"  "IID"   
##  [197] "I881m"  "I881s"  "IID"    "K220m"  "K220s"  "IID"    "K294m" 
##  [204] "K294s"  "IID"    "K500m"  "K500s"  "IID"    "K501m"  "K501s" 
##  [211] "IID"    "K508m"  "K508s"  "IID"    "K509m"  "K509s"  "IID"   
##  [218] "K510m"  "K510s"  "IID"    "K511m"  "K511s"  "IID"    "K512m" 
##  [225] "K512s"  "IID"    "K513m"  "K513s"  "IID"    "K514m"  "K514s" 
##  [232] "IID"    "K515m"  "K515s"  "IID"    "K518m"  "K518s"  "IID"   
##  [239] "K519m"  "K519s"  "IID"    "K580m"  "K580s"  "IID"    "K589m" 
##  [246] "K589s"  "IID"    "K721m"  "K721s"  "IID"    "K754m"  "K754s" 
##  [253] "IID"    "K900m"  "K900s"  "IID"    "L100m"  "L100s"  "IID"   
##  [260] "L102m"  "L102s"  "IID"    "L104s"  "IID"    "L108m"  "L108s" 
##  [267] "IID"    "L109m"  "L109s"  "IID"    "L110m"  "L110s"  "IID"   
##  [274] "L111m"  "L111s"  "IID"    "L118m"  "IID"    "L119m"  "L119s" 
##  [281] "IID"    "L120m"  "L120s"  "IID"    "L121m"  "L121s"  "IID"   
##  [288] "L123s"  "IID"    "L128m"  "L128s"  "IID"    "L129m"  "L129s" 
##  [295] "IID"    "L130m"  "L130s"  "IID"    "L131m"  "L131s"  "IID"   
##  [302] "L138m"  "L138s"  "IID"    "L139m"  "L139s"  "IID"    "L14s"  
##  [309] "IID"    "L400m"  "L400s"  "IID"    "L401m"  "L401s"  "IID"   
##  [316] "L403m"  "L403s"  "IID"    "L404m"  "L404s"  "IID"    "L405m" 
##  [323] "L405s"  "IID"    "L408m"  "L408s"  "IID"    "L409m"  "L409s" 
##  [330] "IID"    "L410m"  "L410s"  "IID"    "L430m"  "L430s"  "IID"   
##  [337] "L432m"  "IID"    "L433s"  "IID"    "L438m"  "L438s"  "IID"   
##  [344] "L439m"  "L439s"  "IID"    "L441m"  "L441s"  "IID"    "L443m" 
##  [351] "L443s"  "IID"    "L508m"  "L508s"  "IID"    "L630m"  "L630s" 
##  [358] "IID"    "L631s"  "IID"    "L638m"  "L638s"  "IID"    "L639m" 
##  [365] "L639s"  "IID"    "L80m"   "L80s"   "IID"    "L930m"  "L930s" 
##  [372] "IID"    "L931m"  "L931s"  "IID"    "L932m"  "L932s"  "IID"   
##  [379] "L940m"  "L940s"  "IID"    "L941s"  "IID"    "M023m"  "M023s" 
##  [386] "IID"    "M0230m" "M0230s" "IID"    "M0236m" "IID"    "M0239m"
##  [393] "M0239s" "IID"    "M050m"  "M050s"  "IID"    "M0500m" "M0500s"
##  [400] "IID"    "M0509m" "M0509s" "IID"    "M051m"  "M051s"  "IID"   
##  [407] "M0510m" "M0510s" "IID"    "M0518s" "IID"    "M0519m" "M0519s"
##  [414] "IID"    "M052m"  "M052s"  "IID"    "M0520m" "M0520s" "IID"   
##  [421] "M0524s" "IID"    "M0526m" "IID"    "M0528m" "M0528s" "IID"   
##  [428] "M0529m" "M0529s" "IID"    "M053m"  "M053s"  "IID"    "M0530m"
##  [435] "M0530s" "IID"    "M0538s" "IID"    "M0539s" "IID"    "M058m" 
##  [442] "M058s"  "IID"    "M0580m" "M0580s" "IID"    "M0582m" "IID"   
##  [449] "M0583m" "IID"    "M0584m" "M0584s" "IID"    "M0586m" "IID"   
##  [456] "M0587m" "IID"    "M0588m" "IID"    "M0589m" "M0589s" "IID"   
##  [463] "M059m"  "M059s"  "IID"    "M0590m" "M0590s" "IID"    "M0591m"
##  [470] "M0591s" "IID"    "M0592m" "M0592s" "IID"    "M0593m" "M0593s"
##  [477] "IID"    "M0594m" "M0594s" "IID"    "M0595m" "M0595s" "IID"   
##  [484] "M0596m" "M0596s" "IID"    "M0597m" "M0597s" "IID"    "M0598m"
##  [491] "M0598s" "IID"    "M0599m" "M0599s" "IID"    "M060m"  "M060s" 
##  [498] "IID"    "M0600m" "M0600s" "IID"    "M0601m" "M0601s" "IID"   
##  [505] "M0602m" "M0602s" "IID"    "M0603m" "M0603s" "IID"    "M0604m"
##  [512] "M0604s" "IID"    "M0605m" "M0605s" "IID"    "M0606m" "M0606s"
##  [519] "IID"    "M0607m" "M0607s" "IID"    "M0608m" "IID"    "M0609m"
##  [526] "M0609s" "IID"    "M061m"  "M061s"  "IID"    "M0610m" "M0610s"
##  [533] "IID"    "M0611m" "IID"    "M0616m" "IID"    "M0619m" "M0619s"
##  [540] "IID"    "M062m"  "M062s"  "IID"    "M0621m" "IID"    "M0622m"
##  [547] "IID"    "M0625m" "IID"    "M0627m" "IID"    "M063m"  "M063s" 
##  [554] "IID"    "M0630m" "M0630s" "IID"    "M0632m" "M0632s" "IID"   
##  [561] "M0633m" "M0633s" "IID"    "M0634m" "M0634s" "IID"    "M0636m"
##  [568] "M0636s" "IID"    "M0637m" "M0637s" "IID"    "M0638m" "IID"   
##  [575] "M0639m" "IID"    "M064m"  "M064s"  "IID"    "M0640m" "M0640s"
##  [582] "IID"    "M0641m" "M0641s" "IID"    "M0643m" "M0643s" "IID"   
##  [589] "M0644m" "IID"    "M0645m" "M0645s" "IID"    "M0646m" "M0646s"
##  [596] "IID"    "M0647m" "M0647s" "IID"    "M0649m" "M0649s" "IID"   
##  [603] "M068m"  "M068s"  "IID"    "M0680m" "M0680s" "IID"    "M0681m"
##  [610] "IID"    "M0682m" "M0682s" "IID"    "M0684s" "IID"    "M0685m"
##  [617] "IID"    "M0686m" "IID"    "M0687m" "IID"    "M0688m" "IID"   
##  [624] "M0689m" "M0689s" "IID"    "M069m"  "M069s"  "IID"    "M0690m"
##  [631] "M0690s" "IID"    "M0691m" "M0691s" "IID"    "M0692m" "M0692s"
##  [638] "IID"    "M0693m" "M0693s" "IID"    "M0694m" "M0694s" "IID"   
##  [645] "M0695m" "M0695s" "IID"    "M0696m" "M0696s" "IID"    "M0697m"
##  [652] "M0697s" "IID"    "M0698m" "M0698s" "IID"    "M0699m" "M0699s"
##  [659] "IID"    "M070s"  "IID"    "M0700s" "IID"    "M0701s" "IID"   
##  [666] "M0703s" "IID"    "M0704s" "IID"    "M0707s" "IID"    "M0709s"
##  [673] "IID"    "M071s"  "IID"    "M0719s" "IID"    "M072s"  "IID"   
##  [680] "M0726s" "IID"    "M0728s" "IID"    "M0729s" "IID"    "M073m" 
##  [687] "M073s"  "IID"    "M0730m" "M0730s" "IID"    "M0731s" "IID"   
##  [694] "M0732s" "IID"    "M0733s" "IID"    "M0734m" "M0734s" "IID"   
##  [701] "M0735m" "M0735s" "IID"    "M0736m" "M0736s" "IID"    "M0737m"
##  [708] "M0737s" "IID"    "M0738s" "IID"    "M0739m" "M0739s" "IID"   
##  [715] "M074s"  "IID"    "M0740s" "IID"    "M0746s" "IID"    "M0747s"
##  [722] "IID"    "M0749s" "IID"    "M075s"  "IID"    "M0750m" "M0750s"
##  [729] "IID"    "M0751m" "IID"    "M0755s" "IID"    "M0759s" "IID"   
##  [736] "M076m"  "M076s"  "IID"    "M0760s" "IID"    "M0764s" "IID"   
##  [743] "M0766m" "IID"    "M0769s" "IID"    "M080m"  "M080s"  "IID"   
##  [750] "M0800m" "M0800s" "IID"    "M0802m" "IID"    "M0805m" "IID"   
##  [757] "M0806m" "IID"    "M0808m" "IID"    "M0809m" "M0809s" "IID"   
##  [764] "M0810m" "M0810s" "IID"    "M0819m" "M0819s" "IID"    "M082m" 
##  [771] "M082s"  "IID"    "M0820s" "IID"    "M0822m" "IID"    "M0825s"
##  [778] "IID"    "M0826s" "IID"    "M0828s" "IID"    "M0829m" "M0829s"
##  [785] "IID"    "M0830m" "M0830s" "IID"    "M0836m" "IID"    "M0839s"
##  [792] "IID"    "M0840m" "M0840s" "IID"    "M0844s" "IID"    "M088s" 
##  [799] "IID"    "M089m"  "M089s"  "IID"    "M0890m" "M0890s" "IID"   
##  [806] "M0896m" "IID"    "M0899m" "M0899s" "IID"    "M300m"  "M300s" 
##  [813] "IID"    "M301m"  "M301s"  "IID"    "M302m"  "IID"    "M303m" 
##  [820] "M303s"  "IID"    "M308m"  "M308s"  "IID"    "M320m"  "M320s" 
##  [827] "IID"    "M321m"  "M321s"  "IID"    "M328m"  "M328s"  "IID"   
##  [834] "M329m"  "M329s"  "IID"    "M3290m" "M3290s" "IID"    "M330s" 
##  [841] "IID"    "M331m"  "M331s"  "IID"    "M332m"  "M332s"  "IID"   
##  [848] "M339m"  "M339s"  "IID"    "M340m"  "M340s"  "IID"    "M341m" 
##  [855] "M341s"  "IID"    "M342m"  "M342s"  "IID"    "M348m"  "M348s" 
##  [862] "IID"    "M349m"  "M349s"  "IID"    "M350m"  "M350s"  "IID"   
##  [869] "M351m"  "M351s"  "IID"    "M352m"  "M352s"  "IID"    "M353m" 
##  [876] "M353s"  "IID"    "M354m"  "M354s"  "IID"    "M355s"  "IID"   
##  [883] "M357m"  "M357s"  "IID"    "M358m"  "M358s"  "IID"    "M359m" 
##  [890] "M359s"  "IID"    "M3599s" "IID"    "M45m"   "M45s"   "IID"   
##  [897] "M45X0m" "M45X0s" "IID"    "M45X1s" "IID"    "M45X2m" "M45X2s"
##  [904] "IID"    "M45X4s" "IID"    "M45X6m" "M45X6s" "IID"    "M45X7m"
##  [911] "M45X7s" "IID"    "M45X8s" "IID"    "M45X9m" "M45X9s" "IID"   
##  [918] "M600m"  "M600s"  "IID"    "M6000m" "M6000s" "IID"    "M6001m"
##  [925] "M6001s" "IID"    "M6002m" "IID"    "M6003m" "IID"    "M6005m"
##  [932] "M6005s" "IID"    "M6006m" "M6006s" "IID"    "M6008m" "M6008s"
##  [939] "IID"    "M6009m" "IID"    "M601s"  "IID"    "M6018s" "IID"   
##  [946] "M602m"  "M602s"  "IID"    "M6021s" "IID"    "M6023m" "M6023s"
##  [953] "IID"    "M6024m" "M6024s" "IID"    "M6025m" "IID"    "M6026s"
##  [960] "IID"    "M6027m" "IID"    "M6028m" "M6028s" "IID"    "M6029s"
##  [967] "IID"    "M608m"  "M608s"  "IID"    "M6080m" "IID"    "M6082m"
##  [974] "IID"    "M6085m" "IID"    "M6086s" "IID"    "M6088m" "IID"   
##  [981] "M6089m" "M6089s" "IID"    "M609m"  "M609s"  "IID"    "M6090m"
##  [988] "M6090s" "IID"    "M6091m" "M6091s" "IID"    "M6092m" "M6092s"
##  [995] "IID"    "M6093m" "IID"    "M6095m" "M6095s" "IID"    "M6096m"
## [1002] "M6096s" "IID"    "M6097m" "IID"    "M6098m" "M6098s" "IID"   
## [1009] "M6099m" "M6099s" "IID"    "N030m"  "N030s"  "IID"    "N031m" 
## [1016] "N031s"  "IID"    "N032m"  "N032s"  "IID"    "N033m"  "N033s" 
## [1023] "IID"    "N035m"  "N035s"  "IID"    "N036m"  "N036s"  "IID"   
## [1030] "N037m"  "N037s"  "IID"    "N038m"  "N038s"  "IID"    "N039m" 
## [1037] "N039s"  "IID"    "N050m"  "N050s"  "IID"    "N051m"  "N051s" 
## [1044] "IID"    "N052m"  "N052s"  "IID"    "N053m"  "N053s"  "IID"   
## [1051] "N054m"  "N054s"  "IID"    "N055m"  "N055s"  "IID"    "N056m" 
## [1058] "N056s"  "IID"    "N057m"  "N057s"  "IID"    "N058m"  "N058s" 
## [1065] "IID"    "N059m"  "N059s"  "IID"    "N301m"  "N301s"  "IID"   
## [1072] "N711m"  "N711s"  "IID"    "O264s"

Remove duplicate column

autoimmune_no_duplicate <- autoimmune[!duplicated(as.list(autoimmune))]

