diff --git a/Pilot1/ST1/VocabFiles_spe/SPE_ChEMBL.txt b/Pilot1/ST1/VocabFiles_spe/SPE_ChEMBL.txt
new file mode 100644
index 00000000..65da6743
--- /dev/null
+++ b/Pilot1/ST1/VocabFiles_spe/SPE_ChEMBL.txt
@@ -0,0 +1,3002 @@
+c c
+C C
+O )
+c 1
+c (
+C (
+= O)
+c 2
+C )
+cc cc
+c 3
+C( =O)
+cc c(
+) cc
+( C)
+( =O)
+2 )
+cc (
+C 1
+F )
+N (
+CC CC
+c1 ccc(
+3 )
+C O
+c n
+c1 cccc
+c2 cccc
+c 4
+C N
+C(=O) N
+O C)
+)cc 1
+c2 )
+C 2
+n 1
+n c(
+C( C)
+c2 ccc(
+N )
+[C@H] (
+[C@@H] (
+c2 c(
+= C(
+CC 1
+c1 )
+Cl )
+c3 cccc
+N C(=O)
+cc 1
+O CC
+c1 c(
+c1 cc
+c1 cc(
+= C
+S (=O)
+CC N(
+( F)
+c3 )
+N 1
+n 2
+= O
+c3 ccc(
+S(=O) (=O)
+c3 c(
+CC (=O)
+CC (
+/ C
+c1cccc c1
+C( F)
+F )cc
+c2 cc
+c2 n
+CC C
+N 2
+4 )
+c2cccc c2)
+O C
+Cl )cc
+O =C(
+C(F) (F)
+c1 n
+c( =O)
+c2cccc c2
+(C) C)
+c2 cc(
+C( N
+c1 (
+[C@H] 1
+=C /
+= N
+n (
+[C@@H] 1
+C 3
+CC )
+CC O
+CC N
+CC 2)
+1 )
+C #
+c1 2
+CC 2
+C N(
+c1cccc (
+c( -
+CC (C)
+c3cccc c3
+c( C)
+cc 2)
+N C(
+cc 2
+( O)
+c1cccc c1)
+[C@H] 2
+C c1ccc(
+c( OC)
+C(=O) O)
+c3cccc c3)
+[C@@H] 2
+n 2)
+nc( -
+C(C) C)
+c4 cccc
+)cc1 )
+O =
+/C =C/
+c3 cc
+C 2)
+CC C(
+c 5
+3 )cc
+CO c1ccc(
+CN 1
+[O-] )
+C O)
+C(F)(F) F)
+cc1 )
+[C@H]( O)
+n c2
+c( N
+[C@@H]( O)
+C( O)
+c3 cc(
+CC(=O) N
+c s
+CC1 )
+/ C(
+CC 3)
+[N+] (=O)
+C S
+c4cccc c4
+c1cc 2
+c3 n
+c( O)
+2 )cc1
+CC CN
+nc( N
+CC OCC
+cc 3)
+(C) C
+(=O) =O)
+n 3
+C1 )
+n c1
+S )
+C# N)
+cc c1
+/ N
+)cc (
+C(=O) O
+[C@H] 3
+CCCC CCCC
+( N
+c1 cn
+C 3)
+Br )
+)cc c1
+c2 c1
+O=C( N
+cccc 1
+[C@@H] 3
+c2cccc (
+C(C) (C)C)
+c1cc c2c(
+c4 ccc(
+CN 2
+C =
+- c2ccc(
+- c2
+C(C) =O)
+c( Cl)
+CO C(=O)
+)cc 2)
+C [C@H](
+n (C)
+C( N)
+=C \
+n1 )
+C(C) (C)
+cc 3
+c o
+S (
+OCC )
+CC N1
+c [nH]
+C( =
+n cn
+C n1
+C(F)(F) F)cc
+O C(=O)
+[C@H] (C)
+( [O-])
+C c2ccc(
+[C@@H] (C)
+c4 c(
+OC) c(OC)
+C(=O)N 1
+)cc 2
+CN C(=O)
+nc( C)
+2) c1
+=O) cc1
+S(=O)(=O) N
+CC 3
+C [C@@H](
+C(=O) N(
+Cl )cc1
+n n
+C c1
+O= C1
+C(=O)N 2
+S(=O) (
+C c2ccccc2)
+O CO
+C 4
+CN (C)
+C1 =O
+c4 )
+=N /
+C c1cc
+c2 cn
+5 )
+cccc 2
+cc( -
+)cc 3)
+[N+](=O) [O-]
+C1 (
+c1ccc2c( c1)
+F )cc1
+C c1cc(
+c1cccc 2
+c1cc2 c(
+n 3)
+CO c1cc(
+CC C)
+c2cc 3
+cc (C)
+C(O) =O)
+C c1ccccc1)
+[C@] 1
+n c3
+- c2n
+c2ccc( Cl)cc
+[N+](=O) [O-])
+O C(
+CCN( C(=O)
+CC(C) (C)
+[C@@] 2
+CC C1
+N 3
+=O) c1
+cccc 2)
+[N+] ([O-])
+= C2
+C# N
+c( F)
+[C@] 2
+n( -
+s 1
+O 1
+CC C2
+o 1
+C c1ccccc1
+cc c2
+(C) CC
+c( N)
+[C@@] 1
+CC( O)
+CCO C(=O)
+N C(=O)N
+C c1n
+c4ccccc4 )
+cccc 3)
+c1 c2c(
+cn 1
+F)cc 2)
+C c1c(
+CC (C)C)
+nc( N)
+C [C@H]1
+O=C( O)
+N =C(
+c3cccc (
+C1 CCCC
+= C1
+C n2
+= S)
+c2cc c3c(
+CC( N
+- n2
+CCN( C
+c3ccc( Cl)cc
+c2 )cc1
+Cl) c(
+c(=O) [nH]
+c3 cn
+C(N) =O)
+c3ccc( F)cc
+P (=O)
+( C
+N (C)
+n2 )cc1
+c1c( C)
+CCC N(
+c2 [nH]
+CCCC C2)
+c2c( C)
+CC [C@H](
+3)cc 2)
+c2 s
+O [C@H](
+C [C@@H]1
+OC) c1
+C) cc1
+C2 =O)
+c4 cc
+CC CO
+c2) c1
+N S(=O)(=O)
+Cl)cc (
+c12 c(
+=N \
+c2 3)
+c1 nc(
+/N =C/
+C) =O)
+N #
+cccc c1
+3 )cc1
+N2 CCN(
+N1 CCN(
+CC(=O) O)
+=C( \
+OCC (=O)
+c1 =O
+(C) (
+CC 4)
+CC2 )cc1
+CCN (C)
+c1 -
+n cc
+c2ccc( -
+[C@] 3
+S (C)
+O (
+C c1cccc(
+CC NC(=O)
+N( C(=O)
+c2 1
+c2ccc(Cl)cc 2)
+c1 s
+cc c3
+CN 3
+CCCC )
+cc c2)
+F )cc1)
+cn 2
+CC 4
+C(=O)N [C@@H](
+c4 cc(
+C 4)
+Cl )cc1)
+[N+]([O-]) =O)
+CC O)
+[C@H] 4
+c( S
+CC S
+CC CN1
+Cl) c1
+c2 o
+[C@@H] 4
+C(=O) OC)
+c2 nc(
+c1ccc( Cl)cc1
+CCCC 1
+n n1
+c2ccc3c( c2)
+C [C@H]2
+n o
+c2ccccc2 1
+[C@@] 3
+C2 (
+c5 cccc
+CC n1
+C) cc2)
+CC N2
+c1ccc( N
+3)cc 2
+N) N
+cccc 3
+cccc 1)
+CCCC 2)
+c2cc( -
+c( C(=O)N
+OC) =O)
+c2cc3 c(
+c3ccc(F)cc 3)
+C [C@@H]2
+C2 =O
+/C =C\
+n( C
+S(C) (=O)=O)
+cn 2)
+cn c1
+Cl) c(Cl)
+c2ccc( OC)
+N1 (
+c2cc cn
+c2 c3c(
+cc c1)
+O) cc1
+( -
+c1ccc( -
+c2ccccc2 )cc1
+cn c3
+c3ccc(Cl)cc 3)
+c(C) c1
+n [nH]
+)cc 3
+OC) cc(
+CCOCC 2)
+N c1n
+c2 =O)
+= C(C)
+CO c1cccc(
+O C(C)=O)
+CC C(N
+c2ccc( F)cc2)
+c2cc n
+F) c(
+c2 nc(-
+P(=O) (O)
+N( C(
+CO c1ccccc1
+N C
+CCCC C3)
+CCN( CC)
+n cc1
+OCC O
+c2) =O)
+s 2)
+O [C@@H](
+n 4
+C(= S)
+/C =N/
+CC C(=O)N
+O) c(
+CCOCC 3)
+N (C)C)
+C1 2
+C2 )cc1
+c2 n1
+CCCC 3)
+CC =
+nc( S
+CN( C(=O)
+N( C
+n2) c1
+c1ccc( OC)
+C =C
+=O) =O)
+[nH] 1
+/C( =C/
+c3ccc( OC)
+CC [C@@H](
+/C( =C\
+cc 4
+CN C(
+O c1ccc(
+c1 [nH]
+C1 =O)
+c3ccc( C)
+c2cc (C)
+CCC 3
+c5cccc c5
+c2 cc1
+CC2) c1
+O) c(O)
+CCCC 2
+c1cc (C)
+c1ccc( O
+C2 =N
+cc2 )cc1
+F)cc 2
+c2n (
+C1 CCN(
+c3cc 4
+c2cccc c12
+cc 4)
+N) =O)
+[C@]1 2
+NC(=O) [C@H](
+c1 (C)
+C1 CN(
+C c3ccccc3)
+c1 nc(-
+OC)c(OC) c(OC)
+[C@] 4
+Cl)cc 2)
+N2 C(=O)
+C3 =O)
+C) c1
+c2cccc 3
+c2c( -
+N c1ccc(
+CCCC C1
+C( O
+S(=O) (N
+CC(=O) O
+cc c3)
+CC C(C)
+C S(=O)(=O)
+c1c( O)
+c3 [nH]
+OCC) =O)
+OC) c(
+C(=O) OC
+[C@@H]1 O
+c2n cn
+c 6
+s 1)
+C1 =C(
+CCCN 2
+C [C@@H](O)
+CCC 2)
+(=O) =O
+o c(
+( O
+N( CC)
+c(=O) n(
+n n2
+/C =C
+c2c( =O)
+C [C@H](O)
+-c2 cn
+c2c( cccc2)
+c3c( C)
+c1 O
+- c2ccccc2)
+- c1ccc(
+NC( =S)
+C(C) C
+CCO CC1
+=C( /
+C(=O)N C
+c3c( cccc3)
+( C(F)(F)F)
+[n+] 1
+CC1 (C)
+cc( O)
+- c2cc(
+N 4
+O 2)
+C( OC)=O)
+CCCC (=O)
+- 2
+cn 3)
+c3ccc( -
+= N)
+CC #
+c2) CC1
+[C@@H](O) [C@H](O)
+C(=O)N [C@H](
+c( NC(=O)
+c1cc2c( cc1
+c2 nc(N
+C c1cn
+C2 CC2)
+O 2
+C(=O)N 3
+N1 C(=O)
+[C@@H]( CO)
+c1ccc( Cl)cc1)
+c3 s
+/C( =N\
+C =C(
+S(=O)(=O) N2
+CCO c1ccc(
+/C =C2
+(F) (F)
+[C@H]1 O
+CC [C@H]2
+cs 1
+c2ccc(OC) cc2)
+c3 o
+C1 C(
+n c2)
+c2cc co
+cs 2)
+c2c( O)
+F)cc (
+[C@]2 (C)
+[C@@] 4
+[C@@]2 (C)
+O[C@H]( CO)
+c1c( Cl)
+c2cc( Cl)cc
+Cl)cc 2
+CCCC (
+ccc( -
+C1 N(
+c1 C
+c2cccc( Cl)
+Cc1cc (C)
+C1 =
+cn 1)
+CC(=O) N1
+n1 c(
+c1ccc( F)cc1
+cccc 4)
+c1 2)
+S( N)
+CN1 CCN(
+CCC( O)
+C3 CC3)
+c3cc c4c(
+c1c( OC)
+CC C(=O)O)
+C(=O) OCC)
+Br )cc
+n cc(
+c1 o
+n n2)
+O CCCC
+- c1ccccc1
+C2 =C(
+C2 CCCCC2)
+C1 (=O)
+c2ccc( C)cc2)
+c1cc2c( cc1)
+/C =C(\
+nc2 c1
+c3cc n
+c2ccc( O)
+C1 =N
+S 1
+C) cc1)
+( CC)
+C(=O) C(
+CCN 3
+c2ccc(Cl)cc 2
+cn c2
+C c2ccccc2
+C [C@H]3
+n cc2
+CS c1n
+CO C(
+c3ccc(OC) cc3)
+c3 c2
+c2c( Cl)
+CCC 3)
+[C@@] (C)(
+Br )cc1
+C(F)(F) F
+CC c1ccc(
+[C@@H]( N)
+C(C) (C)C
+c(N 3
+c(=O) c(
+C2 CCN(
+c3cccc c23)
+C(=O) OCC
+S(N) (=O)=O)
+s c1
+o 2)
+C( OCC)=O)
+/ C(C)
+c1 nc(N
+N C(N
+CN1 C(=O)
+S (N
+CN )
+Cl)cc c1
+C( c2ccccc2)
+CO c1cc
+c2ccn cc2)
+OCO 2
+OCO 3)
+c(OC) c1
+c( O
+c3 4)
+c4 n
+OC)c1 OC
+4 )cc
+I )
+c1) =O
+n 4)
+C [C@@H]3
+c4 cn
+c5 c(
+N) N)
+CCCC C1)
+OCC(=O) N
+- c2ccccc2
+[C@@H]( NC(=O)
+N2 CCOCC2)
+N1 CCC(
+C( CC)
+CC2) =O)
+n2 c(
+CCO CC1)
+C# C
+[nH] c(=O)
+C= C1
+C(=O)N (C)
+CN( C
+O) cc1)
+[C@] (C)(
+O) c1
+cc2 c(
+F) c(F)
+[C@@]1 2
+cccc (
+c2ccc( C)
+c2 c[nH]
+s 3)
+C(=O)N )
+N( CC
+n c12
+N CC
+c2n cc
+CCN (C)C)
+n(C) c(=O)
+c3ccccc3 2)
+c1 =O)
+c3n cn
+O C1
+c3ccc(C) cc3)
+P (O)
+ccc( OC)
+/C( =N/
+c3cc (C)
+c( C#N)
+c3ccc( O)
+o c(-
+C(F)(F) F)cc1
+C2 =O)cc1
+c1ccc( F)cc1)
+( CC
+C(=O)N CC
+c2ccco 2)
+O c2ccc(
+C(= N)N
+=O) cc2)
+c3cc4 c(
+C(C) (
+c2 C)
+CCCCCCCC CCCC
+Br )cc2)
+=N /N
+C( c1ccccc1)
+C c2c(
+O [C@H]1
+[C@]3 (C)
+4 )cc3)
+C1 CC
+C =O)
+[N+] (C)
+CC [C@@H]1
+c3 2)
+c1( N
+C( N1
+c4ccc( F)cc
+c2) n1
+C(=O) (
+C2 =
+O [C@@H]1
+c1ccc( NC(=O)
+C c2cc(
+c( Br)
+n c3)
+c3ccc4c( c3)
+c2n c3c(
+5 )cc
+CC [C@H]1
+- c1n
+c2n cc(
+c(Cl) c1
+c2cccc n2)
+c1c( F)
+C1CCCC C1
+=O) ccc1
+N C(C)=O)
+c5 ccc(
+n1 cn
+[n+] 2
+n c1)
+O 3)
+c2cc cs2)
+c1cc( -
+[n+] (
+c3cc cn
+C(F)(F)F)cc 2)
+CC1 (
+[C@]2 (
+c3cc( Cl)cc
+O= [N+]([O-])
+CC(=O) N(
+c1 c[nH]
+cc c4
+c2ccccc2) c1
+cs 1)
+c2ccc( O
+CN (C)C)
+[nH] 2)
+cc( OC)
+c3cc co
+c3 n(
+n c4
+C1 CC1
+CC(O) =O)
+O 1)
+c1cc( OC)
+3 C)
+nc(N 3
+C( N2
+c1cc co
+2 )ccc1
+/N =C(\
+CCC2 (
+n c2c(
+CC( CC(
+CC [C@@H]2
+c3ccccc3 )cc2)
+OC 3
+[C@] (
+CCN( C(
+CCCC 1)
+C 5
+CC [C@H]3
+c4ccc( Cl)cc
+c( C(N
+c2ccccc2) CC1
+OCC (
+C(=O) /C=C/
+[C@@] (
+4 CCCC
+cs 3)
+n1 cc(
+N=C( N)
+/C=C2 \
+/ C1
+c2c( F)
+=C1 \
+c3c( =O)
+c3 c4c(
+)cc c2
+c1c( N
+Cl) c3)
+nc( O)
+c2n c3ccccc3
+C( C(=O)N
+C n3
+C(F)(F)F) c1
+c3ccn cc3)
+C(= C)
+c1cc cnc1
+c1cccc2 c1
+[N+](=O)[O-] )cc1
+c1c( -
+CC(=O) N2
+O) =O)
+c2ccc( N
+O (C)
+CC) =O)
+ccc( C)
+c3cccc 4
+[C@]1 (C)
+CC= C)
+CCCC C3
+n2 cn
+S(=O) (C)
+C(C) =O
+O= S(=O)(
+c(=O) o
+c2 nc(C)
+N [C@@H](
+CC c1n
+CC 3)cc
+c2) C1
+O C2
+= C)
+c2cccc (F)
+CCC 4
+n n(
+[nH] c(
+c2c( c1)
+n1 2
+[C@H]( NC(=O)
+c1c( =O)
+c1cc( N
+c3ccco 3)
+C( C(
+P(=O)(O) O)
+CC(C) (
+c2cc3c( cc2)
+c3cccc n3)
+[C@@]1 (C)
+C[C@H]( NC(=O)
+ccc( F)
+CCCC C2
+CCOCC 4)
+CCN1 C(=O)
+CC C1)
+S C)
+c(C) c(
+C1CCCC C1)
+c5 )
+CO c1c(
+c2c( OC)
+c1cccc (F)
+C1 CC(
+OC(=O) C)
+[C@@]2 (
+c4cccc (
+C3 CCCCC3)
+n nc1
+c1ccc(OC) cc1)
+(O) (
+cccc 4
+c2c( cc(
+s c(
+n o1
+CS c2n
+[C@H]( CO)
+CO c1cc2
+c3n cc
+c2cccc c12)
+C [C@@H](C)
+c(F) c1
+C /C=C\
+CC S(=O)(=O)
+CC OC
+CN (C)C
+c1cn (
+CO C)
+= CC(=O)
+[C@@H]1 2
+CC2 (
+(C) c1
+CC [C@]4
+nc( NC(=O)
+n1 (
+C(=O)N c2ccc(
+c3 =O)
+CCCN C(=O)
+c1 (=O)
+Cc1 c[nH]
+c1n (
+c1n cc(
+c2cc( OC)
+cn c1)
+CCCC N
+CCN (C)CC
+c(- c3ccc(
+[C@]1 (
+ccc( N
+o 1)
+N1 CC
+c(- c2ccc(
+CCCC CC
+[C@@H] 5
+6 )
+F)cc (F)
+c1( OC)
+c1cc( O)
+C( c1ccc(
+NC(=S) N
+c3) =O)
+[C@@]3 (C)
+c( OCC
+C(=O)N c1ccc(
+OCO 4)
+O C(C)(C)C)
+F)cc c1
+c2cccn c2)
+=C 3
+O [C@@H]2
+c2 )ccc1
+C c3ccccc3
+c3ccc(Cl)cc 3
+c1 cs
+c -2
+C(=O)O) cc1
+c2ccccc2 c1
+c2 3)cc1
+C2) c1
+OC)cc( OC)
+-c2 nc(
+n2) CC1
+c2ccccc2 n1
+[C@@]1 (
+n cc1)
+c3cc( -
+c1ccc(OC) cc1
+C3 (
+4) CC3)
+CCCN 3
+c1) =O)
+Cn1 cc(
+n n1)
+c1n cc
+F C(F)(F)
+C#N )cc
+N c1ccccc1
+C1 (C)
+P(=O) (
+c3c( Cl)
+[C@H]1 2
+C(N) =N
+c(- c3ccccc3)
+[nH] 3)
+c2cccc( -
+c1( -
+c2ccccc2) =O)
+C( NC(=O)
+/C=C(\ C)
+c(=O) n1
+c3cccn c3)
+c2cccc( C(F)(F)F)
+C(N C(
+O C(C)(C)
+C(=O)N C(
+C(F)(F)F)cc 3)
+CC C(=O)
+CO c2ccc(
+n(- c2ccccc2)
+OC c1ccccc1)
+C( N(
+CC [C@@H]3
+3) c1
+)cc( OC)c1OC
+C c2n
+[N+] (
+P (
+c3 nc(
+CCC n1
+C(F) F)
+CN2 C(=O)
+S(=O)(=O)N 3
+c(O) c1
+s c2
+[C@H]( N)
+3 c(
+c1( Cl)
+[C@H](O) [C@H](O)
+=O) ccc(
+n cc3
+cc cn
+CCCC 3
+/C=C/ C(=O)
+c3cc cs3)
+c2ccccc2 Cl)
+c1n c2c(
+CN2 CCN(
+c(- c2ccccc2)
+CC (F)(F)
+C(=S) N
+c3c( F)
+N) ncn
+Cl c1ccc(
+)cc 2)cc1
+o c(=O)
+c5ccccc5 )
+O [C@H]2
+c1cccc( Cl)c1
+[N+](=O)[O-]) c1
+N2 CCC(
+C1 C2
+CCC [C@H]1
+S 2
+[C@H]1 CC
+CN( C(
+c3ccc( Br
+C(= N)N)
+cn (
+Br )cc1)
+Cl) c1)
+N1 CCOCC1
+Cn1 cn
+C(=O) C)
+C(N [C@H](
+c1cc( Cl)ccc1
+(O) =O)
+c1ccc( OCC
+nc2 1
+CO c1ccc2c(c1)
+c2cc c3ccccc3
+CN(C) C(=O)
+C4 CC4)
+CC1) =O
+c3ccc( O
+c3 C)
+c1 (F)
+O= S(
+C( CCCC
+CC2 )ccc1
+[C@@H]( NC(
+c3ccccc3) CC2)
+c2ccc( N3
+O=C(N c1ccc(
+cc3 c(
+C) =O
+CC1 =C(
+c2 c1)
+n3 c(
+(=O) o
+=O) C
+c2ccc(O) cc2)
+cc( N
+O=C( /C=C/
+C(=O)N O)
+c2cc( O)
+c( NC(
+CC c1ccccc1)
+C 5)
+C[C@H]( N)
+[S+] ([O-])
+c2 =O)cc1
+=O) CC1
+OC) cc2)
+C= C(C)
+c2 cs
+/C =C(/
+c3 nc(-
+c2cc( F)cc
+c3 )cc2)
+C2 CCCC2)
+o 3)
+C(O) (
+Cc1ccc( NC(=O)
+C2 3
+S(=O)(=O) c1ccc(
+C1 =C(C)
+C(N [C@@H](
+C(F) (
+o 2)cc1
+c2ccc3c(c2) OCO3)
+n2 C)
+c2cccc(Cl) c2)
+n1 C
+c2n cccc2
+[C@@H]1 CC
+[nH] 1)
+n2 )ccc1
+c3cc cnc3
+= S
+Br )cc(
+c2ccccc2 F)
+c2ccc( F)cc2
+c2ccc( Br)cc2)
+- c1c(
+Cc2ccc( -
+c2ccc( OCC
+/C =N/N
+C(C)C) =O)
+C(F)(F) F)cc1)
+P(=O)(O) O
+c1cc ncc1
+c(O) c(
+# N)
+CCN C(
+3)cc (
+n n3
+c -
+CC2) C1
