From 988f12d82712cf6687fa6e5b3c525704b88b48b9 Mon Sep 17 00:00:00 2001
From: Jaclyn Taroni <jaclyn.n.taroni@gmail.com>
Date: Mon, 2 Mar 2020 18:51:51 -0500
Subject: [PATCH] Updates to generate v15 CI files (#575)

* Update to accommodate v15

* Add biospecimen.RDS

Co-authored-by: Candace Savonen <cansav09@gmail.com>
Co-authored-by: jashapiro <jashapiro@gmail.com>
---
 .../01-get_biospecimen_identifiers.R          |   7 +++++--
 .../create-subset-files/02-subset_files.R     |   6 +++++-
 .../biospecimen_ids_for_subset.RDS            | Bin 35149 -> 42264 bytes
 .../create_subset_files.sh                    |   2 +-
 4 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/analyses/create-subset-files/01-get_biospecimen_identifiers.R b/analyses/create-subset-files/01-get_biospecimen_identifiers.R
index a75a39da32..a4b1195330 100644
--- a/analyses/create-subset-files/01-get_biospecimen_identifiers.R
+++ b/analyses/create-subset-files/01-get_biospecimen_identifiers.R
@@ -16,7 +16,7 @@
 #     consideration. This number will be 10% of num_matched.
 #   - We include (and hardcode) a set of biospecimen IDs for samples that have
 #     TP53 and NF1 mutations that meet the criteria in the tp53_nf1_module and
-#     are represented in the stranded RNA-seq dataset. 
+#     are represented in the stranded RNA-seq dataset.
 #     See 00-enrich-positive-examples for more information.
 #
 # EXAMPLE USAGE:
@@ -73,6 +73,9 @@ get_biospecimen_ids <- function(filename, id_mapping_df) {
     } else {
       biospecimen_ids <- unique(cnv_file$ID)
     }
+  } else if (grepl("consensus_seg_annotated", filename)) {
+    annotated_cn_file <- read_tsv(filename)
+    biospecimen_ids <- unique(annotated_cn_file$biospecimen_id)
   } else if (grepl("pbta-fusion", filename)) {
     fusion_file <- read_tsv(filename)
     # the biospecimen IDs in the filtered/prioritize fusion list included with
@@ -127,7 +130,7 @@ option_list <- list(
   make_option(
     c("-r", "--supported_string"),
     type = "character",
-    default = "pbta-snv|pbta-cnv|pbta-fusion|pbta-isoform|pbta-sv|pbta-gene|cnv_consensus",
+    default = "pbta-snv|pbta-cnv|pbta-fusion|pbta-isoform|pbta-sv|pbta-gene|consensus_seg_annotated",
     help = "string for pattern matching used to subset to only supported files"
   ),
   make_option(
diff --git a/analyses/create-subset-files/02-subset_files.R b/analyses/create-subset-files/02-subset_files.R
index 1b2ae1d8e7..759cf6cf68 100644
--- a/analyses/create-subset-files/02-subset_files.R
+++ b/analyses/create-subset-files/02-subset_files.R
