Add dataset ROASMI_85 (#196)

* added dataset ROASMI_85

* Preprocessing draft_45277

* properly sort SMILES into isomeric and canonical

* cleaned up missing data

* Preprocessing draft_45277

* [no ci] set IDs for newly submitted datasets: 0436; previously draft_45277

---------

Co-authored-by: Pablo Gago-Ferrero, Anna A. Bletsou, Dimitrios E. Damalas, Reza Aalizadeh, Nikiforos A.Alygizakis, Heinz P.Singer, Juliane Hollender, Nikolaos S. Thomaidis <No Mail provided>
Co-authored-by: Github Actions <[email protected]>
Co-authored-by: Fleming Kretschmer <[email protected]>

processed_data/0436/0436_gradient.tsv

@@ -0,0 +1,5 @@
+t [min]	flow rate [ml/min]	A [%]	B [%]
+0.1		99	1
+3		61	39
+14		0.1	99.9
+16		0.1	99.9

processed_data/0436/0436_info.tsv

@@ -0,0 +1,2 @@
+id	authors	name	comment	url
+0436	Pablo Gago-Ferrero, Anna A. Bletsou, Dimitrios E. Damalas, Reza Aalizadeh, Nikiforos A.Alygizakis, Heinz P.Singer, Juliane Hollender, Nikolaos S. Thomaidis 	ROASMI_85	flow rate:0.2-0.48, Submitted by Fangyuan Sun	10.1016/j.jhazmat.2019.121712