+c3cc( OC)
+Cn1 c(=O)
+CC2) CC1
+C [C@H](C)
+C1 CC1)
+OC [C@H]1
+= [N+]
+(C) (O)
+[C@H] 5
+1 C
+C#N )cc1
+c1( O)
+c1c2c( ccc1)
+[n+] ([O-])
+[N+](=O)[O-] )cc2)
+nn 3)
+/ c(
+CN 4
+c4ccc(F)cc 4)
+F c1ccc(
+s 2)cc1
+Cc1 nc(
+c( N2
+C [C@]12
+OCC 2
+c1cc c2[nH]
+O) cc2)
+[C@H]2 O)
+c2ccc( NC(=O)
+c1) N
+c4 [nH]
+=O) cc(
+c1 nc(N)
+CC OC)
+C= C2
+3)cc 2)cc1
+N(C) C(=O)
+c3c( O)
+c1cccc n1
+(=O) N
+nc2 n1
+c1cc( -c2ccc(
+c1cc2 cccc
+C( C
+Br )cc2
+c1c( -c2ccc(
+C( \
+O=C1 N
+c2cc3c( cc2
+C( Cl)
+c1 nc(C)
+C2 CCCC
+CC 5)
+c3ccc(O) cc3)
+c3c( -
+c1 N
+c1ccc( -c2ccc(
+c3c( cc(
+CC c1ccccc1
+/C=N/ NC(=O)
+n( -c2ccc(
+c3ccc(F)cc 3
+ccc( Cl)
+CO c1cc2c(cc1
+C(F)(F)F)cc (C(F)(F)F)
+C1 O
+c2cccc (C)
+c1cc( NC(=O)
+C c3ccc(
+C( C#N)
+C(=O)O C(C)(C)C)
+C(=O) c1ccccc1
+CC(C)(C) O
+c3cccc (F)
+CCCCCCCC CCCCCCCC
+c2 F)
+CC= C(C)C)
+O c1c(
+C( OC)
+CC c2ccccc2)
+c2 )cc(
+=O) cc2
+c4ccccc4 3)
+Br) c1
+(F) F
+C(N) =O
+n1 c2c(
+=C( O)
+n nc2
+c4cccc c34)
+/C=C /C
+Cc2ccc( F)cc2)
+c1cccc n1)
+O= c1[nH]
+n(- c3ccccc3)
+C( C(N
+[C@H]3 CC
+O[C@H](CO) [C@@H](O)
+CCCC C)
+- c2cc
+c1ccc( C)cc1)
+ncn 2
+c(=O) n2
+c2cccc( OC)
+nc1 -
+c2cc3 cccc
+C4 CCCC
+=O) cc1)
+c( C(F)(F)F)
+O C(C)C)
+c3 c2)
+o c1
+c2ccccc2 1)
+c3 )cc
+c2 c3ccccc3
+C(F)(F)F)cc 2
+c2n (C)
+2) CC1
+s c2c1
+CCC3 (
+c1n cn2
+)cc1) =O
+c4c( cccc4)
+/C(C) =C/
+COc1ccc( NC(=O)
+[C@H]1 (
+[C@@] 5
+Cl)cc( Cl)
+= N1
+c3 )cc2
+O= S(=O)(N
+C1CCCC 1
+c1ccccc1 -
+n2 cc(
+c1( -c2ccc(
+S CC(=O)N
+[N+](=O)[O-] )cc
+N# Cc1ccc(
+c12c( cccc1)
+OC c2ccccc2)
+C(N 3
+C1 C
+c2 Cl)
+c1ccc( -c2n
+CCCN( C(=O)
+c1ccc( -n2
+CN2 CCC(
+c1c( NC(=O)
+CN C
+N (C)C
+c3n c4ccccc4
+c(=O)[nH] c1=O
+[C@H](O) [C@@H](O)
+=O) C1
+c3 c[nH]
+C(=O) C1
+c3cccc( Cl)c3)
+-c2 o
+N [C@H](
+OC c1ccccc1
+O CC1
+n1 c(-
+c3cc( F)cc
+-c2 cs
+c1ccc( O)cc1
+O[C@H](CO) [C@@H](O)[C@H](O)
+C#N )cc2)
+)cc (C)
+c4ccc(Cl)cc 4)
+[C@@]2 3
+ccc( O)
+C c1ccc2c(c1)
+Cc1cc co
+CC( NC(=O)
+Cc2ccc( Cl)cc2)
+c2 O)
+c3n cc(
+C(=O) C2
+c1cc cs1
+CCCN (C)C)
+n c3c(
+[C@]2 3
+C1 CO
+nc1 N
+C(=O) C
+CCN(C) CC3)
+c2n cnc3
+CN1 CCC(
+c2cc( OC)c(OC)c(OC)
+c( C(=O)O)
+c2 nc(N)
+[n+] (C)
+C3 =N
+c2cc( NC(=O)
+cc2 1
+c(C) cc1
+CCN1 CCN(
+C2) C1
+c2cc c1
+S(=O)(C) =O)
+C= C)
+C(=O)N1 CCN(
+n2 cc
+[C@@H]1 (
+c3ccccc3 )cc2
+CN S(=O)(=O)
+c4ccc( OC)
+C( CO)
+(C) (C)
+C( /C=C/
+cc2) c1
+c2 N
+CCCN1 C(=O)
+c1) C
+=C1 /
+OCC (O)
+)cc1 2
+c1ccc( N2
+C) c(
+c2c( N
+cc2 c1
+N c1nc(
+[C@]3 (
+[C@@H]3 CC
+n3 cn
+N=C( N)N
+o n1
+C(=O)N (C)C)
+cc n1
+[C@@H]( OC(C)=O)
+S(=O)(=O) O)
+c3 nc(N
+cn 3
+c2cc( OC)c(OC)
+N( CC(=O)N
+C3 CCCC3)
+[nH] c(-
+cc c4)
+CC(C) =
+O c1ccccc1
+Cc1ccccc1) NC(=O)
+c2c( c1
+[C@@H]2 CC
+c3c( OC)
+C2 =O)c1
+C1 CCC(
+C( S
+c4ccc( C)
+OC) cc1
+C c2cn
+n n(C)
+CC( N)
+c3ccc( N4
+C(C)C) cc1
+c1n cn
+CCC O)
+c1ccccc1) c1ccccc1
+Cl)c(Cl) c1
+n1 cc
+3) CC1
+C( C(=O)O)
+ncn 1
+CN1 CC
+c1ccco 1)
+C12 CC3
+[C@@H]( N
+N2 CCCCC2)
+C3 =C(
+c3cc( O)
+[C@H] (C)C
+c12 ccccc1
+c3cc( OC)c(OC)
+2 )cc(
+C(=O)N2 CCN(
+[C@H]( O
+c2cccc3 cccc
+N1 CCCC1
+c(S CC(=O)N
+CCOCC 2)cc1
+c12 cc(
+[C@@H]( O
+C2) CC1
+=O) [nH]
+c3ccc(Br )cc3)
+c(=O) n(C)
+C( CO
+C(= N)
+c3ccccc3 Cl)
+c( C(=O)
+cc c2c1
+c4cc cn
+N c1cc(
+Cc1 o
+OCO 2)
+c1ccco 1
+Cc1c( C)
+c3ccccc3) =O)
+CC 3)cc2
+= [N-]
+c1cc cnc1)
+C(C)(C)C) =O)
+c( CC)
+c1cccc(F) c1
+CC 5
+4 CCOCC4)
+CCN(C) CC2)
+3)cc c1
+c3 nc(C)
+[C@@]3 (
+c2ccccc2 )cc1)
+[C@@H]( CC
+CCC2( CC1)
+C(F)(F)F) c3)
+c1cc cs1)
+[C@H]( OC(C)=O)
+c2cc( N
+P(O) (=O)
+=C( N)
+/N =N/
+n nc(
+CO 2
+C(=O)N( C
+c1ccc( C)cc1
+CC# N)
+O c3ccc(
+cccc c12
+S(=O)(=O) C)
+c1( NC(
+CC[C@]4 (C)
+CCCC N)
+[nH] c1
+CCCC NC(=O)
+( c2ccccc2)
+nc1 C
+c1cccc (C)c1
+c1c( N)
+cc c12
+(C)C) =O)
+C( CC
+c4ccccc4 )cc3)
+n2 C
+CCN CC3)
+c2c( N)
+CCCC O
+CCCC C
+c3n cccc3
+c1cc( C(=O)N
+Cl)cc 3)
+s c3
+c2cc1 OC
+c(C) c(C)
+/C=C2 /
+c1cc ncc1)
+c2nc(N 3
+c3ccc( OCC
+c2c(Cl) cccc2
+2 )cc1)
+O C(C)
+O= c1
+4) =O)
+[nH] c2
+C(=O)N1 CCC(
+[C@] 5
+[C@@H]( CO
+C3 =
+c3ccccc3 2)cc1
+c4ccccc4) CC3)
+CC( N)=O)
+c2cc( Cl)c(
+c2cccc (N
+[C@H]3 O)
+c2n c1
+)cc2 c(
+N =C1
+CC2) n1
+c5 cc
+cc2) =O)
+c1cccc( NC(=O)
+OCCO 2
+c1cc( Cl)c(
+[C@H]1 CC[C@H](
+n2) C1
+C /C=C/
+c( Cl)cc1
+ccc( Cl)c1
+C(C) =C(
+C /C(=N\
+C1) C2
+c1ccc( Br)cc1
+CCC S
+NC( N)
+CN( CC)
+3)cc c2
+C(N C
+)cc c3
+c(OC) cc1
+c( C
+nc(- c3ccccc3)
+O O
+c4ccc( O)
+C4 =O)
+S) =N
+cc1) =O
+=[N+] =[N-]
+C /C(=C\
+/N =C(/
+N2 CC
+O c2c(
+CCCN )
+2) C1
+Cn1 cc
+c3ccccc3 F)
+c1ccc( C(=O)N
+N =C2
+nc(S CC(=O)N
+CCCC N1
+C1CCCC 1)
+c1c(Cl) cccc1
+= C(C)C)
+n3 C)
+c1cc(OC) ccc1
+C(=O) (N
+F) c(Cl)
+c3cccc c23)cc1
+c3cccc (C)
+c1ccc( OC
+n1 -
+c1c(OC) ccc(
+Cc1ccc( O)cc1)
+c4cc ncc
+cccc c4
+c( =S)
+N(CC) CC)
+n n(-
+[C@@H]( C
+c1n c2ccccc2
+c2 1)
+c1cccc( N
+4 )cc3
+c(=O)[nH] c(=O)
+c2ccc( Cl)c(Cl)
+c1c( NC(
+O[C@H]( CO
+n3 cc
+Cc1ccc( Cl)cc1
+=O) =O
+c1n cccc1
+( Cl)
+/ C2
+o c(C)
+c1cc(C) ccc1
+c1( NC(=O)
+CC2 CC2)
+n 3)cc2)
+CCO 1
+c2cccc (O)
+Cc1 nc(-
+c2c(F) cccc2
+c1cc( -c2n
+N2 CCCC
+C( OCC
+/C=C 3
+CC1 2
+C(O) =O
+C[C@H]1 CN(
+= N)N
+[C@H]( CC
+C) ccc1
+c2 c1cccc2
+c1cn cc(
+c1c( Cl)cc(
+C3 CCN(
+c2cccc(F) c2)
+c3ccc4c(c3) OCO4)
+N C1
+CCO c1ccccc1
+N1 CCN(C(=O)
+F)cc 3)
+Cc1 cs
+c- 3
+n2cn c3c(
+N2 CCCC2)
+[C@@]4 (C)
+- c2c(
+c3cc( OC)c(OC)c(OC)
+c1c(Cl) ccc(
+n( CC)
+c1( C(N
+c5 cc(
+C( c1cc(
+[C@@H]( OC(=O)
+[C@@H](O) [C@@H](O)
+(=O)=O) cc1
+NC( =N)
+c1c( C(=O)N
+[C@@H] (C)C
+cn c(N
+CN CC
+N2 CCN(C(=O)
+N C1=O
+[C@@]1 (O)
+c2) ccc(
+ccc2 1
+S C
+NC(=O) C(
+CC3) =O)
+c2cc( C(F)(F)F)cc
+)cc n1
+[N+] 1
+NC(=O) c1ccc(
+CC [C@H](C)
+c4cc 5
+c3cc4c( cc3
+N1 CCCCC1
+CO 1
+c1cc( F)ccc1
+CC(=O)N c1ccc(
+CC 3)cc2)
+N CCCC
+CO c1ccc2c(
+-c2 [nH]
+c2cc(Cl)cc c2
+c2ccc( C(F)(F)F)cc2)
+COc1cc2c(cc1 OC)
+COc1ccc( -c2n
+o c2c1
+=C( N)N)
+cc2 )ccc1
+C3) C2
+C1 =C
+S(=O)(=O) N(
+CO C
+CC [C@]3(C)
+COc1ccc( C2
+C( c3ccccc3)
+c3ccc( N
+CC1 CC1)
+)cc( -
+n1 c(N
+CC(C) (C)C)
+n 3)cc
+c2c( Cl)cc(
+c1c(F) cccc1
+N2 C
+[C@H](C) CO)
+-c2 nc(-
+[N+](=O)[O-] )cc1)
+/C=C/ C(=O)N
+C c1cc2
+CC(C) C
+c1( -c2n
+CN C(=O)N
+C(=O)O 1
+C c1cccc2
+n n2)cc1
+c2cccc(C(F)(F)F) c2)
+c3cc c4ccccc4
+F C(F)(
+n2 c(=O)
+S(=O)(=O) c2ccc(
+Cc1cn (
+ccc(F) c1
+O [C@@H]3
+c3cccc(F) c3)
+CC N)
+c2o ccc2)
+CCC 4)
+C#N )cc3)
+Cc1ccc( C(=O)N
+OC[C@H]1 O[C@@H](
+c( C(
+n c4)
+C [n+]1
+F)cc 2)cc1
+[C@H](O) [C@@H]1O
+ccc( NC(=O)
+CC c1cc(
+c3ccc( C(F)(F)F)cc3)
+-c2 s
+[C@] (O)(
+c1n (C)
+CS )
+c(F) c2)
+C(O) C(O)
+CC1 CCCCC1)
+n1 c(=O)
+C) C
+N1 CCOCC1)
+[C@@] (O)(
+CC1 =O
+c1ccc2c(c1) OCO2
+CCN CC2)
+Cn2 cn
+[C@@]2 (O)
+c3 cs
+Cn1 c(
+c4 c(C)
+c2cccc 3)
+c2cc (=O)
+c2 C1
+c(=O)c( C(=O)O)
+Cc2ccccc2) CC1
+/C1 =C\
+n c2ccccc12
+CCCC CC)
+c1c2c( cc(
+c2c( n1)
+c1( C(
+Cc1ccc( F)cc1)
+n2 )cc(
+cccc1 2
+[N+](=O)[O-] )cc2
+c1c( C(N
+c2[nH] 1
+C(=O) c2ccccc2
+CO C(=O)N
+CCN( CC
+Cc1ccc( F)cc1
+n nc(-
+C1 CCCN(
+C[C@@H]( N)
+CCN CC1
+[C@@H]1 C
+C2) =O)
+[C@]1 (O)
+/C(=N/ O)
+cs 2)cc1
+c3cccc( OC)
+C( =C/
+C(=O) CC
+[C@H]( OC(=O)
+ccc( NC(
+c2n nc(
+c1 3)
+cccc 2)c1
+C(F)(F)F)cc (
+OCCO 3)
+Cc1 s
+c1n nc(
+c1cc( Cl)cc
+c4 3)
+[C@@]2 1C
+ncn 3)
+c2ccc( [N+](=O)[O-])cc2)
+CCN(C) CC1
+c2ccc( C(=O)N
+CC1) =O)
+c1cc( NC(
+c1cc( Cl)
+CC2 )cc(
+C Cl)
+[nH] c3
+c3ccccc3 )cc
+cc( NC(=O)
+c2cc( C(=O)N
+c1ccc( O)cc1)
+[N+](C) (C)C)
+C1 CC2
+C( CN
+cn 2)cc1
+cc2 C)
+CC3 (
+Cc1ccc( N
+C1) =O
+c1cc( Cl)cc(
+c(=O)[nH] 1
+c( OC
+o 2)c1
+c1c( -c2n
+COc1ccc( N
+/C =C1\
+c2cccc3cccc c23)
+N c1cccc(
+c1c( O
+Br )ccc1
+N =
+OC)c(OC) c1
+CC(F)(F) F)
+CC2 CCCCC2)
+cc( C(=O)N
+c3c(F) cccc3
+CC( C(=O)N
+/N =
+NC(=O) c1ccccc1
+c2c[nH] c3ccccc23)
+c(N C
+s 2)c1
+[C@H]1 CC[C@H]2
+c2 )cc1)
+N c1cc
+C23 CC4
+c12 cccc
+[N+](C) (C)
+[C@]2 (O)
+c3cc(Cl)cc c3
+C(C)(C)C) cc1
+cc n2)
+c1n nc(-
+c2cc s
+[C@H]1 C
+N3 CCOCC3)
+OCC N
+F)cc 3
+c2ccc( OC
+Cc1ccc( -c2ccccc2
+C1 CCN(C(=O)
+cc(C) c1
+c2ccccc2) C1
+c3ccc( [N+](=O)[O-]
+C(C)C) c1
+Cc1c[nH] c2ccccc12)
+c1ccc( Br)cc1)
+c4ccc( -
+C3 )cc1
+(F) F)
+CC3 CC3)
+nn n2
+Cc1ccc( S(=O)(=O)N
+Cc1ccc( -
+N) c1
+c1( N)
+nn n1
+ccc( O
+cc 3)cc
+Cc1ccc( Cl)cc1)
+COc1ccc( -n2
+c1ccc( Cl)
+c2cc( F)
+[nH] c2c1
+CCO C(
+n2 c1
+c1ccc( C)
+c1ccc( [N+](=O)[O-])cc1
+C1=C( O)
+C(F)(F)F) c1)
+CC c3ccccc3)
+Cc1ccc( -n2
+[C@]4 (C)
+c3cc4c( cc3)
+[C@@H]2 [C@@H](
+c3n c4c(
+[C@H]( C
+c2cc c3[nH]
+n 5
+NC(=O) CS
+nc2 N
+c(C) c2)
+S1 (=O)
+CCCC CCC
+C( =N
+C1 (C)C
+c1 c2cccc
+OC)c(OC) c3)
+CC(CC( C3)
+c( [N+](=O)[O-])
+[C@H]( N
+[C@H]( C(=O)O)
+c2cccc( [N+](=O)[O-])
+ccc1 O
+c(C) n1
+CCC(O) =O)
+CC C1(
+c1cc( O
+COc1ccc( C(=O)N
+[C@@H]2 O
+c4cc c5c(
+CCO C1
+B (O)
+C2 C(
+N# Cc1c(
+CCO c1cc(
+c1ccccc1) =O
+CC(=O)N [C@@H](
+5)cc 4)
+c3n (C)
+NC(=O) CO
+c3cccc( Cl)
+S(=O)( N)=O)
+C(=O)O) c1
+c2s ccc2)
+c1c( C(
+c2ccccc2) n1
+N3 CCN(
+c3ccc( C(=O)N
+c1 co
+C(N CC
+# N
+OCC N(
+=O) CC2)
+n2 c3c(
+c1(Cl) ccc(
+N(CC) CC
+c3 F)
+COc1ccc( -
+CCCC(=O) N
+F)cc 2)c1
+c4cc co
+c2ccc( OC)c(OC)
+c1( C(=O)N
+C(C)(C) O)
+Cc1cc( N
+c2 =O
+N1 C
+=C( N
+c1ccccc1 2
+nc2 cc1
+c1s c(
+S(C) (=O)=O
+nc( Cl)
+cn 4)
+OCC CO
+ncn 2)
+CC( O
+c4 s
+c(O) cc1
+O=C( CSc1n
+CC [C@H](O)
+C(=O)O) cc2)
+c4cc( Cl)cc
+[nH] 2)cc1
+c1ccccc1 Cl)
+Cl)c(Cl) c3)
+c2 =O)c1
+c6 cccc
+[C@H]( CC(C)C)
+=O) C)
+C(=O)N( CC)
+CCCC 4)
+c2nc(- c3ccccc3)
+C2 C3
+c2cc( Br)cc
+(- c3ccccc3)
+c12 ccc(
+CC [C@@H](C)
+nc2 )cc1
+CC1 =
+(F)(F) F)
+C(F)(F)F)cc c1
+c12c( cc(
+C(=O) c1c(
+CCC [C@H]2
+C(=O)N[C@@H]( Cc1ccccc1)
+CCC =C(C)C)
+=[N+]=[N-] )
+=C 4
+n1 c(C)
+c1cc( -n2
+Cn2 cc
+n2) ccc(
+c2s c(
+OCO 4
+C [C@H]4
+c2ccc(Cl)cc2 Cl)
+OC c3ccccc3)
+c2cc( Cl)
+Cl)c(Cl) c1)
+[C@@]1 (C)CC
+/N =C2
+c(- c2n
+[C@H]( C(C)C)
+c1c2c( ccc1
+c2cn (
+n1 (C)
+Cl)cc 3
+c2ccccc2 OC)
+c2c(- c3ccccc3)
+/C( C#N)
+no 2)
+S(=O)(=O) c1ccccc1
+nc2 C)
+c2s c3c(
+=C /C
+c3cc(OC)c(OC)c(OC) c3)
+cc1 -
+s 2
+c4ccc(OC) cc4)
+CC(O) (
+Cc1 [nH]
+c1( O
+C(=O)N1 CC
+n( CC(=O)N
+n ccc1
+C S(=O)(=O)N
+)cc 4)
+c4 ncc
+[C@] (C)(O)
+C) C)
+C2) n1
+Cc2ccc( OC)cc2)
+c2cccn c2
+CCN (C)C
+c1( -n2
+N c1c(
+CCN2 C(=O)
+C [C@@H]4
+[nH] 2
+[C@H]( NC(
+c1ccc( NC(
+OCC (N
+COc1ccc( Cl)cc1
+CC1 (C)C
+c4 c3
+CN2 CC
+c4cccc n4)
+NC(=O) [C@@H]1
+Cc1ccco 1)
+C(=O)N2 CC
+c2c( ccc(
+cc 5)
+cc1 2
+c1cc (=O)
+NC(=O) C
+CCn1 cc(
+c1cccc( Cl)c1)
+C2 )ccc1
+C2 CCN(C
+c1cc( OC)c(OC)c(OC)
+4 )cc2)
+c1c( -n2
+c3cccc( C(F)(F)F)c3)
+O=C1 c2ccccc2
+C[C@H]( N
+( N)
+CCCC (C)
+c2ccc( Cl)
+[N+](=O)[O-] )cc(
+CCOCC 2)c1
+CC C(C)(C)
+n2 )cc1)
+Cn2 c(=O)
+c2ncn (
+CC(C) N
+c(=O) c1
+[C@]3 4
+C c3c(
+)cc c1)
+C1 (O)
+CCC) =O)
+c2ccccc2 )ccc1
+C(=O)N C(=O)
+C( OCC)
+C /C(
+c1cn c(
+[C@@H]1 O)
+CC3 )cc1
+c1nc(- c2ccccc2)
+c1cn 2
+/N =C1\
+CCC [C@@H](
+Nc1n cn
+C= CC(
+c1c(F) ccc(
+c1ccc( C2
+[C@@H]( OC)
+Cc1n o
+c3) CC2)
+OC [C@@H]1
+Cl)cc2 Cl)
+C(N) =N)
+cc 3)cc2)
+[C@H]2 [C@H](
+cccc 5)
+-c2ccc( -
+OCC OCC
+C3 =O
+N2 CCN(C
+CO c1cccc2
+S) N
+( CO)
+c1ccccc1 Cl
+c1cc c2ccccc2c1
+n cc(-
+ccc(OC) cc1
+nc2 -
+CC( C(=O)O)
+c2ccc(OC) cc2
+c3cc o
+C(N C)=O)
+CCCC CCN
+CC(C) (O)
+c2cc3cccc c3
+=O) o
+-c2 c3c(
+(C)C) cc1
+OCO 3
+Cc1ccc( O
+CC( c2ccccc2)
+CC4 )cc3)
+n cc2)
+CCCCCCCC )
+c1cc2 cc(
+(=O)=O) c1
+n2 ccc(
+cc3) =O)
+c1c( Br)
+cc2c( c1)
+c1ccccc1) =O)
+N(CC Cl)
+N( c2ccccc2)