@@ -96,7 +96,11 @@ subset_files <- function(filename, biospecimen_ids, output_directory) {
     cnv_file %>%
       dplyr::filter(!!rlang::sym(biospecimen_column) %in% biospecimen_ids) %>%
       readr::write_tsv(output_file)
-
+  } else if (grepl("consensus_seg_annotated", filename)) {
+    annotated_cn_file <- readr::read_tsv(filename)
+    annotated_cn_file %>%
+      dplyr::filter(biospecimen_id %in% biospecimen_ids) %>%
+      readr::write_tsv(output_file)
   } else if (grepl("pbta-fusion", filename)) {
     # original files contain the biospecimen IDs in a column called 'tumor_id',
     # the filtered/prioritized list biospecimen IDs are in 'Sample'
diff --git a/analyses/create-subset-files/biospecimen_ids_for_subset.RDS b/analyses/create-subset-files/biospecimen_ids_for_subset.RDS
index a7bae9e69f7ba42398be1d4280857eaf32eef79c..2849d52a0f6dd3888a61dcb5f4cabaa2c5024fe2 100644
GIT binary patch
literal 42264
zcmeHQTW{OQ6?S(w1=@XCpl^NX{sK8e4zF$Zf%hp1vct>r_F^cu5*V>1LsE=Qe|%Be
z5tGAcnjO=kW5)xmHpzfGn#-B*+z;zN9~~WifAswyyZ^uF{(AJ{*TSC}M@QfNrTfRv
z-RGz7Lyvwq`cwDkk9K~7bXBq18o{ANMKp5^IFveaS|j*HNx~{|Pzj!r3R?Mjq=6yT
zrE!{;0T|LW1FOhu;ZSIM$W(MVR2VwRX$^)9Q}siv6ky1-?J9R%_=~2G%(~QM@RVJ(
zMO+mz7;=#6N0|Z12RI80yLG`+UTo^Bn?mwIU{*LZ8}O8$s)lQ|a3_MIQA3m~;HfZ(
zvP4fTFcjA^ZW{z?Q8T1k=)<QH)M};Nz%5Lq%JFL12DFl@4wN>@!4Q?gMyn$g4k@nD
z;2a(;O=_38J_b)^8dj<(fya^Aa*iU`hfgI*l_mk)!dzFqHgqfSRBk$jf-HF2xu2zV
ztixTc%)~SlC52y1bD{=1+=;wsWk;9bQ*}(uI>}7%#m4o@*p=blw?@-yX#h8;a&;>$
z4Y=&8B7sFRxL>tjC|*J!Gc}QmtHy_W-;`PIcn(}pi*-~easuYn63Mq~72Y(-X=&-y
z8F)$#6+ci2WG00YDYgUnlo~pcq$QA}4JoHGso}DH$BLp>hQH_+rdlWsyvVth>Pck5
zohT~9O^FeLc~zRClwRq<p+=3GoWQ5rtmA+vf;=I`v8Ves+<Pg}<Fp+tNJib&3lKa<
zC9ULKN+GYRvR8O$u!U+#W8`DF_nKR%NF(rC8CD|)u>$XqrKd)K8VM}OB34cP0Pcj<
zP}?FQB=5)xQGFM}kZ(jvna1#T_z||%+$Df~5Y;Zm4ICm~sLLgWU!<7&DlXx&sS;^b
zG{7868{}0KE-0%LwNM*4uOf?xoKtUy`~L=$nHcvKDX)^sg7X_K3ixoJ0rH~}J#er?
z%mQ){AEJl8>`^IzY|IJr3`8fM8-yBUy(A84ZIloIA1&?+kl$%o0_1yLQ-FNG6W<8P
ztBI~53U#}QLEefoV$%fvA_Mmwr)^P^La91l6pYp66FGEoSwr|{DfbNAf2^9kKy-oV
zUtMiC-Pj;f1}zMs$xrIRab#TTjst9msX<<{)RySb{lEbEhevb)-@W=Gye|Dt=&|OT
zK?<FQ3`dNage3J$sE|Ag-%M*J4v}l<V-xP0{%D_*yJliUXTY~BN2a3>T%Y3+T~ll|
zb|D+{xogJzW=8Aiv7Z?Ug??d%1D+NQ#fAYFbWorCw3>V!V<h`N^h67ve2*%R0`~>T
z_s8+oK^{h8Cicls4Dy!kb}oMjf))e!oigwf$A&?p@wm_Bn+e@Gmb>66Fkrp{?oS+L
zofgr@!*}l6N^ZgUX;q@!NE8^loI3Doc(RHJbQ+3SY!84U7TfQ{!^UDC5cg%AR>-y?
zFw0(8<v53C>uBkqQ9lji7)H(cBDR*@_@>;#U@1djOe`HDNhw3ggR>XXp}!I$;ilh-
z=a6uNlNx8X16}JP2d8I%L*?K=%l~QX`v=A9$Zw=zki7P2Jvh%)lYgYik=R#hW)4z2
zN9Ri#O_w7YyAiMyABDRHkxH-hfwm?*I6W|bbq@~A%YEXAZWo2_66h&mfV`7>UNOu|
zoLEO6uaM_mim#%<jP66`OQspoO>C6_FVadwT|P2QlYT;;`|*ArKIwo1sWuIm3eL=?
