CA2032490A1 - Multiply charged ions and a method for determining the molecular weight of large molecules - Google Patents

Abstract

This invention describes the production of mass spectra which contain a multiplicty of peaks. The component ions of these peaks, which are multiply charged, are formed by dispersing a solution containing an analyte into a bath gas as highly charged droplets.
The analyte is generally a compound of high molecular weight and is of biochemical interest. The invention also describes methods for calculating the molecular weight of the analyte from the measured mass values of the highly charged ions.

Description

WO90/14148 ~ V~ 9~ PcT/us9o/o27l6 Multiply Charged Ions and a Method for Determining the Molecular Weight of Large Molecules RIGHTS STATEMENT .
.. , The U.S. Government has a paid-up license to this invention and the right in limited circumstances to require the patent owner to license others on reasonable terms as provided for by the terms of Grant No. 2ROl GM31660-04Al awarded by the National Institutes of Health.

TECHNICAL FIELD

This invention relates to improvements in a method for mass spectrometric analysis of chemical compounds in solution. In particular it is concerned with determining the mass or molecular weight of large fragile solute species with greater speed, convenience and accuracy than has been possible by previous methods. The invention also relates to new compositions of matter comprising populations of ions having a multiplicity of charges.

BACKGROUND ART
, .
Mass spectrometry consists in "weighing" individual molecules by transforming them intact into ions in vacuo and then measuring the response of their trajectories to various combinations of electric and/or magnetic fields. Attempts to extend the application-of mass spectrometric methods to the ; analysis of very large polar organic and bio-organic molecules hav~ long been frustrated by the difficulties of transforming such molecules into ions. The analytical advantagès of mass i spectrometry for such parameters-as~detection sensitivity, -accuracy of.mass measurement and abundance determinations cànnot be.realized.if the prerequisite ions cannot be formed. Large polar mol~cules generaIly cannot be vaporized,- even-in vacuo,-witho~t extensive, even catastophic, decomposition.
Consequently, one-cannot apply the classical methods of ~~
ionization based on gas phase encounters of the molecule to be - ~UB~ T~TE~ ET

'' ~ ' ; . - : ' . ;
- . . . .
- . . .
.. . .
: . .

WO90/14148 ~ 2 4 9 0 PCT/US90/02716 ionized with electrons as in Electron Ionization (EI), photons as in Photo Ionization (PI), other ions as in Chemical Ionization (CI), or excited atoms or molecules as in Auger Ionization (AI). Such encounters can form ions from a neutral molecule by a variety of mechanisms including removal or attachment of an electron and removal or attachment of a positively charged entity, typically a proton.
In recent years a number of so-calle* "soft" ionization methods have been developed which with varying degrees of success have been able to produce intact ions from molecular species of ever increasing size. One class of such methods is based on very rapid deposition of energy on a surface over which the species to be analyzed (analyte) has been dispersed. The idea is, as first suggested by Beuhler et al, Journal of American Chemical 8Ociety, 96, 3990 (1974), that if the heat required is applied rapidly enough, vaporization may occur before decomposition has a chance to take place. The rapid heating methods now in use include Plasma Desorption (PD), in which disintegration of a radioactive isotope, usually Californium-252, produces a small blob of plasma on the surface from which a few intact ions of analyte emerge; Secondary Ionization Mass Spectrometry (SIMS), hereafter referred to as Fast Ion Bombardment (FIB), in which the analyte-containing surface is bombarded by ions, e.g. Cs+, accelerated to energies in the tens of kilovolts; Fast Atom Bombardment (FAB) in which the accelerated ions are neutralized by charge exchange before they strike the surface; Laser Desorption (LD) in which photons comprise the vehicle for depositing energy on the surface.
These methods have been able to produce intact ions from , . . .., .. ~, remarkably large analyte species even though, except for LD, they are highly irreversible and characterized by brute force.
.. . ..
To date, intact ions have been produced from bio-organic : -- . ...
compounds with molecular--weights on the order of 2lOjOOO:with LD
_ (M. Karas and;Fj. Hillenkamp, paper presented at 11th - ~ ~~
International Mass SpectrometryiConference, Bordeaux, France~
., . . . ---1988; cf. Analytical-Chemistry--(19B8) 60j-2299),-24-,000 with FAB
(or FIB) (M. Barber and B. N. Green, Rapid Communications in.
Ma Y Spectrometry, (1987) l, 80) and 45,000 with PD (G. Jonsson, P. Hakansson, A. Hedin, D. Fenyo, B. Sundqvist, H. Bennich and - - ~ B~3TITU FE SHE~
, . . . .. .... . . ... . .... . .

WO90/14148 ~ ~ 2 9 ~ PCT/US90/02716 P. Roepstorff, Rapid Commun. Mass ~pectrom. in press). The ion currents in these methods have been very small and except for LD
decrease rapidly with increasing molecular weight. When the ions get very large their detection with multipliers requires post-acceleration voltages that are often awkwardly high.
Except possibly with LD, the ions produced often have high levels of internal excitation which can result in substantial peak broadening due to predissociation.
Quite diSferent in practice and principle from these "violent" ionization methods are techniques that use very strong electrostatic fields to extract ions from a substrate. In so called Field Desorption (FD) ionization the analyte molecules are applied to a fine wire on whose surface is disposed an array of sharp pointed needles or "whiskers'~. When the wire is placed in a vacuum system and a high voltage is applied while it is carefully heated, the analyte molecules will desorb as ions from the tips of the needles where the effective field strength is very high. Even through it can transform very involatile analytes into ions in vacuo FD has not become widely used, in part because sample preparation is tedious, in part because of difficulties in adjusting the wire to just the right temperature and voltage, and in part because the desorbed ions have such high energies that relatively expensive magnetic sector analyzers must be used for mass determination. In so called Electrohydrodynamic Ionization (EH) analyte is dissolved in a non-volatile liquid (e.g. glycerol) and injected into an evacuated chamber through a small capillary tube maintained at high voltage. The solvent liquid must have a low vapor pressure so that it won't "freeze-dry" from rapid evaporation-into vacuum. Solute ions, along with molecules and clusters of solvent, are desorbed from the emerging liquid by the high field at its--surface ana can be mass analyzed. EH has not been widèly practiced, in part because few-liquids-that have low vapor; -pressure are good solvents:for large polar-bio-organic-- ~
compounds,- in part because the desorbed~ions are usually ~ ~
solvated with one or-more molecules of the solvent, and in part because they often have a wide distribution of energies.
Moreover, as in the case of FD, the product ions have high energies and require magnetic sector analyzers. `

$~
.... . ......... .

:
:~ ' WO90/14148 ~ 2 4 9 ~ PCT/US90/02716 In the past few years there has emerged a new family of ionization techniques that also make use of high electric fields to desorb ions. These techniques differ from FD and EH in that desorption is from small charged droplets of solution into an ambient bath gas instead of into vacuum. The required high fields at the droplet surface result from the increasing charge density and decreasing radius of curvature of the droplet surface as the solvent evaporates. A portion of the bath gas containing the desorbed ions is then admitted through a small orifice into a vacuum system containing an appropriate mass analyzer. The bath gas acts as a very effective moderator, i.e.. it maintains both internal and translational energies of the ions at levels corresponding to the bath gas temperature which is rarely high enough to cause thermal decomposition of even labile bio-organic compounds. In Thermospray (TS) ionization which was developed by Vestal and his colleagues the sample solution is passed through a heated tube whose walls are hot enough to vaporize most of the solvent. ~J. Amer. Chem. ~oc.
( 1980) 102 / 5931) ~ The consequent rapid expansion of solvent vapor produces acceleration and shear forces that atomize the' remaining liguid. Thus there emerges from the end of the tube a supersonic~jet of superheated solvent vapor in which the- ' remaining sample solution that was atomized is dispersed as small droplets, equal numbers of which are positively and negatively charged. The charging is a result of statistical fluctuations in the distribution of cations and anions as the liquid is nebulized. In a somewhat equivalent -technique, called Atmospheric Pressure Ion Evaporation (APIE) by its originators,-J.V. Iribarne and B.A.-Thomson,' dropIets are produced by intersecting a flow of sample solution with a high speed jet of air. (J. Chem. Phys. (1976) 64 ~ 2287 and ibid.-(1979? r71~ 4451)-~ In this discussion APIE will-be referred to by the more convenient term Aerospray (AS)-to-~indicate that'it' is based on-pneumatic nebulization of the-sampl-e-li~quid.~ 'As`~in TS the charging is due to;~statistical fluctuations'in the-~:'S~'-..
distribution of cations and anions among--the droplets during'`~
atomization of the liquid. It'was found that an-induction '-~` electrode, at a potential of 3 kilovolts and placed near the atomization region, greatly increased the total ion current.
:
-~! SUBSTITIJTE SHEEl .:. I
: ... . - :
: ` : .: .