colnames(autoimmune_no_duplicate)
##   [1] "IID"    "D590m"  "D590s"  "D591m"  "D591s"  "D613m"  "D686m" 
##   [8] "D686s"  "D690m"  "D690s"  "D693m"  "D693s"  "D70m"   "D70s"  
##  [15] "D721m"  "D721s"  "D730s"  "D731m"  "D731s"  "D732m"  "D732s" 
##  [22] "D760m"  "D760s"  "D761m"  "D761s"  "D860m"  "D860s"  "D861m" 
##  [29] "D861s"  "D862m"  "D862s"  "D863m"  "D863s"  "D868m"  "D868s" 
##  [36] "D869m"  "D869s"  "D890m"  "D890s"  "D891m"  "D891s"  "D892m" 
##  [43] "D892s"  "E05s"   "E050m"  "E050s"  "E063m"  "E063s"  "E100m" 
##  [50] "E100s"  "E101m"  "E101s"  "E102m"  "E102s"  "E103m"  "E103s" 
##  [57] "E104m"  "E104s"  "E105m"  "E105s"  "E106m"  "E106s"  "E107m" 
##  [64] "E107s"  "E108m"  "E108s"  "E109m"  "E109s"  "E121s"  "E128s" 
##  [71] "E129s"  "E208s"  "E271m"  "E271s"  "E283m"  "E283s"  "E310m" 
##  [78] "E310s"  "E318m"  "E319s"  "E351s"  "G122m"  "G122s"  "G35m"  
##  [85] "G35s"   "G360m"  "G360s"  "G368s"  "G369m"  "G369s"  "G370s" 
##  [92] "G373m"  "G373s"  "G378m"  "G378s"  "G379m"  "G379s"  "G610m" 
##  [99] "G610s"  "G618m"  "G618s"  "G619m"  "G619s"  "G700m"  "G700s" 
## [106] "G724m"  "G724s"  "G731m"  "G731s"  "H150m"  "H150s"  "H151m" 
## [113] "H151s"  "H201m"  "H201s"  "H208m"  "H208s"  "H209m"  "H209s" 
## [120] "H353m"  "H353s"  "I241m"  "I241s"  "I730m"  "I730s"  "I731m" 
## [127] "I731s"  "I881m"  "I881s"  "K220m"  "K220s"  "K294m"  "K294s" 
## [134] "K500m"  "K500s"  "K501m"  "K501s"  "K508m"  "K508s"  "K509m" 
## [141] "K509s"  "K510m"  "K510s"  "K511m"  "K511s"  "K512m"  "K512s" 
## [148] "K513m"  "K513s"  "K514m"  "K514s"  "K515m"  "K515s"  "K518m" 
## [155] "K518s"  "K519m"  "K519s"  "K580m"  "K580s"  "K589m"  "K589s" 
## [162] "K721m"  "K721s"  "K754m"  "K754s"  "K900m"  "K900s"  "L100m" 
## [169] "L100s"  "L102m"  "L102s"  "L104s"  "L108m"  "L108s"  "L109m" 
## [176] "L109s"  "L110m"  "L110s"  "L111m"  "L111s"  "L118m"  "L119m" 
## [183] "L119s"  "L120m"  "L120s"  "L121m"  "L121s"  "L123s"  "L128m" 
## [190] "L128s"  "L129m"  "L129s"  "L130m"  "L130s"  "L131m"  "L131s" 
## [197] "L138m"  "L138s"  "L139m"  "L139s"  "L14s"   "L400m"  "L400s" 
## [204] "L401m"  "L401s"  "L403m"  "L403s"  "L404m"  "L404s"  "L405m" 
## [211] "L405s"  "L408m"  "L408s"  "L409m"  "L409s"  "L410m"  "L410s" 
## [218] "L430m"  "L430s"  "L432m"  "L433s"  "L438m"  "L438s"  "L439m" 
## [225] "L439s"  "L441m"  "L441s"  "L443m"  "L443s"  "L508m"  "L508s" 
## [232] "L630m"  "L630s"  "L631s"  "L638m"  "L638s"  "L639m"  "L639s" 
## [239] "L80m"   "L80s"   "L930m"  "L930s"  "L931m"  "L931s"  "L932m" 
## [246] "L932s"  "L940m"  "L940s"  "L941s"  "M023m"  "M023s"  "M0230m"
## [253] "M0230s" "M0236m" "M0239m" "M0239s" "M050m"  "M050s"  "M0500m"
## [260] "M0500s" "M0509m" "M0509s" "M051m"  "M051s"  "M0510m" "M0510s"
## [267] "M0518s" "M0519m" "M0519s" "M052m"  "M052s"  "M0520m" "M0520s"
## [274] "M0524s" "M0526m" "M0528m" "M0528s" "M0529m" "M0529s" "M053m" 
## [281] "M053s"  "M0538s" "M0539s" "M058m"  "M058s"  "M0580m" "M0580s"
## [288] "M0582m" "M0583m" "M0584m" "M0584s" "M0586m" "M0587m" "M0588m"
## [295] "M0589m" "M0589s" "M059m"  "M059s"  "M0590m" "M0590s" "M0591m"
## [302] "M0591s" "M0592m" "M0592s" "M0593m" "M0593s" "M0594m" "M0594s"
## [309] "M0595m" "M0595s" "M0596m" "M0596s" "M0597m" "M0597s" "M0598m"
## [316] "M0598s" "M0599m" "M0599s" "M060m"  "M060s"  "M0600m" "M0600s"
## [323] "M0601m" "M0601s" "M0602m" "M0602s" "M0603m" "M0603s" "M0604m"
## [330] "M0604s" "M0605m" "M0605s" "M0606m" "M0606s" "M0607m" "M0607s"
## [337] "M0608m" "M0609m" "M0609s" "M061m"  "M061s"  "M0610m" "M0610s"
## [344] "M0611m" "M0616m" "M0619m" "M0619s" "M062m"  "M062s"  "M0621m"
## [351] "M0622m" "M0625m" "M0627m" "M063m"  "M063s"  "M0630m" "M0630s"
## [358] "M0632m" "M0632s" "M0633m" "M0633s" "M0634m" "M0634s" "M0636m"
## [365] "M0636s" "M0637m" "M0637s" "M0638m" "M0639m" "M064m"  "M064s" 
## [372] "M0640m" "M0640s" "M0641m" "M0641s" "M0643m" "M0643s" "M0644m"
## [379] "M0645m" "M0645s" "M0646m" "M0646s" "M0647m" "M0649m" "M0649s"
## [386] "M068m"  "M068s"  "M0680m" "M0680s" "M0681m" "M0682m" "M0682s"
## [393] "M0684s" "M0685m" "M0686m" "M0687m" "M0688m" "M0689m" "M0689s"
## [400] "M069m"  "M069s"  "M0690m" "M0690s" "M0691m" "M0691s" "M0692m"
## [407] "M0692s" "M0693m" "M0693s" "M0694m" "M0694s" "M0695m" "M0695s"
## [414] "M0696m" "M0696s" "M0697m" "M0697s" "M0698m" "M0698s" "M0699m"
## [421] "M0699s" "M070s"  "M0700s" "M0701s" "M0703s" "M0704s" "M0707s"
## [428] "M0709s" "M071s"  "M0719s" "M072s"  "M0726s" "M0728s" "M0729s"
## [435] "M073m"  "M073s"  "M0730m" "M0730s" "M0731s" "M0732s" "M0733s"
## [442] "M0734m" "M0734s" "M0735m" "M0735s" "M0736m" "M0736s" "M0737m"
## [449] "M0737s" "M0738s" "M0739m" "M0739s" "M074s"  "M0740s" "M0746s"
## [456] "M0749s" "M075s"  "M0750m" "M0750s" "M0751m" "M0755s" "M0759s"
## [463] "M076m"  "M076s"  "M0760s" "M0766m" "M0769s" "M080m"  "M080s" 
## [470] "M0800m" "M0800s" "M0802m" "M0805m" "M0806m" "M0808m" "M0809s"
## [477] "M0810m" "M0819m" "M0819s" "M082m"  "M082s"  "M0820s" "M0825s"
## [484] "M0826s" "M0828s" "M0829m" "M0829s" "M0830m" "M0830s" "M0836m"
## [491] "M0839s" "M0840m" "M0840s" "M0844s" "M088s"  "M089m"  "M089s" 
## [498] "M0890m" "M0890s" "M0899m" "M0899s" "M300m"  "M300s"  "M301m" 
## [505] "M301s"  "M302m"  "M303m"  "M303s"  "M308m"  "M308s"  "M320m" 
## [512] "M320s"  "M321m"  "M321s"  "M328m"  "M328s"  "M329m"  "M329s" 
## [519] "M3290m" "M3290s" "M330s"  "M331m"  "M331s"  "M332m"  "M332s" 
## [526] "M339m"  "M339s"  "M340m"  "M340s"  "M341m"  "M341s"  "M342m" 
## [533] "M342s"  "M348m"  "M348s"  "M349m"  "M349s"  "M350m"  "M350s" 
## [540] "M351m"  "M351s"  "M352m"  "M352s"  "M353m"  "M353s"  "M354m" 
## [547] "M354s"  "M355s"  "M357m"  "M357s"  "M358m"  "M358s"  "M359m" 
## [554] "M359s"  "M3599s" "M45m"   "M45s"   "M45X0m" "M45X0s" "M45X1s"
## [561] "M45X2m" "M45X2s" "M45X4s" "M45X6m" "M45X6s" "M45X7m" "M45X7s"
## [568] "M45X8s" "M45X9m" "M45X9s" "M600m"  "M600s"  "M6000m" "M6000s"
## [575] "M6001m" "M6001s" "M6002m" "M6005m" "M6005s" "M6006m" "M6006s"
## [582] "M6008m" "M6008s" "M6009m" "M601s"  "M6018s" "M602m"  "M602s" 
## [589] "M6021s" "M6023m" "M6023s" "M6024m" "M6024s" "M6025m" "M6026s"
## [596] "M6027m" "M6028m" "M6028s" "M6029s" "M608m"  "M608s"  "M6080m"
## [603] "M6082m" "M6085m" "M6086s" "M6088m" "M6089m" "M6089s" "M609m" 
## [610] "M609s"  "M6090m" "M6090s" "M6091m" "M6091s" "M6092m" "M6092s"
## [617] "M6093m" "M6095m" "M6095s" "M6096m" "M6096s" "M6097m" "M6098m"
## [624] "M6098s" "M6099m" "M6099s" "N030m"  "N030s"  "N031m"  "N031s" 
## [631] "N032m"  "N032s"  "N033m"  "N033s"  "N035m"  "N035s"  "N036m" 
## [638] "N037m"  "N037s"  "N038m"  "N038s"  "N039m"  "N039s"  "N050m" 
## [645] "N050s"  "N051m"  "N051s"  "N052m"  "N052s"  "N053m"  "N053s" 
## [652] "N054m"  "N054s"  "N055m"  "N055s"  "N056m"  "N056s"  "N057m" 
## [659] "N057s"  "N058m"  "N058s"  "N059m"  "N059s"  "N301m"  "N301s" 
## [666] "N711m"  "N711s"  "O264s"

Create summary column

autoimmune_no_duplicate$ICD.autoimmune.raw <-
  apply(
    autoimmune_no_duplicate[,2:ncol(autoimmune_no_duplicate)] == 1,
    1,
    any)

autoimmune_no_duplicate$ICD.autoimmune <-
  as.integer(
    autoimmune_no_duplicate$ICD.autoimmune.raw
    )

autoimmune_reduced <- autoimmune_no_duplicate %>%
  select(IID, ICD.autoimmune)

Summary

summary(as.factor(autoimmune_reduced$ICD.autoimmune))
##      0      1 
## 460600  42019

autoinflammatory

Read in data

autoinflammatory <- fread(
  input = "data_raw/2019_05_29_ICD/ICD10.autoinflammatory.txt",
  header = TRUE,
  stringsAsFactors = F,
  data.table = F)

