Table 2.

Known compounds used as validation set

Compound	Chemical name	Chemical formula	Monoisotopic molecular mass Da	CAS number
Kigali Amendment to the Montreal Protocol
HFC-41	fluoromethane	${\text{CH}}_3$F	34.021878	593-53-3
HFC-32	difluoromethane	${\text{CH}}_2{\text{F}}_2$	52.012456	75-10-5
HFC-152	1,2-difluoroethane	${\text{C}}_2{\text{H}}_4{\text{F}}_2$	66.028106	624-72-6
HFC-152a	1,1-difluoroethane	${\text{C}}_2{\text{H}}_4{\text{F}}_2$	66.028106	75-37-6
HFC-23	fluoroform	${\text{CHF}}_3$	70.003035	75-46-7
HFC-143	1,1,2-trifluoroethane	${\text{C}}_2{\text{H}}_3{\text{F}}_3$	84.018685	430-66-0
HFC-143a	1,1,1-trifluoroethane	${\text{C}}_2{\text{H}}_3{\text{F}}_3$	84.018685	420-46-2
HFC-134	1,1,2,2-tetrafluoroethane	${\text{C}}_2{\text{H}}_2{\text{F}}_4$	102.009263	359-35-3
HFC-134a	1,1,1,2-tetrafluoroethane	${\text{C}}_2{\text{H}}_2{\text{F}}_4$	102.009263	811-97-2
HFC-125	pentafluoroethane	${\text{C}}_2{\text{HF}}_5$	119.999841	354-33-6
HFC-245ca	1,1,2,2,3-pentafluoropropane	${\text{C}}_3{\text{H}}_3{\text{F}}_5$	134.015491	679-86-7
HFC-245fa	1,1,1,3,3-pentafluoropropane	${\text{C}}_3{\text{H}}_3{\text{F}}_5$	134.015491	460-73-1
HFC-365mfc	1,1,1,3,3-pentafluorobutane	${\text{C}}_4{\text{H}}_5{\text{F}}_5$	148.031141	406-58-6
HFC-236cb	1,1,1,2,2,3-hexafluoropropane	${\text{C}}_3{\text{H}}_2{\text{F}}_6$	152.006069	677-56-5
HFC-236ea	1,1,1,2,3,3-hexafluoropropane	${\text{C}}_3{\text{H}}_2{\text{F}}_6$	152.006069	431-63-0
HFC-236fa	1,1,1,3,3,3-hexafluoropropane	${\text{C}}_3{\text{H}}_2{\text{F}}_6$	152.006069	690-39-1
HFC-227ea	1,1,1,2,3,3,3-heptafluoropropane	${\text{C}}_3{\text{HF}}_7$	169.996647	431-89-0
HFC-43-10mee	1,1,1,2,2,3,4,5,5,5-decafluoropentane	${\text{C}}_5{\text{H}}_2{\text{F}}_{10}$	251.999682	138495-42-8
HFOs
HFO-1234yf	2,3,3,3-tetrafluoroprop-1-ene	${\text{H}}_2{\text{C}}_3{\text{F}}_4$	114.009263	754-12-1
HFO-1234ze(E)	(E)-1,3,3,3-tetrafluoroprop-1-ene	${\text{H}}_2{\text{C}}_3{\text{F}}_4$	114.009263	29118-24-9
HCFO-1233zd(E)	(E)-1-chloro-3,3,3-trifluoro prop-1-ene	${\text{H}}_2{\text{C}}_3{\text{F}}_3$Cl	129.979712	102687-65-0
Halogenated compounds with high boiling point
HCBD	1,1,2,3,4,4-hexachlorobuta-1,3-diene	${\text{C}}_4{\text{Cl}}_6$	257.813116	87-68-3
TCHFB	1,2,3,4-tetrachlorohexafluorobutane	${\text{C}}_4{\text{Cl}}_4{\text{F}}_6$	301.865830	375-45-1

Identification and quantification of these 23 compounds has been done by [8, 44, 49, 70]. Present chemical elements: H, C, N, O, F, Cl. Chemical elements used as input for the knapsack algorithm are the same as for the training set: H, C, N, O, F, S, Cl, Br and I. SMILES codes can be found in the Additional file 1