wo go/14148 2 ~ 3 2 ~ 9 3 PCTIUS90/02716 ' S

Moreover, all the resulting droplets and desorbed ions had the same sign, positive or negative, depending upon the electrode polarity.
The invention described in this application stems from and relates to so called Electrospray (ES) ionization which can be considered a sort of mirror image of TS and AS in that instead of producing charging by atomization it produces atomization by charging. In ES the liquid sample is introduced through a small bore tube maintained at several kilovolts with respect to the surrounding walls of a chamber containing bath gas, usually but not necessarily at or near atmospheric pressure. The electrostatic field at the tip of the tube charges the surface of the emerging liquid. The resulting coulomb forces overcome the liquid's surface tension and disperse it into a fine spray of charged droplets. Thus, the nebulization is by electrostatic forces that provide a much higher charge/mass ratio for the resulting droplets that can be achieved in TS and AS. lf the field at the tip of the tube is too high, or the pressure of the ambient bath gas is too low, a corona discharge will occur at the tip of the tube and substantially decrease the effectiveness of the nebulization. This ES ionization technique is fully described in U.S.-Patents 4,531,056 and 4,542,293 which were granted in 1985.

SUMMARY OF THE INVENTION

- We have recently discovered that an ES source can produce ions from very large and complex solute species without any fragmentation. These species are so involatile that they could not possibly be converted intact into ions by-ionization techniques such as EI, PI, CI or AI. Nor have-there been reports that such large species have been ionized by either TS
or AS. Moreover,_ and-unexpectedly, it~turns out that for -~
~ species of large molecular weight the resulting ions each~~-~
- ~contain a large number of charges, distributed between a`minimum and maximum number.---The values~of these~minimum and maximum`
numbers depend-on the size and composition of the species.- For example,-from protein solutes with molecular weights up-to-~5-nearly 40,000 ions with up to 40 or more charges have been -., .: .
BS~T~
. `

.. : :
:. . .
~ .

WO90/14148 ~0 3 2 ~ 9 0 PCT/US90/02716 obtained. Thls multiplicity of charges reduces the mass/charge (m/z) ration of the ions and, therefore, increases the effective mass range of any analyzer by a factor equal to the number of charges/ion. Thus, it was possible to analyze molecules having masses up to at least 40,000 daltons with a modest quadrupole mass filter whose nominal upper mass limit is 1500 daltons. The terms "effective" and "nominal" are used here to characterize the mass capability of an analyzer because conventional practice in mass spectrometry presumes that ions to be analyzed will almost always be singly charged. Consequently, in the m/z value for an ion, which is what analyzers measure, z has almost always been unity. Thus, an important feature of this invention was the discovery that with an ES ion source one could obtain useful mass spectra containing peaks corresponding to intact parent molecules, even though the molecular weight of those molecules was much higher than the nominal upper mass limit of the-analyzer used to obtain the spectra. This remarkable result was entirely unexpected and had never been anticipated before-this invention was reduced to practice.
Following the initial disclosure of our discovery (Annual ~eet~ng of the American Society for Mass Spoctromet~y in San Francisco, 5-lO June 1988) and using our methods, others have since produced protein ions with molecular weights as high as 130,000. ~R.D. Smith, J.A. Loo, C.J. Barinaga and H. Udseth, presentation at the 5th (Montreux) Symposium on LC-MS, Freiburg, November 1988). These large ions contain as many as lO0 or more charges and their masses have been analyzed with a quadrupole mass spectrometer having a nominal mass range with an upper ;
limit on the order of 1500 daltons. Moreover, this muItiple-... . ... .. .
charging phenomenon is not limited to ions having protein orprotein-like structures. Multiply charged ions have~also been produced by these methods from other-larg~ and compIex molecules such as sugars,-polynucleotides and synthetic polymers. For~;
example" with an oligonucleotide having a-molecular weight close to 4250, Covey, et al. obtained a mass spectrum~with 6 pea~s for parent ions containing from 6 to ll negative charges. (T.R. ;
Covey, R.F. Bonner, B.I. Shushan and J.D. Henion, Rapid. Commun.
Mass pectro~. 2, 249 (1988)). A key requirement is-that --molecules that are not themselves ions contain polar atoms or':' . ,.
, SUEISTITUTE SHEeT

~, .' . .

W090/14148 2 ~ 3 2 4 ~ ~ PCT/USgo/02716 groups, e.g. ~, N, and S, to which the charge bearing species can attach, held presumably by ion induced dipole forces. Thus, molecules like hydrocarbons that are highly nonpolar cannot be effectively analyzed by the ES technique. The original experiments of Malcolm Dole and his colleagues (M. Dole, L.L.
Mack, R.L. Hines, R.C. Mobley, LD. Ferguson, and M.B. Alice, J.
Chemi¢~l Physics, 49, 2240 (1968); see also 52, 4977 (1970)) seemed to show that ES could produce singly charged ions of large polystyrene polymers. However, convincing evidence has accumulated that the observed ions probably compri~ed clusters of polymer molecules with a plurality of charges on each cluster. These charged clusters probably represented residues of charged droplets after all the solvent had evaporated.
It is to be noted that ions comprising individual molecules with such high degrees of multiple charging are new to the laboratory. The classical ionization methods based on gas phase encounters between volatile molecules and electrons, photons or other ions, usually produce only singly charged ions but sometimes have provided ions with two charges and on rare occasions with three. Ions containing multiple charges have been produced by some of the recently developed "soft"
ionization methods mentioned earlier such as TS, AS, FAB, SIMS
and PD but usually with only two or three charges, never more than five or six. Moreover, a substantial fraction of the ions produced by these methods are singly charged, even for the very largest species. With ES ionization of species above some minimum size there are no detectable amounts of ions with less than some minimum number of charges. This minimum number of charges-increases with increasing molecular weight of the parent species. For example, in the case of small proteins such as -bovine insulin, lysozyme, and alcohol dehydrogenase, with respective molecular weights of 5,735, 14,306 and 39,830, the-minimum numbers of charges-were-respectively 4,-lO and 32 in experiments under typical operating conditions.-- Traditionally, when peaks for doubly~charged ions have been obsèrved!in 'a'mass spectrum, mass spectrometrists have used them'to confirm'the assignment of a peak in that same spectrum to the:'molecular ion of the~analyte.- This assignment operation was'-fairly straightforward for two reasons: first','the molecular ion was SUBSTI~U~E ~EEr .`. .
.
~.
... ~ - , . ~:
. ~ . .

singly charged/ present in great abundance (since only the most stable molecules could form multiply charged ions) and had a mass that only rarely was outside the mass range of the analyzer: second, the multiple of the charge was almost always only two. This assignment technique is still used with PD where the multiplicity is still small, even very large ions having at most perhaps 2 to 5 charges. In some cases multiply charged ions have been regarded as a nuisance to be avoided because they were presumed to decrease the sensitivity of detection by ~' robbing both analyte and charge from the primary peak (of singly charged ions) or because they might mask important fragments.
Indeed, the initial reaction of mass spectrometrists, when confronted with a spectra containing a plurality of multiply charged parent peaks, has invariably been one of dismay. They instinctively feel that such.peak plurality must inevitably decrease sensitivity and make interpretation of the spectrum much more difficult. A feature of this invention is that it turns into a substantial advantage this presumed disadvantage of multiplicity in numbers of peaks per spectrum and charges per ion. This advantage is especially real for situations in which the mass of the analyte species far exceeds the mass range of the mass analyzer. In such cases a peak-for singly charged parent ions could.not be observed in the spectrum, even ~f these ions were present in great abundance in the stream of ions entering.the analyzer.
Another advantage of multiply charged ions, when they are produced.~in relatively high pressure gas that then carries them into the vacuum system by free jet expansion, is the narrow energy spread of the ions as they enter the mass analyzer.: In order to promote evaporation of the droplets and desolvation of the ionsjit is often desirable.to heat the bath gas to'350 K or sO! a temperature well.within the-thermal stability-limits'of most organic and bio-organic.compounds.- During the-adiabatic-: ~ .. ,. ~. ...... .
-' free jet.expansion from:ithe orifice into vacuum~the bath~gas'~~
'''` temperature drops to values usually.well below-lO0 K so that the .~ internal.degrees of freedom of.the ions are-quite cold when'they ~:. enter the mass analyzer. The translational "temperature"'of :-.~
these ions as indicated by the density of the bath gas, or as measured by a thermometer moving with the gas at its same ; :' SVBSTITUTE S~IEET
: , . .
:~ .

