diff --git "a/notebooks/data_curation.ipynb" "b/notebooks/data_curation.ipynb" --- "a/notebooks/data_curation.ipynb" +++ "b/notebooks/data_curation.ipynb" @@ -116,7 +116,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "metadata": {}, "outputs": [ { @@ -147,7 +147,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "metadata": {}, "outputs": [ { @@ -294,7 +294,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 6, "metadata": {}, "outputs": [ { @@ -534,7 +534,7 @@ "[5 rows x 89 columns]" ] }, - "execution_count": 7, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -560,7 +560,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -687,7 +687,7 @@ "[334 rows x 2 columns]" ] }, - "execution_count": 8, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -706,7 +706,7 @@ }, { "cell_type": "code", - "execution_count": 72, + "execution_count": 8, "metadata": {}, "outputs": [ { @@ -932,7 +932,7 @@ "[5 rows x 43 columns]" ] }, - "execution_count": 72, + "execution_count": 8, "metadata": {}, "output_type": "execute_result" } @@ -953,7 +953,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 9, "metadata": {}, "outputs": [ { @@ -1015,7 +1015,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -1028,7 +1028,7 @@ } ], "source": [ - "def is_active(DC50: float, Dmax: float) -> bool:\n", + "def is_active(DC50: float, Dmax: float, oring=False) -> bool:\n", " \"\"\" Check if a PROTAC is active based on DC50 and Dmax.\t\n", " Args:\n", " DC50(float): DC50 in nM\n", @@ -1044,10 +1044,18 @@ " if pd.notnull(Dmax):\n", " if Dmax < 0.8:\n", " return False\n", - " if pd.notnull(pDC50) and pd.notnull(Dmax):\n", - " return True if pDC50 >= 7.0 and Dmax >= 0.8 else False\n", + " if oring:\n", + " if pd.notnull(pDC50):\n", + " return True if pDC50 >= 7.0 else False\n", + " elif pd.notnull(Dmax):\n", + " return True if Dmax >= 0.8 else False\n", + " else:\n", + " return np.nan\n", " else:\n", - " return np.nan\n", + " if pd.notnull(pDC50) and pd.notnull(Dmax):\n", + " return True if pDC50 >= 7.0 and Dmax >= 0.8 else False\n", + " else:\n", + " return np.nan\n", "\n", "\n", "print(is_active(20, 80))\n", @@ -1063,7 +1071,7 @@ }, { "cell_type": "code", - "execution_count": 73, + "execution_count": 11, "metadata": {}, "outputs": [], "source": [ @@ -1086,7 +1094,7 @@ }, { "cell_type": "code", - "execution_count": 74, + "execution_count": 12, "metadata": {}, "outputs": [], "source": [ @@ -1097,7 +1105,7 @@ }, { "cell_type": "code", - "execution_count": 75, + "execution_count": 13, "metadata": {}, "outputs": [ { @@ -1124,7 +1132,7 @@ }, { "cell_type": "code", - "execution_count": 76, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -1154,7 +1162,7 @@ }, { "cell_type": "code", - "execution_count": 77, + "execution_count": 15, "metadata": {}, "outputs": [], "source": [ @@ -1164,7 +1172,7 @@ }, { "cell_type": "code", - "execution_count": 78, + "execution_count": 16, "metadata": {}, "outputs": [ { @@ -1208,13 +1216,13 @@ }, { "cell_type": "code", - "execution_count": 79, + "execution_count": 17, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "734d487c61494c38a8e220984ca1ca25", + "model_id": "270288154fa2473a8a0151a8c4e93ecb", "version_major": 2, "version_minor": 0 }, @@ -1266,7 +1274,7 @@ }, { "cell_type": "code", - "execution_count": 80, + "execution_count": 18, "metadata": {}, "outputs": [ { @@ -1286,7 +1294,7 @@ "Name: Article DOI, Length: 925, dtype: object" ] }, - "execution_count": 80, + "execution_count": 18, "metadata": {}, "output_type": "execute_result" } @@ -1308,7 +1316,7 @@ }, { "cell_type": "code", - "execution_count": 81, + "execution_count": 19, "metadata": {}, "outputs": [ { @@ -1333,7 +1341,7 @@ " 32.0]" ] }, - "execution_count": 81, + "execution_count": 19, "metadata": {}, "output_type": "execute_result" } @@ -1353,13 +1361,13 @@ }, { "cell_type": "code", - "execution_count": 82, + "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "51b9b715dcd74bc58b1de014da1bc342", + "model_id": "8b01d418bb7f433db823484196bd1ac3", "version_major": 2, "version_minor": 0 }, @@ -1373,7 +1381,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "f7d24dde1c76490d8dc4e171ec724d10", + "model_id": "6b19f9aaf2864a8ab7ce0203ff8b6852", "version_major": 2, "version_minor": 0 }, @@ -1407,7 +1415,7 @@ }, { "cell_type": "code", - "execution_count": 83, + "execution_count": 21, "metadata": {}, "outputs": [], "source": [ @@ -1446,7 +1454,7 @@ }, { "cell_type": "code", - "execution_count": 84, + "execution_count": 22, "metadata": {}, "outputs": [], "source": [ @@ -1455,7 +1463,7 @@ }, { "cell_type": "code", - "execution_count": 85, + "execution_count": 23, "metadata": {}, "outputs": [], "source": [ @@ -1496,7 +1504,7 @@ }, { "cell_type": "code", - "execution_count": 86, + "execution_count": 24, "metadata": {}, "outputs": [ { @@ -1535,7 +1543,7 @@ }, { "cell_type": "code", - "execution_count": 87, + "execution_count": 25, "metadata": {}, "outputs": [ { @@ -1735,7 +1743,7 @@ "4888 1.26 " ] }, - "execution_count": 87, + "execution_count": 25, "metadata": {}, "output_type": "execute_result" } @@ -1750,14 +1758,14 @@ }, { "cell_type": "code", - "execution_count": 88, + "execution_count": 26, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Non-assay columns: ['Molecular Weight', 'Target', 'Topological Polar Surface Area', 'InChI', 'E3 Ligase', 'Hydrogen Bond Donor Count', 'Smiles', 'Heavy Atom Count', 'InChI Key', 'Ring Count', 'Uniprot', 'Molecular Formula', 'Article DOI', 'Hydrogen Bond Acceptor Count', 'Compound ID', 'Rotatable Bond Count', 'Name', 'Exact Mass', 'XLogP3', 'PDB']\n", + "Non-assay columns: ['E3 Ligase', 'Heavy Atom Count', 'Hydrogen Bond Acceptor Count', 'Compound ID', 'Molecular Formula', 'Rotatable Bond Count', 'Molecular Weight', 'InChI Key', 'Target', 'XLogP3', 'Smiles', 'Article DOI', 'Ring Count', 'Name', 'Hydrogen Bond Donor Count', 'Uniprot', 'PDB', 'InChI', 'Topological Polar Surface Area', 'Exact Mass']\n", "Assay columns: ['DC50 (nM)', 'Dmax (%)', 'Assay (DC50/Dmax)', 'Percent degradation (%)', 'Assay (Percent degradation)', 'IC50 (nM, Protac to Target)', 'Assay (Protac to Target, IC50)', 'EC50 (nM, Protac to Target)', 'Assay (Protac to Target, EC50)', 'Kd (nM, Protac to Target)', 'Assay (Protac to Target, Kd)', 'Ki (nM, Protac to Target)', 'Assay (Protac to Target, Ki)', 'delta G (kcal/mol, Protac to Target)', 'delta H (kcal/mol, Protac to Target)', '-T*delta S (kcal/mol, Protac to Target)', 'Assay (Protac to Target, G/H/-TS)', 'kon (1/Ms, Protac to Target)', 'koff (1/s, Protac to Target)', 't1/2 (s, Protac to Target)', 'Assay (Protac to Target, kon/koff/t1/2)', 'IC50 (nM, Protac to E3)', 'Assay (Protac to E3, IC50)', 'EC50 (nM, Protac to E3)', 'Assay (Protac to E3, EC50)', 'Kd (nM, Protac to E3)', 'Assay (Protac to E3, Kd)', 'Ki (nM, Protac to E3)', 'Assay (Protac to E3, Ki)', 'delta G (kcal/mol, Protac to E3)', 'delta H (kcal/mol, Protac to E3)', '-T*delta S (kcal/mol, Protac to E3)', 'Assay (Protac to E3, G/H/-TS)', 'kon (1/Ms, Protac to E3)', 'koff (1/s, Protac to E3)', 't1/2 (s, Protac to E3)', 'Assay (Protac to E3, kon/koff/t1/2)', 'IC50 (nM, Ternary complex)', 'Assay (Ternary complex, IC50)', 'EC50 (nM, Ternary complex)', 'Assay (Ternary complex, EC50)', 'Kd (nM, Ternary complex)', 'Assay (Ternary complex, Kd)', 'Ki (nM, Ternary complex)', 'Assay (Ternary complex, Ki)', 'delta G (kcal/mol, Ternary complex)', 'delta H (kcal/mol, Ternary complex)', '-T*delta S (kcal/mol, Ternary complex)', 'Assay (Ternary complex, G/H/-TS)', 'kon (1/Ms, Ternary complex)', 'koff (1/s, Ternary complex)', 't1/2 (s, Ternary complex)', 'Assay (Ternary complex, kon/koff/t1/2)', 'IC50 (nM, Cellular activities)', 'Assay (Cellular activities, IC50)', 'EC50 (nM, Cellular activities)', 'Assay (Cellular activities, EC50)', 'GI50 (nM, Cellular activities)', 'Assay (Cellular activities, GI50)', 'ED50 (nM, Cellular activities)', 'Assay (Cellular activities, ED50)', 'GR50 (nM, Cellular activities)', 'Assay (Cellular activities, GR50)', 'PAMPA Papp (nm/s, Permeability)', 'Assay (Permeability, PAMPA Papp)', 'Caco-2 A2B Papp (nm/s, Permeability)', 'Assay (Permeability, Caco-2 A2B Papp)', 'Caco-2 B2A Papp (nm/s, Permeability)', 'Assay (Permeability, Caco-2 B2A Papp)']\n" ] } @@ -1803,7 +1811,7 @@ }, { "cell_type": "code", - "execution_count": 89, + "execution_count": 27, "metadata": {}, "outputs": [ { @@ -4043,7 +4051,7 @@ }, { "cell_type": "code", - "execution_count": 90, + "execution_count": 28, "metadata": {}, "outputs": [ { @@ -4202,7 +4210,7 @@ }, { "cell_type": "code", - "execution_count": 91, + "execution_count": 29, "metadata": {}, "outputs": [ { @@ -4211,7 +4219,7 @@ "1019" ] }, - "execution_count": 91, + "execution_count": 29, "metadata": {}, "output_type": "execute_result" } @@ -4230,13 +4238,13 @@ }, { "cell_type": "code", - "execution_count": 92, + "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "f9fda7549fc04c5fb6effc975c8ad270", + "model_id": "8dc21c335d764482b9c202ad0ddce4c5", "version_major": 2, "version_minor": 0 }, @@ -4510,7 +4518,7 @@ }, { "cell_type": "code", - "execution_count": 93, + "execution_count": 31, "metadata": {}, "outputs": [ { @@ -4534,6 +4542,7 @@ " \n", " \n", " \n", + " Assay (DC50/Dmax)\n", " Target\n", " Target (Parsed)\n", " \n", @@ -4541,176 +4550,301 @@ " \n", " \n", " 2\n", + " Degradation of HiBiT-BRD9 in HEK293 cells afte...\n", " BRD9\n", " HiBiT-BRD9\n", " \n", " \n", " 6\n", + " Degradation of HiBiT-BRD7 in HEK293 cells afte...\n", " BRD7\n", " HiBiT-BRD7\n", " \n", " \n", " 77\n", + " Degradation of NPM-ALK/EML4-ALK in SU-DHL-1/NC...\n", " ALK\n", " NPM-ALK\n", " \n", " \n", " 78\n", + " Degradation of NPM-ALK/EML4-ALK in SU-DHL-1/NC...\n", " ALK\n", " EML4-ALK\n", " \n", " \n", " 102\n", + " Degradation of Fak in PC3 cells after 24 h tre...\n", " FAK\n", " Fak\n", " \n", " \n", " 111\n", + " Degradation of WT/Exon 20 Ins EGFR in OVCAR8/H...\n", " EGFR\n", " WT\n", " \n", " \n", " 112\n", + " Degradation of WT/Exon 20 Ins EGFR in OVCAR8/H...\n", " EGFR\n", " Exon 20 Ins EGFR\n", " \n", " \n", " 113\n", + " Degradation of Exon 19 del/L858R EGFR in HCC82...\n", " EGFR\n", " Exon 19 del\n", " \n", " \n", " 114\n", + " Degradation of Exon 19 del/L858R EGFR in HCC82...\n", " EGFR\n", " L858R EGFR\n", " \n", " \n", " 115\n", + " Degradation of L858R, T790M EGFR in H1975 cell...\n", " EGFR\n", " L858R, T790M EGFR\n", " \n", " \n", " 122\n", + " Degradation of C481S BTK in XLA cells after 24...\n", " BTK C481S\n", " C481S BTK\n", " \n", " \n", " 141\n", + " Degradation of BRD4 short/long in HeLa cells a...\n", " BRD4\n", " BRD4 short\n", " \n", " \n", " 142\n", + " Degradation of BRD4 short/long in HeLa cells a...\n", " BRD4\n", " BRD4 long\n", " \n", " \n", " 144\n", + " Degradation of BRD4 BD1/2 assessed by EGFP/mCh...\n", " BRD4\n", " BRD4 BD1\n", " \n", " \n", " 145\n", + " Degradation of BRD4 BD1/2 assessed by EGFP/mCh...\n", " BRD4\n", " BRD4 BD2\n", " \n", " \n", " 208\n", + " Degradation of total STAT3 and p-STAT3Y705 pro...\n", + " STAT3\n", + " p-STAT3Y705\n", + " \n", + " \n", + " 212\n", + " Degradation of total STAT3 and p-STAT3Y705 pro...\n", " STAT3\n", " p-STAT3Y705\n", " \n", " \n", " 262\n", + " Degradation of G1202R ALK in 293T cells\n", " ALK G1202R\n", " G1202R ALK\n", " \n", " \n", " 356\n", + " Degradation of SMARCA2 in MV-4-11 cells after ...\n", " SMARCA4\n", " SMARCA2\n", " \n", " \n", " 365\n", + " Degradation of ERalpha in MCF-7/T47D cells aft...\n", + " ER\n", + " ERalpha\n", + " \n", + " \n", + " 367\n", + " Degradation of ERalpha in MCF-7 cells after 6 ...\n", + " ER\n", + " ERalpha\n", + " \n", + " \n", + " 368\n", + " Degradation of ERalpha in MCF-7 cells after 6h...\n", " ER\n", " ERalpha\n", " \n", " \n", " 387\n", + " Degradation of pVHL30 in HeLa cells after 24 h...\n", " VHL\n", " pVHL30\n", " \n", " \n", " 388\n", + " Degradation of TrkC in Hs578t cells after 24 h...\n", " TRKC\n", " TrkC\n", " \n", " \n", " 389\n", + " Degradation of HADC6 in MM.1S cells after 24 h...\n", " HDAC6\n", " HADC6\n", " \n", " \n", + " 408\n", + " Degradation of ERalpha in MCF-7 cells after 4/...\n", + " ER\n", + " ERalpha\n", + " \n", + " \n", + " 411\n", + " Degradation of ERalpha in MCF-7 cells after 4h...\n", + " ER\n", + " ERalpha\n", + " \n", + " \n", + " 412\n", + " Degradation of ERalpha in MCF-7 cells after 4/...\n", + " ER\n", + " ERalpha\n", + " \n", + " \n", " 495\n", + " Degradation of total tau/P-tau in A152T neuron...\n", " Tau\n", " tau/P-tau\n", " \n", " \n", + " 523\n", + " Degradation of ERalpha in MCF7 cells\n", + " ER\n", + " ERalpha\n", + " \n", + " \n", + " 536\n", + " Degradation of Fak in primary Sertoli/germ cel...\n", + " FAK\n", + " Fak\n", + " \n", + " \n", + " 620\n", + " Degradation of Fak in HLE/HuH-7/SNU-423 cells ...\n", + " FAK\n", + " Fak\n", + " \n", + " \n", + " 623\n", + " Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel...\n", + " FAK\n", + " Fak\n", + " \n", + " \n", + " 626\n", + " Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ...\n", + " FAK\n", + " Fak\n", + " \n", + " \n", + " 629\n", + " Degradation of Fak in HLF/SNU-398/HUCCT1 cells...\n", + " FAK\n", + " Fak\n", + " \n", + " \n", " 663\n", + " Degradation of TPM3-TRKA/TRKA in KM12/HEL cell...\n", " TRKA\n", " TPM3-TRKA\n", " \n", " \n", " 718\n", + " Degradation of EGFR del19 in HCC827 cells afte...\n", " EGFR e19d\n", " EGFR del19\n", " \n", " \n", + " 769\n", + " Degradation of ERalpha in MCF-7 cells\n", + " ER\n", + " ERalpha\n", + " \n", + " \n", " 806\n", + " Degradation of WDR5-HiBiT in MV4-11 (WDR5-HiBi...\n", " WDR5\n", " WDR5-HiBiT\n", " \n", " \n", + " 824\n", + " Degradation of BRD4 long in HEK293 cells after...\n", + " BRD4\n", + " BRD4 long\n", + " \n", + " \n", " 892\n", + " Degradation of PYK2 in SR cells after 24 h tre...\n", " PTK2B\n", " PYK2\n", " \n", " \n", " 896\n", + " Degradation of RSK1 in NCI-H2228/A549/Calu-1 c...\n", " RPS6KA1\n", " RSK1\n", " \n", " \n", + " 899\n", + " Degradation of EGFR del19 in HCC-827 cells aft...