colnames(autoinflammatory)
##    [1] "IID"    "A150m"  "A150s"  "IID"    "A151m"  "A151s"  "IID"   
##    [8] "A152m"  "A152s"  "IID"    "A153m"  "A153s"  "IID"    "A154s" 
##   [15] "IID"    "A155s"  "IID"    "A156m"  "A156s"  "IID"    "A157m" 
##   [22] "A157s"  "IID"    "A159m"  "A159s"  "IID"    "A160m"  "A160s" 
##   [29] "IID"    "A161s"  "IID"    "A162m"  "A162s"  "IID"    "A163m" 
##   [36] "A163s"  "IID"    "A164m"  "A164s"  "IID"    "A165m"  "A165s" 
##   [43] "IID"    "A167s"  "IID"    "A169m"  "A169s"  "IID"    "A170m" 
##   [50] "A170s"  "IID"    "A178m"  "A178s"  "IID"    "A180m"  "A180s" 
##   [57] "IID"    "A181m"  "A181s"  "IID"    "A182m"  "A182s"  "IID"   
##   [64] "A183m"  "A183s"  "IID"    "A184m"  "A184s"  "IID"    "A185m" 
##   [71] "A185s"  "IID"    "A187m"  "A187s"  "IID"    "A188m"  "A188s" 
##   [78] "IID"    "A190m"  "IID"    "A192m"  "IID"    "A199m"  "A199s" 
##   [85] "IID"    "B159m"  "B159s"  "IID"    "B160m"  "IID"    "B169m" 
##   [92] "B169s"  "IID"    "B171m"  "B171s"  "IID"    "B172m"  "B172s" 
##   [99] "IID"    "B178m"  "B178s"  "IID"    "B179m"  "B179s"  "IID"   
##  [106] "B180m"  "B180s"  "IID"    "B181m"  "B181s"  "IID"    "B182m" 
##  [113] "B182s"  "IID"    "B188m"  "B188s"  "IID"    "B189m"  "B189s" 
##  [120] "IID"    "B199m"  "B199s"  "IID"    "B200m"  "IID"    "B201m" 
##  [127] "IID"    "B202m"  "B202s"  "IID"    "B203m"  "B203s"  "IID"   
##  [134] "B204m"  "B204s"  "IID"    "B206m"  "B206s"  "IID"    "B207m" 
##  [141] "B207s"  "IID"    "B208m"  "B208s"  "IID"    "B210m"  "B210s" 
##  [148] "IID"    "B211m"  "IID"    "B212m"  "B212s"  "IID"    "B213m" 
##  [155] "B213s"  "IID"    "B217m"  "IID"    "B218m"  "IID"    "B220m" 
##  [162] "B220s"  "IID"    "B221m"  "B221s"  "IID"    "B222m"  "IID"   
##  [169] "B227m"  "B227s"  "IID"    "B230m"  "B230s"  "IID"    "B232m" 
##  [176] "B232s"  "IID"    "B238m"  "B238s"  "IID"    "B24m"   "B24s"  
##  [183] "IID"    "C000m"  "IID"    "C001m"  "C001s"  "IID"    "C002m" 
##  [190] "IID"    "C003m"  "IID"    "C004m"  "C004s"  "IID"    "C005s" 
##  [197] "IID"    "C006m"  "IID"    "C009m"  "C009s"  "IID"    "C01m"  
##  [204] "C01s"   "IID"    "C020m"  "C020s"  "IID"    "C021m"  "C021s" 
##  [211] "IID"    "C022m"  "C022s"  "IID"    "C023m"  "C023s"  "IID"   
##  [218] "C024m"  "C024s"  "IID"    "C028m"  "C028s"  "IID"    "C029m" 
##  [225] "C029s"  "IID"    "C030m"  "IID"    "C031m"  "C031s"  "IID"   
##  [232] "C039m"  "C039s"  "IID"    "C040m"  "C040s"  "IID"    "C041m" 
##  [239] "C041s"  "IID"    "C048m"  "IID"    "C049m"  "C049s"  "IID"   
##  [246] "C050m"  "IID"    "C051m"  "C051s"  "IID"    "C052m"  "IID"   
##  [253] "C058m"  "IID"    "C059m"  "C059s"  "IID"    "C060m"  "C060s" 
##  [260] "IID"    "C061m"  "IID"    "C062m"  "C062s"  "IID"    "C068m" 
##  [267] "C068s"  "IID"    "C069m"  "C069s"  "IID"    "C07m"   "C07s"  
##  [274] "IID"    "C080m"  "C080s"  "IID"    "C081m"  "IID"    "C088m" 
##  [281] "IID"    "C089m"  "C089s"  "IID"    "C090m"  "C090s"  "IID"   
##  [288] "C091m"  "C091s"  "IID"    "C098m"  "IID"    "C099m"  "C099s" 
##  [295] "IID"    "C100m"  "C100s"  "IID"    "C102m"  "IID"    "C103m" 
##  [302] "C103s"  "IID"    "C104m"  "C104s"  "IID"    "C108m"  "C108s" 
##  [309] "IID"    "C109m"  "C109s"  "IID"    "C110m"  "IID"    "C111m" 
##  [316] "C111s"  "IID"    "C112m"  "C112s"  "IID"    "C113m"  "C113s" 
##  [323] "IID"    "C119m"  "C119s"  "IID"    "C12m"   "C12s"   "IID"   
##  [330] "C130m"  "C130s"  "IID"    "C131m"  "IID"    "C132s"  "IID"   
##  [337] "C138m"  "IID"    "C139m"  "C139s"  "IID"    "C140m"  "C140s" 
##  [344] "IID"    "C148m"  "C148s"  "IID"    "C150m"  "C150s"  "IID"   
##  [351] "C151m"  "C151s"  "IID"    "C152m"  "C152s"  "IID"    "C153m" 
##  [358] "C153s"  "IID"    "C154m"  "C154s"  "IID"    "C155m"  "C155s" 
##  [365] "IID"    "C158m"  "C158s"  "IID"    "C159m"  "C159s"  "IID"   
##  [372] "C160m"  "C160s"  "IID"    "C161m"  "C161s"  "IID"    "C162m" 
##  [379] "C162s"  "IID"    "C163m"  "C163s"  "IID"    "C164m"  "C164s" 
##  [386] "IID"    "C165m"  "C165s"  "IID"    "C166m"  "C166s"  "IID"   
##  [393] "C168m"  "C168s"  "IID"    "C169m"  "C169s"  "IID"    "C170m" 
##  [400] "C170s"  "IID"    "C171m"  "C171s"  "IID"    "C172m"  "C172s" 
##  [407] "IID"    "C173m"  "C173s"  "IID"    "C178m"  "C178s"  "IID"   
##  [414] "C179m"  "C179s"  "IID"    "C180m"  "C180s"  "IID"    "C181m" 
##  [421] "C181s"  "IID"    "C182m"  "C182s"  "IID"    "C183m"  "C183s" 
##  [428] "IID"    "C184m"  "C184s"  "IID"    "C185m"  "C185s"  "IID"   
##  [435] "C186m"  "C186s"  "IID"    "C187m"  "C187s"  "IID"    "C188m" 
##  [442] "C188s"  "IID"    "C189m"  "C189s"  "IID"    "C19m"   "C19s"  
##  [449] "IID"    "C20m"   "C20s"   "IID"    "C210m"  "C210s"  "IID"   
##  [456] "C211m"  "C211s"  "IID"    "C218m"  "C218s"  "IID"    "C220m" 
##  [463] "C220s"  "IID"    "C221m"  "C221s"  "IID"    "C222s"  "IID"   
##  [470] "C223m"  "C223s"  "IID"    "C224m"  "C224s"  "IID"    "C227m" 
##  [477] "C227s"  "IID"    "C229m"  "C229s"  "IID"    "C23m"   "C23s"  
##  [484] "IID"    "C240m"  "C240s"  "IID"    "C241m"  "C241s"  "IID"   
##  [491] "C248m"  "C248s"  "IID"    "C249m"  "C249s"  "IID"    "C250m" 
##  [498] "C250s"  "IID"    "C251m"  "C251s"  "IID"    "C252m"  "C252s" 
##  [505] "IID"    "C253m"  "C253s"  "IID"    "C254m"  "C254s"  "IID"   
##  [512] "C257m"  "C257s"  "IID"    "C258m"  "C258s"  "IID"    "C259m" 
##  [519] "C259s"  "IID"    "C260m"  "C260s"  "IID"    "C261m"  "C261s" 
##  [526] "IID"    "C268m"  "C268s"  "IID"    "C269m"  "C269s"  "IID"   
##  [533] "C300m"  "C300s"  "IID"    "C301m"  "IID"    "C310m"  "C310s" 
##  [540] "IID"    "C311m"  "C311s"  "IID"    "C312m"  "IID"    "C313m" 
##  [547] "IID"    "C318s"  "IID"    "C319m"  "C319s"  "IID"    "C320m" 
##  [554] "C320s"  "IID"    "C321m"  "C321s"  "IID"    "C322m"  "C322s" 
##  [561] "IID"    "C323m"  "C323s"  "IID"    "C328m"  "IID"    "C329m" 
##  [568] "C329s"  "IID"    "C33m"   "C33s"   "IID"    "C340m"  "C340s" 
##  [575] "IID"    "C341m"  "C341s"  "IID"    "C342m"  "C342s"  "IID"   
##  [582] "C343m"  "C343s"  "IID"    "C348m"  "C348s"  "IID"    "C349m" 
##  [589] "C349s"  "IID"    "C37m"   "C37s"   "IID"    "C380m"  "IID"   
##  [596] "C381m"  "C381s"  "IID"    "C382m"  "IID"    "C383m"  "C383s" 
##  [603] "IID"    "C384m"  "C384s"  "IID"    "C390m"  "IID"    "C399s" 
##  [610] "IID"    "C400m"  "C400s"  "IID"    "C401m"  "C401s"  "IID"   
##  [617] "C402m"  "C402s"  "IID"    "C403m"  "C403s"  "IID"    "C408m" 
##  [624] "IID"    "C410m"  "C410s"  "IID"    "C411m"  "C411s"  "IID"   
##  [631] "C412m"  "C412s"  "IID"    "C413m"  "C413s"  "IID"    "C414m" 
##  [638] "C414s"  "IID"    "C419m"  "C419s"  "IID"    "C430m"  "IID"   
##  [645] "C431m"  "IID"    "C432m"  "C432s"  "IID"    "C433m"  "C433s" 
##  [652] "IID"    "C434m"  "C434s"  "IID"    "C435m"  "C435s"  "IID"   
##  [659] "C436m"  "C436s"  "IID"    "C437m"  "C437s"  "IID"    "C438m" 
##  [666] "IID"    "C439m"  "C439s"  "IID"    "C440m"  "C440s"  "IID"   
##  [673] "C441m"  "C441s"  "IID"    "C442m"  "C442s"  "IID"    "C443m" 
##  [680] "C443s"  "IID"    "C444m"  "C444s"  "IID"    "C445m"  "C445s" 
##  [687] "IID"    "C446m"  "C446s"  "IID"    "C447m"  "C447s"  "IID"   
##  [694] "C448m"  "C448s"  "IID"    "C449m"  "C449s"  "IID"    "C450m" 
##  [701] "C450s"  "IID"    "C451m"  "C451s"  "IID"    "C457m"  "C457s" 
##  [708] "IID"    "C459m"  "C459s"  "IID"    "C460m"  "C460s"  "IID"   
##  [715] "C461s"  "IID"    "C462s"  "IID"    "C463m"  "C463s"  "IID"   
##  [722] "C467m"  "C467s"  "IID"    "C468s"  "IID"    "C469m"  "C469s" 
##  [729] "IID"    "C470m"  "C470s"  "IID"    "C471m"  "C471s"  "IID"   
##  [736] "C472m"  "IID"    "C473m"  "C473s"  "IID"    "C474s"  "IID"   
##  [743] "C475m"  "C475s"  "IID"    "C476m"  "IID"    "C479m"  "C479s" 
##  [750] "IID"    "C480m"  "C480s"  "IID"    "C481m"  "C481s"  "IID"   
##  [757] "C482m"  "C482s"  "IID"    "C488m"  "IID"    "C490m"  "C490s" 
##  [764] "IID"    "C491m"  "C491s"  "IID"    "C492m"  "C492s"  "IID"   
##  [771] "C493m"  "C493s"  "IID"    "C494m"  "C494s"  "IID"    "C495m" 
##  [778] "C495s"  "IID"    "C496m"  "C496s"  "IID"    "C498m"  "C498s" 
##  [785] "IID"    "C499m"  "C499s"  "IID"    "C500m"  "C500s"  "IID"   
##  [792] "C501m"  "C501s"  "IID"    "C502m"  "C502s"  "IID"    "C503m" 
##  [799] "C503s"  "IID"    "C504m"  "C504s"  "IID"    "C505m"  "C505s" 
##  [806] "IID"    "C506m"  "C506s"  "IID"    "C508m"  "C508s"  "IID"   
##  [813] "C509m"  "C509s"  "IID"    "C510m"  "C510s"  "IID"    "C511m" 
##  [820] "C511s"  "IID"    "C512s"  "IID"    "C518m"  "IID"    "C519m" 
##  [827] "C519s"  "IID"    "C52m"   "C52s"   "IID"    "C530m"  "C530s" 
##  [834] "IID"    "C531m"  "IID"    "C538m"  "C538s"  "IID"    "C539m" 
##  [841] "C539s"  "IID"    "C540m"  "C540s"  "IID"    "C541m"  "C541s" 
##  [848] "IID"    "C542m"  "IID"    "C543m"  "IID"    "C548m"  "IID"   
##  [855] "C549m"  "C549s"  "IID"    "C55m"   "C55s"   "IID"    "C56m"  
##  [862] "C56s"   "IID"    "C570m"  "C570s"  "IID"    "C571m"  "IID"   
##  [869] "C574m"  "IID"    "C577m"  "C577s"  "IID"    "C578m"  "C578s" 
##  [876] "IID"    "C579m"  "C579s"  "IID"    "C58m"   "IID"    "C600m" 
##  [883] "C600s"  "IID"    "C601m"  "C601s"  "IID"    "C602m"  "C602s" 
##  [890] "IID"    "C608m"  "IID"    "C609m"  "C609s"  "IID"    "C61m"  
##  [897] "C61s"   "IID"    "C620m"  "IID"    "C621m"  "C621s"  "IID"   
##  [904] "C629m"  "C629s"  "IID"    "C631m"  "IID"    "C632m"  "C632s" 
##  [911] "IID"    "C637m"  "IID"    "C639m"  "IID"    "C64m"   "C64s"  
##  [918] "IID"    "C65m"   "C65s"   "IID"    "C66m"   "C66s"   "IID"   
##  [925] "C670m"  "C670s"  "IID"    "C671m"  "C671s"  "IID"    "C672m" 
##  [932] "C672s"  "IID"    "C673m"  "C673s"  "IID"    "C674m"  "C674s" 
##  [939] "IID"    "C675m"  "C675s"  "IID"    "C676m"  "C676s"  "IID"   
##  [946] "C677m"  "C677s"  "IID"    "C678m"  "C678s"  "IID"    "C679m" 
##  [953] "C679s"  "IID"    "C680m"  "C680s"  "IID"    "C688m"  "IID"   
##  [960] "C689m"  "C689s"  "IID"    "C690m"  "IID"    "C691m"  "IID"   
##  [967] "C692m"  "C692s"  "IID"    "C693m"  "C693s"  "IID"    "C694m" 
##  [974] "C694s"  "IID"    "C695m"  "C695s"  "IID"    "C696m"  "C696s" 
##  [981] "IID"    "C698m"  "IID"    "C699m"  "C699s"  "IID"    "C700m" 
##  [988] "C700s"  "IID"    "C701m"  "C701s"  "IID"    "C709m"  "C709s" 
##  [995] "IID"    "C710m"  "C710s"  "IID"    "C711m"  "C711s"  "IID"   
## [1002] "C712m"  "C712s"  "IID"    "C713m"  "C713s"  "IID"    "C714m" 
## [1009] "C714s"  "IID"    "C715m"  "C715s"  "IID"    "C716m"  "C716s" 
## [1016] "IID"    "C717m"  "C717s"  "IID"    "C718m"  "C718s"  "IID"   
## [1023] "C719m"  "C719s"  "IID"    "C720m"  "C720s"  "IID"    "C721m" 
## [1030] "C721s"  "IID"    "C722m"  "C722s"  "IID"    "C724m"  "IID"   
## [1037] "C725m"  "IID"    "C728m"  "IID"    "C729m"  "IID"    "C73m"  
## [1044] "C73s"   "IID"    "C740m"  "C740s"  "IID"    "C741m"  "C741s" 
## [1051] "IID"    "C749m"  "C749s"  "IID"    "C750m"  "C750s"  "IID"   
## [1058] "C751m"  "C751s"  "IID"    "C752s"  "IID"    "C753s"  "IID"   
## [1065] "C755m"  "C755s"  "IID"    "C759m"  "C759s"  "IID"    "D000m" 
## [1072] "D000s"  "IID"    "D001m"  "D001s"  "IID"    "D002m"  "D002s" 
## [1079] "IID"    "D010m"  "D010s"  "IID"    "D012m"  "D012s"  "IID"   
## [1086] "D013m"  "D013s"  "IID"    "D015m"  "D015s"  "IID"    "D017m" 
## [1093] "IID"    "D020m"  "D020s"  "IID"    "D021m"  "D021s"  "IID"   
## [1100] "D022m"  "D022s"  "IID"    "D023m"  "D023s"  "IID"    "D030m" 
## [1107] "IID"    "D031m"  "D031s"  "IID"    "D032m"  "D032s"  "IID"   
## [1114] "D033m"  "D033s"  "IID"    "D034m"  "D034s"  "IID"    "D035m" 
## [1121] "D035s"  "IID"    "D036m"  "D036s"  "IID"    "D037m"  "D037s" 
## [1128] "IID"    "D038m"  "D038s"  "IID"    "D039m"  "D039s"  "IID"   
## [1135] "D040m"  "IID"    "D041m"  "D041s"  "IID"    "D042m"  "D042s" 
## [1142] "IID"    "D043m"  "D043s"  "IID"    "D044m"  "D044s"  "IID"   
## [1149] "D045m"  "D045s"  "IID"    "D046m"  "D046s"  "IID"    "D047m" 
## [1156] "D047s"  "IID"    "D048m"  "D048s"  "IID"    "D049m"  "D049s" 
## [1163] "IID"    "D050m"  "D050s"  "IID"    "D051m"  "D051s"  "IID"   
## [1170] "D057m"  "D057s"  "IID"    "D059m"  "D059s"  "IID"    "D060m" 
## [1177] "D060s"  "IID"    "D061m"  "D061s"  "IID"    "D067m"  "D067s" 
## [1184] "IID"    "D069m"  "D069s"  "IID"    "D070m"  "IID"    "D071m" 
## [1191] "D071s"  "IID"    "D072m"  "D072s"  "IID"    "D073m"  "D073s" 
## [1198] "IID"    "D074m"  "D074s"  "IID"    "D075m"  "D075s"  "IID"   
## [1205] "D076m"  "D076s"  "IID"    "D090m"  "D090s"  "IID"    "D091m" 
## [1212] "D091s"  "IID"    "D092m"  "IID"    "D093m"  "D093s"  "IID"   