zC#qIe&>|b1VBeO0Q8gM&<Q3_dJ#vb4%zh^(Ovn5i00*>RST)}3(u7!Z4Ok`+wOJ(T
zKFl)6_G@%1J@&&^h29{Bna@B1zDvlsUJM<Iv*zTG1tuZYGdqT5JEN;fEUnx8Du7;X
zM(N1t3Xq5fO68DzSG55%uUPuU*wQ>)q`7Ah$S!<-JBCj1Xcd6bar&`V9;*ayY;cB=
zW_8d?HqBMSbWjY)6vz9;ZO^lkjUg{(jB?48p&y;$GUKd18(V4?R49n57^+p12((W{
z!$oYy1Z6OWq1ec_$^tqM8Mt4CCQ*`h5Q^Kc&Gb-$Y0)Lgd?;7`>z75SLMu1$Yy_Sf
zEmaxv@@Wf4%}`y-8Sn<5>tMWa+%KZMqa^%r>d=JZ6MLvOjG{K6wZ~Va{#eBxv8||y
zQWz>{n8LACNRe7WE0mF`9P3dNAPMR$<EzNA<{-<4Cq%gl%TwJ<sM<htjL$lLN>Y`t
zK3s^<T`|qW%gb*{I6{HTg2{c86OA<(MoU#KD3L)5h!>+F*ERjx$|P8}Ke6!<R!(hX
z5-dkypfC$^4bP5R7uLYDAeW}0j0P<e4(X%h!`F<MG$t5Mm8A+X+Ix((Z5V1*-k{De
z;6p*iuz<=;_cJMh%*1e39Mn$YLv+#cqc4vX9Y1zE@fBlJpNuu^sg6Vwh?o({8_UKp
z3765iC988gG-a5d#Soo(tcOW}(9T$cw|8QBq(n+n8ED|r8{2Mbv^*Lue0<_*tv-O<
zplBUG$e?w6$SjE1sk~Gk)Sj^9(Sy6p9$wNg#EOt1eK5qz>&Ddm$+94@B<T`{QFGB-
zs^9yk*jwruNE+Gh5`#J~>mgi>qa}@_Cpc6R*j#V4@HwPdnOKITo?cm21fyV_HqCzQ
z^N?;Nh5<9RSW!xwggI0Xo<o1aM6sp3ZDHFy&hRnLWH&W5aBGF65t8QaHqF4trlHi<
zYiM*F)XeF;^m%MSXA`5VE_Rg0iX&*hjdsrQ$s^O#uv}93iy{r6zf0qr;~vm^#t=TG
z5qMVDkQV^pLCqY~3tSb$z-#TJw(Cm_bN3D^qFmb}9)<BEQOVhJp{V5ScjBQcIiG>$
zGqG4<$PiBt3yT`?jvvy@Aw}TkG==Gp<2$oI&*qI)mJ*uRunRFm_#9Ny?6+aBBhr|b
z1~acXlh;I?=Du+nY{!AG1+bKn5yc;!LByFZx1VS9jWlcjBv!ijL+G-SKn3pGjplGQ
z6IPQhB`TL-t|Q<3MEJ}czW&08lt+BR=PNW5_PZCuXc6=_G8&a-60WuG-73Jsc&^U5
zeGw((QLm6!hb-g}ZwlGTZ$>cw{#^<_37>CP(qKnNay=+>#cfOsRfpA7Dh|@9^q}wW
z;f<k*B~7S%v0V%bGWk;5CXV?C8PX%?6Otj8p(nJpU{MI80%YPBP}ND1+N}jOW=3Wc
zUkL=G-ba`@J!3vyNdq%a5K2R@6Ldg-J!mv%|AmNhW)@C{poje7#fsxmSF<B{RmV%3
zEXUoO?qI~~31t^NAxRUPO&j4H9$HdHU9_-<*6?_@o7*-2po603@qIaCD|BReFfZ|r
z#GTqM<WVm}?pPQ2$uyb7^7&A9DEc*=Ftj$#gquT}`A@cAgWw>+K_6eQ%~t{PS;r5-
zL4tz>2Yq-yz34jBYfBH?bx2^4z@YnK5X{(TIaS7%p^Ls%JtFWm-QaU^9I`Zmkqvav
