From b2e0c09f2a8cdbe8e0950cb66ab20e86aa61a14e Mon Sep 17 00:00:00 2001 From: Kemal Yaylali Date: Tue, 29 Sep 2026 07:06:47 +0100 Subject: [PATCH] Track the packaged CN data files (the data/ ignore rule matched src/simurg/cn/data) Found by the CN cloud validation: mask_GRCh3{7,8}.bed and cytoBand_GRCh3{7,8}.txt.gz were never committed nor shipped in the wheel. The ignore rule now covers only the top-level data/. Co-Authored-By: Claude Opus 5.5 Claude-Session: https://claude.ai/code/session_01814GKVzZVL3FuF3DeiZXhv --- .gitignore | 2 +- src/simurg/cn/data/cytoBand_GRCh37.txt.gz | Bin 0 -> 6609 bytes src/simurg/cn/data/cytoBand_GRCh38.txt.gz | Bin 0 -> 12118 bytes src/simurg/cn/data/mask_GRCh37.bed | 26 ++++++++++++++++++++++ src/simurg/cn/data/mask_GRCh38.bed | 26 ++++++++++++++++++++++ 5 files changed, 53 insertions(+), 1 deletion(-) create mode 100644 src/simurg/cn/data/cytoBand_GRCh37.txt.gz create mode 100644 src/simurg/cn/data/cytoBand_GRCh38.txt.gz create mode 100644 src/simurg/cn/data/mask_GRCh37.bed create mode 100644 src/simurg/cn/data/mask_GRCh38.bed diff --git a/.gitignore b/.gitignore index b91a2b1..3be7554 100644 --- a/.gitignore +++ b/.gitignore @@ -1,5 +1,5 @@ # vendor / large data — never commit -data/ +/data/ refs/ _phase0_archive/ *.idat diff --git a/src/simurg/cn/data/cytoBand_GRCh37.txt.gz b/src/simurg/cn/data/cytoBand_GRCh37.txt.gz new file mode 100644 index 0000000000000000000000000000000000000000..ee9ab76fb039fac9522bed267e9d1cbb0e5ffd2f GIT binary patch literal 6609 zcmV;?87}4@iwFqjM>R?S17mq~Z$e>iWG-}gbO3akS&k&h4Me|7hbaUXU*b58!Jr3_ zFzTEUbbduvCe27jslOWW3{0mlbdp}b{qdK493N`O^WVoWo1bPMKmYvw=RbaXq5#8_ zKtF!|`uE>DUXnmdlSGn@0A~`Y6&ry>SJG%Q0wOb;kuNjjc#DGRk;W^3Ni0OrOT$$M_Y3eY?kHF<6UwkIpExxGgD5`pa=M9<;cB=9D}m%trKp?&5II)TG_MFnB$ivO_(dXu<-9a?vB*SL zvLwY)5YZ#Hu{1j%qB26$oC6UZ2Q~8XaRJcG!XBQ)Jk5E-Y0rp+>l%wtf~EP=@!NmWJ!A~W{M zL;bVIQtY91oK%$+1CgakQ};EQtch6~)jN=DR~j|VJ22T}Q&qeJk@E=6{ooVIX-QVx z1CettYOI?Is5p0z7Sc#mVwXP<8gcJ{sd!SA3k*axV*10IcSP6!;t;sDD-1{#=in)7 zg95ygft6$}Pl!1%PolbhWNI@Ft6B=8Zm?8$6p8wIMTB|f0S|XtIX<2j^Gote$_62@ zO+j&)XiiEb+n9)E5rxI`5EGFV*PN7L;Ja)F&Chz}CMdDVzEoN)VgG5iB-Iiimi?