W090/14148 ~ ~ 2 ~ 9 ~ PCT/US90/02716 velocity, woùld be quite 1QW~ even somewhat lower than the "temperatures" of the internal degrees of freedom of either the ion itself or of the bath gas molecules. The reason is that these measures of temperature reflect primarily the translational energies of the ions and the molecules. The translational temperatures of any species in a gas undergoing rapid adiabatic expansion are always lower than the internal energies of those species. Thus the distribution of the ion translational energies is quite narrow, a substantial advantage for accurate mass analyses. Because heavy species ~ions) are accelerated by the lighter carrier gas, the total translational energies (more properly "enthalpies") of the ions after expansion are higher than their thermal energies at the source temperature by a factor that is approximately equal to the ratio of the molecular weight of the ion to the mean molecular weight of the source gas, i.e. the concentration weighted average of the heavy species (ions) and the light species (bath gas).
Thus, ions with a molecular weight of lOO,OOO at very low concentration in a bath gas of nitrogen expanded from a source temperature of 350K, could in principle be accelerated to a translational kinetic energy of about 370 eV. That much energy in a singly charged ion as it entered a mass analyzer would complicate mass analysis because it would be too large for a quadrupole mass analyzer, for which acceptable inlet energies are much less than 370 eV. In addition, that much energy would constitute an appreciable but unknown fraction of the energy applied~to an ion for mass analysis by time-of-flight or ---magnetic sector instruments. However,-it has been well established that because of slip effects that result in a velocity lag-for heavy species during acceleration by a much lighter carrier gas, the final velocity of such a heavy ion would probably be only 50:to 70 per cent-of the maximum bath gas velocity so that the translationa~ energy of an ion with a ~
molecular weight of lOOjOOO would`be somewhere-betwèen Z5-and 50 per cent of the limiting;-value of 370-eV, i.e.~less than-~185 eV.
Moreover, as will emer7e, ions with molecular weights of lOO,OOO
praduced from an Electrospray-source will generally have as many as 80 or more charges. -Most mass analyzers respond to the ratio of kinetic energy or momentum to charge.- Consequently, for .
SUBSTIl~UTE-- SHEET
. . ,. ", . ,., - . - - - . . - - , "~, WO90/141~ PcT/US9o/o27l6 2~24~ lo -example, an ion with 80 charges and a kinetic energy of 185 eV
will behave in an analyzer like a singly charged ion with an energy of about 2.3 ev so that its mass analysis presents no difficulties.
A further advantage of.this invention stems from a surprising finding in the ES ionization of large solute species that are pure compounds. With such substances, in which all molecules have the same molecular weight, the spectrum resulting from mass analysis of ions from an ES source comprises a sequence of peaks whose ions are multiply charged and differ from those of adjacent peaks by a single charge. In earlier experiments with poly ethylene glycols (PEGs) we had observed ions with a multiplicity of charges. (S.F. Wong, C.K. Meng and J.B. Fenn, J. Phy~. Chem. 92, 546 (1988)) However, because in every sample there was a broad range of oligomers, each of which would produce ions with varying numbers of charges, the spectra were so congested that we could only resolve individual peaks for ions with six charges or less. Moreover, even then the congestion made it impossible to discern whether a particular oligomer of given molecular weight gave rise to a coherent sequence of peaks in which the constituent ions of any one peak differed by a single charge from those of.an adjacent`peak.
Indeed, the journal referees for that paper and another not yet published insisted that the relatively featureless band that was interpreted to represent multiply charged PED oligomers was probably due to impurities. It was not until experiments described here had been carried out with proteins, each sample of which comprised mostly molecules that had essentially the same molecular weight (except for isotopic differences),- that the remarkable coherent sequences of peaks that are an essential feature of our invention were discovered.. Only after these protein results were revealed and interpreted did the mass spectrometry community accept the reality of such extensive ~' multiple charging and the~coherence of the resulting multiplicity of peaks in~the mass spectra.
As this.invention shows,. when solutions containing a relatively small number of different solute-species with --relatively large molecular weights are.introduced into an ES
source, or any equivalent source that depends upon dispersing ;U~STITUTE` SHE:ET- ` I
~ . , .~ . . ,~ .

WO90/14148 2 ~.~ 3 2 ~Qt~ pcTlusgo/o27l6 , ' 11 :
the solution ~o be analyzed into a bath gas as droplets that have a sufficiently high charge, the resulting ions constitute for each solute species a population in which each member consists of a molecule of that species to which are attached n charges. In that population n takes on all integral values between the maximum and minimum. Those minimum and maximum values are determined by the size and the composition of the species, both increasing as the species molecular weight increases. For the species studied to date the maximum number o~ charges seems to be such that the mass/charge (m/z) ratio of the ions is generally not less than about 500. Results also suggest that the minimum number of charges is such that the maximum value of m/z is probably under about 3000. For the large molecules of interest values this maximum value of m/z corresponds to values of n that are usually greater than 3 or 4.
A key difference between these ES ions and those produced by other soft methods, including FAB, PD, FIB, FD and LD, is that for most species with molecular weights above 3000 or so ions with values of n as low as l or 2 are absent altogether or constitute a very small fraction of the total population. In the other "soft" methods they are a significant component of the total ion population. These observations attest to substantial differences in the nature of the ionization process. It is believed that species with fewer than some minimum number of charges attached simply will not be desorbed from the droplet by the field existing at its surface. Thus, as species get larger the minimum number of charges required for "lift off" increases so that ions with-fewer than the critical number are not found.
~ It has also been discovered, contrary to conventional mass spectrometry practice, that-the multiplicity of peaks found in ` ES spectra-is of great utility--because it makes possible a significant enhancement of the confidence and accuracy with ~-which one can assign a molecular weight~to the parent species.
Moreover, we have found-convenient méthods-for achieving this ` enhancement and recovering-information-from~mass spectra with- such a multiplicity of peaks.-` Although these methods can be applied to any spectrum featuring multiple peaks due to multiple charging of a parent species, no matter how produced, they will be described with reference to mass spectra of ions produced in : .
8UB~T~T~lrE S~EE~
' .
' ~.. ` ~ , -. - .

2~ 49~ 12 an Electrospray ion source that embodies principles that have been previously set forth in detail.
In sum, our invention relates to the production of mass spectra comprising a multiplicity of peaks, these peaks being produced by multiple charging-of species with a relatively high molecular weight. It further relates to methods for the recovery of infoxmation from such spectra. An additional feature of the invention,relates to the nature of the populations of multiply charged ions that we have been able to produce. They represent a new composition of matter. These features of the invention will be of particular value in the mass spectrometric analysis of samples containing complex and non-volatile species with molecular weights above about 3000.
Other features and advantages of the invention will become apparent.