\n", + " EGFR e19d\n", + " EGFR del19\n", + " \n", + " \n", " 1014\n", + " Degradation of total AKT in BT474 cells after ...\n", " AKT2\n", " AKT\n", " \n", " \n", " 1015\n", + " Degradation of total AKT in BT474 cells after ...\n", " AKT1\n", " AKT\n", " \n", " \n", " 1016\n", + " Degradation of total AKT in BT474 cells after ...\n", " AKT3\n", " AKT\n", " \n", " \n", " 1058\n", + " Degradation of GSK3B in SH-SY5Y cells after 24...\n", " GSK-3beta\n", " GSK3B\n", " \n", " \n", " 1145\n", + " Degradation of SMARCA2 HiBiT in HT1080 cells a...\n", " SMARCA2\n", " SMARCA2 HiBiT\n", " \n", " \n", " 1191\n", + " Degradation of Tau5 in HEK293-hTau cells after...\n", " Tau\n", " Tau5\n", " \n", " \n", " 1192\n", + " Degradation of ENL in MV4;11 cells after 24 h ...\n", " MLLT1\n", " ENL\n", " \n", @@ -4719,57 +4853,124 @@ "" ], "text/plain": [ - " Target Target (Parsed)\n", - "2 BRD9 HiBiT-BRD9\n", - "6 BRD7 HiBiT-BRD7\n", - "77 ALK NPM-ALK\n", - "78 ALK EML4-ALK\n", - "102 FAK Fak\n", - "111 EGFR WT\n", - "112 EGFR Exon 20 Ins EGFR\n", - "113 EGFR Exon 19 del\n", - "114 EGFR L858R EGFR\n", - "115 EGFR L858R, T790M EGFR\n", - "122 BTK C481S C481S BTK\n", - "141 BRD4 BRD4 short\n", - "142 BRD4 BRD4 long\n", - "144 BRD4 BRD4 BD1\n", - "145 BRD4 BRD4 BD2\n", - "208 STAT3 p-STAT3Y705\n", - "262 ALK G1202R G1202R ALK\n", - "356 SMARCA4 SMARCA2\n", - "365 ER ERalpha\n", - "387 VHL pVHL30\n", - "388 TRKC TrkC\n", - "389 HDAC6 HADC6\n", - "495 Tau tau/P-tau\n", - "663 TRKA TPM3-TRKA\n", - "718 EGFR e19d EGFR del19\n", - "806 WDR5 WDR5-HiBiT\n", - "892 PTK2B PYK2\n", - "896 RPS6KA1 RSK1\n", - "1014 AKT2 AKT\n", - "1015 AKT1 AKT\n", - "1016 AKT3 AKT\n", - "1058 GSK-3beta GSK3B\n", - "1145 SMARCA2 SMARCA2 HiBiT\n", - "1191 Tau Tau5\n", - "1192 MLLT1 ENL" + " Assay (DC50/Dmax) Target \\\n", + "2 Degradation of HiBiT-BRD9 in HEK293 cells afte... BRD9 \n", + "6 Degradation of HiBiT-BRD7 in HEK293 cells afte... BRD7 \n", + "77 Degradation of NPM-ALK/EML4-ALK in SU-DHL-1/NC... ALK \n", + "78 Degradation of NPM-ALK/EML4-ALK in SU-DHL-1/NC... ALK \n", + "102 Degradation of Fak in PC3 cells after 24 h tre... FAK \n", + "111 Degradation of WT/Exon 20 Ins EGFR in OVCAR8/H... EGFR \n", + "112 Degradation of WT/Exon 20 Ins EGFR in OVCAR8/H... EGFR \n", + "113 Degradation of Exon 19 del/L858R EGFR in HCC82... EGFR \n", + "114 Degradation of Exon 19 del/L858R EGFR in HCC82... EGFR \n", + "115 Degradation of L858R, T790M EGFR in H1975 cell... EGFR \n", + "122 Degradation of C481S BTK in XLA cells after 24... BTK C481S \n", + "141 Degradation of BRD4 short/long in HeLa cells a... BRD4 \n", + "142 Degradation of BRD4 short/long in HeLa cells a... BRD4 \n", + "144 Degradation of BRD4 BD1/2 assessed by EGFP/mCh... BRD4 \n", + "145 Degradation of BRD4 BD1/2 assessed by EGFP/mCh... BRD4 \n", + "208 Degradation of total STAT3 and p-STAT3Y705 pro... STAT3 \n", + "212 Degradation of total STAT3 and p-STAT3Y705 pro... STAT3 \n", + "262 Degradation of G1202R ALK in 293T cells ALK G1202R \n", + "356 Degradation of SMARCA2 in MV-4-11 cells after ... SMARCA4 \n", + "365 Degradation of ERalpha in MCF-7/T47D cells aft... ER \n", + "367 Degradation of ERalpha in MCF-7 cells after 6 ... ER \n", + "368 Degradation of ERalpha in MCF-7 cells after 6h... ER \n", + "387 Degradation of pVHL30 in HeLa cells after 24 h... VHL \n", + "388 Degradation of TrkC in Hs578t cells after 24 h... TRKC \n", + "389 Degradation of HADC6 in MM.1S cells after 24 h... HDAC6 \n", + "408 Degradation of ERalpha in MCF-7 cells after 4/... ER \n", + "411 Degradation of ERalpha in MCF-7 cells after 4h... ER \n", + "412 Degradation of ERalpha in MCF-7 cells after 4/... ER \n", + "495 Degradation of total tau/P-tau in A152T neuron... Tau \n", + "523 Degradation of ERalpha in MCF7 cells ER \n", + "536 Degradation of Fak in primary Sertoli/germ cel... FAK \n", + "620 Degradation of Fak in HLE/HuH-7/SNU-423 cells ... FAK \n", + "623 Degradation of Fak in HUH-1/HepG2/SK-Hep-1 cel... FAK \n", + "626 Degradation of Fak in A549/Hep3B2.1-7/SNU-387 ... FAK \n", + "629 Degradation of Fak in HLF/SNU-398/HUCCT1 cells... FAK \n", + "663 Degradation of TPM3-TRKA/TRKA in KM12/HEL cell... TRKA \n", + "718 Degradation of EGFR del19 in HCC827 cells afte... EGFR e19d \n", + "769 Degradation of ERalpha in MCF-7 cells ER \n", + "806 Degradation of WDR5-HiBiT in MV4-11 (WDR5-HiBi... WDR5 \n", + "824 Degradation of BRD4 long in HEK293 cells after... BRD4 \n", + "892 Degradation of PYK2 in SR cells after 24 h tre... PTK2B \n", + "896 Degradation of RSK1 in NCI-H2228/A549/Calu-1 c... RPS6KA1 \n", + "899 Degradation of EGFR del19 in HCC-827 cells aft... EGFR e19d \n", + "1014 Degradation of total AKT in BT474 cells after ... AKT2 \n", + "1015 Degradation of total AKT in BT474 cells after ... AKT1 \n", + "1016 Degradation of total AKT in BT474 cells after ... AKT3 \n", + "1058 Degradation of GSK3B in SH-SY5Y cells after 24... GSK-3beta \n", + "1145 Degradation of SMARCA2 HiBiT in HT1080 cells a... SMARCA2 \n", + "1191 Degradation of Tau5 in HEK293-hTau cells after... Tau \n", + "1192 Degradation of ENL in MV4;11 cells after 24 h ... MLLT1 \n", + "\n", + " Target (Parsed) \n", + "2 HiBiT-BRD9 \n", + "6 HiBiT-BRD7 \n", + "77 NPM-ALK \n", + "78 EML4-ALK \n", + "102 Fak \n", + "111 WT \n", + "112 Exon 20 Ins EGFR \n", + "113 Exon 19 del \n", + "114 L858R EGFR \n", + "115 L858R, T790M EGFR \n", + "122 C481S BTK \n", + "141 BRD4 short \n", + "142 BRD4 long \n", + "144 BRD4 BD1 \n", + "145 BRD4 BD2 \n", + "208 p-STAT3Y705 \n", + "212 p-STAT3Y705 \n", + "262 G1202R ALK \n", + "356 SMARCA2 \n", + "365 ERalpha \n", + "367 ERalpha \n", + "368 ERalpha \n", + "387 pVHL30 \n", + "388 TrkC \n", + "389 HADC6 \n", + "408 ERalpha \n", + "411 ERalpha \n", + "412 ERalpha \n", + "495 tau/P-tau \n", + "523 ERalpha \n", + "536 Fak \n", + "620 Fak \n", + "623 Fak \n", + "626 Fak \n", + "629 Fak \n", + "663 TPM3-TRKA \n", + "718 EGFR del19 \n", + "769 ERalpha \n", + "806 WDR5-HiBiT \n", + "824 BRD4 long \n", + "892 PYK2 \n", + "896 RSK1 \n", + "899 EGFR del19 \n", + "1014 AKT \n", + "1015 AKT \n", + "1016 AKT \n", + "1058 GSK3B \n", + "1145 SMARCA2 HiBiT \n", + "1191 Tau5 \n", + "1192 ENL " ] }, - "execution_count": 93, + "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "parsed_table[parsed_table['Target'] !=\n", - " parsed_table['Target (Parsed)']][['Target', 'Target (Parsed)']].drop_duplicates()" + " parsed_table['Target (Parsed)']][['Assay (DC50/Dmax)', 'Target', 'Target (Parsed)']].drop_duplicates()" ] }, { "cell_type": "code", - "execution_count": 94, + "execution_count": 32, "metadata": {}, "outputs": [ { @@ -4806,7 +5007,7 @@ }, { "cell_type": "code", - "execution_count": 95, + "execution_count": 33, "metadata": {}, "outputs": [], "source": [ @@ -4822,7 +5023,7 @@ }, { "cell_type": "code", - "execution_count": 96, + "execution_count": 34, "metadata": {}, "outputs": [ { @@ -5234,7 +5435,7 @@ "[2141 rows x 30 columns]" ] }, - "execution_count": 96, + "execution_count": 34, "metadata": {}, "output_type": "execute_result" } @@ -5247,7 +5448,7 @@ }, { "cell_type": "code", - "execution_count": 97, + "execution_count": 35, "metadata": {}, "outputs": [ { @@ -5350,7 +5551,7 @@ "2083 NaN BCR-ABL T315I BCR-ABL T315I 10.1016/j.apsb.2020.11.009" ] }, - "execution_count": 97, + "execution_count": 35, "metadata": {}, "output_type": "execute_result" } @@ -5362,7 +5563,7 @@ }, { "cell_type": "code", - "execution_count": 98, + "execution_count": 36, "metadata": {}, "outputs": [], "source": [ @@ -5379,58 +5580,195 @@ }, { "cell_type": "code", - "execution_count": 99, + "execution_count": 37, "metadata": {}, "outputs": [ { "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAukAAAGxCAYAAADf8SgMAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8o6BhiAAAACXBIWXMAAA9hAAAPYQGoP6dpAADq80lEQVR4nOzdeVyO2f/48dfddrenQkVRKFlKGoxtJCSSyWDsSxiy71tDdrIvM2MfqpkxljEY+76PfckaEyN8RoYRZY3q+v3h1/V1qwiR5f18PK7HuM51zrne15Hp3Oc+1zkaRVEUhBBCCCGEEO8NvdwOQAghhBBCCKFLOulCCCGEEEK8Z6STLoQQQgghxHtGOulCCCGEEEK8Z6STLoQQQgghxHtGOulCCCGEEEK8Z6STLoQQQgghxHtGOulCCCGEEEK8Z6STLoQQQgghxHtGOulCCJENkZGRaDQa9TAwMMDR0ZF27drxzz//5HZ4b+zs2bOMGDGCuLi43A4lR23bto1y5cphZmaGRqNh1apVmeaLi4tT/26XLFmS4fqIESPQaDT8999/rxxD+s+OsbExly9fznC9evXqlC5d+pXrfVPpzyTejerVq1O9evXcDkN8QKSTLoQQryAiIoL9+/ezZcsWOnbsyOLFi/niiy+4f/9+bof2Rs6ePcvIkSM/qk66oig0adIEQ0NDVq9ezf79+/Hx8XlpuSFDhvDkyZMcjyc5OZmhQ4fmeL1CiI+TdNKFEOIVlC5dmooVK+Lr68vw4cMZOHAgly5dynKE9lU8ePDgzQMUqmvXrpGQkMBXX31FzZo1qVixItbW1i8sU7duXf7++2/mzJmT4/HUqVOHX3/9lRMnTuR43eL1PHnyhJSUlNwOQ4hMSSddCCHeQMWKFQHUaQyKojBr1iy8vLwwMTHB2tqaxo0b8/fff+uUS5/isHv3bipXroypqSnt27cH4M6dO/Tr148iRYqg1WrJnz8/AQEBnDt3Ti3/+PFjxowZg7u7O1qtlnz58tGuXTtu3rypcx9nZ2cCAwPZuHEj3t7emJiY4O7uzsKFC9U8kZGRfP311wD4+vqq0z4iIyMB2LJlC0FBQTg6OmJsbEyxYsUICQnJdOrHH3/8gaenJ1qtliJFijBjxoxMp1Vkt52ysnfvXmrWrImFhQWmpqZUrlyZdevWqddHjBiBo6MjAIMGDUKj0eDs7PzSemvUqIG/vz+jR4/m7t27L8z7Ku0CMHDgQGxtbRk0aFC2nvFZvXv3xszMjKSkpAzXmjZtip2dnTr6v3TpUmrXro2DgwMmJiaUKFGCwYMHZ+vbHo1Gw4gRIzKkOzs7ExwcrJN2/fp1QkJCcHR0xMjICBcXF0aOHJmh0zt79mzKlCmDubk5FhYWuLu78+23374wjvTpRxMnTmTs2LEUKlQIY2NjypUrx7Zt2zLkj42NpUWLFuTPnx+tVkuJEiWYOXOmTp6dO3ei0Wj4+eef6devHwULFkSr1XLhwoUs40hOTmbUqFGUKFECY2NjbG1t8fX1Zd++fWqeR48eERoaiouLC0ZGRhQsWJBu3bpx586dFz5jejw7d+7M9NnT//0BBAcHY25uzrlz5/D398fMzAwHBwfGjx8PwIEDB6hatSpmZma4ubkRFRWlU2f6lKsdO3bQpUsX8ubNi62tLQ0bNuTatWsvjFPkHumkCyHEG0j/BZ8vXz4AQkJC6N27N7Vq1WLVqlXMmjWLM2fOULlyZf7991+dsvHx8bRq1YoWLVqwfv16unbtyt27d6latSpz586lXbt2rFmzhjlz5uDm5kZ8fDwAaWlpBAUFMX78eFq0aMG6desYP348W7ZsoXr16jx8+FDnPidOnKBfv3706dNH7UR36NCB3bt3A1CvXj3GjRsHwMyZM9m/fz/79++nXr16AFy8eJFKlSoxe/ZsNm/ezLBhwzh48CBVq1bVmRayceNGGjZsiK2tLUuXLmXixIksXrw4Q4fhVdvpebt27aJGjRokJiayYMECFi9ejIWFBfXr12fp0qUAfPPNN6xYsQKAHj16sH//flauXJmNv1GYMGEC//33H5MmTXphvuy2SzoLCwuGDh3Kpk2b2L59e7ZiSde+fXsePHjAsmXLdNLv3LnDH3/8QatWrTA0NASedlgDAgJYsGABGzdupHfv3ixbtoz69eu/0j1f5Pr161SoUIFNmzYxbNgwNmzYQIcOHQgPD6djx45qviVLltC1a1d8fHxYuXIlq1atok+fPtmeHvbDDz+wceNGpk+fzi+//IKenh5169Zl//79ap6zZ89Svnx5Tp8+zZQpU1i7di316tWjZ8+ejBw5MkOdoaGhXLlyhTlz5rBmzRry58+f6b1TUlKoW7cuo0ePJjAwkJUrVxIZGUnlypW5cuUK8PTDZoMGDZg8eTKtW7dm3bp19O3bl6ioKGrUqEFycvKrNOsLPXnyhIYNG1KvXj3++OMP6tatS2hoKN9++y1t27alffv2rFy5kuLFixMcHMzRo0cz1PHNN99gaGjIr7/+ysSJE9m5cyetWrXKsRhFDlOEEEK8VEREhAIoBw4cUJ48eaLcvXtXWbt2rZIvXz7FwsJCuX79urJ//34FUKZMmaJT9urVq4qJiYkycOBANc3Hx0cBlG3btunkHTVqlAIoW7ZsyTKWxYsXK4Dy+++/66QfPnxYAZRZs2apaYULF1aMjY2Vy5cvq2kPHz5UbGxslJCQEDXtt99+UwBlx44dL2yHtLQ05cmTJ8rly5cVQPnjjz/Ua+XLl1ecnJyU5ORkNe3u3buKra2t8uyvm1dpp8xUrFhRyZ8/v3L37l01LSUlRSldurTi6OiopKWlKYqiKJcuXVIAZdKkSS+sL7O8LVu2VMzMzJT4+HhFURRl+PDhCqDcvHnzldsl/Wfn8OHDSnJyslKkSBGlXLlyapw+Pj5KqVKlXhqjt7e3UrlyZZ20WbNmKYBy6tSpF8a1a9cuBVBOnDihXkt/pmcByvDhwzPUU7hwYaVt27bqeUhIiGJubq7zc6UoijJ58mQFUM6cOaMoiqJ0795dyZMnz0uf7Xnpfx8FChRQHj58qKYnJSUpNjY2Sq1atdQ0f39/xdHRUUlMTNSpo3v37oqxsbGSkJCgKIqi7NixQwGUatWqZSuGn376SQGU+fPnZ5ln48aNCqBMnDhRJ33p0qUKoMybN09N8/HxUXx8fNTz9Hie/zeX/uwRERFqWtu2bTP8m3/y5ImSL18+BVCOHTumpt+6dUvR19dX+vbtq6al/wx27dpV514TJ05UAPXnXLxfZCRdCCFeQcWKFTE0NMTCwoLAwEDs7e3ZsGEDdnZ2rF27Fo1GQ6tWrUhJSVEPe3t7ypQpk+FrbWtra2rUqKGTtmHDBtzc3KhVq1aWMaxdu5Y8efJQv359nft4eXlhb2+f4T5eXl4UKlRIPTc2NsbNzS3TlUYyc+PGDTp37oyTkxMGBgYYGhpSuHBhAGJiYgC4f/8+R44coUGDBhgZGallzc3NM4zgvmo7Pev+/fscPHiQxo0bY25urqbr6+vTunVr/ve//3H+/PlsPdeLjBkzhidPnmQ6EpsuO+3yPCMjI8aMGcORI0cyjIq/TLt27di3b5/O80VERFC+fHmd1WH+/vtvWrRogb29Pfr6+hgaGqovzGYV16tau3Ytvr6+FChQQOfvsG7dusDTbzsAKlSowJ07d2jevDl//PHHK6+O07BhQ4yNjdXz9G9Mdu/eTWpqKo8ePWLbtm189dVXmJqa6sQSEBDAo0ePOHDggE6djRo1yta9N2zYgLGxsToNLTPp34g8PxXo66+/xszMLNOpOa9Lo9EQEBCgnhsYGFCsWDEcHBwoW7asmm5jY0P+/Pkz/ff95Zdf6px7enoCZPv/BeLdMsjtAIQQ4kPy008/UaJECQwMDLCzs8PBwUG99u+//6IoCnZ2dpmWLVKkiM75s2XT3bx5U6dDnZl///2XO3fu6HSGn/V8R8jW1jZDHq1Wm2FaTGbS0tKoXbs2165dIywsDA8PD8zMzEhLS6NixYpqHbdv387y2Z9Pe9V2elb6fTJruwIFCgBw69atlz7Xyzg7O9O1a1d++OEH+vbtm+F6dtslM82aNWPy5MkMGTKEhg0bZjumli1b0r9/fyIjIwkPD+fs2bMcPnyYWbNmqXnu3bvHF198gbGxMWPGjMHNzQ1TU1OuXr1Kw4YNs/V3nh3//vsva9asUafYPC/9Z7B169akpKQwf/58GjVqRFpaGuXLl2fMmDH4+fm99D729vaZpj1+/Jh79+5x7949UlJS+P777/n+++9fGEu6zH52MnPz5k0KFCiAnl7W45m3bt3CwMBAne6WTqPRYG9vnyM/i+lMTU11PrDA0w99NjY2GfIaGRnx6NGjDOnP/79Aq9UC5NjPhchZ0kkXQohXUKJECcqVK5fptbx586LRaNizZ4/6y+9Zz6dltkZ1vnz5+N///vfCGNJf+tq4cWOm1y0sLF5Y/lWcPn2aEydOEBkZSdu2bdX051+2s7a2RqPRZDqf/Pr16zrnr9pOz99HT09PnZ//rPQX4PLmzfvih8qmoUOHsnDhQr799ltKlSqlcy277ZIZjUbDhAkT8PPzY968edmOx9ramqCgIH766SfGjBlDREQExsbGNG/eXM2zfft2rl27xs6dO3WWm3zZS4zptFptpvOon+9s5s2bF09PT8aOHZtpPekfmODpNwDt2rXj/v377N69m+HDhxMYGMhff/2lfvOQled/dtLTjIyMMDc3x9DQUP0WpVu3bpnW4eLionOe3bXh8+XLx969e0lLS8uyo25ra0tKSgo3b97U6agrisL169cpX758lvWnd7ifb+/XWYtffJxkuosQQuSQwMBAFEXhn3/+oVy5chkODw+Pl9ZRt25d/vrrrxe+WBgYGMitW7dITU3N9D7Fixd/5dizGlFL79A833GeO3euzrmZmRnlypVj1apVPH78WE2/d+8ea9euzRD/67aTmZkZn3/+OStWrNCJNS0tjV9++QVHR0fc3Nxe4cmzlr4Sy/Llyzl06JDOtey2S1Zq1aqFn58fo0aN4t69e9mOqV27dly7do3169fzyy+/8NVXX5EnT54ci8vZ2ZmTJ0/qpG3fvj1DjIGBgZw+fZqiRYtm+nf4bCc9nZmZGXXr1mXIkCE8fvyYM2fOvDSeFStW6IwI3717lzVr1vDFF1+gr6+Pqakpvr6+HD9+HE9Pz0xjyeybpOyoW7cujx490lll5Xk1a9YE4JdfftFJ//3337l//756PTPpqw09396rV69+rXjFx0dG0oUQIodUqVKFTp060a5dO44cOUK1atUwMzMjPj6evXv34uHhQZcuXV5YR+/evVm6dClBQUEMHjyYChUq8PDhQ3bt2kVgYCC+vr40a9aMRYsWERAQQK9evahQoQKGhob873//Y8eOHQQFBfHVV1+9Uuzpc5rnzZuHhYUFxsbGuLi44O7uTtGiRRk8eDCKomBjY8OaNWvYsmVLhjpGjRpFvXr18Pf3p1evXqSmpjJp0iTMzc1JSEjIsXYKDw/Hz88PX19f+vfvj5GREbNmzeL06dMsXrw4R3fR7N27NzNnzmTDhg066a/SLlmZMGECn332GTdu3MgwUp+V2rVr4+joSNeuXbl+/Trt2rXTuV65cmWsra3p3Lkzw4cPx9DQkEWLFmV7bfbWrVsTFhbGsGHD8PHx4ezZs/zwww9YWVnp5Bs1ahRbtmyhcuXK9OzZk+LFi/Po0SPi4uJYv349c+bMwdHRkY4dO2JiYkKVKlVwcHDg+vXrhIeHY2Vl9cJR5nT6+vr4+fnRt29f0tLSmDBhAklJSTrvCsyYMYOqVavyxRdf0KVLF5ydnbl79y4XLlxgzZo1r7ySTrrmzZsTERFB586dOX/+PL6+vqSlpXHw4EFKlChBs2bN8PPzw9/fn0GDBpGUlESVKlU4efIkw4cPp2zZsrRu3TrL+u3t7alVqxbh4eFYW1tTuHBhtm3bpq5KJISs7iKEENnw7AodL7Nw4ULl888/V8zMzBQTExOlaNGiSps2bZQjR46oeV60osft27eVXr16KYUKFVIMDQ2V/PnzK/Xq1VPOnTun5nny5IkyefJkpUyZMoqxsbFibm6uuLu7KyEhIUpsbKyar3Dhwkq9evUy3OP5lSYURVGmT5+uuLi4KPr6+jqrS5w9e1bx8/NTLCwsFGtra+Xrr79Wrly5kulKICtXrlQ8PDwUIyMjpVChQsr48eOVnj17KtbW1q/VTlnZs2ePUqNGDbVsxYoVlTVr1ujkeZPVXZ41b948Bciwukt22+VFPzstWrRQgGyt7pLu22+/VQDFyclJSU1NzXB93759SqVKlRRTU1MlX758yjfffKMcO3Ysw4ohma3ukpycrAwcOFBxcnJSTExMFB8fHyU6OjrD6i6Koig3b95