processed_data/0436/0436_metadata.tsv

@@ -0,0 +1,2 @@
+id	column.name	column.usp.code	column.length	column.id	column.particle.size	column.temperature	column.flowrate	column.t0	eluent.A.h2o	eluent.A.meoh	eluent.A.acn	eluent.A.iproh	eluent.A.acetone	eluent.A.hex	eluent.A.chcl3	eluent.A.ch2cl2	eluent.A.hept	eluent.A.formic	eluent.A.formic.unit	eluent.A.acetic	eluent.A.acetic.unit	eluent.A.trifluoroacetic	eluent.A.trifluoroacetic.unit	eluent.A.phosphor	eluent.A.phosphor.unit	eluent.A.nh4ac	eluent.A.nh4ac.unit	eluent.A.nh4form	eluent.A.nh4form.unit	eluent.A.nh4carb	eluent.A.nh4carb.unit	eluent.A.nh4bicarb	eluent.A.nh4bicarb.unit	eluent.A.nh4f	eluent.A.nh4f.unit	eluent.A.nh4oh	eluent.A.nh4oh.unit	eluent.A.trieth	eluent.A.trieth.unit	eluent.A.triprop	eluent.A.triprop.unit	eluent.A.tribut	eluent.A.tribut.unit	eluent.A.nndimethylhex	eluent.A.nndimethylhex.unit	eluent.A.medronic	eluent.A.medronic.unit	eluent.A.pH	eluent.B.h2o	eluent.B.meoh	eluent.B.acn	eluent.B.iproh	eluent.B.acetone	eluent.B.hex	eluent.B.chcl3	eluent.B.ch2cl2	eluent.B.hept	eluent.B.formic	eluent.B.formic.unit	eluent.B.acetic	eluent.B.acetic.unit	eluent.B.trifluoroacetic	eluent.B.trifluoroacetic.unit	eluent.B.phosphor	eluent.B.phosphor.unit	eluent.B.nh4ac	eluent.B.nh4ac.unit	eluent.B.nh4form	eluent.B.nh4form.unit	eluent.B.nh4carb	eluent.B.nh4carb.unit	eluent.B.nh4bicarb	eluent.B.nh4bicarb.unit	eluent.B.nh4f	eluent.B.nh4f.unit	eluent.B.nh4oh	eluent.B.nh4oh.unit	eluent.B.trieth	eluent.B.trieth.unit	eluent.B.triprop	eluent.B.triprop.unit	eluent.B.tribut	eluent.B.tribut.unit	eluent.B.nndimethylhex	eluent.B.nndimethylhex.unit	eluent.B.medronic	eluent.B.medronic.unit	eluent.B.pH	eluent.C.h2o	eluent.C.meoh	eluent.C.acn	eluent.C.iproh	eluent.C.acetone	eluent.C.hex	eluent.C.chcl3	eluent.C.ch2cl2	eluent.C.hept	eluent.C.formic	eluent.C.formic.unit	eluent.C.acetic	eluent.C.acetic.unit	eluent.C.trifluoroacetic	eluent.C.trifluoroacetic.unit	eluent.C.phosphor	eluent.C.phosphor.unit	eluent.C.nh4ac	eluent.C.nh4ac.unit	eluent.C.nh4form	eluent.C.nh4form.unit	eluent.C.nh4carb	eluent.C.nh4carb.unit	eluent.C.nh4bicarb	eluent.C.nh4bicarb.unit	eluent.C.nh4f	eluent.C.nh4f.unit	eluent.C.nh4oh	eluent.C.nh4oh.unit	eluent.C.trieth	eluent.C.trieth.unit	eluent.C.triprop	eluent.C.triprop.unit	eluent.C.tribut	eluent.C.tribut.unit	eluent.C.nndimethylhex	eluent.C.nndimethylhex.unit	eluent.C.medronic	eluent.C.medronic.unit	eluent.C.pH	eluent.D.h2o	eluent.D.meoh	eluent.D.acn	eluent.D.iproh	eluent.D.acetone	eluent.D.hex	eluent.D.chcl3	eluent.D.ch2cl2	eluent.D.hept	eluent.D.formic	eluent.D.formic.unit	eluent.D.acetic	eluent.D.acetic.unit	eluent.D.trifluoroacetic	eluent.D.trifluoroacetic.unit	eluent.D.phosphor	eluent.D.phosphor.unit	eluent.D.nh4ac	eluent.D.nh4ac.unit	eluent.D.nh4form	eluent.D.nh4form.unit	eluent.D.nh4carb	eluent.D.nh4carb.unit	eluent.D.nh4bicarb	eluent.D.nh4bicarb.unit	eluent.D.nh4f	eluent.D.nh4f.unit	eluent.D.nh4oh	eluent.D.nh4oh.unit	eluent.D.trieth	eluent.D.trieth.unit	eluent.D.triprop	eluent.D.triprop.unit	eluent.D.tribut	eluent.D.tribut.unit	eluent.D.nndimethylhex	eluent.D.nndimethylhex.unit	eluent.D.medronic	eluent.D.medronic.unit	eluent.D.pH	gradient.start.A	gradient.start.B	gradient.start.C	gradient.start.D	gradient.end.A	gradient.end.B	gradient.end.C	gradient.end.D
+0436	Thermo Scientific Acclaim RSLC 120 C18	L1	100	2.1	2.2	30		0	90	10	0	0	0	0	0	0	0	0.01	%	0		0		0		0		5	mM	0		0		0		0		0		0		0		0		0			0	100	0	0	0	0	0	0	0	0.01	%	0		0		0		0		5	mM	0		0		0		0		0		0		0		0		0			0	0	0	0	0	0	0	0	0	0		0		0		0		0		0		0		0		0		0		0		0		0		0		0			0	0	0	0	0	0	0	0	0	0		0		0		0		0		0		0		0		0		0		0		0		0		0		0			99	1	0	0	0.1	99.9	0	0

processed_data/0436/0436_metadata.yaml

@@ -0,0 +1,27 @@
+id: '0436'
+column:
+  name: Thermo Scientific Acclaim RSLC 120 C18
+  usp.code: L1
+  length: 100
+  id: 2.1
+  particle.size: 2.2
+  temperature: 30
+  t0: 0
+eluent:
+  A:
+    h2o: 90
+    meoh: 10
+    formic:
+      value: 0.01
+      unit: '%'
+    nh4form:
+      value: 5
+      unit: mM
+  B:
+    meoh: 100
+    formic:
+      value: 0.01
+      unit: '%'
+    nh4form:
+      value: 5
+      unit: mM