## [1219] "D097m"  "IID"    "D099m"  "D099s"  "IID"    "D70m"   "D70s"  
## [1226] "IID"    "D71m"   "D71s"   "IID"    "D721m"  "D721s"  "IID"   
## [1233] "D728m"  "D728s"  "IID"    "D729m"  "D729s"  "IID"    "D730s" 
## [1240] "IID"    "D731m"  "D731s"  "IID"    "D732m"  "D732s"  "IID"   
## [1247] "D733m"  "D733s"  "IID"    "D734m"  "D734s"  "IID"    "D735m" 
## [1254] "D735s"  "IID"    "D748s"  "IID"    "D749s"  "IID"    "D750m" 
## [1261] "D750s"  "IID"    "D751m"  "D751s"  "IID"    "D752m"  "D752s" 
## [1268] "IID"    "D758m"  "D758s"  "IID"    "D759m"  "D759s"  "IID"   
## [1275] "D760m"  "D760s"  "IID"    "D761m"  "D761s"  "IID"    "D762s" 
## [1282] "IID"    "D763m"  "D763s"  "IID"    "D77s"   "IID"    "D860m" 
## [1289] "D860s"  "IID"    "D861m"  "D861s"  "IID"    "D862m"  "D862s" 
## [1296] "IID"    "D863m"  "D863s"  "IID"    "D868m"  "D868s"  "IID"   
## [1303] "D869m"  "D869s"  "IID"    "D890m"  "D890s"  "IID"    "D891m" 
## [1310] "D891s"  "IID"    "D892m"  "D892s"  "IID"    "D898m"  "D898s" 
## [1317] "IID"    "D899m"  "D899s"  "IID"    "E05s"   "IID"    "E051m" 
## [1324] "E051s"  "IID"    "E052m"  "E052s"  "IID"    "E053m"  "E053s" 
## [1331] "IID"    "E054s"  "IID"    "E055m"  "E055s"  "IID"    "E058m" 
## [1338] "E058s"  "IID"    "E059m"  "E059s"  "IID"    "E060m"  "IID"   
## [1345] "E062m"  "E062s"  "IID"    "E064m"  "E064s"  "IID"    "E065m" 
## [1352] "E065s"  "IID"    "E069m"  "E069s"  "IID"    "E110m"  "E110s" 
## [1359] "IID"    "E111m"  "E111s"  "IID"    "E112m"  "E112s"  "IID"   
## [1366] "E113m"  "E113s"  "IID"    "E114m"  "E114s"  "IID"    "E115m" 
## [1373] "E115s"  "IID"    "E116m"  "E116s"  "IID"    "E117m"  "E117s" 
## [1380] "IID"    "E118m"  "E118s"  "IID"    "E119m"  "E119s"  "IID"   
## [1387] "E121s"  "IID"    "E128s"  "IID"    "E129s"  "IID"    "E230m" 
## [1394] "E230s"  "IID"    "E231m"  "E231s"  "IID"    "E236m"  "E236s" 
## [1401] "IID"    "E237m"  "E237s"  "IID"    "E282m"  "E282s"  "IID"   
## [1408] "E320m"  "E320s"  "IID"    "E328m"  "E328s"  "IID"    "E329m" 
## [1415] "E329s"  "IID"    "E340m"  "E340s"  "IID"    "E351s"  "IID"   
## [1422] "E840m"  "E840s"  "IID"    "E841m"  "E841s"  "IID"    "E848m" 
## [1429] "E848s"  "IID"    "E849m"  "E849s"  "IID"    "G031m"  "G031s" 
## [1436] "IID"    "G032m"  "G032s"  "IID"    "G618m"  "G618s"  "IID"   
## [1443] "G619m"  "G619s"  "IID"    "G724m"  "G724s"  "IID"    "H044m" 
## [1450] "H044s"  "IID"    "H051m"  "H051s"  "IID"    "H150m"  "H150s" 
## [1457] "IID"    "H151m"  "H151s"  "IID"    "H163m"  "H163s"  "IID"   
## [1464] "H200m"  "H200s"  "IID"    "H201m"  "H201s"  "IID"    "H202m" 
## [1471] "H202s"  "IID"    "H208m"  "H208s"  "IID"    "H209m"  "H209s" 
## [1478] "IID"    "H353m"  "H353s"  "IID"    "H652m"  "H652s"  "IID"   
## [1485] "H653m"  "H653s"  "IID"    "H654m"  "H654s"  "IID"    "H661m" 
## [1492] "H661s"  "IID"    "H662m"  "H662s"  "IID"    "H663m"  "H663s" 
## [1499] "IID"    "H701m"  "H701s"  "IID"    "H731m"  "H731s"  "IID"   
## [1506] "H912m"  "H912s"  "IID"    "I050m"  "I050s"  "IID"    "I051m" 
## [1513] "I051s"  "IID"    "I052m"  "I052s"  "IID"    "I058m"  "I058s" 
## [1520] "IID"    "I059m"  "I059s"  "IID"    "I060m"  "I060s"  "IID"   
## [1527] "I061m"  "I061s"  "IID"    "I062m"  "I062s"  "IID"    "I068s" 
## [1534] "IID"    "I069m"  "I069s"  "IID"    "I070m"  "I070s"  "IID"   
## [1541] "I071m"  "I071s"  "IID"    "I072s"  "IID"    "I078m"  "I078s" 
## [1548] "IID"    "I079s"  "IID"    "I080m"  "I080s"  "IID"    "I081m" 
## [1555] "I081s"  "IID"    "I082m"  "I082s"  "IID"    "I083m"  "I083s" 
## [1562] "IID"    "I088m"  "I088s"  "IID"    "I089m"  "I089s"  "IID"   
## [1569] "I091m"  "I091s"  "IID"    "I098m"  "IID"    "I099m"  "I099s" 
## [1576] "IID"    "I241m"  "I241s"  "IID"    "I418s"  "IID"    "I731m" 
## [1583] "I731s"  "IID"    "I881m"  "I881s"  "IID"    "J310m"  "J310s" 
## [1590] "IID"    "J311m"  "J311s"  "IID"    "J312m"  "J312s"  "IID"   
## [1597] "J320m"  "J320s"  "IID"    "J321m"  "J321s"  "IID"    "J322m" 
## [1604] "J322s"  "IID"    "J323m"  "J323s"  "IID"    "J324m"  "J324s" 
## [1611] "IID"    "J328m"  "J328s"  "IID"    "J329m"  "J329s"  "IID"   
## [1618] "J350m"  "J350s"  "IID"    "J351m"  "J351s"  "IID"    "J352m" 
## [1625] "J352s"  "IID"    "J353m"  "IID"    "J358m"  "J358s"  "IID"   
## [1632] "J359m"  "J359s"  "IID"    "J370m"  "J370s"  "IID"    "J40m"  
## [1639] "J40s"   "IID"    "J410m"  "J410s"  "IID"    "J411m"  "IID"   
## [1646] "J42m"   "J42s"   "IID"    "J430m"  "J430s"  "IID"    "J431m" 
## [1653] "J431s"  "IID"    "J432m"  "J432s"  "IID"    "J438m"  "J438s" 
## [1660] "IID"    "J439m"  "J439s"  "IID"    "J440m"  "J440s"  "IID"   
## [1667] "J441m"  "J441s"  "IID"    "J448m"  "J448s"  "IID"    "J449m" 
## [1674] "J449s"  "IID"    "J450m"  "J450s"  "IID"    "J451m"  "J451s" 
## [1681] "IID"    "J458m"  "J458s"  "IID"    "J459m"  "J459s"  "IID"   
## [1688] "J46m"   "J46s"   "IID"    "J47m"   "J47s"   "IID"    "J840m" 
## [1695] "J840s"  "IID"    "J841m"  "J841s"  "IID"    "J848m"  "J848s" 
## [1702] "IID"    "J849m"  "J849s"  "IID"    "K033m"  "K033s"  "IID"   
## [1709] "K040m"  "K040s"  "IID"    "K044m"  "K044s"  "IID"    "K045m" 
## [1716] "K045s"  "IID"    "K046m"  "K046s"  "IID"    "K047m"  "K047s" 
## [1723] "IID"    "K050m"  "K050s"  "IID"    "K051m"  "K051s"  "IID"   
## [1730] "K052m"  "K052s"  "IID"    "K0522s" "IID"    "K053m"  "K053s" 
## [1737] "IID"    "K054m"  "K054s"  "IID"    "K055m"  "K055s"  "IID"   
## [1744] "K056m"  "K056s"  "IID"    "K090m"  "K090s"  "IID"    "K091m" 
## [1751] "K091s"  "IID"    "K092m"  "K092s"  "IID"    "K098m"  "K098s" 
## [1758] "IID"    "K099m"  "K099s"  "IID"    "K102m"  "K102s"  "IID"   
## [1765] "K103m"  "K103s"  "IID"    "K112m"  "K112s"  "IID"    "K121m" 
## [1772] "K121s"  "IID"    "K122m"  "K122s"  "IID"    "K123m"  "K123s" 
## [1779] "IID"    "K140m"  "K140s"  "IID"    "K220m"  "K220s"  "IID"   
## [1786] "K227m"  "K227s"  "IID"    "K254m"  "K254s"  "IID"    "K255m" 
## [1793] "K255s"  "IID"    "K256m"  "K256s"  "IID"    "K257m"  "K257s" 
## [1800] "IID"    "K264m"  "K264s"  "IID"    "K265m"  "K265s"  "IID"   
## [1807] "K266m"  "K266s"  "IID"    "K267m"  "K267s"  "IID"    "K274m" 
## [1814] "K274s"  "IID"    "K275m"  "K275s"  "IID"    "K276m"  "K276s" 
## [1821] "IID"    "K277m"  "K277s"  "IID"    "K284m"  "IID"    "K285m" 
## [1828] "IID"    "K286m"  "IID"    "K287m"  "K287s"  "IID"    "K292m" 
## [1835] "K292s"  "IID"    "K293m"  "K293s"  "IID"    "K294m"  "K294s" 
## [1842] "IID"    "K295m"  "K295s"  "IID"    "K296m"  "K296s"  "IID"   
## [1849] "K500m"  "K500s"  "IID"    "K501m"  "K501s"  "IID"    "K508m" 
## [1856] "K508s"  "IID"    "K509m"  "K509s"  "IID"    "K510m"  "K510s" 
## [1863] "IID"    "K511m"  "K511s"  "IID"    "K512m"  "K512s"  "IID"   
## [1870] "K513m"  "K513s"  "IID"    "K514m"  "K514s"  "IID"    "K515m" 
## [1877] "K515s"  "IID"    "K518m"  "K518s"  "IID"    "K519m"  "K519s" 
## [1884] "IID"    "K520m"  "K520s"  "IID"    "K521m"  "K521s"  "IID"   
## [1891] "K522m"  "K522s"  "IID"    "K523m"  "K523s"  "IID"    "K528m" 
## [1898] "K528s"  "IID"    "K529m"  "K529s"  "IID"    "K580m"  "K580s" 
## [1905] "IID"    "K589m"  "K589s"  "IID"    "K601m"  "K601s"  "IID"   
## [1912] "K700m"  "K700s"  "IID"    "K701m"  "K701s"  "IID"    "K702m" 
## [1919] "K702s"  "IID"    "K703m"  "K703s"  "IID"    "K704m"  "K704s" 
## [1926] "IID"    "K709m"  "K709s"  "IID"    "K710m"  "K710s"  "IID"   
## [1933] "K711m"  "K711s"  "IID"    "K712m"  "K712s"  "IID"    "K713s" 
## [1940] "IID"    "K715m"  "IID"    "K716m"  "K716s"  "IID"    "K717m" 
## [1947] "K717s"  "IID"    "K718m"  "K718s"  "IID"    "K719m"  "K719s" 
## [1954] "IID"    "K720m"  "K720s"  "IID"    "K721m"  "K721s"  "IID"   
## [1961] "K729m"  "K729s"  "IID"    "K730m"  "IID"    "K731m"  "K731s" 
## [1968] "IID"    "K732m"  "K732s"  "IID"    "K738m"  "K738s"  "IID"   
## [1975] "K739m"  "K739s"  "IID"    "K740m"  "K740s"  "IID"    "K741m" 
## [1982] "K741s"  "IID"    "K742m"  "K742s"  "IID"    "K743m"  "K743s" 
## [1989] "IID"    "K744m"  "K744s"  "IID"    "K745m"  "K745s"  "IID"   
## [1996] "K746m"  "K746s"  "IID"    "K750m"  "K750s"  "IID"    "K751s" 
## [2003] "IID"    "K752m"  "K752s"  "IID"    "K753m"  "K753s"  "IID"   
## [2010] "K754m"  "K754s"  "IID"    "K758m"  "K758s"  "IID"    "K759m" 
## [2017] "K759s"  "IID"    "K760m"  "K760s"  "IID"    "K761m"  "K761s" 
## [2024] "IID"    "K762m"  "K762s"  "IID"    "K763m"  "K763s"  "IID"   
## [2031] "K765s"  "IID"    "K766m"  "K766s"  "IID"    "K767m"  "K767s" 
## [2038] "IID"    "K768m"  "K768s"  "IID"    "K769m"  "K769s"  "IID"   
## [2045] "K770m"  "K770s"  "IID"    "K778s"  "IID"    "K811m"  "K811s" 
## [2052] "IID"    "K830m"  "K830s"  "IID"    "K860m"  "K860s"  "IID"   
## [2059] "K861m"  "K861s"  "IID"    "K900m"  "K900s"  "IID"    "L410m" 
## [2066] "L410s"  "IID"    "M300m"  "M300s"  "IID"    "M301m"  "M301s" 
## [2073] "IID"    "M302m"  "IID"    "M303m"  "M303s"  "IID"    "M308m" 
## [2080] "M308s"  "IID"    "M310m"  "M310s"  "IID"    "M311m"  "M311s" 
## [2087] "IID"    "M312s"  "IID"    "M313m"  "M313s"  "IID"    "M314m" 
## [2094] "M314s"  "IID"    "M315m"  "M315s"  "IID"    "M316m"  "M316s" 
## [2101] "IID"    "M317m"  "M317s"  "IID"    "M318m"  "M318s"  "IID"   
## [2108] "M319m"  "M319s"  "IID"    "M320m"  "M320s"  "IID"    "M321m" 
## [2115] "M321s"  "IID"    "M328m"  "M328s"  "IID"    "M329m"  "M329s" 
## [2122] "IID"    "M3290m" "M3290s" "IID"    "M330s"  "IID"    "M331m" 
## [2129] "M331s"  "IID"    "M332m"  "M332s"  "IID"    "M339m"  "M339s" 
## [2136] "IID"    "M350m"  "M350s"  "IID"    "M351m"  "M351s"  "IID"   
## [2143] "M352m"  "M352s"  "IID"    "M353m"  "M353s"  "IID"    "M354m" 
## [2150] "M354s"  "IID"    "M355s"  "IID"    "M357m"  "M357s"  "IID"   
## [2157] "M358m"  "M358s"  "IID"    "M359m"  "M359s"  "IID"    "M3599s"
## [2164] "IID"    "M360m"  "M360s"  "IID"    "M362s"  "IID"    "M364s" 
## [2171] "IID"    "M368s"  "IID"    "M461m"  "M461s"  "IID"    "M4616m"
## [2178] "M4616s" "IID"    "M4617m" "M4617s" "IID"    "M4618m" "M4618s"
## [2185] "IID"    "M4619m" "M4619s" "IID"    "M600m"  "M600s"  "IID"   
## [2192] "M6000m" "M6000s" "IID"    "M6001m" "M6001s" "IID"    "M6002m"
## [2199] "IID"    "M6003m" "IID"    "M6005m" "M6005s" "IID"    "M6006m"
## [2206] "M6006s" "IID"    "M6008m" "M6008s" "IID"    "M6009m" "IID"   
## [2213] "M601s"  "IID"    "M6018s" "IID"    "M602m"  "M602s"  "IID"   
## [2220] "M6021s" "IID"    "M6023m" "M6023s" "IID"    "M6024m" "M6024s"
## [2227] "IID"    "M6025m" "IID"    "M6026s" "IID"    "M6027m" "IID"   
## [2234] "M6028m" "M6028s" "IID"    "M6029s" "IID"    "M608m"  "M608s" 
## [2241] "IID"    "M6080m" "IID"    "M6082m" "IID"    "M6085m" "IID"   
## [2248] "M6086s" "IID"    "M6088m" "IID"    "M6089m" "M6089s" "IID"   
## [2255] "M609m"  "M609s"  "IID"    "M6090m" "M6090s" "IID"    "M6091m"
## [2262] "M6091s" "IID"    "M6092m" "M6092s" "IID"    "M6093m" "IID"   
## [2269] "M6095m" "M6095s" "IID"    "M6096m" "M6096s" "IID"    "M6097m"
## [2276] "IID"    "M6098m" "M6098s" "IID"    "M6099m" "M6099s" "IID"   
## [2283] "M610m"  "IID"    "M6106m" "IID"    "M6114s" "IID"    "M6115m"
## [2290] "IID"    "M6125s" "IID"    "M613s"  "IID"    "M614m"  "M614s" 
## [2297] "IID"    "M615m"  "M615s"  "IID"    "M6150s" "IID"    "M6152m"
## [2304] "IID"    "M6155m" "M6155s" "IID"    "M6156m" "M6156s" "IID"   
## [2311] "M6158s" "IID"    "M6159m" "IID"    "M619m"  "M619s"  "IID"   
## [2318] "M6190s" "IID"    "M6191s" "IID"    "M6192s" "IID"    "M6195m"
## [2325] "IID"    "M6196s" "IID"    "M6198s" "IID"    "M632s"  "IID"   
## [2332] "M633s"  "IID"    "M638s"  "IID"    "M863m"  "IID"    "M8630m"
## [2339] "IID"    "N001m"  "N001s"  "IID"    "N002s"  "IID"    "N004s" 
## [2346] "IID"    "N005m"  "IID"    "N007s"  "IID"    "N008m"  "N008s" 
## [2353] "IID"    "N009m"  "N009s"  "IID"    "N015s"  "IID"    "N017m" 
## [2360] "N017s"  "IID"    "N019m"  "N019s"  "IID"    "N030m"  "N030s" 
## [2367] "IID"    "N031m"  "N031s"  "IID"    "N032m"  "N032s"  "IID"   
## [2374] "N033m"  "N033s"  "IID"    "N035m"  "N035s"  "IID"    "N036m" 
## [2381] "N036s"  "IID"    "N037m"  "N037s"  "IID"    "N038m"  "N038s" 
## [2388] "IID"    "N039m"  "N039s"  "IID"    "N050m"  "N050s"  "IID"   
## [2395] "N051m"  "N051s"  "IID"    "N052m"  "N052s"  "IID"    "N053m" 
## [2402] "N053s"  "IID"    "N054m"  "N054s"  "IID"    "N055m"  "N055s" 
## [2409] "IID"    "N056m"  "N056s"  "IID"    "N057m"  "N057s"  "IID"   
## [2416] "N058m"  "N058s"  "IID"    "N059m"  "N059s"  "IID"    "N301m" 
## [2423] "N301s"  "IID"    "N411m"  "N411s"  "IID"    "N701m"  "N701s" 
## [2430] "IID"    "N711m"  "N711s"  "IID"    "N731m"  "N731s"  "IID"   
## [2437] "N734s"  "IID"    "N761m"  "N761s"

