Merge pull request #200 from cloudcell/master

changes to column particle size and id for datasets 0260, 0261

processed_data/0260/0260_rtdata_isomeric_success.tsv

@@ -30,7 +30,7 @@ id	name	formula	rt	smiles.std	inchi.std	inchikey.std	classyfire.kingdom	classyfi
 0260_00244	Oxamyl	C7H13N3O3S	7.936	CNC(=O)O/N=C(\C(=O)N(C)C)/SC	InChI=1S/C7H13N3O3S/c1-8-7(12)13-9-5(14-4)6(11)10(2)3/h1-4H3,(H,8,12)/b9-5+	KZAUOCCYDRDERY-WEVVVXLNSA-N	Organic compounds (CHEMONTID:0000000)	Organic acids and derivatives (CHEMONTID:0000264)	Carboxylic acids and derivatives (CHEMONTID:0000265)	Carboxylic acid derivatives (CHEMONTID:0001093)	Carboxylic acid amides (CHEMONTID:0000475)	Tertiary carboxylic acid amides (CHEMONTID:0001664)	
 0260_00254	Pymetrozine	C10H11N5O	6.198	CC1=NNC(=O)N(C1)/N=C\C2=CN=CC=C2	InChI=1S/C10H11N5O/c1-8-7-15(10(16)14-13-8)12-6-9-3-2-4-11-5-9/h2-6H,7H2,1H3,(H,14,16)/b12-6-	QHMTXANCGGJZRX-SDQBBNPISA-N	Organic compounds (CHEMONTID:0000000)	Organoheterocyclic compounds (CHEMONTID:0000002)	Triazines (CHEMONTID:0000098)	1,2,4-triazines (CHEMONTID:0004107)	NA (NA)	NA (NA)	
 0260_00259	Rotenone	C23H22O6	11.955	CC(=C)[C@H]1CC2=C(O1)C=CC3=C2O[C@@H]4COC5=CC(=C(C=C5[C@@H]4C3=O)OC)OC	InChI=1S/C23H22O6/c1-11(2)16-8-14-15(28-16)6-5-12-22(24)21-13-7-18(25-3)19(26-4)9-17(13)27-10-20(21)29-23(12)14/h5-7,9,16,20-21H,1,8,10H2,2-4H3/t16-,20-,21+/m1/s1	JUVIOZPCNVVQFO-HBGVWJBISA-N	Organic compounds (CHEMONTID:0000000)	Phenylpropanoids and polyketides (CHEMONTID:0000261)	Isoflavonoids (CHEMONTID:0002506)	Rotenoids (CHEMONTID:0001607)	Rotenones (CHEMONTID:0003528)	NA (NA)	
-0260_00264	Thiamethoxam	C8H10ClN5O3S	8.679	CN\1COCN(/C1=N\[N+](=O)[O-])CC2=CN=C(S2)Cl	InChI=1S/C8H10ClN5O3S/c1-12-4-17-5-13(8(12)11-14(15)16)3-6-2-10-7(9)18-6/h2H,3-5H2,1H3/b11-8-	NWWZPOKUUAIXIW-FLIBITNWSA-N	Organic compounds (CHEMONTID:0000000)	Organoheterocyclic compounds (CHEMONTID:0000002)	Azoles (CHEMONTID:0000436)	Thiazoles (CHEMONTID:0000095)	2,5-disubstituted thiazoles (CHEMONTID:0002635)	NA (NA)	
+0260_00264	Thiamethoxam	C8H10ClN5O3S	8.679	CN\1COCN(/C1=N\[N+](=O)[O-])CC2=CN=C(S2)Cl	InChI=1S/C8H10ClN5O3S/c1-12-4-17-5-13(8(12)11-14(15)16)3-6-2-10-7(9)18-6/h2H,3-5H2,1H3	NWWZPOKUUAIXIW-UHFFFAOYSA-N	Organic compounds (CHEMONTID:0000000)	Organoheterocyclic compounds (CHEMONTID:0000002)	Azoles (CHEMONTID:0000436)	Thiazoles (CHEMONTID:0000095)	2,5-disubstituted thiazoles (CHEMONTID:0002635)	NA (NA)	
 0260_00273	Aldicarb-sulfone (Aldoxycarb)	C7H14N2O4S	7.269	CC(C)(/C=N\OC(=O)NC)S(=O)(=O)C	InChI=1S/C7H14N2O4S/c1-7(2,14(4,11)12)5-9-13-6(10)8-3/h5H,1-4H3,(H,8,10)/b9-5-	YRRKLBAKDXSTNC-UITAMQMPSA-N	Organic compounds (CHEMONTID:0000000)	Organic nitrogen compounds (CHEMONTID:0004707)	Organonitrogen compounds (CHEMONTID:0000278)	Oxime carbamates (CHEMONTID:0004752)	NA (NA)	NA (NA)	
 0260_00279	Dikegulac	C12H18O7	9.108	CC1(OC[C@H]2[C@@H](O1)[C@H]3[C@@](O2)(OC(O3)(C)C)C(=O)O)C	InChI=1S/C12H18O7/c1-10(2)15-5-6-7(17-10)8-12(16-6,9(13)14)19-11(3,4)18-8/h6-8H,5H2,1-4H3,(H,13,14)/t6-,7+,8-,12+/m0/s1	FWCBATIDXGJRMF-FLNNQWSLSA-N	Organic compounds (CHEMONTID:0000000)	Organic oxygen compounds (CHEMONTID:0004603)	Organooxygen compounds (CHEMONTID:0000323)	Ethers (CHEMONTID:0000254)	Acetals (CHEMONTID:0001656)	Ketals (CHEMONTID:0004472)	
 0260_00287	Diallate	C10H17Cl2NOS	11.36	CC(C)N(C(C)C)C(=O)SC/C(=C/Cl)/Cl	InChI=1S/C10H17Cl2NOS/c1-7(2)13(8(3)4)10(14)15-6-9(12)5-11/h5,7-8H,6H2,1-4H3/b9-5-	SPANOECCGNXGNR-UITAMQMPSA-N	Organic compounds (CHEMONTID:0000000)	Organosulfur compounds (CHEMONTID:0000004)	Thiocarbonyl compounds (CHEMONTID:0001198)	Thiocarbamic acid derivatives (CHEMONTID:0001368)	NA (NA)	NA (NA)	