(J zhPWZlBq?zrF~j}+4CHl+1DSi$^jQvQNVA@*GSNVeJgZ&_iFjnIkDDZj$949&{SuI$ zXVSDW0}joq;yut5gx4N`5}Y{d^|nuB#qIgf9)1#Bju@DABsGU^~*8N6m#2 z*$Y2qH_rg~Sud(&D9EYFP~WnEr>9%7ZhoMXce%wef^UH5iQC2N9D&Fo^}fr72<5PY zGAp*o(gtheHt(b&o^&->09|UKsK*_^D=ovGsYOs`q9#ez zXAShK<3`d|Kf$i>F{$dt0L8|*t`uKivSjP4rcL2}WE4P9=UfWUzaeC-Nb5E7ZAB_A zVaXM#Bs)@u6GWMYdpqPpsEapFURfb|&-F`Ej+BtuL}V^*;kz61bZvtH@{LKBIv9{4 zlM>N78o*&IsZ#6~qA_A0HbHzJ4BXoN2AkN;_4X5zX--Kg>4j_#{Fv1R1)19^(Pk&u zI+CcY1jrgnN!zGkYY9bVzk}?7ddOSw5W>BUsxm zq=}GaN4_PREkJpm&v_lLXJn@(eP+c>M$0XuAj6ZQ>{xvz#AGo$JVtNBXrC z)s)0GPJb1|cb^Pb%_|^3Q*@9r7NCK`^r`79A8>e%du4ur28z2L_>^qyG^A=L$V5)j zFES;&_BlmmuokazBfoR2GHWHwS5)nX?I9&FyBkEhMjV-B-E zZ&L*1BPC*eiU573jIK@*&_It@TFq-@SG7e^u>&&B6p?CdGs3CgM@b`@;~ph3Nq}?b z09Y*rT9$sS1xX`aBjt}}x zSK3I}7U@lCD~*vwRdJ2zO0>~V@2w$AG%DUvzvpYB3H6|?zJynY6JT- z;YF&JBBJB-Mk1R7qT_pd8!Pe9N#gCI$3rJ!r{yLI!ajX1rJcl5&@5BoIiZB6B-Bn~ z_v~!IPB3FwE!mlqpbKz6>YiEzsS2!qfiU*mx|^PY4|{-GJp&nh@@l)-$(VQ6^XVz? zWL?^_At#&ueJC#{uXzf5O3lw?s$4F zKhu+0UopTF%}T46yc6MJ{7ci;jIZW1g(oS_0bL=;DQdGsc*Tqq4XuodEZPNc)y-Pa zD^!`E*ZuI)rIC$i>_MWGV$ZklHNEeNr7dMFiY(c5KW!6yyAmI zS*?}H7$kOlA9@CfN$O-ZJ78uhK9v~-NeNVWb{i>uVvlOn(SSIAsJ#FVGWTSsj0VKd zTOj0kg7Ljb+Z=KDkl z)0;>;7GQGdFtJnnW5@hJ(%JvYX9CE<%CP>#Bon?L*WS(~svWy-3EADuDk+u%p+m~X z9t?r0Cy{15AewTxx|%ZuCr?RQu>)fB`#f%@tZ1hstxAIMPl{^Lo+KmvUD9Wn8<2q> zk!W8ou(9}bP^`rFnL177lAc719pyF{kk#7nc`#thzfY?s$vSbOT3R*9(%H1SP&}EQ z?6i#ow(%ZP!^tGs_@ka4PA1uT*zh&1hm+Nt=@}V{SPII-Eui!YS#Hgh-XP;|qv9p* zJ!^|Z`FAK~doL38gOap&7m2c+&?V?bOOliy05iEd?A$DpRa1CeT>8e%d;K3|>BMH9@AN;-c9Bn{4d1tpzf@-j`)_{SN>D z|Nk<9*WkzlnJDJKWKdT38Kb%fE@zJD?3kkZ3jhEB|Nmr~OA^E&2t?O&9AcrJW6k|H z$t>)Tvwjv9Q36PlEOwq(p9e;Us=MC~>Xhx_H?X&7MSscx$tqhBF5{yirv*anphRjL zrM?G()vjDBH$+s+qR!$4A}qtde@j@Pw=GG(HyM|ugZ!04aImDyTnQ2N?991qyKYnc zlr6~)Nvk8Ryu=Xe=`j_Ch^Pj)=;WE2RQ#B8$P&?zXhAwGO`zmlOSps~QnwH_qgW#33=yR@YE#S-A%!$n z4*&oF|NnHGTN1(`3`Msj7mCfUbpJor(cTBuUk*cgbVx#O)`VRNTK+U$v9j!`WP0YZ zl-ezKYCmyV+SELw=y0~P)Zv+*Pzi*;o98@<`tBj-vSPx{GrsH{(dZ_-SOy{+F1+Y5 zB|X8P0>$SgUtWS+v(NRI64B;y?`Sy^;Wljx24bWW9l;{@+WV)E|H5wx0M9zEV6dIH z?4rL0iBzv)4Pc_z)4hBwMg>BR1wmn(ARw0ong50PEDU|ZQbOP>#ryO?Yz9$BQy*Uu zfuaLoS8)gggEh?I;&Hho{}WD(r3K%%BN#C+wFMJ+jtSnEJy;BvPg4pLwYHDaxKATjg=QC$>#w~Qih8inLu0Iw)B zv=1y8anm#$NlZB8Uz(CE#4*@L42X9az|PgYPGZi@vr#nY~$da)z)pjS43>Z!|d^!B?#dY03|J9OS z`lRtpY(NH{Vw@qGJ(Gtd6^nl`RS1ZLw6qB(EPu&&NkN%f$Ck9foa&4WlZ39@vRTPS zBP6jbUR54~u`YAsJO%3HXGc^U?