+Cc1ccc( -c2n
+5 CCCC
+O c1cc(
+3)cc 2)c1
+Nc1n cc(
+c2 C)cc1
+N( Cc2ccccc2)
+CC )cc1
+c2c( C#N)
+CC1 CCN(
+OC)c(OC) cc1
+c1cccc( O
+o n2)
+ncn c(N
+c1cn ccc1
+C1 N(C(
+[C@@] (C)(O)
+NC(=O) [C@@H](
+c3 c4ccccc4
+c1c( Cl)c(
+/C=C/ C(
+c2ccn cc2
+[C@H]( OC)
+n c2ccccc21
+5 CCOCC
+c4 cc(C)
+Br) c2)
+n c3ccccc3
+cnc2 c1ncn2
+CCCC N(
+CC) c1
+cn n2
+=O) c(
+c1( C2
+O C(C)(C)C
+n(C c3ccccc3)
+c(C) c3)
+nc( C(=O)N
+CC2 )cc1)
+c2cc( N3
+c2c(Cl) cccc2)
+c2ccc( C#N)cc2)
+O 4)
+c1cccc 2)
+CC C(=O)O
+c4ccc(C) cc4)
+cn2) CC1
+OCC 3
+(- c2ccccc2)
+N1 CCCC
+c1cn c(N
+c4) CC3)
+c [n+](
+Cc1ccc( S(=O)(=O)
+c4cccc( Cl)
+c3cc s
+CC1 =N
+c[nH] 1
+c(=O) n(C)c(=O)
+cc(- c3ccccc3)
+OCC(=O) O)
+c1(OC) ccc(
+CC C(C)C)
+c3cc( Cl)c(
+c1- c1ccccc1
+C#N) c1
+c2ccc3ccccc3 c2)
+CC(CC( C4)
+C) cc(
+c1cccc(F) c1)
+c3ccc( C#N)cc3)
+CN(C) c1ccc(
+( c1ccccc1)
+c1cc( C(N
+c1c( OC)cc(
+CC1 CCCO
+CCC [C@@H]1
+nn1 2
+Cn2 cc(
+(=O) O
+[C@]12 C
+[C@H]2 O
+c1cc( C(
+c(OC) c2)
+CCC(N 3
+c3ccc(OC) cc3
+C2) C3)
+NC(=O) C2
+c2cn ccc2)
+C/C=C\ C/C=C\
+c4 o
+NC( =N)N
+[C@H]( CC)
+c2cc( O
+C(=O) CS
+CCCC C2)cc1
+O=C( COC(=O)
+c1ccc( O)
+c2c(C) cc(C)
+C(=O)N2 CCC(
+ncn c3
+c3ccccc3 OC)
+[C@@H]4 [C@@]5
+[C@H]2 CC[C@H](
+/N =C\
+[C@@H]2 O)
+c3cccc( -
+N( C(C)=O)
+c3ccccc3 -
+c3cc(OC)c(OC) cc3
+c2ccccc2 c1=O
+S C(=S)
+c1ccccc1) N
+CCCN (C)
+CCS C)
+nc(C) c1
+NC(=O) C)
+C(=O)N C(=O)N
+c1c(C) ccc(
+c2n cccc2)
+c(N 4
+C(=O)N1 CCC[C@H]1
+CC(=O)N 3
+CN3 CCN(
+c2ccc(O) cc2
+CCC( CC)
+n2) n1
+[C@@H](C) O)
+NC(=O) /C=C/
+=O) n(
+[n+] 3
+C#N )cc2
+F C(
+c2cc( Cl)cc(Cl)
+N C1=N
+c3c( N
+c2c1 =O
+CCC #N)
+c1 O)
+C c4ccccc4)
+c2cccc3 c2
+N( Cc1ccccc1)
+c6cccc c6
+ccc( OC)c1
+O C1=O
+nc( C(F)(F)F)
+C(=O)N C)
+c2 co
+c( F)cc1
+c3o ccc3)
+O 2)cc1
+c1cccc2 ccccc12
+N=C( N
+c1ccccc1 O
+N1 CCN(C
+n s
+nc2 3)
+c4 c3)
+CO C(C)=O)
+CC3 CC(
+c3ccc( Cl)
+CCCN( CCC)
+c1cc( F)c(
+[C@]3 (C)CC
+c(C) cc(
+c1cccc( C(F)(F)F)c1
+c1ccc( CN
+C(=O) /C(=C/
+c3ccc(O) cc3
+c1cccc( -
+cc n3)
+- c1cc
+c1c( -c2ccccc2)
+S C1
+CO [C@@H]1
+c1c(C) cccc1
+O= S1(=O)
+c1cccc( -c2n
+c(C) cc(C)
+cc 5
+c( CN
+c3c(Cl) cccc3
+COc1ccc( OC)c(
+C(=O)N [C@@H](C)
+c3cc( C(F)(F)F)cc
+n1) =O
+=C( C#N)
+=O) cccc1
+CO [C@H]1
+[C@H]( Cc2ccccc2)
+c(=O) n3
+CCCN( C
+CC(C) (C)C
+c2c(OC) cccc2)
+CN(C) S(=O)(=O)
+s c(-
+c1cccc (C)
+Cc2ccc( O)cc2)
+c1ccc( O)c(O)
+[N+](=O)[O-] )ccc1
+c(=O)[nH] c2=O)
+[C@@]3 (C)CC
+nc3 2)
+CO CCO
+c2cc c3n
+[C@H]( Cc1ccccc1)
+CC [C@@H](O)
+c3ccc( Cl)c(Cl)c3)
+c2cc(C) ccc2
+c2ccccc2 C)
+[C@@]2 1
+-c2 nc(N
+[C@@]3 4
+/C =N\
+C =C\
+nc( OC)
+CCC( N)
+c2ccc(Cl)cc 2)cc1
+c1( S
+[nH] n1
+ccccc1 2)
+c1 c-2
+CN( CC
+CO c1cc2c(
+c2cc(OC)c(OC)c(OC) c2)
+CCCN2 C(=O)
+C2 CC
+C(N O)=O)
+C(=O)N [C@H]1
+CCCN1 CCN(
+c2cccc( O
+C2 (C)
+CCCO 2)
+cc3 C)
+[C@@]2 (C)CC
+)cc (O)
+N( O)
+C( C(=O)
+c( /C=C/
+c2ccc(Cl)c(Cl) c2)
+CC [C@H]4
+N( CCC)
+C(=O)N CCCC
+c3n cccc3)
+n 3)cc2
+4 )cc2
+COc1ccc( C(=O)
+cn 2)c1
+c4 5)
+CCCN C(=N)N)
+CCC [C@H](
+c3ccc([N+](=O)[O-] )cc3)
+nc( N2
+c2n nc(-
+CC n2
+c1( N2
+c4 )cc3)
+C1= CC(=O)
+S S
+C2 1
+O=C(N /N=C/
+c(- n2
+nc3 c2
+C( N1CCN(
+n( Cc2ccccc2)
+C(O) =C(
+N2CCN( C(
+c2ccccc2 c1)
+CC(O) CO
+c2cc( F)c(
+CC(=O) OC
+C(=O)N c1ccccc1
+c3cc(OC) ccc3
+Br) c3)
+4CCCC C4)
+CCCC (N
+C( C(C)C)
+CC C(=O)N1
+C(=O)N /N=C/
+c1ccc(Cl)cc1 Cl
+c3ccccc3 C)
+c3 c2cccc3)
+c1ccc( Cl)c(
+4) c3)
+o 2
+c3cccc (O)
+C1 CCN(C
+c(=O) cc(
+[C@@]4 (C)CC
+Cc1cc( O)
+[C@H](C) N
+Cc1c( Cl)
+c2ccccc2) CC1)
+c1(F) ccc(
+CN( S(=O)(=O)
+cc1) =O)
+c1c( cccc1)
+c1c( OCC
+c3 nc(N)
+c2c( F)cc(
+c(OC) c3)
+c2s ccc2
+CC2 =O
+n ccc2
+CCC3( CC2)
+Cn2 c(
+CCCC(=O) O)
+/C(=N\ O)
+cccc 2)cc1
+c3c( ccc(
+c2c(C) cccc2
+P(O) (O)=O)
+CN =C(
+C( OC
+N 2)
+cc c5
+cc (=O)
+COc1cc( N
+c1s ccc1
+O=C1 N(
+/C=C3 \
+C(C)(C) O
+CC )cc2)
+c1c( F)cc(
+C) C(=O)
+C3 )cc2)
+C2 (C)C)
+c2c(=O) n1
+CCN S(=O)(=O)
+c3n nn
+C(=S) S
+C [C@@]12
+c2ccc(- c3ccccc3)cc2)
+c2ccc( N(C)C)
+C1 N(C(=O)
+Cc1cc(C) cc(
+c1 oc(
+[C@@H](C) CO)
+c4 )cc
+c( C(N)=O)
+N O
+/C=C /C=C/
+- n1
+c1ccc( C(F)(F)F)cc1
+c(N (C)C)
+C1 (N
+C(C) (O)
+N3 C(=O)
+C c1cccc(C)c1
+c3cc4 ccccc4
+C3 4
+( C(=O)O)
+[C@H]1 [C@H](
+[C@H]1 O)
+N( S(=O)(=O)
+c2cccc(OC) c2)
+O=C1 NC(=O)
+CC(C) O
+C2=C( O)
+[C@H]2 CC
+C(C)(C)C) cc2)
+Cc1 c2c(
+CCC [C@@H]2
+C2 CCN(C(=O)
+c(OC) c1)
+c4cc cs
+COc1cc( OC)
+NC(=O) c1cc(
+c2cccc( NC(=O)
+-c2ccc( F)cc2)
+S(=O)(=O) N1
+c2cc(- c3ccccc3)
+c( CO
+c(C) c2
+P(O) (O)
+CCN(CC) C(=O)
+C( C(F)(F)F)
+n c2n(
+c2ccc(C) cc2
+n( C(C)C)
+CC[C@]4 3C)
+C(=O)N (C)C
+c4ccco 4)
+cn (C)
+c2n cc(-
+c1n ccc(
+c3cn ccc3)
+c3ccc(Cl)cc3 Cl)
+N c1nc(N
+no 1)
+S1 (=O)=O
+P(O)(=O) O)
+n n2)c1
+c2ccc(F)cc2) CC1
+C2 (C)C
+nc(S C
+CCN 4
+CCCO 3)
+c 7
+CC[C@]4(C) [C@H]3CC
+c2ccc( S(=O)(=O)N
+c2ccc( Br)cc2
+[N+] (C)(
+c4cc5 c(
+C(=O)N[C@@H]( CC(C)C)
+c1ccc2c(c1) OCO2)
+N C(=O)N1
+n(C) c1
+Cc1ccc( C)
+Cc1 nc(N
+c2cc(C) cc(C)
+c1( OC)cc(
+c2cc o
+C( CCC)
+COC(=O) c1ccc(
+C) C1
+N1 2
+c3cccc c13)
+[C@]3 (O)
+c3s ccc3)
+O= c1cc(
+NC(=O)[C@H]( CC(C)C)
+C4CCCC C4)
+CCN1 CCC(
+C2 CC(
+c4cccc 5
+c2n (C
+NS(=O)(=O) c1ccc(
+CCCN =C(N)N)
+n1 c(N)
+cc4 c(
+c2 c3
+N S(=O)(
+OCCO 4)
+N1( C(
+nc(N3 CCOCC3)
+- c1cc(
+c4ccc5c( c4)
+N )cc1
+c1ccccc1 F)
+c4ccncc 4)
+N =C
+c3c( c1)
+/N=C(\ C)
+c4 n(
+c3cc(C) ccc3
+c2o c(-
+[C@@H]( C(=O)O)
+CCC(O) (
+c3 Cl)
+C12CC3 CC(CC(C3)
+C c1ccc2c(
+c(=O) c2c1
+c3ccc( C(=O)O)
+/C1 =C/
+C(Cl) (Cl)
+c2cc(OC) ccc2
+OC [C@@H]2
+C( C(O)=O)
+cc(C) cc1
+c12 n(
+3 )cc1)
+Cn1 c2c(
+ccc( Cl)cc1
+c3c( n2)
+F) c1
+[C@@]3 (O)
+O=C( CN1
+c1( -c2cc(
+C3 CCC3)
+c1( Cl)cc(
+N( C(=O)N
+c3cc( Br)cc
+CCC1 2
+cc n1)
+Cc1cc cnc1)
+c3cccc4 cccc
+[C@H]2 C
+[C@H]2 [C@@H](
+CCC( C(=O)N
+c3ccccc3) CC2)cc1
+CCCC CC3)
+n(C)c(=O) n(C)
+[C@H](O) [C@@H](O)[C@H](O)
+N(CCCl) CC
+Cc1ccco 1
+CCN2 CCOCC2)
+[C@H]( CO
+OC( CO)
+c1- 2
+CC(C)(C) N
+=C /C=C/
+C(=O) OCC(=O)
+c4cccc (F)
+c1ccc( S(=O)(=O)N
+4CCCC 4)
+/C=N/ NC(
+c1cn (C)
+c1c(C) cc(
+F) c(-
+C(C)(C) [C@@H]5
+c1ccc( S
+C1= S
+Cc1cc cs1)
+c3n [nH]
+CCN(C) CC1)
+[nH] 2)c1
+c(N C(=O)N
+c(Cl) c2)
+=O) cc3)
+c3cccc (N
+c(S C)
+c3 2)cc1
+c(F) c3)
+c2 -
+c3ncc cn3)
+c3cc( N
+-c2ccc( Cl)cc2)
+c4 c(Cl)
+c( OCC)
+c3ccc( S(=O)(=O)N
+nc(- c2ccccc2)
+CCOCC 3)cc2)
+c(=O) n(C
+C(C)C) cc2)
+c2n o
+c4 c5c(
+COc1ccccc1 N1CCN(
+n 5)
+CC COc1ccc(
+co 1
+c1cccc( O)c1
+(N 3
+c1cc( OCC
+N1 )
+=O) (
+= N2
+nc( NC(
+c4ccc( N
+c1cccc( -n2
+OC 4
+c3c( N)
+O [C@H](C)
+n c2)c1
+c4ccc( C(F)(F)F)cc
+c2cc( OCC
+c2nc( O)
+Cc1ccc( OC)
+N1 (C
+Cc1cc cnc1
+c4cccn c4)
+c3 n2)
+C( OC(=O)
+c5 cn
+O=C( CS
+C1( c2ccccc2)
+C(F)(F)F) c(
+[C@H]1 CO
+c4 ncn
+C(C#N) =C(N)
+C1 CN(C(=O)
+C1 c2c(
+c1( Br)
+n[nH] 1
+c3c( c2)
+c2 )cc
+C(=O) C(C)
+c4c( F)
+c1ccc( C(
+/C =C1/
+c(OC) c(OC)
+[C@H]( C(=O)N
+c1c(O) cc(
+c1ccc( CN2
+[C@]2 (C)CC
+Cc1n n(C)
+CC(=O) OC)
+c1c( C2
+C3 CCCCC3
+c1c( C#N)
+c1(C) ccc(
+C2=O) ccc1
+C) (
+[C@@H](O) [C@H]1O
+c2ccccc2 O)
+c2cc nc(N
+c2c(F) cccc2)
+P(=O) (O
+)cc( OC)c1
+c3cc(O) ccc3
+C1 N
+Br) c1)
+[C@H]( Cc1ccccc1)NC(=O)
+[nH] c12
+3)cc2 1
+cn c12
+c1cc( F)cc
+c( C(C)C)
+c4cc( F)cc
+N( S(
+CCn1 c(=O)
+C(=O)N2 C
+C( CS
+s c1)
+c2cn (C)
+c1cc( C2
+c(N) n1
+C[C@H]( NC(
+C [S+]([O-])
+c2cn n3
+CC[C@H]( NC(=O)
+C#N )cc1)
+c2ccc(- c3n
+P (O
+CCN(CC) CC)
+c3cccc(OC) c3)
+CCCC CCC)
+OCCO 2)
+CC c2c(
+c2) nc1
+ccc( C)c1
+c3 -
+c2ccc(Cl)cc2) CC1
+nc3 C)
+C23CC4 CC(CC(C4)
+c3ccc( C(F)(F)F)cc
+C[C@@H]( NC(=O)
+c2cc( S(=O)(=O)N
+cc( Cl)
+n1 ccc(
+[C@]1 (C)CC
+ncn c32)
+c4ccc(Cl)cc 4
+c3cccc c3c(=O)
+3)cc2) CC1
+N S(
+c(C) cc2)
+CC [C@@]4
+ccc1) =O
+Cc1ccc( S(=O)(=O)N2
+cc nc1
+CC1 CC1
+c1ccc( Cl)c(Cl)c1
+c1c( OC)c(OC)
+CC( CO
+n( CC
+c4 n3)
+c2ccccc2 C1
+nc3 n2
+c2)cc1 OC
+c1( Cl)c(
+CO 2)
+Cc2ccccc2) c1
+C=C 3
+C4 (
+N [C@H]1
+c1n cc(-
+[N+]([O-])=O) cc2)
+c4 nn
+o c12
+/ C(O)
+CN( Cc1ccccc1)
+C3) =O)
+[N+]([O-]) =O)cc1
+CCCCCCCC CC
+-c2 c[nH]
+C(=O) c2c(
+c1( CN2
+c3 n2
+C1=C(C) N
+C#N )cc(
+C(=O)N [C@@H]1
+c1 C)
+O=C( N1
+N( C(N
+COc1cc c2[nH]
+c2n ccc(
+O) =O
+cn cc1
+c3c(F)cccc3 F)
+CC(C)C) =O)
+[nH] cc2
+/C( =C(\
+c(=O) n(-
+C[C@@H]( CO)
+CCN3 CCOCC3)
+c1cc( OC)c(
+N1 (C)
+c4ccc(F)cc 4
+[C@@H]2 C
+n cc3)
+O=C(N c1cccc(
+cccc1) =O
+c2ccc( S(=O)(=O)N3
+N# Cc1cccc(
+c1c( F)c(
+c1( CN
+c3ccc(C) cc3
+c( [N+](=O)[O-])c1
+c( Cl)cc
+c2cccc(C) c2)
+c(Br) c1
+CC(=O) N1CCN(
+c1c( C(F)(F)F)
+[N+] 2
+CCN( S(=O)(=O)
+C) cc2
+/C( =C(/
+c2c(Cl)cccc2 Cl)
+[C@@]1 3
+c(- c4ccccc4)
+nc1 S
+O [C@H]3
+C(=O)O) cc1)
+c2c(C) cccc2)
+c1c( O)c(
+n2) =O)
+OCO 5)
+O =C
+C(N (C)C)
+c1ccc(- c2ccccc2)cc1
+CC2 =O)
+C( CNC(=O)
+c5 [nH]
+CC(=O)N (C)
+cs 2)c1
+c2ncn c(N
+c2ccc(Cl)cc 2)c1
+Cc1n c2c(
+CC( CO)
+c(S C
+c(C) c1)
+[n+] (C
+C) CC1
+c3cccc(C) c3)
+c3cn (C)
+c1cn n2
+[nH] c2)
+CC [C@]2(C)
+c1cccc( [N+](=O)[O-])c1
+C(N)=O) c(N
+c2ccc(- n3
+[C@@H]4 CC
+C(=O)N S(=O)(=O)
+C(=O)N C2
+c( F)cc2
+S C(
+c1ccccc1 F
+c1cc( Br)
+c1cc n
+[C@@H]1 [C@@H](
+c(OC) cc(
+Cc2ccc( C)cc2)
+c3c( Cl)cc(
+c1cc c2nc(
+[nH] c1)
+c2cc( Br)
+[C@@H]2 C1
+/C(C) =N/
+c3ccc( NC(=O)
+ncc 4
+P(=O)( OCC)
+c1n [nH]
+CCN1 C
+ccc( F)cc1
+OC)c(OC) c1)
+N( S(=O)(
+c1cc( O)c(O)
+C1 C2(
+CC(C) C[C@H](NC(=O)
+c1c(O) ccc(
+(O) =O
+S2 (=O)=O
+N( C(C)C)
+C2 CCC2)
+ncn c2
+c3ccccc3 C2=O)
+C4 )cc3)
+[C@@H]( CC(C)C)
+OC(C)(C)C) =O)
+[N+]([O-]) =O
+C= CC(=O)
+C) O
+c3 c1
+c1( -c2ccccc2)
+c3 O)
+cn c2)
+o c2
+n4 cn
+N c1nc(-
+CC( NC(
+cn n1
+C(F)(F) C(F)(F)
+c23) c1
+CCCC 2)cc1
+c3cc( C(=O)N
+CC(=O) NC(
+c1cc( Br)ccc1
+C(=O)N1 CCN(C(=O)
+C(C)=O) cc1
+c2cc3c(cc2) OCO3)
+nc(S C)
+[C@@H]( CC)
+OC [C@H]2
+c1ccc( C(N
+C(=O) [C@H](
+C =N
+c23) CC1
+[N+]([O-]) =O)c1
+3)cc c21
+)ccc1 O
+[C@@H]1 (O)
+/N=C2 \
+CC( c1ccccc1)
+no 2)cc1
+n n(C
+[C@H]1 (O)
diff --git a/Pilot1/ST1/VocabFiles_spe/vocab_spe.txt b/Pilot1/ST1/VocabFiles_spe/vocab_spe.txt
new file mode 100644
index 00000000..f7a74519
--- /dev/null
+++ b/Pilot1/ST1/VocabFiles_spe/vocab_spe.txt
@@ -0,0 +1,3132 @@
+[PAD]
+[unused1]
+[unused2]
+[unused3]
+[unused4]
+[unused5]
+[unused6]
+[unused7]
+[unused8]
+[unused9]
+[unused10]
+[UNK]
+[CLS]
+[SEP]
+[MASK]
+[c-]
+[SeH]
+[N]
+[C@@]
+[Te]
+[OH+]
+n
+[AsH]
+[B]
+b
+[S@@]
+o
+)
+[NH+]
+[SH]
+O
+I
+[C@]
+-
+[As+]
+[Cl+2]
+[P+]
+[o+]
+[C]
+[C@H]
+[CH2]
+\
+P
+[O-]
+[NH-]
+[S@@+]
+[te]
+[s+]
+s
+[B-]
+B
+F
+=
+[te+]
+[H]
+[C@@H]
+[Na]
+[Si]
+[CH2-]
+[S@+]
+C
+[se+]
+[cH-]
+6
+N
+[IH2]
+[As]
+[Si@]
+[BH3-]
+[Se]
+Br
+[C+]
+[I+3]
+[b-]
+[P@+]
+[SH2]
+[I+2]
+%11
+[Ag-3]
+[O]
+9
+c
+[N-]
+[BH-]
+4
+[N@+]
+[SiH]
+[Cl+3]
+#
+(
+[O+]
+[S-]
+[Br+2]
+[nH]
+[N+]
+[n-]
+3
+[Se+]
+[P@@]
+[Zn]
+2
+[NH2+]
+%10
+[SiH2]
+[nH+]
+[Si@@]
+[P@@+]
+/
+1
+[c+]
+[S@]
+[S+]
+[SH+]
+[B@@-]
+8
+[B@-]
+[C-]
+7
+[P@]
+[se]
+S
+[n+]
+[PH]
+[I+]
+5
+p
+[BH2-]
+[N@@+]
+[CH]
+Cl
+cc
+CC
+O)
+c1
+c(
+C(
+=O)
+c2
+C)
+cccc
+c3
+C(=O)
+ccc(
+)cc
+(C)
+(=O)
+2)
+cc(
+C1
+F)
+N(
+CCCC
+c1ccc(
+3)
+CO
+cn
+c1cccc
+c2cccc
+c4
+CN
+C(=O)N
+OC)
+)cc1
+c2)
+C2
+n1
+nc(
+C(C)
+c2ccc(
+N)
+[C@H](
+[C@@H](
+c2c(
+=C(
+CC1
+c1)
+Cl)
+c3cccc
+NC(=O)
+cc1
+OCC
+c1c(
+c1cc
+c1cc(
+=C
+S(=O)
+CCN(
+(F)
+c3)
+N1
+n2
+=O
+c3ccc(
+S(=O)(=O)
+c3c(
+CC(=O)
+CC(
+/C
+c1ccccc1
+C(F)
+F)cc
+c2cc
+c2n
+CCC
+N2
+4)
+c2ccccc2)
+OC
+Cl)cc
+O=C(
+C(F)(F)
+c1n
+c(=O)
+c2ccccc2