- BRIEF DESCRIPTION OF THE DRAWINGS

The invention will now be set forth in greater detail by reference to the drawings in which:
FIG. l is a simplified~schematic representation of an apparatus with which-the invention-can be practiced.
FIG. 2 displays mass spectra obtained for eight proteins with an apparatus that embodies the essential features '' schematically portrayed in Fig l. The number i of charges per constituent ion is,indicated for representative peaks.
FIG. 3 shows a consistency check for the various peaks in the spectrum of the-,protein cyctochrome C shown in Fig.'2.- The solid line is plot of Equation 5.: The points are ratios of measured m/z values for-different pairs of peaks (X'i/K'i+j), each for a different pair,of peaks. In ~a) the peak positions are,as measured in the~spectrum from Fig. l. (b) same-~as-(a)-except that the peak,for i-14 has been deliberately-offset by 5 units on the-m/z scale.~ The points representing peak ratios'' involving ,the offset-peak-are crosses. ~/~ -~~' ~ '---''- '-' FIG.4 shows the-result of offsetting m/z for the i=l9 peak by an amount m in the mass spectrum for cyctochome C. The -dashed line shows the-effect on the unweighted average mass, the solid line on the weighted mass. Note that the weighted average '~ 5UBSTITl~TE SH~Ef .. .. .

, WO90/14148 2~3 2'~a pCT/US90/o27l6 is much less affected by the offset peak once that peak i5 away from its "best position" with respect to the rest of the peaks in the sequence. The open circles represent (on the right hand ordinate) the relative weighting factor wlg when p=2.
- FIG. 5 (a) A synthetic sequence of peaks for ions with from 6 to 15 charges. (b) Deconvolution of (a) by Equation 8. The mass scale is in units of the parent mass M.
FIG. 6 (a3 Synthetic sequence of peaks whose shapes are-approximated by isosceles triangles (FWHH=0.5~) A constant background contribution that is 10% of the peak height has been incorporated. (b) Transformation of (a) according to E~uation 8.
FIG.7 (a) Deconvolution by Equation 8 of the spectrum for cytochrome C (M=12,260) in Figure 2-. The theoretical positions of the first side peaks are marked by dark triangles. (b) "zoom" expansion of the spectrum in (a) for the mass range between lO,OOO and 14,000. See text for explanation of the peak marked by the open triangle.
FIG.8 Results as in Figure 7 of applying the deconvolution algorithm to the spectrum in Figure 2 for carbonic anhydrase II
~M=29,006).
FIG. 9 Electrospray mass spectrum for a mixture of cytochrome C and myoglobin along with the deconvoluted spectrum for each species obtained by application of Equation 8.

DETAILED DESCRIPTION OF T~E INVENTION
., .
Figure l shows a schematic representation of an apparatus in our laboratory that embodies the essential features of-Electrospray Mass Spectrometry (ESMS) and has-been described elsewhere. (C.M. Whitehouse, R.N. Dreyer, ~. Yamashita, and J.B. Fenn, Anal. Chem. (1985) 57, 675; U.S.- Patents 4,531,056, (Labowsky, Fenn and Yamashita) and 4,542,293,- (Fenn, Yamashita and Whitehouse).j-`- ~he following description of its operation-also provides a convenient introduction to its principles. A
solution containing the-analyte at a-flow rate usually between l and 40 ul/min enters the ES-chamber l through a stainless steel hypodermic needle 2 maintained at a few kilovolts relative to the walls-and end-plate 3.- The most direct way to achieve this potential difference is to float the source of sample liquid, SUBSTITU~:E SHEE F

' WO90/14148 PCT/US9OlO2716 2~32~9~ 14 :~
the hypodermic injection needle and the tube connecting them, at the required voltage while the rest of the apparatus is at or near ground potential. It is also possible to maintain the liquid injection needle at the required high potential, leaving the source of liquid sample at ground potential so that there is a voltage drop along the line between the two through which the sample liquid flows from source to needle. This voltage drop causes an electric current to flow from the needle, through the connecting tube to the source of liquid sample. The resulting current drain on the high voltage power supply can be minimized by making the connecting tube very long, thereby increasing its electrical resistance. Alternatively, a high voltage power supply can be installed that has sufficient capacity to maintain the desired voltage on the injection needle in spite of the current drain. In either of these cases the aperture leading into the vacuum system 4 can be a simple orifice or nozzle, but ~hey both encounter problems of cost and safety. A more advantageous method of maintaining the source of sample liquid at ground potential, a most desirable operating condition when the sample source is a Liquid Chromatograph, is to replace the orifice with a capillary 5 of dielectric material, e.g. glass, as shown in Fig. l. Satisfactory operation to produce positive ions can be then be obtained with the typical values of applied voltages indicated in parentheses after each of the following components: needle 2 (ground), surrounding cylindrical electrode 6 (-3500), metalized inlet 7 and exit 8 ends of the glass capillary (-4500 and +40 respectively), skimmer 9 (-20) through which a core portion of the ion-bearing gas~from the-free jet passes into a second vacuum chamber lO containing-ion lens ll in front of the means of mass analysis 12 (ground).
With this configuration, the source of liquid sample, thé liquid sample injection needle 2 and the connecting tube, along with all external parts of the-apparatusj are at ground potential- and pose no hazard-to an operator, as will be explained later. --To produce negative ions similar voltages of~opposite signare applied. -In addition, it is useful to introduce a small ~
. . .
stream of oxygen or other electron scavenger near the needle tip in order to inhibit the onset of a corona discharge which occurs at lower voltages in the negative ion mode. If the electrospray : ;``^q- SUBSTITUl~`SHEET

WO90/14148 2 ~ ~ 2 4 9 ~ PCT/US90/02716 chamber is open to inspection the corona at the needle tip can be seen if the room is sufficiently dark and heard if it is sufficiently quiet. When the voltage is high enough to produce a corona in the positive mode the adduct cation in the spectral peaks very often becomes a proton, no matter what it was at lower voltages. In the negative ion mode the spectra sometimes contain peaks for ions to be expected if there is a discharge in ,a gas containing O,,N and C, i.e. O-, NO-, CN-, N02-, OCN- and At first inspection the indicated potential difference of 45~0 V between the inlet and exit ends of the capillary may seem startling. We have found that with the carrier bath-gas (nitrogen) at about one atmosphere the ion mobility is low enough so that the gas flow through the capillary can drag the ions out of the potential well at the capillary inlet and raise them back up to ground potential or as much as 15 kV above it.
Thus, we can readily provide the energies necessary for injection into a magnetic sector analyzer. The capillary, with a bore of 0.2x70 mm, passes just about the same flux of both bath gas and ions as did the thin plate orifice (d=O.lmm) used in the original apparatus for producing the free jet "lock"
between high and low pressure chambers in our first apparatus.
As the sample solution flows into the ES apparatus the field at the needle tip charges the surface of the emerging liquid which becomes dispersed by Coulomb forces into a fine spray of charged droplets. Driven by the electric field the droplets migrate toward the inlet end of the capillary through a countercurrent flow of bath gas typically at 800 torr,' at an ,entering temperature from 320 to 350 K, and~at a flow rate of about lOO mL/s.- The optimum values of'temperature and flow rate depend upon ,the design-details of a particular apparatus, thé
species being,analyzed and the objectives of the experiment.' , ,,Flow rates-,of;,the,bath-gas:that:are too high-may decreàse - ~;
sensitivity-by-preventing analyte ions-with low mobilities from reaching the entrance-,to the capillary.~ If the~flow rates are too low the extent of ion solvation may be excessive'. ~owever, in some cases it may be;desirable to retain a certain amount of solvation in the ions by decreasing the bath-gas temperature -and/or the flow rate. Thus, while useable ion beams will~be SUBSTi'rl~TE ~H~

` :

., . . ~, .