=kJ{NQtPMu^n3(f1}3u+=rEVdz>NQRtWd9o zN}$W4zPckmRdBC~%ZOJM1j#L(4%!9~9KK&S|DOioWWL--KtUiCatN^H8)P-run!f) zAla>TY4`Px)Y5jdwfjVQno2!NtpE2Dj;~Sf5NFrnnz7D)88HM@Pf%WM(jyT}lO z{nTfYL;HCRW#1OS=FG}xan0phb8?wu@obpzL!-OX8K6R#(@zqCju&KJ!hDxygT zPuM5{OtIQq*8nXB&iNoQg5Ww?!>1k4=Jl=i3yL>o`1!4fPDwy-VK+PeszNb7$4TSD%?ehFAEVYhWJq0hFc59T;7(R1N_ zLl_75i=QKx$U+D~gt#8V=M7;*$$82|fkbQ(RqeBw885ddmiJqN?nAtMd-)_HjMOU& z>vxdg1?X#ek=SHDx zmi3yQfFY6ItIbZJI8$Y{*$EgY6Arg`JjnAD#7~_zJHbLy^S95=lj#|Zzd!wpK;l-v zd0Xb6Iv1o2%Q4X~q=9lqD=hoU0TRvi3=vc!6B>PbGXEfx7m23!{~!^YefmfaG1~WL zB^3i8X?iW~evl2uGY##Qr+6>~$r}WK>(xJ@pTS#KJZmPGY=gy9JkQFX;>olem5<`3 zk>RbGVEg#0-pBt!NB{r;0RR6oN1mcGMhSDclsTd_GDJxNa0v_eP_q#L00960WSm=$ z!ypVrcT~*T8&s+HL4I>mYK+0b7$fg$4Y8$wE&QU^5LwgyDY6fT*kU|0mh>U8 z-wXP$Q$$K3XY*vs~*sTv~uS%!!kHJ=}!tRQX94H7`AshDDnWH+UL%@9Szz2@Vs zn9o#~)+dKa3|)O%p&Ai%<Khi%82HKTe=EQEMhZYaCJXpyIntA(IT-hOHI9{>RV|7@H=3IHGo z1plP1^#7N2%2~l{6G2N5g${LhA?Em=8XQ`pW-b_%?s89wVeKsmGQ*_F{YE4WD(s2m z$5x=q^*>2~@;cj`t9 -asej|Tt%|Nk;Zs_;<51hKu)47rzrWC~ou0~!;a0x`y4l~6800030|7@ID4#O}AM6Z;An5g%^Skp?K#p!RJWtoTsGsckV zMxY(*FFm%@a#wg)WS9S2S1ltr{6=W+Q~e;+7BA|MmyvsSnDN!WNisl%`xS3m<*smm z$>$#uuaJVx!0;s@FZHz%0&Gm#Bm`)aNf8SnQl3<93Llqv{@+H3{T)*T9f3YfCPmmo zWO8hXpksq0$Gl#w5(`^6uq$CB~U;a#4EFluIPh-v|5|e`Nb4cfzF+jnWnX@U3rhsv&nw9+_ zkhqr2nI77Joi1jaiDC&CV{&78_qCE+OR%aQCV?D5!|~U$l!EP$h*kHfO(f(2`RaeS zsG5xOVmm>I2!;D`YuFJA_f2iGj9Zsg1T}#v)&r%orSY$TKy%iTsd_PMVUMZr_#zhR zaTZnpOxEdInpngj)#4J0B^oZr3`Ec58Zf#4#hO%Q7AwDf zl?6@+;AM(vvKaMaBLSF0toTTPCOzkm2mmKA-&pEZ5z+raK}73mROf?~RTKC#1Y;1v z3k8Z~FNyj^d!+!kb*SjPK`sWI;v}n%`@k-}=BOEp7`DKmT0y0w$YS|&Q&p_tAARwU zUY6Lb=1ZSMwjroEoFVB}#7f7uctP%qjzqSynF5p;U|MHZSs1X?RyJGg96;_Yo2w*u z1|`Sr-#4;I6zXJi6-ZD!&vFPQBnFNdA{|rmdkkb$p4v;D7f7(DHY2}=fG(f4{p{B)f`62c%1Mc3ZOK-)>~e=+NV{P&r5>(dOW z2qEOh1=9gFmn;X$Hk$a1P2!HcUFhYe8)}k(fVkquDyfiZbnQF5pb!oY_ zfUV)vS}>-92y5S%K=(-my6553K=9sB{~sCSYb|>e)CY&8 z^#%^G1Y(n=wTVzF?B%pjLeW8@P16!k$@)Iq3pMK<0h<|NnKJ zOLnX<3`ED-O$+gP+KJi4+y5xd=|*)6$TXLuHpG^NB^AlOR^C&CKNA^+M21dO((Xw$ zpxG{+)3PA`vvGf+jT0c$r_(P6`VUF@(w`wDu7a_minzL2F#@$KPmG1b9)==stJvn9 zG}&0yWEBcUbq?>yYBLQiBX3Rm^+!%V%}%@57hVL?htsU$G4L({mF(SSzl!!&c;GZM zCn>5f<;9Nl5m`H)wi+A7OEKwf2?