Remove duplicate column

autoinflammatory_no_duplicate <- autoinflammatory[!duplicated(as.list(autoinflammatory))]

colnames(autoinflammatory_no_duplicate)
##    [1] "IID"    "A150m"  "A150s"  "A151m"  "A151s"  "A152m"  "A152s" 
##    [8] "A153m"  "A153s"  "A154s"  "A155s"  "A156m"  "A156s"  "A157m" 
##   [15] "A157s"  "A159m"  "A159s"  "A160m"  "A160s"  "A161s"  "A162m" 
##   [22] "A162s"  "A163m"  "A163s"  "A164m"  "A165m"  "A165s"  "A167s" 
##   [29] "A169m"  "A169s"  "A170m"  "A170s"  "A178m"  "A178s"  "A180m" 
##   [36] "A180s"  "A181m"  "A181s"  "A182m"  "A182s"  "A183m"  "A183s" 
##   [43] "A184m"  "A184s"  "A185m"  "A187m"  "A187s"  "A188m"  "A188s" 
##   [50] "A190m"  "A192m"  "A199m"  "A199s"  "B159m"  "B159s"  "B160m" 
##   [57] "B169m"  "B169s"  "B171m"  "B171s"  "B172m"  "B172s"  "B178m" 
##   [64] "B178s"  "B179m"  "B179s"  "B180m"  "B180s"  "B181m"  "B181s" 
##   [71] "B182m"  "B182s"  "B188m"  "B188s"  "B189m"  "B189s"  "B199m" 
##   [78] "B199s"  "B200m"  "B201m"  "B202m"  "B202s"  "B203m"  "B203s" 
##   [85] "B204m"  "B204s"  "B206m"  "B206s"  "B207m"  "B207s"  "B208m" 
##   [92] "B208s"  "B210m"  "B210s"  "B211m"  "B212m"  "B212s"  "B213m" 
##   [99] "B213s"  "B217m"  "B218m"  "B220m"  "B220s"  "B221m"  "B221s" 
##  [106] "B222m"  "B227m"  "B227s"  "B230m"  "B230s"  "B232m"  "B232s" 
##  [113] "B238m"  "B238s"  "B24m"   "B24s"   "C000m"  "C001m"  "C001s" 
##  [120] "C002m"  "C003m"  "C004m"  "C005s"  "C006m"  "C009m"  "C009s" 
##  [127] "C01m"   "C01s"   "C020m"  "C020s"  "C021m"  "C021s"  "C022m" 
##  [134] "C022s"  "C023m"  "C023s"  "C024m"  "C024s"  "C028m"  "C028s" 
##  [141] "C029m"  "C029s"  "C030m"  "C031m"  "C031s"  "C039m"  "C039s" 
##  [148] "C040m"  "C040s"  "C041m"  "C041s"  "C048m"  "C049m"  "C049s" 
##  [155] "C050m"  "C051m"  "C051s"  "C052m"  "C058m"  "C059m"  "C059s" 
##  [162] "C060m"  "C060s"  "C061m"  "C062m"  "C062s"  "C068m"  "C068s" 
##  [169] "C069m"  "C069s"  "C07m"   "C07s"   "C080m"  "C080s"  "C081m" 
##  [176] "C088m"  "C089m"  "C089s"  "C090m"  "C090s"  "C091m"  "C091s" 
##  [183] "C098m"  "C099m"  "C099s"  "C100m"  "C100s"  "C102m"  "C103m" 
##  [190] "C103s"  "C104m"  "C104s"  "C108m"  "C108s"  "C109m"  "C109s" 
##  [197] "C110m"  "C111m"  "C111s"  "C112m"  "C113m"  "C113s"  "C119m" 
##  [204] "C119s"  "C12m"   "C12s"   "C130m"  "C130s"  "C131m"  "C132s" 
##  [211] "C138m"  "C139m"  "C139s"  "C140m"  "C140s"  "C148m"  "C148s" 
##  [218] "C150m"  "C150s"  "C151m"  "C151s"  "C152m"  "C152s"  "C153m" 
##  [225] "C153s"  "C154m"  "C154s"  "C155m"  "C155s"  "C158m"  "C158s" 
##  [232] "C159m"  "C159s"  "C160m"  "C160s"  "C161m"  "C161s"  "C162m" 
##  [239] "C162s"  "C163m"  "C163s"  "C164m"  "C164s"  "C165m"  "C165s" 
##  [246] "C166m"  "C166s"  "C168m"  "C168s"  "C169m"  "C169s"  "C170m" 
##  [253] "C170s"  "C171m"  "C171s"  "C172m"  "C172s"  "C173m"  "C173s" 
##  [260] "C178m"  "C178s"  "C179m"  "C179s"  "C180m"  "C180s"  "C181m" 
##  [267] "C181s"  "C182m"  "C182s"  "C183m"  "C183s"  "C184m"  "C184s" 
##  [274] "C185m"  "C185s"  "C186m"  "C186s"  "C187m"  "C187s"  "C188m" 
##  [281] "C188s"  "C189m"  "C189s"  "C19m"   "C19s"   "C20m"   "C20s"  
##  [288] "C210m"  "C210s"  "C211m"  "C211s"  "C218m"  "C218s"  "C220m" 
##  [295] "C220s"  "C221m"  "C221s"  "C222s"  "C223m"  "C223s"  "C224m" 
##  [302] "C224s"  "C227m"  "C227s"  "C229m"  "C229s"  "C23m"   "C23s"  
##  [309] "C240m"  "C240s"  "C241m"  "C241s"  "C248m"  "C248s"  "C249m" 
##  [316] "C249s"  "C250m"  "C250s"  "C251m"  "C251s"  "C252m"  "C252s" 
##  [323] "C253m"  "C253s"  "C254m"  "C254s"  "C257m"  "C257s"  "C258m" 
##  [330] "C258s"  "C259m"  "C259s"  "C260m"  "C260s"  "C261m"  "C261s" 
##  [337] "C268m"  "C268s"  "C269m"  "C269s"  "C300m"  "C300s"  "C301m" 
##  [344] "C310m"  "C310s"  "C311m"  "C311s"  "C312m"  "C313m"  "C318s" 
##  [351] "C319m"  "C319s"  "C320m"  "C320s"  "C321m"  "C321s"  "C322m" 
##  [358] "C322s"  "C323m"  "C323s"  "C328m"  "C329m"  "C329s"  "C33m"  
##  [365] "C33s"   "C340m"  "C340s"  "C341m"  "C341s"  "C342m"  "C342s" 
##  [372] "C343m"  "C343s"  "C348m"  "C348s"  "C349m"  "C349s"  "C37m"  
##  [379] "C37s"   "C380m"  "C381m"  "C381s"  "C382m"  "C383m"  "C383s" 
##  [386] "C384m"  "C384s"  "C390m"  "C399s"  "C400m"  "C400s"  "C401m" 
##  [393] "C401s"  "C402m"  "C402s"  "C403m"  "C403s"  "C408m"  "C410m" 
##  [400] "C410s"  "C411m"  "C411s"  "C412m"  "C412s"  "C413m"  "C413s" 
##  [407] "C414m"  "C414s"  "C419m"  "C419s"  "C430m"  "C431m"  "C432m" 
##  [414] "C432s"  "C433m"  "C433s"  "C434m"  "C434s"  "C435m"  "C435s" 
##  [421] "C436m"  "C436s"  "C437m"  "C437s"  "C438m"  "C439m"  "C439s" 
##  [428] "C440m"  "C440s"  "C441m"  "C441s"  "C442m"  "C442s"  "C443m" 
##  [435] "C443s"  "C444m"  "C444s"  "C445m"  "C445s"  "C446m"  "C446s" 
##  [442] "C447m"  "C447s"  "C448m"  "C448s"  "C449m"  "C449s"  "C450m" 
##  [449] "C450s"  "C451m"  "C451s"  "C457m"  "C457s"  "C459m"  "C459s" 
##  [456] "C460m"  "C460s"  "C461s"  "C462s"  "C463s"  "C467s"  "C469m" 
##  [463] "C469s"  "C470m"  "C470s"  "C471m"  "C471s"  "C472m"  "C473m" 
##  [470] "C473s"  "C474s"  "C475m"  "C475s"  "C476m"  "C479m"  "C479s" 
##  [477] "C480m"  "C480s"  "C481m"  "C481s"  "C482m"  "C482s"  "C488m" 
##  [484] "C490m"  "C490s"  "C491m"  "C491s"  "C492m"  "C492s"  "C493m" 
##  [491] "C493s"  "C494m"  "C494s"  "C495m"  "C495s"  "C496m"  "C496s" 
##  [498] "C498m"  "C498s"  "C499m"  "C499s"  "C500m"  "C500s"  "C501m" 
##  [505] "C501s"  "C502m"  "C502s"  "C503m"  "C503s"  "C504m"  "C504s" 
##  [512] "C505m"  "C505s"  "C506m"  "C506s"  "C508m"  "C508s"  "C509m" 
##  [519] "C509s"  "C510m"  "C510s"  "C511m"  "C511s"  "C512s"  "C518m" 
##  [526] "C519m"  "C519s"  "C52m"   "C52s"   "C530m"  "C530s"  "C531m" 
##  [533] "C538m"  "C538s"  "C539m"  "C539s"  "C540m"  "C540s"  "C541m" 
##  [540] "C541s"  "C542m"  "C543m"  "C548m"  "C549m"  "C549s"  "C55m"  
##  [547] "C55s"   "C56m"   "C56s"   "C570m"  "C570s"  "C571m"  "C574m" 
##  [554] "C577m"  "C577s"  "C578m"  "C578s"  "C579m"  "C579s"  "C58m"  
##  [561] "C600m"  "C600s"  "C601m"  "C601s"  "C602m"  "C602s"  "C608m" 
##  [568] "C609m"  "C609s"  "C61m"   "C61s"   "C620m"  "C621m"  "C621s" 
##  [575] "C629m"  "C629s"  "C631m"  "C632m"  "C632s"  "C637m"  "C639m" 
##  [582] "C64m"   "C64s"   "C65m"   "C65s"   "C66m"   "C66s"   "C670m" 
##  [589] "C670s"  "C671m"  "C671s"  "C672m"  "C672s"  "C673m"  "C673s" 
##  [596] "C674m"  "C674s"  "C675m"  "C675s"  "C676m"  "C676s"  "C677m" 
##  [603] "C677s"  "C678m"  "C678s"  "C679m"  "C679s"  "C680m"  "C680s" 
##  [610] "C688m"  "C689m"  "C689s"  "C690m"  "C691m"  "C692m"  "C692s" 
##  [617] "C693m"  "C693s"  "C694m"  "C694s"  "C695m"  "C695s"  "C696m" 
##  [624] "C696s"  "C698m"  "C699m"  "C699s"  "C700m"  "C700s"  "C701m" 
##  [631] "C701s"  "C709m"  "C709s"  "C710m"  "C710s"  "C711m"  "C711s" 
##  [638] "C712m"  "C712s"  "C713m"  "C713s"  "C714m"  "C714s"  "C715m" 
##  [645] "C715s"  "C716m"  "C716s"  "C717m"  "C717s"  "C718m"  "C718s" 
##  [652] "C719m"  "C719s"  "C720m"  "C720s"  "C721m"  "C721s"  "C722m" 
##  [659] "C722s"  "C724m"  "C725m"  "C728m"  "C729m"  "C73m"   "C73s"  
##  [666] "C740m"  "C740s"  "C741m"  "C741s"  "C749m"  "C749s"  "C750m" 
##  [673] "C750s"  "C751m"  "C751s"  "C752s"  "C753s"  "C755m"  "C755s" 
##  [680] "C759m"  "C759s"  "D000m"  "D000s"  "D001m"  "D001s"  "D002m" 
##  [687] "D002s"  "D010m"  "D010s"  "D012m"  "D012s"  "D013m"  "D013s" 
##  [694] "D015m"  "D015s"  "D017m"  "D020m"  "D020s"  "D021m"  "D021s" 
##  [701] "D022m"  "D022s"  "D023m"  "D023s"  "D030m"  "D031m"  "D031s" 
##  [708] "D032m"  "D032s"  "D033m"  "D033s"  "D034m"  "D034s"  "D035m" 
##  [715] "D035s"  "D036m"  "D036s"  "D037m"  "D037s"  "D038m"  "D038s" 
##  [722] "D039m"  "D039s"  "D040m"  "D041m"  "D041s"  "D042m"  "D042s" 
##  [729] "D043m"  "D043s"  "D044m"  "D044s"  "D045m"  "D045s"  "D046m" 
##  [736] "D046s"  "D047m"  "D047s"  "D048m"  "D048s"  "D049m"  "D049s" 
##  [743] "D050m"  "D050s"  "D051m"  "D051s"  "D057m"  "D057s"  "D059m" 
##  [750] "D059s"  "D060m"  "D060s"  "D061m"  "D061s"  "D067m"  "D067s" 
##  [757] "D069m"  "D069s"  "D070m"  "D071m"  "D071s"  "D072m"  "D072s" 
##  [764] "D073m"  "D073s"  "D074m"  "D074s"  "D075m"  "D075s"  "D076m" 
##  [771] "D076s"  "D090m"  "D090s"  "D091m"  "D091s"  "D092m"  "D093m" 
##  [778] "D093s"  "D097m"  "D099m"  "D099s"  "D70m"   "D70s"   "D71m"  
##  [785] "D71s"   "D721m"  "D721s"  "D728m"  "D728s"  "D729m"  "D729s" 
##  [792] "D730s"  "D731m"  "D731s"  "D732m"  "D732s"  "D733m"  "D733s" 
##  [799] "D734m"  "D734s"  "D735m"  "D735s"  "D748s"  "D749s"  "D750m" 
##  [806] "D750s"  "D751m"  "D751s"  "D752m"  "D752s"  "D758m"  "D758s" 
##  [813] "D759m"  "D759s"  "D760m"  "D760s"  "D761m"  "D761s"  "D762s" 
##  [820] "D763m"  "D763s"  "D77s"   "D860m"  "D860s"  "D861m"  "D861s" 
##  [827] "D862m"  "D862s"  "D863m"  "D863s"  "D868m"  "D868s"  "D869m" 
##  [834] "D869s"  "D890m"  "D890s"  "D891m"  "D891s"  "D892m"  "D892s" 
##  [841] "D898m"  "D898s"  "D899m"  "D899s"  "E05s"   "E051m"  "E051s" 
##  [848] "E052m"  "E052s"  "E053m"  "E053s"  "E054s"  "E055m"  "E055s" 
##  [855] "E058m"  "E058s"  "E059m"  "E059s"  "E060m"  "E062m"  "E062s" 
##  [862] "E064m"  "E064s"  "E065m"  "E065s"  "E069m"  "E069s"  "E110m" 
##  [869] "E110s"  "E111m"  "E111s"  "E112m"  "E112s"  "E113m"  "E113s" 
##  [876] "E114m"  "E114s"  "E115m"  "E115s"  "E116m"  "E116s"  "E117m" 
##  [883] "E117s"  "E118m"  "E118s"  "E119m"  "E119s"  "E121s"  "E128s" 
##  [890] "E129s"  "E230m"  "E230s"  "E231m"  "E231s"  "E236m"  "E236s" 
##  [897] "E237m"  "E237s"  "E282m"  "E282s"  "E320m"  "E320s"  "E328m" 
##  [904] "E328s"  "E329m"  "E329s"  "E340m"  "E340s"  "E351s"  "E840m" 
##  [911] "E840s"  "E841m"  "E841s"  "E848m"  "E848s"  "E849m"  "E849s" 
##  [918] "G031m"  "G031s"  "G032m"  "G032s"  "G618m"  "G618s"  "G619m" 
##  [925] "G619s"  "G724m"  "G724s"  "H044m"  "H044s"  "H051m"  "H051s" 
##  [932] "H150m"  "H150s"  "H151m"  "H151s"  "H163m"  "H163s"  "H200m" 
##  [939] "H200s"  "H201m"  "H201s"  "H202m"  "H202s"  "H208m"  "H208s" 
##  [946] "H209m"  "H209s"  "H353m"  "H353s"  "H652m"  "H652s"  "H653m" 
##  [953] "H653s"  "H654m"  "H654s"  "H661m"  "H661s"  "H662m"  "H662s" 
##  [960] "H663m"  "H663s"  "H701m"  "H701s"  "H731m"  "H731s"  "H912m" 
##  [967] "H912s"  "I050m"  "I050s"  "I051m"  "I051s"  "I052m"  "I052s" 
##  [974] "I058m"  "I058s"  "I059m"  "I059s"  "I060m"  "I060s"  "I061m" 
##  [981] "I061s"  "I062m"  "I062s"  "I068s"  "I069m"  "I069s"  "I070m" 
##  [988] "I070s"  "I071m"  "I071s"  "I072s"  "I078m"  "I078s"  "I079s" 
##  [995] "I080m"  "I080s"  "I081m"  "I081s"  "I082m"  "I082s"  "I083m" 
## [1002] "I083s"  "I088m"  "I088s"  "I089m"  "I089s"  "I091m"  "I091s" 
## [1009] "I098m"  "I099m"  "I099s"  "I241m"  "I241s"  "I418s"  "I731m" 
## [1016] "I731s"  "I881m"  "I881s"  "J310m"  "J310s"  "J311m"  "J311s" 
## [1023] "J312m"  "J312s"  "J320m"  "J320s"  "J321m"  "J321s"  "J322m" 
## [1030] "J322s"  "J323m"  "J323s"  "J324m"  "J324s"  "J328m"  "J328s" 
## [1037] "J329m"  "J329s"  "J350m"  "J350s"  "J351m"  "J351s"  "J352m" 
## [1044] "J352s"  "J353m"  "J358m"  "J358s"  "J359m"  "J359s"  "J370m" 
## [1051] "J370s"  "J40m"   "J40s"   "J410m"  "J410s"  "J411m"  "J42m"  
## [1058] "J42s"   "J430m"  "J430s"  "J431m"  "J431s"  "J432m"  "J432s" 
## [1065] "J438m"  "J438s"  "J439m"  "J439s"  "J440m"  "J440s"  "J441m" 
## [1072] "J441s"  "J448m"  "J448s"  "J449m"  "J449s"  "J450m"  "J450s" 
## [1079] "J451m"  "J451s"  "J458m"  "J458s"  "J459m"  "J459s"  "J46m"  
## [1086] "J46s"   "J47m"   "J47s"   "J840m"  "J840s"  "J841m"  "J841s" 
## [1093] "J848m"  "J848s"  "J849m"  "J849s"  "K033m"  "K033s"  "K040m" 
## [1100] "K040s"  "K044m"  "K044s"  "K045m"  "K045s"  "K046m"  "K046s" 
## [1107] "K047m"  "K047s"  "K050m"  "K050s"  "K051m"  "K051s"  "K052m" 
## [1114] "K052s"  "K0522s" "K053m"  "K053s"  "K054m"  "K054s"  "K055m" 
## [1121] "K055s"  "K056m"  "K056s"  "K090m"  "K090s"  "K091m"  "K091s" 
## [1128] "K092m"  "K092s"  "K098m"  "K098s"  "K099m"  "K099s"  "K102m" 
## [1135] "K102s"  "K103m"  "K103s"  "K112m"  "K112s"  "K121m"  "K121s" 
## [1142] "K122m"  "K122s"  "K123m"  "K123s"  "K140m"  "K140s"  "K220m" 
## [1149] "K220s"  "K227m"  "K227s"  "K254m"  "K254s"  "K255m"  "K255s" 
## [1156] "K256m"  "K256s"  "K257m"  "K257s"  "K264m"  "K264s"  "K265m" 
## [1163] "K265s"  "K266m"  "K266s"  "K267m"  "K267s"  "K274m"  "K274s" 
## [1170] "K275m"  "K275s"  "K276m"  "K276s"  "K277m"  "K277s"  "K284m" 
## [1177] "K285m"  "K286m"  "K287m"  "K287s"  "K292m"  "K292s"  "K293m" 
## [1184] "K293s"  "K294m"  "K294s"  "K295m"  "K295s"  "K296m"  "K296s" 
## [1191] "K500m"  "K500s"  "K501m"  "K501s"  "K508m"  "K508s"  "K509m" 
## [1198] "K509s"  "K510m"  "K510s"  "K511m"  "K511s"  "K512m"  "K512s" 
## [1205] "K513m"  "K513s"  "K514m"  "K514s"  "K515m"  "K515s"  "K518m" 
## [1212] "K518s"  "K519m"  "K519s"  "K520m"  "K520s"  "K521m"  "K521s" 
## [1219] "K522m"  "K522s"  "K523m"  "K523s"  "K528m"  "K528s"  "K529m" 
## [1226] "K529s"  "K580m"  "K580s"  "K589m"  "K589s"  "K601m"  "K601s" 
## [1233] "K700m"  "K700s"  "K701m"  "K701s"  "K702m"  "K702s"  "K703m" 
## [1240] "K703s"  "K704m"  "K704s"  "K709m"  "K709s"  "K710m"  "K710s" 
## [1247] "K711m"  "K711s"  "K712m"  "K712s"  "K713s"  "K715m"  "K716m" 
## [1254] "K716s"  "K717m"  "K717s"  "K718m"  "K718s"  "K719m"  "K719s" 
## [1261] "K720m"  "K720s"  "K721m"  "K721s"  "K729m"  "K729s"  "K730m" 
## [1268] "K731m"  "K731s"  "K732m"  "K732s"  "K738m"  "K738s"  "K739m" 
## [1275] "K739s"  "K740m"  "K740s"  "K741m"  "K741s"  "K742m"  "K742s" 
## [1282] "K743m"  "K743s"  "K744m"  "K744s"  "K745m"  "K745s"  "K746m" 
## [1289] "K746s"  "K750m"  "K750s"  "K751s"  "K752m"  "K752s"  "K753m" 
## [1296] "K753s"  "K754m"  "K754s"  "K758m"  "K758s"  "K759m"  "K759s" 
## [1303] "K760m"  "K760s"  "K761m"  "K761s"  "K762m"  "K762s"  "K763m" 
## [1310] "K763s"  "K765s"  "K766m"  "K766s"  "K767m"  "K767s"  "K768m" 
## [1317] "K768s"  "K769m"  "K769s"  "K770m"  "K770s"  "K778s"  "K811m" 
## [1324] "K811s"  "K830m"  "K830s"  "K860m"  "K860s"  "K861m"  "K861s" 
## [1331] "K900m"  "K900s"  "L410m"  "L410s"  "M300m"  "M300s"  "M301m" 
## [1338] "M301s"  "M302m"  "M303m"  "M303s"  "M308m"  "M308s"  "M310m" 
## [1345] "M310s"  "M311m"  "M311s"  "M312s"  "M313m"  "M313s"  "M314m" 
## [1352] "M314s"  "M315m"  "M315s"  "M316m"  "M316s"  "M317m"  "M317s" 
## [1359] "M318m"  "M318s"  "M319m"  "M319s"  "M320m"  "M320s"  "M321m" 
## [1366] "M321s"  "M328m"  "M328s"  "M329m"  "M329s"  "M3290m" "M3290s"
## [1373] "M330s"  "M331m"  "M331s"  "M332m"  "M332s"  "M339m"  "M339s" 
## [1380] "M350m"  "M350s"  "M351m"  "M351s"  "M352m"  "M352s"  "M353m" 
## [1387] "M353s"  "M354m"  "M354s"  "M355s"  "M357m"  "M357s"  "M358m" 
## [1394] "M358s"  "M359m"  "M359s"  "M3599s" "M360m"  "M360s"  "M362s" 
## [1401] "M364s"  "M368s"  "M461m"  "M461s"  "M4616m" "M4616s" "M4617m"
## [1408] "M4617s" "M4618m" "M4618s" "M4619m" "M4619s" "M600m"  "M600s" 
## [1415] "M6000m" "M6000s" "M6001m" "M6001s" "M6002m" "M6005m" "M6005s"
## [1422] "M6006m" "M6006s" "M6008m" "M6008s" "M6009m" "M601s"  "M6018s"
## [1429] "M602m"  "M602s"  "M6021s" "M6023m" "M6023s" "M6024m" "M6024s"
## [1436] "M6025m" "M6026s" "M6027m" "M6028m" "M6028s" "M6029s" "M608m" 
## [1443] "M608s"  "M6080m" "M6082m" "M6085m" "M6086s" "M6088m" "M6089m"
## [1450] "M6089s" "M609m"  "M609s"  "M6090m" "M6090s" "M6091m" "M6091s"
## [1457] "M6092m" "M6092s" "M6093m" "M6095m" "M6095s" "M6096m" "M6096s"
## [1464] "M6097m" "M6098m" "M6098s" "M6099m" "M6099s" "M610m"  "M6106m"
## [1471] "M6114s" "M6115m" "M6125s" "M613s"  "M614m"  "M614s"  "M615m" 
## [1478] "M615s"  "M6152m" "M6155m" "M6155s" "M6156m" "M6156s" "M6159m"
## [1485] "M619m"  "M619s"  "M6191s" "M6192s" "M6195m" "M6196s" "M6198s"
## [1492] "M632s"  "M638s"  "M863m"  "M8630m" "N001m"  "N001s"  "N002s" 
## [1499] "N004s"  "N005m"  "N007s"  "N008m"  "N008s"  "N009m"  "N009s" 
## [1506] "N015s"  "N017m"  "N017s"  "N019m"  "N019s"  "N030m"  "N030s" 
## [1513] "N031m"  "N031s"  "N032m"  "N032s"  "N033m"  "N033s"  "N035m" 
## [1520] "N035s"  "N036m"  "N037m"  "N037s"  "N038m"  "N038s"  "N039m" 
## [1527] "N039s"  "N050m"  "N050s"  "N051m"  "N051s"  "N052m"  "N052s" 
## [1534] "N053m"  "N053s"  "N054m"  "N055m"  "N055s"  "N056m"  "N056s" 
## [1541] "N057m"  "N057s"  "N058m"  "N058s"  "N059m"  "N059s"  "N301m" 
## [1548] "N301s"  "N411m"  "N411s"  "N701m"  "N701s"  "N711m"  "N711s" 
## [1555] "N731m"  "N731s"  "N734s"  "N761m"  "N761s"