processed_data/0436/0436_validation_qspr_outliers.tsv

@@ -0,0 +1,67 @@
+id	error
+0436_00003	9.491415933170602
+0436_00052	2.3655632344244313
+0436_00059	4.141517975798225
+0436_00060	2.412791843437299
+0436_00165	2.509691557811794
+0436_00195	2.4654949283997922
+0436_00276	2.511058200568427
+0436_00341	2.9109367456529665
+0436_00359	2.995978649790275
+0436_00482	2.8140648525915184
+0436_00509	2.6352991828688124
+0436_00516	2.9012193442810625
+0436_00537	2.805902745575655
+0436_00538	2.7904412022500855
+0436_00547	2.8941883625735088
+0436_00550	3.8825595682873013
+0436_00552	3.488810670550648
+0436_00565	3.4092032635900815
+0436_00592	4.010473226378605
+0436_00605	2.6300814741504217
+0436_00606	5.940765246872711
+0436_00643	4.194552685027399
+0436_00648	2.415577497374266
+0436_00658	2.7424684606803433
+0436_00688	2.459153255444
+0436_00704	2.483021244870815
+0436_00730	2.4815124828897197
+0436_00752	2.4781735607767006
+0436_00760	3.4350015593080405
+0436_00770	2.8761836337198536
+0436_00776	2.8558430682097873
+0436_00779	3.508380225765019
+0436_00874	2.6536679921938235
+0436_00879	3.1645028507130517
+0436_00881	3.0270258925993367
+0436_00905	2.7128788608406893
+0436_00919	2.6198450629467445
+0436_00959	2.386091815152249
+0436_00969	2.5318462377412754
+0436_00976	2.356831288462163
+0436_00990	2.412384553346625
+0436_00996	2.3817510415641303
+0436_00999	2.530716266619118
+0436_01024	4.453684051004743
+0436_01027	2.9843731282859256
+0436_01034	6.155580023842982
+0436_01037	2.6299724056625235
+0436_01050	4.310816899492989
+0436_01071	2.6177679510931045
+0436_01072	5.094097516069928
+0436_01088	2.836107608180007
+0436_01097	2.944962594354992
+0436_01103	3.193463889064266
+0436_01105	6.690996862361059
+0436_01134	2.5791477514582777
+0436_01165	4.395717369463171
+0436_01181	2.522620372980553
+0436_01186	2.843453721746238
+0436_01187	8.300929326819073
+0436_01196	3.0047576327630736
+0436_01209	4.003655075683455
+0436_01225	4.22027182451418
+0436_01261	9.016800217079494
+0436_01281	5.684185597574196
+0436_01284	4.086728868336786
+0436_01305	3.1503202343451253

processed_data/studies.tsv

@@ -431,3 +431,4 @@ id	name	url	pmid	source	method.type	comment	missing information	authors	mail
 0433	ROASMI_66	10.1016/j.jchromb.2017.07.016.				 mobile phase A was 5 mM ammonium formate in water with an adjusted pH of 3.0 by the addition of formic acid., Submitted by Fangyuan Sun		Tobias Bruderer , Emmanuel Varesio , Gérard Hopfgartner	
 0434	ROASMI_71	10.1016/j.jchromb.2017.07.016.				 mobile phase A was 5 mM ammonium formate in water with an adjusted pH of 3.0 by the addition of formic acid, Submitted by Tobias Bruderer , Emmanuel Varesio , Gérard Hopfgartner		Tobias Bruderer , Emmanuel Varesio , Gérard Hopfgartner	
 0435	ROASMI_77	10.1016/j.jchromb.2017.07.016.				Mobile A was 5 mM ammonium acetate in water with an adjusted pH of 8.0 by the addition of ammonium hydroxide., Submitted by Fangyuan Sun		Tobias Bruderer , Emmanuel Varesio , Gérard Hopfgartner	
+0436	ROASMI_85	10.1016/j.jhazmat.2019.121712				flow rate:0.2-0.48, Submitted by Fangyuan Sun		Pablo Gago-Ferrero, Anna A. Bletsou, Dimitrios E. Damalas, Reza Aalizadeh, Nikiforos A.Alygizakis, Heinz P.Singer, Juliane Hollender, Nikolaos S. Thomaidis 	