~2~9~ 16 ' obtained with the bath gas parameters at what have been indicated as typical values, a certain amount of trial and error is advisable for determining the best flow rate and temperature for a particular experiment in a particular apparatus. The choice of bath gas is another important variable. The gas should be inert in the sense of not undergoing reaction or charge exchange with analyte ions. In addition it should have a relatively high dielectric strength in order to avoid breakdown and discharge at the tip of the injection needle even when the applied voltages are relativel~ high. It is also desirable that the gas should be inexpensive if the apparatus is to run for long periods of time. We have found that nitrogen is generally satisfactory. Carbon dioxide also works very well for many species.- Air would serve if it is free of contaminants that might make chemical noise in the spectrum.
The solvent vapor from the evaporating droplets along with any other uncharged material are swept away from the capillary inlet by the bath gas flow. Meanwhile, in accordance with the scenario described earlier, the rapid evaporation of the migrating droplets promotes the sequence of Coulomb explosions that gives rise to droplets with a radius of curvature so small that the electric field at their surface is high enough to ' desorb solute ions into the ambient gas. Even solute species that are not themselves ions can attach solute cations or anions to their polar groups and desorb from the droplet as so-called "quasimolecular ions" suitable for mass analysis. Some of these desorbed ions are entrained in the flow of dry bath gas that enters the glass capillary to emerge at the exit'end as a ;
supersonic free jet in the first of'two-vacuum chambers. A core portion of this free jet-passes through a skimmer into the second vacuum chamber, delivering ions-to the mass analyzer. In the reduction to practice of this invention in our laboratoryj a quadrupol'e mass-filter was used.: However,-the-invention may be practiced with any kind of mass analyzer-as-long;as the m/z values~of th~ions to be~analyzed are within~its'range. -~--As noted~earlier, ions produced by the ion'sourcestraditionally used in mass spectrometry-generally'comprise singly charged species resulting from the loss or gain of an electron by a parent molecule. Thus the value of z is unity so ,- .. $U!~;TITU,~E~-Ct~

. .

. :, ... ..

WO90/14148 2 ~ ~ 2 ~ ~ ~ pCT/US90/027l6 that m/z which is what analyzers measure, is numerically equal to the mass of the ion. Moreover, an appreciable fraction of the ions are often charged fragments of the parent molecule. On the other hand, ions produced by some of the more recently developed sources comprise neutral parent molecules to which small cations or anions are attached or from which protons or other charge bearing entities have been detached. These newer and "softer" ionization methods include those to which we have referred earlier: FAB, FIB, PD, LD, TS and AS. Due in part to the larger size of the parent molecules that can be accommodated by these sources and in part to the nature of their ionization processes, ions with up to five or six adduct charges have been observed. (P. Roepstorff and B. Sundqvist in "Mass 8pectrometry in Biome~ical ~esearch," S.J. Gaskell, Ed., John Wiley, London, pp 269 ff (1986). However, such "extra" peaks have usually been unwelcome because they confuse the spectrum and are considered to "rob" intensity from the primary singly charged peak on which the determination of parent species mass is almost invariably based.
With the ES ion source shown in Figure l mounted to a quadrupole mass spectrometer mass spectra for a number of proteins with molecular weights from 5000 to almost 40,000 -daltons have been obtained. Figure 2 shows some representative examples. Analoguous spectra have been obtained with other organic and bio-organic species including carbohydrates and oligo nucleotides. The analytical procedure involves dissolving the analyte samples in solvent or mixtu e of solvents. Solvent mixtures comprising acetonitrile, water and methanol or l- ~
propanol were most effective.---It was advantageous in most analyses to lower-the pH of the solution by addition of small quantities of acetic acid (HAC) or trifluoroacetic acid- (TFA).
The~optimum proportions of these solvent components depended `on the particular sample;type:and-were determinëd-by-trial and~~
error. Solutisns with analyte concentràtions rànging from 0.7 to l37 umols/L, depending:upon the:species,`were injëctedLàt flow rates of 8 uL/min.- Similar spectra can be obtainediwith lower and higher flow rates. Flow rates as low as l uLjmin and as high as 20 uL/min, even up to 40uL/min in some cases have been utilized. At higher liquid~flow rates, the spray tends-to BS-I ITUTE S~

, wo go/l4l~482 4 9 ~ 18 PCT/US90/02716 become unstable. It is possible however to maintain a reasonably stable spray at still higher flow rates if a flow of gas is used to "assist" the electrostatic dispersion of the liquid. However, such assistance always results in a lower charge/mass ratio for the droplets and in a decrease-in sensitivity. In general, sensitivity increases as the liquid flow rate decreases because total ES ion current does not depend appreciably on flow rate so that the ratio of available charge to analyte mass increases as flow rate decreases. Each of the spectra shown in Figure 2 is the result of a single scan reguiring 30 seconds to cover the indicated mass range.
Table I summarizes the essential features of each mass spectrum shown in Fig. 2 and the information it provides. It is immediately apparent from the mass spectrum and Table I that the extent of multiple charging in ES ionization is much larger than has been encountered with any other soft ionization method. For example, the ionization of bovine insulin by FAB (xenon at 8-lO
4 KeV) produced only the singly and doubly charge molecular ion.
(see e.g. Desidero and Katakuse, Biomed. Mass Spectrom., 1984, ll (2), 55)- This multiple charging feature of ES is very attractive in that it extends the effective mass range of any mass analyzer by a factor equal to the number of charges per ion. Moreover, because the multiply charged ions have lower m/z values, they are generally easier to detect and "weigh" than are the corresponding singly charged ions of the same specie. On the other hand, peak multiplicity distributes the signal for one species over several masses. For relatively large analyte molecules the number of charges per ion is almost~always greater than the number of peaks. Therefore, the total current carried - by one species is greater when there is peak multiplicity than would be the case for a single peak containing the same total number of;singly charged ions. Unfortunately, the detector response per charge of a~multiply-charged ion is-not known.~ It is known,~however, that no post-acceleration has-been requiréd -, . ~, . . . -for multiply charged ions;that were large enough to requirè sùch acceleration had they been singly-charged. It is also known ., ~ , . . .
that the detection sensitivity obtained with-ES ionization of large molecules seems to be substantially greater than has been obtained with sources giving rise to ions that are predominantly ` `~SUBSTITUTE` SHEET
. ~. .. . ..

.. :

:`:
2~32~ 9~
WO90/141~ PCT/US90/02716 singly charged. Moreover, ion peak multiplicity allows multiple independent mass deter~inations from the data obtained in a single analytical procedure (i.e. mass can). Such determinations can be averaged to provide mass assignments to the parent ion o~ large molecules with more precision and confidence than would be the case for a single peak of a singly charged ion. Two algorithms for achieving this improved method of mass determination, along with illustrative results obtained by applying them will be set forth in what followings. one method of mass determination employs an averaging algorithm and the second employs a deconvolution algorithm. In all the calculations it is assumed that the detector response to any ion does not depend on the number of its charges. The application of the principles of this invention for the d'etermination of the mass of large molecules are not limited to the described algorithms. Other algorithms and calculation methods for practicing the principle of the invention can be developed by those skilled in the art.
"
I AVERAGING ALGORITHM
,, .
If one assumes that in a particular~mass spectrum the adduct ions such a hydrogen, sodium etc. of each analyte all have the same identity, and therefore mass, and that any neutral adducts such as solvation species are the same for each ion, then there are three variables associated with each of the peaks in the series: the mass M (numerically equal to the relative molecular weight Mr) of the parent molecule including neutral adducts, the number of charges i, and the mass ma f the adduct ions. We use i rather than z to designate the number of charges in order to avoid confusion with the customary m/z scale of mass spectra for which m=M+ima, the total mass of the'ion. In ' general z-iq where q is an elementary A charge-and i-;is unity~in ~conventional spéctra for singly charged ions. -It-should be-kept in mind that the units of m/z?are~properly daltons-~Da)~ pr'; -elemèntàry chàrge even though a measured peak position is~often 'loosely expressed simply in daltons when z is one. All the;
formulas apply equally well to negatively charged ions with ma - . - . . :
~' Sa,lBSTITUT~: S~IEE~

WO90/14148 PCT~US90lO27l6 2~'~2~ 20 being negative in the case of charging by atom abstraction.
Thus one can write for each peaks:

~ K ' ~ -tk¢ I m, or . . .
- : : " (K;-m~- K';-k~

where Ki is the value of m/z for a peak position on the scale of the mass analyzer and R'i ~ Ki ~ ma equals the m~z value of that peak position minus the adduct ion mass ma. All masses are isotope averaged i.e., calculated using the chemical atomic weight scale. The positions of the peak maxima are used to determine the value of Ki. With the further constraint that i must be integral, equations 1 for any pair of peaks are in principle enough to determine the three unknowns simultaneously.
j Elementary manipulation of eqs. 1 for two charge states i and > 0) yields.for the:number of charges i: - -~ . .
;' - . .
_ i . ' i 3 j hl ~2) K',-K'hj . _ ., , : .
.
,; , . - - . ,.
- -- --. ... .
.. . .
t --For-example,-.~if the adduct ions are protons (ma=l) and a peak at Ki=1001.0 and another one two peaks away (j=2j at Ki~2--~834.31~are--observed then i=2-K~i+2/(K~i-K~i+2)-ti666-6j(iooo-833.3)-~O... That is,--the'peak at lOOi has lO'charges and the one at 834.3-has-12.:-The accuracy:required in Ki for determining i -is low,- especially'-if Xi-Ki~j is made largè, but lncreases as i getæ.larger. From eq.'2 it can be shown that an`accuracy of one m/z unit in the determination of K~-suffices'''for i~5 Up to 100 or more i.e., a 100 kDa molecule if the average value of m/z is U13~;TOlrUlTE SH~
.. ~ ~` ..