(OtF8xWf(vC`P=}Q}*d63$q+i5>87oEOwlzHeb zjx)i=Vrg97^%{FbIB4n$!L)s&fI?!cdC@j4z{p-cY5PV2Me1ef>Wal;es6&J4*1Ue z_1DrkQqDL}Num>U(Ua!KXSR+;1wV{gHX4NT3jT^Xgraz|!;v)UlE?qoUWg$!&Af=C zX)=|E`I@LhtT$bE`2+168+MLxGpg9{FC@O*=*;JPf_cRi+ziJ9DA9`15Oz#?n6qS#t-e%j1$ z;6bzh7ZEgL3*iklfWy9OpAR~1wgu5plj7Sz`g}mGH61da4*l_6Ew5Kyv$tdRDqL7n zkA=SP=K~Un32HmE(tnRhzqI)C5yBCPiOLN-AZa~`$&VWbSfmcPR==?(F)M$t+5RxV zLalwD@>E%B67z;@EVCu`xH?50mNtvpyTDf(Sdm3riWG-}gbO3CZTW%aV3`M_t7SpIp>bZg-nAt;M z7=h;_NZd)_^+)Y4UXpVB+2`PvNU5mu^Z!3_IWD5d{qORs?W%ft`Tq6gpXWO=P@^E1 zm)9S^q&^fw9YI0JFffB4nlcPQYH%ckkf6?>;60`ur({fy@GPW)jEJ_N*IX5mdVlLRRz;vC7)U8ZI=Pr~jWrPz?QZ0fh)Pp;Vnqb?5HlY2blYhIwQ?nr zRzgrmbwko75w&Bu6IVjeJOyWOErqB}btm?gV3gvQCvTQBpob)+BqJ-)T8%A- z1Oi()w&F-2THL|q>G|t-bCfyte3Ng;hW(DBV#a#T+tbg};O{8?tnT(`qOXNyZEbUB ztBP#332vo6lb|*x?KzD(lQ~N?LyTZhi+6dCND8hAF)u3(P3Du<1T*~|B zY~8S7Svkpw6y@XciE<)k%-YI&pKhgi%CWv_?9ja;9S{e$xpyIz?8siryMma(_fWS*KL;m584zS5^ zEA0nK8$r=6h_EZCtK{QK((80Z^2U;d2`u^5AsH=SQ)xkjqj$GbWh4_JXg{)qQ#4p9 ziD=g7Xs(TL`i)<5k4V-t;m+11hwED`T%MY;oZ-+ArrT+9iu3#E^zx)2Tm8rvXzIJu zb&muu4+|o20-bkgnmaz8FnMP3KS7bLkGB%6y=$cF^Q;Fi*GUHP1K&Pu0U=cT?C;Zm zX))`|r~hD3Rp+`&s%iqKDaF$qf>Az}OxJ=yWkc90-weo`G1A_nC{T~#G$d1DKq9fJ zu8~g&dYk1Ln7jgs@}!aC70~a!PJKeiJxSDxS3vRY`eF9!)BG#k9eAK~cF!b(JLms@ z?`QOF=+fR*<~&v!@|iwxX41U6^iXll@5lG&&)3^)nm4hh>`(I5GzyJx1bhqe(98{*^Nh$p(n8b7XE$BkYtp0Z`F^-& zJqIZtIyGiD>5UYr7iqAo8DAn{n?RxlP3qP>_M6*gk+E@)U#r5k&U59DusRHdhU?kNNh;maa zM-58JX{Qk*>HP%irqEQQoAp5@WuKc^G~l{DQ83#{l)iiri|w?OUZ`LLkKfrPt`Ec* zsnrA<*pf@GCdgsr)9Q~H6w~#TB`b_qRnpYO@dp3^|Nm^7&5j!}41>@6GK;b4ANg^5 z?p}%(eg1m78H!ST3-U1@%NU!W9Ma`2xiAjD*TjTeTZl}tzp2|E3~45gm{!|i@ow8~ zc5&~M?N4H3`K5Haf1oV4g6Vs z*OBLAbJ~=Mws&N~N#oAnZjUcP^RimE$bDFkqeK#8S#8-#~}Qjp5A4Aps-`h2sFu;L{F=9-Lss zXy(T!oV6x#DJ~IF>s2(VGQu|07ei@8{Swcsu{5%--WkRrd4;`GrxXrHId@9oWOVha z5*LYZnBLaKksdU)Et^~qPG^&jYFKWP$%V{KS2&y2T@)6H#Qb*YeUS)_O=qM5^^gRN^?}M=Q7|Iaz`0LcWh~{t8p+o>-GF2;uhrso$lm} z(NJyc9!D`YO-2SC@L5N<&tVA7slMHop+6o?<8cHxwV{n9qdjYHeu`%_mAw!v8Iuiq#^4&K@p*)c2c|GO#r zl9!Q(VLe~+y0zR0M9migS|v#0zIvcn*n#L(j_-E`Xw>S0j#J0TLWH zlb5pq3l3(5$mtoLeD?c$zMKUhbgCcoB9%%>qc{X5Sc9TVGP6WJt{tnL&&yeW)vi%0 zlCzO!WNC{=Ex=l#$dgPgk%su&VX+rrZKl>OIVc1HADofd#I6C|OwO93>Y1W((g0ED9zYP%HnwK6hyR$vtZ?QzoJA)^9D9$EO| zH575m`ctCY_`~CoE$jM+GnbW~;WvNY3X)%6v}G_$ly2RhcA@!C$_3KwOeqb(^`^B6%L+rsydoPN@~Zmtfc}g zh2+R+5-F1mY18o}R-K|pa*q?K-=zyFCowYrUFQYcKX2fv##?