remove genes which are Unknown or "Not Imprinted"

diff --git a/combine_imprinted_genes.R b/combine_imprinted_genes.R
index 7b75d523fd5cd0bcc440435b5b1ab73491d13e1b..c1e9271716df4b266abf62b69e182d11db04c4a8 100644 (file)
--- a/combine_imprinted_genes.R
+++ b/combine_imprinted_genes.R
@@ -4,6 +4,10 @@ args <- commandArgs(trailingOnly=TRUE)
 
 geneimprint <- fread(args[1])
 geneimprint <- geneimprint[!grepl(" ",Gene),]
+
+geneimprint <- geneimprint[Status!="Not Imprinted",]
+geneimprint <- geneimprint[Status!="Unknown",]
+
 parent <- fread(args[2])
 ### fix up the 0 prefixed chromosomes
 parent[,chr:=gsub("^0","",chromosome)]

diff --git a/imprinted_genes.txt b/imprinted_genes.txt
index 80012f5463756bfade54375587c4db43b636ca32..ab857131eca82e8bde5f0ee5022bbdc74a5eb1e3 100644 (file)
--- a/imprinted_genes.txt
+++ b/imprinted_genes.txt
@@ -78,7 +78,6 @@ GABRB3
 GABRG3
 GAREM
 GATA3
-GATM
 GDAP1L1
 GFI1
 GLI3
@@ -154,13 +153,11 @@ MEST
 MESTIT1
 MIMT1
 MIMT1
-MIR184
 MIR296
 MIR298
 MIR371A
 MIR483
 MKRN3
-MKRN3-AS1
 MPC1
 MRAP2
 MRAP2
@@ -170,7 +167,6 @@ MYCN
 MYEOV2
 MZF1
 NAA60
-NAP1L4
 NAP1L5
 NDN
 NDUFA4P1
@@ -266,7 +262,6 @@ TMEM88
 TP73
 TRPM5
 TSHZ3
-TSIX
 TSPAN32
 TSPEAR
 TSSC4
@@ -281,7 +276,6 @@ W89101
 WIF1
 WRAP73
 WT1
-XIST
 ZC3H12C
 ZDBF2
 ZFAT
@@ -289,11 +283,9 @@ ZFAT-AS1
 ZFP36L2
 ZIC1
 ZIM2
-ZIM3
 ZNF215
 ZNF225
 ZNF229
-ZNF264
 ZNF331
 ZNF597
 ZRSR1