+(C)C)
+c2cc(
+C(N
+c1(
+[C@H]1
+=C/
+=N
+n(
+[C@@H]1
+C3
+CC)
+CCO
+CCN
+CC2)
+1)
+C#
+c12
+CC2
+CN(
+c1cccc(
+c(-
+CC(C)
+c3ccccc3
+c(C)
+cc2)
+NC(
+cc2
+(O)
+c1ccccc1)
+[C@H]2
+Cc1ccc(
+c(OC)
+C(=O)O)
+c3ccccc3)
+[C@@H]2
+n2)
+nc(-
+C(C)C)
+c4cccc
+)cc1)
+O=
+/C=C/
+c3cc
+C2)
+CCC(
+c5
+3)cc
+COc1ccc(
+CN1
+[O-])
+CO)
+C(F)(F)F)
+cc1)
+[C@H](O)
+nc2
+c(N
+[C@@H](O)
+C(O)
+c3cc(
+CC(=O)N
+cs
+CC1)
+/C(
+CC3)
+[N+](=O)
+CS
+c4ccccc4
+c1cc2
+c3n
+c(O)
+2)cc1
+CCCN
+nc(N
+CCOCC
+cc3)
+(C)C
+(=O)=O)
+n3
+C1)
+nc1
+S)
+C#N)
+ccc1
+/N
+)cc(
+C(=O)O
+[C@H]3
+CCCCCCCC
+(N
+c1cn
+C3)
+Br)
+)ccc1
+c2c1
+O=C(N
+cccc1
+[C@@H]3
+c2cccc(
+C(C)(C)C)
+c1ccc2c(
+c4ccc(
+CN2
+C=
+-c2ccc(
+-c2
+C(C)=O)
+c(Cl)
+COC(=O)
+)cc2)
+C[C@H](
+n(C)
+C(N)
+=C\
+n1)
+C(C)(C)
+cc3
+co
+S(
+OCC)
+CCN1
+c[nH]
+C(=
+ncn
+Cn1
+C(F)(F)F)cc
+OC(=O)
+[C@H](C)
+([O-])
+Cc2ccc(
+[C@@H](C)
+c4c(
+OC)c(OC)
+C(=O)N1
+)cc2
+CNC(=O)
+nc(C)
+2)c1
+=O)cc1
+S(=O)(=O)N
+CC3
+C[C@@H](
+C(=O)N(
+Cl)cc1
+nn
+Cc1
+O=C1
+C(=O)N2
+S(=O)(
+Cc2ccccc2)
+OCO
+C4
+CN(C)
+C1=O
+c4)
+=N/
+Cc1cc
+c2cn
+5)
+cccc2
+cc(-
+)cc3)
+[N+](=O)[O-]
+C1(
+c1ccc2c(c1)
+F)cc1
+Cc1cc(
+c1cccc2
+c1cc2c(
+n3)
+COc1cc(
+CCC)
+c2cc3
+cc(C)
+C(O)=O)
+Cc1ccccc1)
+[C@]1
+nc3
+-c2n
+c2ccc(Cl)cc
+[N+](=O)[O-])
+OC(
+CCN(C(=O)
+CC(C)(C)
+[C@@]2
+CCC1
+N3
+=O)c1
+cccc2)
+[N+]([O-])
+=C2
+C#N
+c(F)
+[C@]2
+n(-
+s1
+O1
+CCC2
+o1
+Cc1ccccc1
+ccc2
+(C)CC
+c(N)
+[C@@]1
+CC(O)
+CCOC(=O)
+NC(=O)N
+Cc1n
+c4ccccc4)
+cccc3)
+c1c2c(
+cn1
+F)cc2)
+Cc1c(
+CC(C)C)
+nc(N)
+C[C@H]1
+O=C(O)
+N=C(
+c3cccc(
+C1CCCC
+=C1
+Cn2
+=S)
+c2ccc3c(
+CC(N
+-n2
+CCN(C
+c3ccc(Cl)cc
+c2)cc1
+Cl)c(
+c(=O)[nH]
+c3cn
+C(N)=O)
+c3ccc(F)cc
+P(=O)
+(C
+N(C)
+n2)cc1
+c1c(C)
+CCCN(
+c2[nH]
+CCCCC2)
+c2c(C)
+CC[C@H](
+3)cc2)
+c2s
+O[C@H](
+C[C@@H]1
+OC)c1
+C)cc1
+C2=O)
+c4cc
+CCCO
+c2)c1
+NS(=O)(=O)
+Cl)cc(
+c12c(
+=N\
+c23)
+c1nc(
+/N=C/
+C)=O)
+N#
+ccccc1
+3)cc1
+N2CCN(
+N1CCN(
+CC(=O)O)
+=C(\
+OCC(=O)
+c1=O
+(C)(
+CC4)
+CC2)cc1
+CCN(C)
+c1-
+ncc
+c2ccc(-
+[C@]3
+S(C)
+O(
+Cc1cccc(
+CCNC(=O)
+N(C(=O)
+c21
+c2ccc(Cl)cc2)
+c1s
+ccc3
+CN3
+CCCC)
+ccc2)
+F)cc1)
+cn2
+CC4
+C(=O)N[C@@H](
+c4cc(
+C4)
+Cl)cc1)
+[N+]([O-])=O)
+CCO)
+[C@H]4
+c(S
+CCS
+CCCN1
+Cl)c1
+c2o
+[C@@H]4
+C(=O)OC)
+c2nc(
+c1ccc(Cl)cc1
+CCCC1
+nn1
+c2ccc3c(c2)
+C[C@H]2
+no
+c2ccccc21
+[C@@]3
+C2(
+c5cccc
+CCn1
+C)cc2)
+CCN2
+c1ccc(N
+3)cc2
+N)N
+cccc3
+cccc1)
+CCCC2)
+c2cc(-
+c(C(=O)N
+OC)=O)
+c2cc3c(
+c3ccc(F)cc3)
+C[C@@H]2
+C2=O
+/C=C\
+n(C
+S(C)(=O)=O)
+cn2)
+cnc1
+Cl)c(Cl)
+c2ccc(OC)
+N1(
+c2cccn
+c2c3c(
+ccc1)
+O)cc1
+(-
+c1ccc(-
+c2ccccc2)cc1
+cnc3
+c3ccc(Cl)cc3)
+c(C)c1
+n[nH]
+)cc3
+OC)cc(
+CCOCC2)
+Nc1n
+c2=O)
+=C(C)
+COc1cccc(
+OC(C)=O)
+CCC(N
+c2ccc(F)cc2)
+c2ccn
+F)c(
+c2nc(-
+P(=O)(O)
+N(C(
+COc1ccccc1
+NC
+CCCCC3)
+CCN(CC)
+ncc1
+OCCO
+c2)=O)
+s2)
+O[C@@H](
+n4
+C(=S)
+/C=N/
+CCC(=O)N
+O)c(
+CCOCC3)
+N(C)C)
+C12
+C2)cc1
+c2n1
+CCCC3)
+CC=
+nc(S
+CN(C(=O)
+N(C
+n2)c1
+c1ccc(OC)
+C=C
+=O)=O)
+[nH]1
+/C(=C/
+c3ccc(OC)
+CC[C@@H](
+/C(=C\
+cc4
+CNC(
+Oc1ccc(
+c1[nH]
+C1=O)
+c3ccc(C)
+c2cc(C)
+CCC3
+c5ccccc5
+c2cc1
+CC2)c1
+O)c(O)
+CCCC2
+c1cc(C)
+c1ccc(O
+C2=N
+cc2)cc1
+F)cc2
+c2n(
+C1CCN(
+c3cc4
+c2ccccc12
+cc4)
+N)=O)
+[C@]12
+NC(=O)[C@H](
+c1(C)
+C1CN(
+Cc3ccccc3)
+c1nc(-
+OC)c(OC)c(OC)
+[C@]4
+Cl)cc2)
+N2C(=O)
+C3=O)
+C)c1
+c2cccc3
+c2c(-
+Nc1ccc(
+CCCCC1
+C(O
+S(=O)(N
+CC(=O)O
+ccc3)
+CCC(C)
+CS(=O)(=O)
+c1c(O)
+c3[nH]
+OCC)=O)
+OC)c(
+C(=O)OC
+[C@@H]1O
+c2ncn
+c6
+s1)
+C1=C(
+CCCN2
+C[C@@H](O)
+CCC2)
+(=O)=O
+oc(
+(O
+N(CC)
+c(=O)n(
+nn2
+/C=C
+c2c(=O)
+C[C@H](O)
+-c2cn
+c2c(cccc2)
+c3c(C)
+c1O
+-c2ccccc2)
+-c1ccc(
+NC(=S)
+C(C)C
+CCOCC1
+=C(/
+C(=O)NC
+c3c(cccc3)
+(C(F)(F)F)
+[n+]1
+CC1(C)
+cc(O)
+-c2cc(
+N4
+O2)
+C(OC)=O)
+CCCC(=O)
+-2
+cn3)
+c3ccc(-
+=N)
+CC#
+c2)CC1
+[C@@H](O)[C@H](O)
+C(=O)N[C@H](
+c(NC(=O)
+c1cc2c(cc1
+c2nc(N
+Cc1cn
+C2CC2)
+O2
+C(=O)N3
+N1C(=O)
+[C@@H](CO)
+c1ccc(Cl)cc1)
+c3s
+/C(=N\
+C=C(
+S(=O)(=O)N2
+CCOc1ccc(
+/C=C2
+(F)(F)
+[C@H]1O
+CC[C@H]2
+cs1
+c2ccc(OC)cc2)
+c3o
+C1C(
+nc2)
+c2ccco
+cs2)
+c2c(O)
+F)cc(
+[C@]2(C)
+[C@@]4
+[C@@]2(C)
+O[C@H](CO)
+c1c(Cl)
+c2cc(Cl)cc
+Cl)cc2
+CCCC(
+ccc(-
+C1N(
+c1C
+c2cccc(Cl)
+Cc1cc(C)
+C1=
+cn1)
+CC(=O)N1
+n1c(
+c1ccc(F)cc1
+cccc4)
+c12)
+S(N)
+CN1CCN(
+CCC(O)
+C3CC3)
+c3ccc4c(
+c1c(OC)
+CCC(=O)O)
+C(=O)OCC)
+Br)cc
+ncc(
+c1o
+nn2)
+OCCCC
+-c1ccccc1
+C2=C(
+C2CCCCC2)
+C1(=O)
+c2ccc(C)cc2)
+c1cc2c(cc1)
+/C=C(\
+nc2c1
+c3ccn
+c2ccc(O)
+C1=N
+S1
+C)cc1)
+(CC)
+C(=O)C(
+CCN3
+c2ccc(Cl)cc2
+cnc2
+Cc2ccccc2
+C[C@H]3
+ncc2
+CSc1n
+COC(
+c3ccc(OC)cc3)
+c3c2
+c2c(Cl)
+CCC3)
+[C@@](C)(
+Br)cc1
+C(F)(F)F
+CCc1ccc(
+[C@@H](N)
+C(C)(C)C
+c(N3
+c(=O)c(
+C2CCN(
+c3ccccc23)
+C(=O)OCC
+S(N)(=O)=O)
+sc1
+o2)
+C(OCC)=O)
+/C(C)
+c1nc(N
+NC(N
+CN1C(=O)
+S(N
+CN)
+Cl)ccc1
+C(c2ccccc2)
+COc1cc
+c2ccncc2)
+OCO2
+OCO3)
+c(OC)c1
+c(O
+c34)
+c4n
+OC)c1OC
+4)cc
+I)
+c1)=O
+n4)
+C[C@@H]3
+c4cn
+c5c(
+N)N)
+CCCCC1)
+OCC(=O)N
+-c2ccccc2
+[C@@H](NC(=O)
+N2CCOCC2)
+N1CCC(
+C(CC)
+CC2)=O)
+n2c(
+CCOCC1)
+C#C
+[nH]c(=O)
+C=C1
+C(=O)N(C)
+CN(C
+O)cc1)
+[C@](C)(
+O)c1
+cc2c(
+F)c(F)
+[C@@]12
+cccc(
+c2ccc(C)
+c2c[nH]
+s3)
+C(=O)N)
+N(CC
+nc12
+NCC
+c2ncc
+CCN(C)C)
+n(C)c(=O)
+c3ccccc32)
+c1=O)
+c3ncn
+OC1
+c3ccc(C)cc3)
+P(O)
+ccc(OC)
+/C(=N/
+c3cc(C)
+c(C#N)
+c3ccc(O)
+oc(-
+C(F)(F)F)cc1
+C2=O)cc1
+c1ccc(F)cc1)
+(CC
+C(=O)NCC
+c2ccco2)
+Oc2ccc(
+C(=N)N
+=O)cc2)
+c3cc4c(
+C(C)(
+c2C)
+CCCCCCCCCCCC
+Br)cc2)
+=N/N
+C(c1ccccc1)
+Cc2c(
+O[C@H]1
+[C@]3(C)
+4)cc3)
+C1CC
+C=O)
+[N+](C)
+CC[C@@H]1
+c32)
+c1(N
+C(N1
+c4ccc(F)cc
+c2)n1
+C(=O)(
+C2=
+O[C@@H]1
+c1ccc(NC(=O)
+Cc2cc(
+c(Br)
+nc3)
+c3ccc4c(c3)
+c2nc3c(
+5)cc
+CC[C@H]1
+-c1n
+c2ncc(
+c(Cl)c1
+c2ccccn2)
+c1c(F)
+C1CCCCC1
+=O)ccc1
+NC(C)=O)
+c5ccc(
+n1cn
+[n+]2
+nc1)
+O3)
+c2cccs2)
+c1cc(-
+[n+](
+c3cccn
+C(F)(F)F)cc2)
+CC1(
+[C@]2(
+c3cc(Cl)cc
+O=[N+]([O-])
+CC(=O)N(
+c1c[nH]
+ccc4
+c2ccccc2)c1
+cs1)
+c2ccc(O
+CN(C)C)
+[nH]2)
+cc(OC)
+c3ccco
+c3n(
+nc4
+C1CC1
+CC(O)=O)
+O1)
+c1cc(OC)
+3C)
+nc(N3
+C(N2
+c1ccco
+2)ccc1
+/N=C(\
+CCC2(
+nc2c(
+CC(CC(
+CC[C@@H]2
+c3ccccc3)cc2)
+OC3
+[C@](
+CCN(C(
+CCCC1)
+C5
+CC[C@H]3
+c4ccc(Cl)cc
+c(C(N
+c2ccccc2)CC1
+OCC(
+C(=O)/C=C/
+[C@@](
+4CCCC
+cs3)
+n1cc(
+N=C(N)
+/C=C2\
+/C1
+c2c(F)
+=C1\
+c3c(=O)
+c3c4c(
+)ccc2
+c1c(N
+Cl)c3)
+nc(O)
+c2nc3ccccc3
+C(C(=O)N
+Cn3
+C(F)(F)F)c1
+c3ccncc3)
+C(=C)
+c1cccnc1
+c1cccc2c1
+[N+](=O)[O-])cc1
+c1c(-
+CC(=O)N2
+O)=O)
+c2ccc(N
+O(C)
+CC)=O)
+ccc(C)
+c3cccc4
+[C@]1(C)
+CC=C)
+CCCCC3
+n2cn
+S(=O)(C)
+C(C)=O
+O=S(=O)(
+c(=O)o
+c2nc(C)
+N[C@@H](
+CCc1n
+CC3)cc
+c2)C1
+OC2
+=C)
+c2cccc(F)
+CCC4
+nn(
+[nH]c(
+c2c(c1)
+n12
+[C@H](NC(=O)
+c1c(=O)
+c1cc(N
+c3ccco3)
+C(C(
+P(=O)(O)O)
+CC(C)(
+c2cc3c(cc2)
+c3ccccn3)
+[C@@]1(C)
+C[C@H](NC(=O)
+ccc(F)
+CCCCC2
+CCOCC4)
+CCN1C(=O)
+CCC1)
+SC)
+c(C)c(
+C1CCCCC1)
+c5)
+COc1c(
+c2c(OC)
+c1cccc(F)
+C1CC(
+OC(=O)C)
+[C@@]2(
+c4cccc(
+C3CCCCC3)
+nnc1
+c1ccc(OC)cc1)
+(O)(
+cccc4
+c2c(cc(
+sc(
+no1
+CSc2n
+[C@H](CO)
+COc1cc2
+c3ncc
+c2ccccc12)
+C[C@@H](C)
+c(F)c1
+C/C=C\
+CCS(=O)(=O)
+CCOC
+CN(C)C
+c1cn(
+COC)
+=CC(=O)
+[C@@H]12
+CC2(
+(C)c1
+CC[C@]4
+nc(NC(=O)
+n1(
+C(=O)Nc2ccc(
+c3=O)
+CCCNC(=O)
+c1(=O)
+Cc1c[nH]
+c1n(
+c1ncc(
+c2cc(OC)
+cnc1)
+CCCCN
+CCN(C)CC
+c(-c3ccc(
+[C@]1(
+ccc(N
+o1)
+N1CC
+c(-c2ccc(
+CCCCCC
+[C@@H]5
+6)
+F)cc(F)
+c1(OC)
+c1cc(O)
+C(c1ccc(
+NC(=S)N
+c3)=O)
+[C@@]3(C)
+c(OCC
+C(=O)Nc1ccc(
+OCO4)
+OC(C)(C)C)
+F)ccc1
+c2cccnc2)
+=C3
+O[C@@H]2
+c2)ccc1
+Cc3ccccc3
+c3ccc(Cl)cc3
+c1cs
+c-2
+C(=O)O)cc1
+c2ccccc2c1
+c23)cc1
+C2)c1
+OC)cc(OC)
+-c2nc(
+n2)CC1
+c2ccccc2n1
+[C@@]1(
+ncc1)
+c3cc(-
+c1ccc(OC)cc1
+C3(
+4)CC3)
+CCCN3
+c1)=O)
+Cn1cc(
+nn1)
+c1ncc
+FC(F)(F)
+C#N)cc
+Nc1ccccc1
+C1(C)
+P(=O)(
+c3c(Cl)
+[C@H]12
+C(N)=N
+c(-c3ccccc3)
+[nH]3)
+c2cccc(-
+c1(-
+c2ccccc2)=O)
+C(NC(=O)
+/C=C(\C)
+c(=O)n1
+c3cccnc3)
+c2cccc(C(F)(F)F)
+C(NC(
+OC(C)(C)
+C(=O)NC(
+C(F)(F)F)cc3)
+CCC(=O)
+COc2ccc(
+n(-c2ccccc2)
+OCc1ccccc1)
+C(N(
+CC[C@@H]3
+3)c1
+)cc(OC)c1OC
+Cc2n
+[N+](
+P(
+c3nc(
+CCCn1
+C(F)F)
+CN2C(=O)
+S(=O)(=O)N3
+c(O)c1
+sc2
+[C@H](N)
+3c(
+c1(Cl)
+[C@H](O)[C@H](O)
+=O)ccc(
+ncc3
+cccn
+CCCC3
+/C=C/C(=O)
+c3cccs3)
+c2ccccc2Cl)
+c1nc2c(
+CN2CCN(
+c(-c2ccccc2)
+CC(F)(F)
+C(=S)N
+c3c(F)
+N)ncn
+Clc1ccc(
+)cc2)cc1
+oc(=O)
+c5ccccc5)
+O[C@H]2
+c1cccc(Cl)c1
+[N+](=O)[O-])c1
+N2CCC(
+C1C2
+CCC[C@H]1
+S2
+[C@H]1CC
+CN(C(
+c3ccc(Br
+C(=N)N)
+cn(
+Br)cc1)
+Cl)c1)
+N1CCOCC1
+Cn1cn
+C(=O)C)
+C(N[C@H](
+c1cc(Cl)ccc1
+(O)=O)
+c1ccc(OCC
+nc21
+COc1ccc2c(c1)
+c2ccc3ccccc3
+CN(C)C(=O)
+C4CC4)
+CC1)=O
+c3ccc(O
+c3C)
+c1(F)
+O=S(
+C(CCCC
+CC2)ccc1
+[C@@H](NC(
+c3ccccc3)CC2)
+c2ccc(N3
+O=C(Nc1ccc(
+cc3c(
+C)=O
+CC1=C(
+c2c1)
+n3c(
+(=O)o
+=O)C
+c2ccc(O)cc2)
+cc(N
+O=C(/C=C/
+C(=O)NO)
+c2cc(O)
+c(NC(
+CCc1ccccc1)
+C5)
+C[C@H](N)
+[S+]([O-])
+c2=O)cc1
+=O)CC1
+OC)cc2)
+C=C(C)
+c2cs
+/C=C(/
+c3nc(-
+c2cc(F)cc
+c3)cc2)
+C2CCCC2)
+o3)
+C(O)(
+Cc1ccc(NC(=O)
+C23
+S(=O)(=O)c1ccc(
+C1=C(C)
+C(N[C@@H](
+C(F)(
+o2)cc1
+c2ccc3c(c2)OCO3)
+n2C)
+c2cccc(Cl)c2)
+n1C
+c2ncccc2
+[C@@H]1CC
+[nH]1)
+n2)ccc1
+c3cccnc3
+=S
+Br)cc(
+c2ccccc2F)
+c2ccc(F)cc2
+c2ccc(Br)cc2)
+-c1c(
+Cc2ccc(-
+c2ccc(OCC
+/C=N/N
+C(C)C)=O)
+C(F)(F)F)cc1)
+P(=O)(O)O
+c1ccncc1
+c(O)c(
+#N)
+CCNC(
+3)cc(
+nn3
+c-
+CC2)C1
+c3cc(OC)
+Cn1c(=O)
+CC2)CC1
+C[C@H](C)
+C1CC1)
+OC[C@H]1
+=[N+]
+(C)(O)
+[C@H]5
+1C
+C#N)cc1
+c1(O)
+c1c2c(ccc1)
+[n+]([O-])
+[N+](=O)[O-])cc2)
+nn3)
+/c(
+CN4
+c4ccc(F)cc4)
+Fc1ccc(
+s2)cc1
+Cc1nc(
+c(N2
+C[C@]12
+OCC2
+c1ccc2[nH]
+O)cc2)
+[C@H]2O)
+c2ccc(NC(=O)
+c1)N
+c4[nH]
+=O)cc(
+c1nc(N)
+CCOC)
+C=C2
+3)cc2)cc1
+N(C)C(=O)
+c3c(O)
+c1ccccn1
+(=O)N
+nc2n1
+c1cc(-c2ccc(
+c1cc2cccc
+C(C
+Br)cc2
+c1c(-c2ccc(
+C(\
+O=C1N
+c2cc3c(cc2
+C(Cl)
+c1nc(C)
+C2CCCC
+CC5)
+c3ccc(O)cc3)
+c3c(-
+c1N
+c1ccc(-c2ccc(
+c3c(cc(
+CCc1ccccc1
+/C=N/NC(=O)
+n(-c2ccc(
+c3ccc(F)cc3
+ccc(Cl)
+COc1cc2c(cc1
+C(F)(F)F)cc(C(F)(F)F)
+C1O
+c2cccc(C)
+c1cc(NC(=O)
+Cc3ccc(
+C(C#N)
+C(=O)OC(C)(C)C)
+C(=O)c1ccccc1
+CC(C)(C)O
+c3cccc(F)
+CCCCCCCCCCCCCCCC
+c2F)
+CC=C(C)C)
+Oc1c(
+C(OC)
+CCc2ccccc2)
+c2)cc(
+=O)cc2
+c4ccccc43)
+Br)c1
+(F)F
+C(N)=O
+n1c2c(
+=C(O)
+nnc2
+c4ccccc34)
+/C=C/C
+Cc2ccc(F)cc2)
+c1ccccn1)
+O=c1[nH]
+n(-c3ccccc3)
+C(C(N
+[C@H]3CC
+O[C@H](CO)[C@@H](O)
+CCCCC)
+-c2cc
+c1ccc(C)cc1)
+ncn2
+c(=O)n2
+c2cccc(OC)
+nc1-
+c2cc3cccc
+C4CCCC
+=O)cc1)
+c(C(F)(F)F)
+OC(C)C)
+c3c2)
+oc1
+c2ccccc21)
+c3)cc
+c2c3ccccc3
+C(F)(F)F)cc2
+c2n(C)
+2)CC1
+sc2c1
+CCC3(
+c1ncn2
+)cc1)=O
+c4c(cccc4)
+/C(C)=C/
+COc1ccc(NC(=O)
+[C@H]1(
+[C@@]5
+Cl)cc(Cl)
+=N1
+c3)cc2
+O=S(=O)(N
+C1CCCC1
+c1ccccc1-
+n2cc(
+c1(-c2ccc(
+SCC(=O)N
+[N+](=O)[O-])cc
+N#Cc1ccc(
+c12c(cccc1)
+OCc2ccccc2)
+C(N3
+C1C
+c2Cl)
+c1ccc(-c2n
+CCCN(C(=O)
+c1ccc(-n2
+CN2CCC(
+c1c(NC(=O)
+CNC
+N(C)C
+c3nc4ccccc4
+c(=O)[nH]c1=O
+[C@H](O)[C@@H](O)
+=O)C1
+c3c[nH]
+C(=O)C1
+c3cccc(Cl)c3)
+-c2o
+N[C@H](
+OCc1ccccc1
+OCC1
+n1c(-
+c3cc(F)cc
+-c2cs
+c1ccc(O)cc1
+O[C@H](CO)[C@@H](O)[C@H](O)
+C#N)cc2)
+)cc(C)
+c4ccc(Cl)cc4)
+[C@@]23
+ccc(O)
+Cc1ccc2c(c1)
+Cc1ccco
+CC(NC(=O)
+Cc2ccc(Cl)cc2)
+c2O)
+c3ncc(
+C(=O)C2
+c1cccs1
+CCCN(C)C)
+nc3c(
+[C@]23
+C1CO
+nc1N
+C(=O)C
+CCN(C)CC3)
+c2ncnc3
+CN1CCC(
+c2cc(OC)c(OC)c(OC)
+c(C(=O)O)
+c2nc(N)
+[n+](C)