zdTi0RYUfJei>osH*rIP$e}^XQTO|PS<OxL+1pxL}LJk!_PzbE#AKg-&;Y*r00?2T$
z3IObn_F)_M2>=uT_|b+C8eo431pxLt@vV0*6#yszPynD6MXe00L<Il}06hB9&QC_S
zq7**Bo`ZxBu-^&JR9Vq@cjr75KER%Hrtty(@Ljjjf7oS~zF5vL7n^S2r|$FfZZJAN
ze%bwZHs8))t``@J`DQV@meiSyWQ1hdczL>7ZWhbUyUodF@#bW{T&}kB?c(g@ba^s=
zw_R;k9nItI=KA=}e|9AQbq|uib-!?S@_tBA`#pkJueS5q>GJyK^Y(mu+|BgUbWHwl
z_e&iT_~%^+Y}c!c*XzaNbhre*NxXiyIbSVj^Y!}t)qF_6=9<Kgz}36%jLxqYv(@r+
z^=7d=zn#tQc<5aytrw^7*6YP`d+~nO5nr6mI&zE6?A80t{POBzaWlys-CyoPce9<Z
zKTLMG%!G@`%^YT@t9Q%oX13leE@zA1t`?`aTzNBie6_lGKR;fdZFW;j4?=abU3bj6
zI0J+Oe!|@p*Ne^V`M#ZBT%2#VtG#)K_airYf}5MG(=-3<@|Jr#KHOfunsrkJXUsRj
zFOWN3ot-b=0E#}>lGzlGFXyj^?DKbSY8Uh6>0*0)y|}ui@)5lL!A+strjF<2eG+_l
zakHfEz!n#8=L{PB)3~0m&(2R7D^d7Xay`48FSnneO~&=z+iM8;`t~ZmzIuDvG1JAx
z{HlYCJr*bTqr69N+zq^)>GtY!j~pLToNrdISL>T)azhZ`&FKk$zNxIK{(8Ti1ZTv+
wjo(!ZZbk0@Wq@M_NxmImlDt_ygJQw81O1+U;jkFA<2%u2o!5Zq(b0eZ2f)c3l>h($

literal 35149
zcmeHQTW{OQ6?S(w1-5-D(3gGa{scL^U)t^i@5Bsdz}xaNFM(n+fe~9aB*kd@<BQT>
zGkX{j$%K&<Dm#Fk%YZtX>o?z=^UY!Xm$S38@6W#fbNA=7?w@DRel5a<b$0gM-@E_(
z-2MKo`;E_jIQy~t`>$^PLXuJxsDTcPG{rCdl)xg>p-tYTu!!nXl6e*=QZl>nGD!tR
zs%#~?R+*qkv%|D5lmHazenQf;j9^jV<%*jYu!t&A5D^~~8G6H-DjpOWma0nugHIth
zkZcWB!m3cFIS#C9SP_(9uLK|Tb4|6p8df!+N{LO{fTzMRN(~vq&WW;IEi?swV{8!z
z`<V+qh$Pj-nhQG`Ici-eGBl5zD2`bT2MyucQNz>&wy@#YOwtf2VzH5U7KY|=);LVE
zGw>8{A~iNV0~8TLGbRVHLDZ&lZCW*WipHU<Gzi+FNUM^x#Neq^&J&~=uqV=5R*+H2
z;HgYPo^0fB0%Qu)2v$S*lpd*RA`d=DX_e9l)+^UaJCJMG6S*$oG^pXw<^@wcQ-*CU
zrBse=je>719Vd2ULjpyOAC$ybG*HBRJ*J8cyRh<$!b~CsJXObq8mbzc(RCJDzO2Ir
zH9=7@nZluMh=V*u$$_mVvprMuU{#rFO5K!$MTKKmiB`awQ#4M)Y*qnVwV5KXL~vp@
zU6W%agx_csBw;v*%PK8Y%9I8cVN_Id=E6#(ajuq9lz?xP2?@;5h2~{yl9WYoGU-ZC
z1d<N>UM~|Og(~c5!!LBnh~a{9Vy8~RXt1`i>gu@<dm^$)N@NV@YJ_WFRU7zJ93WFE
z2eUA(a?45wpis+x9u#FT3w%{QETyFnmxM}bY9u)v;#r{Zp&?f`6QhdZ78T2c)-;Aa