raw_data/0436/0436_gradient.tsv

@@ -0,0 +1,5 @@
+t [min]	flow rate [ml/min]	A [%]	B [%]
+0.1		99	1
+3		61	39
+14		0.1	99.9
+16		0.1	99.9

raw_data/0436/0436_info.tsv

@@ -0,0 +1,2 @@
+id	authors	name	comment	url
+0436	Pablo Gago-Ferrero, Anna A. Bletsou, Dimitrios E. Damalas, Reza Aalizadeh, Nikiforos A.Alygizakis, Heinz P.Singer, Juliane Hollender, Nikolaos S. Thomaidis 	ROASMI_85	flow rate:0.2-0.48, Submitted by Fangyuan Sun	10.1016/j.jhazmat.2019.121712

raw_data/0436/0436_metadata.tsv

@@ -0,0 +1,2 @@
+id	column.name	column.usp.code	column.length	column.id	column.particle.size	column.temperature	column.flowrate	eluent.A.h2o	eluent.A.meoh	eluent.A.acn	eluent.A.iproh	eluent.A.acetone	eluent.A.hex	eluent.A.chcl3	eluent.A.ch2cl2	eluent.A.hept	eluent.A.formic	eluent.A.formic.unit	eluent.A.acetic	eluent.A.acetic.unit	eluent.A.trifluoroacetic	eluent.A.trifluoroacetic.unit	eluent.A.phosphor	eluent.A.phosphor.unit	eluent.A.nh4ac	eluent.A.nh4ac.unit	eluent.A.nh4form	eluent.A.nh4form.unit	eluent.A.nh4carb	eluent.A.nh4carb.unit	eluent.A.nh4bicarb	eluent.A.nh4bicarb.unit	eluent.A.nh4f	eluent.A.nh4f.unit	eluent.A.nh4oh	eluent.A.nh4oh.unit	eluent.A.trieth	eluent.A.trieth.unit	eluent.A.triprop	eluent.A.triprop.unit	eluent.A.tribut	eluent.A.tribut.unit	eluent.A.nndimethylhex	eluent.A.nndimethylhex.unit	eluent.A.medronic	eluent.A.medronic.unit	eluent.A.pH	eluent.A.heptafluorobutyric	eluent.A.heptafluorobutyric.unit	eluent.B.h2o	eluent.B.meoh	eluent.B.acn	eluent.B.iproh	eluent.B.acetone	eluent.B.hex	eluent.B.chcl3	eluent.B.ch2cl2	eluent.B.hept	eluent.B.formic	eluent.B.formic.unit	eluent.B.acetic	eluent.B.acetic.unit	eluent.B.trifluoroacetic	eluent.B.trifluoroacetic.unit	eluent.B.phosphor	eluent.B.phosphor.unit	eluent.B.nh4ac	eluent.B.nh4ac.unit	eluent.B.nh4form	eluent.B.nh4form.unit	eluent.B.nh4carb	eluent.B.nh4carb.unit	eluent.B.nh4bicarb	eluent.B.nh4bicarb.unit	eluent.B.nh4f	eluent.B.nh4f.unit	eluent.B.nh4oh	eluent.B.nh4oh.unit	eluent.B.trieth	eluent.B.trieth.unit	eluent.B.triprop	eluent.B.triprop.unit	eluent.B.tribut	eluent.B.tribut.unit	eluent.B.nndimethylhex	eluent.B.nndimethylhex.unit	eluent.B.medronic	eluent.B.medronic.unit	eluent.B.pH	eluent.B.heptafluorobutyric	eluent.B.heptafluorobutyric.unit	eluent.C.h2o	eluent.C.meoh	eluent.C.acn	eluent.C.iproh	eluent.C.acetone	eluent.C.hex	eluent.C.chcl3	eluent.C.ch2cl2	eluent.C.hept	eluent.C.formic	eluent.C.formic.unit	eluent.C.acetic	eluent.C.acetic.unit	eluent.C.trifluoroacetic	eluent.C.trifluoroacetic.unit	eluent.C.phosphor	