Table 1.

The training datasets statistics. The number of molecules is smaller than the number of spectra because of the existence of mass spectra of the same molecules measured in different collision energies.

MS type	Instrument type	No. of spectra	No. of molecules	Fingerprints
MS2	(1) LC-APCI-ITFT-CID	295	65	179
	(2) LC-APCI-ITFT-HCD	882	86	181
	(3) LC-ESI-ITFT-CID	447	224	281
	(4) LC-ESI-ITFT-HCD	2655	225	281
	(5) LC-ESI-QTOF-CID	1027	523	290
MS1	LC-ESI-ITFT	41	41	-
	LC-ESI-QTOF	62	62	-