Create summary column

autoinflammatory_no_duplicate$ICD.autoinflammatory.raw <-
  apply(
    autoinflammatory_no_duplicate[,2:ncol(autoinflammatory_no_duplicate)] == 1,
    1,
    any)

autoinflammatory_no_duplicate$ICD.autoinflammatory <-
  as.integer(
    autoinflammatory_no_duplicate$ICD.autoinflammatory.raw
    )

autoinflammatory_reduced <- autoinflammatory_no_duplicate %>%
  select(IID, ICD.autoinflammatory)

Summary

summary(as.factor(autoinflammatory_reduced$ICD.autoinflammatory))
##      0      1 
## 352522 150097

Read in data

immunodeficiency <- fread(
  input = "data_raw/2019_05_29_ICD/ICD10.immunodeficiency.txt",
  header = TRUE,
  stringsAsFactors = F,
  data.table = F)

colnames(immunodeficiency)
##   [1] "IID"   "B200m" "IID"   "B201m" "IID"   "B202m" "B202s" "IID"  
##   [9] "B203m" "B203s" "IID"   "B204m" "B204s" "IID"   "B206m" "B206s"
##  [17] "IID"   "B207m" "B207s" "IID"   "B208m" "B208s" "IID"   "B210m"
##  [25] "B210s" "IID"   "B211m" "IID"   "B212m" "B212s" "IID"   "B213m"
##  [33] "B213s" "IID"   "B217m" "IID"   "B218m" "IID"   "B220m" "B220s"
##  [41] "IID"   "B221m" "B221s" "IID"   "B222m" "IID"   "B227m" "B227s"
##  [49] "IID"   "B230m" "B230s" "IID"   "B232m" "B232s" "IID"   "B238m"
##  [57] "B238s" "IID"   "B24m"  "B24s"  "IID"   "D71m"  "D71s"  "IID"  
##  [65] "D760m" "D760s" "IID"   "D761m" "D761s" "IID"   "D762s" "IID"  
##  [73] "D763m" "D763s" "IID"   "D800m" "D800s" "IID"   "D801m" "D801s"
##  [81] "IID"   "D802m" "D802s" "IID"   "D803m" "D803s" "IID"   "D804m"
##  [89] "D804s" "IID"   "D805m" "D805s" "IID"   "D806m" "D806s" "IID"  
##  [97] "D808m" "D808s" "IID"   "D809m" "D809s" "IID"   "D810m" "IID"  
## [105] "D811m" "D811s" "IID"   "D818m" "IID"   "D819m" "D819s" "IID"  
## [113] "D821m" "D821s" "IID"   "D823m" "D823s" "IID"   "D824m" "D824s"
## [121] "IID"   "D829m" "D829s" "IID"   "D830m" "D830s" "IID"   "D831m"
## [129] "D831s" "IID"   "D832m" "IID"   "D838m" "D838s" "IID"   "D839m"
## [137] "D839s" "IID"   "D840s" "IID"   "D841m" "D841s" "IID"   "D848m"
## [145] "D848s" "IID"   "D849m" "D849s"

Remove duplicate column

immunodeficiency_no_duplicate <- immunodeficiency[!duplicated(as.list(immunodeficiency))]

colnames(immunodeficiency_no_duplicate)
##  [1] "IID"   "B200m" "B201m" "B202m" "B202s" "B203m" "B203s" "B204m"
##  [9] "B204s" "B206m" "B206s" "B207m" "B207s" "B208m" "B208s" "B210m"
## [17] "B210s" "B211m" "B212m" "B212s" "B213m" "B213s" "B217m" "B218m"
## [25] "B220m" "B220s" "B221m" "B221s" "B222m" "B227m" "B227s" "B230m"
## [33] "B230s" "B232m" "B232s" "B238m" "B238s" "B24m"  "B24s"  "D71m" 
## [41] "D71s"  "D760m" "D760s" "D761m" "D761s" "D762s" "D763m" "D763s"
## [49] "D800m" "D800s" "D801m" "D801s" "D802m" "D802s" "D803m" "D803s"
## [57] "D804m" "D804s" "D805m" "D805s" "D806m" "D806s" "D808m" "D808s"
## [65] "D809m" "D809s" "D810m" "D811m" "D819m" "D819s" "D821m" "D821s"
## [73] "D823m" "D823s" "D824m" "D829m" "D829s" "D830m" "D830s" "D831m"
## [81] "D831s" "D838m" "D838s" "D839m" "D839s" "D840s" "D841m" "D841s"
## [89] "D848m" "D848s" "D849m" "D849s"

Create summary column

immunodeficiency_no_duplicate$ICD.immunodeficiency.raw <-
  apply(
    immunodeficiency_no_duplicate[,2:ncol(immunodeficiency_no_duplicate)] == 1,
    1,
    any)

immunodeficiency_no_duplicate$ICD.immunodeficiency <-
  as.integer(
    immunodeficiency_no_duplicate$ICD.immunodeficiency.raw
    )

immunodeficiency_reduced <- immunodeficiency_no_duplicate %>%
  select(IID, ICD.immunodeficiency)

Summary

summary(as.factor(immunodeficiency_reduced$ICD.immunodeficiency))
##      0      1 
## 502050    569

Read in data

memory <- fread(
  input = "data_raw/2019_05_29_ICD/ICD10.memory.txt",
  header = TRUE,
  stringsAsFactors = F,
  data.table = F)

colnames(memory)
##   [1] "IID"   "F000m" "F000s" "IID"   "F001m" "F001s" "IID"   "F002m"
##   [9] "F002s" "IID"   "F009m" "F009s" "IID"   "F010m" "F010s" "IID"  
##  [17] "F011m" "F011s" "IID"   "F012s" "IID"   "F013m" "IID"   "F019m"
##  [25] "F019s" "IID"   "F020m" "F020s" "IID"   "F023m" "F023s" "IID"  
##  [33] "F024s" "IID"   "F028m" "F028s" "IID"   "F03m"  "F03s"  "IID"  
##  [41] "F04s"  "IID"   "F050m" "F050s" "IID"   "F051m" "F051s" "IID"  
##  [49] "F058m" "F058s" "IID"   "F059m" "F059s" "IID"   "F06m"  "IID"  
##  [57] "F060m" "F060s" "IID"   "F062m" "F062s" "IID"   "F063m" "F063s"
##  [65] "IID"   "F064m" "F064s" "IID"   "F066s" "IID"   "F067m" "F067s"
##  [73] "IID"   "F068m" "F068s" "IID"   "F069m" "F069s" "IID"   "F070m"
##  [81] "F070s" "IID"   "F071m" "F071s" "IID"   "F072m" "F072s" "IID"  
##  [89] "F078m" "F078s" "IID"   "F079m" "F079s" "IID"   "F09m"  "F09s" 
##  [97] "IID"   "G10m"  "G10s"  "IID"   "G20m"  "G20s"  "IID"   "G210m"
## [105] "G210s" "IID"   "G211m" "G211s" "IID"   "G212s" "IID"   "G213s"
## [113] "IID"   "G214m" "G214s" "IID"   "G218m" "G218s" "IID"   "G219m"
## [121] "G219s" "IID"   "G231m" "G231s" "IID"   "G238m" "G238s" "IID"  
## [129] "G239s" "IID"   "G240m" "G240s" "IID"   "G241m" "G241s" "IID"  
## [137] "G242s" "IID"   "G243m" "G243s" "IID"   "G244m" "G244s" "IID"  
## [145] "G245m" "G245s" "IID"   "G248m" "G248s" "IID"   "G249m" "G249s"
## [153] "IID"   "G250m" "G250s" "IID"   "G251m" "G251s" "IID"   "G252m"
## [161] "G252s" "IID"   "G253m" "G253s" "IID"   "G255m" "G255s" "IID"  
## [169] "G258m" "G258s" "IID"   "G259m" "G259s" "IID"   "G300m" "G300s"
## [177] "IID"   "G301m" "G301s" "IID"   "G308m" "G308s" "IID"   "G309m"
## [185] "G309s" "IID"   "G310m" "G310s" "IID"   "G311s" "IID"   "G312m"
## [193] "G312s" "IID"   "G318m" "G318s" "IID"   "G319m" "G319s" "IID"  
## [201] "G320m" "G320s" "IID"   "G328m" "G328s"

Remove duplicate column

memory_no_duplicate <- memory[!duplicated(as.list(memory))]

colnames(memory_no_duplicate)
##   [1] "IID"   "F000m" "F000s" "F001m" "F001s" "F002m" "F002s" "F009m"
##   [9] "F009s" "F010m" "F010s" "F011m" "F011s" "F012s" "F013m" "F019m"
##  [17] "F019s" "F020m" "F020s" "F023m" "F023s" "F024s" "F028m" "F028s"
##  [25] "F03m"  "F03s"  "F04s"  "F050m" "F050s" "F051m" "F051s" "F058m"
##  [33] "F058s" "F059m" "F059s" "F06m"  "F060m" "F060s" "F062m" "F062s"
##  [41] "F063m" "F063s" "F064m" "F064s" "F066s" "F067m" "F067s" "F068m"
##  [49] "F068s" "F069m" "F069s" "F070m" "F070s" "F071m" "F071s" "F072m"
##  [57] "F072s" "F078m" "F078s" "F079m" "F079s" "F09m"  "F09s"  "G10m" 
##  [65] "G10s"  "G20m"  "G20s"  "G210m" "G210s" "G211m" "G211s" "G212s"
##  [73] "G213s" "G214m" "G214s" "G218m" "G218s" "G219m" "G219s" "G231m"
##  [81] "G231s" "G238m" "G238s" "G239s" "G240m" "G240s" "G241m" "G241s"
##  [89] "G242s" "G243m" "G243s" "G244m" "G244s" "G245m" "G245s" "G248m"
##  [97] "G248s" "G249m" "G249s" "G250m" "G250s" "G251m" "G251s" "G252m"
## [105] "G252s" "G253m" "G253s" "G255m" "G255s" "G258m" "G258s" "G259m"
## [113] "G259s" "G300m" "G300s" "G301m" "G301s" "G308m" "G308s" "G309m"
## [121] "G309s" "G310m" "G310s" "G311s" "G312m" "G312s" "G318m" "G318s"
## [129] "G319m" "G319s" "G320m" "G320s" "G328m" "G328s"

Create summary column

memory_no_duplicate$ICD.memory.raw <-
  apply(
    memory_no_duplicate[,2:ncol(memory_no_duplicate)] == 1,
    1,
    any)

memory_no_duplicate$ICD.memory <-
  as.integer(
    memory_no_duplicate$ICD.memory.raw
    )

memory_reduced <- memory_no_duplicate %>%
  select(IID, ICD.memory)

Summary

summary(as.factor(memory_reduced$ICD.memory))
##      0      1 
## 497863   4756

Read in data

metabolic <- fread(
  input = "data_raw/2019_05_29_ICD/ICD10.metabolic.txt",
  header = TRUE,
  stringsAsFactors = F,
  data.table = F)

colnames(metabolic)
##   [1] "IID"   "E011m" "E011s" "IID"   "E018s" "IID"   "E02m"  "E02s" 
##   [9] "IID"   "E030m" "E030s" "IID"   "E031s" "IID"   "E032m" "E032s"
##  [17] "IID"   "E033s" "IID"   "E034m" "IID"   "E035s" "IID"   "E038m"
##  [25] "E038s" "IID"   "E039m" "E039s" "IID"   "E040m" "E040s" "IID"  
##  [33] "E041m" "E041s" "IID"   "E042m" "E042s" "IID"   "E048m" "E048s"
##  [41] "IID"   "E049m" "E049s" "IID"   "E05s"  "IID"   "E050m" "E050s"
##  [49] "IID"   "E051m" "E051s" "IID"   "E052m" "E052s" "IID"   "E053m"
##  [57] "E053s" "IID"   "E054s" "IID"   "E055m" "E055s" "IID"   "E058m"
##  [65] "E058s" "IID"   "E059m" "E059s" "IID"   "E060m" "IID"   "E061m"
##  [73] "E061s" "IID"   "E062m" "E062s" "IID"   "E063m" "E063s" "IID"  
##  [81] "E064m" "E064s" "IID"   "E065m" "E065s" "IID"   "E069m" "E069s"
##  [89] "IID"   "E070m" "E070s" "IID"   "E071s" "IID"   "E078m" "E078s"
##  [97] "IID"   "E079m" "E079s" "IID"   "E100m" "E100s" "IID"   "E101m"
## [105] "E101s" "IID"   "E102m" "E102s" "IID"   "E103m" "E103s" "IID"  
## [113] "E104m" "E104s" "IID"   "E105m" "E105s" "IID"   "E106m" "E106s"
## [121] "IID"   "E107m" "E107s" "IID"   "E108m" "E108s" "IID"   "E109m"
## [129] "E109s" "IID"   "E110m" "E110s" "IID"   "E111m" "E111s" "IID"  
## [137] "E112m" "E112s" "IID"   "E113m" "E113s" "IID"   "E114m" "E114s"
## [145] "IID"   "E115m" "E115s" "IID"   "E116m" "E116s" "IID"   "E117m"
## [153] "E117s" "IID"   "E118m" "E118s" "IID"   "E119m" "E119s" "IID"  
## [161] "E121s" "IID"   "E128s" "IID"   "E129s" "IID"   "E131m" "E131s"
## [169] "IID"   "E132s" "IID"   "E133m" "E133s" "IID"   "E135s" "IID"  
## [177] "E136s" "IID"   "E137s" "IID"   "E138m" "E138s" "IID"   "E139m"
## [185] "E139s" "IID"   "E140m" "E140s" "IID"   "E141m" "E141s" "IID"  
## [193] "E142m" "E142s" "IID"   "E143m" "E143s" "IID"   "E144m" "E144s"
## [201] "IID"   "E145m" "E145s" "IID"   "E146m" "E146s" "IID"   "E147m"
## [209] "E147s" "IID"   "E148m" "E148s" "IID"   "E149m" "E149s" "IID"  
## [217] "E15m"  "E15s"  "IID"   "E160m" "E160s" "IID"   "E161m" "E161s"
## [225] "IID"   "E162m" "E162s" "IID"   "E163s" "IID"   "E164m" "E164s"
## [233] "IID"   "E168s" "IID"   "E169m" "E169s" "IID"   "E201m" "E201s"
## [241] "IID"   "E208s" "IID"   "E209m" "E209s" "IID"   "E210m" "E210s"
## [249] "IID"   "E211m" "E211s" "IID"   "E212m" "E212s" "IID"   "E213m"
## [257] "E213s" "IID"   "E214m" "E214s" "IID"   "E215m" "E215s" "IID"  
## [265] "E220m" "E220s" "IID"   "E221m" "E221s" "IID"   "E222m" "E222s"
## [273] "IID"   "E228m" "E228s" "IID"   "E229m" "E229s" "IID"   "E230m"
## [281] "E230s" "IID"   "E231m" "E231s" "IID"   "E232m" "E232s" "IID"  
## [289] "E233m" "E233s" "IID"   "E236m" "E236s" "IID"   "E237m" "E237s"
## [297] "IID"   "E240m" "E240s" "IID"   "E241m" "E241s" "IID"   "E242m"
## [305] "E242s" "IID"   "E243s" "IID"   "E248m" "E248s" "IID"   "E249m"
## [313] "E249s" "IID"   "E250m" "E250s" "IID"   "E258m" "IID"   "E259m"
## [321] "E259s" "IID"   "E260m" "E260s" "IID"   "E261s" "IID"   "E268s"
## [329] "IID"   "E269m" "E269s" "IID"   "E270s" "IID"   "E271m" "E271s"
## [337] "IID"   "E272m" "E272s" "IID"   "E273m" "E273s" "IID"   "E274m"
## [345] "E274s" "IID"   "E275m" "E275s" "IID"   "E278m" "E278s" "IID"  
## [353] "E279m" "E279s" "IID"   "E281m" "IID"   "E282m" "E282s" "IID"  
## [361] "E283m" "E283s" "IID"   "E288m" "E288s" "IID"   "E289m" "IID"  
## [369] "E290m" "E290s" "IID"   "E291m" "E291s" "IID"   "E298m" "E298s"
## [377] "IID"   "E299m" "E299s" "IID"   "E300s" "IID"   "E309s" "IID"  
## [385] "E310m" "E310s" "IID"   "E318m" "IID"   "E319s" "IID"   "E320m"
## [393] "E320s" "IID"   "E328m" "E328s" "IID"   "E329m" "E329s" "IID"  
## [401] "E340m" "E340s" "IID"   "E343s" "IID"   "E345m" "E345s" "IID"  
## [409] "E348m" "E348s" "IID"   "E349m" "E349s" "IID"   "E351s" "IID"  
## [417] "E700s" "IID"   "E701s" "IID"   "E702m" "E702s" "IID"   "E703m"
## [425] "E703s" "IID"   "E708s" "IID"   "E709s" "IID"   "E711m" "E711s"
## [433] "IID"   "E713m" "E713s" "IID"   "E720m" "E720s" "IID"   "E721m"
## [441] "E721s" "IID"   "E722m" "E722s" "IID"   "E724s" "IID"   "E725m"
## [449] "E725s" "IID"   "E731m" "IID"   "E738s" "IID"   "E739m" "E739s"
## [457] "IID"   "E740m" "E740s" "IID"   "E742s" "IID"   "E743m" "E743s"
## [465] "IID"   "E744s" "IID"   "E748s" "IID"   "E749m" "IID"   "E750s"
## [473] "IID"   "E752m" "E752s" "IID"   "E753s" "IID"   "E754s" "IID"  
## [481] "E755m" "E755s" "IID"   "E756s" "IID"   "E760s" "IID"   "E761s"
## [489] "IID"   "E762m" "E762s" "IID"   "E778m" "E778s" "IID"   "E780m"
## [497] "E780s" "IID"   "E781m" "E781s" "IID"   "E782m" "E782s" "IID"  
## [505] "E783s" "IID"   "E784m" "E784s" "IID"   "E785m" "E785s" "IID"  
## [513] "E786s" "IID"   "E788s" "IID"   "E789m" "E789s" "IID"   "E790s"
## [521] "IID"   "E791s" "IID"   "E798s" "IID"   "E800s" "IID"   "E801m"
## [529] "E801s" "IID"   "E802m" "E802s" "IID"   "E804m" "E804s" "IID"  
## [537] "E806m" "E806s" "IID"   "E807s" "IID"   "E830m" "E830s" "IID"  
## [545] "E831m" "E831s" "IID"   "E832m" "E832s" "IID"   "E833m" "E833s"
## [553] "IID"   "E834m" "E834s" "IID"   "E835m" "E835s" "IID"   "E838s"
## [561] "IID"   "E839m" "E839s" "IID"   "E840m" "E840s" "IID"   "E841m"
## [569] "E841s" "IID"   "E848m" "E848s" "IID"   "E849m" "E849s" "IID"  
## [577] "E850m" "E850s" "IID"   "E851m" "E851s" "IID"   "E852s" "IID"  
## [585] "E853m" "E853s" "IID"   "E854m" "E854s" "IID"   "E858m" "E858s"
## [593] "IID"   "E859m" "E859s" "IID"   "E86m"  "E86s"  "IID"   "E870m"
## [601] "E870s" "IID"   "E871m" "E871s" "IID"   "E872m" "E872s" "IID"  
## [609] "E873m" "E873s" "IID"   "E874s" "IID"   "E875m" "E875s" "IID"  
## [617] "E876m" "E876s" "IID"   "E877m" "E877s" "IID"   "E878m" "E878s"
## [625] "IID"   "E880m" "E880s" "IID"   "E881m" "E881s" "IID"   "E882m"
## [633] "E882s" "IID"   "E883m" "E883s" "IID"   "E888m" "E888s" "IID"  
## [641] "E889m" "E889s" "IID"   "E890m" "E890s" "IID"   "E891m" "E891s"
## [649] "IID"   "E892m" "E892s" "IID"   "E893m" "E893s" "IID"   "E894m"
## [657] "E894s" "IID"   "E895m" "E895s" "IID"   "E896m" "E896s" "IID"  
## [665] "E898m" "E898s" "IID"   "E899m" "E899s"