zF;`%o4!Ot2*Ih8JwOY=@9B!S*$5#QSJ<Xddn3CL;Gv9%m^{4R_(uBS8S0`n)X~Vtb
zgedI@n7YK){m6qPXSS5qQ)J7e4xkBqEEoHE5$O#aG(O@xhOeO&+THO4RDzS`&H-`-
zzV>J*$ZFpcp9WLNcJ~UVT+RR$$8~qSfv3C?W~v2F>H2tZIykz^U<6-h3#NPY4^Yk5
z-6VzQw=v}8a|Q^Qd~&-@KGQRllg=41*e7MjwGsl0u)_k{Fvz}zGoZ)B@TkrJ=$qUp
zzDiY!5`#f5eA;C74*{l=-KYXNzZ5z534kds)B+70-GX!W_&RsaIYKaxAAmAwQAeo*
z{rpC)8nIN`;Pm;;aZVf-0V-wK#_6YZF3y>lL1X(h+$VFtkdf+q<(QP0QmQyGLNtq*
zl<=AMI5t<G=_%r?6B>*Tj`_!j-05H%G_0;7h!>|F^Cy+5MWG4<W8zHTFZ;33z1Jx>
zvStvv-;L()6FF5BD23@jkC&aeY8~tFJh@LwEBI?a0X~hdKLLs+?dqWT2&Ta$RLXV*
zE|siWdS=0h#|U%a)2WPzQbvR%hNb(CM+Sn8lh$y2AlUc?j^|WC++^>I7I&%>QbJ9F
zK2`n3x5s%Vkt^GWx}$)QP)it8jeK)bx5;~4cUFrNGlgipPZ8UQVvR4BH(7W#d8@)|
zkZF1bm2}fLp$=4Zn?Rk`frV!yny-(6{qHK-g4iUMG8hEWT*-CH0xp=)b1-HKRIF9V
zjy1}lMvhqxGtvlxX&_NGDH8gmANvP{qr+}5MuSwtw;&V5EW@%H!jRn9CS;NjF&zdS
z4!jBRsRk94n3+okU^-by_|QAmK*V`qZ6Qt~t@2_xH)gd}P2QIb6xVf`!6TF-`=wo&
z&@scedvWedsB+4ou>JU|Y*dGqqc~8oIwI7@fo>4eK-@U6Q|yFxuTH;-t4fCou@TZb
zc|)7NdmUCIeIi>Gyj-x)=;mZHeM)YnlfE}X5MqcFP(MGJU+)u+GP7V=&Y-VmguY}f
zE{T#tXUYf*A7M0n#GLQ&J?3dTtXpZWXvfFxv?Ph0w1&)du0DEPM@WtdBsY8~jgGN+
zazf$J9LIU%xGLNMS!U`1#_;fw)wzpo1xD5qH3@aKgyh~NCZdrfJ)JZJe7`WF0%sA0
zIA+TVt+fFk8)2qyPE;0G8aS*82}|!o9lHsb$4MDW@C?0I+~0MS&H~Y^L<t*RhH>6~
z^4Ae>?P-JjToGNs_be}Rj{vh%=9-@m?zr*+bC8FQof~iqJ?%K}EC{(n(ul|dS<?t1
zKQLA&%rCHILU-lyo#!K1%}m3Ra|6cm1bp`-;#flM-~If@W#5nr?bCT8)tMPJ4h+%=
ze@Z{8My`9uRLUKd!6U$aQ*-Dwi-vhPcC&S0EOj310^U93a{?2Om{yZOCFykB*Q+j{
ziU*x1e*}(xU_x%1s%-iVJSlcZbK9sq=zkKp-!D;t`-jZGq{gP)<+Oo7!zWmp9{l4{
zI*l-SKH46lzzx$F`r5{5yXi#K)!|co@xac-gG@xA7j3`0!^Ff*)T-(tq!3jm<9=>;
zo<nBAsQF%TA5-c?3RHR={|GS3_jAXHN*HbzKKUMn`F!%iUDNm1*YmbZ)RSo{!I**I
z`~9%QY8a?R44pb7M}S!%I$;Q9K7;YC$%wvJ_>L5>pa#qlITQHiNwPOt8ZzRpF+=Gg