processed_data/0260/0260_validation_qspr_outliers.tsv

@@ -0,0 +1,63 @@
+id	error
+0260_00059	2.0943410021858186
+0260_00070	1.7614776266870873
+0260_00076	3.206897758208706
+0260_00078	3.704629991751398
+0260_00101	3.3600330529976734
+0260_00148	2.166984512108069
+0260_00149	6.76640627106201
+0260_00153	2.474847092879197
+0260_00172	1.9880768980103003
+0260_00202	1.706612314829142
+0260_00204	3.943344087902932
+0260_00207	2.487168147375107
+0260_00219	1.9859894558108557
+0260_00248	2.445186092789477
+0260_00254	2.5473292484548793
+0260_00259	1.9075176786330665
+0260_00281	2.250970770728033
+0260_00283	3.4683882560312043
+0260_00297	2.3472569424219314
+0260_00299	3.5088628839075016
+0260_00301	1.7325381193409841
+0260_00314	3.5043273096549408
+0260_00315	1.7720686365136036
+0260_00360	6.846466738441804
+0260_00369	3.974728197706219
+0260_00373	1.8935684110526712
+0260_00385	6.838700051813568
+0260_00401	3.096489506223662
+0260_00410	1.9249791398664557
+0260_00424	3.592981732312816
+0260_00431	1.867270688421688
+0260_00435	3.5166292468846554
+0260_00437	4.2368807577104555
+0260_00454	2.8656968296471517
+0260_00467	1.7468855181735279
+0260_00473	1.6563894307733724
+0260_00475	1.7637823875199574
+0260_00481	2.3580242227811463
+0260_00483	2.179029346716579
+0260_00497	2.977800498002214
+0260_00506	2.084571345923373
+0260_00509	4.494441079454905
+0260_00511	3.9252598456370427
+0260_00515	2.346494601853939
+0260_00516	4.4872026985663975
+0260_00517	2.1818000769959136
+0260_00535	3.6204921581508014
+0260_00536	1.8449333862438744
+0260_00537	6.689183429458863
+0260_00557	3.952661238628035
+0260_00567	2.7594770334061334
+0260_00581	2.570053410055693
+0260_00585	2.5372953663811186
+0260_00590	1.689095579453733
+0260_00596	3.083922057833143
+0260_00597	4.740149321030902
+0260_00604	2.789992290082929
+0260_00627	1.6935819352628148
+0260_00628	1.8123563362536363
+0260_00653	2.111223349671614
+0260_00655	1.8129431009185017
+0260_00656	2.3175574552037856