%2>&Od{kR6rC7(2VdJ6jEl}0Y{|j zHeG?CX70`6vz$aGhTP8ABC+KF%xTNNKQs7shjpO)d@lcujo#$c4E@9yUG{*wHEkD7 zTZWhMO&f(we(y2-#-XH6DbxCeQ(^Ki^Jgvd8;6oQ>p4qtLULg8mposRKQ<4aZX7aw8ktGNgHz1HoLCW z2FweQoaH3qS!RA#yER~ejFqXJM4}B)Xj5uHV&pb(QZ`ajKj{Y9fK&;C@mQdCDP40u zuEZ)b7V@m}dPBvs8psV$e-QT9!6ZVVl&`^1Acd;ebO~;x&%fml8nD6ciae-927W5e zg_GF8K2daDi3|>=i|TH`<`YXvm3pe~wzU_(nO+*JoaDeL8*}YHLis4TAr|LY8c)*A zZEF-t@3#6{Wj7KSF}r36E{pa1P(LQlvZ(p<(u z5}~MtWQaQucM48BOGzZp6&!DO2jczyc6T5VcdN7mAv^GxGwi@ejWb9|q#RYHSeqSK zX>6RSpbeGDiNsUV2CH*KRUT$Sbt1&6&moca=o=0xiL{`X_mGoVE1Df7IU8x2K0eD} zIHx^Gc+{;;iQbOKgPKUW%Q^9{R^4ek%LdwqDZ7{@bS2 zfn?e6WrF!ZdX-L#|3-!zYx@%P!zmCHu^h%5hZKd!l;V}-KvB%cB?;I+)jj0BF7M33 zZXD>zSFItggTLfs7yL0LqyYIwKK|ONYGgBeB7;iC`%sw;TE)JsdCqS}nvf7L<_j zkI`l^fVkbG90Q2=`+hQj1P;ob6-fgiB^O-tWtFtS^>o8aEDAXspe=bm4q-O2~Nh z72X^!o3I`iIn#_)LAU3|q46x!OG-56YmMexEat&X;8Iukd5)9n3WIG=kwew^Mx0Yp zX3ZuIh~3=@h&@@jg_HbP6zr3-m{hBuY43xuuZM9?4L_0BNtc}CgeE~$^?Sw%29kj1 zy-TS0S7bE>C00;fpjDz15YG92m77k0l>@mULrSOy-GE{$DM30KuvjjVHngotKm454S_Zx?+qQ~Q>oLOckGi@$& zN2;rn)AP5Mu~q%KamYk{-W=lf$LI#Fmwx%~7ZO*YJ?&NbHvO5pDV&d%qllf)cBN1m+On(LjY9iGL~nlMV4qm4Ey{&5sBZi{CDU&lQr*k2p0^Q? zA{JVW8;8$hz4^r(hb#S;&3OGSn))-V-KIVUFZvo+&g6MDsnXk=Nn7M7Z{x-ie|t^8T}EZ%ZI@^5ofndv?kVnelcePUy*(u^tkB=<<#H2DiUG>f zY5ki-etYrS%*Tbo1!8rGD&G`x+G|<=E)*=rWk)YL7Yfx1zmcK~gKG`y z>&JXkNQp0(u7A&YOnTqjdQ!A7{3k{Cv1KLD<#|0V_@hgRlL`NTVk9B~R4pH&JEyYc zEJlzBpi?bEdI7HIM;wr6@w3Du9f0QnBv)J40fiBVXOuwX=_B`JMhV3r4$mlo!mW-> zZf-(pHUD-V35;ntP)&=XoU&BN1vVK<0u9G?n>ywWEZz9ubg0J3yGQSgqDy51-7>qU z&nJPbEIV@%PDN+snu~A%Sypx&Vs;=iAF@Pr9KZ~ULBWx802A52gRz0NJzOg+oe+ES zERvn;02rE0Y2?Vc4b?M<6SBI2S@ulfe5BKLGkCD&98qHCMm6v+zM@c0pp~N(2BH$N(zz1m6qV<93kq*^#R7TT9e{Jp zFR>lgJTop%h}A)<64jKz)@E=$c30N|_ zL=1&9;pglUv&qHqx}Rh%{LHj_oLU^1KUoYG`s{!#2g<V=-~;PKmf>$ygL! zPJq^Hnm3abF|K>I82TsLxmlw9kmo6m(0u`jM|M|;uMGyEM}~)@>s?BOno%vzahIqa zmD}rb%pVrrrRP_6m5}BYj?0s3P~>?6g0-Srln~1vg-1ULC(MoORAe*>QJ<(IiQ(KQ zs&Y=;MAC*ba(HY-gv4`AiaQ~i6qjE@R-C$Re2qE5NPYG-`-BQYc&;}w5p*8YFsBn# z{u<_V0;}D_oK8?}R2zB>DY42w7c!)T>f}(UEMx-P>l#?=XPDD>N1TrEocV}Bj+XCk zH=JBp?m8zmlf%h{<*;x^0&w8g)X_Lj?