+C3=N
+c2cc(NC(=O)
+cc21
+c(C)cc1
+CCN1CCN(
+C2)C1
+c2ccc1
+S(=O)(C)=O)
+C=C)
+C(=O)N1CCN(
+n2cc
+[C@@H]1(
+c3ccccc3)cc2
+CNS(=O)(=O)
+c4ccc(OC)
+C(CO)
+(C)(C)
+C(/C=C/
+cc2)c1
+c2N
+CCCN1C(=O)
+c1)C
+=C1/
+OCC(O)
+)cc12
+c1ccc(N2
+C)c(
+c2c(N
+cc2c1
+Nc1nc(
+[C@]3(
+[C@@H]3CC
+n3cn
+N=C(N)N
+on1
+C(=O)N(C)C)
+ccn1
+[C@@H](OC(C)=O)
+S(=O)(=O)O)
+c3nc(N
+cn3
+c2cc(OC)c(OC)
+N(CC(=O)N
+C3CCCC3)
+[nH]c(-
+ccc4)
+CC(C)=
+Oc1ccccc1
+Cc1ccccc1)NC(=O)
+c2c(c1
+[C@@H]2CC
+c3c(OC)
+C2=O)c1
+C1CCC(
+C(S
+c4ccc(C)
+OC)cc1
+Cc2cn
+nn(C)
+CC(N)
+c3ccc(N4
+C(C)C)cc1
+c1ncn
+CCCO)
+c1ccccc1)c1ccccc1
+Cl)c(Cl)c1
+n1cc
+3)CC1
+C(C(=O)O)
+ncn1
+CN1CC
+c1ccco1)
+C12CC3
+[C@@H](N
+N2CCCCC2)
+C3=C(
+c3cc(O)
+[C@H](C)C
+c12ccccc1
+c3cc(OC)c(OC)
+2)cc(
+C(=O)N2CCN(
+[C@H](O
+c2cccc3cccc
+N1CCCC1
+c(SCC(=O)N
+CCOCC2)cc1
+c12cc(
+[C@@H](O
+C2)CC1
+=O)[nH]
+c3ccc(Br)cc3)
+c(=O)n(C)
+C(CO
+C(=N)
+c3ccccc3Cl)
+c(C(=O)
+ccc2c1
+c4cccn
+Nc1cc(
+Cc1o
+OCO2)
+c1ccco1
+Cc1c(C)
+c3ccccc3)=O)
+CC3)cc2
+=[N-]
+c1cccnc1)
+C(C)(C)C)=O)
+c(CC)
+c1cccc(F)c1
+CC5
+4CCOCC4)
+CCN(C)CC2)
+3)ccc1
+c3nc(C)
+[C@@]3(
+c2ccccc2)cc1)
+[C@@H](CC
+CCC2(CC1)
+C(F)(F)F)c3)
+c1cccs1)
+[C@H](OC(C)=O)
+c2cc(N
+P(O)(=O)
+=C(N)
+/N=N/
+nnc(
+CO2
+C(=O)N(C
+c1ccc(C)cc1
+CC#N)
+Oc3ccc(
+ccccc12
+S(=O)(=O)C)
+c1(NC(
+CC[C@]4(C)
+CCCCN)
+[nH]c1
+CCCCNC(=O)
+(c2ccccc2)
+nc1C
+c1cccc(C)c1
+c1c(N)
+ccc12
+(C)C)=O)
+C(CC
+c4ccccc4)cc3)
+n2C
+CCNCC3)
+c2c(N)
+CCCCO
+CCCCC
+c3ncccc3
+c1cc(C(=O)N
+Cl)cc3)
+sc3
+c2cc1OC
+c(C)c(C)
+/C=C2/
+c1ccncc1)
+c2nc(N3
+c3ccc(OCC
+c2c(Cl)cccc2
+2)cc1)
+OC(C)
+O=c1
+4)=O)
+[nH]c2
+C(=O)N1CCC(
+[C@]5
+[C@@H](CO
+C3=
+c3ccccc32)cc1
+c4ccccc4)CC3)
+CC(N)=O)
+c2cc(Cl)c(
+c2cccc(N
+[C@H]3O)
+c2nc1
+)cc2c(
+N=C1
+CC2)n1
+c5cc
+cc2)=O)
+c1cccc(NC(=O)
+OCCO2
+c1cc(Cl)c(
+[C@H]1CC[C@H](
+n2)C1
+C/C=C/
+c(Cl)cc1
+ccc(Cl)c1
+C(C)=C(
+C/C(=N\
+C1)C2
+c1ccc(Br)cc1
+CCCS
+NC(N)
+CN(CC)
+3)ccc2
+C(NC
+)ccc3
+c(OC)cc1
+c(C
+nc(-c3ccccc3)
+OO
+c4ccc(O)
+C4=O)
+S)=N
+cc1)=O
+=[N+]=[N-]
+C/C(=C\
+/N=C(/
+N2CC
+Oc2c(
+CCCN)
+2)C1
+Cn1cc
+c3ccccc3F)
+c1ccc(C(=O)N
+N=C2
+nc(SCC(=O)N
+CCCCN1
+C1CCCC1)
+c1c(Cl)cccc1
+=C(C)C)
+n3C)
+c1cc(OC)ccc1
+C(=O)(N
+F)c(Cl)
+c3ccccc23)cc1
+c3cccc(C)
+c1ccc(OC
+n1-
+c1c(OC)ccc(
+Cc1ccc(O)cc1)
+c4ccncc
+ccccc4
+c(=S)
+N(CC)CC)
+nn(-
+[C@@H](C
+c1nc2ccccc2
+c21)
+c1cccc(N
+4)cc3
+c(=O)[nH]c(=O)
+c2ccc(Cl)c(Cl)
+c1c(NC(
+O[C@H](CO
+n3cc
+Cc1ccc(Cl)cc1
+=O)=O
+c1ncccc1
+(Cl)
+/C2
+oc(C)
+c1cc(C)ccc1
+c1(NC(=O)
+CC2CC2)
+n3)cc2)
+CCO1
+c2cccc(O)
+Cc1nc(-
+c2c(F)cccc2
+c1cc(-c2n
+N2CCCC
+C(OCC
+/C=C3
+CC12
+C(O)=O
+C[C@H]1CN(
+=N)N
+[C@H](CC
+C)ccc1
+c2c1cccc2
+c1cncc(
+c1c(Cl)cc(
+C3CCN(
+c2cccc(F)c2)
+c3ccc4c(c3)OCO4)
+NC1
+CCOc1ccccc1
+N1CCN(C(=O)
+F)cc3)
+Cc1cs
+c-3
+n2cnc3c(
+N2CCCC2)
+[C@@]4(C)
+-c2c(
+c3cc(OC)c(OC)c(OC)
+c1c(Cl)ccc(
+n(CC)
+c1(C(N
+c5cc(
+C(c1cc(
+[C@@H](OC(=O)
+[C@@H](O)[C@@H](O)
+(=O)=O)cc1
+NC(=N)
+c1c(C(=O)N
+[C@@H](C)C
+cnc(N
+CNCC
+N2CCN(C(=O)
+NC1=O
+[C@@]1(O)
+c2)ccc(
+ccc21
+SC
+NC(=O)C(
+CC3)=O)
+c2cc(C(F)(F)F)cc
+)ccn1
+[N+]1
+NC(=O)c1ccc(
+CC[C@H](C)
+c4cc5
+c3cc4c(cc3
+N1CCCCC1
+CO1
+c1cc(F)ccc1
+CC(=O)Nc1ccc(
+CC3)cc2)
+NCCCC
+COc1ccc2c(
+-c2[nH]
+c2cc(Cl)ccc2
+c2ccc(C(F)(F)F)cc2)
+COc1cc2c(cc1OC)
+COc1ccc(-c2n
+oc2c1
+=C(N)N)
+cc2)ccc1
+C3)C2
+C1=C
+S(=O)(=O)N(
+COC
+CC[C@]3(C)
+COc1ccc(C2
+C(c3ccccc3)
+c3ccc(N
+CC1CC1)
+)cc(-
+n1c(N
+CC(C)(C)C)
+n3)cc
+c2c(Cl)cc(
+c1c(F)cccc1
+N2C
+[C@H](C)CO)
+-c2nc(-
+[N+](=O)[O-])cc1)
+/C=C/C(=O)N
+Cc1cc2
+CC(C)C
+c1(-c2n
+CNC(=O)N
+C(=O)O1
+Cc1cccc2
+nn2)cc1
+c2cccc(C(F)(F)F)c2)
+c3ccc4ccccc4
+FC(F)(
+n2c(=O)
+S(=O)(=O)c2ccc(
+Cc1cn(
+ccc(F)c1
+O[C@@H]3
+c3cccc(F)c3)
+CCN)
+c2occc2)
+CCC4)
+C#N)cc3)
+Cc1ccc(C(=O)N
+OC[C@H]1O[C@@H](
+c(C(
+nc4)
+C[n+]1
+F)cc2)cc1
+[C@H](O)[C@@H]1O
+ccc(NC(=O)
+CCc1cc(
+c3ccc(C(F)(F)F)cc3)
+-c2s
+[C@](O)(
+c1n(C)
+CS)
+c(F)c2)
+C(O)C(O)
+CC1CCCCC1)
+n1c(=O)
+C)C
+N1CCOCC1)
+[C@@](O)(
+CC1=O
+c1ccc2c(c1)OCO2
+CCNCC2)
+Cn2cn
+[C@@]2(O)
+c3cs
+Cn1c(
+c4c(C)
+c2cccc3)
+c2cc(=O)
+c2C1
+c(=O)c(C(=O)O)
+Cc2ccccc2)CC1
+/C1=C\
+nc2ccccc12
+CCCCCC)
+c1c2c(cc(
+c2c(n1)
+c1(C(
+Cc1ccc(F)cc1)
+n2)cc(
+cccc12
+[N+](=O)[O-])cc2
+c1c(C(N
+c2[nH]1
+C(=O)c2ccccc2
+COC(=O)N
+CCN(CC
+Cc1ccc(F)cc1
+nnc(-
+C1CCCN(
+C[C@@H](N)
+CCNCC1
+[C@@H]1C
+C2)=O)
+[C@]1(O)
+/C(=N/O)
+cs2)cc1
+c3cccc(OC)
+C(=C/
+C(=O)CC
+[C@H](OC(=O)
+ccc(NC(
+c2nnc(
+c13)
+cccc2)c1
+C(F)(F)F)cc(
+OCCO3)
+Cc1s
+c1nnc(
+c1cc(Cl)cc
+c43)
+[C@@]21C
+ncn3)
+c2ccc([N+](=O)[O-])cc2)
+CCN(C)CC1
+c2ccc(C(=O)N
+CC1)=O)
+c1cc(NC(
+c1cc(Cl)
+CC2)cc(
+CCl)
+[nH]c3
+c3ccccc3)cc
+cc(NC(=O)
+c2cc(C(=O)N
+c1ccc(O)cc1)
+[N+](C)(C)C)
+C1CC2
+C(CN
+cn2)cc1
+cc2C)
+CC3(
+Cc1ccc(N
+C1)=O
+c1cc(Cl)cc(
+c(=O)[nH]1
+c(OC
+o2)c1
+c1c(-c2n
+COc1ccc(N
+/C=C1\
+c2cccc3ccccc23)
+Nc1cccc(
+c1c(O
+Br)ccc1
+N=
+OC)c(OC)c1
+CC(F)(F)F)
+CC2CCCCC2)
+cc(C(=O)N
+c3c(F)cccc3
+CC(C(=O)N
+/N=
+NC(=O)c1ccccc1
+c2c[nH]c3ccccc23)
+c(NC
+s2)c1
+[C@H]1CC[C@H]2
+c2)cc1)
+Nc1cc
+C23CC4
+c12cccc
+[N+](C)(C)
+[C@]2(O)
+c3cc(Cl)ccc3
+C(C)(C)C)cc1
+ccn2)
+c1nnc(-
+c2ccs
+[C@H]1C
+N3CCOCC3)
+OCCN
+F)cc3
+c2ccc(OC
+Cc1ccc(-c2ccccc2
+C1CCN(C(=O)
+cc(C)c1
+c2ccccc2)C1
+c3ccc([N+](=O)[O-]
+C(C)C)c1
+Cc1c[nH]c2ccccc12)
+c1ccc(Br)cc1)
+c4ccc(-
+C3)cc1
+(F)F)
+CC3CC3)
+nnn2
+Cc1ccc(S(=O)(=O)N
+Cc1ccc(-
+N)c1
+c1(N)
+nnn1
+ccc(O
+cc3)cc
+Cc1ccc(Cl)cc1)
+COc1ccc(-n2
+c1ccc(Cl)
+c2cc(F)
+[nH]c2c1
+CCOC(
+n2c1
+c1ccc(C)
+c1ccc([N+](=O)[O-])cc1
+C1=C(O)
+C(F)(F)F)c1)
+CCc3ccccc3)
+Cc1ccc(-n2
+[C@]4(C)
+c3cc4c(cc3)
+[C@@H]2[C@@H](
+c3nc4c(
+[C@H](C
+c2ccc3[nH]
+n5
+NC(=O)CS
+nc2N
+c(C)c2)
+S1(=O)
+CCCCCCC
+C(=N
+C1(C)C
+c1c2cccc
+OC)c(OC)c3)
+CC(CC(C3)
+c([N+](=O)[O-])
+[C@H](N
+[C@H](C(=O)O)
+c2cccc([N+](=O)[O-])
+ccc1O
+c(C)n1
+CCC(O)=O)
+CCC1(
+c1cc(O
+COc1ccc(C(=O)N
+[C@@H]2O
+c4ccc5c(
+CCOC1
+B(O)
+C2C(
+N#Cc1c(
+CCOc1cc(
+c1ccccc1)=O
+CC(=O)N[C@@H](
+5)cc4)
+c3n(C)
+NC(=O)CO
+c3cccc(Cl)
+S(=O)(N)=O)
+C(=O)O)c1
+c2sccc2)
+c1c(C(
+c2ccccc2)n1
+N3CCN(
+c3ccc(C(=O)N
+c1co
+C(NCC
+#N
+OCCN(
+=O)CC2)
+n2c3c(
+c1(Cl)ccc(
+N(CC)CC
+c3F)
+COc1ccc(-
+CCCC(=O)N
+F)cc2)c1
+c4ccco
+c2ccc(OC)c(OC)
+c1(C(=O)N
+C(C)(C)O)
+Cc1cc(N
+c2=O
+N1C
+=C(N
+c1ccccc12
+nc2cc1
+c1sc(
+S(C)(=O)=O
+nc(Cl)
+cn4)
+OCCCO
+ncn2)
+CC(O
+c4s
+c(O)cc1
+O=C(CSc1n
+CC[C@H](O)
+C(=O)O)cc2)
+c4cc(Cl)cc
+[nH]2)cc1
+c1ccccc1Cl)
+Cl)c(Cl)c3)
+c2=O)c1
+c6cccc
+[C@H](CC(C)C)
+=O)C)
+C(=O)N(CC)
+CCCC4)
+c2nc(-c3ccccc3)
+C2C3
+c2cc(Br)cc
+(-c3ccccc3)
+c12ccc(
+CC[C@@H](C)
+nc2)cc1
+CC1=
+(F)(F)F)
+C(F)(F)F)ccc1
+c12c(cc(
+C(=O)c1c(
+CCC[C@H]2
+C(=O)N[C@@H](Cc1ccccc1)
+CCC=C(C)C)
+=[N+]=[N-])
+=C4
+n1c(C)
+c1cc(-n2
+Cn2cc
+n2)ccc(
+c2sc(
+OCO4
+C[C@H]4
+c2ccc(Cl)cc2Cl)
+OCc3ccccc3)
+c2cc(Cl)
+Cl)c(Cl)c1)
+[C@@]1(C)CC
+/N=C2
+c(-c2n
+[C@H](C(C)C)
+c1c2c(ccc1
+c2cn(
+n1(C)
+Cl)cc3
+c2ccccc2OC)
+c2c(-c3ccccc3)
+/C(C#N)
+no2)
+S(=O)(=O)c1ccccc1
+nc2C)
+c2sc3c(
+=C/C
+c3cc(OC)c(OC)c(OC)c3)
+cc1-
+s2
+c4ccc(OC)cc4)
+CC(O)(
+Cc1[nH]
+c1(O
+C(=O)N1CC
+n(CC(=O)N
+nccc1
+CS(=O)(=O)N
+)cc4)
+c4ncc
+[C@](C)(O)
+C)C)
+C2)n1
+Cc2ccc(OC)cc2)
+c2cccnc2
+CCN(C)C
+c1(-n2
+Nc1c(
+CCN2C(=O)
+C[C@@H]4
+[nH]2
+[C@H](NC(
+c1ccc(NC(
+OCC(N
+COc1ccc(Cl)cc1
+CC1(C)C
+c4c3
+CN2CC
+c4ccccn4)
+NC(=O)[C@@H]1
+Cc1ccco1)
+C(=O)N2CC
+c2c(ccc(
+cc5)
+cc12
+c1cc(=O)
+NC(=O)C
+CCn1cc(
+c1cccc(Cl)c1)
+C2)ccc1
+C2CCN(C
+c1cc(OC)c(OC)c(OC)
+4)cc2)
+c1c(-n2
+c3cccc(C(F)(F)F)c3)
+O=C1c2ccccc2
+C[C@H](N
+(N)
+CCCC(C)
+c2ccc(Cl)
+[N+](=O)[O-])cc(
+CCOCC2)c1
+CCC(C)(C)
+n2)cc1)
+Cn2c(=O)
+c2ncn(
+CC(C)N
+c(=O)c1
+[C@]34
+Cc3c(
+)ccc1)
+C1(O)
+CCC)=O)
+c2ccccc2)ccc1
+C(=O)NC(=O)
+C(OCC)
+C/C(
+c1cnc(
+[C@@H]1O)
+CC3)cc1
+c1nc(-c2ccccc2)
+c1cn2
+/N=C1\
+CCC[C@@H](
+Nc1ncn
+C=CC(
+c1c(F)ccc(
+c1ccc(C2
+[C@@H](OC)
+Cc1no
+c3)CC2)
+OC[C@@H]1
+Cl)cc2Cl)
+C(N)=N)
+cc3)cc2)
+[C@H]2[C@H](
+cccc5)
+-c2ccc(-
+OCCOCC
+C3=O
+N2CCN(C
+COc1cccc2
+S)N
+(CO)
+c1ccccc1Cl
+c1ccc2ccccc2c1
+ncc(-
+ccc(OC)cc1
+nc2-
+CC(C(=O)O)
+c2ccc(OC)cc2
+c3cco
+C(NC)=O)
+CCCCCCN
+CC(C)(O)
+c2cc3ccccc3
+=O)o
+-c2c3c(
+(C)C)cc1
+OCO3
+Cc1ccc(O
+CC(c2ccccc2)
+CC4)cc3)
+ncc2)
+CCCCCCCC)
+c1cc2cc(
+(=O)=O)c1
+n2ccc(
+cc3)=O)
+c1c(Br)
+cc2c(c1)
+c1ccccc1)=O)
+N(CCCl)
+N(c2ccccc2)
+Cc1ccc(-c2n
+5CCCC
+Oc1cc(
+3)cc2)c1
+Nc1ncc(
+c2C)cc1
+N(Cc2ccccc2)
+CC)cc1
+c2c(C#N)
+CC1CCN(
+OC)c(OC)cc1
+c1cccc(O
+on2)
+ncnc(N
+c1cnccc1
+C1N(C(
+[C@@](C)(O)
+NC(=O)[C@@H](
+c3c4ccccc4
+c1c(Cl)c(
+/C=C/C(
+c2ccncc2
+[C@H](OC)
+nc2ccccc21
+5CCOCC
+c4cc(C)
+Br)c2)
+nc3ccccc3
+cnc2c1ncn2
+CCCCN(
+CC)c1
+cnn2
+=O)c(
+c1(C2
+OC(C)(C)C
+n(Cc3ccccc3)
+c(C)c3)
+nc(C(=O)N
+CC2)cc1)
+c2cc(N3
+c2c(Cl)cccc2)
+c2ccc(C#N)cc2)
+O4)
+c1cccc2)
+CCC(=O)O
+c4ccc(C)cc4)
+cn2)CC1
+OCC3
+(-c2ccccc2)
+N1CCCC
+c1cnc(N
+c4)CC3)
+c[n+](
+Cc1ccc(S(=O)(=O)
+c4cccc(Cl)
+c3ccs
+CC1=N
+c[nH]1
+c(=O)n(C)c(=O)
+cc(-c3ccccc3)
+OCC(=O)O)
+c1(OC)ccc(
+CCC(C)C)
+c3cc(Cl)c(
+c1-c1ccccc1
+C#N)c1
+c2ccc3ccccc3c2)
+CC(CC(C4)
+C)cc(
+c1cccc(F)c1)
+c3ccc(C#N)cc3)
+CN(C)c1ccc(
+(c1ccccc1)
+c1cc(C(N
+c1c(OC)cc(
+CC1CCCO
+CCC[C@@H]1
+nn12
+Cn2cc(
+(=O)O
+[C@]12C
+[C@H]2O
+c1cc(C(
+c(OC)c2)
+CCC(N3
+c3ccc(OC)cc3
+C2)C3)
+NC(=O)C2
+c2cnccc2)
+C/C=C\C/C=C\
+c4o
+NC(=N)N
+[C@H](CC)
+c2cc(O
+C(=O)CS
+CCCCC2)cc1
+O=C(COC(=O)
+c1ccc(O)
+c2c(C)cc(C)
+C(=O)N2CCC(
+ncnc3
+c3ccccc3OC)
+[C@@H]4[C@@]5
+[C@H]2CC[C@H](
+/N=C\
+[C@@H]2O)
+c3cccc(-
+N(C(C)=O)
+c3ccccc3-
+c3cc(OC)c(OC)cc3
+c2ccccc2c1=O
+SC(=S)
+c1ccccc1)N
+CCCN(C)
+CCSC)
+nc(C)c1
+NC(=O)C)
+C(=O)NC(=O)N
+c1c(C)ccc(
+c2ncccc2)
+c(N4
+C(=O)N1CCC[C@H]1
+CC(=O)N3
+CN3CCN(
+c2ccc(O)cc2
+CCC(CC)
+n2)n1
+[C@@H](C)O)
+NC(=O)/C=C/
+=O)n(
+[n+]3
+C#N)cc2
+FC(
+c2cc(Cl)cc(Cl)
+NC1=N
+c3c(N
+c2c1=O
+CCC#N)
+c1O)
+Cc4ccccc4)
+c2cccc3c2
+N(Cc1ccccc1)
+c6ccccc6
+ccc(OC)c1
+OC1=O
+nc(C(F)(F)F)
+C(=O)NC)
+c2co
+c(F)cc1
+c3occc3)
+O2)cc1
+c1cccc2ccccc12
+N=C(N
+c1ccccc1O
+N1CCN(C
+ns
+nc23)
+c4c3)
+COC(C)=O)
+CC3CC(
+c3ccc(Cl)
+CCCN(CCC)
+c1cc(F)c(
+[C@]3(C)CC
+c(C)cc(
+c1cccc(C(F)(F)F)c1
+c1ccc(CN
+C(=O)/C(=C/
+c3ccc(O)cc3
+c1cccc(-
+ccn3)
+-c1cc
+c1c(-c2ccccc2)
+SC1
+CO[C@@H]1
+c1c(C)cccc1
+O=S1(=O)
+c1cccc(-c2n
+c(C)cc(C)
+cc5
+c(CN
+c3c(Cl)cccc3
+COc1ccc(OC)c(
+C(=O)N[C@@H](C)
+c3cc(C(F)(F)F)cc
+n1)=O
+=C(C#N)
+=O)cccc1
+CO[C@H]1
+[C@H](Cc2ccccc2)
+c(=O)n3
+CCCN(C
+CC(C)(C)C
+c2c(OC)cccc2)
+CN(C)S(=O)(=O)
+sc(-
+c1cccc(C)
+Cc2ccc(O)cc2)
+c1ccc(O)c(O)
+[N+](=O)[O-])ccc1
+c(=O)[nH]c2=O)
+[C@@]3(C)CC
+nc32)
+COCCO
+c2ccc3n
+[C@H](Cc1ccccc1)
+CC[C@@H](O)
+c3ccc(Cl)c(Cl)c3)
+c2cc(C)ccc2
+c2ccccc2C)
+[C@@]21
+-c2nc(N
+[C@@]34
+/C=N\
+C=C\
+nc(OC)
+CCC(N)
+c2ccc(Cl)cc2)cc1
+c1(S
+[nH]n1
+ccccc12)
+c1c-2
+CN(CC
+COc1cc2c(
+c2cc(OC)c(OC)c(OC)c2)
+CCCN2C(=O)
+C2CC
+C(NO)=O)
+C(=O)N[C@H]1
+CCCN1CCN(
+c2cccc(O
+C2(C)
+CCCO2)
+cc3C)
+[C@@]2(C)CC
+)cc(O)
+N(O)
+C(C(=O)
+c(/C=C/
+c2ccc(Cl)c(Cl)c2)
+CC[C@H]4
+N(CCC)
+C(=O)NCCCC
+c3ncccc3)
+n3)cc2
+4)cc2
+COc1ccc(C(=O)
+cn2)c1
+c45)
+CCCNC(=N)N)
+CCC[C@H](
+c3ccc([N+](=O)[O-])cc3)
+nc(N2
+c2nnc(-
+CCn2
+c1(N2
+c4)cc3)
+C1=CC(=O)
+SS
+C21
+O=C(N/N=C/
+c(-n2
+nc3c2
+C(N1CCN(
+n(Cc2ccccc2)
+C(O)=C(
+N2CCN(C(
+c2ccccc2c1)
+CC(O)CO
+c2cc(F)c(
+CC(=O)OC
+C(=O)Nc1ccccc1
+c3cc(OC)ccc3
+Br)c3)
+4CCCCC4)
+CCCC(N
+C(C(C)C)