2~2~9~
W090~}41~ PCT/US90/02716 around 1000. Nor does the value of ma need to be exact for the determination of i because ma does not effect the denominator of eq. 2 and has only a small effect on the numerator. However, to determine the ion adduct mass directly from the peak positions - we need a substantially higher accuracy in the measured values of Ki. From eqs. 1:
.
.. m, - l( (i + j) K~J ~

(3) . . .

... .
where i and i+j are for any two peaks. A measurement of Ki with an accuracy of about 1/iKi would be required to determine ma to within one dalton (i.e. an accuracy for Ki of approximately +o.01 Da if Ki = 1000 and M = 10 kDa). However, a more modest mass accuracy will usually suffice because the possible values of ma are often well separated e.g. Na+ at 23 and Kf at 30 Da.
For proteins it is an assumed that ma=l which seems to be appropriate (at least as long as there is not too much sodium in the solution1 and this,assumption will be made in the numerical examples in this discussion. '"
With known charge number, and measured or as~umed adduct ion mas~ ma, the parent ion mass M can be obtained from any one peak or averaged from a number of peaks:
, ' M - 1 ~ iK;

(4) ~: . .. . . . , ~ -.. . .
.

~, where the ummation is,over the~i values for the peaks selected for averaging and nO is the number-of those peaks. '' The coherence~of the peak sequence makes-possible a`'further .
improvement in the estimate of M given by eq 4.- ~his '' improvement allows us to identify and ignore peaks that do not , .

WO90/14t48 PCT/USgO/02716 '2~3~4~Q 22 belong in the sequence and to evaluate the quality of the spectrum. From eq l for any two peaks we obtain:

K; , K.hj l,l~RC'i 1~ (5) Hence any pair of peaks in an experimental mass spectrum defines a point with y=tK'i/K'i+j)-l)/j and x=l/i. All such points should fall on the line y=x. The scatter of the pair-points around this line is a measure of the quality of the mass spectrum. The more accurate the mass determination, the closer to the line the point will fall. Figure 3a shows such a plot for the cytochrome C mass spectrum of Figure 2. The seven points at each abscissa value of l/i correspond to the seven possible ratios of R'i/K'i+~ for the eight peaks in the spectrum as i to i+; goes from 12 to l9. The quality of-the experimental results can be readily inferred for~each individual peak and for the mas~ spectrum as a whole from the departure'of thë'points from the line values. The larger the spread around, or systematic offset from, the x-y line, the less reliable is the measurement. The sensitivity of this quality index is demonstrated in Figure 3b. The points are from the same mass spectrum of cytochrome C, but the peak at i-14 was deliberately offset by 5 units of m/z. It is apparent that this "stray peak"
can be readily distinguished from the sequence of peaks by the much larger spread about the line of all the points i-14 and of the cross points at the other values of i. The cross points represent pair combinations with the peak at i=14 when it was displaced by five m/z units. It should be pointed out that this plot is a test for self-consistency of the peaks in-a sequênce and does not depend on the Yalue of parent mass;~
The information on the quality of--K'i--valuess obtained from thé above procedure can yield a better'estimate of-~M~by ~ '-''~'~
providing a weighting factor for each peak. In essence the contribution of each K'i in the averaging process is weighted in - S~aSm~T~ 5~
' .. . .

WO90/~4148 2 0 ~ 2 4 ~ ~pCT/US90/027l6 ac~ordance with the proximity of its corresponding points to the straight line in a plot like the one in Figure 3a. Equation 6 defines a relative weighting factor Wi for each peak i:

W~
pO i+j (6~

where ! ' W ~ ~ Wi W is the normalizing constant and p is an-integer equal to or greater than 2 which specifies the dependence of w on the proximity of the parent point to the straight line in Figure 3b.
' For a peak whose K'i has a better than average fit into the sequence pattern, Wi tends to be greater than onè. It tends to ` be less than one if the K'i value departs from its,'lideal"
'I pssition by an amount greater than the average of all the other peaks. The larger its departure the smaller will be its weighting factor and its relative contribution to the overall average. Figure 4 shows how the unweighted average differs in behavior from the weighted average obtained with wi's from eq. 6 for p-2. To produce Figure 4, the peak at i'l9 in the cytochrome C spectrum (Figure 2) was shifted in increments from -7.5 to ~7.5 units from its measured m/z value and at every --position we calculated the relative weighting factor wlg, the unweighted average, and the weighted average with a value of 2 for p. ,Evidently a shift of -7.5 mass-units in K'lg results in an unweighted mass-average shift of -17.8 mass units whereas the weighted average shifts by just -2.6 mas~-units, only lS% of~the ; mass shift in the unweighted,case.' The location of the maximum ,in wlg,indicates tha~t the measured R~lg~was'one unitAtoo iow according to the other--peaks~of the~sequencè~ corresponding to an error somewhat,larger-than~the standard deviation of'+'Da in the final_mass;-determination~for cytochrome-C~.-' Choosing~'a'va'iue for p greater than,2 further enhances the depend~nce of'the weighting factor Wi on the deviatlon of peak ~'i from the ideal m~z ~alue. The decrease in the weighted standard deviation sw~
.
'2, -~ SUBSl lTUTE` SWEET

~ !
., .
.:

~ .

whi2c~ is calculated by multiplying by Wi the contributions of each K'i to the error, becomes smaller as p increases. Table II
shows this effect for the case of carbonic anhydrase II
(M=29,006): Sw decreases from + 15.6 mass units for the unweighted average to + 7.9 mass units for p=6. It should be noted that the weighted average does not necessarily change monotonically as p is increased.
In comparing the parent mass obtained by this weighting procedure with the true mass one has to keep in mind that there are at least two sources of error that contribute to ~M (i.e.
Mtrue ~ Mmeas) One~ the 9tatistical error in ascertaining the indi~idual peak positions, is expressed in the unweighted or weighted standard deviation of the measured mass M. The other arises from systematic errors in the calibration of the analyzer mass scale. This latter source of error will obviously not be affected by any weighting procedure. If the error due to mass calibration predominates, weighting the average will not provide a major improvement in mass accuracy. In such a case the standard deviations, weighted or unweighted, do not indicate the experimental accuracy of a measurement but only its precision.
A criterion for deciding if mass scale calibration is negligible in determining the error in M is:

i(~ve)~Da~s (7) v where iave is an average number of charges per ion i~ the -.
sequence of peaks, s is the~standard deviation derived from averaging the individual peaks, and ~Da is the absolute value o the error; in daltons of the mass scale calibration. For the example,of the cytochrome C spectrum (iave=l5, s--+5Da, ~Da~lia) the criterion is not fulfilled and~the.overall error is ; ~
dominated by ~Da.~ Hence in these measurements we would not expect a major decrease in ~M from the--weighting procedure.
Calculating the weighting factors-wi allows a j~dgement of the quality of a spectrum in:much the same way as does noting the scatter of points in a plot like the~one in Figure 3a. In `. SUZSTITIVTE ~3HE~F
, ` .