Remove duplicate column

metabolic_no_duplicate <- metabolic[!duplicated(as.list(metabolic))]

colnames(metabolic_no_duplicate)
##   [1] "IID"   "E011m" "E011s" "E018s" "E02m"  "E02s"  "E030m" "E030s"
##   [9] "E031s" "E032m" "E032s" "E033s" "E034m" "E035s" "E038m" "E038s"
##  [17] "E039m" "E039s" "E040m" "E040s" "E041m" "E041s" "E042m" "E042s"
##  [25] "E048m" "E048s" "E049m" "E049s" "E05s"  "E050m" "E050s" "E051m"
##  [33] "E051s" "E052m" "E052s" "E053m" "E053s" "E054s" "E055m" "E055s"
##  [41] "E058m" "E058s" "E059m" "E059s" "E060m" "E061m" "E061s" "E062m"
##  [49] "E062s" "E063m" "E063s" "E064m" "E064s" "E065m" "E065s" "E069m"
##  [57] "E069s" "E070m" "E070s" "E071s" "E078m" "E078s" "E079m" "E079s"
##  [65] "E100m" "E100s" "E101m" "E101s" "E102m" "E102s" "E103m" "E103s"
##  [73] "E104m" "E104s" "E105m" "E105s" "E106m" "E106s" "E107m" "E107s"
##  [81] "E108m" "E108s" "E109m" "E109s" "E110m" "E110s" "E111m" "E111s"
##  [89] "E112m" "E112s" "E113m" "E113s" "E114m" "E114s" "E115m" "E115s"
##  [97] "E116m" "E116s" "E117m" "E117s" "E118m" "E118s" "E119m" "E119s"
## [105] "E121s" "E128s" "E129s" "E131m" "E131s" "E132s" "E133m" "E133s"
## [113] "E135s" "E136s" "E137s" "E138m" "E138s" "E139m" "E139s" "E140m"
## [121] "E140s" "E141m" "E141s" "E142m" "E142s" "E143m" "E143s" "E144m"
## [129] "E144s" "E145m" "E145s" "E146m" "E146s" "E147m" "E147s" "E148m"
## [137] "E148s" "E149m" "E149s" "E15m"  "E15s"  "E160m" "E160s" "E161m"
## [145] "E161s" "E162m" "E162s" "E163s" "E164m" "E164s" "E168s" "E169m"
## [153] "E169s" "E201m" "E201s" "E208s" "E209m" "E209s" "E210m" "E210s"
## [161] "E211m" "E211s" "E212m" "E212s" "E213m" "E213s" "E214m" "E214s"
## [169] "E215m" "E215s" "E220m" "E220s" "E221m" "E221s" "E222m" "E222s"
## [177] "E228m" "E228s" "E229m" "E229s" "E230m" "E230s" "E231m" "E231s"
## [185] "E232m" "E232s" "E233m" "E233s" "E236m" "E236s" "E237m" "E237s"
## [193] "E240m" "E240s" "E241m" "E241s" "E242m" "E242s" "E243s" "E248m"
## [201] "E248s" "E249m" "E249s" "E250m" "E250s" "E258m" "E259m" "E259s"
## [209] "E260m" "E260s" "E261s" "E268s" "E269m" "E269s" "E270s" "E271m"
## [217] "E271s" "E272m" "E272s" "E273m" "E273s" "E274m" "E274s" "E275m"
## [225] "E275s" "E278m" "E278s" "E279m" "E279s" "E281m" "E282m" "E282s"
## [233] "E283m" "E283s" "E288m" "E288s" "E289m" "E290m" "E290s" "E291m"
## [241] "E291s" "E298m" "E298s" "E299m" "E299s" "E300s" "E309s" "E310m"
## [249] "E310s" "E318m" "E319s" "E320m" "E320s" "E328m" "E328s" "E329m"
## [257] "E329s" "E340m" "E340s" "E343s" "E345m" "E345s" "E348m" "E348s"
## [265] "E349m" "E349s" "E351s" "E700s" "E701s" "E702m" "E702s" "E703m"
## [273] "E703s" "E708s" "E709s" "E711m" "E711s" "E713m" "E713s" "E720m"
## [281] "E720s" "E721m" "E721s" "E722m" "E722s" "E724s" "E725m" "E725s"
## [289] "E731m" "E738s" "E739m" "E739s" "E740m" "E740s" "E742s" "E743m"
## [297] "E743s" "E744s" "E748s" "E749m" "E750s" "E752m" "E752s" "E753s"
## [305] "E754s" "E755m" "E755s" "E756s" "E760s" "E761s" "E762m" "E762s"
## [313] "E778m" "E778s" "E780m" "E780s" "E781m" "E781s" "E782m" "E782s"
## [321] "E783s" "E784m" "E784s" "E785m" "E785s" "E786s" "E788s" "E789m"
## [329] "E789s" "E790s" "E791s" "E798s" "E800s" "E801m" "E801s" "E802m"
## [337] "E802s" "E804m" "E804s" "E806m" "E806s" "E807s" "E830m" "E830s"
## [345] "E831m" "E831s" "E832m" "E832s" "E833m" "E833s" "E834m" "E834s"
## [353] "E835m" "E835s" "E838s" "E839m" "E839s" "E840m" "E840s" "E841m"
## [361] "E841s" "E848m" "E848s" "E849m" "E849s" "E850m" "E850s" "E851m"
## [369] "E851s" "E852s" "E853m" "E853s" "E854m" "E854s" "E858m" "E858s"
## [377] "E859m" "E859s" "E86m"  "E86s"  "E870m" "E870s" "E871m" "E871s"
## [385] "E872m" "E872s" "E873m" "E873s" "E874s" "E875m" "E875s" "E876m"
## [393] "E876s" "E877m" "E877s" "E878m" "E878s" "E880m" "E880s" "E881m"
## [401] "E881s" "E882m" "E882s" "E883m" "E883s" "E888m" "E888s" "E889m"
## [409] "E889s" "E890m" "E890s" "E891m" "E891s" "E892m" "E892s" "E893m"
## [417] "E893s" "E894m" "E894s" "E895m" "E895s" "E896m" "E896s" "E898m"
## [425] "E898s" "E899m" "E899s"

Create summary column

metabolic_no_duplicate$ICD.metabolic.raw <-
  apply(
    metabolic_no_duplicate[,2:ncol(metabolic_no_duplicate)] == 1,
    1,
    any)

metabolic_no_duplicate$ICD.metabolic <-
  as.integer(
    metabolic_no_duplicate$ICD.metabolic.raw
    )

metabolic_reduced <- metabolic_no_duplicate %>%
  select(IID, ICD.metabolic)

Summary

summary(as.factor(metabolic_reduced$ICD.metabolic))
##      0      1 
## 418254  84365

Read in data

psychiatric <- fread(
  input = "data_raw/2019_05_29_ICD/ICD10.psychiatric.txt",
  header = TRUE,
  stringsAsFactors = F,
  data.table = F)

colnames(psychiatric)
##   [1] "IID"   "F000m" "F000s" "IID"   "F001m" "F001s" "IID"   "F002m"
##   [9] "F002s" "IID"   "F009m" "F009s" "IID"   "F010m" "F010s" "IID"  
##  [17] "F011m" "F011s" "IID"   "F012s" "IID"   "F013m" "IID"   "F019m"
##  [25] "F019s" "IID"   "F020m" "F020s" "IID"   "F023m" "F023s" "IID"  
##  [33] "F024s" "IID"   "F028m" "F028s" "IID"   "F03m"  "F03s"  "IID"  
##  [41] "F04s"  "IID"   "F050m" "F050s" "IID"   "F051m" "F051s" "IID"  
##  [49] "F058m" "F058s" "IID"   "F059m" "F059s" "IID"   "F06m"  "IID"  
##  [57] "F060m" "F060s" "IID"   "F062m" "F062s" "IID"   "F063m" "F063s"
##  [65] "IID"   "F064m" "F064s" "IID"   "F066s" "IID"   "F067m" "F067s"
##  [73] "IID"   "F068m" "F068s" "IID"   "F069m" "F069s" "IID"   "F070m"
##  [81] "F070s" "IID"   "F071m" "F071s" "IID"   "F072m" "F072s" "IID"  
##  [89] "F078m" "F078s" "IID"   "F079m" "F079s" "IID"   "F09m"  "F09s" 
##  [97] "IID"   "F10m"  "F10s"  "IID"   "F100m" "F100s" "IID"   "F101m"
## [105] "F101s" "IID"   "F102m" "F102s" "IID"   "F103m" "F103s" "IID"  
## [113] "F104m" "F104s" "IID"   "F105m" "F105s" "IID"   "F106m" "F106s"
## [121] "IID"   "F107m" "F107s" "IID"   "F108m" "F108s" "IID"   "F109m"
## [129] "F109s" "IID"   "F110m" "F110s" "IID"   "F111s" "IID"   "F112m"
## [137] "F112s" "IID"   "F113m" "F113s" "IID"   "F114m" "IID"   "F115m"
## [145] "F115s" "IID"   "F117m" "IID"   "F119s" "IID"   "F120m" "F120s"
## [153] "IID"   "F121m" "F121s" "IID"   "F122m" "F122s" "IID"   "F125m"
## [161] "IID"   "F128s" "IID"   "F129s" "IID"   "F130s" "IID"   "F131s"
## [169] "IID"   "F132m" "F132s" "IID"   "F133m" "F133s" "IID"   "F134s"
## [177] "IID"   "F139s" "IID"   "F140s" "IID"   "F141m" "F141s" "IID"  
## [185] "F142m" "F142s" "IID"   "F145s" "IID"   "F149s" "IID"   "F150m"
## [193] "F150s" "IID"   "F151m" "F151s" "IID"   "F152s" "IID"   "F153s"
## [201] "IID"   "F155m" "IID"   "F158s" "IID"   "F159s" "IID"   "F161s"
## [209] "IID"   "F162m" "F162s" "IID"   "F163m" "IID"   "F165m" "IID"  
## [217] "F168s" "IID"   "F169m" "IID"   "F170m" "F170s" "IID"   "F171m"
## [225] "F171s" "IID"   "F172m" "F172s" "IID"   "F173m" "F173s" "IID"  
## [233] "F174s" "IID"   "F179s" "IID"   "F181s" "IID"   "F182s" "IID"  
## [241] "F185m" "IID"   "F189s" "IID"   "F190s" "IID"   "F191m" "F191s"
## [249] "IID"   "F192m" "F192s" "IID"   "F193m" "F193s" "IID"   "F194s"
## [257] "IID"   "F195m" "F195s" "IID"   "F198m" "F198s" "IID"   "F199m"
## [265] "F199s" "IID"   "F20m"  "F20s"  "IID"   "F200m" "F200s" "IID"  
## [273] "F201m" "IID"   "F202m" "F202s" "IID"   "F203m" "IID"   "F204m"
## [281] "F204s" "IID"   "F205m" "F205s" "IID"   "F206m" "F206s" "IID"  
## [289] "F208m" "F208s" "IID"   "F209m" "F209s" "IID"   "F21m"  "F21s" 
## [297] "IID"   "F220m" "F220s" "IID"   "F228m" "F228s" "IID"   "F229m"
## [305] "F229s" "IID"   "F23s"  "IID"   "F230m" "F230s" "IID"   "F231m"
## [313] "F231s" "IID"   "F232m" "IID"   "F233m" "F233s" "IID"   "F238m"
## [321] "IID"   "F239m" "F239s" "IID"   "F24m"  "IID"   "F250m" "F250s"
## [329] "IID"   "F251m" "F251s" "IID"   "F252m" "F252s" "IID"   "F258m"
## [337] "F258s" "IID"   "F259m" "F259s" "IID"   "F28m"  "F28s"  "IID"  
## [345] "F29m"  "F29s"  "IID"   "F300m" "F300s" "IID"   "F301m" "F301s"
## [353] "IID"   "F302m" "F302s" "IID"   "F308m" "F308s" "IID"   "F309m"
## [361] "F309s" "IID"   "F310m" "F310s" "IID"   "F311m" "F311s" "IID"  
## [369] "F312m" "F312s" "IID"   "F313m" "F313s" "IID"   "F314m" "F314s"
## [377] "IID"   "F315m" "F315s" "IID"   "F316m" "F316s" "IID"   "F317m"
## [385] "F317s" "IID"   "F318m" "F318s" "IID"   "F319m" "F319s" "IID"  
## [393] "F32m"  "IID"   "F320m" "F320s" "IID"   "F321m" "F321s" "IID"  
## [401] "F322m" "F322s" "IID"   "F323m" "F323s" "IID"   "F328m" "F328s"
## [409] "IID"   "F329m" "F329s" "IID"   "F330m" "F330s" "IID"   "F331m"
## [417] "F331s" "IID"   "F332m" "F332s" "IID"   "F333m" "F333s" "IID"  
## [425] "F334m" "F334s" "IID"   "F338m" "F338s" "IID"   "F339m" "F339s"
## [433] "IID"   "F340m" "F340s" "IID"   "F341m" "F341s" "IID"   "F348m"
## [441] "F348s" "IID"   "F349s" "IID"   "F380m" "F380s" "IID"   "F381s"
## [449] "IID"   "F388m" "F388s" "IID"   "F39m"  "F39s"  "IID"   "F400m"
## [457] "F400s" "IID"   "F401m" "F401s" "IID"   "F402m" "F402s" "IID"  
## [465] "F408m" "F408s" "IID"   "F409s" "IID"   "F410m" "F410s" "IID"  
## [473] "F411m" "F411s" "IID"   "F412m" "F412s" "IID"   "F413m" "F413s"
## [481] "IID"   "F418m" "F418s" "IID"   "F419m" "F419s" "IID"   "F420m"
## [489] "F420s" "IID"   "F421m" "F421s" "IID"   "F422m" "F422s" "IID"  
## [497] "F428m" "F428s" "IID"   "F429m" "F429s" "IID"   "F430m" "F430s"
## [505] "IID"   "F431m" "F431s" "IID"   "F432m" "F432s" "IID"   "F438m"
## [513] "F438s" "IID"   "F439m" "F439s" "IID"   "F440m" "F440s" "IID"  
## [521] "F441m" "F441s" "IID"   "F443m" "F443s" "IID"   "F444m" "F444s"
## [529] "IID"   "F445m" "F445s" "IID"   "F446m" "F446s" "IID"   "F447m"
## [537] "IID"   "F448m" "F448s" "IID"   "F449m" "F449s" "IID"   "F450m"
## [545] "F450s" "IID"   "F451s" "IID"   "F452m" "F452s" "IID"   "F453m"
## [553] "F453s" "IID"   "F454m" "F454s" "IID"   "F458m" "F458s" "IID"  
## [561] "F459m" "F459s" "IID"   "F480m" "F480s" "IID"   "F481s" "IID"  
## [569] "F488m" "F488s" "IID"   "F489m" "F489s" "IID"   "F500m" "F500s"
## [577] "IID"   "F501m" "F501s" "IID"   "F502m" "F502s" "IID"   "F505m"
## [585] "F505s" "IID"   "F508m" "F508s" "IID"   "F509m" "F509s" "IID"  
## [593] "F510m" "F510s" "IID"   "F511m" "F511s" "IID"   "F512s" "IID"  
## [601] "F513m" "F513s" "IID"   "F514m" "F514s" "IID"   "F515m" "F515s"
## [609] "IID"   "F519m" "F519s" "IID"   "F520m" "F520s" "IID"   "F521s"
## [617] "IID"   "F522m" "F522s" "IID"   "F524m" "F524s" "IID"   "F526m"
## [625] "F526s" "IID"   "F527m" "F527s" "IID"   "F528m" "IID"   "F529m"
## [633] "F529s" "IID"   "F530m" "F530s" "IID"   "F531m" "F531s" "IID"  
## [641] "F538s" "IID"   "F539m" "IID"   "F54m"  "F54s"  "IID"   "F55s" 
## [649] "IID"   "F59m"  "F59s"  "IID"   "F600m" "F600s" "IID"   "F601m"
## [657] "F601s" "IID"   "F602m" "F602s" "IID"   "F603m" "F603s" "IID"  
## [665] "F604m" "F604s" "IID"   "F605m" "F605s" "IID"   "F606m" "F606s"
## [673] "IID"   "F607m" "F607s" "IID"   "F608m" "F608s" "IID"   "F609m"
## [681] "F609s" "IID"   "F61m"  "F61s"  "IID"   "F620m" "F620s" "IID"  
## [689] "F621m" "F621s" "IID"   "F628m" "F628s" "IID"   "F629m" "F629s"
## [697] "IID"   "F630m" "F630s" "IID"   "F631s" "IID"   "F633m" "F633s"
## [705] "IID"   "F638s" "IID"   "F639s" "IID"   "F640m" "F640s" "IID"  
## [713] "F641s" "IID"   "F648m" "IID"   "F649s" "IID"   "F650s" "IID"  
## [721] "F659s" "IID"   "F660s" "IID"   "F661s" "IID"   "F662s" "IID"  
## [729] "F669s" "IID"   "F680s" "IID"   "F681m" "F681s" "IID"   "F69m" 
## [737] "F69s"  "IID"   "F700m" "F700s" "IID"   "F701m" "IID"   "F708m"
## [745] "IID"   "F709m" "F709s" "IID"   "F711s" "IID"   "F719s" "IID"  
## [753] "F729s" "IID"   "F789m" "F789s" "IID"   "F790s" "IID"   "F799s"
## [761] "IID"   "F800m" "F800s" "IID"   "F801m" "F801s" "IID"   "F802m"
## [769] "F802s" "IID"   "F803s" "IID"   "F809s" "IID"   "F810m" "F810s"
## [777] "IID"   "F812s" "IID"   "F819m" "F819s" "IID"   "F82m"  "F82s" 
## [785] "IID"   "F840s" "IID"   "F841m" "F841s" "IID"   "F843s" "IID"  
## [793] "F845m" "F845s" "IID"   "F89s"  "IID"   "F900s" "IID"   "F911s"
## [801] "IID"   "F918m" "F918s" "IID"   "F919m" "F919s" "IID"   "F920s"
## [809] "IID"   "F929s" "IID"   "F940s" "IID"   "F950s" "IID"   "F951m"
## [817] "F951s" "IID"   "F952m" "F952s" "IID"   "F959s" "IID"   "F981m"
## [825] "IID"   "F985m" "F985s" "IID"   "F988s" "IID"   "F99m"  "F99s"