+CCC(=O)N1
+C(=O)N/N=C/
+c1ccc(Cl)cc1Cl
+c3ccccc3C)
+c3c2cccc3)
+c1ccc(Cl)c(
+4)c3)
+o2
+c3cccc(O)
+C1CCN(C
+c(=O)cc(
+[C@@]4(C)CC
+Cc1cc(O)
+[C@H](C)N
+Cc1c(Cl)
+c2ccccc2)CC1)
+c1(F)ccc(
+CN(S(=O)(=O)
+cc1)=O)
+c1c(cccc1)
+c1c(OCC
+c3nc(N)
+c2c(F)cc(
+c(OC)c3)
+c2sccc2
+CC2=O
+nccc2
+CCC3(CC2)
+Cn2c(
+CCCC(=O)O)
+/C(=N\O)
+cccc2)cc1
+c3c(ccc(
+c2c(C)cccc2
+P(O)(O)=O)
+CN=C(
+C(OC
+N2)
+ccc5
+cc(=O)
+COc1cc(N
+c1sccc1
+O=C1N(
+/C=C3\
+C(C)(C)O
+CC)cc2)
+c1c(F)cc(
+C)C(=O)
+C3)cc2)
+C2(C)C)
+c2c(=O)n1
+CCNS(=O)(=O)
+c3nnn
+C(=S)S
+C[C@@]12
+c2ccc(-c3ccccc3)cc2)
+c2ccc(N(C)C)
+C1N(C(=O)
+Cc1cc(C)cc(
+c1oc(
+[C@@H](C)CO)
+c4)cc
+c(C(N)=O)
+NO
+/C=C/C=C/
+-n1
+c1ccc(C(F)(F)F)cc1
+c(N(C)C)
+C1(N
+C(C)(O)
+N3C(=O)
+Cc1cccc(C)c1
+c3cc4ccccc4
+C34
+(C(=O)O)
+[C@H]1[C@H](
+[C@H]1O)
+N(S(=O)(=O)
+c2cccc(OC)c2)
+O=C1NC(=O)
+CC(C)O
+C2=C(O)
+[C@H]2CC
+C(C)(C)C)cc2)
+Cc1c2c(
+CCC[C@@H]2
+C2CCN(C(=O)
+c(OC)c1)
+c4cccs
+COc1cc(OC)
+NC(=O)c1cc(
+c2cccc(NC(=O)
+-c2ccc(F)cc2)
+S(=O)(=O)N1
+c2cc(-c3ccccc3)
+c(CO
+c(C)c2
+P(O)(O)
+CCN(CC)C(=O)
+C(C(F)(F)F)
+nc2n(
+c2ccc(C)cc2
+n(C(C)C)
+CC[C@]43C)
+C(=O)N(C)C
+c4ccco4)
+cn(C)
+c2ncc(-
+c1nccc(
+c3cnccc3)
+c3ccc(Cl)cc3Cl)
+Nc1nc(N
+no1)
+S1(=O)=O
+P(O)(=O)O)
+nn2)c1
+c2ccc(F)cc2)CC1
+C2(C)C
+nc(SC
+CCN4
+CCCO3)
+c7
+CC[C@]4(C)[C@H]3CC
+c2ccc(S(=O)(=O)N
+c2ccc(Br)cc2
+[N+](C)(
+c4cc5c(
+C(=O)N[C@@H](CC(C)C)
+c1ccc2c(c1)OCO2)
+NC(=O)N1
+n(C)c1
+Cc1ccc(C)
+Cc1nc(N
+c2cc(C)cc(C)
+c1(OC)cc(
+c2cco
+C(CCC)
+COC(=O)c1ccc(
+C)C1
+N12
+c3ccccc13)
+[C@]3(O)
+c3sccc3)
+O=c1cc(
+NC(=O)[C@H](CC(C)C)
+C4CCCCC4)
+CCN1CCC(
+C2CC(
+c4cccc5
+c2n(C
+NS(=O)(=O)c1ccc(
+CCCN=C(N)N)
+n1c(N)
+cc4c(
+c2c3
+NS(=O)(
+OCCO4)
+N1(C(
+nc(N3CCOCC3)
+-c1cc(
+c4ccc5c(c4)
+N)cc1
+c1ccccc1F)
+c4ccncc4)
+N=C
+c3c(c1)
+/N=C(\C)
+c4n(
+c3cc(C)ccc3
+c2oc(-
+[C@@H](C(=O)O)
+CCC(O)(
+c3Cl)
+C12CC3CC(CC(C3)
+Cc1ccc2c(
+c(=O)c2c1
+c3ccc(C(=O)O)
+/C1=C/
+C(Cl)(Cl)
+c2cc(OC)ccc2
+OC[C@@H]2
+C(C(O)=O)
+cc(C)cc1
+c12n(
+3)cc1)
+Cn1c2c(
+ccc(Cl)cc1
+c3c(n2)
+F)c1
+[C@@]3(O)
+O=C(CN1
+c1(-c2cc(
+C3CCC3)
+c1(Cl)cc(
+N(C(=O)N
+c3cc(Br)cc
+CCC12
+ccn1)
+Cc1cccnc1)
+c3cccc4cccc
+[C@H]2C
+[C@H]2[C@@H](
+CCC(C(=O)N
+c3ccccc3)CC2)cc1
+CCCCCC3)
+n(C)c(=O)n(C)
+[C@H](O)[C@@H](O)[C@H](O)
+N(CCCl)CC
+Cc1ccco1
+CCN2CCOCC2)
+[C@H](CO
+OC(CO)
+c1-2
+CC(C)(C)N
+=C/C=C/
+C(=O)OCC(=O)
+c4cccc(F)
+c1ccc(S(=O)(=O)N
+4CCCC4)
+/C=N/NC(
+c1cn(C)
+c1c(C)cc(
+F)c(-
+C(C)(C)[C@@H]5
+c1ccc(S
+C1=S
+Cc1cccs1)
+c3n[nH]
+CCN(C)CC1)
+[nH]2)c1
+c(NC(=O)N
+c(Cl)c2)
+=O)cc3)
+c3cccc(N
+c(SC)
+c32)cc1
+c(F)c3)
+c2-
+c3ncccn3)
+c3cc(N
+-c2ccc(Cl)cc2)
+c4c(Cl)
+c(OCC)
+c3ccc(S(=O)(=O)N
+nc(-c2ccccc2)
+CCOCC3)cc2)
+c(=O)n(C
+C(C)C)cc2)
+c2no
+c4c5c(
+COc1ccccc1N1CCN(
+n5)
+CCCOc1ccc(
+co1
+c1cccc(O)c1
+(N3
+c1cc(OCC
+N1)
+=O)(
+=N2
+nc(NC(
+c4ccc(N
+c1cccc(-n2
+OC4
+c3c(N)
+O[C@H](C)
+nc2)c1
+c4ccc(C(F)(F)F)cc
+c2cc(OCC
+c2nc(O)
+Cc1ccc(OC)
+N1(C
+Cc1cccnc1
+c4cccnc4)
+c3n2)
+C(OC(=O)
+c5cn
+O=C(CS
+C1(c2ccccc2)
+C(F)(F)F)c(
+[C@H]1CO
+c4ncn
+C(C#N)=C(N)
+C1CN(C(=O)
+C1c2c(
+c1(Br)
+n[nH]1
+c3c(c2)
+c2)cc
+C(=O)C(C)
+c4c(F)
+c1ccc(C(
+/C=C1/
+c(OC)c(OC)
+[C@H](C(=O)N
+c1c(O)cc(
+c1ccc(CN2
+[C@]2(C)CC
+Cc1nn(C)
+CC(=O)OC)
+c1c(C2
+C3CCCCC3
+c1c(C#N)
+c1(C)ccc(
+C2=O)ccc1
+C)(
+[C@@H](O)[C@H]1O
+c2ccccc2O)
+c2ccnc(N
+c2c(F)cccc2)
+P(=O)(O
+)cc(OC)c1
+c3cc(O)ccc3
+C1N
+Br)c1)
+[C@H](Cc1ccccc1)NC(=O)
+[nH]c12
+3)cc21
+cnc12
+c1cc(F)cc
+c(C(C)C)
+c4cc(F)cc
+N(S(
+CCn1c(=O)
+C(=O)N2C
+C(CS
+sc1)
+c2cn(C)
+c1cc(C2
+c(N)n1
+C[C@H](NC(
+C[S+]([O-])
+c2cnn3
+CC[C@H](NC(=O)
+C#N)cc1)
+c2ccc(-c3n
+P(O
+CCN(CC)CC)
+c3cccc(OC)c3)
+CCCCCCC)
+OCCO2)
+CCc2c(
+c2)nc1
+ccc(C)c1
+c3-
+c2ccc(Cl)cc2)CC1
+nc3C)
+C23CC4CC(CC(C4)
+c3ccc(C(F)(F)F)cc
+C[C@@H](NC(=O)
+c2cc(S(=O)(=O)N
+cc(Cl)
+n1ccc(
+[C@]1(C)CC
+ncnc32)
+c4ccc(Cl)cc4
+c3ccccc3c(=O)
+3)cc2)CC1
+NS(
+c(C)cc2)
+CC[C@@]4
+ccc1)=O
+Cc1ccc(S(=O)(=O)N2
+ccnc1
+CC1CC1
+c1ccc(Cl)c(Cl)c1
+c1c(OC)c(OC)
+CC(CO
+n(CC
+c4n3)
+c2ccccc2C1
+nc3n2
+c2)cc1OC
+c1(Cl)c(
+CO2)
+Cc2ccccc2)c1
+C=C3
+C4(
+N[C@H]1
+c1ncc(-
+[N+]([O-])=O)cc2)
+c4nn
+oc12
+/C(O)
+CN(Cc1ccccc1)
+C3)=O)
+[N+]([O-])=O)cc1
+CCCCCCCCCC
+-c2c[nH]
+C(=O)c2c(
+c1(CN2
+c3n2
+C1=C(C)N
+C#N)cc(
+C(=O)N[C@@H]1
+c1C)
+O=C(N1
+N(C(N
+COc1ccc2[nH]
+c2nccc(
+O)=O
+cncc1
+c3c(F)cccc3F)
+CC(C)C)=O)
+[nH]cc2
+/C(=C(\
+c(=O)n(-
+C[C@@H](CO)
+CCN3CCOCC3)
+c1cc(OC)c(
+N1(C)
+c4ccc(F)cc4
+[C@@H]2C
+ncc3)
+O=C(Nc1cccc(
+cccc1)=O
+c2ccc(S(=O)(=O)N3
+N#Cc1cccc(
+c1c(F)c(
+c1(CN
+c3ccc(C)cc3
+c([N+](=O)[O-])c1
+c(Cl)cc
+c2cccc(C)c2)
+c(Br)c1
+CC(=O)N1CCN(
+c1c(C(F)(F)F)
+[N+]2
+CCN(S(=O)(=O)
+C)cc2
+/C(=C(/
+c2c(Cl)cccc2Cl)
+[C@@]13
+c(-c4ccccc4)
+nc1S
+O[C@H]3
+C(=O)O)cc1)
+c2c(C)cccc2)
+c1c(O)c(
+n2)=O)
+OCO5)
+O=C
+C(N(C)C)
+c1ccc(-c2ccccc2)cc1
+CC2=O)
+C(CNC(=O)
+c5[nH]
+CC(=O)N(C)
+cs2)c1
+c2ncnc(N
+c2ccc(Cl)cc2)c1
+Cc1nc2c(
+CC(CO)
+c(SC
+c(C)c1)
+[n+](C
+C)CC1
+c3cccc(C)c3)
+c3cn(C)
+c1cnn2
+[nH]c2)
+CC[C@]2(C)
+c1cccc([N+](=O)[O-])c1
+C(N)=O)c(N
+c2ccc(-n3
+[C@@H]4CC
+C(=O)NS(=O)(=O)
+C(=O)NC2
+c(F)cc2
+SC(
+c1ccccc1F
+c1cc(Br)
+c1ccn
+[C@@H]1[C@@H](
+c(OC)cc(
+Cc2ccc(C)cc2)
+c3c(Cl)cc(
+c1ccc2nc(
+[nH]c1)
+c2cc(Br)
+[C@@H]2C1
+/C(C)=N/
+c3ccc(NC(=O)
+ncc4
+P(=O)(OCC)
+c1n[nH]
+CCN1C
+ccc(F)cc1
+OC)c(OC)c1)
+N(S(=O)(
+c1cc(O)c(O)
+C1C2(
+CC(C)C[C@H](NC(=O)
+c1c(O)ccc(
+(O)=O
+S2(=O)=O
+N(C(C)C)
+C2CCC2)
+ncnc2
+c3ccccc3C2=O)
+C4)cc3)
+[C@@H](CC(C)C)
+OC(C)(C)C)=O)
+[N+]([O-])=O
+C=CC(=O)
+C)O
+c3c1
+c1(-c2ccccc2)
+c3O)
+cnc2)
+oc2
+n4cn
+Nc1nc(-
+CC(NC(
+cnn1
+C(F)(F)C(F)(F)
+c23)c1
+CCCC2)cc1
+c3cc(C(=O)N
+CC(=O)NC(
+c1cc(Br)ccc1
+C(=O)N1CCN(C(=O)
+C(C)=O)cc1
+c2cc3c(cc2)OCO3)
+nc(SC)
+[C@@H](CC)
+OC[C@H]2
+c1ccc(C(N
+C(=O)[C@H](
+C=N
+c23)CC1
+[N+]([O-])=O)c1
+3)ccc21
+)ccc1O
+[C@@H]1(O)
+/N=C2\
+CC(c1ccccc1)
+no2)cc1
+nn(C
+[C@H]1(O)
diff --git a/Pilot1/ST1/config_st_spe_training.json b/Pilot1/ST1/config_st_spe_training.json
new file mode 100644
index 00000000..43f18b90
--- /dev/null
+++ b/Pilot1/ST1/config_st_spe_training.json
@@ -0,0 +1,52 @@
+{
+    "general": {
+        "use_hvd": true,
+        "batch_size": 64,
+        "epochs": 400,
+        "lr": 0.00000991301767144166,
+        "loss_fn": "mean_squared_error"
+    },
+
+    "data_loading": {
+        "data_path": "/lus/grand/projects/datascience/avasan/Data_Docking/2M-flatten",
+        "rec": "3CLPro_7BQY_A_1_F",
+        "pattern": "Orderable_zinc_db_enaHLL.sorted.4col.descriptors.parquet.xform-smiles.csv.reg"
+    },
+
+    "tokenization": {
+        "vocab_size": 3132,
+        "maxlen": 45,
+        "tokenizer": {
+            "category": "smilespair",
+            "spe_file": "VocabFiles/SPE_ChEMBL.txt",
+            "vocab_file": "VocabFiles/vocab_spe.txt"
+        }
+    },
+
+    "architecture": {
+        "embedding": {
+            "embed_dim": 128 
+        },
+        "transformer_block": {
+            "num_blocks": 5,
+            "activation": "selu",
+            "ff_dim": 128,
+            "num_heads": 21,
+            "dr1": 0.12717945391278226,
+            "dr2": 0.12717945391278226,
+            "drop_mha": true
+        },
+        "regressor_head": {
+            "activation": "selu",
+            "dr": 0.04990303516069576
+        }
+    },
+    
+    "callbacks": {
+        "checkpt_file": "smile_regress.autosave.model.h5",
+        "log_csv": "smile_regress.training.log",
+        "patience_red_lr": 20,
+        "patience_early_stop": 100
+    }
+
+}
diff --git a/Pilot1/ST1/polaris_sub_smiles_regress_transformer_spe.sh b/Pilot1/ST1/polaris_sub_smiles_regress_transformer_spe.sh
new file mode 100755
index 00000000..4dc1990b
--- /dev/null
+++ b/Pilot1/ST1/polaris_sub_smiles_regress_transformer_spe.sh
@@ -0,0 +1,27 @@
+#!/bin/bash
+#PBS -N st_spe
+#PBS -l select=4
+#PBS -l walltime=12:00:00
+#PBS -q preemptable
+#PBS -l filesystems=grand
+#PBS -A datascience
+#PBS -o logs/
+#PBS -e logs/
+#PBS -m abe
+#PBS -M avasan@anl.gov
+
+module load conda/2022-09-08
+conda activate
+
+cd /grand/datascience/avasan/ST_Benchmarks/Test_Tokenizers/SMILESPair_Encoder_continue 
+
+NP=16
+PPN=4
+OUT=logfile.log
+let NDEPTH=64/$NP
+let NTHREADS=$NDEPTH
+
+TF_GPU_ALLOCATOR=cuda_malloc_async
+export TF_FORCE_GPU_ALLOW_GROWTH=true
+
+mpiexec --np 16 -ppn 4 --cpu-bind verbose,list:0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16 -env NCCL_COLLNET_ENABLE=1 -env NCCL_NET_GDR_LEVEL=PHB python smiles_regress_transformer_run.py > $OUT
diff --git a/Pilot1/ST1/smiles_pair_encoders_functions.py b/Pilot1/ST1/smiles_pair_encoders_functions.py
new file mode 100644
index 00000000..15a8c6a2
--- /dev/null
+++ b/Pilot1/ST1/smiles_pair_encoders_functions.py
@@ -0,0 +1,420 @@
+# Tokenizaion classes for huggingface interface
+# reference: https://github.com/huggingface/transformers/blob/master/src/transformers/tokenization_bert.py
+# reference https://github.com/rxn4chemistry/rxnmapper
+
+import collections
+import logging
+import os
+import re
+import codecs
+import unicodedata
+from typing import List, Optional
+from transformers import PreTrainedTokenizer
+from SmilesPE.tokenizer import SPE_Tokenizer
+
+def load_vocab(vocab_file):
+    """Loads a vocabulary file into a dictionary."""
+    vocab = collections.OrderedDict()
+    with open(vocab_file, "r", encoding="utf-8") as reader:
+        tokens = reader.readlines()
+    for index, token in enumerate(tokens):
+        token = token.rstrip("\n")
+        vocab[token] = index
+    return vocab
+
+class Atomwise_Tokenizer(object):
+    """Run atom-level SMILES tokenization"""
+
+    def __init__(self):
+        """ Constructs a atom-level Tokenizer.
+        """
+        self.regex_pattern = r"(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=|#|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])"
+        self.regex = re.compile(self.regex_pattern)
+
+    def tokenize(self, text):
+        """ Basic Tokenization of a SMILES.
+        """
+        tokens = [token for token in self.regex.findall(text)]
+        return tokens
+    
+class SMILES_SPE_Tokenizer(PreTrainedTokenizer):
+    r"""
+    Constructs a SMILES tokenizer. Based on SMILES Pair Encoding (https://github.com/XinhaoLi74/SmilesPE).
+    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the methods. Users
+    should refer to the superclass for more information regarding methods.
+    Args:
+        vocab_file (:obj:`string`):
+            File containing the vocabulary.
+        spe_file (:obj:`string`):
+            File containing the trained SMILES Pair Encoding vocabulary.
+        unk_token (:obj:`string`, `optional`, defaults to "[UNK]"):
+            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
+            token instead.
+        sep_token (:obj:`string`, `optional`, defaults to "[SEP]"):
+            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences
+            for sequence classification or for a text and a question for question answering.
+            It is also used as the last token of a sequence built with special tokens.