zf(A*1pzZxi`_^eY%xbt#ca1?Bt5Rbq|2i~$hlvs!CCmb;?=iWmS*2Q+M+ru!1Dt6z
zr|=v3_`V;+DAYVC9OTsholXkYd4T*(<EIDq%`iK`Ov|9hOCb6m1<}89?yIB;@=nnN
z1SETP#K@Q`{y-2kIbF8VnBha7U{F;)_&zjNcUw)2eCW$Meg<s;-#uOk=Sklae9jX&
z*GsdiVCZJ9{uJW7g_-N{BGbndF~7ZN;3t3=;-2jLxp6wV&Of+(B*yav-@=~jDi-7U
zP2Xb|>r<@Hoj2)-JQMxKd;E8We1Nwi&%_InXQH2tBUdCuo{7G5M4pMhCk~irLco!L
zqxUZY6mZn9xRIBu2{`IIN5B!sJ1F^l<01=JKdJa$vLo10-(Lcb`koMQB;e@rJ;ozx
zmH4jDOpe|OIO-RnfTO-A1RM!C5^ywlU-sy=i-YQR1soj~j(+&A%O3Qnr_lbh)$*p@
zJf#!*`Ki!2KY!l+TrRiE=j-;mU2fXNy{s)1Ns+oA_4(b)?Q(Ikx_|h6bG1F+w6D)!
z|M%(BHvgw@SDSXVdAk`J`1j`+*sgD{U#;8r;(WWg|J+Kvdb_#0T`iXD_0`Me(16QT
zi6;YhZ@0_s)qT6TU0vM1ZdX^2wR!4~<Z~>o+l#mBb-UVLzgu+1+sj2~uH7tNzS}Hs
z?ylR1N<P{B<#X(Aw#)Tzl^r&dav6E3!{Xxh?P|MOtT*k=qW#ZZd$DaVUpy9`-`!rn
zTb{2kH&0bd_hNOkT`yOc?IkcA@f+@{xNbL(<NIcLeSNjr-tN>BeVMt*72G^5oqqB!
zZXRb(HxIWrFBe@^!5H&Z@FV6fZZEG^uYtvotI6XQ&u^BmhSTSt+}5s_tBZDfe&60b
zT6vEa|KhgLbyGLzlwA{ic=6DrZot~>H_H(l{MEQ$t}m}HMp~lrwd8(rvs`UIK%0!~
zvyaOV%<IRc`0DP>O*fgYua|cnT<lEo_{%Ks*qgQjA8We3yV)_vhZI+v+gG>ihh}m^
z5Z}t_4S(3FV^#h2%X$)w(FktfFEf5VVv?^1M(5N+^G7TeT$Swm^do~cVw-%H?XmG1
K7(F}t-~RzEpii6t

diff --git a/analyses/create-subset-files/create_subset_files.sh b/analyses/create-subset-files/create_subset_files.sh
index 06e21c2e14..d169282e60 100755
--- a/analyses/create-subset-files/create_subset_files.sh
+++ b/analyses/create-subset-files/create_subset_files.sh
@@ -7,7 +7,7 @@ set -o pipefail
 
 # Set defaults for release and biospecimen file name
 BIOSPECIMEN_FILE=${BIOSPECIMEN_FILE:-biospecimen_ids_for_subset.RDS}
-RELEASE=${RELEASE:-release-v14-20200203}
+RELEASE=${RELEASE:-release-v15-20200228}
 NUM_MATCHED=${NUM_MATCHED:-15}
 
 # This option controls whether or not the two larger MAF files are skipped as