249~
WO ~14148 PCT/US90/02716 the plot a misassigned peak can be identified by a large difference between y and x values of points in a plot like the one in Figure 3b. Large differences correspond to low Wi values in the numerical procedure of eq 6. Table III illustrates the results of the numerical procedure for the case of cytochrome C.
The accuracy with which mass assignments can be made depends directly on the accuracy of the analyzer's mass scale.
For unit mass accuracy at l00 kDa the scale error must be smaller than 0.0l m/z units (eq 7). If mass scale calibration is not a problem (i.e. if eq 7 is satisfied, for example, by peak matching) and the values of K'i could be determined to within 0.l mass units, then unit mass accuracy up to masses of several tens of kilodaltons might be possible even for guadrupole instruments (cf. eq 4 with iave = 50 and nO = 25).
Of course, this calculation presupposes that the K'i values can be determined as accurately for high mass molecules with multiple charges as they can be for singly charged low mass molecules.
It should be noted that isotope spread does not contribute appreciably to peak broadening. The contribution to peak half-width from the isotope distribution in a typical protein even at l00 kDa (C4590 H6720 Nl260 1500 S30, i.e. a scaled-up version of Glucagon) is less than 30 mass units (8). The corresponding spread in m/z is less than 0.3 mass units in a peak for ions with l00 charges, not an unreasonable number for such a large ; molecule.
-; -DECONVOLUTION ALGORITHM
.:
-; Visual interpretation of a spectrum comprising multiply charged peaks, and determination of parent mass, would be simplified if the coherent sequence of peaks could be `
transformed to one singly charged peak located on an m/z scale at the molecular mass M of the parent compound.

. , .
. .
.. . . , , -,:. -.
~ .
E ~ b .. . .

' 2~32490 26 ~~
It will be shown t.hat the following function can provide such a ,transformation:

,, F(M )= ~ ftM + m~ ' ' F ig the transformation function for which the argument M* i5 any arbitrarily chosen trial value of M for which F is to be evaluated. The symbol f represents the distribution function for peak heights in a measured mass spectrum. For example, if there i8 a peak of relative intensity 5 at m~z=500 then f(500)=5. ma is the adduct ion mass, as previously defined. It will be shown below that the function F has its maximum value when M* equals the actual value of M, the parent mass of the multiply charged ions in the sequence. Thus, evaluating F at all values of M* with 0 < M ~ yields a transformed or "deconvoluted" spectrum, in which the peak with maximum height corresponds to the parent species with a single massless charge.
An example,will make it clear how the deconvolution,algorithm reconstructs the parent peak from the sequence. For simplicity we assume ma=0. ~igure 5a shaws a hypothetical measured spectrum f generated by,charging a molecule with mass M with from 6 to 15 massless adduct ions such that the height'is unity for every peak in the sequence. These "measured" peaks occur at M/6, M/7, ...N/15. If F is evaluated at M =M the following sum is obtained:
.. ..
: .. . .... ..
( ) f(1) (2) '~ (5) (6) ~15)~ (lfi)~17)~
O + O . + ... + . O + 1 + . + 1 +

Thus, the function F has created a peak at the position M*=M
with a height equal to the sum of the heights of the sequence peaks. It is assumed that the height of any peak in a measured .. ..

' WO90/14148 2~'~249a PCT/US90/02716 ! . 27 spectrum is related to the abundance of its ions by the same proportionality constant no matter how many charges are on those ions.
If F is evaluated at M + E, a'position slightly larger than - M, then F wiIl be zero because (M+E) does not correspond to the position of any of the'sequence peaks. However, it is also i apparent from the example that the function F will create peaks in the deconvoluted spectrum at more positions than at M*=M. At N =2/3M the following sum results:

F(2~) Z f~ ~1 ))'f( 2 ~+' = f(6~ f(9J (1~ (15 , , : .
Figure 5b shows the results of applylng eq.8 to the spectrum of Figure 5a, an ideal sequence of multiply charged ions with 6 ~ i < 15. It is a property of the spectrum resulting from the transformation F, as shown in Figure 5b, that it compr~ses a series of calculated peaks containing contributions from the-actual peaks in an observed spectrum. By reference to the above procedure, a number of general features of the deconvoluted spectrum can be inferred. As we have already noted, its most prominent peak occurs when M* equals the parent mass M and has a magnitude equal to the sum of the magnit~udes of the individual peaks in the sequence. The next highest peak occurs at M/2 and it is at'most only'half as high as the peak at M. In general:there are~pëaks at (k/i) M, where imin < i < imaX and k is any integer. In the sequence of "side peaks" on either side of the-parent peak those closest to the parent (maximum) peak M ocsur at ((imaX + l)/imaX)M where imaX
is the highest number of charges on a single ion.''~'The position of these closest side'peaks''is indicated by arrowheads in-Figure 5b. -The-height of these-side peaks is a factor of ii(imaX - .
- - . . - . I
imin) smaller than the:~height of the molecular peak àt mass M.
~`' The deconvoluted spectrum is periodic in'M. This periodicity may be--viewed physically as-being-due-to synthetia "overtonës"
of the basic spectrum corresponding to doubling, tripling etc., SUBSTlTlJTF. SHEET
' ' , -`
. , .

.

2~324~ 28 `
both the parent mass and the number of charges on each peak, and a difference of 2,3 etc. in the i values of adjacent peaks.
The transformed spectrum changes somewhat in appearance if finite resolution and background are taken into account. To simulate th-se effects, the shapes of individual peaks in the sequence of Figure 5a are represented in Figure 6a by isoceles triangles with a relative full width at half height (FWHH) of 0.005. Furthermore, a constant background of 10% of the peak height was introduced. The consequences of this treatment are seen in Figure 6b. There is a progressive increase in the magnitude of the "side peaks" because the non-zero peak width in the observed spectrum results in a contribution to F at m/z values on either side of the peak centers. The steady increase in the "baseline" is caused by more frequent sampling of the background at higher values of M .
` This "deconvolution algorithm" was applied to the eight experimental spectra shown in Figure 2 with the assumption that ma = }. Each mass spectrum was represented by 1150 da~a points for a full scan.,-- In the algorithm a linear interpolation between adjacent data points was used. It should be pointed out that the algorithm needs no apriori information about charge states or the number of peaks in the sequence. The only instruction specific to a particular spectrum is the range of m/z in the "window" that spans the peaks to be deconvoluted.
Thus the summation of eq.8 goes only from the minimum-to the maximum values of m/z within this window. Such a limitation in the range of the summation reduces the noise in the transformed spectrum because background signal that lies outside the range-of interest is not sampled.~Figure 7a displays the~result of applying the deconvolution procedure to the mass spectrum of-cytochrome C in Figure,2. The transformed spectrum clearIy ~
shows the side peaks, the overtone-periodicity and the baseline increase discussed above,. ,The parent (largest)-;peakiis ;. æ;- ~:. -3J'` -magnified in Figure 7b by "zoom" expansion of the--mass scale in ~, its vicinity. Figure 8 shows the results of the same treatment for the case of a larger protein, carbonic anhydrase II , -,--.... . . . . . .. . ..
~` (M-29,006Da). Widths at half maximum for both measured and deconvoluted peaks for the other spectra were usually about 1%.
Such large spreads resulted in part because effective resolution . ,, .. . ~ .
,~ ' --:

WO90/141~ 2~32~9a PCT/US90/027l6 of the mass analyzer used to collect these mass spectra was only about 300. Table IV summarizes the results for molecular weight determination from the spectra in Figure 2.
In general there is a region immediately around the parent peak that is free from artifacts of the deconvolution algorithm.
As noted above, this region should extend from imaX-l)/i maXXM
to (imaX+l)/imaxxM~ where imaX is the maximum number of charges found on a molecule. In Figures 5 and 6 the boundaries of this region are marked by black triangles. In the deconvoluted cytochrome C mass spectrum (Figure 7), however, a small peak (marked with an open triangle) is observed about 340 ~ass units higher than the molecular peak. Detailed examination of the measured spectrum reveals a small peak just above each main peak in the sequence whose position agrees with the peak found in the deconvolution. This observation indicates that the algorithm can readily detect small peaks close to a parent peak that may be due, for example, to parent species variants with slightly different masses.
This method for the determination of the mass of large molecules can also be applied when two or more parent species are present in the sample. Figure 9 shows the mass spectrum for a solution of cytochrome C and myogolobin, each at a concentration of 0.5 mg/ml in an acidified mixture of acetonitrile, methanol and water. Also shown is the result of applying the deconvolution algorithm along with a "zoom"
magnification of the pertinent parts of the deconvoluted spectrum. As might be expected, the number of different species that a mixture can contain and still be resolved by this ~
procedure depends upon their relative concentration in the mixture and different in their masses. ~he key factor is how close-together are the peaXs of the component multiply charged ionsiand whether the avaiIable analyzer can resolve them.