+        pad_token (:obj:`string`, `optional`, defaults to "[PAD]"):
+            The token used for padding, for example when batching sequences of different lengths.
+        cls_token (:obj:`string`, `optional`, defaults to "[CLS]"):
+            The classifier token which is used when doing sequence classification (classification of the whole
+            sequence instead of per-token classification). It is the first token of the sequence when built with
+            special tokens.
+        mask_token (:obj:`string`, `optional`, defaults to "[MASK]"):
+            The token used for masking values. This is the token used when training this model with masked language
+            modeling. This is the token which the model will try to predict.
+    """
+
+    def __init__(
+        self,
+        vocab_file,
+        spe_file,
+        unk_token="[UNK]",
+        sep_token="[SEP]",
+        pad_token="[PAD]",
+        cls_token="[CLS]",
+        mask_token="[MASK]",
+        **kwargs
+    ):
+        super().__init__(
+            unk_token=unk_token,
+            sep_token=sep_token,
+            pad_token=pad_token,
+            cls_token=cls_token,
+            mask_token=mask_token,
+            **kwargs,
+        )
+
+        if not os.path.isfile(vocab_file):
+            raise ValueError(
+                "Can't find a vocabulary file at path '{}'.".format(vocab_file)
+            )
+        if not os.path.isfile(spe_file):
+            raise ValueError(
+                "Can't find a SPE vocabulary file at path '{}'.".format(spe_file)
+            )
+        self.vocab = load_vocab(vocab_file)
+        self.spe_vocab = codecs.open(spe_file)
+        self.ids_to_tokens = collections.OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
+        self.spe_tokenizer = SPE_Tokenizer(self.spe_vocab)
+
+    @property
+    def vocab_size(self):
+        return len(self.vocab)
+
+    def get_vocab(self):
+        return dict(self.vocab, **self.added_tokens_encoder)
+
+    def _tokenize(self, text):
+        return self.spe_tokenizer.tokenize(text).split(' ')
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.vocab.get(token, self.vocab.get(self.unk_token))
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.ids_to_tokens.get(index, self.unk_token)
+
+    def convert_tokens_to_string(self, tokens):
+        """ Converts a sequence of tokens (string) in a single string. """
+        out_string = " ".join(tokens).replace(" ##", "").strip()
+        return out_string
+
+    def build_inputs_with_special_tokens(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks
+        by concatenating and adding special tokens.
+        A BERT sequence has the following format:
+        - single sequence: ``[CLS] X [SEP]``
+        - pair of sequences: ``[CLS] A [SEP] B [SEP]``
+        Args:
+            token_ids_0 (:obj:`List[int]`):
+                List of IDs to which the special tokens will be added
+            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            :obj:`List[int]`: list of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
+        """
+        if token_ids_1 is None:
+            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
+        cls = [self.cls_token_id]
+        sep = [self.sep_token_id]
+        return cls + token_ids_0 + sep + token_ids_1 + sep
+
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer ``prepare_for_model`` method.
+        Args:
+            token_ids_0 (:obj:`List[int]`):
+                List of ids.
+            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
+                Set to True if the token list is already formatted with special tokens for the model
+        Returns:
+            :obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+
+        if already_has_special_tokens:
+            if token_ids_1 is not None:
+                raise ValueError(
+                    "You should not supply a second sequence if the provided sequence of "
+                    "ids is already formated with special tokens for the model."
+                )
+            return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0))
+
+        if token_ids_1 is not None:
+            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1]
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
+        A BERT sequence pair mask has the following format:
+        ::
+            0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
+            | first sequence    | second sequence |
+        if token_ids_1 is None, only returns the first portion of the mask (0's).
+        Args:
+            token_ids_0 (:obj:`List[int]`):
+                List of ids.
+            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            :obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given
+            sequence(s).
+        """
+        sep = [self.sep_token_id]
+        cls = [self.cls_token_id]
+        if token_ids_1 is None:
+            return len(cls + token_ids_0 + sep) * [0]
+        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
+
+    def save_vocabulary(self, vocab_path):
+        """
+        Save the sentencepiece vocabulary (copy original file) and special tokens file to a directory.
+        Args:
+            vocab_path (:obj:`str`):
+                The directory in which to save the vocabulary.
+        Returns:
+            :obj:`Tuple(str)`: Paths to the files saved.
+        """
+        index = 0
+        if os.path.isdir(vocab_path):
+            vocab_file = os.path.join(vocab_path, VOCAB_FILES_NAMES["vocab_file"])
+        else:
+            vocab_file = vocab_path
+        with open(vocab_file, "w", encoding="utf-8") as writer:
+            for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
+                if index != token_index:
+                    logger.warning(
+                        "Saving vocabulary to {}: vocabulary indices are not consecutive."
+                        " Please check that the vocabulary is not corrupted!".format(vocab_file)
+                    )
+                    index = token_index
+                writer.write(token + "\n")
+                index += 1
+        return (vocab_file,)
+
+class Atomwise_Tokenizer(object):
+    """Run atom-level SMILES tokenization"""
+
+    def __init__(self):
+        """ Constructs a atom-level Tokenizer.
+        """
+        self.regex_pattern = r"(\[[^\]]+]|Br?|Cl?|N|O|S|P|F|I|b|c|n|o|s|p|\(|\)|\.|=|#|-|\+|\\|\/|:|~|@|\?|>>?|\*|\$|\%[0-9]{2}|[0-9])"
+        self.regex = re.compile(self.regex_pattern)
+
+    def tokenize(self, text):
+        """ Basic Tokenization of a SMILES.
+        """
+        tokens = [token for token in self.regex.findall(text)]
+        return tokens
+
+class SMILES_Atomwise_Tokenizer(PreTrainedTokenizer):
+    r"""
+    Constructs a SMILES tokenizer. Based on SMILES Pair Encoding (https://github.com/XinhaoLi74/SmilesPE).
+    This tokenizer inherits from :class:`~transformers.PreTrainedTokenizer` which contains most of the methods. Users
+    should refer to the superclass for more information regarding methods.
+    Args:
+        vocab_file (:obj:`string`):
+            File containing the vocabulary.
+        unk_token (:obj:`string`, `optional`, defaults to "[UNK]"):
+            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
+            token instead.
+        sep_token (:obj:`string`, `optional`, defaults to "[SEP]"):
+            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences
+            for sequence classification or for a text and a question for question answering.
+            It is also used as the last token of a sequence built with special tokens.
+        pad_token (:obj:`string`, `optional`, defaults to "[PAD]"):
+            The token used for padding, for example when batching sequences of different lengths.
+        cls_token (:obj:`string`, `optional`, defaults to "[CLS]"):
+            The classifier token which is used when doing sequence classification (classification of the whole
+            sequence instead of per-token classification). It is the first token of the sequence when built with
+            special tokens.
+        mask_token (:obj:`string`, `optional`, defaults to "[MASK]"):
+            The token used for masking values. This is the token used when training this model with masked language
+            modeling. This is the token which the model will try to predict.
+    """
+
+    def __init__(
+        self,
+        vocab_file,
+        unk_token="[UNK]",
+        sep_token="[SEP]",
+        pad_token="[PAD]",
+        cls_token="[CLS]",
+        mask_token="[MASK]",
+        **kwargs
+    ):
+        super().__init__(
+            unk_token=unk_token,
+            sep_token=sep_token,
+            pad_token=pad_token,
+            cls_token=cls_token,
+            mask_token=mask_token,
+            **kwargs,
+        )
+
+        if not os.path.isfile(vocab_file):
+            raise ValueError(
+                "Can't find a vocabulary file at path '{}'.".format(vocab_file)
+            )
+        self.vocab = load_vocab(vocab_file)
+        self.ids_to_tokens = collections.OrderedDict([(ids, tok) for tok, ids in self.vocab.items()])
+        self.tokenizer = Atomwise_Tokenizer()
+
+    @property
+    def vocab_size(self):
+        return len(self.vocab)
+
+    def get_vocab(self):
+        return dict(self.vocab, **self.added_tokens_encoder)
+
+    def _tokenize(self, text):
+        return self.tokenizer.tokenize(text)
+
+    def _convert_token_to_id(self, token):
+        """ Converts a token (str) in an id using the vocab. """
+        return self.vocab.get(token, self.vocab.get(self.unk_token))
+
+    def _convert_id_to_token(self, index):
+        """Converts an index (integer) in a token (str) using the vocab."""
+        return self.ids_to_tokens.get(index, self.unk_token)
+
+    def convert_tokens_to_string(self, tokens):
+        """ Converts a sequence of tokens (string) in a single string. """
+        out_string = " ".join(tokens).replace(" ##", "").strip()
+        return out_string
+
+    def build_inputs_with_special_tokens(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Build model inputs from a sequence or a pair of sequence for sequence classification tasks
+        by concatenating and adding special tokens.
+        A BERT sequence has the following format:
+        - single sequence: ``[CLS] X [SEP]``
+        - pair of sequences: ``[CLS] A [SEP] B [SEP]``
+        Args:
+            token_ids_0 (:obj:`List[int]`):
+                List of IDs to which the special tokens will be added
+            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            :obj:`List[int]`: list of `input IDs <../glossary.html#input-ids>`__ with the appropriate special tokens.
+        """
+        if token_ids_1 is None:
+            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
+        cls = [self.cls_token_id]
+        sep = [self.sep_token_id]
+        return cls + token_ids_0 + sep + token_ids_1 + sep
+
+    def get_special_tokens_mask(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
+    ) -> List[int]:
+        """
+        Retrieves sequence ids from a token list that has no special tokens added. This method is called when adding
+        special tokens using the tokenizer ``prepare_for_model`` method.
+        Args:
+            token_ids_0 (:obj:`List[int]`):
+                List of ids.
+            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+                Optional second list of IDs for sequence pairs.
+            already_has_special_tokens (:obj:`bool`, `optional`, defaults to :obj:`False`):
+                Set to True if the token list is already formatted with special tokens for the model
+        Returns:
+            :obj:`List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
+        """
+
+        if already_has_special_tokens:
+            if token_ids_1 is not None:
+                raise ValueError(
+                    "You should not supply a second sequence if the provided sequence of "
+                    "ids is already formated with special tokens for the model."
+                )
+            return list(map(lambda x: 1 if x in [self.sep_token_id, self.cls_token_id] else 0, token_ids_0))
+
+        if token_ids_1 is not None:
+            return [1] + ([0] * len(token_ids_0)) + [1] + ([0] * len(token_ids_1)) + [1]
+        return [1] + ([0] * len(token_ids_0)) + [1]
+
+    def create_token_type_ids_from_sequences(
+        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
+    ) -> List[int]:
+        """
+        Creates a mask from the two sequences passed to be used in a sequence-pair classification task.
+        A BERT sequence pair mask has the following format:
+        ::
+            0 0 0 0 0 0 0 0 0 0 0 1 1 1 1 1 1 1 1 1
+            | first sequence    | second sequence |
+        if token_ids_1 is None, only returns the first portion of the mask (0's).
+        Args:
+            token_ids_0 (:obj:`List[int]`):
+                List of ids.
+            token_ids_1 (:obj:`List[int]`, `optional`, defaults to :obj:`None`):
+                Optional second list of IDs for sequence pairs.
+        Returns:
+            :obj:`List[int]`: List of `token type IDs <../glossary.html#token-type-ids>`_ according to the given
+            sequence(s).
+        """
+        sep = [self.sep_token_id]
+        cls = [self.cls_token_id]
+        if token_ids_1 is None:
+            return len(cls + token_ids_0 + sep) * [0]
+        return len(cls + token_ids_0 + sep) * [0] + len(token_ids_1 + sep) * [1]
+
+    def save_vocabulary(self, vocab_path):
+        """
+        Save the sentencepiece vocabulary (copy original file) and special tokens file to a directory.
+        Args:
+            vocab_path (:obj:`str`):
+                The directory in which to save the vocabulary.
+        Returns:
+            :obj:`Tuple(str)`: Paths to the files saved.
+        """
+        index = 0
+        if os.path.isdir(vocab_path):
+            vocab_file = os.path.join(vocab_path, VOCAB_FILES_NAMES["vocab_file"])
+        else:
+            vocab_file = vocab_path
+        with open(vocab_file, "w", encoding="utf-8") as writer:
+            for token, token_index in sorted(self.vocab.items(), key=lambda kv: kv[1]):
+                if index != token_index:
+                    logger.warning(
+                        "Saving vocabulary to {}: vocabulary indices are not consecutive."
+                        " Please check that the vocabulary is not corrupted!".format(vocab_file)
+                    )
+                    index = token_index
+                writer.write(token + "\n")
+                index += 1
+        return (vocab_file,)
+
diff --git a/Pilot1/ST1/smiles_regress_transformer_spe_funcs.py b/Pilot1/ST1/smiles_regress_transformer_spe_funcs.py
new file mode 100644
index 00000000..1082bede
--- /dev/null
+++ b/Pilot1/ST1/smiles_regress_transformer_spe_funcs.py
@@ -0,0 +1,768 @@
+############# Module Loading ##############
+
+import argparse
+import os
+import numpy as np
+import matplotlib
+import pandas as pd
+import json
+from functools import partial
+
+matplotlib.use("Agg")
+
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras import backend as K
+from tensorflow.keras import layers
+from tensorflow.keras.callbacks import (
+    CSVLogger,
+    EarlyStopping,
+    ModelCheckpoint,
+    ReduceLROnPlateau,
+)
+import codecs
+from SmilesPE.tokenizer import *
+#from SmilesPE.spe2vec import *
+from smiles_pair_encoders_functions import *
+from tensorflow.keras.optimizers import Adam
+from tensorflow.keras.preprocessing import sequence, text
+import horovod.keras as hvd ### importing horovod to use data parallelization in another step
+from clr_callback import *
+import deephyper
+from deephyper.problem import HpProblem
+from tensorflow.python.client import device_lib
+import ray
+from deephyper.evaluator import Evaluator
+from deephyper.evaluator.callback import TqdmCallback
+from deephyper.search.hps import CBO
+from itertools import chain, repeat, islice
+
+def pad_infinite(iterable, padding=None):
+   return chain(iterable, repeat(padding))
+
+def pad(iterable, size, padding=None):
+   return islice(pad_infinite(iterable, padding), size)
+
+
+def ParamsJson(json_file):
+    with open(json_file) as f:
+       params = json.load(f)
+    return params
+
+
+def ArgParsing():
+    file_path = os.path.dirname(os.path.realpath(__file__))
+    # psr and args take input outside of the script and assign:
+    # (1) file paths for data_path_train and data_path_vali
+    # (2) number of training epochs
+
+    psr = argparse.ArgumentParser(description="input csv file")
+    psr.add_argument("--in_train", default="in_train")
+    psr.add_argument("--in_vali", default="in_vali")
+    psr.add_argument("--ep", type=int, default=400)
+    psr.add_argument("--num_heads", type=int, default=16)
+    psr.add_argument("--DR_TB", type=float, default=0.1)
+    psr.add_argument("--DR_ff", type=float, default=0.1)
+    psr.add_argument("--activation", default="activation")
+    psr.add_argument("--drop_post_MHA", type=bool, default=True)
+    psr.add_argument("--lr", type=float, default=1e-5)
+    psr.add_argument("--loss_fn", default="mean_squared_error")
+    psr.add_argument("--hvd_switch", type=bool, default=True)
+    
+    args = vars(psr.parse_args()) # returns dictionary mapping of an object
+    
+    ######## Set  hyperparameters ########
+    data_path_train = args["in_train"]
+    data_path_vali = args["in_vali"]
+
+    EPOCH = args["ep"]
+    num_heads = args["num_heads"]
+    DR_TB = args["DR_TB"]
+    DR_ff = args["DR_ff"]
+    activation = args["activation"]
+    dropout1 = args["drop_post_MHA"]
+    lr = args["lr"]
+    loss_fn = args["loss_fn"]
+    hvd_switch = args["hvd_switch"]
+
+    return data_path_train, data_path_vali, EPOCH, num_heads, DR_TB, DR_ff, activation, dropout1, lr, loss_fn, hvd_switch
+
+def initialize_hvd():
+    hvd.init() 
+    print("I am rank %d of %d" %(hvd.rank(), hvd.size()))
+    
+    #HVD-2: GPU pinning
+    gpus = tf.config.experimental.list_physical_devices('GPU')
+    # Ping GPU to each9 rank
+    for gpu in gpus:
+    	tf.config.experimental.set_memory_growth(gpu,True)
+    if gpus:
+    	tf.config.experimental.set_visible_devices(gpus[hvd.local_rank()], 'GPU')
+
+    return 
+
+
+def split_data(data_x, data_y):
+    data_x = np.array_split(data_x, hvd.size())[hvd.rank()]
+    data_y = np.array_split(data_y, hvd.size())[hvd.rank()]
+    return (data_x, data_y)
+
+
+#def implement_hvd(x_train, y_train):
+#    x_train = x_train[hvd.rank()]
+#    y_train = y_train[hvd.rank()]
+#    return (x_train, y_train)
+
+# Implement embedding layer
+# Two seperate embedding layers, one for tokens, one for token index (positions).
+
+class TokenAndPositionEmbedding(layers.Layer):
+    def __init__(self, maxlen, vocab_size, embed_dim):
+        super(TokenAndPositionEmbedding, self).__init__()
+        self.token_emb = layers.Embedding(input_dim=vocab_size, output_dim=embed_dim)
+        self.pos_emb = layers.Embedding(input_dim=maxlen, output_dim=embed_dim)
+
+    def call(self, x):
+        maxlen = tf.shape(x)[-1]
+        positions = tf.range(start=0, limit=maxlen, delta=1)
+        positions = self.pos_emb(positions)
+        x = self.token_emb(x)
+        return x + positions
+
+def prep_text(texts, tokenizer, max_sequence_length):
+    # Turns text into into padded sequences.
+    text_sequences = tokenizer.texts_to_sequences(texts) # turns text into tokens
+    return sequence.pad_sequences(text_sequences, maxlen=max_sequence_length) # pad all sequences so they all have same length
+
+
+#def train_val_data(data_path_train, data_path_vali, hvd_switch, vocab_size, maxlen):
+
+def preprocess_smiles_pair_encoding(data, maxlen, vocab_file, spe_file):
+    # some default tokens from huggingface
+    default_toks = ['[PAD]', 
+                    '[unused1]', '[unused2]', '[unused3]', '[unused4]','[unused5]', '[unused6]', '[unused7]', '[unused8]', '[unused9]', '[unused10]', 
+                    '[UNK]', '[CLS]', '[SEP]', '[MASK]']
+    
+    
+    # atom-level tokens used for trained the spe vocabulary
+    atom_toks = ['[c-]', '[SeH]', '[N]', '[C@@]', '[Te]', '[OH+]', 'n', '[AsH]', '[B]', 'b', 
+                 '[S@@]', 'o', ')', '[NH+]', '[SH]', 'O', 'I', '[C@]', '-', '[As+]', '[Cl+2]', 
+                 '[P+]', '[o+]', '[C]', '[C@H]', '[CH2]', '\\', 'P', '[O-]', '[NH-]', '[S@@+]', 
+                 '[te]', '[s+]', 's', '[B-]', 'B', 'F', '=', '[te+]', '[H]', '[C@@H]', '[Na]', 
+                 '[Si]', '[CH2-]', '[S@+]', 'C', '[se+]', '[cH-]', '6', 'N', '[IH2]', '[As]', 
+                 '[Si@]', '[BH3-]', '[Se]', 'Br', '[C+]', '[I+3]', '[b-]', '[P@+]', '[SH2]', '[I+2]', 
+                 '%11', '[Ag-3]', '[O]', '9', 'c', '[N-]', '[BH-]', '4', '[N@+]', '[SiH]', '[Cl+3]', '#', 
+                 '(', '[O+]', '[S-]', '[Br+2]', '[nH]', '[N+]', '[n-]', '3', '[Se+]', '[P@@]', '[Zn]', '2', 
+                 '[NH2+]', '%10', '[SiH2]', '[nH+]', '[Si@@]', '[P@@+]', '/', '1', '[c+]', '[S@]', '[S+]', 
+                 '[SH+]', '[B@@-]', '8', '[B@-]', '[C-]', '7', '[P@]', '[se]', 'S', '[n+]', '[PH]', '[I+]', '5', 'p', '[BH2-]', '[N@@+]', '[CH]', 'Cl']
+    
+    tokenizer = SMILES_SPE_Tokenizer(vocab_file=vocab_file, spe_file= spe_file)
+
+    tokenized_data = np.array([list(pad(tokenizer(smi)['input_ids'], maxlen, 0)) for smi in data])
+    
+    return tokenized_data
+
+
+def train_val_data(hyper_params):
+
+    data_path = hyper_params['data_loading']['data_path']
+    rec = hyper_params['data_loading']['rec']
+    pattern = hyper_params['data_loading']['pattern']
+
+    tokenizer_params = hyper_params['tokenization']['tokenizer']
+    #vocabulary = hyper_params['tokenization']['vocab']
+    vocab_size = hyper_params['tokenization']['vocab_size']
+    maxlen = hyper_params['tokenization']['maxlen']
+    hvd_switch = hyper_params['general']['use_hvd']
+
+    data_train = pd.read_csv(f'{data_path}/ml.{rec}.{pattern}.train')
+    data_vali = pd.read_csv(f'{data_path}/ml.{rec}.{pattern}.val')
+    
+    data_train.head()
+    # Dataset has type and smiles as the two fields
+    # reshaping: y formatted as [[y_1],[y_2],...] with floats
+    x_smiles_train = data_train["smiles"]
+    x_smiles_val = data_vali["smiles"]
+    y_train = data_train["type"].values.reshape(-1, 1) * 1.0 
+    y_val = data_vali["type"].values.reshape(-1, 1) * 1.0
+
+    if hvd_switch:
+        x_smiles_train, y_train = split_data(x_smiles_train, y_train)
+    
+    if tokenizer_params['category'] == 'smilespair':
+        spe_file = tokenizer_params['spe_file']
+        vocab_file = tokenizer_params['vocab_file']
+        x_train = preprocess_smiles_pair_encoding(x_smiles_train,
+                                                    maxlen,
+                                                    vocab_file,
+                                                    spe_file)
+
+        x_val = preprocess_smiles_pair_encoding(x_smiles_val,
+                                                    maxlen,
+                                                    vocab_file,
+                                                    spe_file)
+        print(x_train)
+
+    else:
+        tokenizer = text.Tokenizer(num_words=vocab_size)
+        tokenizer.fit_on_texts(data_train["smiles"])
+
+        x_train = prep_text(data_train["smiles"], tokenizer, maxlen)
+        x_val = prep_text(data_vali["smiles"], tokenizer, maxlen)
+    
+    ######## Implement horovod if necessary ########
+    #if hvd_switch:
+    #    x_train, y_train = initialize_hvd(x_train, y_train)
+    #    x_train, y_train = implement_hvd(x_train, y_train)
+
+    return x_train, y_train, x_val, y_val
+
+def get_available_gpus():
+    local_device_protos = device_lib.list_local_devices()
+    n_gpus = len([x.name for x in local_device_protos if x.device_type == "GPU"])
+    print(f"Num of gpus is {n_gpus}")
+    if n_gpus > 1:
+        n_gpus -= 1
+    
+    is_gpu_available = n_gpus > 0
+    
+    #if is_gpu_available:
+        #print(f"{n_gpus} GPU{'s are' if n_gpus > 1 else ' is'} available.")