{Cwb;P>hikM`^u^J^F4NU^b7Ue|0LOF*g) z@0~19qxTN&MNUd~`=~^5o4~6tWR`1sfo!J$J3d zbLzX3UcnD5L=qeZs+K(jCH9_hnRCQZ;N?3s(Gl@omOFdWpdjAskJ-F&1|l52G!8?8 zLcv~Zjk8|9-BZeF4R2f^0SZNS%Bx;(9Eysz);ZGP{wt3S=>qq>JkxRE1@3v>LhF_w zA(32w#{zdCcCTA{DI3Y&tfz{0KpyN;h(>gPT9+RpDGT$n(C>6S99TNNhu^{OFrV@b zm6KS>Mm_4aIgk>hd|l-vR^XechIT+@GUt@E!TJmvrHwBQy$`z&r-Sutr)9O793&#< zTE9go|M_=&J4Zo@ujg!`ls`o-+ApU*y_OrzH4s+IRaj``ZFVkY1Wix>v?}LyK&u+; zJ8#2>rP0h`)33rLocVKha@=SV(3~@Ry|E;qx&9m%7I!1?I;UOkD|aLC^}zV(4>%O; zfBXJi?!xFCJZ|1Dw|#Uf!&$yTT*f?|0dXz@s7hZuf4`-_p+(@pUv`$;5XJ2IpJ=Kx^YY3V4?3_ynXE61Dz zfJBSMZ4C++LrjtRBoNPEg3bXb5CG>1vVD6K8rvt;*g*iu?ht3_fE!2jYv4Hm%;y?-4gfQwfG1-EQ@Sgs z#To$Ca5U_UmnacxC3W;>iF@;1Y0eVTc()zCKHVFD_DH>wi>#61X=77T*9|~R+gy9S z1R-XfM8z?z1eXsKL{nM$Jqf3{x^@^30u42`<|HjBrjI(dmWuB$VV_Qn-H}mR* zaiOsJ8V}bgBt;mXw{mMy z>i484b#k-09MkV-G^vrBwPOADL+pjr#+7*G^>A~O=abSUukW|+lS|LFUlK9o2Kdx= z0YJf`s!j9@hl{9DIla{d2xTFv>W4yU2$sWQ63Dpzr%O3BRsmLU47l)Z$+)9*x1$N6 zAKFL>JdC{jnYb2K7hJB0L`ILrg_?2nCPu(+ zpu`2`ZzmDIP$-1D%!Ju46dKFhtu-zbt|niWM7>bNewti2Sg~HybdW-3Io3Nr1mnlIB9?Pn2BK zaTP$F8brxaBp}}mVeL}slOcI9Qo=@+3MY{m)NQkJ$38w1#!~XwB!WV5td)eiggZz| z0w}>cf@u}dK;4Eel?49&sgO!v3PB&@%4-51n1_Y2w zBc;nqmEy=CQ|WjoaURjCnnEP0!up^d3+Mb2WD_KGeq?}f&-ZhF30gEV9Atipti?}7 zc=~<0ts~U*aY@`;tu7Ox>#5uKK#vAax&d{~ZU+c^mmX_C5f()H6 z<4~xHaLr>qZxX5=mmwd+-_S*HwxjNYhnnVeDUtYTyA^AHqr-R2eDbM<-I|L(Zt}cg z#0!Pb*(~?^{H6Z^00960be&6Fm^D08T8JnxOw=e;TSRF|v+2hJg^smy z%qMZ_Si2O156UsAwp=k?PaNni`!<;#dX@dMvxJX9XxvVj{4j+OITn&RG&El9vdNy5 z_=g@y;8aWk-&-@IBtZm~E@8P84Oip&Wfq32ms67@0^F5l$&Co~WT~1Zxx2!M;u`<2 zRdoU}kLo{~-Cbd%ZJ1~Ihc;;>aIJ9`0lj=UncnA5z>0Cd9-Un{@R#i^KQYbjt%oSoMiK_x&OSG{V-s~FV-r}J8|v&@n> z4svSqRG?T1;4b~g^x@hD6^{7%{@Ut!6H$cg=toV`ymL^k28w!unoM;d2p zA#k&z;{1_>uv_$PJ(r_F*8fnxLeM=kmtvc;;~&k!DE{q$anPucq{Wg5G>_?&(4zU% znvdn{;bk_TokcGY)J2bX$DI)9>XW>WJ0aA)fhDwTU|c34Ujs(r>aCO^v4Ig&x_tAA zARLxFLt>y!&Dv=Qna(g#jz@~14S6nJ%>of`9Be}f&TDny#dJDEWsT=V zYCUu@D{?Q(QN&geDb>>*`F#^sM4(cSts-Knp-2WJ@tlPzh z0O&~z3;H$`y628)U3>_D8+yX4R}H}XWZ%n`DuNY?)vE^W*2NUPN!t|2Mt;}zaf;;< zfmboS<$)9j^!)_mb&MwML+cm^wtT8Kdk`DFDXh3=AZDGy>ZNXgW{9gL(P0oWD5xT_ z>-_rxt#J+xlNuH>9AsY8x&}dW&coWIj)flY$r=ax8UT*C-lIRUm}|f=$zru$lLMZt6@&oid(SY;zwv>eNTJknhcs6cD>b=WPyU zLTeY^lh;V53GF0pV=abml<#(fuUG1?yhvHsPo06Uejtmm4w6v`*kH}m@AW<>fMGhj z$wL^nviuO3ClI7krB`F2)QhLhxdTbCR=EzPk4*q%R$pWDq}1xzOyN=|$Sol@_oYsS z9PzG8ogi9plm+)<2~hKd8p$TWi3xljBP69Kq_erqYY!p>sd028ak*pinA@T*cg`hX zCXG?