. ~

~, .
.
.
--` - ~ `-: ~ - ; -SUE~STIT~JTE SHEET
., "
, , :

, .

Claims (39)

WE CLAIM:

1. A composition of matter comprising a population of multiply charged ions derived from a polyatomic parent molecular species, the number of charges on each ion defining the ion's charge state number, said population of ions consisting of a plurality of sub-populations, one for each charge state number between a minimum value not less than two and a maximum value not less than five.

2. The composition of matter according to claim 1 generated by dispersing a solution of said polyatomic parent molecular species in a volatile solvent as highly charged droplets into a bath gas, causing said solvent to vaporize and the size of said droplets to shrink until said multiply charged ions desorb from said droplets.

3. The composition of matter according to claim 2 wherein an electric field is applied to said solution for dispersing the same.

4. The composition of matter according to claim 1 generated by dispersing a solution of said polyatomic parent molecular species in a volatile solvent as highly charged droplets into a gas where said solvent vaporizes from said droplets of said solution thereby shrinking them until said multiply charged ions desorb from said droplets.

5. The composition of matter of claim 4 wherein said gas is at approximately atmospheric pressure.

6. The composition of matter of claim 1 wherein said minimum charge state number is not less than 8 and said maximum charge state number is not less than 12.

7. The composition of matter of claim 1 wherein said minimum charge state number is not less than 5 and said maximum charge state number is not less than 9.

8. The composition of matter of claim 1 wherein said polyatomic parent molecular species is selected from the class of compounds known as bio-polymers.

9. The composition of matter of claim 1 wherein said polyatomic parent molecular species is selected from the group comprising proteins, peptides, nucleic acids, carbohydrates and combinations of two or more of these species.

10. The composition of matter of claim 1 wherein said polyatomic parent molecular species is selected from the group comprising sugars, polynucleotides, synthetic polymers and combinations of two or more of these species.

11. A composition of matter comprising a plurality of sub-populations of charged ions derived from a polyatomic parent molecular species, each of said sub-populations characterized by ions having the same number of charges, a first sub-population of said ions having a minimum number of charges not less than two, a second sub-population of said ions having a maximum number of charges not less than five, and for each possible integral number between said minimum and maximum number of charges, sub-populations of ions each having said integral number of charges.

12. The composition of matter according to claim 11 generated by a process comprising the step of applying an electric field to a solution containing a solvent and said polyatomic parent molecular species and dispersing said solution as highly charged droplets into a substantially atmospheric pressure environment wherein said solvent of said solution is vaporized and said droplets shrink in size so that said charged ions desorb from said droplets.

13. A composition of matter comprising a population of multiply charged ions derived from a polyatomic parent molecular species, the number of charges on each of said ions defining that ions charge state number, said population of ions comprising a plurality of sub-populations, one for each respective charge state number between a minimum value not less than 2 and a maximum value not less than 5, said population generated by applying an electric field to a solution of said polyatomic parent molecular species and dispersing the solution as highly charged droplets into a bath gas at approximately atmospheric pressure for vaporizing the solvent portion of said solution, thus causing the said droplets to shrink until ions constituting said population desorb from said droplets.

14. The composition of matter of claim 13 wherein said minimum charge state number is not less than 8 and said maximum charge state number is not less than 12.

15. The composition of matter of claim 13 wherein said minimum charge state number is not less than 5 and said maximum charge state number is not less than 9.

16. The composition of matter of claim 13 wherein said polyatomic parent molecular species is selected from the group comprising bio-polymers.

17. The composition of matter of claim 13 wherein said polyatomic parent molecular species is selected from the group comprising proteins, peptides, nucleic acids, carbohydrates and combinations of two or more of said species.

18. The composition of matter of claim 13 wherein said polyatomic parent molecular species is selected from the group comprising sugars, polynucleotides, synthetic polymers and combinations of two or more of said species.

19. A composition of matter comprising a population of multiply charged ions for which the mass spectrum is characterized by a sequence of not less than three peaks, each peak corresponding to a discrete sub-population of multiply charged ions, each of said ions having a distinct integral number of charges wherein the multiply charged ions of each peak in said sequence differ from those of adjacent peaks by one charge.

20. A method of determining the molecular weight of molecules with masses above the nominal range of a mass analyzer comprising the steps of:
generating a population of multiply charged ions from a polyatomic parent molecular species, the number of charges on said ions defining the ion's charge state number, said population of ions comprising a plurality of sub-populations the ions of each subpopulation having the same charge state number, said population including one subpopulation for each possible integral value of charge state number between a minimum of three and a maximum not less than five;

producing a mass spectrum and from it determining the mass/charge ratio for the ions of each of said sub-populations; and determining the most probable molecular weight of said polyatomic parent molecular species.

21. The method of claim 20 wherein said most probable molecular weight of said polyatomic parent molecular species is calculated by use of an averaging algorithm.

22. The method of claim 20 wherein said most probable molecular weight of said polyatomic parent molecular species is calculated with a deconvolution formula.

23. The method of claim 20 wherein said nominal mass range of said mass spectrometer for any single ion having a charge state of unity is increased by a factor equal to the charge state number on said ion after it has been multiply charged.

24. The method of claim 20 wherein said minimum and maximum values of charge state number increase as the molecular weight of said polyatomic parent molecular species increases.

25. The method of claim 20 wherein said minimum and maximum of charged state numbers increase as the size of said polyatomic parent molecular species increases.

26. The method of claim 20 wherein said most probable molecular weight is determined by averaging values, each of said values having been calculated from the mass/charge values of any pair of peaks in said spectrum, each of said peaks in said pair corresponding to scans of said polyatomic parent molecular species.

27. The method of claim 26 wherein said independent calculations are made from separate peaks of a spectrum obtained from a single mass scan of said mass spectrometer.

28. A method for producing a population of multiply charged ions comprising the steps of:
supplying a solution comprising at least one polyatomic parent molecular specie dissolved in the solvent portion of said solution, applying an electric field to a stream of said solution:
dispersing said solution as charged droplets into a chamber, supplying a bath gas to said dispersed solution to effect vaporization of said solvent portion of said solution and shrinking of said charged droplets, so that multiply charged ions desorb from said droplets.

29. The method as claimed in Claim 28 wherein said polyatomic parent molecule species comprises biopolymers.

30. The method as claimed in Claim 28 further comprising the steps of applying an electric field to move said multiply charged ions in a first direction and flowing said bath gas in a direction opposite to said first direction.

31. The method as claimed in Claim 28 wherein said bath gas is heated.

32. The method as claimed in Claim 28 wherein said chamber is maintained at substantially atmospheric pressure.

33. Apparatus for producing a population of multiply charged ions comprising means for supplying a solution comprising a polyatomic parent molecular specie and a solvent into a chamber, means for applying an electric field to said solution, means for dispersing said solution as charged droplets in said chamber, means for applying a bath gas to said dispersed charged solution to vaporize said solvent portion of said solution and to shrink said charged droplets, whereby multiply charged ions desorb from said droplets, said multiply charged ions ranging in charge state from a minimum of 3 to a maximum not less than five.

34. The apparatus as claimed in Claim 33 wherein said polyatomic parent molecular species comprises a biopolymer.

35. The apparatus as claimed in Claim 33 further comprising means for applying an electric field to flow said multiply charged ions in a direction opposite to that of said direction of flow of said bath gas.

36. The apparatus as claimed in Claim 33 further comprising means for heating said bath gas.

37. The apparatus as claimed in Claim 33, further comprising means for maintaining said chamber at substantially atmospheric pressure.

38. A method of determining the molecular weight of a molecule comprising generating a mass spectrum comprising a sequence of discrete peaks of multiply charged ions of said molecule;
and analyzing the peaks of said spectrum to determine said molecular weight.

39. The method as claimed in Claim 38 wherein said peaks of said spectrum correspond to ions having no fewer than three unit charges.