+    #else:
+        #print("No GPU available")
+
+    return local_device_protos, [x.name for x in local_device_protos if x.device_type == "GPU"], n_gpus, is_gpu_available
+
+
+def r2(y_true, y_pred):
+    SS_res = K.sum(K.square(y_true - y_pred))
+    SS_tot = K.sum(K.square(y_true - K.mean(y_true)))
+    return 1 - SS_res / (SS_tot + K.epsilon())
+
+
+# Implement a Transformer block as a layer
+# embed_dim: number of tokens. This is used for the key_dim for the multi-head attention calculation
+# ff_dim: number of nodes in Dense layer
+# epsilon: needed for numerical stability... not sure what this means to be honest
+
+class TransformerBlock(layers.Layer):
+    # __init__: defining all class variables
+    def __init__(self, embed_dim, num_heads, ff_dim, rate, activation, dropout1):
+        super(TransformerBlock, self).__init__()
+        self.drop_chck = dropout1
+        self.att = layers.MultiHeadAttention(num_heads=num_heads, key_dim=embed_dim)#, activation=activation)
+        self.ffn = keras.Sequential(
+            [
+                layers.Dense(ff_dim, activation=activation),
+                layers.Dense(embed_dim),
+            ]
+        )
+        self.layernorm1 = layers.LayerNormalization(epsilon=1e-6)
+        self.layernorm2 = layers.LayerNormalization(epsilon=1e-6)
+        self.dropout1 = layers.Dropout(rate)
+        self.dropout2 = layers.Dropout(rate)
+    # call: building simple transformer architecture
+    def call(self, inputs, training):
+        attn_output = self.att(inputs, inputs)
+        if self.drop_chck:
+            attn_output = self.dropout1(attn_output, training=training)
+        out1 = self.layernorm1(inputs + attn_output)
+        ffn_output = self.ffn(out1)
+        ffn_output = self.dropout2(ffn_output, training=training)
+
+        return self.layernorm2(out1 + ffn_output)
+
+class ModelArchitecture(layers.Layer):
+    #def __init__(self, vocab_size, maxlen, embed_dim, num_heads, ff_dim, DR_TB, DR_ff, activation, dropout1, lr, loss_fn, hvd_switch):
+    def __init__(self, hyper_params):
+                
+        lr = hyper_params['general']['lr']
+        vocab_size = hyper_params['tokenization']['vocab_size']
+        maxlen = hyper_params['tokenization']['maxlen']
+        hvd_switch = hyper_params['general']['use_hvd']
+
+        arch_params = hyper_params['architecture']
+        embed_dim = arch_params['embedding']['embed_dim']
+        num_heads = arch_params['transformer_block']['num_heads']
+        ff_dim = arch_params['transformer_block']['ff_dim']
+        DR_TB_1 = arch_params['transformer_block']['dr1']
+        DR_TB_2 = arch_params['transformer_block']['dr2']
+        DR_ff = arch_params['regressor_head']['dr']
+        activation_transformer = arch_params['transformer_block']['activation']
+        activation_regressor = arch_params['regressor_head']['activation']
+        dropout1 = arch_params['transformer_block']['drop_mha']
+
+        self.num_tb = arch_params['transformer_block']['num_blocks']
+        self.loss_fn = hyper_params['general']['loss_fn']
+
+        self.inputs = layers.Input(shape=(maxlen,))
+        self.embedding_layer = TokenAndPositionEmbedding(maxlen,
+                                                        vocab_size,
+                                                        embed_dim)
+
+        self.transformer_block = TransformerBlock(embed_dim,
+                                                    num_heads,
+                                                    ff_dim,
+                                                    DR_TB_1,
+                                                    activation_transformer,
+                                                    dropout1)
+
+        self.reshape = layers.Reshape((1, maxlen * embed_dim),
+                                        input_shape=(maxlen, embed_dim,))         
+
+        self.dropout1 = layers.Dropout(DR_ff)
+        self.dropout2 = layers.Dropout(DR_ff)
+        self.dropout3 = layers.Dropout(DR_ff)
+        self.dropout4 = layers.Dropout(DR_ff)
+        self.dropout5 = layers.Dropout(DR_ff)
+
+        self.dense1 = layers.Dense(1024, activation=activation_regressor)
+        self.dense2 = layers.Dense(256, activation=activation_regressor)
+        self.dense3 = layers.Dense(64, activation=activation_regressor)
+        self.dense4 = layers.Dense(16, activation=activation_regressor)
+        self.dense5 = layers.Dense(1, activation=activation_regressor)
+
+        if hvd_switch:
+            lr = lr * hvd.size()
+            self.opt = Adam(learning_rate=lr) 
+            self.opt = hvd.DistributedOptimizer(self.opt)
+        else:
+            self.opt = Adam(learning_rate=lr)
+    
+    def call(self):
+        x = self.embedding_layer(self.inputs)
+        for tb in range(self.num_tb):
+            x = self.transformer_block(x)
+
+        x = self.reshape(x)
+
+        x = self.dropout1(x)
+        x = self.dense1(x)
+
+        x = self.dropout2(x)
+        x = self.dense2(x)
+
+        x = self.dropout3(x)
+        x = self.dense3(x)
+        
+        x = self.dropout4(x)
+        x = self.dense4(x)
+        
+        x = self.dropout5(x)
+        outputs = self.dense5(x)
+        
+        model = keras.Model(inputs=self.inputs, outputs=outputs)
+        model.summary()
+
+        model.compile(
+            loss=self.loss_fn, optimizer=self.opt, metrics=["mae", r2], steps_per_execution=100
+        )
+        
+        return model
+
+class TrainingAndCallbacks:
+    #def __init__(self, hvd_switch, checkpt_file, lr, csv_file, patience_red_lr, patience_early_stop):
+    def __init__(self, hyper_params):
+        self.hvd_switch = hyper_params['general']['use_hvd']
+        checkpt_file = hyper_params['callbacks']['checkpt_file']
+        csv_file = hyper_params['callbacks']['log_csv']
+        patience_red_lr = hyper_params['callbacks']['patience_red_lr']
+        patience_early_stop = hyper_params['callbacks']['patience_early_stop']
+        lr = hyper_params['general']['lr']
+        if self.hvd_switch:
+            lr = lr * hvd.size()
+
+        self.checkpointer = ModelCheckpoint(
+            filepath=checkpt_file,#"smile_regress.autosave.model.h5",
+            verbose=1,
+            save_weights_only=True,
+            save_best_only=True,
+            )
+
+        self.clr = CyclicLR(base_lr = lr, max_lr = 5*lr, step_size=2000.)
+        self.csv_logger = CSVLogger(csv_file)
+
+        self.reduce_lr = ReduceLROnPlateau(
+            monitor="val_loss",
+            factor=0.75,
+            patience=patience_red_lr,
+            verbose=1,
+            mode="auto",
+            epsilon=0.0001,
+            cooldown=3,
+            min_lr=0.000000001,
+            )
+
+        self.early_stop = EarlyStopping(
+            monitor="val_loss",
+            patience=patience_early_stop,
+            verbose=1,
+            mode="auto",
+            )
+
+        if self.hvd_switch:
+        #HVD broadcast initial variables from rank0 to all other processes 
+            self.hvd_broadcast = hvd.callbacks.BroadcastGlobalVariablesCallback(0)
+
+    def callback_defining(self):
+
+        if self.hvd_switch:
+            callbacks = [self.hvd_broadcast, self.reduce_lr, self.clr]
+            if hvd.rank() == 0:
+                callbacks.append(self.csv_logger)
+                callbacks.append(self.early_stop)
+                callbacks.append(self.checkpointer)
+            return callbacks
+        else:
+            return [self.reduce_lr, self.clr, self.csv_logger, self.early_stop, self.checkpointer]
+
+    def training(self, model, x_train, y_train, validation_data, hyper_params):
+        BATCH = hyper_params['general']['batch_size']
+        EPOCH = hyper_params['general']['epochs']
+
+        callbacks = self.callback_defining()
+        history = model.fit(
+            x_train,
+            y_train,
+            batch_size=BATCH,
+            epochs=EPOCH,
+            verbose=1,
+            validation_data=validation_data,
+            callbacks=callbacks,
+        )
+
+        return history
+
+
+
+class RunFnDeepHyper:
+    def __init__(self, x_train, y_train, x_val, y_val): 
+        # Params that are currently static
+        self.vocab_size = 40000
+        self.maxlen = 250
+        self.embed_dim = 128
+        self.ff_dim = 128
+        self.BATCH = 32
+        self.patience_red_lr = 20
+        self.patience_early_stop = 100
+        self.hvd_switch = False
+        self.checkpt_file = 'smile_regress.autosave.model.h5'
+        self.csv_file = 'smile_regress.training.log'
+
+        self.x_train = x_train
+        self.y_train = y_train
+        self.x_val = x_val
+        self.y_val = y_val
+
+    def run(self, config):
+        
+        num_heads = config["num_heads"]
+        DR_TB = config["DR_TB"]
+        DR_ff = config["DR_ff"]
+        activation = config["activation"]
+        dropout1 = config["dropout_aftermulti"]
+        lr = config["lr"]
+        loss_fn = config["loss_fn"]
+        EPOCH = config["epochs"]
+        validation_data = (self.x_val, self.y_val)
+
+        model = ModelArchitecture(self.vocab_size, self.maxlen, self.embed_dim, num_heads, self.ff_dim, DR_TB, DR_ff, activation, dropout1, lr, loss_fn, self.hvd_switch).call()
+
+        history = TrainingAndCallbacks(self.hvd_switch, self.checkpt_file, lr, self.csv_file, self.patience_red_lr, self.patience_early_stop).training( model, self.x_train, self.y_train, validation_data, self.BATCH, EPOCH)
+
+        return history.history["val_accuracy"] [-1]
+
+
+def run(config):
+
+    DATA_PATH='/grand/datascience/avasan/ST_Benchmarks/Data/1M-flatten'
+    
+    TFIL='ml.3CLPro_7BQY_A_1_F.Orderable_zinc_db_enaHLL.sorted.4col.dd.parquet.xform-smiles.csv.reg.train'
+    
+    VFIL='ml.3CLPro_7BQY_A_1_F.Orderable_zinc_db_enaHLL.sorted.4col.dd.parquet.xform-smiles.csv.reg.val'
+    
+    data_path_train = f'{DATA_PATH}/{TFIL}'
+    data_path_vali = f'{DATA_PATH}/{TFIL}'
+    hvd_switch = False
+    BATCH = 32 # batch size used for training
+    vocab_size = 40000
+    maxlen = 250
+    embed_dim = 128   # Embedding size for each token
+    ff_dim = 128   # Hidden layer size in feed forward network inside transformer
+    checkpt_file = "smile_regress.autosave.model.h5"
+    csv_file = "smile_regress.training.log"
+    patience_red_lr = 20
+    patience_early_stop = 100
+    
+    ########Create training and validation data##### 
+    x_train, y_train, x_val, y_val = train_val_data(data_path_train, data_path_vali, hvd_switch, vocab_size, maxlen)
+    num_heads = config["num_heads"]
+    DR_TB = config["DR_TB"]
+    DR_ff = config["DR_ff"]
+    activation = config["activation"]
+    dropout1 = config["dropout_aftermulti"]
+    lr = config["lr"]
+    loss_fn = config["loss_fn"]
+    EPOCH = config["epochs"]
+    validation_data = (x_val, y_val)
+
+    model = ModelArchitecture(vocab_size, maxlen, embed_dim, num_heads, ff_dim, DR_TB, DR_ff, activation, dropout1, lr, loss_fn, hvd_switch).call()
+
+    history = TrainingAndCallbacks(hvd_switch, checkpt_file, lr, csv_file, patience_red_lr, patience_early_stop).training( model, x_train, y_train, validation_data, BATCH, EPOCH)
+
+    return history.history["val_accuracy"] [-1]
+
+
+
+def hyper_param_problem():
+
+    ACTIVATIONS = [
+    "elu", "gelu", "hard_sigmoid", "linear", "relu", "selu",
+    "sigmoid", "softplus", "softsign", "swish", "tanh",
+    ]
+
+    LRS = [1e-6 * i for i in range(0,11)]
+    
+    LOSSFNS = ["mean_squared_error", "mean_absolute_error"]
+
+    problem = HpProblem()
+    problem.add_hyperparameter((12, 32), "num_heads", default_value = 16)
+    problem.add_hyperparameter((0.025, 0.5), "DR_TB", default_value = 0.1)
+    problem.add_hyperparameter((0.025, 0.5), "DR_ff", default_value = 0.1)
+    problem.add_hyperparameter(ACTIVATIONS, "activation", default_value = "elu")
+    problem.add_hyperparameter((1e-7, 1e-5), "lr", default_value = 1e-6)
+    problem.add_hyperparameter(LOSSFNS, "loss_fn", default_value = "mean_squared_error")
+    problem.add_hyperparameter((2,10), "epochs", default_value = 2)
+    problem.add_hyperparameter([True, False], "dropout_aftermulti", default_value = False)
+
+    return problem
+
+
+def default_evaluation(problem, is_gpu_available, n_gpus, run):
+    if is_gpu_available:
+        if not(ray.is_initialized()):
+            ray.init(num_cpus=n_gpus, num_gpus=n_gpus, log_to_driver=False)
+    
+
+        run_default = ray.remote(num_cpus=1, num_gpus=1)(run)
+        objective_default = ray.get(run_default.remote(problem.default_configuration))
+    else:
+        if not(ray.is_initialized()):
+            ray.init(num_cpus=1, log_to_driver=False)
+        run_default = run
+        print(problem.default_configuration)
+        objective_default = run_default(problem.default_configuration)
+    return objective_default
+
+
+def get_evaluator(run_function, is_gpu_available, n_gpus):
+    # Default arguments for Ray: 1 worker and 1 worker per evaluation
+    method_kwargs = {
+        "num_cpus": 1,
+        "num_cpus_per_task": 1,
+        "callbacks": [TqdmCallback()]
+    }
+
+    # If GPU devices are detected then it will create 'n_gpus' workers
+    # and use 1 worker for each evaluation
+    if is_gpu_available:
+        method_kwargs["num_cpus"] = n_gpus
+        method_kwargs["num_gpus"] = n_gpus
+        method_kwargs["num_cpus_per_task"] = 1
+        method_kwargs["num_gpus_per_task"] = 1
+
+    evaluator = Evaluator.create(
+        run_function,
+        method="ray",
+        method_kwargs=method_kwargs
+    )
+    print(f"Created new evaluator with {evaluator.num_workers} worker{'s' if evaluator.num_workers > 1 else ''} and config: {method_kwargs}", )
+
+    return evaluator
+
+
+def build_model_tuner(hp):
+    #units = hp.Int("units", min_value=32, max_value=512, step=32)
+    vocab_size = 40000
+    maxlen = 250
+    embed_dim = 128
+    num_heads = hp.Int("num_heads", min_value=12, max_value=40, step=4)
+    ff_dim = 128
+    DR_TB = hp.Float("DR_TB", min_value=0.025, max_value=0.5, step=0.025)
+    DR_ff = hp.Float("DR_TB", min_value=0.025, max_value=0.5, step=0.025)
+    activation = hp.Choice("activation", ["relu", "elu", "gelu"])
+    #activation="elu"
+    dropout1 = hp.Boolean("dropout_aftermulti")
+    lr = hp.Float("lr", min_value=1e-6, max_value=1e-5, step=1e-6)
+    loss_fn = hp.Choice("loss_fn", ["mean_squared_error", "mean_absolute_error"])
+    # call existing model-building code with the hyperparameter values.
+    model = ModelArchitecture(vocab_size, maxlen, embed_dim, num_heads, ff_dim, DR_TB, DR_ff, activation, dropout1, lr, loss_fn, hvd_switch).call()
+
+    return model
+
+
+#tfm.optimization.lars_optimizer.LARS(
+#    learning_rate = 0.0000025,
+#    momentum = 0.9,
+#    weight_decay_rate = 0.0,
+#    eeta = 0.001,
+#    nesterov = False,
+#    classic_momentum = True,
+#    exclude_from_weight_decay = None,
+#    exclude_from_layer_adaptation = None,
+#    name = 'LARS',
+#    )
+
+def model_architecture(embed_dim, num_heads, ff_dim, DR_TB, DR_ff, activation, dropout1, lr, loss_fn, hvd_switch):
+
+    vocab_size = 40000  #number of possible 'words' in SMILES data
+    maxlen = 250  #length of each SMILE sequence in input
+    inputs = layers.Input(shape=(maxlen,))
+    embedding_layer = TokenAndPositionEmbedding(maxlen, vocab_size, embed_dim)
+    x = embedding_layer(inputs)
+    transformer_block = TransformerBlock(embed_dim, num_heads, ff_dim, DR_TB, activation, dropout1)
+    # Use 4 transformer blocks here
+    x = transformer_block(x)
+    x = transformer_block(x)
+    x = transformer_block(x)
+    x = transformer_block(x)
+    
+    x = layers.Reshape((1, 32000), input_shape=(250, 128,))(
+        x
+    )  # reshaping increases parameters but improves accuracy a lot
+    x = layers.Dropout(DR_ff)(x)
+    x = layers.Dense(1024, activation=activation)(x)
+    x = layers.Dropout(DR_ff)(x)
+    x = layers.Dense(256, activation=activation)(x)
+    x = layers.Dropout(DR_ff)(x)
+    x = layers.Dense(64, activation=activation)(x)
+    x = layers.Dropout(DR_ff)(x)
+    x = layers.Dense(16, activation=activation)(x)
+    x = layers.Dropout(DR_ff)(x)
+    outputs = layers.Dense(1, activation=activation)(x)
+    
+    model = keras.Model(inputs=inputs, outputs=outputs)
+    
+    model.summary()
+
+    # Train and Evaluate
+
+    opt = Adam(learning_rate=lr)
+    
+    #HVD Wrap optimizer in hvd Distributed Optimizer delegates gradient comp to original optimizer, averages gradients, and applies averaged gradients
+    if hvd_switch:
+        opt = hvd.DistributedOptimizer(opt)
+
+    model.compile(
+        loss=loss_fn, optimizer=opt, metrics=["mae", r2]
+    )
+    return model
+
+def callback_setting(hvd_switch, checkpt_file, lr, csv_file, patience_red_lr, patience_early_stop):
+    
+    checkpointer = ModelCheckpoint(
+        filepath=checkpt_file,#"smile_regress.autosave.model.h5",
+        verbose=1,
+        save_weights_only=True,
+        save_best_only=True,
+    )
+    
+    clr = CyclicLR(base_lr = lr, max_lr = 5*lr, step_size=2000.)
+    
+    csv_logger = CSVLogger(csv_file)#"smile_regress.training.log")
+    
+    # learning rate tuning at each epoch
+    # is it possible to do batch size tuning at each epoch as well? 
+    reduce_lr = ReduceLROnPlateau(
+        monitor="val_loss",
+        factor=0.75,
+        patience=patience_red_lr,#20,
+        verbose=1,
+        mode="auto",
+        epsilon=0.0001,
+        cooldown=3,
+        min_lr=0.000000001,
+    )
+
+    early_stop = EarlyStopping(
+        monitor="val_loss",
+        patience=patience_early_stop,#100,
+        verbose=1,
+        mode="auto",
+        )
+
+    if hvd_switch:
+        #HVD broadcast initial variables from rank0 to all other processes 
+        hvd_broadcast = hvd.callbacks.BroadcastGlobalVariablesCallback(0)
+
+        callbacks = [hvd_broadcast,reduce_lr,clr]
+
+        if hvd.rank() == 0:
+            callbacks.append(csv_logger)
+            callbacks.append(early_stop)
+            callbacks.append(checkpointer)
+
+        return callbacks
+
+    else:
+        return [reduce_lr, clr, csv_logger, early_stop, checkpointer]
+
+
+def build_model_DeepHyper(x_train, y_train, x_val, y_val, config, hvd_switch=False, checkpt_file = 'smile_regress.autosave.model.h5', csv_file = 'smile_regress.training.log'):
+    #units = hp.Int("units", min_value=32, max_value=512, step=32)
+    embed_dim = 128
+    ff_dim = 128
+    BATCH = 32
+    patience_red_lr = 20
+    patience_early_stop = 100
+
+    num_heads = config["num_heads"]
+    DR_TB = config["DR_TB"]
+    DR_ff = config["DR_ff"]
+    activation = config["activation"]
+    dropout1 = config["dropout_aftermulti"]
+    lr = config["lr"]
+    loss_fn = config["loss_fn"]
+    EPOCH = config["epochs"]
+
+        # call existing model-building code with the hyperparameter values.
+    model = model_architecture (
+        embed_dim=embed_dim, num_heads=num_heads, ff_dim=ff_dim, DR_TB=DR_TB, DR_ff = DR_ff, activation=activation, dropout1=dropout1, lr=lr, loss_fn=loss_fn
+    )
+
+    callbacks = callback_setting (
+        hvd_switch,
+        checkpt_file,
+        lr,
+        csv_file,
+        patience_red_lr,
+        patience_early_stop
+        )
+    
+    history = model.fit(
+        x_train,
+        y_train,
+        batch_size=BATCH,
+        epochs=EPOCH,
+        verbose=1,
+        validation_data=(x_val, y_val),
+        callbacks=callbacks,
+    )
+
+    return history.history["val_accuracy"] [-1]
+
+
+
+
+#def build_model(num_heads, DR_TB, DR_ff, activation, dropout1, lr, loss_fn, hvd_switch):
+#    #units = hp.Int("units", min_value=32, max_value=512, step=32)
+#    embed_dim = 128
+#    ff_dim = 128
+#    # call existing model-building code with the hyperparameter values.
+#    model = model_architecture (
+#        embed_dim=embed_dim, num_heads=num_heads, ff_dim=ff_dim, DR_TB=DR_TB, DR_ff = DR_ff, activation=activation, dropout1=dropout1, lr=lr, loss_fn=loss_fn, hvd_switch=hvd_switch
+#    )
+#    return model
+
+
+
diff --git a/Pilot1/ST1/smiles_regress_transformer_spe_run.py b/Pilot1/ST1/smiles_regress_transformer_spe_run.py
new file mode 100644
index 00000000..8124de42
--- /dev/null
+++ b/Pilot1/ST1/smiles_regress_transformer_spe_run.py
@@ -0,0 +1,53 @@
+############# Module Loading ##############
+import argparse
+import os
+import numpy as np
+import matplotlib
+import pandas as pd
+matplotlib.use("Agg")
+import tensorflow as tf
+from tensorflow import keras
+from tensorflow.keras import backend as K
+from tensorflow.keras import layers
+from tensorflow.keras.callbacks import (
+    CSVLogger,
+    EarlyStopping,
+    ModelCheckpoint,
+    ReduceLROnPlateau,
+)
+from tensorflow.keras.optimizers import Adam
+from tensorflow.keras.preprocessing import sequence, text
+import horovod.keras as hvd ### importing horovod to use data parallelization in another step
+
+from clr_callback import *
+from smiles_regress_transformer_spe_funcs import *
+from tensorflow.python.client import device_lib
+import json
+
+#######HyperParamSetting#############
+
+json_file = 'config_st_spe_training.json'
+hyper_params = ParamsJson(json_file)
+
+if hyper_params['general']['use_hvd']==True:
+    initialize_hvd()
+
+########Create training and validation data##### 
+x_train, y_train, x_val, y_val = train_val_data(hyper_params)
+
+######## Build model #############
+
+model = ModelArchitecture(hyper_params).call()
+
+####### Set callbacks + train model ##############
+
+train_and_callbacks = TrainingAndCallbacks(hyper_params)
+
+history = train_and_callbacks.training(
+    model,
+    x_train,
+    y_train,
+    (x_val, y_val),
+    hyper_params
+    )
+
diff --git a/Pilot1/ST1/sub_smiles_regress_transformer_spe.sh b/Pilot1/ST1/sub_smiles_regress_transformer_spe.sh
new file mode 100755
index 00000000..4e8035db
--- /dev/null
+++ b/Pilot1/ST1/sub_smiles_regress_transformer_spe.sh
@@ -0,0 +1,16 @@
+
+module load conda/2022-09-08
+conda activate
+
+cd /grand/datascience/avasan/ST_Benchmarks/Test_Tokenizers/SMILESPair_Encoder_Github
+
+NP=16
+PPN=4
+OUT=logfile.log
+let NDEPTH=64/$NP
+let NTHREADS=$NDEPTH
+
+TF_GPU_ALLOCATOR=cuda_malloc_async
+export TF_FORCE_GPU_ALLOW_GROWTH=true
+
+mpiexec --np 16 -ppn 4 --cpu-bind verbose,list:0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16 -env NCCL_COLLNET_ENABLE=1 -env NCCL_NET_GDR_LEVEL=PHB python smiles_regress_transformer_run.py > $OUT