eluent.C.phosphor.unit	eluent.C.nh4ac	eluent.C.nh4ac.unit	eluent.C.nh4form	eluent.C.nh4form.unit	eluent.C.nh4carb	eluent.C.nh4carb.unit	eluent.C.nh4bicarb	eluent.C.nh4bicarb.unit	eluent.C.nh4f	eluent.C.nh4f.unit	eluent.C.nh4oh	eluent.C.nh4oh.unit	eluent.C.trieth	eluent.C.trieth.unit	eluent.C.triprop	eluent.C.triprop.unit	eluent.C.tribut	eluent.C.tribut.unit	eluent.C.nndimethylhex	eluent.C.nndimethylhex.unit	eluent.C.medronic	eluent.C.medronic.unit	eluent.C.pH	eluent.C.heptafluorobutyric	eluent.C.heptafluorobutyric.unit	eluent.D.h2o	eluent.D.meoh	eluent.D.acn	eluent.D.iproh	eluent.D.acetone	eluent.D.hex	eluent.D.chcl3	eluent.D.ch2cl2	eluent.D.hept	eluent.D.formic	eluent.D.formic.unit	eluent.D.acetic	eluent.D.acetic.unit	eluent.D.trifluoroacetic	eluent.D.trifluoroacetic.unit	eluent.D.phosphor	eluent.D.phosphor.unit	eluent.D.nh4ac	eluent.D.nh4ac.unit	eluent.D.nh4form	eluent.D.nh4form.unit	eluent.D.nh4carb	eluent.D.nh4carb.unit	eluent.D.nh4bicarb	eluent.D.nh4bicarb.unit	eluent.D.nh4f	eluent.D.nh4f.unit	eluent.D.nh4oh	eluent.D.nh4oh.unit	eluent.D.trieth	eluent.D.trieth.unit	eluent.D.triprop	eluent.D.triprop.unit	eluent.D.tribut	eluent.D.tribut.unit	eluent.D.nndimethylhex	eluent.D.nndimethylhex.unit	eluent.D.medronic	eluent.D.medronic.unit	eluent.D.pH	eluent.D.heptafluorobutyric	eluent.D.heptafluorobutyric.unit	gradient.start.A	gradient.start.B	gradient.start.C	gradient.start.D	gradient.end.A	gradient.end.B	gradient.end.C	gradient.end.D	eluent.A.h2o.unit	eluent.A.meoh.unit	eluent.B.h2o.unit	eluent.B.meoh.unit
+0436	Thermo Scientific Acclaim RSLC 120 C18	L1	100.0	2.1	2.2	30.0		90	10	0	0	0	0	0	0	0	0.01	%	0		0		0		0		5	mM	0		0		0		0		0		0		0		0		0			0		0	100	0	0	0	0	0	0	0	0.01	%	0		0		0		0		5	mM	0		0		0		0		0		0		0		0		0			0		0	0	0	0	0	0	0	0	0	0		0		0		0		0		0		0		0		0		0		0		0		0		0		0			0		0	0	0	0	0	0	0	0	0	0		0		0		0		0		0		0		0		0		0		0		0		0		0		0			0		99.0	1.0	0	0	0.1	99.9	0	0	%	%	%	%

raw_data/0436/0436_metadata.yaml

@@ -0,0 +1,35 @@
+column:
+  name: Thermo Scientific Acclaim RSLC 120 C18
+  id: 2.1
+  temperature: 30
+  usp.code: L1
+  length: 100
+  particle.size: '2.2'
+eluent:
+  A:
+    h2o:
+      value: 90
+      unit: '%'
+    meoh:
+      value: 10
+      unit: '%'
+    nh4form:
+      value: 5
+      unit: mM
+    formic:
+      value: 0.01
+      unit: '%'
+  B:
+    h2o:
+      value: 0
+      unit: '%'
+    meoh:
+      value: 100
+      unit: '%'
+    nh4form:
+      value: 5
+      unit: mM
+    formic:
+      value: 0.01
+      unit: '%'
+id: '0436'