Uevbsqbi4uCiGhoaKjY2N8tlnnylDhgxR7t27pyiKokRFRSm+vr6KnZ2dYmRkpBQoUEBp0qSJcvLkyRc+Y/rfx4QJE5SRI0cqjo6OipGRkVK2bFll06ZNmeZv3769UrBgQcXQ0FDJly+fUrlyZWXMmDFqnvTVVH777beXNbHq4cOHyrBhwxRXV1fFyMhIsbW1VWrUqKHs27dPJ8+gQYOUwoULK4aGhoqDg4PSpUsX5fbt2zp1ZfZvLj4+XmncuLFiY2OjWFlZKa1atVKOHDmS6eouZmZmGeLL6v8jz/+7z+pnMKsVZsT7QaMoivKuPxgIIYT4NDx58gQvLy8KFizI5s2bczsc8YGIi4vDxcWFSZMm0b9//9wOR4hcIdNdhBBC5JgOHTrg5+enTm2YM2cOMTExzJgxI7dDE0KID4p00oUQQuSYu3fv0r9/f27evImhoSHe3t6sX7/+heu+CyGEyEimuwghhBBCCPGekSUYhRBCCCGEeM9IJ10IIYQQQoj3jHTShRBCCCGEeM/Ii6NCfIDS0tK4du0aFhYWObpxixBCCCHeHkVRuHv3LgUKFEBP78Vj5dJJF+IDdO3aNZycnHI7DCGEEEK8hqtXr+Lo6PjCPNJJFx+k7du307VrV86ePfvST6Lvm+DgYO7cucOqVasAaNy4MZUrV6Zv377ZrsPCwgJ4uuGHtbX12whTvEBqaioXL16kaNGi6Ovr53Y4nxRp+9wjbZ+7pP1zT062fVJSEk5OTurv8ReRTvon5mVTI9q2bUtkZOS7CeY5zs7O9O7dm969e78078CBAxkyZIjaQY+MjKRdu3bqdXt7e7744gsmTJiAi4vL2wo5RwwbNgxfX1+++eYbLC0ts1Um/e/R0tIy22VEzklNTcXc3BxLS0v5ZfmOSdvnHmn73CXtn3veRttnZ6qqdNI/MfHx8eqfly5dyrBhwzh//ryaZmJi8kr1PX78GCMjoxyLLzv27dtHbGwsX3/9tU66paUl58+fR1EUzp07R0hICF9++SXR0dGv9Y/qyZMnGBoa5lTYWfL09MTZ2ZlFixbRpUuXVyrrPXoLipHZW4pMZEVfo+BXMI0tURdIVeSdgHfpTds+bny9txCVEELkvA9rnoB4Y/b29uphZWWFRqNRzw0NDencuTOOjo6Ympri4eHB4sWLdcpXr16d7t2707dvX/LmzYufnx8Aq1evxtXVFRMTE3x9fYmKikKj0XDnzh217L59+6hWrRomJiY4OTnRs2dP7t+/r9Z7+fJl+vTpg0ajeeEnzCVLllC7dm2MjY110tOfxcHBAV9fX4YPH87p06e5cOEChw8fxs/Pj7x582JlZYWPjw/Hjh3LUH7OnDkEBQVhZmbGmDFjuH37Ni1btiRfvnyYmJjg6upKRESEWuaff/6hadOmWFtbY2trS1BQEHFxcer11NRU+vbtS548ebC1tWXgwIFktn/Yl19+maGthRBCCPHpkk66UD169IjPPvuMtWvXcvr0aTp16kTr1q05ePCgTr6oqCgMDAz4888/mTt3LnFxcTRu3JgGDRoQHR1NSEgIQ4YM0Slz6tQp/P39adiwISdPnmTp0qXs3buX7t27A7BixQocHR0ZNWoU8fHxOiP+z9u9ezflypV76fOkfyvw5MkT7t69S9u2bdmzZw8HDhzA1dWVgIAA7t69q1Nm+PDhBAUFcerUKdq3b09YWBhnz55lw4YNxMTEMHv2bPLmzQvAgwcP8PX1xdzcnN27d7N3717Mzc2pU6cOjx8/BmDKlCksXLiQBQsWsHfvXhISEli5cmWGWCtUqMChQ4dITk7O9FmSk5NJSkrSOYQQQgjx8ZLpLkJVsGBB+vfvr5736NGDjRs38ttvv/H555+r6cWKFWPixInq+eDBgylevDiTJk0CoHjx4pw+fZqxY8eqeSZNmkSLFi3U+eaurq589913+Pj4MHv2bGxsbNDX18fCwgJ7e/sXxhkXF0eBAgVemOd///sfkyZNwtHRETc3N0qXLq1zfe7cuVhbW7Nr1y4CAwPV9BYtWtC+fXv1/MqVK5QtW1b9UODs7KxeW7JkCXp6evz444/qyH9ERAR58uRh586d1K5dm+nTpxMaGkqjRo0AmDNnDps2bcoQb8GCBUlOTub69esULlw4w/Xw8HBGjhz5wmcWQgghxMdDRtKFKjU1lbFjx+Lp6YmtrS3m5uZs3ryZK1eu6OR7fhT7/PnzlC9fXietQoUKOudHjx4lMjISc3Nz9fD39yctLY1Lly69UpwPHz7MMNUFIDExEXNzc8zMzHBycuLx48esWLECIyMjbty4QefOnXFzc8PKygorKyvu3bv30mfr0qULS5YswcvLi4EDB7Jv3z6dZ7pw4QIWFhbqM9nY2PDo0SMuXrxIYmIi8fHxVKpUSS1jYGCQ6bcA6aP+Dx48yPSZQ0NDSUxMVI+rV69mv8GEEEII8cGRkXShmjJlCtOmTWP69Ol4eHhgZmZG79691akb6czMdF9UVBQlwxzy5+ddp6WlERISQs+ePTPct1ChQq8UZ968ebl9+3aGdAsLC44dO4aenh52dnY6cQYHB3Pz5k2mT59O4cKF0Wq1VKpU6aXPVrduXS5fvsy6devYunUrNWvWpFu3bkyePJm0tDQ+++wzFi1alCGWfPnyvdIzJSQkvLCcVqtFq9W+Up1CCCGE+HBJJ12o9uzZQ1BQEK1atQKedqxjY2MpUaLEC8u5u7uzfv16nbQjR47onHt7e3PmzBmKFSuWZT1GRkakpqa+NM6yZcty9uzZDOl6enpZ1r9nzx5mzZpFQEAA8HQTgf/++++l94KnHefg4GCCg4P54osvGDBgAJMnT8bb25ulS5eSP3/+LJdBdHBw4MCBA1SrVg2AlJQUjh49ire3t06+06dP4+joqM53z65jYX6yTnouSE1NJTY2lpmurrIU2jsmbS+E+FTIdBehKlasGFu2bGHfvn3ExMQQEhLC9evXX1ouJCSEc+fOMWjQIP766y+WLVumrrWePsI+aNAg9u/fT7du3YiOjiY2NpbVq1fTo0cPtR5nZ2d2797NP//888IOtL+/P3v37n3lZ/v555+JiYnh4MGDtGzZMlvLTQ4bNow//viDCxcucObMGdauXat+aGnZsiV58+YlKCiIPXv2cOnSJXbt2kWvXr343//+B0CvXr0YP348K1eu5Ny5c3Tt2lVnxZt0e/bsoXbt2q/0TEIIIYT4eEknXajCwsLw9vbG39+f6tWrY29vT4MGDV5azsXFheXLl7NixQo8PT2ZPXu2urpL+hQNT09Pdu3aRWxsLF988QVly5YlLCwMBwcHtZ5Ro0YRFxdH0aJFXzhdpFWrVpw9e1ZnffeXWbhwIbdv36Zs2bK0bt2anj17kj9//peWMzIyIjQ0FE9PT6pVq4a+vj5LliwBwNTUlN27d1OoUCEaNmxIiRIlaN++PQ8fPlRH1vv160ebNm0IDg6mUqVKWFhY8NVXX+nc49GjR6xcuZKOHTtm+3mEEEII8XHTKJkt2izEGxo7dixz5sx5ay84Dhw4kMTERObOnftW6n+XZs6cyR9//MHmzZuzXSYpKQkrKysSEhJkuksuSJ9y4SpTLt45afvcI22fu6T9c09Otn367+/ExMSX7hguI+kiR8yaNYvDhw/z999/8/PPPzNp0iTatm371u43ZMgQChcunK057O87Q0NDvv/++9wOQwghhBDvEemkixwRGxtLUFAQJUuWZPTo0fTr148RI0a8tftZWVnx7bffqp9oU1NTqVy5sroeebrExEScnJwYOnQocXFxaDQaoqOj31pcO3fuVHdM1Wg05MuXj7p163LixAk1z4gRI3B3d8fMzAxra2uWLVuW6Tx1IYQQQny6ZHUXkSOmTZvGtGnTcu3++vr6REVF4eXlxaJFi2jZsiXwdEMmGxsbhg0bxrVr195ZPOfPn8fS0pIrV67Qs2dP6tSpw7lz57CyssLNzY0ffviBIkWK8PDhQ6ZNm0bt2rW5cOHCKy/d6D16C4qR2cszihylr1HwK5jGlqgLpCqalxcQOeZN2z5ufL23EJUQQuQ8GUkXHw1XV1fCw8Pp0aMH165d448//mDJkiVERUVhZGT00vLJycnqC6XGxsZUrVqVw4cP6+RZvXo1rq6umJiY4OvrS1RUFBqNJsNIeP78+bG3t6dChQpMmTKF69evc+DAAeDprqa1atWiSJEilCpViqlTp5KUlMTJkydzrC2EEEII8WGTTrr4qPTo0YMyZcrQpk0bOnXqxLBhw/Dy8spW2YEDB/L7778TFRXFsWPHKFasGP7+/upGQ3FxcTRu3JgGDRoQHR1NSEiIuorNi6Qv9fjkyZMM1x4/fsy8efOwsrKiTJkyWdaRnJxMUlKSziGEEEKIj5d00sVHRaPRMHv2bLZt24adnR2DBw/OVrn79+8ze/ZsJk2aRN26dSlZsiTz58/HxMSEBQsWADBnzhyKFy/OpEmTKF68OM2aNSM4OPiF9d66dYuRI0diYWFBhQoV1PS1a9dibm6OsbEx06ZNY8uWLS/cyCg8PBwrKyv1cHJyytZzCSGEEOLDJJ108dFZuHAhpqamXLp0Sd1U6GUuXrzIkydPqFKlippmaGhIhQoViImJAZ7OMy9fvrxOuWc73s9ydHTE3NycvHnzEhMTw2+//aazLruvry/R0dHs27ePOnXq0KRJE27cuJFlfKGhoSQmJqrH21raUgghhBDvB+mki4/K/v37mTZtGn/88QeVKlWiQ4cOZGcrgPQ86TukPpuenvbsn58v97w9e/Zw4sQJEhMT+euvv/D399e5bmZmRrFixahYsSILFizAwMBAHbHPjFarxdLSUucQQgghxMdLVncRH42HDx/Stm1bQkJCqFWrFm5ubpQuXZq5c+fSuXPnF5YtVqwYRkZG7N27lxYtWgBP55AfOXKE3r17A+Du7s769et1yh05ciTT+lxcXMiTJ0+2Y1cUheTk5GznT3cszE82M8oF6RtbzJRNRd45aXshxKdCOuniozF48GDS0tKYMGECAIUKFWLKlCn07duXOnXqqPnOnz+foWzJkiXp0qULAwYMwMbGhkKFCjFx4kQePHhAhw4dAAgJCWHq1KkMGjSIDh06EB0dTWRkJJBxBD4r9+/fZ+zYsXz55Zc4ODhw69YtZs2axf/+9z++/vrrN2wBIYQQQnwspJMuPgq7du1i5syZ7Ny5EzOz/1s3vGPHjixfvpwOHTrw448/AtCsWbMM5S9dusT48eNJS0ujdevW3L17l3LlyrFp0yZ1pNrFxYXly5fTr18/ZsyYQaVKlRgyZAhdunRBq9VmK059fX3OnTtHVFQU//33H7a2tpQvX549e/ZQqlSpHGgJIYQQQnwMNEp2JuwKITI1duxY5syZ885f5ExKSsLKyoqEhASZ7pIL0qdcuMqUi3dO2j73SNvnLmn/3JOTbZ/++zsxMfGl75fJSLoQr2DWrFmUL18eW1tb/vzzTyZNmkT37t1zOywhhBBCfGSkky7EK4iNjWXMmDEkJCRQqFAh+vXrR2hoaG6HJYQQQoiPjHTSxVsVHBxMVFRUhnR/f382btz4TmIYMWIEq1atIjo6+qX5Ro4cmWlsEydOZNCgQfj4+HDt2rW3GO2r8R69BcXI7OUZRY7S1yj4FUxjS9QFUpXsvTQscsabtn3c+HpvISohhMh50kkXb12dOnWIiIjQScvui5bvmoODAzt27OB///sfjo6OanpERASFChXKxciEEEII8SmRzYzEW6fVarG3t9c50l923LlzJ0ZGRuzZs0fNP2XKFPLmzUt8fDwAGzdupGrVquTJkwdbW1sCAwO5ePGizj3+97//0axZM2xsbDAzM6NcuXIcPHiQyMhIRo4cyYkTJ9BoNGg0GnXZxMzkz5+f2rVr64z+79u3j//++4969XRH4A4fPoyfnx958+bFysoKHx8fjh07ppNnxIgRFCpUCK1WS4ECBejZs6d6bdasWbi6umJsbIydnR2NGzfOMq7k5GSSkpJ0DiGEEEJ8vKSTLnJV9erV6d27N61btyYxMZETJ04wZMgQ5s+fj4ODA/B0bfG+ffty+PBhtm3bhp6eHl999RVpaWkA3Lt3T52Gsnr1ak6cOMHAgQNJS0ujadOm9OvXj1KlShEfH098fDxNmzZ9YUzt27fX6cgvXLiQli1bYmRkpJPv7t27tG3blj179nDgwAFcXV0JCAjg7t27ACxfvpxp06Yxd+5cYmNjWbVqFR4eHsDTTZB69uzJqFGjOH/+PBs3bqRatWpZxhQeHo6VlZV6ODk5vXJbCyGEEOLDIdNdxFu3du1azM3NddIGDRpEWFgYAGPGjGHr1q106tSJM2fO0Lp1a7766is1b6NGjXTKLliwgPz583P27FlKly7Nr7/+ys2bNzl8+DA2NjbA0x1E05mbm2NgYIC9vX224g0MDKRz587s3r2bzz77jGXLlrF3714WLlyok69GjRo653PnzsXa2ppdu3YRGBjIlStXsLe3p1atWhgaGlKoUCEqVKgAwJUrVzAzMyMwMBALCwsKFy5M2bJls4wpNDSUvn37qudJSUnSURdCCCE+YjKSLt46X19foqOjdY5u3bqp142MjPjll1/4/fffefjwIdOnT9cpf/HiRVq0aEGRIkWwtLTExcUFeNrRBYiOjqZs2bJqB/1NGRoa0qpVKyIiIvjtt99wc3PD09MzQ74bN27QuXNn3Nzc1BHue/fuqXF9/fXXPHz4kCJFitCxY0dWrlxJSkoKAH5+fhQuXJgiRYrQunVrFi1axIMHD7KMSavVYmlpqXMIIYQQ4uMlI+nirTMzM9MZ2c7Mvn37AEhISCAhIUFn19D69evj5OTE/PnzKVCgAGlpaZQuXZrHjx8DYGJikuMxt2/fns8//5zTp0/Tvn37TPMEBwdz8+ZNpk+fTuHChdFqtVSqVEmNy8nJifPnz7Nlyxa2bt1K165dmTRpErt27cLCwoJjx46xc+dONm/ezLBhwxgxYgSHDx8mT548Of48QgghhPiwSCdd5LqLFy/Sp08f5s+fz7Jly2jTpo069/zWrVvExMQwd+5cvvjiCwD27t2rU97T05Mff/yRhISETEfTjYyMSE1NfaWYSpUqRalSpTh58iQtWrTINM+ePXuYNWsWAQEBAFy9epX//vtPJ4+JiQlffvklX375Jd26dcPd3Z1Tp07h7e2NgYEBtWrVolatWgwfPpw8efKwfft2GjZsmO04j4X5yY6juSB997mZsvPfOydtL4T4VEgnXbx1ycnJXL9+XSfNwMCAvHnzkpqaSuvWralduzbt2rWjbt26eHh4MGXKFAYMGIC1tTW2trbMmzcPBwcHrly5wuDBg3Xqat68OePGjaNBgwaEh4fj4ODA8ePHKVCgAJUqVcLZ2ZlLly4RHR2No6MjFhYW2VoCcvv27Tx58iTLke1ixYrx888/U65cOZKSkhgwYIDOqH5kZCSpqal8/vnnmJqa8vPPP2NiYkLhwoVZu3Ytf//9N9WqVcPa2pr169eTlpZG8eLFX72BhRBCCPHRkTnp4q3buHEjDg4OOkfVqlUBGDt2LHFxccybNw8Ae3t7fvzxR4YOHUp0dDR6enosWbKEo0ePUrp0afr06cOkSZN06jcyMmLz5s3kz5+fgIAAPDw8GD9+vDrK1qhRI+rUqYOvry/58uVj8eLF2YrbzMzshVNPFi5cyO3btylbtiytW7emZ8+e5M+fX72eJ08e5s+fT5UqVfD09GTbtm2sWbMGW1tb8uTJw4oVK6hRowYlSpRgzpw5LF68mFKlSr1K0wohhBDiI6VRFEXJ7SCEEK8mKSkJKysrEhISZLpLLkifcuEqUy7eOWn73CNtn7uk/XNPTrZ9+u/vxMTEly4CISPp4qVu3bpF/vz5iYuLy+1QPkqnTp3C0dGR+/fv53YoQgghhHhPSCc9F+zbtw99fX3q1KmT26FkS3h4OPXr18fZ2RmAuLg4dfdOjUaDhYUFpUqVolu3bsTGxmYo//jxYyZOnEiZMmUwNTUlb968VKlShYiICJ48eQI83Znz2To1Gk2Gdc0VRWHEiBEUKFAAExMTqlevzpkzZzKN2cXFhY0bN7Jz5061Pj09PaysrChbtiwDBw5UdzTNbR4eHlSoUIFp06bldihCCCGEeE/Ii6O5YOHChfTo0YMff/yRK1euUKhQodwOKUsPHz5kwYIFrF+/PsO1rVu3UqpUKR48eMCpU6eYMWMGZcqUYc2aNdSsWRN42kH39/fnxIkTjB49mipVqmBpacmBAweYPHkyZcuWxcvLC3i6osrWrVvV+p//SmnixIlMnTqVyMhI3NzcGDNmDH5+fpw/fx4LCws138mTJ7l16xa+vr7s378fgPPnz2NpaUlSUhLHjh1j4sSJLFiwgJ07d6q7gOamdu3a0blzZ0JDQ1/pqzTv0VtQjMxenlHkKH2Ngl/BNLZEXSBV0eR2OJ+UN237uPH13kJUQgiR82Qk/R27f/8+y5Yto0uXLgQGBupsPw9w+/ZtWrZsSb58+TAxMcHV1ZWIiAjgaYe3e/fuODg4YGxsjLOzM+Hh4WrZqVOn4uHhgZmZGU5OTnTt2pV79+6p97W0tGT58uU691uzZg1mZmbqVvbP27BhAwYGBlSqVCnDNVtbW+zt7SlSpAhBQUFs3bqVzz//nA4dOqhLHk6fPp3du3ezbds2unXrhpeXF0WKFKFFixYcPHgQV1dXtb70XUHTj3z58qnXFEVh+vTpDBkyhIYNG1K6dGmioqJ48OABv/76q05cf/zxB/7+/joruOTPnx97e3vc3Nxo1qwZf/75J/ny5aNLly5qnuDgYBo0aMC4ceOws7MjT548jBw5kpSUFAYMGICNjQ2Ojo4Zdh4dNGgQbm5umJqaUqRIEcLCwtRvCBRFoVatWtSpU4f01z/u3LlDoUKFGDJkiFqHv78/t27dYteuXZn+PQghhBDi0yKd9Hds6dKlFC9enOLFi6u7Wj777m5YWBhnz55lw4YNxMTEMHv2bPLmzQvAd999x+rVq1m2bBnnz5/nl19+UaegAOjp6fHdd99x+vRpoqKi2L59OwMHDgSerlTSrFkztcOfLiIigsaNG+uMRD9r9+7dlCtXLlvPpqenR69evbh8+TJHjx4FYNGiRdSqVSvTLe8NDQ11Ni2KjY2lQIECuLi40KxZM/7++2/12qVLl7h+/Tq1a9dW07RaLT4+PupGSOlWr15NUFDQC2M1MTGhc+fO/Pnnn9y4cUNN3759O9euXWP37t1MnTqVESNGEBgYiLW1NQcPHqRz58507tyZq1evqmUsLCyIjIzk7NmzzJgxg/nz56tTVzQaDVFRURw6dIjvvvsOgM6dO2NnZ8eIESPUOoyMjChTpgx79uzJNN7k5GSSkpJ0DiGEEEJ8vGS6yzu2YMECWrVqBUCdOnW4d+8e27Zto1atWsDTre7Lli2rdoyf7YRfuXIFV1dXqlatikajoXDhwjp19+7dW/2zi4sLo0ePpkuXLsyaNQuAb775hsqVK3Pt2jUKFCjAf//9x9q1a9myZUuW8cbFxVGgQIFsP5+7u7tarkKFCsTGxlK9evWXlvv888/56aefcHNz499//2XMmDFUrlyZM2fOYGtrq66zbmdnp1POzs6Oy5cvq+f//PMPJ06cUDcYym6s6Usn2tjY8N1336Gnp0fx4sWZOHEiDx484NtvvwUgNDSU8ePH8+eff9KsWTMAhg4dqtbp7OxMv379WLp0qfoBqWDBgsydO5fWrVvz77//smbNGo4fP46hoaFOPAULFszy5dzw8HBGjhz50mcSQgghxMdBRtLfofPnz3Po0CG1c2dgYEDTpk11pk906dKFJUuW4OXlxcCBA3VGiYODg4mOjqZ48eL07NmTzZs369S/Y8cO/Pz8KFiwIBYWFrRp04Zbt26pq4ZUqFCBUqVK8dNPPwHw888/U6hQIapVq5ZlzA8fPsTY2Djbz5j+rYBGo1HP0//8InXr1qVRo0Z4eHhQq1Yt1q1bB0BUVJROvufrer7+1atXU6VKlUx3Hn1ZrPB0Xrye3v/9s7Czs9OZs66vr4+tra3O6Pvy5cupWrUq9vb2mJubExYWxpUrV3Tu9fXXX9OwYUPCw8OZMmUKbm5uGeIxMTHhwYMHmcYaGhpKYmKiejw7ki+EEEKIj4900t+hBQsWkJKSQsGCBTEwMMDAwIDZs2ezYsUKbt++DTztrF6+fJnevXtz7do1atasSf/+/QHw9vbm0qVLjB49mocPH9KkSRMaN24MwOXLlwkICKB06dL8/vvvHD16lJkzZwKo86Ph6Wh6+pSXiIgI2rVr98JOdN68edXYsiMmJgZ4OpIP4Obmpqa9CjMzMzw8PNTVYtJXenl+59IbN27ojK5nZ6rL87E++23F86PbGo0m07S0tDQADhw4QLNmzahbty5r167l+PHjDBkyhMePH+uUefDgAUePHkVfXz/TFXAAEhISdObhP0ur1WJpaalzCCGEEOIjpoh34smTJ4qdnZ0yZcoU5dSpUzqHm5ub8v3332dabs6cOYqFhUWm1zZu3KgAyq1bt5Tly5crBgYGSmpqqnp99OjRCqDcvn1bTUtISFCMjY2VGTNmKHp6esrVq1dfGPekSZOUMmXK6KRdunRJAZTjx4/rpKempio+Pj6Ki4uLkpKSoiiKoowfP17R09NTjh07lmmb3Lt3L9P7Pnr0SClYsKAycuRIRVEUJS0tTbG3t1cmTJig5klOTlasrKyUOXPmKIqiKHfv3lW0Wq1y8eJFNc+OHTsytIGiKMqDBw+U4sWLK9WqVVPT2rZtqwQFBenk8/HxUXr16qWTVrhwYWXatGmKoijK5MmTlSJFiuhc79Chg2JlZaWT1rlzZ8Xd3V3ZvHmzYmBgoGzbti3DMzs6Oio//vhjpu3xvMTERAVQEhISspVf5KyUlBQlJiZG/TkX7460fe6Rts9d0v65JyfbPv33d2Ji4kvzypz0d2Tt2rXcvn2bDh06YGVlpXOtcePGLFiwgO7duzNs2DA+++wzSpUqRXJyMmvXrqVEiRIATJs2DQcHB7y8vNDT0+O3337D3t6ePHnyULRoUVJSUvj++++pX78+f/75J3PmzMkQh7W1NQ0bNmTAgAHUrl0bR0fHF8bt7+9PaGgot2/fzrCz5a1bt7h+/ToPHjzg9OnTTJ8+nUOHDrFu3Tp1GcHevXuzbt06atasyejRo6latSoWFhYcOXKECRMmsGDBAry8vOjfvz/169enUKFC3LhxgzFjxpCUlETbtm2Bp6PXvXv3Zty4cbi6uuLq6sq4ceMwNTWlRYsWAGzcuBFXV1eKFCmS4Tlu3LjBo0ePuHv3LkePHmXixIn8999/rFixIpt/g5krVqwYV65cYcmSJZQvX55169axcuVKnTzr1q1j4cKF7N+/H29vbwYPHkzbtm05efKk2qZxcXH8888/6rsJQgghhPjEvfFHApEtgYGBSkBAQKbXjh49qgDK0aNHldGjRyslSpRQTExMFBsbGyUoKEj5+++/FUVRlHnz5ileXl6KmZmZYmlpqdSsWVNnhHrq1KmKg4ODYmJiovj7+ys//fRTpqPI27ZtUwBl2bJl2Yq9YsWK6mi1ovzfSHr6YWpqqpQoUULp2rWrEhsbm6H8o0ePlPDwcMXDw0MxNjZWbGxslCpVqiiRkZHKkydPFEVRlKZNmyoODg6KoaGhUqBAAaVhw4bKmTNndOpJS0tThg8frtjb2ytarVapVq2acurUKfV6q1atlCFDhuiUSR9JBxSNRqNYWFgoZcqUUQYMGKDEx8fr5H2dkXRFUZQBAwYotra2irm5udK0aVNl2rRp6kj6jRs3FDs7O2XcuHFq/idPnigVKlRQmjRpoqaNGzdO8ff3z9B2WZGR9NwlI1q5R9o+90jb5y5p/9yTWyPpGkV5Zv0/8UlYtGgRvXr14tq1axgZGb00//r16+nfvz+nT5/WeanyfZKamkr+/PnZsGEDFSpUyO1wXklycjKurq4sXryYKlWqZKtMUlISVlZWJCQkZPiGQ7x9qampxMbG4urq+kqbT4k3J22fe6Ttc5e0f+7JybZP//2dmJj40vfLZLrLJ+TBgwdcunSJ8PBwQkJCstVBBwgICCA2NpZ//vkHJyentxzl67l16xZ9+vShfPnyuR3KK7t8+TJDhgzJdgddCCGEEB+/93NYVLwVEydOxMvLCzs7O0JDQ1+pbK9evd7bDjo83VF06NCh2VruEZ4uZ6nRaBg/frxO+qpVq7JdR05xc3MjJCTknd5TCCGEEO83GUn/hIwYMUJnl8tPnbGxMRMmTCAkJOSDnTLiPXoLipHZyzOKHKWvUfArmMaWqAukKu/2Q92nTto+90jbPxU3vl5uhyA+ETKSLj5ZtWrVwt7envDw8Eyv37p1i+bNm+Po6IipqSkeHh4sXrxYJ0/16tXp0aMHvXv3xtraGjs7O+bNm8f9+/dp164dFhYWFC1alA0bNuiUO3v2LAEBAZibm2NnZ0fr1q3577//3tqzCiGEEOLDIp108cnS19dn3LhxfP/99/zvf//LcP3Ro0d89tlnrF27ltOnT9OpUydat27NwYMHdfJFRUWRN29eDh06RI8ePejSpQtff/01lStX5tixY/j7+9O6dWt1N9H4+Hh8fHzw8vLiyJEjbNy4kX///ZcmTZpkGWtycjJJSUk6hxBCCCE+XtJJF5+0r776Ci8vL4YPH57hWsGCBenfvz9eXl4UKVKEHj164O/vz2+//aaTr0yZMgwdOhRXV1dCQ0MxMTEhb968dOzYEVdXV4YNG8atW7c4efIkALNnz8bb25tx48bh7u5O2bJlWbhwITt27OCvv/7KNM7w8HCsrKzU431+P0AIIYQQb0466eKTN2HCBKKiojh79qxOempqKmPHjsXT0xNbW1vMzc3ZvHkzV65c0cnn6emp/llfXx9bW1s8PDzUNDs7O+DphkoAR48eZceOHZibm6uHu7s7ABcvXsw0xtDQUBITE9Xj6tWrb/7gQgghhHhvyYuj4pNXrVo1/P39+fbbbwkODlbTp0yZwrRp05g+fToeHh6YmZnRu3dvHj9+rFPe0NBQ51yj0eikpa8Wk5aWpv63fv36TJgwIUMsDg4Omcao1WrRarWv9XxCCCGE+PBIJ10IYPz48Xh5eeHm5qam7dmzh6CgIFq1agU87VzHxsZSokSJN7qXt7c3v//+O87OzhgYvNk/wWNhfh/syjQfsvSNLWbKpiLvnLR97pG2F+LdkukuQgAeHh60bNmS77//Xk0rVqwYW7ZsYd++fcTExBASEsL169ff+F7dunUjISGB5s2bc+jQIf7++282b95M+/btSU1NfeP6hRBCCPHhk066EP/f6NGjURRFPQ8LC8Pb2xt/f3+qV6+Ovb09DRo0eOP7FChQgD///JPU1FT8/f0pXbo0vXr1wsrKCj09+ScphBBCCJnuIj5RkZGRGdIKFy7Mo0eP1HMbGxtWrVr1wnp27tyZIS0uLi5D2rOdfwBXV1dWrFiRnVCFEEII8QmSYTshhBBCCCHeM9JJF0IIIYQQ4j0j012EyIbg4GCioqIAMDAwwMnJiYYNGzJy5Ehu3ryJi4uLmtfc3JxChQpRvXp1evfujaurq3otMjKSdu3aqedmZmYUL16cIUOG0LBhw1eOy3v0FhQjszd4MvE69DUKfgXT2BJ1gVRFk9vhfFKk7XOPtH3ukvZ/d+LG18vtEAAZSRci2+rUqUN8fDx///03Y8aMYdasWfTv31+9vnXrVuLj4zlx4gTjxo0jJiaGMmXKsG3bNp16LC0tiY+PJz4+nuPHj+Pv70+TJk04f/78u34kIYQQQrynpJMuRDZptVrs7e1xcnKiRYsWtGzZUufFUltbW+zt7SlSpAhBQUFs3bqVzz//nA4dOugsrajRaLC3t8fe3h5XV1fGjBmDnp4eJ0+ezPLeycnJJCUl6RxCCCGE+HhJJ12I12RiYsKTJ0+yvK6np0evXr24fPkyR48ezTRPamqqOo3G29s7y7rCw8OxsrJSDycnpzcLXgghhBDvNemkC/EaDh06xK+//krNmjVfmM/d3R3QXZYxMTERc3NzzM3NMTIyokuXLsybN4+iRYtmWU9oaCiJiYnqcfXq1Rx5DiGEEEK8n+TFUSGyae3atZibm5OSksKTJ08ICgri+++/58GDB1mWSV8fXaP5v5d8LCwsOHbsGAAPHjxg69athISEYGtrS/369TOtR6vVotVqc/BphBBCCPE+k066ENnk6+vL7NmzMTQ0pECBAhgaGgKZb16ULiYmBkBn9Rc9PT2KFSumnnt6erJ582YmTJiQZSddCCGEEJ8W6aQLkU1mZmY6neuXSUtL47vvvsPFxYWyZcu+MK++vj4PHz585ZiOhflhbW39yuXEm0lNTSU2NpaZrq7o6+vndjifFGn73CNtn7uk/T890kkXIofcunWL69ev8+DBA06fPs306dM5dOgQ69at0/kfqqIoXL9+HYCHDx+yZcsWNm3axLBhw3IrdCGEEEK8Z6STLkQOqVWrFgCmpqYULlwYX19f5s2bl2H0PSkpCQcHB+DpXPPChQszatQoBg0a9M5jFkIIIcT7STrpQmRDZGRkltecnZ3VF0RfJjg4mODg4JwJSgghhBAfLVmCUQghhBBCiPeMdNLFJ0Gj0bzwyM3RbWdnZ6ZPn55r9xdCCCHE+0emu4hPQnx8vPrnpUuXMmzYMM6fP6+mmZiYvFJ9jx8/xsjIKMfie13eo7egGJnldhifHH2Ngl/BNLZEXSBV0by8gMgxb9r2cePrvYWohBAi58lIuvgk2Nvbq4eVlRUajUY9NzQ0pHPnzjg6OmJqaoqHhweLFy/WKV+9enW6d+9O3759yZs3L35+fgCsXr0aV1dXTExM8PX1JSoqCo1Gw507d9Sy+/bto1q1apiYmODk5ETPnj25f/++Wu/ly5fp06ePOqovhBBCCCGddPHJe/ToEZ999hlr167l9OnTdOrUidatW3Pw4EGdfFFRURgYGPDnn38yd+5c4uLiaNy4MQ0aNCA6OpqQkBCGDBmiU+bUqVP4+/vTsGFDTp48ydKlS9m7dy/du3cHYMWKFTg6OjJq1Cji4+N1RvyflZycTFJSks4hhBBCiI+XTHcRn7yCBQvSv39/9bxHjx5s3LiR3377jc8//1xNL1asGBMnTlTPBw8eTPHixZk0aRIAxYsX5/Tp04wdO1bNM2nSJFq0aEHv3r0BcHV15bvvvsPHx4fZs2djY2ODvr4+FhYW2NvbZxljeHg4I0eOzKlHFkIIIcR7TkbSxScvNTWVsWPH4unpia2tLebm5mzevJkrV67o5CtXrpzO+fnz5ylfvrxOWoUKFXTOjx49SmRkJObm5urh7+9PWloaly5dynaMoaGhJCYmqsfVq1df8SmFEEII8SGRkXTxyZsyZQrTpk1j+vTpeHh4YGZmRu/evXn8+LFOPjMz3Rc0FUXJMIf8+fXS09LSCAkJoWfPnhnuW6hQoWzHqNVq0Wq12c4vhBBCiA+bdNLFJ2/Pnj0EBQXRqlUr4GnHOjY2lhIlSrywnLu7O+vXr9dJO3LkiM65t7c3Z86cybDr6LOMjIxITU19rdiPhflhbW39WmXF60tNTSU2NpaZrq7o6+vndjifFGl7IcSnQqa7iE9esWLF2LJlC/v27SMmJoaQkBCuX7/+0nIhISGcO3eOQYMG8ddff7Fs2TJ1Z9L0EfZBgwaxf/9+unXrRnR0NLGxsaxevZoePXqo9Tg7O7N7927++ecf/vvvv7fyjEIIIYT4sEgnXXzywsLC8Pb2xt/fn+rVq2Nvb0+DBg1eWs7FxYXly5ezYsUKPD09mT17trq6S/rUFE9PT3bt2kVsbCxffPEFZcuWJSwsDAcHB7WeUaNGERcXR9GiRcmXL99beUYhhBBCfFg0yvOTaIUQr23s2LHMmTPnrb/YmZSUhJWVFQkJCTLdJRekT7lwlSkX75y0fe6Rts9d0v65JyfbPv33d2JiIpaWli/MK3PShXgDs2bNonz58tja2vLnn38yadIkdQ10IYQQQojXJdNdhHiORqNh1apV2cobGxtLUFAQJUuWZPTo0fTr148RI0a8sExcXJy6u6hGo8Ha2ppq1aqxa9euNw9eCCGEEB8FGUkX4g1MmzaNadOmvVbZrVu3UqpUKW7cuMG3335LQEAAp0+fxsXFJdt1eI/egmJk9vKMIkfpaxT8CqaxJeoCqYrm5QVEjpG2f3Nx4+vldghCiGyQkXTxSUpLS2PChAkUK1YMrVZLoUKFdHYKfVG5UaNG4ejoiFarxcvLi40bN+rk2bdvH15eXhgbG1OuXDlWrVqFRqMhOjpaJ5+trS329vZ4enoyd+5cHjx4wObNm3PyMYUQQgjxgZKRdPFJCg0NZf78+UybNo2qVasSHx/PuXPnXlpuxowZTJkyhblz51K2bFkWLlzIl19+yZkzZ3B1deXu3bvUr1+fgIAAfv31Vy5fvkzv3r1fWq+pqSkAT548yfR6cnIyycnJ6nlSUlL2HlQIIYQQHyTppItPzt27d5kxYwY//PADbdu2BaBo0aJUrVr1pWUnT57MoEGDaNasGQATJkxgx44dTJ8+nZkzZ7Jo0SI0Gg3z58/H2NiYkiVL8s8//9CxY8cs67x//z6hoaHo6+vj4+OTaZ7w8HBGjhz5Gk8rhBBCiA+RTHcRn5yYmBiSk5OpWbPmK5VLSkri2rVrVKlSRSe9SpUqxMTEAHD+/Hk8PT0xNjZWr1eoUCHT+ipXroy5uTkWFhasWbOGyMhIPDw8Ms0bGhpKYmKierztJR6FEEIIkbtkJF18ckxMTN6ofPpuoukURVHTnv3zs9czs3TpUkqWLEmePHmwtbV94T21Wq26QZIQQgghPn7SSRefHFdXV0xMTNi2bRvffPNNtstZWlpSoEAB9u7dS7Vq1dT0ffv2qaPl7u7uLFq0iOTkZLVTfeTIkUzrc3JyomjRom/wJHAszE82M8oF6RtbzJRNRd45aXshxKdCOunik2NsbMygQYMYOHAgRkZGVKlShZs3b3LmzBk6dOgAwKVLlzKsxlKsWDEGDBjA8OHDKVq0KF5eXkRERBAdHc2iRYsAaNGiBUOGDKFTp04MHjyYK1euMHnyZCDjCLwQQgghRFakky4+SWFhYRgYGDBs2DCuXbuGg4MDnTt3Vq/37ds3Q5kdO3bQs2dPkpKS6NevHzdu3KBkyZKsXr0aV1dX4Olo+5o1a+jSpQteXl54eHgwbNgwWrRooTNPXQghhBDiRTRKVhNmhRA5YtGiRbRr147ExMQ3ng+fLikpCSsrKxISEmS6Sy5In3LhKlMu3jlp+9wjbZ+7pP1zT062ffrv78TERCwtLV+YV0bShchhP/30E0WKFKFgwYKcOHGCQYMG0aRJkxzroAshhBDi4ydLMH4idu7ciUaj4c6dO+/sniNGjMDLy+ud3e99cf36dVq1akWJEiXo06cP/v7+LFq0KMMcdyGEEEKIrEgn/T0VHByMRqPRmSedrmvXrmg0GoKDg999YO+J6tWro9FoMhwpKSm5HRoDBw4kLi6OR48ecenSJcLCwnI7JCGEEEJ8YKST/h5zcnJiyZIlPHz4UE179OgRixcvplChQrkY2bvz5MmTLK917NiR+Ph4ncPA4PVmcD1+/Ph1QxRCCCGEyHHSSX+PeXt7U6hQIVasWKGmrVixAicnJ8qWLauTNzk5mZ49e5I/f36MjY2pWrUqhw8ffmH9+/bto1q1apiYmODk5ETPnj25f/++Tp0DBw7EyckJrVaLq6srCxYsACAyMpI8efLo1Ldq1aoXLjN4+PBh/Pz8yJs3L1ZWVvj4+HDs2DGdPBqNhjlz5hAUFISZmRljxozJsj5TU1Ps7e11jnS///47pUqVQqvV4uzszJQpU3TKOjs7M2bMGIKDg7GysqJjx47qM61du5bixYtjampK48aNuX//PlFRUTg7O2NtbU2PHj1ITU3ViXnVqlU69efJk4fIyMhM405NTaVDhw64uLhgYmJC8eLFmTFjRpbPCU//LpKSknQOIYQQQny8pJP+nmvXrh0RERHq+cKFC2nfvn2GfAMHDuT3338nKiqKY8eOUaxYMfz9/UlISMi03lOnTuHv70/Dhg05efIkS5cuZe/evXTv3l3N06ZNG5YsWcJ3331HTEwMc+bMwdzc/LWf5e7du7Rt25Y9e/Zw4MABXF1dCQgI4O7duzr5hg8fTlBQEKdOncr0WV/m6NGjNGnShGbNmnHq1ClGjBhBWFhYhk7zpEmTKF26NEePHlWnpDx48IDvvvuOJUuWsHHjRnbu3EnDhg1Zv34969ev5+eff2bevHksX778tdshLS0NR0dHli1bxtmzZxk2bBjffvsty5Yty7JMeHg4VlZW6uHk5PTa9xdCCCHEB0AR76W2bdsqQUFBys2bNxWtVqtcunRJiYuLU4yNjZWbN28qQUFBStu2bRVFUZR79+4phoaGyqJFi9Tyjx8/VgoUKKBMnDhRURRF2bFjhwIot2/fVhRFUVq3bq106tRJ55579uxR9PT0lIcPHyrnz59XAGXLli2ZxhcREaFYWVnppK1cuVJ59kdq+PDhSpkyZbJ8xpSUFMXCwkJZs2aNmgYovXv3flnzKD4+PoqhoaFiZmamHn379lUURVFatGih+Pn56eQfMGCAUrJkSfW8cOHCSoMGDTI8E6BcuHBBTQsJCVFMTU2Vu3fvqmn+/v5KSEiITswrV67UqcvKykqJiIhQFEVRLl26pADK8ePHs3yerl27Ko0aNcry+qNHj5TExET1uHr1qgIoCQkJWZYRb09KSooSExOjpKSk5HYonxxp+9wjbZ+7pP1zT062fWJiogIoiYmJL80rSzC+5/LmzUu9evWIiopCURTq1atH3rx5dfJcvHiRJ0+eUKVKFTXN0NCQChUqEBMTk2m9R48e5cKFC+pOmQCKopCWlsalS5c4deoU+vr6+Pj45Niz3Lhxg2HDhrF9+3b+/fdfUlNTefDgAVeuXNHJV65cuWzV17JlS4YMGaKep0+/iYmJISgoSCdvlSpVmD59Oqmpqeoap5ndx9TUlKJFi6rndnZ2ODs763yDYGdnx40bN7IVY1bmzJnDjz/+yOXLl3n48CGPHz9+4Uo4Wq0WrVb7RvcUQgghxIdDOukfgPbt26vTUGbOnJnhuvL/96N6fj64oihZzhFPS0sjJCSEnj17ZrhWqFAhLly48MKY9PT01Pume9FLnvB0xZqbN28yffp0ChcujFarpVKlShle2jQzM3thPemsrKwoVqxYhvTMnvv5WLO6j6Ghoc65RqPJNC0tLU3n/FXaYtmyZfTp04cpU6ZQqVIlLCwsmDRpEgcPHsyyjBBCCCE+LdJJ/wDUqVNH7cj6+/tnuF6sWDGMjIzYu3cvLVq0AJ52Eo8cOULv3r0zrdPb25szZ85k2skF8PDwIC0tjV27dlGrVq0M1/Ply8fdu3e5f/++2tl92Trge/bsYdasWQQEBABw9epV/vvvvxeWeR0lS5Zk7969Omn79u3Dzc3trezSli9fPuLj49Xz2NhYHjx4kGX+PXv2ULlyZbp27aqmXbx4McfjEkIIIcSHS14c/QDo6+sTExNDTExMpp1MMzMzunTpwoABA9i4cSNnz56lY8eOPHjwgA4dOmRa56BBg9i/fz/dunUjOjqa2NhYVq9eTY8ePYCnq5+0bduW9u3bs2rVKi5dusTOnTvVlxs///xzTE1N+fbbb7lw4QK//vprlquZpCtWrBg///wzMTExHDx4kJYtW76VXTj79evHtm3bGD16NH/99RdRUVH88MMP9O/fP8fvBVCjRg1++OEHjh07xpEjR+jcuXOG0fdnFStWjCNHjrBp0yb++usvwsLCXroSjxBCCCE+LdJJ/0BYWlpiaWmZ5fXx48fTqFEjWrdujbe3NxcuXGDTpk1YW1tnmt/T05Ndu3YRGxvLF198QdmyZQkLC8PBwUHNM3v2bBo3bkzXrl1xd3enY8eO6hKNNjY2/PLLL6xfvx4PDw8WL17MiBEjXvgMCxcu5Pbt25QtW5bWrVurS0bmNG9vb5YtW8aSJUsoXbo0w4YNY9SoUW9t86cpU6bg5OREtWrVaNGiBf3798fU1DTL/J07d6Zhw4Y0bdqUzz//nFu3bumMqgshhBBCaJTMJusKId5rSUlJWFlZkZCQkOUHMfH2pKamEhsbi6ur61uZQiWyJm2fe6Ttc5e0f+7JybZP//2dmJj4wsFXkJF0IXTs3LkTjUbDnTt3cjsUIYQQQnzCpJMu3ivBwcFoNBp1VRU7Ozv8/PxYuHChzooqL5PZjqhCCCGEEB8K6aSL906dOnWIj48nLi6ODRs24OvrS69evQgMDCQlJSW3wxNCCCGEeOukky7eO1qtFnt7ewoWLIi3tzfffvstf/zxBxs2bFBXkJk6dSoeHh6YmZnh5ORE165duXfvHvB0ykq7du1ITExUR+XTX2r95ZdfKFeuHBYWFtjb29OiRYtMNyb6888/KVOmDMbGxnz++eecOnVKvXbr1i2aN2+Oo6Mjpqam6ouzz1q+fDkeHh6YmJhga2tLrVq11JduASIiIihRogTGxsa4u7sza9asHG5FIYQQQnzIpJMuPgg1atSgTJkyrFixAni6mdJ3333H6dOniYqKYvv27QwcOBCAypUrM336dCwtLYmPjyc+Pl5dfvHx48eMHj2aEydOqEtLZrbqy4ABA5g8eTKHDx8mf/78fPnll+oGRY8ePeKzzz5j7dq1nD59mk6dOtG6dWt1M6L4+HiaN29O+/btiYmJYefOnTRs2FDd8Gj+/PkMGTKEsWPHEhMTw7hx4wgLCyMqKirL509OTiYpKUnnEEIIIcRHTBHiPdK2bVslKCgo02tNmzZVSpQokem1ZcuWKba2tup5RESEYmVl9dL7HTp0SAGUu3fvKoqiKDt27FAAZcmSJWqeW7duKSYmJsrSpUuzrCcgIEDp16+foiiKcvToUQVQ4uLiMs3r5OSk/Prrrzppo0ePVipVqpRl/cOHD1eADEdCQsJLn1HkvJSUFCUmJkZJSUnJ7VA+OdL2uUfaPndJ++eenGz7xMREBVASExNfmldG0sUHQ1EUNBoNADt27MDPz4+CBQtiYWFBmzZtuHXrls6UkswcP36coKAgChcujIWFBdWrVwfgypUrOvkqVaqk/tnGxobixYsTExMDPF2KaezYsXh6emJra4u5uTmbN29W6yhTpgw1a9bEw8ODr7/+mvnz53P79m0Abt68ydWrV+nQoQPm5ubqMWbMmBfuOhoaGkpiYqJ6XL169dUaTwghhBAfFOmkiw9GTEwMLi4uXL58mYCAAEqXLs3vv//O0aNHmTlzJoA6JSUz9+/fp3bt2pibm/PLL79w+PBhVq5cCTydBvMy6R8QpkyZwrRp0xg4cCDbt28nOjoaf39/tQ59fX22bNnChg0bKFmyJN9//z3Fixfn0qVL6go18+fPJzo6Wj1Onz7NgQMHsry3VqtVN7R62cZWQgghhPjwGeR2AEJkx/bt2zl16hR9+vThyJEjpKSkMGXKFPT0nn7OXLZsmU5+IyMjUlNTddLOnTvHf//9x/jx43FycgLgyJEjmd7vwIEDFCpUCIDbt2/z119/4e7uDsCePXsICgqiVatWAKSlpREbG0uJEiXU8hqNhipVqlClShWGDRtG4cKFWblyJX379qVgwYL8/ffftGzZMgdaRgghhBAfI+mki/dOcnIy169fJzU1lX///ZeNGzcSHh5OYGAgbdq04dSpU6SkpPD9999Tv359/vzzT+bMmaNTh7OzM/fu3WPbtm2UKVMGU1NTChUqhJGREd9//z2dO3fm9OnTjB49OtMYRo0aha2tLXZ2dgwZMoS8efPSoEEDAIoVK8bvv//Ovn37sLa2ZurUqVy/fl3tpB88eJBt27ZRu3Zt8ufPz8GDB7l586Z6fcSIEfTs2RNLS0vq1q1LcnIyR44c4fbt2/Tt2/ftNawQQgghPhgy3UW8dzZu3IiDgwPOzs7UqVOHHTt28N133/HHH3+gr6+Pl5cXU6dOZcKECZQuXZpFixYRHh6uU0flypXp3LkzTZs2JV++fEycOJF8+fIRGRnJb7/9RsmSJRk/fjyTJ0/ONIbx48fTq1cvPvvsM+Lj41m9ejVGRkYAhIWF4e3tjb+/P9WrV8fe3l7twANYWlqye/duAgICcHNzY+jQoUyZMoW6desC8M033/Djjz8SGRmJh4cHPj4+REZG4uLi8nYaVAghhBAfHI2i/P914YQQH4ykpCSsrKxISEjA2to6t8P55KSmphIbG4urqyv6+vq5Hc4nRdo+90jb5y5p/9yTk22f/vs7MTHxpe+XyUi6EEIIIYQQ7xnppIt37vr16/To0YMiRYqg1WpxcnKifv36bNu2LbdDeyt27tyJRqPhzp07uR2KEEIIIT4Q8uKoeKfi4uKoUqUKefLkYeLEiXh6evLkyRM2bdpEt27dOHfuXG6H+EHxHr0Fxcgst8P45OhrFPwKprEl6gKpiia3w/mkSNvnHmn73PUm7R83vt5bikq8TTKSLt6prl27otFoOHToEI0bN8bNzY1SpUrRt29fdZ3wK1euEBQUhLm5OZaWljRp0oR///1XrWPEiBF4eXmxcOFCChUqhLm5OV26dCE1NZWJEydib29P/vz5GTt2rM69NRoNc+fOJTAwEFNTU0qUKMH+/fu5cOEC1atXx8zMjEqVKmXYVGjNmjV89tlnGBsbU6RIEUaOHElKSopOvT/++CNfffUVpqamuLq6snr1auDphxJfX18ArK2t0Wg0BAcHA7B8+XI8PDwwMTHB1taWWrVqvXQzJiGEEEJ8GqSTLt6ZhIQENm7cSLdu3TAzyzj6mydPHhRFoUGDBiQkJLBr1y62bNnCxYsXadq0qU7eixcvsmHDBjZu3MjixYtZuHAh9erV43//+x+7du1iwoQJDB06NMMGQaNHj6ZNmzZER0fj7u5OixYtCAkJITQ0VF0zvXv37mr+TZs20apVK3r27MnZs2eZO3cukZGRGT4AjBw5kiZNmnDy5EkCAgJo2bIlCQkJODk58fvvvwNw/vx54uPjmTFjBvHx8TRv3pz27dsTExPDzp07adiwIVm9x52cnExSUpLOIYQQQoiPl0x3Ee/MhQsXUBRF3RQoM1u3buXkyZNcunRJ3XDo559/plSpUhw+fJjy5csDTzcQWrhwIRYWFpQsWRJfX1/Onz/P+vXr0dPTo3jx4kyYMIGdO3dSsWJFtf527drRpEkTAAYNGkSlSpUICwvD398fgF69etGuXTs1/9ixYxk8eDBt27YFoEiRIowePZqBAwcyfPhwNV9wcDDNmzcHYNy4cXz//fccOnSIOnXqYGNjA0D+/PnJkycP8PRDRkpKCg0bNqRw4cIAeHh4ZNku4eHhjBw5MhutLIQQQoiPgYyki3cmfZRYo8l6Ll1MTAxOTk5qBx2gZMmS5MmTh5iYGDXN2dkZCwsL9dzOzo6SJUuqO5Cmp924cUOnfk9PT53roNs5trOz49GjR+pI9dGjRxk1ahTm5ubq0bFjR+Lj43nw4EGm9ZqZmWFhYZHh3s8qU6YMNWvWxMPDg6+//pr58+dz+/btLPOHhoaSmJioHlevXs0yrxBCCCE+fNJJF++Mq6srGo1Gp7P9PEVRMu3EP59uaGioc12j0WSalpaWppP2bJ70+jJLSy+XlpbGyJEjiY6OVo9Tp04RGxuLsbHxC+N5/t7P0tfXZ8uWLWzYsIGSJUvy/fffU7x4cS5dupRpfq1Wi6Wlpc4hhBBCiI+XTHcR74yNjQ3+/v7MnDmTnj17ZpiXfufOHUqWLMmVK1e4evWqOpp+9uxZEhMTKVGixDuP2dvbm/Pnz1OsWLHXriN9p9LU1FSddI1GQ5UqVahSpQrDhg2jcOHCrFy5kr59+2a77mNhfrKZUS5I39hipmwq8s5J2+ceafvcJe3/6ZFOuninZs2aReXKlalQoQKjRo3C09OTlJQUtmzZwuzZszl79iyenp60bNmS6dOnk5KSQteuXfHx8aFcuXLvPN5hw4YRGBiIk5MTX3/9NXp6epw8eZJTp04xZsyYbNVRuHBhNBoNa9euJSAgABMTE86cOcO2bduoXbs2+fPn5+DBg9y8eTNXPogIIYQQ4v0j013EO+Xi4sKxY8fw9fWlX79+lC5dGj8/P7Zt28bs2bPRaDSsWrUKa2trqlWrRq1atShSpAhLly7NlXj9/f1Zu3YtW7ZsoXz58lSsWJGpU6eqL3tmR8GCBRk5ciSDBw/Gzs6O7t27Y2lpye7duwkICMDNzY2hQ4cyZcoU6tat+xafRgghhBAfCo2S1ZpvQoj3VlJSElZWViQkJMh0l1yQ/rWzq3zt/M5J2+ceafvcJe2fe3Ky7dN/fycmJr70/TIZSRdCCCGEEOI9I5108cFLnyKTHem7lQohhBBCvM+kky5yxb59+9DX16dOnTrZLpNVBzs+Pv6dzuUODg5Go9Goyz7a2dnh5+fHwoULM112cd++fQQEBGBtbY2xsTEeHh5MmTIl09VesvthQwghhBAfN+mki1yxcOFCevTowd69e7ly5coL8yqKQkpKSpbX7e3t0Wq1OR3iC9WpU4f4+Hji4uLYsGEDvr6+9OrVi8DAQJ1YV65ciY+PD46OjuzYsYNz587Rq1cvxo4dS7NmzZBXQoQQQgiRGemki3fu/v37LFu2jC5duhAYGEhkZKTO9Z07d6LRaNi0aRPlypVDq9Xy888/M3LkSE6cOKGOYqeXe34E+n//+x/NmjXDxsYGMzMzypUrx8GDB7OMJyIighIlSmBsbIy7uzuzZs166TNotVrs7e0pWLAg3t7efPvtt/zxxx9s2LBBjev+/ft07NiRL7/8knnz5uHl5YWzszPffPMNUVFRLF++nGXLlmWrzZKTk0lKStI5hBBCCPHxkk66eOeWLl1K8eLFKV68OK1atSIiIiLTEeWBAwcSHh5OTEwMtWvXpl+/fpQqVYr4+Hji4+Np2rRphjL37t3Dx8eHa9eusXr1ak6cOMHAgQOz3P1z/vz5DBkyhLFjxxITE8O4ceMICwsjKirqlZ+rRo0alClThhUrVgCwefNmbt26Rf/+/TPkrV+/Pm5ubixevDhbdYeHh2NlZaUe6Rs9CSGEEOLjJJsZiXduwYIFtGrVCng6beTevXts27aNWrVq6eQbNWoUfn5+6rm5uTkGBgbY29tnWfevv/7KzZs3OXz4MDY2NgAv3C109OjRTJkyhYYNGwJP13E/e/Ysc+fOpW3btq/8bO7u7pw8eRKAv/76CyDLDYrc3d3VPC8TGhqqsxNpUlKSdNSFEEKIj5h00sU7df78eQ4dOqSONhsYGNC0aVMWLlyYoZP+OjuMRkdHU7ZsWbWD/iI3b97k6tWrdOjQgY4dO6rpKSkpWFlZvfK94en8eY1GkyEtu3mzotVq3/m8eyGEEELkHumki3dqwYIFpKSkULBgQTVNURQMDQ25ffu2zsY8ZmZmr1y/iYlJtvOmT4GZP38+n3/+uc61192sICYmBhcXFwDc3NzUtMqVK2fIe+7cOUqWLPla9xFCCCHEx03mpIt3JiUlhZ9++okpU6YQHR2tHidOnKBw4cIsWrToheWNjIwyLFv4PE9PT6Kjo0lISHhpPHZ2dhQsWJC///6bYsWK6RzpHe1XsX37dk6dOkWjRo0AqF27NjY2NkyZMiVD3tWrVxMbG0vz5s1f+T5CCCGE+PjJSLp4Z9auXcvt27fp0KFDhukkjRs3ZsGCBXTv3j3L8s7Ozly6dIno6GgcHR2xsLDIMAWkefPmjBs3jgYNGhAeHo6DgwPHjx+nQIECVKpUKUOdI0aMoGfPnlhaWlK3bl2Sk5M5cuQIt2/f1pkD/rzk5GSuX79Oamoq//77Lxs3biQ8PJzAwEDatGkDPP0mYO7cuTRr1oxOnTrRvXt3LC0t2bZtGwMGDKBx48Y0adLkVZpQCCGEEJ8IGUkX78yCBQuoVatWpvO9GzVqRHR0NMeOHcuyfKNGjahTpw6+vr7ky5cv05VRjIyM2Lx5M/nz5ycgIAAPDw/Gjx+f5fSVb775hh9//JHIyEg8PDzw8fEhMjLypSPpGzduxMHBAWdnZ+rUqcOOHTv47rvv+OOPP3Tu1bhxY3bs2MHVq1epVq0axYsXZ+rUqQwZMoQlS5Zke066EEIIIT4tGkV2UxHig5OUlISVlRUJCQk68/jFu5GamkpsbCyurq6v/f6CeD3S9rlH2j53Sfvnnpxs+/Tf34mJiVhaWr4wr4ykC/EGIiMjyZMnT26HIYQQQoiPjHTSxSdn37596OvrU6dOnVcq5+zszPTp03XSmjZtmu21zoUQQgghskteHBWfnIULF9KjRw9+/PFHrly5QqFChV67LhMTk1da9jGneY/egmL06ktVijejr1HwK5jGlqgLpCryXsG79CG2fdz4erkdghDiAyQj6eKTcv/+fZYtW0aXLl0IDAwkMjJS5/rq1aspV64cxsbG5M2bV92JtHr16ly+fJk+ffqg0WjUFz6fne5y/vx5NBoN586d06lz6tSpODs7q5sanT17loCAAMzNzbGzs6N169b8999/b/fBhRBCCPFBkU66+KQsXbqU4sWLU7x4cVq1akVERITaeV63bh0NGzakXr16HD9+nG3btqm7nq5YsQJHR0dGjRpFfHw88fHxGeouXrw4n332WYb13n/99VdatGiBRqMhPj4eHx8fvLy8OHLkCBs3buTff/996VKMycnJJCUl6RxCCCGE+HjJdBfxSVmwYAGtWrUCoE6dOty7d49t27ZRq1Ytxo4dS7NmzRg5cqSav0yZMgDY2Nigr6+PhYUF9vb2WdbfsmVLfvjhB0aPHg3AX3/9xdGjR/npp58AmD17Nt7e3owbN04ts3DhQpycnPjrr7/UXUqfFx4erhOXEEIIIT5uMpIuPhnnz5/n0KFDNGvWDAADAwOaNm3KwoULAYiOjqZmzZpvdI9mzZpx+fJlDhw4AMCiRYvw8vKiZMmSABw9epQdO3Zgbm6uHu7u7gBcvHgxy3pDQ0NJTExUj6tXr75RnEIIIYR4v8lIuvhkLFiwgJSUFAoWLKimKYqCoaEht2/fzpEXQB0cHPD19eXXX3+lYsWKLF68mJCQEPV6Wloa9evXZ8KECZmWzYpWq82wu6oQQgghPl7SSRefhJSUFH766SemTJlC7dq1da41atSIRYsW4enpybZt22jXrl2mdRgZGZGamvrSe7Vs2ZJBgwbRvHlzLl68qI7cA3h7e/P777/j7OyMgcGb//M7FuYnmxnlgvSNLWbKpiLvnLS9EOJTIdNdxCdh7dq13L59mw4dOlC6dGmdo3HjxixYsIDhw4ezePFihg8fTkxMDKdOnWLixIlqHc7OzuzevZt//vnnhauxNGzYkKSkJLp06YKvr6/OyH23bt1ISEigefPmHDp0iL///pvNmzfTvn37bH0AEEIIIcSnQTrp4pOwYMECatWqhZWVVYZrjRo1Ijo6GktLS3777TdWr16Nl5cXNWrU4ODBg2q+UaNGERcXR9GiRcmXL1+W97K0tKR+/fqcOHGCli1b6lwrUKAAf/75J6mpqfj7+1O6dGl69eqFlZUVenryz1EIIYQQT2mU9PXnhBAfjKSkJKysrEhISJDpLrkgfcqFq0y5eOek7XOPtH3ukvbPPTnZ9um/vxMTE7G0tHxhXhm6E0IIIYQQ4j0jnXQh3kBYWBidOnV6ozr69+9Pz549cygiIYQQQnwMZLqLyHXBwcFERUUBT9cut7GxwdPTk+bNmxMcHPzeztX+999/cXV15eTJkzg7OwNP10UfPHgw9+/fp0OHDkyaNEnNHxcXR+3atTly5IjOV1w3btygaNGinDx5EhcXl2zdO/3rMuc+S1GMzHL0ucTL6WsU/AqmseUfPVIVTW6H80mRts89r9L2