Remove duplicate column

psychiatric_no_duplicate <- psychiatric[!duplicated(as.list(psychiatric))]

colnames(psychiatric_no_duplicate)
##   [1] "IID"   "F000m" "F000s" "F001m" "F001s" "F002m" "F002s" "F009m"
##   [9] "F009s" "F010m" "F010s" "F011m" "F011s" "F012s" "F013m" "F019m"
##  [17] "F019s" "F020m" "F020s" "F023m" "F023s" "F024s" "F028m" "F028s"
##  [25] "F03m"  "F03s"  "F04s"  "F050m" "F050s" "F051m" "F051s" "F058m"
##  [33] "F058s" "F059m" "F059s" "F06m"  "F060m" "F060s" "F062m" "F062s"
##  [41] "F063m" "F063s" "F064m" "F064s" "F066s" "F067m" "F067s" "F068m"
##  [49] "F068s" "F069m" "F069s" "F070m" "F070s" "F071m" "F071s" "F072m"
##  [57] "F072s" "F078m" "F078s" "F079m" "F079s" "F09m"  "F09s"  "F10m" 
##  [65] "F10s"  "F100m" "F100s" "F101m" "F101s" "F102m" "F102s" "F103m"
##  [73] "F103s" "F104m" "F104s" "F105m" "F105s" "F106m" "F106s" "F107m"
##  [81] "F107s" "F108m" "F108s" "F109m" "F109s" "F110m" "F110s" "F111s"
##  [89] "F112m" "F112s" "F113m" "F113s" "F114m" "F115m" "F115s" "F117m"
##  [97] "F119s" "F120m" "F120s" "F121m" "F121s" "F122m" "F122s" "F125m"
## [105] "F128s" "F129s" "F130s" "F131s" "F132m" "F132s" "F133m" "F133s"
## [113] "F134s" "F139s" "F140s" "F141m" "F141s" "F142m" "F142s" "F145s"
## [121] "F149s" "F150m" "F150s" "F151m" "F151s" "F152s" "F153s" "F155m"
## [129] "F158s" "F159s" "F161s" "F162m" "F162s" "F163m" "F165m" "F168s"
## [137] "F170m" "F170s" "F171m" "F171s" "F172m" "F172s" "F173m" "F173s"
## [145] "F174s" "F179s" "F181s" "F182s" "F185m" "F189s" "F190s" "F191m"
## [153] "F191s" "F192m" "F192s" "F193m" "F193s" "F194s" "F195m" "F195s"
## [161] "F198m" "F198s" "F199m" "F199s" "F20m"  "F20s"  "F200m" "F200s"
## [169] "F201m" "F202m" "F202s" "F203m" "F204m" "F204s" "F205m" "F205s"
## [177] "F206m" "F206s" "F208m" "F208s" "F209m" "F209s" "F21m"  "F21s" 
## [185] "F220m" "F220s" "F228m" "F228s" "F229m" "F229s" "F23s"  "F230m"
## [193] "F230s" "F231m" "F231s" "F232m" "F233m" "F233s" "F238m" "F239m"
## [201] "F239s" "F24m"  "F250m" "F250s" "F251m" "F251s" "F252m" "F252s"
## [209] "F258m" "F258s" "F259m" "F259s" "F28m"  "F28s"  "F29m"  "F29s" 
## [217] "F300m" "F300s" "F301m" "F301s" "F302m" "F302s" "F308m" "F308s"
## [225] "F309m" "F309s" "F310m" "F310s" "F311m" "F311s" "F312m" "F312s"
## [233] "F313m" "F313s" "F314m" "F314s" "F315m" "F315s" "F316m" "F316s"
## [241] "F317m" "F317s" "F318m" "F318s" "F319m" "F319s" "F32m"  "F320m"
## [249] "F320s" "F321m" "F321s" "F322m" "F322s" "F323m" "F323s" "F328m"
## [257] "F328s" "F329m" "F329s" "F330m" "F330s" "F331m" "F331s" "F332m"
## [265] "F332s" "F333m" "F333s" "F334m" "F334s" "F338m" "F338s" "F339m"
## [273] "F339s" "F340m" "F340s" "F341m" "F341s" "F348m" "F348s" "F349s"
## [281] "F380m" "F380s" "F381s" "F388m" "F388s" "F39m"  "F39s"  "F400m"
## [289] "F400s" "F401m" "F401s" "F402m" "F402s" "F408m" "F408s" "F409s"
## [297] "F410m" "F410s" "F411m" "F411s" "F412m" "F412s" "F413m" "F413s"
## [305] "F418m" "F418s" "F419m" "F419s" "F420m" "F420s" "F421m" "F421s"
## [313] "F422m" "F422s" "F428m" "F428s" "F429m" "F429s" "F430m" "F430s"
## [321] "F431m" "F431s" "F432m" "F432s" "F438m" "F438s" "F439m" "F439s"
## [329] "F440m" "F440s" "F441m" "F441s" "F443m" "F443s" "F444m" "F444s"
## [337] "F445m" "F445s" "F446m" "F446s" "F447m" "F448m" "F448s" "F449m"
## [345] "F449s" "F450m" "F450s" "F451s" "F452m" "F452s" "F453m" "F453s"
## [353] "F454m" "F454s" "F458m" "F458s" "F459m" "F459s" "F480m" "F480s"
## [361] "F481s" "F488m" "F488s" "F489m" "F489s" "F500m" "F500s" "F501m"
## [369] "F501s" "F502m" "F502s" "F505m" "F505s" "F508m" "F508s" "F509m"
## [377] "F509s" "F510m" "F510s" "F511m" "F511s" "F512s" "F513m" "F513s"
## [385] "F514m" "F514s" "F515m" "F515s" "F519m" "F519s" "F520m" "F520s"
## [393] "F521s" "F522m" "F522s" "F524m" "F524s" "F526m" "F526s" "F527m"
## [401] "F527s" "F528m" "F529m" "F529s" "F530m" "F530s" "F531m" "F531s"
## [409] "F538s" "F539m" "F54m"  "F54s"  "F55s"  "F59m"  "F59s"  "F600m"
## [417] "F600s" "F601m" "F601s" "F602m" "F602s" "F603m" "F603s" "F604m"
## [425] "F604s" "F605m" "F605s" "F606m" "F606s" "F607m" "F607s" "F608m"
## [433] "F608s" "F609m" "F609s" "F61m"  "F61s"  "F620m" "F620s" "F621m"
## [441] "F621s" "F628m" "F628s" "F629m" "F629s" "F630m" "F630s" "F631s"
## [449] "F633m" "F633s" "F638s" "F639s" "F640m" "F640s" "F641s" "F648m"
## [457] "F649s" "F650s" "F659s" "F660s" "F661s" "F669s" "F680s" "F681m"
## [465] "F681s" "F69m"  "F69s"  "F700m" "F700s" "F701m" "F708m" "F709m"
## [473] "F709s" "F711s" "F719s" "F729s" "F789m" "F789s" "F790s" "F799s"
## [481] "F800m" "F800s" "F801m" "F801s" "F802m" "F802s" "F803s" "F809s"
## [489] "F810m" "F810s" "F812s" "F819m" "F819s" "F82m"  "F82s"  "F840s"
## [497] "F841m" "F841s" "F843s" "F845m" "F845s" "F89s"  "F900s" "F911s"
## [505] "F918m" "F918s" "F919m" "F919s" "F920s" "F929s" "F940s" "F950s"
## [513] "F951m" "F951s" "F952s" "F959s" "F981m" "F985m" "F985s" "F988s"
## [521] "F99m"  "F99s"

Create summary column

psychiatric_no_duplicate$ICD.psychiatric.raw <-
  apply(
    psychiatric_no_duplicate[,2:ncol(psychiatric_no_duplicate)] == 1,
    1,
    any)

psychiatric_no_duplicate$ICD.psychiatric <-
  as.integer(
    psychiatric_no_duplicate$ICD.psychiatric.raw
    )

psychiatric_reduced <- psychiatric_no_duplicate %>%
  select(IID, ICD.psychiatric)

Summary

summary(as.factor(psychiatric_reduced$ICD.psychiatric))
##      0      1 
## 463308  39311

Merge all data frames

ICD10.dx.groups <- cbind(
  autoimmune_reduced,
  autoinflammatory_reduced,
  immunodeficiency_reduced,
  memory_reduced,
  metabolic_reduced,
  psychiatric_reduced
  )

Summary

summary(ICD10.dx.groups)
##       IID          ICD.autoimmune        IID          ICD.autoinflammatory
##  Min.   :1000015   Min.   :0.0000   Min.   :1000015   Min.   :0.0000      
##  1st Qu.:2256558   1st Qu.:0.0000   1st Qu.:2256558   1st Qu.:0.0000      
##  Median :3513105   Median :0.0000   Median :3513105   Median :0.0000      
##  Mean   :3513104   Mean   :0.0836   Mean   :3513104   Mean   :0.2986      
##  3rd Qu.:4769650   3rd Qu.:0.0000   3rd Qu.:4769650   3rd Qu.:1.0000      
##  Max.   :6026196   Max.   :1.0000   Max.   :6026196   Max.   :1.0000      
##       IID          ICD.immunodeficiency      IID         
##  Min.   :1000015   Min.   :0.000000     Min.   :1000015  
##  1st Qu.:2256558   1st Qu.:0.000000     1st Qu.:2256558  
##  Median :3513105   Median :0.000000     Median :3513105  
##  Mean   :3513104   Mean   :0.001132     Mean   :3513104  
##  3rd Qu.:4769650   3rd Qu.:0.000000     3rd Qu.:4769650  
##  Max.   :6026196   Max.   :1.000000     Max.   :6026196  
##    ICD.memory            IID          ICD.metabolic         IID         
##  Min.   :0.000000   Min.   :1000015   Min.   :0.0000   Min.   :1000015  
##  1st Qu.:0.000000   1st Qu.:2256558   1st Qu.:0.0000   1st Qu.:2256558  
##  Median :0.000000   Median :3513105   Median :0.0000   Median :3513105  
##  Mean   :0.009462   Mean   :3513104   Mean   :0.1679   Mean   :3513104  
##  3rd Qu.:0.000000   3rd Qu.:4769650   3rd Qu.:0.0000   3rd Qu.:4769650  
##  Max.   :1.000000   Max.   :6026196   Max.   :1.0000   Max.   :6026196  
##  ICD.psychiatric  
##  Min.   :0.00000  
##  1st Qu.:0.00000  
##  Median :0.00000  
##  Mean   :0.07821  
##  3rd Qu.:0.00000  
##  Max.   :1.00000
ICD10.dx.groups_no_duplicate <- ICD10.dx.groups[!duplicated(as.list(ICD10.dx.groups))]

ICD10.dx.groups_no_duplicate$ICD.immunodysregulation.raw <-
  with(ICD10.dx.groups_no_duplicate,
  if_else(condition = ICD.autoimmune == 1 | ICD.autoinflammatory == 1 | ICD.immunodeficiency == 1,
          1,
          0)
  )

ICD10.dx.groups_no_duplicate$ICD.immunodysregulation <-
  as.integer(
    ICD10.dx.groups_no_duplicate$ICD.immunodysregulation.raw
    )

ICD10.dx.groups_no_duplicate$ICD.immunodysregulation.raw <- NULL

summarytools::freq(ICD10.dx.groups_no_duplicate[,-1])
## Frequencies  
## ICD10.dx.groups_no_duplicate$ICD.autoimmune  
## 
##                 Freq   % Valid   % Valid Cum.   % Total   % Total Cum.
## ----------- -------- --------- -------------- --------- --------------
##           0   460600     91.64          91.64     91.64          91.64
##           1    42019      8.36         100.00      8.36         100.00
##        <NA>        0                               0.00         100.00
##       Total   502619    100.00         100.00    100.00         100.00
## 
## ICD10.dx.groups_no_duplicate$ICD.autoinflammatory  
## 
##                 Freq   % Valid   % Valid Cum.   % Total   % Total Cum.
## ----------- -------- --------- -------------- --------- --------------
##           0   352522     70.14          70.14     70.14          70.14
##           1   150097     29.86         100.00     29.86         100.00
##        <NA>        0                               0.00         100.00
##       Total   502619    100.00         100.00    100.00         100.00
## 
## ICD10.dx.groups_no_duplicate$ICD.immunodeficiency  
## 
##                 Freq   % Valid   % Valid Cum.   % Total   % Total Cum.
## ----------- -------- --------- -------------- --------- --------------
##           0   502050     99.89          99.89     99.89          99.89
##           1      569      0.11         100.00      0.11         100.00
##        <NA>        0                               0.00         100.00
##       Total   502619    100.00         100.00    100.00         100.00
## 
## ICD10.dx.groups_no_duplicate$ICD.memory  
## 
##                 Freq   % Valid   % Valid Cum.   % Total   % Total Cum.
## ----------- -------- --------- -------------- --------- --------------
##           0   497863     99.05          99.05     99.05          99.05
##           1     4756      0.95         100.00      0.95         100.00
##        <NA>        0                               0.00         100.00
##       Total   502619    100.00         100.00    100.00         100.00
## 
## ICD10.dx.groups_no_duplicate$ICD.metabolic  
## 
##                 Freq   % Valid   % Valid Cum.   % Total   % Total Cum.
## ----------- -------- --------- -------------- --------- --------------
##           0   418254     83.21          83.21     83.21          83.21
##           1    84365     16.79         100.00     16.79         100.00
##        <NA>        0                               0.00         100.00
##       Total   502619    100.00         100.00    100.00         100.00
## 
## ICD10.dx.groups_no_duplicate$ICD.psychiatric  
## 
##                 Freq   % Valid   % Valid Cum.   % Total   % Total Cum.
## ----------- -------- --------- -------------- --------- --------------
##           0   463308     92.18          92.18     92.18          92.18
##           1    39311      7.82         100.00      7.82         100.00
##        <NA>        0                               0.00         100.00
##       Total   502619    100.00         100.00    100.00         100.00
## 
## ICD10.dx.groups_no_duplicate$ICD.immunodysregulation  
## 
##                 Freq   % Valid   % Valid Cum.   % Total   % Total Cum.
## ----------- -------- --------- -------------- --------- --------------
##           0   345450     68.73          68.73     68.73          68.73
##           1   157169     31.27         100.00     31.27         100.00
##        <NA>        0                               0.00         100.00
##       Total   502619    100.00         100.00    100.00         100.00

UpSetR plot

UpSetR::upset(
  data = ICD10.dx.groups_no_duplicate,
  nintersects = NA,
  sets = colnames(ICD10.dx.groups_no_duplicate[,2:ncol(ICD10.dx.groups_no_duplicate)]))

pdf(file = "inflammatory_autoimmune/dx.upset.pdf", width = 13, height = 7)
UpSetR::upset(
  data = ICD10.dx.groups_no_duplicate,
  nintersects = NA,
  sets = colnames(ICD10.dx.groups_no_duplicate[,2:ncol(ICD10.dx.groups_no_duplicate)]))
dev.off()
## quartz_off_screen 
##                 2

Export data frame

write.table(x = ICD10.dx.groups_no_duplicate, file = "inflammatory_autoimmune/ICD.dx.txt",
            quote = F, row.names = F, col.names = T)