-W>sh7nm~-HvpaTakYYE-xKd0dROJv?G{KX$I-H8>nJ0M84jXLj@Tr^;kK_&glOBb=TQb3Nyr?MK1({~Bsfmyl9}{>h0IB2 zXYB!tjg^BuhuGj}$KNbzhPbT!-6ZgwCX|!*Hc4Di7Q8P1L}-0uLeA|F0mz)kZ#C`K zarB*$>^AU_R9IysXR7V)!Ges_s)*q_>}*A5BHAe%kQ+@{eHB~`};WB zj-T`QofH0m_m@8}p%(wusy=4qzXlq-Is^J?oIKl(zPEmw;M&pud|g?#B_Rm=?#;YY zB8cv!_P>(WGB|YSyzg8GLIkhn0OHkI*#xuXyjXLi3Fvic@rGxoTVoa_3yTUvLC1B^ z=0^QPvzPM#{DR?&aSsneL1j|fvcS=gvZ`~q*%(`S`aue%BZou_<0D(NOHuIg2x+~M7@hP96o>2B-WnIDxv@Ck1#@KN5 zsu*L^p~~!x4Tl%5ok<(5zj@G?u9!s?BdJlI>$F!T(Xz1DDH~OTE7q%O7^1W&%=Jo( zLUh-q%Nqq5LdReQ8A3xtd*Fo1YHpxPD+>(`F~^zj8<@&8#x_M!#zo|(q)h4!OkHnL z2C4{?Qj~C^h>~O5216lNtrVR;kcah3k<-SZ1BQkmh1D$K0~S&gF|>zgRvEdp)(pXSYMW}1?(CT%T_v<~cg%)(&S%OvsyPhan z&x)^>89Lk5hlNplW?9QdYPJV9Hx>%*Y4C9(!@-dHMOn}>Xu2jLW7JYiR|=D@A@>*R zM~mFw|Nk)*WC=BRNxqVyW+C|=Zdo4vZr2$uE^HoU5WN-V;_p1ow+_g}XQAB6W(I~? zMUR!t5fE-0o1+-q5W-ozsxg0K7D3XN#r9L3pfIwR6tTBU;dG70k0(C`7GuKS~ z8Skub6(JYEg-%7nAx$F`ntK|T~Iq0gws*S+RETZD|a0WIzJkp>niW@ z(KwxJ#&tXK()+1Q|tt`JAJ5HLVA3gb9C(Yt$ z)c2&}u^9Gl$j;qMa+0$U(__2!^^yAB*u78cBxi4w`U?O6|NnJeNs=Wu2)&Z#;SB9| zL@iwLzc;n(h`xc3Z%7Tir&4b-2?P=#KoYE{t(;zdVV!=c;Y$#^V$x1IdY-%eqtIJ= zl&STj+7mBKroZe*O>qTIW`_2U9^lY89(eZ8{)a5| z%l>rhVR&31df7kSDHl|r*|9$w02<7pb^D)pyC4A_=e*#Lx5}b{39>(05pKbtnA>+O zCzN@9u%3_|8x&@2|AFjk;0r`A&aOh89AXSkW-V7=DG~jGe|{gV%z8A2Y5(!50nA}j z?5EGgC9P;O3eqe@Goy)hSz4m2I~xScGD_@JzJYW&<$d~91D5yW89bC69ai7#JK7>V zN_nq8-T?+g;H|0`v`sbp@U|b`T_1kD;Vn@>3*vE@^~c+#5jA*B?EdNLjcp);*ROyE zErdvzpqk(P#?0IP-?7J%Bee@GUq3#zN!(Kob6}EPwt9@fd{{IU1JWoFORD-b zfu5B8B>d=ARu>)D(EZipJOgvDBZra8YHpugWpZiA*u56&3_3ZS~QVynU z5ky_6LEx57xIa@upjO#yZmKb^J%9^~=imv@$T*SC_2ycdbjo&4i{PgoxPl-q(j%BT zGq#j5ILg|p9(+g`R6($`L8ZS57K}7r_k0&mk02StBVB_rdti{X0|z&&pJHP}g(iUz z4>hzBuH)8L&_p~k{4BRICDB;z^)?jVww0iapTP{qO+dAkC}zxkSwajwEQ<)i2Qq!@-0Q_}OX;(`WDwHPC6+gg_WgppF9B*I>*433Bx$IPZ= zj0DRd`f`+P87l>RN0-jFrDG(#?-V`e2e-OlRpAiau|CG7T59EsJ{?t_OrlMe>U8nZcrzdNuk6gDvhm zb=cf{1Mr}TXw_+=)6^Q7$< zF18CVBs)4&+M=EbB=a6U1_F9xPdI&f=@hJ#UTtEKp$*uAAa?}Wl8%?76ZJYULjm-L zn2tumgBYM!%bnp;hJ}U-y+#xpzwk8MIlcBWfT?*ekP0CBi0>v50b$(Ph2n%Rlssst^ialS*dt*#>O@C|#uII+blm+2)&m1f z<>aZU`6355RiQWE<_0W{Xl>vp6axe`TXd59kPi?@m84G6m%o1grQK}6iPt;v33vG5 z7m#U77NgyGho3Nzp6JmZTl0j0G>5*5V+$}~GGtV8>Lp(AKv0{+R#RK}IAIE=OSq8c zYoYM~5`Exg-b4e5gU*j@Z4M#PAwG$}&NCzzig;sGOLKsL!x3d`E-YS?9EiCj3<<0sQ0_awH*8q_$@*!qhuT{r>zXR5H*( zw#`ht!Gwtr^W+)|ZIufVN~Gvwrk1M z%}}E!