cePrvaOoPh0y3SX3yHQX8UmrU6cO8fHxxMXFsWHDBnx9fenVqxeBgYGkpKTkdniZWrBgAZUqVVI76P/99x/ffPMNkydPZtOmTURFRbFu3To1f5cuXRg/fnyGf5T58+endu3azJkz512GL4QQQoj3mHTSxXtBq9Vib29PwYIF8fb25ttvv+WPP/5gw4YNREZGqvk0Gg1z584lMDAQU1NTSpQowf79+7lw4QLVq1fHzMyMSpUq6ezeefHiRYKCgrCzs8Pc3Jzy5cuzdetW9fq5c+cwNTXl119/VdNWrFiBsbExp06dyjLmJUuW8OWXX6rnf//9N1ZWVjRt2pTy5cvj6+vL2bNnAfj1118xMjKiYcOGmdb15Zdfsnjx4izvlZycTFJSks4hhBBCiI+XdNLFe6tGjRqUKVOGFStW6KSPHj2aNm3aEB0djbu7Oy1atCAkJITQ0FCOHDkCQPfu3dX89+7dIyAggK1bt3L8+HH8/f2pX78+V65cAcDd3Z3JkyfTtWtXLl++zLVr1+jYsSPjx4/Hw8Mj09hu377N6dOnKVeunJrm6urKgwcPOH78OAkJCRw+fBhPT08SEhIYNmwYP/zwQ5bPWqFCBa5evcrly5czvR4eHo6VlZV6ODk5Za8RhRBCCPFBkk66eK+5u7sTFxenk9auXTuaNGmCm5sbgwYNIi4ujpYtW+Lv70+JEiXo1asXO3fuVPOXKVOGkJAQPDw8cHV1ZcyYMRQpUoTVq1erebp27UrVqlVp3bo1bdq04bPPPqNXr15ZxnX58mUURaFAgQJqmrW1NVFRUbRp04YKFSrQpk0b/P396d+/Pz169ODSpUuULVuW0qVLs3z5cp360jc8ev5Z04WGhpKYmKgeV69ezWYLCiGEEOJD9Ob7kgvxFimKgkaj+4KSp6en+mc7OzsAnRFvOzs7Hj16RFJSEpaWlty/f5+RI0eydu1arl27RkpKCg8fPlRH0tMtXLgQNzc39PT0OH36dIb7Puvhw4cAGBsb66R/9dVXfPXVV+r5zp07OXXqFD/88APFihVj8eLF2NvbU6FCBapVq0b+/PkBMDExAeDBgweZ3k+r1aLVarOMRwghhBAfF+mki/daTExMhhVPDA0N1T+nd6QzS0tLSwNgwIABbNq0icmTJ1OsWDFMTExo3Lgxjx8/1qn3xIkT3L9/Hz09Pa5fv64zSv68vHnzAk+nvWS1+2hycjJdu3bll19+4cKFC6SkpODj4wOAm5sbBw8epH79+gAkJCQAvHAn08wcC/OTzYxyQfqb/jNllYV3Tto+90jbC/FuyXQX8d7avn07p06dolGjRm9Uz549ewgODuarr77Cw8MDe3v7DNNKEhISCA4OZsiQIbRr146WLVuqo+WZKVq0KJaWluqLoZkZPXo0devWxdvbm9TUVJ1Vap48eUJqaqp6fvr0aQwNDSlVqtTrP6gQQgghPhoyki7eC8nJyVy/fp3U1FT+/fdfNm7cSHh4OIGBgbRp0+aN6i5WrBgrVqygfv36aDQawsLC1FH2dJ07d8bJyYmhQ4fy+PFjvL296d+/PzNnzsy0Tj09PWrVqsXevXtp0KBBhutnzpxh6dKlREdHA0/n1uvp6bFgwQLs7e05d+4c5cuXV/Pv2bOHL774Qp32IoQQQohPm3TSxXth48aNODg4YGBggLW1NWXKlOG7776jbdu2b7yZ0bRp02jfvj2VK1cmb968DBo0SGcJw59++on169dz/PhxDAwMMDAwYNGiRVSuXJl69eoREBCQab2dOnWiQ4cOTJw4USdGRVHo1KkT06ZNw8zs6UZDJiYmREZG0q1bN5KTk/nhhx/Ul0UBFi9ezMiRI9/oOYUQQgjx8ZAdR4V4TYqiULFiRXr37k3z5s1fu55169YxYMAATp48iYFB9j43p+9YlpCQIHPSc4Hs/Jd7pO1zj7R97pL2zz2y46gQ76EFCxZQu3btTK9pNBrmzZv3xjui9uzZkzZt2mS7gy6EEEKIj5/0CsQ7FRwcTFRUFAAGBgbY2Njg6elJ8+bNCQ4OzjC15fjx44wbN47du3eTmJhIoUKF8PHxYcCAAbi5uQFkulTi7Nmz6dy5s3p+6tQpunfvzqFDh7CxsSEkJISwsLAXLrOYnJzMsGHDWLJkSZZ5ypQpQ5kyZXTSqlevzq5duwgPD2fw4ME61wICAtiwYQPDhw9nxIgRwNPpOP3792fgwIGvPLXHe/QWFCOzVyoj3py+RsGvYBpboi6QqmT9MySyFje+Xm6HIIQQ7zUZSRfvXJ06dYiPjycuLo4NGzbg6+tLr169CAwM1BmVXrt2LRUrViQ5OZlFixYRExPDzz//jJWVFWFhYTp1RkREEB8frx5t27ZVryUlJeHn50eBAgU4fPgw33//PZMnT2bq1KkvjPP333/H3NycL7744pWf0cnJiYiICJ20a9eusX37dhwcHHTS69WrR2JiIps2bXrl+wghhBDi4yQj6eKd02q12NvbA0932vT29qZixYrUrFmTyMhIvvnmGx48eEC7du0ICAhg5cqValkXFxc+//xz7ty5o1Nnnjx51Dqft2jRIh49ekRkZCRarZbSpUvz119/MXXqVPr27ZvlaPqSJUv48ssvddKCg4O5c+cOVatWZcqUKTx+/JhmzZoxffp0nbXaAwMDWbZsGX/++SdVqlQBIDIyktq1a2fYRElfX5+AgAAWL15M3bp1M40lOTmZ5ORk9fzZF1+FEEII8fGRkXTxXqhRowZlypRhxYoVAGzatIn//vuPgQMHZpo/T548Oufdu3cnb968lC9fnjlz5ugssbh//358fHx0duz09/fn2rVrGdZLf9aePXsoV65chvQdO3Zw8eJFduzYQVRUFJGRkURGRurkMTIyomXLljqj6ZGRkbRv3z7Te1WoUIE9e/ZkGUt4eDhWVlbq4eTklGVeIYQQQnz4pJMu3hvu7u5qpzk2NlZNe5nRo0fz22+/sXXrVpo1a0a/fv0YN26cev369evY2dnplEk/v379eqZ13rlzhzt37mS666i1tTU//PAD7u7uBAYGUq9ePbZt25YhX4cOHVi2bBn3799X59TXq5f5PNyCBQty5cqVDOu3pwsNDSUxMVE9rl69mnljCCGEEOKjINNdxHtDURR16smrrAw6dOhQ9c9eXl4AjBo1Sif9+Skt6fVnNdUlfbdRY2PjDNdKlSqlswSTg4MDp06dypDP09MTV1dXli9fzo4dO2jdurXOlJhnmZiYkJaWRnJycqYbGmm1Wp1vAoQQQgjxcZNOunhvxMTE4OLiAqCu3HLu3DkqVar0SvVUrFiRpKQk/v33X+zs7LC3t88wYn7jxg2ADCPs6WxtbdFoNNy+fTvDtec72hqNJssR8Pbt2zNz5kzOnj3LoUOHsow5ISEBU1PTV95x9FiYn6yTngvS18ydKesVCyGEeEtkuot4L2zfvp1Tp07RqFEjAGrXrk3evHmZOHFipvmff3H0WcePH8fY2Fidt16pUiV2797N48eP1TybN2+mQIECODs7Z1qHkZERJUuW5OzZs6/1POlatGjBqVOnKF26NCVLlswy3+nTp/H29n6jewkhhBDi4yGddPHOJScnc/36df755x+OHTvGuHHjCAoKIjAwkDZt2gBgZmbGjz/+yLp16/jyyy/ZunUrcXFxHDlyhIEDB6proK9Zs4b58+dz+vRpLl68yI8//siQIUPo1KmTOj2kRYsWaLVagoODOX36NCtXrmTcuHEvXNkFnr5cunfv3jd6Vmtra+Lj4zOds/6sPXv2ZLlpkhBCCCE+PTLdRbxzGzduxMHBAQMDA6ytrSlTpgzfffcdbdu21dnMJygoiH379hEeHk6LFi1ISkrCycmJGjVqMGbMGODp1JNZs2bRt29f0tLSKFKkCKNGjaJbt25qPVZWVmzZsoVu3bpRrlw5rK2t6du3L3379n1hnB07dsTb25vExESsrKxe+3mfX4nmef/88w/79u3jl19+ee17CCGEEOLjolFe5Q09IT4xTZo0oWzZsoSGhr61ewwYMIDExETmzZuX7TJJSUlYWVmRkJAgc9JzQfqcdFeZk/7OSdvnHmn73CXtn3tysu3Tf38nJiZiaWn5wrwy3UV8VOLi4tBoNERHR+dIfZMmTcLc3Dzb+c+fP4+9vT13794Fnq6N/rKR9EOHDmX54qkQQgghPk3SSc9lGo3mhUdwcPBbue+IESPU5QrfBzt37kSj0bzwhdDg4OCXtpeTkxPx8fGULl06R+IqXLgwPXr0yHb+IUOG0K1bNywsLLJd5rfffmPp0qVcunTpdUIUQgghxEdI5qTnsvj4ePXPS5cuZdiwYZw/f15Ne35JvidPnmS51vbHbsaMGYwfP149d3BwICIigjp16qhp+vr62Nvb50Z4/O9//2P16tVMnz79lcrlz5+f2rVrM2fOHCZMmPBKZb1Hb0ExMnulMu+juPGZb/IkhBBCfKpkJD2X2dvbq4eVlRUajUY9f/ToEXny5GHZsmVUr14dY2Nj9eXCiIgISpQogbGxMe7u7syaNUun3kGDBuHm5oapqSlFihQhLCyMJ0+eAE+nYIwcOZITJ06oI9Dp29prNBrmzp1LYGAgpqamlChRgv3793PhwgWqV6+OmZkZlSpV4uLFizr3W7NmDZ999hnGxsYUKVKEkSNHkpKSol7XaDT8+OOPfPXVV5iamuLq6srq1auBp1NUfH19gaeroWT1DYKVlZVOe8HTlzKfTXt+ukv6CP2mTZsoW7YsJiYm1KhRgxs3brBhwwZKlCiBpaUlzZs358GDB+q9FEVh4sSJFClSBBMTE8qUKcPy5ctf+He5bNkyypQpg6OjY4ZrmzZtokSJEpibm1OnTh2dD2cAX375JYsXL35h/UIIIYT4dEgn/QMwaNAgevbsSUxMDP7+/syfP58hQ4YwduxYYmJiGDduHGFhYURFRallLCwsiIyM5OzZs8yYMYP58+czbdo0AJo2bUq/fv0oVaoU8fHxxMfH07RpU7Xs6NGjadOmDdHR0bi7u9OiRQtCQkIIDQ3lyJEjAHTv3l3Nv2nTJlq1akXPnj05e/Ysc+fOJTIykrFjx+o8x8iRI2nSpAknT54kICCAli1bkpCQgJOTE7///jvwdE53fHw8M2bMyNE2HDFiBD/88AP79u3j6tWrNGnShOnTp/Prr7+ybt06tmzZwvfff6/mHzp0KBEREcyePZszZ87Qp08fWrVqxa5du7K8x+7duylXrlyG9AcPHjB58mR+/vlndu/ezZUrV+jfv79OngoVKnD16lUuX76cad3JyckkJSXpHEIIIYT4eEkn/QPQu3dvGjZsiIuLCwUKFGD06NFMmTJFTWvYsCF9+vRh7ty5apmhQ4dSuXJlnJ2dqV+/Pv369WPZsmXA0yk05ubmGBgYqCPQz06radeuHU2aNMHNzY1BgwYRFxdHy5Yt8ff3p0SJEvTq1YudO3eq+ceOHcvgwYNp27YtRYoUwc/Pj9GjR+vEA0/nlDdv3pxixYoxbtw47t+/z6FDh9DX18fGxgZ4OvUj/VuFnDRmzBiqVKlC2bJl6dChA7t27WL27NmULVuWL774gsaNG7Njxw4A7t+/z9SpU1m4cCH+/v4UKVKE4OBgWrVqleGZnhUXF0eBAgUypD958oQ5c+ZQrlw5vL296d69e4Z10wsWLKjWkZnw8HCsrKzUw8nJ6TVbQgghhBAfApmT/gF4dnT25s2bXL16lQ4dOtCxY0c1PSUlRadju3z5cqZPn86FCxe4d+8eKSkpL13qJ52np6f6Zzs7OwA8PDx00h49ekRSUhKWlpYcPXqUw4cP64ycp6am8ujRIx48eICpqWmGes3MzLCwsODGjRvZbYY38vwzpU8Dejbt0KFDAJw9e5ZHjx7h5+enU8fjx48pW7Zslvd4+PAhxsbGGdJNTU0pWrSoeu7g4JDhudM/JD075eZZoaGhOuu6p68ZL4QQQoiPk3TSPwBmZv/3YmD6Un3z58/n888/18mXvnbngQMHaNasGSNHjsTf3x8rKyuWLFnClClTsnW/Z19MTd+RM7O09FjS0tIYOXIkDRs2zFDXs53W51941Wg072zpwefjf1Es6f9dt26dOsKdLn0X08zkzZuX27dvv/De6fd6fnuChIQEAPLly5dp3Vqt9oX3FkIIIcTHRTrpHxg7OzsKFizI33//TcuWLTPN8+eff1K4cGGGDBmipj0/19nIyIjU1NQcicnb25vz589TrFix167DyMgIIMdiehMlS5ZEq9Vy5coVfHx8sl2ubNmynD179rXuefr0aQwNDSlVqtQrlTsW5iebGQkhhBAfIemkf4BGjBhBz549sbS0pG7duiQnJ3PkyBFu375N3759KVasGFeuXGHJkiWUL1+edevWsXLlSp06nJ2duXTpEtHR0Tg6OmJhYfHaI7XDhg0jMDAQJycnvv76a/T09Dh58iSnTp1izJgx2aqjcOHCaDQa1q5dS0BAgDpvPjdYWFjQv39/+vTpQ1paGlWrViUpKYl9+/Zhbm5O27ZtMy3n7+/PN998Q2pq6ivvSLZnzx6++OKLDEtuCiGEEOLTJC+OfoC++eYbfvzxRyIjI/Hw8MDHx4fIyEhcXFwACAoKok+fPnTv3h0vLy/27dtHWFiYTh2NGjWiTp06+Pr6ki9fvjda/s/f35+1a9eyZcsWypcvT8WKFZk6dSqFCxfOdh0FCxZk5MiRDB48GDs7O53VY3LD6NGjGTZsGOHh4ZQoUQJ/f3/WrFmjtnFmAgICMDQ0ZOvWra98v8WLF+u8YyCEEEKIT5tGeX5yrBDitc2aNYs//viDTZs2ZbvMunXrGDBgACdPnsTAIHtfbiUlJWFlZUVCQoJMd8kFqampxMbG4urq+srfmog3I22fe6Ttc5e0f+7JybZP//2dmJj40gU9ZCRdfBJGjBiBl5eXeh4cHEyDBg1y/D6dOnWiWrVq3L17N9tl7t+/T0RERLY76EIIIYT4+EknXbz3rl+/To8ePShSpAharRYnJyfq16+fYa3xnBIcHKzuxJrVkRUDAwOGDBmChYVFtu/XpEmTDCv1CCGEEOLTJkN34r0WFxdHlSpVyJMnDxMnTsTT05MnT56wadMmunXrxrlz53L8njNmzGD8+PHquYODAxEREdSpUyfH7/WmvEdvQTEye3nGbIgbXy9H6hFCCCHEm5ORdPFe69q1KxqNhkOHDtG4cWPc3NwoVaoUffv25cCBA2q+xMREOnXqRP78+bG0tKRGjRqcOHHite5pZWWl7sRqb28PQJ48ebC3t2fevHkZNjkC+Oyzzxg2bBjwf1NpRo4cqcYTEhLC48eP1fyKojBx4kSKFCmCiYkJZcqUYfny5a8VrxBCCCE+PtJJF++thIQENm7cSLdu3XQ2dEqXJ08e4GmHt169ely/fp3169dz9OhRvL29qVmzprpJUE5p3749Z8+e5fDhw2rayZMnOX78OMHBwWratm3biImJYceOHSxevJiVK1cycuRI9frQoUOJiIhg9uzZnDlzhj59+tCqVSt27dqV6X2Tk5NJSkrSOYQQQgjx8ZJOunhvXbhwAUVRcHd3f2G+HTt2cOrUKX777TfKlSuHq6srkydPJk+ePDk+Ou3o6Ii/vz8RERFqWkREBD4+PhQpUkRNMzIyYuHChZQqVYp69eoxatQovvvuO9LS0rh//z5Tp05l4cKF+Pv7U6RIEYKDg2nVqhVz587N9L7h4eFYWVmph5OTU44+lxBCCCHeL9JJF++t9NVBX/SiJsDRo0e5d+8etra2mJubq8elS5e4ePFijsfVsWNHFi9ezKNHj3jy5AmLFi2iffv2OnnKlCmDqampel6pUiXu3bvH1atXOXv2LI8ePcLPz08n3p9++inLeENDQ0lMTFSPq1ev5vhzCSGEEOL9IS+OiveWq6srGo2GmJiYFy6XmJaWhoODAzt37sxwLX1KTE6qX78+Wq2WlStXotVqSU5OplGjRtkqq9FoSEtLA56uj16wYEGd61nt+qrVal97R1ghhBBCfHikky7eWzY2Nvj7+zNz5kx69uyZYV76nTt3yJMnD97e3ly/fh0DAwOcnZ3felwGBga0bduWiIgItFotzZo10xk1Bzhx4gQPHz7ExMQEgAMHDmBubo6joyPW1tZotVquXLmCj4/PG8VyLMxPNjMSQgghPkLSSRfvtVmzZlG5cmUqVKjAqFGj8PT0JCUlhS1btjB79mxiYmKoVasWlSpVokGDBkyYMIHixYtz7do11q9fT4MGDShXrlyOx/XNN99QokQJAP78888M1x8/fkyHDh0YOnQoly9fZvjw4XTv3h09PT0sLCzo378/ffr0IS0tjapVq5KUlMS+ffswNzenbdu2OR6vEEIIIT4s0kkX7zUXFxeOHTvG2LFj6devH/Hx8eTLl4/PPvuM2bNnA0+nkKxfv54hQ4bQvn17bt68ib29PdWqVcPOzu6txOXq6krlypW5detWphsR1axZE1dXV6pVq0ZycjLNmjVjxIgR6vXRo0eTP39+wsPD+fvvv9VvBL799tu3Eq8QQgghPiwaJf3tPCFEtqWvOhMSEkLfvn11rgUHB3Pnzh1WrVr11u6flJSElZUVCQkJMt0lF6SmphIbG4urqyv6+vq5Hc4nRdo+90jb5y5p/9yTk22f/vs7MTERS0vLF+b9KFd3iYuLQ6PREB0dnduhfLCcnZ2ZPn16bofxXrpx4wZTp07ln3/+oV27drkdjhBCCCE+QrnWSU/flfF5O3fuRKPRcOfOnXce0/skODgYjUajHra2ttSpU4eTJ0/mdmgAjBgxQo3NwMCAvHnzUq1aNaZPn05ycnJuh/dSx48f5+uvv8bOzg5jY2Pc3Nzo2LEjf/3110vL2tnZMX78eObNm/fGo9jy8y6EEEKIzHyUI+kvoygKKSkpuR3GS9WpU4f4+Hji4+PZtm0bBgYGBAYG5nZYqlKlShEfH8+VK1fYsWMHX3/9NeHh4VSuXJm7d+/mdng8efIk0/S1a9dSsWJFkpOTWbRoETExMfz8889YWVkRFhb20noVReHmzZu0aNEi0+uRkZFvdaqLEEIIIT5+73Un/f79+1haWmbYNXLNmjWYmZmpHcFDhw5RtmxZjI2NKVeuHMePH9fJnz5auWnTJsqVK4dWq2XPnj0kJyfTs2dP8ufPj7GxMVWrVtXZ7h1g9erVuLq6YmJigq+vL1FRURlGPvft20e1atUwMTHBycmJnj17cv/+ffW6s7Mz48aNo3379lhYWFCoUCHmzZv30ufXarXY29tjb2+Pl5cXgwYN4urVq9y8eVPNc+rUKWrUqIGJiQm2trZ06tSJe/fuqdfTv7GYPHkyDg4O2Nra0q1bN50O7I0bN6hfvz4mJia4uLiwaNGil8YGT5citLe3p0CBAnh4eNCjRw927drF6dOnmTBhgprv9u3btGnTBmtra0xNTalbty6xsbHq9cjISPLkycOmTZsoUaIE5ubm6geUdGlpaYwaNQpHR0e0Wi1eXl5s3LhRvZ4+xWnZsmVUr14dY2NjfvnllwwxP3jwgHbt2hEQEMDq1aupVasWLi4ufP7550yePFlnx89du3ZRoUIFtFotDg4ODB48WOfDXWZTgry8vHReENVoNPz444989dVXmJqa4urqyurVq9WYfX19AbC2tkaj0RAcHJytthdCCCHEx+297qSbmZnRrFkznS3Y4ek27I0bN8bCwoL79+8TGBhI8eLFOXr0KCNGjKB///6Z1jdw4EDCw8OJiYnB09OTgQMH8vvvvxMVFcWxY8coVqwY/v7+JCQkAE87UY0bN6ZBgwZER0cTEhLCkCFDdOo8deoU/v7+NGzYkJMnT7J06VL27t1L9+7ddfJNmTJF/QDRtWtXunTpwrlz57LdFvfu3WPRokUUK1YMW1tb4GmHs06dOlhbW3P48GF+++03tm7dmuHeO3bs4OLFi+zYsYOoqCgiIyOJjIxUrwcHBxMXF8f27dtZvnw5s2bN4saNG9mO7Vnu7u7UrVuXFStW6NR/5MgRVq9ezf79+1EUhYCAAJ0PCg8ePGDy5Mn8/PPP7N69mytXruj8Pc6YMYMpU6YwefJkTp48ib+/P19++aVOZx9g0KBB9OzZk5iYGPz9/TPEt2nTJv777z8GDhyYafzpmx/9888/BAQEUL58eU6cOMHs2bNZsGABY8aMeeU2GTlyJE2aNOHkyZMEBATQsmVLEhIScHJy4vfffwfg/PnzxMfHM2PGjEzrSE5OJikpSecQQgghxEdMySVt27ZV9PX1FTMzM53D2NhYAZTbt28riqIoBw8eVPT19ZV//vlHURRFuXnzpmJoaKjs3LlTURRFmTt3rmJjY6Pcv39frXv27NkKoBw/flxRFEXZsWOHAiirVq1S89y7d08xNDRUFi1apKY9fvxYKVCggDJx4kRFURRl0KBBSunSpXXiHjJkiE58rVu3Vjp16qSTZ8+ePYqenp7y8OFDRVEUpXDhwkqrVq3U62lpaUr+/PmV2bNnZ7t9AMXBwUE5evSommfevHmKtbW1cu/ePTVt3bp1ip6ennL9+nW1nsKFCyspKSlqnq+//lpp2rSpoiiKcv78eQVQDhw4oF6Pifl/7d15XI3p/z/w12k7nbYjhYoSKglFsiQkJtkzjK2iLCkhDEqDyTrIvoxlLGXJOmKsGfqkkaylLB1kyVqDiZNE27l+f/h1f7t12oijvJ+Px/14ONd93dd93e9zZrrOda5FwgCwFStWlFi/4OBgZmNjI/dcYGAgE4lEjDHG7ty5wwCwc+fOcedfvnzJRCIR27dvH2OMsdDQUAaA3b17l8vz+++/szp16nCvjYyM2IIFC3j3ad26NfPz82OMMfbgwQMGgK1cubLEOjPG2OLFixkAlpGRUWq+X375hTVu3JjJZDJenbS0tFhBQQFj7MP7+nGMbGxsWHBwMPcaAJs5cyb3OisriwkEAnbixAnG2P99Ngs/TyUJDg5mAIodZT0H+TLy8/OZRCLh/XdFvg6KveJQ7BWL4q84lRl7qVTKADCpVFpmXoX2pDs5OSExMZF3bN68mZenTZs2aNq0KbZv3w4A2LFjB0xMTNCpUycAgEQigY2NDW/HR3t7e7n3K7qpzb1795CXlwcHBwcuTVVVFW3atIFEIgHwoXezdevWxepTVHx8PMLCwqClpcUdLi4ukMlkePDgAZfP2tqa+7dAIICBgUGZvdVF43Px4kV069YNPXr0wMOHD3nPXnQnTgcHB8hkMty+fZtLa9q0KW/JIENDQ+7eEokEKioqvNhYWlpyPcqfgjEGgUDAK7/oWuJ6enpo3LgxF2cA0NDQQKNGjeTWMTMzE8+ePeO9V4XPWrQMAGVuXMTKueKoRCKBvb099xyF98vKysKTJ0/KVUahou+9pqYmtLW1K/xLRVBQEKRSKXc8fvy4QtcTQgghpGpR6GZGmpqaMDMz46XJawCNHj0aa9euxfTp0xEaGooRI0ZwjafyNroK71eo8LqijbDC9KJlyztflEwmg4+PD/z9/Yvdz8TEhPu3qqoq75xAIIBMJiuzvkXj06pVK4jFYmzatAnz58+XW7+i5Zfn3iXF4XNIJBI0aNCAV/7HPq67vDp+fG1p71Whou+xPBYWFgCAW7dulfhlrqSyP46VkpJSsTrKm6z6Ke/9x4RCIYRCYYWuIYQQQkjV9U2PSS/k4eGBR48eYfXq1bh58yZv23QrKyskJSXh3bt3XNqFCxfKLNPMzAxqamqIjY3l0vLy8nDlyhVuu3dLS8tiE0mvXLnCe21ra4ubN2/CzMys2KGmpvZJz1sSgUAAJSUl7lmtrKyQmJjIm6R67tw5KCkpcY3RsjRp0gT5+fm857p9+/YnLwl469YtREZGYsCAAVwd8/PzcfHiRS7Pf//9hzt37nBxLouOjg6MjIx47xXwYcJuecso1K1bN+jr6yMkJETu+cLntrKyQlxcHK8RHhcXB21tbdStWxcAUKtWLd7k1szMTN6vJ+VR+BkpKCio0HWEEEIIqd6qRCNdV1cX/fv3x7Rp09CtWzfUq1ePO+fm5gYlJSWMGjUKycnJOH78OJYuXVpmmZqamhg7diymTZuGyMhIJCcnw9vbG9nZ2Rg1ahQAwMfHB7du3UJgYCDu3LmDffv2cRMuC3tTAwMDcf78eYwbNw6JiYlISUnB4cOHMWHChM9+7pycHKSnpyM9PR0SiQQTJkxAVlYW+vTpAwBwd3eHuro6PD09cePGDURHR2PChAkYNmwY6tSpU657NG7cGN27d4e3tzcuXryI+Ph4jB49GiKRqMxr8/PzkZ6ejmfPnuH69etYs2YNHB0d0aJFC0ybNg0AYG5uDldXV3h7eyM2NhZJSUnw8PBA3bp14erqWu5YTJs2DYsXL8bevXtx+/ZtTJ8+HYmJiZg4cWK5ywA+vO+bN2/GsWPH0LdvX5w+fRqpqam4cuUKAgIC4OvrCwDw8/PD48ePMWHCBNy6dQt//fUXgoOD8fPPP0NJ6cN/Nl26dMGOHTtw9uxZ3LhxA56enhXeiax+/foQCAQ4evQoXrx4wVuZhxBCCCHfryrRSAeAUaNGITc3FyNHjuSla2lp4ciRI0hOTkbLli0xY8YM3vJ/pVm0aBEGDBiAYcOGwdbWFnfv3sXJkye5DWoaNGiAP//8ExEREbC2tsb69eu51V0Khx5YW1sjJiYGKSkp6NixI1q2bIlZs2bB0NDws585MjIShoaGMDQ0RNu2bbkVXDp37gzgwzjukydPIiMjA61bt8ZPP/2Erl27Yu3atRW6T2hoKIyNjeHo6Ij+/ftjzJgxqF27dpnX3bx5E4aGhjAxMUHnzp2xb98+BAUF4ezZs9DS0uKV36pVK/Tu3Rv29vZgjOH48ePFhoGUxt/fH1OmTMGUKVPQvHlzREZGcstjVpSrqyvi4uKgqqoKNzc3WFpaYujQoZBKpdzqLXXr1sXx48dx6dIl2NjYwNfXF6NGjcLMmTO5coKCgtCpUyf07t0bPXv2RL9+/Xjj6sujbt26mDNnDqZPn446deoUW5mHEEIIId8nAavIoG4FCg8Px8SJE/Hs2bNKH0ZSEQsWLMCGDRto4h5RqMzMTIjFYmRkZHz2rqek4goKCpCSkgJzc/MK/3pCPg/FXnEo9opF8Vecyox94d9vqVQKHR2dUvMqdOJoeWRnZ+PBgwdYuHAhfHx8vnoDfd26dWjdujX09PRw7tw5LFmyhHo7CSGEEELIF/XNDHcp3DEyMTGRlx4SEoIWLVqgTp06CAoK+ur1SklJgaurK6ysrDBv3jxMmTKFt6Pkt0TeDpiEEEIIIaTqqVAjvXCL+Y+dOXMGAoHgk1cEKc3s2bORl5eHqKgo3jjnr2XFihV49uwZ3r9/jzt37mDWrFlQUZH/A4SXlxcEAgF36OnpoXv37rh27dpXrnXpnjx5AjU1NVhaWiq6KnJ17twZkyZN+qL3yMzMxIwZM2BpaQl1dXUYGBjghx9+QERERIWW9awM9OWKEEIIIR/7ZnrSy8IYQ35+vqKrUabu3bsjLS0NaWlpiIqKgoqKCnr37q3oavGEhYVh0KBByM7Oxrlz5xRdnS8mNzdXbvrr16/Rvn17bN++HUFBQUhISMA///yDwYMHIyAgAFKp9CvXlBBCCCGEr9Ib6W/fvoWOjg7+/PNPXvqRI0egqamJN2/eAAAuXbqEli1bQl1dHXZ2drh69Sovf2Hv/MmTJ2FnZwehUIizZ88iJycH/v7+qF27NtTV1dGhQ4dia5kXrvohEong5OSEbdu2Fevpj4uLQ6dOnSASiWBsbAx/f3/eeuOmpqb47bffMHLkSGhra8PExAR//PFHmc8vFAphYGAAAwMDtGjRAoGBgXj8+DFevHjB5bl+/Tq6dOkCkUgEPT09jBkzhrf0XuEvFkuXLoWhoSH09PQwbtw43kY5z58/R58+fSASidCgQQOEh4eXWTfgw5ed0NBQDBs2DG5ubtiyZUuxPOfOnYOjoyM0NDSgq6sLFxcXvHr1CsCHzZsWL14MMzMzCIVCmJiYYMGCBdy1T58+xeDBg6Grqws9PT24uroiNTW12LPNmTMHtWvXho6ODnx8fLgGtZeXF2JiYrBq1SruF4nC62NiYtCmTRsIhUIYGhpi+vTpvC9unTt3xvjx4/Hzzz9DX18fzs7OcmPwyy+/IDU1FRcvXoSnpyesrKxgYWEBb29vJCYmcr/YvHr1CsOHD4euri40NDTQo0cPpKSkcOXMnj0bLVq04JW9cuVKmJqaFnvekt7Lzp074+HDh5g8eTL3vIQQQgghld5I19TUxJAhQxAaGspLDw0NxU8//QRtbW28ffsWvXv3RuPGjREfH4/Zs2dj6tSpcssLCAjAwoULIZFIYG1tjYCAABw4cADbtm1DQkICzMzM4OLigoyMDAAfxrb/9NNP6NevHxITE+Hj48Mtm1jo+vXrcHFxQf/+/XHt2jXs3bsXsbGxxSaELlu2jPsC4efnh7Fjx+LWrVvljkVWVhbCw8NhZmYGPT09AB8mwnbv3h26urrckoqnT58udu/o6Gjcu3cP0dHR2LZtG8LCwrg12oEPjb/U1FT873//w59//ol169aVa6v56OhoZGdn44cffsCwYcOwb98+7osTACQmJqJr165o2rQpzp8/j9jYWPTp04fbbCcoKAiLFy/GrFmzkJycjF27dnFrsmdnZ8PJyQlaWlr4559/EBsbCy0tLXTv3p3Xqx0VFQWJRILo6Gjs3r0bBw8exJw5cwAAq1atgr29Pby9vblfJIyNjfH06VP07NkTrVu3RlJSEtavX48tW7ZwSyYW2rZtG1RUVHDu3Dls3Lix2PPLZDLs2bMH7u7uMDIyKnZeS0uLG87k5eWFK1eu4PDhwzh//jwYY+jZs6fcXUXLinlJ72VERATq1auHuXPncs8rT05ODjIzM3kHIYQQQqoxVgGenp5MWVmZaWpq8g51dXUGgL169YoxxtjFixeZsrIye/r0KWOMsRcvXjBVVVV25swZxhhjGzduZDVr1mRv377lyl6/fj0DwK5evcoYYyw6OpoBYIcOHeLyZGVlMVVVVRYeHs6l5ebmMiMjIxYSEsIYYywwMJA1a9aMV+8ZM2bw6jds2DA2ZswYXp6zZ88yJSUl9u7dO8YYY/Xr12ceHh7ceZlMxmrXrs3Wr19f7vgAYIaGhiw+Pp7L88cffzBdXV2WlZXFpR07dowpKSmx9PR0rpz69euz/Px8Ls/AgQPZ4MGDGWOM3b59mwFgFy5c4M5LJBIGgK1YsaLE+jHGmJubG5s0aRL32sbGhm3atIl7PXToUObg4CD32szMTCYUCnn5i9qyZQtr3Lgxk8lkXFpOTg4TiUTs5MmT3LPJe++1tLRYQUEBY4wxR0dHNnHiRF7Zv/zyS7Gyf//992LXtWjRotTn//fffxkAtnz58lLz3blzhwFg586d49JevnzJRCIR27dvH2OMseDgYGZjY8O7bsWKFax+/frc67LeS8Y+fNbKet+Cg4MZgGJHRkZGqdeRLyM/P59JJBLe+0q+Doq94lDsFYvirziVGXupVMoAMKlUWmbeCvekOzk5ITExkXds3ryZl6dNmzZo2rQptm/fDgDYsWMHTExM0KlTJwCARCKBjY0NNDQ0uGvs7e3l3s/Ozo77971795CXlwcHBwcuTVVVFW3atIFEIgHwYUv71q1bF6tPUfHx8QgLC4OWlhZ3uLi4QCaT8bZ1t7a25v4tEAhgYGBQZm910fhcvHgR3bp1Q48ePfDw4UPes2tqanLXODg4QCaT4fbt21xa06ZNeWtxGhoacveWSCRQUVHhxcbS0hI1atQotW6vX79GREQEPDw8uDQPDw9s3bqVe13Yky6PRCJBTk5Oiefj4+Nx9+5daGtrc3GtWbMm3r9/j3v37nH55L33WVlZpa49L5FIYG9vzxsO4uDggKysLDx58oRLKxoTedj/nxRa1rCSwhi3bduWS9PT00Pjxo25z1p5lfZelldQUBCkUil30Dr9hBBCSPVW4XXSNTU1YWZmxksr2kgqNHr0aKxduxbTp09HaGgoRowYwTWMWAVWzyjamC2pgcUY45Ut73xRMpkMPj4+8Pf3L3Y/ExMT7t8f74gpEAggk8nKrG/R+LRq1QpisRibNm3C/Pnz5davaPnluXd5G5of27VrF96/f89reDLGIJPJkJycDCsrK4hEohKvL+0c8CGurVq1kjs+vlatWmXWr7TnKe19LZpe9PMiT61ataCrq1tmQ7ukz2jReigpKRXLJ28ozKd8jj4mFAq5XW4JIYQQUv19sdVdPDw88OjRI6xevRo3b96Ep6cnd87KygpJSUl49+4dl3bhwoUyyzQzM4OamhpiY2O5tLy8PFy5cgVNmjQB8KFH+eOJpFeuXOG9trW1xc2bN2FmZlbsqOzNkgQCAZSUlLhntbKyQmJiIm+S6rlz56CkpAQLC4tyldmkSRPk5+fznuv27dtlLoG5ZcsWTJkyhfcrSFJSEpycnLjedGtra0RFRcm9vnAybknnbW1tkZKSgtq1axeLq1gs5vLJe++1tLRQr149AICamho3Br6QlZUV4uLieI3iuLg4aGtro27duqU+d1FKSkoYPHgwwsPD8ezZs2Ln3759i/z8fFhZWSE/Px8XL17kzv3333+4c+cO91mrVasW0tPTeXX6eJ3/8pD3vIQQQgj5vn2xRrquri769++PadOmoVu3blwDDADc3NygpKSEUaNGITk5GcePH8fSpUvLLFNTUxNjx47FtGnTEBkZieTkZHh7eyM7OxujRo0CAPj4+ODWrVsIDAzEnTt3sG/fPm6SXmEPaGBgIM6fP49x48YhMTERKSkpOHz4MCZMmPDZz52Tk4P09HSkp6dDIpFgwoQJyMrKQp8+fQAA7u7uUFdXh6enJ27cuIHo6GhMmDABw4YN4yZglqVx48bo3r07vL29cfHiRcTHx2P06NGl9nQnJiYiISEBo0ePRrNmzXjH0KFDsX37duTl5SEoKAiXL1+Gn58frl27hlu3bmH9+vV4+fIl1NXVERgYiICAAGzfvh337t3DhQsXuBVi3N3doa+vD1dXV5w9exYPHjxATEwMJk6cyPu1JTc3l3vvT5w4geDgYIwfPx5KSh8+jqamprh48SJSU1Px8uVLyGQy+Pn54fHjx5gwYQJu3bqFv/76C8HBwfj555+568rrt99+g7GxMdq2bYvt27cjOTkZKSkp2Lp1K1q0aIGsrCyYm5vD1dUV3t7eiI2NRVJSEjw8PFC3bl24uroC+LAyy4sXLxASEoJ79+7h999/x4kTJypUl8Ln/eeff/D06VO8fPmywtcTQgghpPr5ouukjxo1Crm5uRg5ciQvXUtLC0eOHEFycjJatmyJGTNmYPHixeUqc9GiRRgwYACGDRsGW1tb3L17FydPnoSuri4AoEGDBvjzzz8REREBa2trrF+/nlvdpXC4gLW1NWJiYpCSkoKOHTuiZcuWmDVrFgwNDT/7mSMjI2FoaAhDQ0O0bduWW8Glc+fOAAANDQ2cPHkSGRkZaN26NX766Sd07doVa9eurdB9QkNDYWxsDEdHR/Tv3x9jxoxB7dq1S8y/ZcsWWFlZyd3AqF+/fsjIyMCRI0dgYWGBv//+G0lJSWjTpg3s7e3x119/cSuezJo1C1OmTMGvv/6KJk2aYPDgwdz4ag0NDfzzzz8wMTFB//790aRJE4wcORLv3r2Djo4Od7+uXbvC3NwcnTp1wqBBg9CnTx/eLq5Tp06FsrIyrKysUKtWLTx69Ah169bF8ePHcenSJdjY2MDX1xejRo3CzJkzKxQ34MMXyAsXLsDDwwPz589Hy5Yt0bFjR+zevRtLlizhev1DQ0PRqlUr9O7dG/b29mCM4fjx49zwlSZNmmDdunX4/fffYWNjg0uXLpW4SlFp5s6di9TUVDRq1Khcw4IIIYQQUv0JWEUGiFdQeHg4Jk6ciGfPnlX6MJKKWLBgATZs2ECT7b4BXl5eeP36NQ4dOqToqlRpmZmZEIvFyMjI4L6gkq+noKAAKSkpMDc3500KJl8exV5xKPaKRfFXnMqMfeHfb6lUyuvAlOeL9KRnZ2fj5s2bWLhwIXx8fL5qA93Lyws2Nja4fPky7t+/jx07dmDJkiW8MfEVFRYWVubKKRVRuFFTWWPIP4e8jXaqitmzZ6NOnToQCATUmCeEEELId6lSG+mFOyZqamqiWbNmuHnzJn777Tcu3cvLqzJvV6KsrCy4urrCysoK8+bNw5QpU3jDKSpq8ODBuHPnTuVVsBxMTU25uGloaKBZs2ZyN+dRhPv372Po0KEwMjKCuro66tWrB1dX10qJkUQiwZw5c7Bx40akpaWhR48elVDjT/fu3Tvo6uqiZs2avMmuhBBCCCFfUoWXYCxN0d0S9+7di19//ZW39ndZS/hVlubNm1dqD6xIJPpqdS9q7ty58Pb2RlZWFsLCwuDr64saNWpg8ODBX+X+eXl5xZYPzM3NhbOzMywtLREREQFDQ0M8efIEx48fh1QqLbPMorumFlVQUACBQMCtp+7q6lrhJSa/hAMHDqBZs2ZgjCEiIgLu7u6l5pcXM0IIIYSQiqrUnnQDAwPuEIvF3AZAhceuXbvQqFEjqKmpoXHjxtixYwfveoFAgPXr16NHjx4QiURo0KAB9u/fz8tz/fp1dOnSBSKRCHp6ehgzZgyysrJKrFNOTg78/f1Ru3ZtqKuro0OHDsWWaDx8+DC3vKCTkxO2bdvGG44ib7jL4cOHYWdnB3V1dejr66N///7cuZ07d8LOzg7a2towMDCAm5tbhTevAcBdb2Zmhvnz58Pc3Jz78vHo0SO4urpCS0sLOjo6GDRoEP79998Sy7p8+TKcnZ2hr68PsVgMR0dHJCQk8PIIBAJs2LABrq6u0NTUxPz584uVk5ycjPv372PdunVo164d6tevDwcHByxYsIDbRErecJ7ExEQIBAKkpqYC+L+YHj16FFZWVhAKhRgxYgS3Co6SkhLXSC9P3V+/fo0xY8agTp06UFdXR7NmzXD06FHufFxcHDp16gSRSARjY2P4+/vzlsEsyZYtW+Dh4QEPDw9uFZvyxOzIkSNo1aoV1NXV0bBhQ8yZMwf5+fncdcuXL0fz5s2hqakJY2Nj+Pn5lfo5JoQQQsj35Yuu7lLUwYMHMXHiREyZMgU3btyAj48PRowYgejoaF6+WbNmYcCAAdySd0OHDuU2nsnOzkb37t2hq6vLrZpy+vRpjB8/vsT7BgQE4MCBA9i2bRsSEhJgZmYGFxcXZGRkAABSU1Px008/oV+/fkhMTISPjw+3GkxJjh07hv79+6NXr164evUqoqKieDtd5ubmYt68eUhKSsKhQ4fw4MGDShnqo66ujry8PDDGuBVZYmJicOrUKdy7d6/UHvY3b97A09MTZ8+exYULF2Bubo6ePXvizZs3vHzBwcFwdXXF9evXi63KA3xYG1xJSQl//vnnZ6/tnZ2djYULF2Lz5s24efMmVq9ejdDQUAAffpUp/GWmrLrLZDL06NEDcXFx2LlzJ5KTk7Fo0SJucsf169fh4uKC/v3749q1a9i7dy9iY2NL/dwAH3a4PX/+PAYNGoRBgwYhLi4O9+/fL5bv45idPHkSHh4e8Pf3R3JyMjZu3IiwsDAsWLCAu0ZJSQmrV6/GjRs3sG3bNvzvf/9DQEBAiXXJyclBZmYm7yCEEEJINca+kNDQUCYWi7nX7du3Z97e3rw8AwcOZD179uReA2C+vr68PG3btmVjx45ljDH2xx9/MF1dXZaVlcWdP3bsGFNSUmLp6emMMcY8PT2Zq6srY4yxrKwspqqqysLDw7n8ubm5zMjIiIWEhDDGGAsMDGTNmjXj3XPGjBkMAHv16pXcZ7G3t2fu7u7ljsWlS5cYAPbmzRvGGGPR0dG88uWpX78+W7FiBWOMsby8PBYaGsoAsHXr1rG///6bKSsrs0ePHnH5b968yQCwS5cuMcYYCw4OZjY2NiWWn5+fz7S1tdmRI0e4NABs0qRJZT7P2rVrmYaGBtPW1mZOTk5s7ty57N69e9x5ec939epVBoA9ePCAMca450lMTOSVffDgQVbWx/Ljup88eZIpKSmx27dvy80/bNgwNmbMGF7a2bNnmZKSEnv37l2J9/nll19Yv379uNeurq5sxowZvDzyYtaxY0f222+/8dJ27NjBDA0NS7zXvn37mJ6eXonng4ODGYBiR0ZGRonXkC8nPz+fSSQSlp+fr+iqfHco9opDsVcsir/iVGbspVIpA8CkUmmZeb9aT7pEIoGDgwMvzcHBodj27Pb29sVeF+aRSCSwsbHhbf3u4OAAmUzGG/te6N69e8jLy+PdV1VVFW3atOHKvH37NjdMo1CbNm1KfZbExER07dq1xPNXr16Fq6sr6tevD21tbW6N9EePHpVa7scCAwOhpaUFkUiEcePGYdq0afDx8YFEIoGxsTGMjY25vFZWVqhRo0aJ290/f/4cvr6+sLCwgFgshlgsRlZWVrE6Ff1FoCTjxo1Deno6du7cCXt7e+zfvx9NmzbFqVOnKvR8ampqsLa2LjNfWXVPTExEvXr1StyxNT4+HmFhYdDS0uIOFxcXyGQyPHjwQO41BQUF2LZtGzw8PLg0Dw8PbNu2rdgvCB/HLD4+HnPnzuXdz9vbG2lpacjOzgYAREdHw9nZGXXr1oW2tjaGDx+O//77r8QhOEFBQZBKpdxBy4kSQggh1VulThwty8cTARlj5ZocWJintPzy0tn/XwK+tPvKK5OVsXR8aZNI3759i27duqFbt27YuXMntxmPi4sLcnNzSy33Y9OmTYOXlxc0NDRgaGhYZhxKi4+XlxdevHiBlStXon79+hAKhbC3ty9Wp6JfgEqjra2Nvn37om/fvpg/fz5cXFwwf/58ODs7czuAFo1jXl5esTJEIlG53v+y6l7WpF6ZTAYfHx/4+/sXO2diYiL3mpMnT+Lp06fFhhAVFBTg77//5q0683HMZDIZ5syZw5unUEhdXR0PHz5Ez5494evri3nz5qFmzZqIjY3FqFGj5MYJ+LARV+FmXIQQQgip/r5aT3qTJk0QGxvLS4uLi0OTJk14aRcuXCj2unCXTCsrKyQmJvJ6G8+dOwclJSW5vahmZmZQU1Pj3TcvLw9Xrlzh7mtpaVlsIumVK1dKfRZra2tERUXJPXfr1i28fPkSixYtQseOHWFpaflJk0YBQF9fH2ZmZjAyMuI1Zq2srPDo0SNeb2pycjKkUmmxeBY6e/Ys/P390bNnTzRt2hRCobDStqAXCASwtLTk3pfCXTOLrvaTmJj4yeWXVXdra2s8efKkxCUgbW1tcfPmTZiZmRU7SlrDf8uWLRgyZAgSExN5h7u7u9wJpB/f7/bt23Lvp6SkhCtXriA/Px/Lli1Du3btYGFhgWfPnn1yfAghhBBS/Xy1nvRp06Zh0KBBsLW1RdeuXXHkyBFERETg9OnTvHz79++HnZ0dOnTogPDwcFy6dIlrFLm7uyM4OBienp6YPXs2Xrx4gQkTJmDYsGGoU6dOsXtqampi7NixmDZtGmrWrAkTExOEhIQgOzsbo0aNAgD4+Phg+fLlCAwMxKhRo5CYmMgtE1hSL29wcDC6du2KRo0aYciQIcjPz8eJEycQEBAAExMTqKmpYc2aNfD19cWNGzcwb968Sowk8MMPP8Da2hru7u5YuXIl8vPz4efnB0dHxxKHq5iZmWHHjh2ws7NDZmYmpk2b9knLSiYmJiI4OBjDhg2DlZUV1NTUEBMTg61btyIwMJC7l7GxMWbPno358+cjJSUFy5Yt++TnLavujo6O6NSpEwYMGIDly5fDzMwMt27dgkAgQPfu3REYGIh27dph3Lhx8Pb2hqamJiQSCU6dOoU1a9YUu9+LFy9w5MgRHD58GM2aNeOd8/T0RK9evfDixQvuy8jHfv31V/Tu3RvGxsYYOHAglJSUcO3aNVy/fh3z589Ho0aNkJ+fjzVr1qBPnz44d+4cNmzY8MnxIYQQQkg19Nkj4Evw8WRLxhhbt24da9iwIVNVVWUWFhZs+/btvPMA2O+//86cnZ2ZUChk9evXZ7t37+bluXbtGnNycmLq6uqsZs2azNvbm5uQyRh/4ihjjL17945NmDCB6evrM6FQyBwcHLjJlYX++usvZmZmxoRCIevcuTNbv349A8BNKpT3LAcOHGAtWrRgampqTF9fn/Xv3587t2vXLmZqasqEQiGzt7dnhw8fZgDY1atXGWMVnzgqz8OHD1nfvn2ZpqYm09bWZgMHDuQmzzJWfOJoQkICs7OzY0KhkJmbm7P9+/cXuwcAdvDgwRLvyRhjL168YP7+/qxZs2ZMS0uLaWtrs+bNm7OlS5eygoICLl9sbCxr3rw5U1dXZx07dmT79+8vNnH045gyJn/iaHnq/t9//7ERI0YwPT09pq6uzpo1a8aOHj3Knb906RJzdnZmWlpaTFNTk1lbW7MFCxbIfcalS5eyGjVqsNzc3GLn8vLyWM2aNdmyZctKjVlkZCRr3749E4lETEdHh7Vp04b98ccf3Pnly5czQ0NDJhKJmIuLC9u+fXuZn4miCiee0MRRxaAJXIpDsVccir1iUfwVR1ETRwWMlTEA+ysSCAQ4ePAg+vXrp9B6LFiwABs2bKDJeeSblZmZCbFYjIyMDOjq6iq6Ot+dgoICpKSkwNzcnFvqk3wdFHvFodgrFsVfcSoz9oV/v6VSKXR0dErN+9XGpH/L1q1bh8uXL+P+/fvYsWMHlixZAk9PT0VX64swNTXFypUrS80jEAgqdcfWr03e5lOEEEIIIVUJNdIBpKSkwNXVFVZWVpg3bx6mTJmC2bNnl3qNl5cXBAIBBAIBVFRUYGJigrFjx+LVq1flvm9qaioEAsEnTar8lhvShc9VeKipqXG7pn5DP9wgOjoaPXv2hJ6eHjQ0NGBlZYUpU6bg6dOnX7Ue9KWCEEIIIR/7qkswlkVRDbgVK1ZgxYoVFb6ue/fuCA0NRX5+PpKTkzFy5Ei8fv0au3fv/gK1rHpOnz6Npk2bIicnB7GxsRg9ejQMDQ25SbuKtHHjRvj5+cHT0xMHDhyAqakpHj16hO3bt2PZsmVYvny5oqtICCGEkO8Y9aR/BqFQCAMDA9SrVw/dunXD4MGD8ffff3PnZTIZ5s6di3r16kEoFKJFixaIjIzkzjdo0AAA0LJlSwgEAm7To8uXL8PZ2Rn6+voQi8VwdHREQkICd52pqSkA4Mcff4RAIOBe37t3D66urqhTpw60tLTQunXrYqvnAMCbN2/g5uYGLS0tGBkZyV3hpKjC9cJ1dXWhp6cHV1dXpKamlhkfPT09GBgYoH79+nB3d0f79u15z1FWfAp75CMiIuDk5AQNDQ3Y2Njg/PnzvPuEhYXBxMQEGhoa+PHHH/Hff/+VWq8nT57A398f/v7+2Lp1Kzp37gxTU1N06tQJmzdvxq+//srlPXDgALfso6mpabFVauT9olGjRg1uhaCynuHMmTMYMWIEpFIp98tDWb/iEEIIIaT6o0Z6Jbl//z4iIyOhqqrKpa1atQrLli3D0qVLce3aNbi4uKBv375ISUkBAFy6dAnAhx7ntLQ0REREAPjQiPb09MTZs2dx4cIFmJubo2fPnnjz5g0AcOu6h4aGIi0tjXudlZWFnj174vTp07h69SpcXFzQp0+fYruKLlmyBNbW1khISEBQUBAmT55c4m6h2dnZcHJygpaWFv755x/ExsZCS0sL3bt3r9DmTFeuXEFCQgLatm1b7vgUmjFjBqZOnYrExERYWFhg6NChyM/PBwBcvHgRI0eOhJ+fHxITE+Hk5IT58+eXWpf9+/cjNzcXAQEBcs8XDj2Jj4/HoEGDMGTIEFy/fh2zZ8/GrFmzuAZ4RZT0DO3bt8fKlSuho6ODtLQ0pKWlYerUqcWuz8nJQWZmJu8ghBBCSDX22WvJfKc8PT2ZsrIy09TUZOrq6gwAA8CWL1/O5TEyMiq2zF/r1q2Zn58fY4yxBw8e8JZmLEl+fj7T1tZmR44c4dJQjuUSGWPMysqKrVmzhntdv3591r17d16ewYMHsx49esgte8uWLaxx48ZMJpNx53NycphIJGInT56Ue8/C5xKJRExTU5OpqqoyAGzMmDG8fOWNz+bNm7nzN2/eZACYRCJhjDE2dOhQuc8jb3nHQmPHjmU6Ojolni/k5ubGnJ2deWnTpk1jVlZW3Gt574NYLGahoaHlfoaSlqMsKjg4mPuMFT1oCUbFoKXQFIdirzgUe8Wi+CuOopZgpJ70z+Dk5ITExERcvHgREyZMgIuLCyZMmADgwxI7z549g4ODA+8aBwcHSCSSUst9/vw5fH19YWFhAbFYDLFYjKysrGI94h97+/YtAgICYGVlhRo1akBLSwu3bt0qdp29vX2x1yXVKT4+Hnfv3oW2tja0tLSgpaWFmjVr4v3797h3716p9dm7dy8SExORlJSEvXv34q+//sL06dMBVCw+1tbW3L8NDQ0BgNvFVSKRyH2e0jDGStyoqiiJRCK3fikpKSgoKCjz+qJKe4byCAoKglQq5Q5aHpQQQgip3r6piaNVjaamJszMzAAAq1evhpOTE+bMmcPbYfTjxmB5GoheXl548eIFVq5cifr160MoFMLe3r7M4SXTpk3DyZMnsXTpUpiZmUEkEuGnn34q17CUkuokk8nQqlUrhIeHFztX0o6bhYyNjbn4NGnSBPfv38esWbN4Y67LE5+iQ4gKz8lkMi5/RVlYWEAqlSItLY1rMMsjry4f308gEBRLy8vLK1ZWac9QHkKhEEKhsNz5CSGEEFK1UU96JQoODsbSpUvx7Nkz6OjowMjICLGxsbw8cXFxaNKkCQBATU0NAIr1yp49exb+/v7o2bMnN2nx5cuXvDyqqqpyr/Py8sKPP/6I5s2bw8DAQO4EzwsXLhR7bWlpKfeZbG1tkZKSgtq1a8PMzIx3iMXisoNShLKyMvLz85Gbm1uu+JSHlZWV3OcpzU8//QQ1NTWEhITIPf/69WuubHn1s7Cw4DYzqFWrFtLS0rjzKSkpyM7OLnf9gQ+fg4r2zBNCCCGkeqNGeiXq3LkzmjZtit9++w3Ah57txYsXY+/evbh9+zamT5+OxMRETJw4EQBQu3ZtiEQiREZG4t9//4VUKgUAmJmZYceOHZBIJLh48SLc3d0hEol49zI1NUVUVBTS09O5tdnNzMwQERHBDTFxc3OT21t77tw5hISE4M6dO/j999+xf/9+rk4fc3d3h76+PlxdXXH27Fk8ePAAMTExmDhxIp48eVJqPP777z+kp6fjyZMnOHHiBFatWgUnJyduh62y4lMe/v7+iIyM5J5n7dq1vBVi5DE2NsaKFSuwatUqjBo1CjExMXj48CHOnTsHHx8f7peQKVOmICoqCvPmzcOdO3ewbds2rF27ljexs0uXLli7di0SEhJw5coV+Pr68nrNy8PU1BRZWVmIiorCy5cvK9zIJ4QQQkg19Nkj4L9Tnp6ezNXVtVh6eHg4U1NTY48ePWIFBQVszpw5rG7dukxVVZXZ2NiwEydO8PJv2rSJGRsbMyUlJebo6MgYYywhIYHZ2dkxoVDIzM3N2f79+1n9+vXZihUruOsOHz7MzMzMmIqKCqtfvz5j7MMkRScnJyYSiZixsTFbu3Ytc3R0ZBMnTuSuq1+/PpszZw4bNGgQ09DQYHXq1GErV67k1QkfTYZMS0tjw4cPZ/r6+kwoFLKGDRsyb2/vEic9FE6WLDyUlZVZvXr1mLe3N3v+/DmXr6z4yJtY++rVKwaARUdHc2lbtmxh9erVYyKRiPXp04ctXbq0zImYjDF26tQp5uLiwnR1dZm6ujqztLRkU6dOZc+ePePy/Pnnn8zKyoqpqqoyExMTtmTJEl4ZT58+Zd26dWOamprM3NycHT9+XO7E0bKewdfXl+np6TEALDg4uMy6F048oYmjikETuBSHYq84FHvFovgrjqImjgoY+4a2gCSElEtmZibEYjEyMjKgq6ur6Op8dwoKCpCSkgJzc3Nu6BP5Oij2ikOxVyyKv+JUZuwL/35LpVJuZEFJaLgLIYQQQggh3xhqpJNvirwdPAkhhBBCvjfUSCdfhZeXF7ftvYqKCkxMTDB27Fhu0muhtLQ09OjR46vUKTo6Gj179oSenh40NDRgZWWFKVOm4OnTp1/l/oXCwsK4XU4JIYQQQgBqpJOvqHv37khLS0Nqaio2b96MI0eOwM/Pj5fHwMDgq6wHvnHjRvzwww8wMDDAgQMHkJycjA0bNkAqlWLZsmVf/P6EEEIIIaWhRjr5aoRCIQwMDFCvXj1069YNgwcPxt9//83LU3S4S2pqKgQCASIiIuDk5AQNDQ3Y2Njg/PnzvGs2bdoEY2NjaGho4Mcff8Ty5ctL7Zl+8uQJ/P394e/vj61bt6Jz584wNTVFp06dsHnzZvz6669c3gMHDnBr1ZuamhZrwMsbnlOjRg2EhYWV6xnOnDmDESNGQCqVcr80FN3siRBCCCHfJ2qkE4W4f/8+IiMjy7Wm+IwZMzB16lQkJibCwsICQ4cORX5+PoAPa777+vpi4sSJSExMhLOzMxYsWFBqefv370dubi4CAgLkni9s4MfHx2PQoEEYMmQIrl+/jtmzZ2PWrFlcA7wiSnqG9u3bY+XKldDR0UFaWhrS0tJ467AXysnJQWZmJu8ghBBCSPWlougKkO/H0aNHoaWlhYKCArx//x4AsHz58jKvmzp1Knr16gUAmDNnDpo2bYq7d+/C0tISa9asQY8ePbiGrYWFBeLi4nD06NESy0tJSYGOjg4MDQ1Lve/y5cvRtWtXzJo1iys7OTkZS5YsgZeXV3keuVzPIBaLIRAIYGBgUOL1CxcuxJw5cyp0T0IIIYRUXdSTTr4aJycnJCYm4uLFi5gwYQJcXFwwYcKEMq+ztrbm/l3YsH7+/DkA4Pbt22jTpg0v/8evP8YYg0AgKPO+EokEDg4OvDQHBwekpKSgoKCgzOuLKu0ZyiMoKAhSqZQ7Hj9+XKH7E0IIIaRqoUY6+Wo0NTVhZmYGa2trrF69Gjk5OeXqHS46JKawcS2TyQDIb3CXtT+XhYUFpFIp0tLSSs1XnrIFAkGxtLy8vAo9Q3kIhULo6OjwDkIIIYRUX9RIJwoTHByMpUuX4tmzZ59chqWlJS5dusRLu3LlSqnX/PTTT1BTU0NISIjc869fvwYAWFlZITY2lncuLi4OFhYW3I5jtWrV4jX2U1JSkJ2dXaFnUFNTq3DPPCGEEEKqN2qkE4Xp3LkzmjZtit9+++2Ty5gwYQKOHz+O5cuXIyUlBRs3bsSJEydKHc5ibGyMFStWYNWqVRg1ahRiYmLw8OFDnDt3Dj4+Ppg3bx4AYMqUKYiKisK8efNw584dbNu2DWvXruVN7OzSpQvWrl2LhIQEXLlyBb6+vuWaDFuUqakpsrKyEBUVhZcvX1a4kU8IIYSQ6oca6UShfv75Z2zatOmTx1g7ODhgw4YNWL58OWxsbBAZGYnJkydDXV291Ov8/Pzw999/4+nTp/jxxx9haWmJ0aNHQ0dHh2uE29raYt++fdizZw+aNWuGX3/9FXPnzuVNGl22bBmMjY3RqVMnuLm5YerUqdDQ0KjQM7Rv3x6+vr4YPHgwatWqVWIPPyGEEEK+HwJW1gBeQqoYb29v3Lp1C2fPnlV0Vb6YzMxMiMViZGRkQFdXV9HV+e4UFBQgJSUF5ubm3NAn8nVQ7BWHYq9YFH/FqczYF/79lkqlZc4voyUYSZW3dOlSODs7Q1NTEydOnMC2bduwbt06RVeLEEIIIeST0XCXb4yXlxf69etXLP3MmTMQCATcpMaqoHHjxlBTU8PTp0956YW7cCYmJlbKfS5dugRnZ2c0b94cGzZswOrVqzF69Ogyrztw4AA6d+4MsVgMLS0tWFtbY+7cucjIyKiUepXX7Nmz0aJFi696T0IIIYR826iRTr6I2NhYvH//HgMHDvykHTorYt++fXj+/DnevXuHmzdvwtfXt8xrZsyYgcGDB6N169Y4ceIEbty4gWXLliEpKQk7duz4ovUlhBBCCCkLNdKrsLi4OHTq1AkikQjGxsbw9/fH27dvufM7d+6EnZ0dtLW1YWBgADc3N24DHZlMhnr16mHDhg28MhMSEiAQCHD//n2MHDkSvXv35p3Pz8+HgYEBtm7dWmrdtmzZAjc3NwwbNgxbt27lrSXeoEEDAEDLli0hEAjQuXNnrk5z585FvXr1IBQK0aJFC0RGRnLXFfbA79u3Dx07doRIJELr1q1x584dXL58GXZ2dtDS0kL37t3x4sWLEut26dIl/Pbbb1i2bBmWLFmC9u3bw9TUFM7Ozjhw4AA8PT25vOvXr0ejRo2gpqaGxo0b8xrw8n4ReP36NQQCAc6cOQPg/34BiYqKgp2dHTQ0NNC+fXvcvn0bABAWFoY5c+YgKSkJAoEAAoHgi3+pIYQQQsi3jxrpVdT169fh4uKC/v3749q1a9i7dy9iY2Mxfvx4Lk9ubi7mzZuHpKQkHDp0CA8ePOBWJlFSUsKQIUMQHh7OK3fXrl2wt7dHw4YNMXr0aERGRvLWAT9+/DiysrIwaNCgEuv25s0b7N+/Hx4eHnB2dsbbt2+5RisAbl3z06dPIy0tDREREQCAVatWYdmyZVi6dCmuXbsGFxcX9O3bFykpKbzyg4ODMXPmTCQkJEBFRQVDhw5FQEAAVq1ahbNnz+LevXv49ddfS6xfeHg4tLS04OfnJ/d8jRo1AAAHDx7ExIkTMWXKFNy4cQM+Pj4YMWIEoqOjSyy7JDNmzMCyZctw5coVqKioYOTIkQCAwYMHY8qUKWjatCnS0tKQlpaGwYMHF7s+JycHmZmZvIMQQggh1Rgj3xRPT0+mrKzMNDU1eYe6ujoDwF69esUYY2zYsGFszJgxvGvPnj3LlJSU2Lt37+SWfenSJQaAvXnzhjHGWEJCAhMIBCw1NZUxxlhBQQGrW7cu+/3337lrrKys2OLFi7nX/fr1Y15eXqU+wx9//MFatGjBvZ44cSJzd3fnXj948IABYFevXuVdZ2RkxBYsWMBLa926NfPz8+Ndt3nzZu787t27GQAWFRXFpS1cuJA1bty4xPr16NGDWVtbl/oMjDHWvn175u3tzUsbOHAg69mzZ4nP8erVKwaARUdHM8YYi46OZgDY6dOnuTzHjh1jALj3KTg4mNnY2JRal+DgYAag2JGRkVHmc5DKl5+fzyQSCcvPz1d0Vb47FHvFodgrFsVfcSoz9lKplAFgUqm0zLzUk/4NcnJyQmJiIu/YvHkzL098fDzCwsKgpaXFHS4uLpDJZHjw4AEA4OrVq3B1dUX9+vWhra3NDSt59OgRgA/DTSwtLbF7924AQExMDJ4/f87rJR89ejRCQ0MBAM+fP8exY8e4XuCSbNmyBR4eHtxrDw8PRERElDrpNTMzE8+ePYODgwMv3cHBARKJhJdmbW3N/btOnToAgObNm/PSCof1yMMYK3Wzo0ISiaRc9SmPonU2NDQEgFLr+LGgoCBIpVLu+NR15QkhhBBSNVAj/RukqakJMzMz3lG3bl1eHplMBh8fH15DPikpCSkpKWjUqBHevn2Lbt26QUtLCzt37sTly5dx8OBBAB+GwRRyd3fHrl27AHwY6uLi4gJ9fX3u/PDhw3H//n2cP38eO3fuhKmpKTp27Fhi3ZOTk3Hx4kUEBARARUUFKioqaNeuHd69e8d9GSjNx41neQ3qojt6Fp77OE0mk5V4DwsLC9y7dw95eXmfVR8lJSUurVBJZcqrc2l1/JhQKISOjg7vIIQQQkj1RY30KsrW1hY3b94s1pg3MzODmpoabt26hZcvX2LRokXo2LEjLC0t5fbcurm54fr164iPj8eff/4Jd3d33nk9PT3069cPoaGhCA0NxYgRI0qt15YtW9CpUyckJSXxvkAEBARgy5YtAAA1NTUAHzYHKKSjowMjIyPExsbyyouLi0OTJk0+KUYlcXNzQ1ZWVolrqRf2+Ddp0qTU+tSqVQsAeGP2P2VZSTU1NV4sCCGEEEJoM6MqKjAwEO3atcO4cePg7e0NTU1NSCQSnDp1CmvWrIGJiQnU1NSwZs0a+Pr64saNG5g3b16xcho0aID27dtj1KhRyM/Ph6ura7E8o0ePRu/evVFQUMBb+eRjeXl52LFjB+bOnYtmzZoVKyMkJARJSUlo2rQpRCIRIiMjUa9ePairq0MsFmPatGkIDg5Go0aN0KJFC4SGhiIxMbHY5NbP1bZtWwQEBGDKlCl4+vQpfvzxRxgZGeHu3bvYsGEDOnTogIkTJ2LatGkYNGgQbG1t0bVrVxw5cgQRERE4ffo0AEAkEqFdu3ZYtGgRTE1N8fLlS8ycObPC9TE1NcWDBw+QmJiIevXqQVtbG0KhsFKfmRBCCCFVC/WkV1HW1taIiYlBSkoKOnbsiJYtW2LWrFnceOdatWohLCwM+/fvh5WVFRYtWoSlS5fKLcvd3R1JSUno378/RCJRsfM//PADDA0N4eLiAiMjoxLrdPjwYfz333/48ccfi50zNzdH8+bNsWXLFqioqGD16tXYuHEjjIyMuC8G/v7+mDJlCqZMmYLmzZsjMjIShw8fhrm5+aeEqFSLFy/Grl27cPHiRbi4uKBp06b4+eefYW1tzX0R6devH1atWoUlS5agadOm2LhxI0JDQ7mx/QCwdetW5OXlwc7ODhMnTsT8+fMrXJcBAwage/fucHJyQq1atco1LIgQQggh1ZuAFR1QS4gc2dnZMDIywtatW9G/f39FV4fgw0RbsViMjIwM6OrqKro6352CggKkpKTA3NwcysrKiq7Od4VirzgUe8Wi+CtOZca+8O+3VCotc34Z9aQTAP+36U7RFVhkMhmePXuGWbNmQSwWo2/fvpV6z9mzZ6NFixaVWuaX9Cn17dy5MyZNmvRF6kMIIYSQ6osa6VWUl5cXBAIBfH19i53z8/ODQCDgNi76VI8ePULdunWxb98+bN26FSoqVWMKw/Tp04tNNpVIJBAIBBg2bBgvfceOHVBVVUVWVlaZ5U6dOhVRUVGVWlfgw2ovhw4dqvRyCSGEEFJ1USO9CjM2NsaePXvw7t07Lu39+/fYvXs3TExMPrt8U1NTMMbw+PFjdO3a9bPL+xLkLXno5OSEW7duIT09nUs7c+YMjI2Ni+0WeubMGbRp0wZaWlpl3ktLSwt6enqfX2lCCCGEkDJQI70Ks7W1hYmJCSIiIri0iIgIGBsbo2XLlry8OTk58Pf3R+3ataGuro4OHTrg8uXLpZYfFxeHTp06QSQSwdjYGP7+/nj79i2vzICAABgbG0MoFMLc3JxbZjEsLAw1atTglXfo0KFSNxG6fPkynJ2doa+vD7FYDEdHRyQkJPDyCAQCbNiwAa6urtDU1JQ7UbNDhw5QVVXFmTNnuLQzZ85g3LhxePPmDe7evctLd3JyAgBIpVKMGTMGtWvXho6ODrp06YKkpCQu78fDXfLz8+Hv748aNWpAT08PgYGB8PT0RL9+/Xj1kclkCAgIQM2aNWFgYIDZs2dz50xNTQEAP/74IwQCAfeaEEIIId83aqRXcSNGjOB2BAU+rDYib0fQgIAAHDhwANu2bUNCQgLMzMzg4uKCjIwMueVev34dLi4u6N+/P65du4a9e/ciNjYW48eP5/IMHz4ce/bswerVqyGRSLBhw4Zy9UiX5M2bN/D09MTZs2dx4cIFmJubo2fPnnjz5g0vX3BwMFxdXXH9+nW5z6qpqYnWrVvzes1jYmLQtWtXODg4cOmPHz/G/fv34eTkBMYYevXqhfT0dBw/fhzx8fHc0oslxWjx4sUIDw9HaGgozp07h8zMTLnDVrZt2wZNTU1cvHgRISEhmDt3Lk6dOgUA3Bel0NBQpKWllfjFKScnB5mZmbyDEEIIIdUYI1WSp6cnc3V1ZS9evGBCoZA9ePCApaamMnV1dfbixQvm6urKPD09GWOMZWVlMVVVVRYeHs5dn5uby4yMjFhISAhjjLHo6GgGgL169YoxxtiwYcPYmDFjePc8e/YsU1JSYu/evWO3b99mANipU6fk1i80NJSJxWJe2sGDB1nRj1xwcDCzsbEp8Rnz8/OZtrY2O3LkCJcGgE2aNKms8LBffvmFWVhYMMYYu3nzJtPR0WH5+fls0aJFzM3NjTHG2LZt25hQKGTZ2dksKiqK6ejosPfv3/PKadSoEdu4caPc+tapU4ctWbKEV18TExPm6urKpTk6OrIOHTrwymzdujULDAzkPdPBgwdLfZ7g4GAGoNiRkZFRZixI5cvPz2cSiYTl5+cruirfHYq94lDsFYvirziVGXupVMoAMKlUWmZe6kmv4vT19dGrVy9s27YNoaGh6NWrF/T19Xl57t27h7y8PDg4OHBpqqqqaNOmDSQSidxy4+PjERYWBi0tLe5wcXGBTCbjNt5RVlaGo6NjpT3L8+fP4evrCwsLC4jFYojFYmRlZeHRo0e8fHZ2dmWW5eTkhDt37uDZs2c4c+YMOnTowNW3cBjMmTNn0K5dO4hEIsTHxyMrKwt6enq8Z37w4AHu3btXrHypVIp///0Xbdq04dKUlZXRqlWrYnmtra15rw0NDeXu/lqaoKAgSKVS7nj8+HGFrieEEEJI1VI1lusgpRo5ciQ3DOX3338vdp79/6XwPx4PzhgrcYy4TCaDj48P/P39i50zMTHhjeuWR0lJibtvIXmTPIvy8vLCixcvsHLlStSvXx9CoRD29vbIzc3l5dPU1Cy1HABwcHCAmpoazpw5g+joaO7LhJ2dHaRSKe7cuYPo6GhuBRyZTAZDQ0PeOPZCH4+tL0peTD+mqqpa7BqZTFbmMxQlFAppF1JCCCHkO0I96dVA9+7dkZubi9zcXLi4uBQ7b2ZmBjU1NcTGxnJpeXl5uHLlSrGlCgvZ2tri5s2bMDMzK3aoqamhefPmkMlkiImJkXt9rVq18ObNG95E08TExFKf4+zZs/D390fPnj3RtGlTCIVCvHz5shwRKE4kEqFt27Y4c+YM/vnnH26XUBUVFbRv3x7bt29HamoqN2nU1tYW6enpUFFRKfa8H/8yAQBisRh16tTBpUuXuLSCggJcvXq1wnVVVVVFQUHBJz0nIYQQQqonaqRXA8rKypBIJJBIJHJ3wtLU1MTYsWMxbdo0REZGIjk5Gd7e3sjOzsaoUaPklhkYGIjz589j3LhxSExMREpKCg4fPowJEyYA+LAqiaenJ0aOHIlDhw7hwYMHOHPmDPbt2wcAaNu2LTQ0NPDLL7/g7t272LVrF8LCwkp9DjMzM+zYsQMSiQQXL16Eu7s7RCLRJ8fFycmJW6LS1taWS3d0dMTq1au5hjwA/PDDD7C3t0e/fv1w8uRJpKamIi4uDjNnzsSVK1fklj9hwgQsXLgQf/31F27fvo2JEyfi1atXpa5gI4+pqSmioqKQnp6OV69effLzEkIIIaT6oEZ6NaGjo1Pq9rKLFi3CgAEDMGzYMNja2uLu3bs4efJkiVvKW1tbIyYmBikpKejYsSNatmyJWbNmwdDQkMuzfv16/PTTT/Dz84OlpSW8vb25nvOaNWti586dOH78OJo3b47du3fzlh6UZ+vWrXj16hVatmyJYcOGcUtGfionJye8efMGDg4OvI2YHB0d8ebNG7Rv354bQiIQCHD8+HF06tQJI0eOhIWFBYYMGYLU1FTUqVNHbvmBgYEYOnQohg8fDnt7e27cvrq6eoXquWzZMpw6dUru0pmEEEII+T4JmLxBtISQCpPJZGjSpAkGDRqEefPmfdF7ZWZmQiwWIyMjo8QvWuTLKSgoQEpKCszNzeX+ekW+HIq94lDsFYvirziVGfvCv99SqbTUzlWAJo4S8skePnyIv//+G46OjsjJycHatWvx4MEDuLm5KbpqhBBCCKniaLgL+a6cOXMGAoEAr1+//uyylJSUEBYWhtatW8PBwQHXr1/H6dOnS5yMSwghhBBSXtRIJ98kLy8v9OvXr8LXXb16FQMHDkSdOnWgrq4OCwsLeHt7486dO+UuIywsrNRlF4EPY9jj4+Nx7tw5SKVS/PfffzAxMcHgwYNx7dq1CtebEEIIIaQoaqSTauPo0aNo164dcnJyEB4eDolEgh07dkAsFmPWrFlf7L7Z2dno27cvLl++jNjY2GKbFxFCCCGEVBQ10kmV0LlzZ/j7+yMgIAA1a9aEgYEBb7WY7OxsjBgxAj179sThw4fxww8/oEGDBmjbti2WLl2KjRs38sqLj4+HnZ0dNDQ00L59e9y+ffuT6vX69Wt069YNT58+RWxsLBo1agTgw6ZGISEhaNiwIUQiEWxsbPDnn39y58zMzLB06VJeWTdu3ICSkpLcHU4JIYQQ8n2hRjqpMrZt2wZNTU1cvHgRISEhmDt3Lk6dOgUAOHnyJF6+fImAgAC51348fGXGjBlYtmwZrly5AhUVFYwcObLC9UlPT4ejoyO3qVPR5SlnzpyJ0NBQrF+/Hjdv3sTkyZPh4eGBmJgYCAQCjBw5EqGhobzytm7dio4dO3IN/aJycnKQmZnJOwghhBBSfVEjnVQZ1tbWCA4Ohrm5OYYPHw47OztERUUBAFJSUgAAlpaW5SprwYIFcHR0hJWVFaZPn464uDi8f/++QvWZOHEicnNzcfr0ad4yiG/fvsXy5cuxdetWuLi4oGHDhvDy8oKHhwfXoz9ixAjcvn2b27E0Ly8PO3fuLPHLwsKFCyEWi7nD2Ni4QnUlhBBCSNVCjXRSZXw81tvQ0BDPnz8H8GEIyaeWVdgDXlhWefXp0wd37twpNpQmOTkZ79+/h7OzM7S0tLhj+/bt3FAWQ0ND9OrVC1u3bgXwYTz9+/fvMXDgQLn3CgoKglQq5Y7Hjx9XqK6EEEIIqVponXRSZaiqqvJeCwQCyGQyAICFhQUA4NatW7C3t69QWQKBAAC4ssrLw8MDffv2xciRI1FQUICpU6fyyjl27Bjq1q3Lu6Zwh1MAGD16NIYNG4YVK1YgNDQUgwcPhoaGhtx7CYVC3rWEEEIIqd6okU6qhW7dukFfXx8hISE4ePBgsfOvX78uc1nFTzF8+HAoKyvD09MTMpkMAQEBsLKyglAoxKNHj+Do6FjitT179oSmpibWr1+PEydO4J9//qn0+hFCCCGkaqJGOqkWNDU1sXnzZgwcOBB9+/aFv78/zMzM8PLlS+zbtw+PHj3Cnj17vsi93d3doaSkhGHDhkEmk2H69OmYOnUqJk+eDJlMhg4dOiAzMxNxcXHQ0tKCp6cnAEBZWRleXl4ICgqCmZlZuX4BIIQQQsj3gRrppNpwdXVFXFwcFi5cCDc3N2RmZsLY2BhdunTB/Pnzv+i9hw4dCmVlZbi7u0Mmk2HevHmoXbs2Fi5ciPv376NGjRqwtbXFL7/8wrtu1KhR+O233z5pdRlCCCGEVF8CVtEZd4SQSnPu3Dl07twZT548QZ06dcp9XWZmJsRiMTIyMngry5Cvo6CgACkpKTA3N4eysrKiq/NdodgrDsVesSj+ilOZsS/8+y2VSqGjo1NqXlrdhZAv7MyZMxAIBHj9+jWXlpOTg7t372LWrFkYNGhQhRrohBBCCKn+qJFOSBFeXl7o169fha65evUqBg4ciDp16kBdXR0WFhbw9vbGnTt3Srxm9+7daNy4MaRSKUJCQhAWFvZFJrYSQgghpGqiRjohn+Ho0aNo164dcnJyEB4eDolEgh07dkAsFmPWrFklXufl5YWCggLEx8cXW6aREEIIIYQmjhJSgs6dO8Pa2hrq6urYvHkz1NTU4Ovri9mzZwMAsrOzMWLECPTs2ZO37GODBg3Qtm1b3vAWAIiPj0dgYCCSk5PRokULhIaGonHjxl/xiQghhBBSVVBPOiGl2LZtGzQ1NXHx4kWEhIRg7ty5OHXqFADg5MmTePnyJQICAuRe+/HwlRkzZmDZsmW4cuUKVFRUKrSiS05ODjIzM3kHIYQQQqovaqQTUgpra2sEBwfD3Nwcw4cPh52dHaKiogAAKSkpAABLS8tylbVgwQI4OjrCysoK06dPR1xcHN6/f1+uaxcuXAixWMwdxsbGn/ZAhBBCCKkSqJFOSCmsra15rw0NDfH8+XMAQEVXLy1alqGhIQBwZZUlKCgIUqmUOx4/flyhexNCCCGkaqFGOiGlUFVV5b0WCASQyWQAAAsLCwDArVu3KlyWQCAAAK6ssgiFQujo6PAOQgghhFRf1Egn5BN169YN+vr6CAkJkXv+44mjhBBCCCHlRY10Qj6RpqYmNm/ejGPHjqFv3744ffo0UlNTceXKFQQEBMDX11fRVSSEEEJIFUWNdEI+g6urK+Li4qCqqgo3NzdYWlpi6NChkEqlmD9/vqKrRwghhJAqSsAqOvuNEKJwmZmZEIvFyMjIgK6urqKr890pKChASkoKzM3NoaysrOjqfFco9opDsVcsir/iVGbsC/9+S6XSMueXUU86IfgwkfPQoUOKrgYhhBBCCABqpJNvjJeXFwQCQbGje/fuXB4fHx80atQIIpEItWrVgqura5krrHh5eaFfv34lnk9LS0OPHj0q6zEIIYQQQj6LiqIrQMjHunfvjtDQUF6aUCjk/t2qVSu4u7vDxMQEGRkZmD17Nrp164YHDx588s9QBgYGn1VnQgghhJDKRD3p5JsjFAphYGDAO4qOux4zZgw6deoEU1NT2NraYv78+Xj8+DFSU1M/+Z4fD3eJi4tDixYtoK6uDjs7Oxw6dAgCgQCJiYkAPoxPGzVqFBo0aACRSITGjRtj1apVvDLPnDmDNm3aQFNTEzVq1ICDgwMePnzInT9y5AhatWoFdXV1NGzYEHPmzEF+fv4nPwMhhBBCqg/qSSdV2tu3bxEaGooGDRrA2Ni4Usp88+YN+vTpg549e2LXrl14+PAhJk2axMsjk8lQr1497Nu3D/r6+oiLi8OYMWNgaGiIQYMGIT8/H/369YO3tzd2796N3NxcXLp0idvE6OTJk/Dw8MDq1avRsWNH3Lt3D2PGjAEABAcHF6tTTk4OcnJyuNeZmZmV8qyEEEII+TZRTzr55hw9ehRaWlq8Y968ebw869at485FRkbi1KlTUFNTq5T7h4eHQyAQYNOmTbCyskKPHj0wbdo0Xh5VVVXMmTMHrVu3RoMGDeDu7g4vLy/s27cPwIdGtFQqRe/evdGoUSM0adIEnp6eMDExAQAsWLAA06dPh6enJxo2bAhnZ2fMmzcPGzdulFunhQsXQiwWc0dlfSEhhBBCyLeJetLJN8fJyQnr16/npdWsWZP32t3dHc7OzkhLS8PSpUsxaNAgnDt3Durq6p99/9u3b8Pa2ppXVps2bYrl27BhAzZv3oyHDx/i3bt3yM3NRYsWLbj6enl5wcXFBc7Ozvjhhx8waNAgGBoaAgDi4+Nx+fJlLFiwgCuvoKAA79+/R3Z2NjQ0NHj3CgoKws8//8y9zszMpIY6IYQQUo1RI518czQ1NWFmZlZqnsIeZXNzc7Rr1w66uro4ePAghg4d+tn3Z4xxw1KKphW1b98+TJ48GcuWLYO9vT20tbWxZMkSXLx4kcsTGhoKf39/REZGYu/evZg5cyZOnTqFdu3aQSaTYc6cOejfv3+x+8v7oiEUCnmTZwkhhBBSvVEjnVQLjDHemO3PYWlpifDwcOTk5HAN4ytXrvDynD17Fu3bt4efnx+Xdu/evWJltWzZEi1btkRQUBDs7e2xa9cutGvXDra2trh9+3aZX0YIIYQQ8n2iRjr55uTk5CA9PZ2XpqKiAn19fdy/fx979+5Ft27dUKtWLTx9+hSLFy+GSCRCz549Sy1XKpVyq7MUqlmzJjdOvJCbmxtmzJiBMWPGYPr06Xj06BGWLl0KAFwPu5mZGbZv346TJ0+iQYMG2LFjBy5fvowGDRoAAB48eIA//vgDffv2hZGREW7fvo07d+5g+PDhAIBff/0VvXv3hrGxMQYOHAglJSVcu3YN169fx/z58z85doQQQgipHqiRTr45kZGR3NjtQo0bN8atW7egrq6Os2fPYuXKlXj16hXq1KmDTp06IS4uDrVr1y613DNnzqBly5a8NE9PT4SFhfHSdHR0cOTIEYwdOxYtWrRA8+bN8euvv8LNzY0biuLr64vExEQMHjwYAoEAQ4cOhZ+fH06cOAEA0NDQwK1bt7Bt2zb8999/MDQ0xPjx4+Hj4wMAcHFxwdGjRzF37lyEhIRAVVUVlpaWGD169OeEjhBCCCHVhIB9PNiWEFJMeHg4RowYAalUCpFIpOjqIDMzE2KxGBkZGbw15MnXUVBQgJSUFJibm3/yBlrk01DsFYdir1gUf8WpzNgX/v2WSqXQ0dEpNS/1pBMix/bt29GwYUPUrVsXSUlJCAwMxKBBg76JBjohhBBCqj9aJ50QOdLT0+Hh4YEmTZpg8uTJGDhwIP744w9entmzZ3NLLgKAl5cX+vXr93UrSgghhJBqiRrp5Lvw/Plz+Pj4wMTEBEKhEAYGBnBxccH58+fl5g8ICEBqairev3+PBw8eYMWKFcXWLp86dSqioqK+RvUJIYQQ8p2h4S7kuzBgwADk5eVh27ZtaNiwIf79919ERUUhIyPjk8ss3PGUEEIIIaSyUU86qfZev36N2NhYLF68GE5OTqhfvz7atGmDoKAg9OrVC8CHpRU3btyI3r17Q0NDA02aNMH58+dx9+5ddO7cGZqamrC3t+ethf7xcJePMcYQEhKChg0bQiQSwcbGBn/++Sd3/tWrV3B3d0etWrUgEolgbm6O0NBQuWXl5OQgMzOTdxBCCCGk+qJGOqn2Cnu8Dx06VOqGR/PmzcPw4cORmJgIS0tLuLm5wcfHB0FBQdxmRuPHjy/3fWfOnInQ0FCsX78eN2/exOTJk+Hh4YGYmBgAwKxZs5CcnIwTJ05AIpFg/fr10NfXl1vWwoULuV1WxWIxjI2NKxABQgghhFQ1NNyFVHsqKioICwuDt7c3NmzYAFtbWzg6OmLIkCGwtrbm8o0YMQKDBg0CAAQGBsLe3h6zZs2Ci4sLAGDixIkYMWJEue759u1bLF++HP/73/9gb28PAGjYsCFiY2OxceNGODo64tGjR2jZsiXs7OwAAKampiWWFxQUhJ9//pl7nZmZSQ11QgghpBqjnnTyXRgwYACePXuGw4cPw8XFBWfOnIGtrS1vI6OiDfY6deoAAJo3b85Le//+fbmGmiQnJ+P9+/dwdnbmevK1tLSwfft2bsjM2LFjsWfPHrRo0QIBAQGIi4srsTyhUAgdHR3eQQghhJDqi3rSyXdDXV0dzs7OcHZ2xq+//orRo0cjODgYXl5eAABVVVUur0AgKDFNJpOVea/CPMeOHUPdunV554RCIQCgR48eePjwIY4dO4bTp0+ja9euGDduHJYuXfrpD0kIIYSQaoF60sl3y8rKCm/fvv1iZQuFQjx69AhmZma8o+gwlVq1asHLyws7d+7EypUri63FTgghhJDvE/Wkk2rvv//+w8CBAzFy5EhYW1tDW1sbV65cQUhICFxdXb/IPbW1tTF16lRMnjwZMpkMHTp0QGZmJuLi4qClpQVPT0/8+uuvaNWqFZo2bYqcnBwcPXoUTZo0+SL1IYQQQkjVQo10Uu1paWmhbdu2WLFiBe7du4e8vDwYGxvD29sbv/zyyxe777x581C7dm0sXLgQ9+/fR40aNWBra8vdU01NDUFBQUhNTYVIJELHjh2xZ8+eL1YfQgghhFQdAsYYU3QlCCEVk5mZCbFYjIyMDOjq6iq6Ot+dgoICpKSkwNzcHMrKyoquzneFYq84FHvFovgrTmXGvvDvt1QqLXMRCBqTTshHOnfujEmTJim6GoQQQgj5jlEjnVQbJTWuDx06xK3MUh4RERGYN29eJdasZAKBAIcOHfoq9yKEEEJI1UFj0gn5SM2aNT+7jLy8PN7yjYQQQgghFUE96eS7Mnv2bLRo0QI7duyAqakpxGIxhgwZgjdv3nB5Pu6RNzU1xbx58+Dm5gYtLS0YGRlhzZo1vHIFAgE2bNgAV1dXaGpqYv78+QCA9evXo1GjRlBTU0Pjxo2xY8cOXrkA8OOPP0IgEJS64yghhBBCvi/USCffnXv37uHQoUM4evQojh49ipiYGCxatKjUa5YsWQJra2skJCQgKCgIkydPxqlTp3h5goOD4erqiuvXr2PkyJE4ePAgJk6ciClTpuDGjRvw8fHBiBEjEB0dDQC4fPkyACA0NBRpaWnca3lycnKQmZnJOwghhBBSfdFwF/LdkclkCAsLg7a2NgBg2LBhiIqKwoIFC0q8xsHBAdOnTwcAWFhY4Ny5c1ixYgWcnZ25PG5ubhg5ciTvtZeXF/z8/AAAP//8My5cuIClS5fCyckJtWrVAgDUqFEDBgYGpdZ54cKFmDNnzqc9MCGEEEKqHOpJJ98dU1NTroEOAIaGhnj+/Hmp19jb2xd7LZFIeGl2dna81xKJBA4ODrw0BweHYteVR1BQEKRSKXc8fvy4wmUQQgghpOqgnnRSbejo6EAqlRZLf/36NW8t0o8ndAoEAshksgrf7+MVYzQ1NcvMwxir0EozhYRCIYRCYYWvI4QQQkjVRD3ppNqwtLTElStXiqVfvnwZjRs3/qyyL1y4UOy1paVlqdc0adIEsbGxvLS4uDg0adKEe62qqoqCgoLPqhshhBBCqh/qSSfVhp+fH9auXYtx48ZhzJgxEIlEOHXqFLZs2cJbVeVTnDt3DiEhIejXrx9OnTqF/fv349ixY6VeM23aNAwaNAi2trbo2rUrjhw5goiICJw+fZrLY2pqiqioKDg4OEAoFNLuoYQQQggBQD3ppBoxNTXF2bNnce/ePXTr1g2tW7dGWFgYwsLCMHDgwM8qe8qUKYiPj0fLli0xb948LFu2DC4uLqVe069fP6xatQpLlixB06ZNsXHjRoSGhqJz585cnmXLluHUqVMwNjZGy5YtP6uOhBBCCKk+BIwxpuhKEPItMzU1xaRJk+TuZqoomZmZEIvFyMjIoN53BSgoKEBKSgrMzc2hrKys6Op8Vyj2ikOxVyyKv+JUZuwL/35LpVLefDl5qCedkE+UmpoKgUCAxMRERVeFEEIIIdUMNdJJmdLT0zFhwgQ0bNgQQqEQxsbG6NOnD6KiohRdtW/ex7uXdu7cGQKBAAKBAEKhEHXr1kWfPn0QERGhuEoSQggh5JtDE0dJqVJTU+Hg4IAaNWogJCQE1tbWyMvLw8mTJzFu3DjcunVL0VX84lJTUyu1PG9vb8ydOxd5eXl4+vQpDh48iCFDhsDLywt//PFHpd6LEEIIIVUT9aSTUvn5+UEgEODSpUv46aefYGFhgaZNm3K7ZxZ69OgRXF1doaWlBR0dHQwaNAj//vsvd3727Nlo0aIFtm7dChMTE2hpaWHs2LEoKChASEgIDAwMULt27WK7fgoEAqxfvx49evSASCRCgwYNsH//fl6e69evo0uXLhCJRNDT08OYMWOQlZXFnf+4Nxv4MKnTy8uLe21qaorffvsNI0eOhLa2NkxMTIo1mC9duoSWLVtCXV0ddnZ2uHr16ifFVENDAwYGBjA2Nka7du2wePFibNy4EZs2beKt/EIIIYSQ7xc10kmJMjIyEBkZiXHjxsndqKdGjRoAPmzQ069fP2RkZCAmJganTp3CvXv3MHjwYF7+e/fu4cSJE4iMjMTu3buxdetW9OrVC0+ePEFMTAwWL16MmTNnFluTfNasWRgwYACSkpLg4eGBoUOHcrt2Zmdno3v37tDV1cXly5exf/9+nD59GuPHj6/w8y5btoxrfPv5+WHs2LHcLwVv375F79690bhxY8THx2P27NmYOnVqhe9REk9PT+jq6pY47CUnJweZmZm8gxBCCCHVFzXSSYnu3r0LxliZm/acPn0a165dw65du9CqVSu0bdsWO3bsQExMDC5fvszlk8lk2Lp1K6ysrNCnTx84OTnh9u3bWLlyJRo3bowRI0agcePGOHPmDK/8gQMHYvTo0bCwsMC8efNgZ2eHNWvWAADCw8Px7t07bN++Hc