diff --git a/imprinted_genes_information.txt b/imprinted_genes_information.txt
index ae3e1ba273945ecc399de072a8ccfa59956650d1..53e884176c1371cc8d017605aa5db896577f5f4a 100644 (file)
--- a/imprinted_genes_information.txt
+++ b/imprinted_genes_information.txt
@@ -79,7 +79,6 @@ GABRB3        15      15q12   -       26788693        27184686        gamma-aminobutyric acid (GABA) A receptor, b
 GABRG3 15      15q12   +       27216429        27778373        gamma-aminobutyric acid (GABA) A receptor, gamma 3
 GAREM  18      18q12.1 -       29704840        30050447        NA
 GATA3  10      10p14   +       8095567 8117161 GATA binding protein 3
-GATM   15      15q21.1 -       45653322        45694525        glycine amidinotransferase (L-arginine:glycine amidinotransferase)
 GDAP1L1        20      20q13.12        +       42875887        42909013        ganglioside induced differentiation associated protein 1-like 1
 GFI1   1       1p22.1  -       92940319        92952433        growth factor independent 1 transcription repressor
 GLI3   7       7p14.1  -       42000548        42277469        GLI family zinc finger 3
@@ -155,13 +154,11 @@ MEST      7       7q32.2  +       130126012       130146133       mesoderm specific transcript homolog (mouse)
 MESTIT1        NA      NA      NA      NA      NA      NA
 MIMT1  19      19q13.43        +       57352270        57359924        MER1 repeat containing imprinted transcript 1 (non-protein coding)
 MIMT1  19      19q13.43        +       57352270        57359924        MER1 repeat containing imprinted transcript 1 (non-protein coding)
-MIR184 15      15q25.1 +       79502130        79502213        microRNA 184
 MIR296 20      20q13.32        -       57392187        57392780        microRNA 296
 MIR298 20      20q13.32        -       57393281        57393368        microRNA 298
 MIR371A        19      19q13.42        +       54290929        54290995        microRNA 371a
 MIR483 11      11p15.5 -       2155364 2155439 microRNA 483
 MKRN3  15      15q11.2 +       23810454        23873064        makorin ring finger protein 3
-MKRN3-AS1      NA      NA      NA      NA      NA      NA
 MPC1   6       6q27    -       166778407       166796486       NA
 MRAP2  6       6q14.2  +       84743475        84800600        melanocortin 2 receptor accessory protein 2
 MRAP2  6       6q14.2  +       84743475        84800600        melanocortin 2 receptor accessory protein 2
@@ -171,7 +168,6 @@ MYCN        2       2p24.3  +       16080686        16087129        v-myc myelocytomatosis viral related oncogene,
 MYEOV2 2       2q37.3  -       241065980       241076224       myeloma overexpressed 2
 MZF1   19      19q13.43        -       59073298        59084942        myeloid zinc finger 1
 NAA60  16      16p13.3 +       3415099 3536960 N(alpha)-acetyltransferase 60, NatF catalytic subunit
-NAP1L4 11      11p15.4 -       2965667 3013607 nucleosome assembly protein 1-like 4
 NAP1L5 4       4q22.1  -       89617066        89619386        nucleosome assembly protein 1-like 5
 NDN    15      15q11.2 -       23930565        23932450        necdin homolog (mouse)
 NDUFA4P1       NA      NA      NA      NA      NA      NA
@@ -267,7 +263,6 @@ TMEM88      17      17p13.1 +       7758383 7759417 transmembrane protein 88
 TP73   1       1p36.32 +       3569084 3652765 tumor protein p73
 TRPM5  11      11p15.5 -       2425745 2444275 transient receptor potential cation channel, subfamily M, member 5
 TSHZ3  19      19q12   -       31765851        31840453        teashirt zinc finger homeobox 3
-TSIX   X       Xq13.2  +       73012040        73049066        TSIX transcript, XIST antisense RNA (non-protein coding)
 TSPAN32        11      11p15.5 +       2323227 2339430 tetraspanin 32
 TSPEAR 21      21q22.3 -       45917775        46131495        thrombospondin-type laminin G domain and EAR repeats
 TSSC4  11      11p15.5 +       2421718 2425106 tumor suppressing subtransferable candidate 4
@@ -282,7 +277,6 @@ W89101      NA      NA      NA      NA      NA      NA
 WIF1   12      12q14.3 -       65444406        65515346        WNT inhibitory factor 1
 WRAP73 1       1p36.32 -       3547331 3569325 WD repeat containing, antisense to TP73
 WT1    11      11p13   -       32409321        32457176        Wilms tumor 1
-XIST   X       Xq13.2  -       73040486        73072588        X (inactive)-specific transcript (non-protein coding)
 ZC3H12C        11      11q22.3 +       109964087       110042566       zinc finger CCCH-type containing 12C
 ZDBF2  2       2q33.3  +       207139387       207179148       zinc finger, DBF-type containing 2
 ZFAT   8       8q24.22 -       135490031       135725292       zinc finger and AT hook domain containing
@@ -290,11 +284,9 @@ ZFAT-AS1   8       8q24.22 +       135610314       135612932       ZFAT antisense RNA 1 (non-protein codin
 ZFP36L2        2       2p21    -       43449541        43453748        zinc finger protein 36, C3H type-like 2
 ZIC1   3       3q24    +       147111209       147228080       Zic family member 1
 ZIM2   19      19q13.43        -       57285920        57352097        zinc finger, imprinted 2
-ZIM3   19      19q13.43        -       57645464        57656570        zinc finger, imprinted 3
 ZNF215 11      11p15.4 +       6947635 7005863 zinc finger protein 215
 ZNF225 19      19q13.31        +       44616334        44637027        zinc finger protein 225
 ZNF229 19      19q13.31        -       44921685        44952766        zinc finger protein 229
-ZNF264 19      19q13.43        +       57702868        57724724        zinc finger protein 264
 ZNF331 19      19q13.42        +       54024235        54083523        zinc finger protein 331
 ZNF597 16      16p13.3 -       3486104 3493542 zinc finger protein 597
 ZRSR1  5       5q22.2  +       112227313       112228791       zinc finger (CCCH type), RNA-binding motif and serine/arginine rich 1