>ElzjWrJjxoS@lBT7@x^xh$He^b~gw5ZIbDh$SOlCk$+H;v{D7h&Bl}!nxim^X4RCthnp! z46RJWmuToS2Djt^jzO~QfBwQ0`WV^@;wE}<`jhlE(@o_7P2}2ITdvH@Rb!nG|6x!A zo|7K#aCADk0&>(Er;9$p1V)$e#^usVI8KpJqqK05a(spz$b;RI1@uZZ>)nMGNYVG? zxqaZoLKhe4O1!NldQGz8`6i&~HE9X=%Ob!DM;6b$UZ??EEdU|kqz}9%QH9!W>jXmy zIee5isR6H3J9XU%rkx{UN^-9g?1K_Dx_nVO1d-|U-vuJ$$poj<@VFps7!l9I*%?!V zM-$0WqJJ$W1PBuFb0gBNQFs{8tE-n~Xb4kFD3{e_7ogo%6Z|3xbt(C=CJ+xwvOaUW zp+S$56C_(1(A|((zUntnEN0HPi=;yYDn7|^8Z{Y55Pi6FS#t2UeWWWMTX4{oDE&A+ zo5WyBEzvU@OuK~*!*AA%amZ5jfMprYK0>OiR)2FP(8q1wU04EBEuo&fC=|q|$u4*Q M4@-MHs3+9`0GDJ!zW@LL literal 0 HcmV?d00001 diff --git a/src/simurg/cn/data/mask_GRCh37.bed b/src/simurg/cn/data/mask_GRCh37.bed new file mode 100644 index 0000000..3504346 --- /dev/null +++ b/src/simurg/cn/data/mask_GRCh37.bed @@ -0,0 +1,26 @@ +# centromeres, gvar/stalk bands, acrocentric p-arms; derived from UCSC hg19 cytoBand +1 121500000 142600000 +2 90500000 96800000 +3 87900000 98300000 +4 48200000 52700000 +5 46100000 50700000 +6 58700000 63300000 +7 58000000 61700000 +8 43100000 48100000 +9 47300000 65900000 +10 38000000 42300000 +11 51600000 55700000 +12 33300000 38200000 +13 0 19500000 +14 0 19100000 +15 0 20700000 +16 34600000 47000000 +17 22200000 25800000 +18 15400000 19000000 +19 20000000 32400000 +20 25600000 29400000 +21 0 14300000 +22 0 17900000 +X 58100000 63000000 +Y 11600000 13400000 +Y 28800000 59373566 diff --git a/src/simurg/cn/data/mask_GRCh38.bed b/src/simurg/cn/data/mask_GRCh38.bed new file mode 100644 index 0000000..db1af68 --- /dev/null +++ b/src/simurg/cn/data/mask_GRCh38.bed @@ -0,0 +1,26 @@ +# centromeres, gvar/stalk bands, acrocentric p-arms; derived from UCSC hg38 cytoBand +1 121700000 143200000 +2 91800000 96000000 +3 87800000 98600000 +4 48200000 51800000 +5 46100000 51400000 +6 58500000 62600000 +7 58100000 62100000 +8 43200000 47200000 +9 42200000 61500000 +10 38000000 41600000 +11 51000000 55800000 +12 33200000 37800000 +13 0 18900000 +14 0 18200000 +15 0 20500000 +16 35300000 47000000 +17 22700000 27400000 +18 15400000 21500000 +19 19900000 31900000 +20 25700000 30400000 +21 0 13000000 +22 0 17400000 +X 58100000 63800000 +Y 10300000 10600000 +Y 26600000 57227415