2aNUOXLl2wdu1a7Nixg9eTXx49e/aEn58fzMzMEBgYCH19fa4u4eHhKCgowNatW9G0aVP07t0b06ZNq1D5pVFSUoKFhUWJQ2sWLlwIsVjMHcbGxpV2b0IIIYR8e6iRTkpUuDpnWdvYSyQSGBsb8xqOVlZWqFGjBtfjDXwYUqKtrc29rlOnDqysrKCkpMRLe/78Oa98e3v7Yq8Ly5VIJLCxseH19Ds4OEAmk+H27dvlfVQAgLW1NfdvgUAAAwMDri6F99HQ0CixXp+LMVZirIOCgiCVSrnj8ePHlXpvQgghhHxbqJFOSmRubg6BQMBraMtTUuPy43RVVVXeeYFAIDdNJpOVWbfCcktr2BamKykp4ePtAPLy8orlL60uX3o7gcI1WBs0aCD3vFAohI6ODu8ghBBCSPVFjXRSopo1a8LFxQW///473r59W+z869evAXzoNX/06BGvdzc5ORlSqRRNmjT57Hp8PEb9woUL3BAcKysrJCYm8up37tw5bvgIANSqVQtpaWnc+YKCAty4caNCdbCyskJSUhLevXtXYr0+x7Zt2/Dq1SsMGDCg0sokhBBCSNVFjXRSqnXr1qGgoABt2rTBgQMHkJKSAolEgtWrV3PDPX744QdYW1vD3d0dCQkJuHTpEoYPHw5HR0fY2dl9dh3279+PrVu34s6dOwgODsalS5e4iaHu7u5QV1eHp6cnbty4gejoaEyYMAHDhg1DnTp1AABdunTBsWPHcOzYMdy6dQt+fn7cF4zycnNzg5KSEkaNGoXk5GQcP34cS5cu/aTnyc7ORnp6Op48eYKLFy8iMDAQvr6+GDt2LJycnD6pTEIIIYRUL7ROOilVgwYNkJCQgAULFmDKlClIS0tDrVq10KpVK6xfvx7Ah2Ehhw4dwoQJE9CpUycoKSmhe/fu3OTOzzVnzhzs2bMHfn5+MDAwQHh4OKysrAB8WM7w5MmTmDhxIlq3bg0NDQ0MGDAAy5cv564fOXIkkpKSMHz4cKioqGDy5MkVbgxraWnhyJEj8PX1RcuWLWFlZYXFixd/Us/3pk2bsGnTJqipqUFPTw+tWrXC3r178eOPP5a7jMLhN5mZmbQ9tAIUFBQgKyuL4q8AFHvFodgrFsVfcSoz9oWrs5VnGK2AfenBtoR8BoFAgIMHD6Jfv36Krso35f79+2jUqJGiq0EIIYSQT/D48WPUq1ev1DzUk05IFVSzZk0AHzaREovFCq7N9yczMxPGxsZ4/PgxTeL9yij2ikOxVyyKv+JUZuwZY3jz5g2MjIzKzEuNdEKqoMJlK8ViMf3PWoFopR3FodgrDsVesSj+ilNZsS9v5xo10sk3jUZjEUIIIeR7RKu7EEIIIYQQ8o2hRjohVZBQKERwcDCEQqGiq/JdovgrDsVecSj2ikXxVxxFxZ5WdyGEEEIIIeQbQz3phBBCCCGEfGOokU4IIYQQQsg3hhrphBBCCCGEfGOokU4IIYQQQsg3hhrphBBCCCGEfGOokU5IFbRu3To0aNAA6urqaNWqFc6ePavoKlU7CxcuROvWraGtrY3atWujX79+uH37Ni8PYwyzZ8+GkZERRCIROnfujJs3byqoxtXXwoULIRAIMGnSJC6NYv9lPX36FB4eHtDT04OGhgZatGiB+Ph47jzF/8vIz8/HzJkz0aBBA4hEIjRs2BBz586FTCbj8lDsK88///yDPn36wMjICAKBAIcOHeKdL0+sc3JyMGHCBOjr60NTUxN9+/bFkydPKqV+1EgnpIrZu3cvJk2ahBkzZuDq1avo2LEjevTogUePHim6atVKTEwMxo0bhwsXLuDUqVPIz89Ht27d8PbtWy5PSEgIli9fjrVr1+Ly5cswMDCAs7Mz3rx5o8CaVy+XL1/GH3/8AWtra146xf7LefXqFRwcHKCqqooTJ04gOTkZy5YtQ40aNbg8FP8vY/HixdiwYQPWrl0LiUSCkJAQLFmyBGvWrOHyUOwrz9u3b2FjY4O1a9fKPV+eWE+aNAkHDx7Enj17EBsbi6ysLPTu3RsFBQWfX0FGCKlS2rRpw3x9fXlplpaWbPr06Qqq0ffh+fPnDACLiYlhjDEmk8mYgYEBW7RoEZfn/fv3TCwWsw0bNiiqmtXKmzdvmLm5OTt16hRzdHRkEydOZIxR7L+0wMBA1qFDhxLPU/y/nF69erGRI0fy0vr37888PDwYYxT7LwkAO3jwIPe6PLF+/fo1U1VVZXv27OHyPH36lCkpKbHIyMjPrhP1pBNSheTm5iI+Ph7dunXjpXfr1g1xcXEKqtX3QSqVAgBq1qwJAHjw4AHS09N574VQKISjoyO9F5Vk3Lhx6NWrF3744QdeOsX+yzp8+DDs7OwwcOBA1K5dGy1btsSmTZu48xT/L6dDhw6IiorCnTt3AABJSUmIjY1Fz549AVDsv6byxDo+Ph55eXm8PEZGRmjWrFmlvB8qn10CIeSrefnyJQoKClCnTh1eep06dZCenq6gWlV/jDH8/PPP6NChA5o1awYAXLzlvRcPHz786nWsbvbs2YOEhARcvny52DmK/Zd1//59rF+/Hj///DN++eUXXLp0Cf7+/hAKhRg+fDjF/wsKDAyEVCqFpaUllJWVUVBQgAULFmDo0KEA6LP/NZUn1unp6VBTU4Ourm6xPJXxN5ka6YRUQQKBgPeaMVYsjVSe8ePH49q1a4iNjS12jt6Lyvf48WNMnDgRf//9N9TV1UvMR7H/MmQyGezs7PDbb78BAFq2bImbN29i/fr1GD58OJeP4l/59u7di507d2LXrl1o2rQpEhMTMWnSJBgZGcHT05PLR7H/ej4l1pX1ftBwF0KqEH19fSgrKxf7hv78+fNi3/ZJ5ZgwYQIOHz6M6Oho1KtXj0s3MDAAAHovvoD4+Hg8f/4crVq1goqKClRUVBATE4PVq1dDRUWFiy/F/sswNDSElZUVL61Jkybc5HT67H8506ZNw/Tp0zFkyBA0b94cw4YNw+TJk7Fw4UIAFPuvqTyxNjAwQG5uLl69elVins9BjXRCqhA1NTW0atUKp06d4qWfOnUK7du3V1CtqifGGMaPH4+IiAj873//Q4MGDXjnGzRoAAMDA957kZubi5iYGHovPlPXrl1x/fp1JCYmcoednR3c3d2RmJiIhg0bUuy/IAcHh2LLjd65cwf169cHQJ/9Lyk7OxtKSvymmbKyMrcEI8X+6ylPrFu1agVVVVVenrS0NNy4caNy3o/PnnpKCPmq9uzZw1RVVdmWLVtYcnIymzRpEtPU1GSpqamKrlq1MnbsWCYWi9mZM2dYWload2RnZ3N5Fi1axMRiMYuIiGDXr19nQ4cOZYaGhiwzM1OBNa+eiq7uwhjF/ku6dOkSU1FRYQsWLGApKSksPDycaWhosJ07d3J5KP5fhqenJ6tbty47evQoe/DgAYuIiGD6+vosICCAy0Oxrzxv3rxhV69eZVevXmUA2PLly9nVq1fZw4cPGWPli7Wvry+rV68eO336NEtISGBdunRhNjY2LD8//7PrR410Qqqg33//ndWvX5+pqakxW1tbbllAUnkAyD1CQ0O5PDKZjAUHBzMDAwMmFApZp06d2PXr1xVX6Wrs40Y6xf7LOnLkCGvWrBkTCoXM0tKS/fHHH7zzFP8vIzMzk02cOJGZmJgwdXV11rBhQzZjxgyWk5PD5aHYV57o6Gi5/5/39PRkjJUv1u/evWPjx49nNWvWZCKRiPXu3Zs9evSoUuonYIyxz++PJ4QQQgghhFQWGpNOCCGEEELIN4Ya6YQQQgghhHxjqJFOCCGEEELIN4Ya6YQQQgghhHxjqJFOCCGEEELIN4Ya6YQQQgghhHxjqJFOCCGEEELIN4Ya6YQQQgghhHxjqJFOCCGEEELIN4Ya6YQQQgghhHxjqJFOCCGEEELIN+b/AdPaUG/eUw58AAAAAElFTkSuQmCC", "text/plain": [ - "Compound ID 0.000000\n", - "Uniprot 0.000000\n", - "Smiles 0.000000\n", - "E3 Ligase 0.000000\n", - "InChI 0.000000\n", - "InChI Key 0.000000\n", - "Molecular Weight 0.000000\n", - "Heavy Atom Count 0.000000\n", - "Ring Count 0.000000\n", - "Rotatable Bond Count 0.000000\n", - "Topological Polar Surface Area 0.000000\n", - "Hydrogen Bond Acceptor Count 0.000000\n", - "Hydrogen Bond Donor Count 0.000000\n", - "Cell Type 4.110229\n", - "Treatment Time (h) 10.695936\n", - "DC50 (nM) 36.945353\n", - "Dmax (%) 62.073797\n", - "Active 49.229332\n", - "Article DOI 0.140121\n", - "Comments 82.858477\n", - "Database 0.000000\n", - "Molecular Formula 0.000000\n", - "cLogP 56.795890\n", - "Target 43.204110\n", - "PDB 98.972443\n", - "Name 73.610462\n", - "Assay (DC50/Dmax) 43.204110\n", - "Exact Mass 43.204110\n", - "XLogP3 43.204110\n", - "Target (Parsed) 43.204110\n", - "dtype: float64" + "
" ] }, - "execution_count": 99, "metadata": {}, - "output_type": "execute_result" + "output_type": "display_data" } ], "source": [ "# Print NaN percentage per column\n", - "merged_df.isna().sum() / len(merged_df) * 100" + "tmp = merged_df.isna().sum() / len(merged_df) * 100\n", + "# Plot tmp as a horizontal bar plot\n", + "tmp.plot(kind='barh')\n", + "plt.title('Percentage of NaN values per column')\n", + "plt.grid(axis='x', alpha=0.5)\n", + "plt.show()\n", + "\n", + "# plt.figure(figsize=(10, 5))\n", + "# sns.barplot(x=tmp.index, y=tmp.values)\n", + "# plt.xticks(rotation=90)\n", + "# plt.title('NaN percentage per column')\n", + "# plt.grid(axis='y', alpha=0.5)\n", + "# plt.show()" ] }, { "cell_type": "code", - "execution_count": 100, + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
Compound IDTargetCell TypeAssay (DC50/Dmax)
227250NaNNaNNaN
229252NaNNaNNaN
230253NaNNaNNaN
231254NaNNaNNaN
232255NaNNaNNaN
...............
1089340BRD4NaNDegradation of BRD4 BD1/2 assessed by EGFP/mCh...
1090342BRD4 BD1NaNDegradation of BRD4 BD1 assessed by EGFP/mCher...
1091343BRD4NaNDegradation of BRD4 BD1/2 assessed by EGFP/mCh...
1092343BRD4NaNDegradation of BRD4 BD1/2 assessed by EGFP/mCh...
1093350BRD4 BD1NaNDegradation of BRD4 BD1 assessed by EGFP/mCher...
\n", + "

88 rows × 4 columns

\n", + "
" + ], + "text/plain": [ + " Compound ID Target Cell Type \\\n", + "227 250 NaN NaN \n", + "229 252 NaN NaN \n", + "230 253 NaN NaN \n", + "231 254 NaN NaN \n", + "232 255 NaN NaN \n", + "... ... ... ... \n", + "1089 340 BRD4 NaN \n", + "1090 342 BRD4 BD1 NaN \n", + "1091 343 BRD4 NaN \n", + "1092 343 BRD4 NaN \n", + "1093 350 BRD4 BD1 NaN \n", + "\n", + " Assay (DC50/Dmax) \n", + "227 NaN \n", + "229 NaN \n", + "230 NaN \n", + "231 NaN \n", + "232 NaN \n", + "... ... \n", + "1089 Degradation of BRD4 BD1/2 assessed by EGFP/mCh... \n", + "1090 Degradation of BRD4 BD1 assessed by EGFP/mCher... \n", + "1091 Degradation of BRD4 BD1/2 assessed by EGFP/mCh... \n", + "1092 Degradation of BRD4 BD1/2 assessed by EGFP/mCh... \n", + "1093 Degradation of BRD4 BD1 assessed by EGFP/mCher... \n", + "\n", + "[88 rows x 4 columns]" + ] + }, + "execution_count": 38, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# List the Nan cell types in merged_df\n", + "merged_df[merged_df['Cell Type'].isna()][['Compound ID', 'Target', 'Cell Type', 'Assay (DC50/Dmax)']]" + ] + }, + { + "cell_type": "code", + "execution_count": 39, "metadata": {}, "outputs": [ { @@ -5519,7 +5857,33 @@ }, { "cell_type": "code", - "execution_count": 101, + "execution_count": 40, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plot active vs inactive in merged_df\n", + "sns.countplot(data=merged_df, x='Active')\n", + "# Put the number of active and inactive on top of the bars\n", + "for i, count in enumerate(merged_df['Active'].value_counts()):\n", + " plt.text(i, count, count, ha='center', va='bottom')\n", + "plt.title('Active vs Inactive')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 41, "metadata": {}, "outputs": [ { @@ -5528,7 +5892,7 @@ "[]" ] }, - "execution_count": 101, + "execution_count": 41, "metadata": {}, "output_type": "execute_result" } @@ -5539,7 +5903,7 @@ }, { "cell_type": "code", - "execution_count": 102, + "execution_count": 42, "metadata": {}, "outputs": [ { @@ -5548,7 +5912,7 @@ "[]" ] }, - "execution_count": 102, + "execution_count": 42, "metadata": {}, "output_type": "execute_result" } @@ -5560,7 +5924,7 @@ }, { "cell_type": "code", - "execution_count": 103, + "execution_count": 43, "metadata": {}, "outputs": [ { @@ -5621,7 +5985,7 @@ "[0 rows x 30 columns]" ] }, - "execution_count": 103, + "execution_count": 43, "metadata": {}, "output_type": "execute_result" } @@ -5632,30 +5996,7 @@ }, { "cell_type": "code", - "execution_count": 104, - "metadata": {}, - "outputs": [ - { - "data": { - "image/png": "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", - "text/plain": [ - "
" - ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "# Plot active distribution\n", - "sns.histplot(data=merged_df, x='Active', bins=16)\n", - "plt.title('Histogram of Active')\n", - "plt.show()" - ] - }, - { - "cell_type": "code", - "execution_count": 105, + "execution_count": 44, "metadata": {}, "outputs": [], "source": [ @@ -5675,7 +6016,7 @@ }, { "cell_type": "code", - "execution_count": 106, + "execution_count": 45, "metadata": {}, "outputs": [], "source": [ @@ -5704,13 +6045,13 @@ }, { "cell_type": "code", - "execution_count": 107, + "execution_count": 46, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "711005125bf74309a3262f711bc11c4c", + "model_id": "8ac0afc72e254a3fb0dd7efeca7cb3ac", "version_major": 2, "version_minor": 0 }, @@ -5757,7 +6098,7 @@ }, { "cell_type": "code", - "execution_count": 108, + "execution_count": 47, "metadata": {}, "outputs": [], "source": [ @@ -5782,7 +6123,7 @@ }, { "cell_type": "code", - "execution_count": 109, + "execution_count": 48, "metadata": {}, "outputs": [], "source": [ @@ -5857,7 +6198,7 @@ }, { "cell_type": "code", - "execution_count": 110, + "execution_count": 49, "metadata": {}, "outputs": [ { @@ -5991,7 +6332,7 @@ }, { "cell_type": "code", - "execution_count": 126, + "execution_count": 50, "metadata": {}, "outputs": [ { @@ -6010,7 +6351,7 @@ " 'FEM1B']" ] }, - "execution_count": 126, + "execution_count": 50, "metadata": {}, "output_type": "execute_result" } @@ -6021,7 +6362,7 @@ }, { "cell_type": "code", - "execution_count": 127, + "execution_count": 51, "metadata": {}, "outputs": [ { @@ -6041,7 +6382,7 @@ "Name: E3 Ligase Uniprot, Length: 2141, dtype: object" ] }, - "execution_count": 127, + "execution_count": 51, "metadata": {}, "output_type": "execute_result" } @@ -6071,13 +6412,13 @@ }, { "cell_type": "code", - "execution_count": 128, + "execution_count": 52, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "39433e15aef54103bff4aec5c3c6d06e", + "model_id": "79f14bb2b87d45b2ad1902d11cd6c341", "version_major": 2, "version_minor": 0 }, @@ -6121,7 +6462,7 @@ }, { "cell_type": "code", - "execution_count": 130, + "execution_count": 53, "metadata": {}, "outputs": [ { @@ -6149,7 +6490,7 @@ }, { "cell_type": "code", - "execution_count": 114, + "execution_count": 54, "metadata": {}, "outputs": [ { @@ -6204,13 +6545,13 @@ }, { "cell_type": "code", - "execution_count": 115, + "execution_count": 55, "metadata": {}, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "e1e8cc3fc7dc48b89db7c34e00dcd158", + "model_id": "27356213a53b463996e9bd4ef93e35bc", "version_major": 2, "version_minor": 0 }, @@ -6272,7 +6613,7 @@ }, { "cell_type": "code", - "execution_count": 118, + "execution_count": 56, "metadata": {}, "outputs": [ { @@ -6378,7 +6719,7 @@ "[181 rows x 2 columns]" ] }, - "execution_count": 118, + "execution_count": 56, "metadata": {}, "output_type": "execute_result" } @@ -6395,18 +6736,122 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Save to HF Dataset" + "## Apply Active - ORed Version" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": {}, + "outputs": [], + "source": [ + "merged_df['Active - OR'] = merged_df.apply(\n", + " lambda row: is_active(row['DC50 (nM)'], row['Dmax (%)'], oring=True), axis=1,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plot the number of \n", + "\n", + "# Plot the number of NaN values in Dmax and DC50 columns\n", + "tmp = merged_df[['DC50 (nM)', 'Dmax (%)']].isna().sum()\n", + "tmp.plot(kind='bar')\n", + "plt.title('Number of NaN values in DC50 and Dmax columns')\n", + "plt.grid(axis='y', alpha=0.5)\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# plot the columns Active and 'Active - OR' side by side\n", + "fig, axes = plt.subplots(1, 2, figsize=(10, 5))\n", + "axes[0].set_title('Active')\n", + "axes[1].set_title('Active - OR')\n", + "sns.countplot(data=merged_df, x='Active', ax=axes[0])\n", + "sns.countplot(data=merged_df, x='Active - OR', ax=axes[1])\n", + "# Add the number of active and inactive on top of the bars\n", + "for i, count in enumerate(merged_df['Active'].value_counts()):\n", + " axes[0].text(i, count, count, ha='center', va='bottom')\n", + "for i, count in enumerate(merged_df['Active - OR'].value_counts()):\n", + " axes[1].text(i, count, count, ha='center', va='bottom')\n", + "plt.show()" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# Plot the percentage of rows for which the columns 'Active' and 'Active - OR' are different\n", + "\n", + "# Isolate the ones having Active not nan\n", + "merged_df_active = merged_df[merged_df['Active'].notnull()]\n", + "\n", + "tmp = (merged_df_active['Active'] != merged_df_active['Active - OR']).sum() / len(merged_df_active) * 100\n", + "plt.bar(['Different', 'Equal'], [tmp, 100-tmp])\n", + "plt.title('Percentage of rows for which \"Active\" and \"Active - OR\" are different')\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Save to HF Dataset (TODO)" ] }, { "cell_type": "code", - "execution_count": 131, + "execution_count": 61, "metadata": {}, "outputs": [], "source": [ "# Save to csv\n", "merged_df.to_csv(\n", - " os.path.join(data_dir, 'processed', 'PROTAC-Degradation-DB.csv'),\n", + " os.path.join(data_dir, 'PROTAC-Degradation-DB.csv'),\n", " index=False,\n", ")" ]