Electron Ionization Mass Spectra Research Articles

Essential oils from fennel plants as valuable chemical products: gas chromatography–mass spectrometry, FTIR, quantum mechanical investigation, and antifungal activity

AbstractIn the present study, the biomass produced by fennel plants (Foeniculum vulgare Mill.) was converted to yield bioactive chemicals, and the hydrodistillation method was used to extract the essential oils (EOs) from both the leaves and the umbels. The antifungal activity of the EOs was tested using bioassay against the development of Fusarium oxysporum MW854649 and Alternaria solani MT279570. Molecular spectroscopic detection techniques were used to evaluate the EO products using gas chromatography–mass spectrometer (GC–MS) and Fourier transform infrared spectroscopy (FTIR). GC–MS equipped with single quadruple analyzers have been used to measure the electron ionization (EI) mass spectra of the primary constituents of fennel EOs at 70 eV. The main chemical compounds in the EO from leaves were anethole, estragole, D-limonene, trans-β-ocimene, and fenchone, with percentages of 37.94, 35.56, 17.46, 1.53, and 1.49%, respectively. The abundant compounds in the EO from umbels were estragole, anethole, D-limonene, fenchone, and γ-terpinene, with percentages of 51.18, 25.08, 12.22, 6.57, and 2.86%, respectively. EI mass spectral fragmentation of the major compounds D-limonene, estragole, anethole, and fenchone has been investigated. Umbels and leaf EOs at 5000 mg/L displayed the strongest suppression of fungal growth against A. solani, with values of 87.78% and 79.63%, respectively, compared to the positive control (94.44%). The EOs from umbels and leaves at 5000 mg/L showed the highest inhibition of fungal growth against F. oxysprium as compared to the positive control (94.44%), with values of 77.77% and 72.96%, respectively. All of the important ions—including a few distinctive fragment ions—have comprehensive fragmentation pathways defined. Based on EI, the main routes of fragmentation for the primary compounds have been identified. The existence of alkenes, aliphatic alcohols, ethers, carboxylic acids, ester compounds, alkanes, hydrogen-bonded alcohols, and phenols was demonstrated by the FTIR analysis of fennel EOs. On the other hand, the reactive behavior of the studied molecules has been investigated using two quantum mechanics method: the modified neglect of diatomic overlap (MNDO), a semi-empirical method, and the density functional theory (DFT)/B3LYP hybrid density functional method with the 6-311G (d, p) basis set in the ground state for gas phase. The optimum geometries have been obtained through the execution of computations and electrostatic potential. The obtained analytical and calculated results were then used to understand the activity of the studied EOs in further medical applications.

Characteristic structures of liquid crystal monomers in EI-MS analysis and the potential application in suspect screening

Liquid crystal monomers (LCMs) are of emerging concern due to their ubiquitous presence in indoor and outdoor environments and their potential negative impacts on human health and ecosystems. Suspect screening approaches have been developed to monitor thousands of LCMs that could enter the environment, but an updated suspect list of LCMs is difficult to maintain given the rapid development of material innovations. To facilitate suspect screening for LCMs, in-silico mass fragmentation model and quantitative structure-activity relationship (QSPR) models were applied to predict electron ionization (EI) mass spectra of LCMs. The in-silico model showed limited predictive power for EI mass spectra, while the QSPR models trained with 437 published mass spectra of LCMs achieved an acceptable absolute error of 12 percentage points in predicting the relative intensity of the molecular ion, but failed to predict the mass-to-charge ratio of the base peak. A total of 41 characteristic structures were identified from an updated suspect list of 1606 LCMs. Multi-phenyl groups form the rigid cores of 85% of LCMs and produce 154 characteristic peaks in EI mass spectra. Monitoring the characteristic structures and fragments of LCMs may help identify new LCMs with the same rigid cores as those in the suspect list.

Characterization of the Volatile Constituents of Plai (Zingiber purpureum) by Gas Chromatography-Mass Spectrometry.

Zingiber purpureum Roscoe, known as plai in Thailand, is a perennial plant of the Zingiberaceae family and has traditionally been used in Southeast Asian countries to treat inflammation, pain, and asthma. In this study, we performed the characterization of the volatile constituents in ethyl acetate extracts of plai. Ethyl acetate extracts derived from the rhizomes of plai were subjected to gas chromatography-mass spectrometry, and the key peaks in the total ion current chromatograms were annotated or identified. In total, twenty-one compounds were identified using isolation procedures or standards, and nine compounds were annotated by comparing their Kovats retention index (RI) and electron ionization (EI) mass spectra with those in the literature. Most of the identifications were inconsistent with the tentative annotations found via library search and suggested that some peaks were incorrectly assigned in previous studies. Thus, to avoid further misannotations and contribute to the research on dereplication, the RI value, EI mass spectral data, and NMR spectroscopy data of the isolated compounds are reported.

Thermodynamic properties of indoline and benzoxazine based spiropyrans studied by Knudsen effusion mass spectrometry

An approach including thermal analysis and Knudsen effusion mass spectrometry was used to investigate the thermal stability range and the thermodynamic properties of sublimation for four indoline and benzoxazine based spiropyrans: 1,3,3-trimethyl-6′- (tert-butyl) −8′-formyl-spiro [indoline-2,2′-2H-chromene] (1), 1,3,3,8′-tetramethyl-6′-formyl-spiro [indoline-2,2′-2H-chromene] (4), 1,3,3-trimethyl-8′-methoxy-6′-formyl-spiro [indoline-2,2′-2H-chromene] (7), and 3-methyl-6′-methoxy-8′-formyl-spiro [1,3-benzoxazin-4-one-2,2′-2H-chromene] (9). The melting and decomposition temperatures as well as the melting enthalpies were obtained by thermal analysis. The electron ionization mass spectra as well as the ionization efficiency curves were measured. Schemes of the formation of the main ions in the mass spectra were suggested. The temperature dependencies of vapor pressures were used to obtain the sublimation enthalpies. All data were obtained for the first time.

New Cytotoxic Monoalkyl Glycerol Ether from the Red Sea Soft Coral Nephthea mollis.

A new monoalkyl glycerol ether, 3-(n-henicosyloxy)propane-1,2-diol (1), was isolated from the CH2 Cl2 /MeOH crude extract of the Red Sea soft coral Nephthea mollis. Additionally, three known related analogs were identified: chimyl alcohol (2), batyl alcohol (3), and 3-(icosyloxy)propane-1,2-diol (4). The chemical structure of 3-(n-henicosyloxy)propane-1,2-diol was determined using advanced spectroscopic analyses, including 1D, 2D Nuclear Magnetic Resonance (NMR), Electron Ionization mass spectra (EI-MS), and High-Resolution Electron Spray Ionization mass spectra (HR-ESI-MS) analyses. Furthermore, the identification of chimyl alcohol, batyl alcohol and 3-(icosyloxy)propane-1,2-diol was achieved by studying their EI mass fragmentation analyses and comparing their mass data with those previously reported in the literature. The cytotoxic activity of the Nephthea mollis crude extract and 3-(n-henicosyloxy)propane-1,2-diol was evaluated against five human cancer cell lines: HepG2 (hepatocellular carcinoma), MCF-7 (breast carcinoma), NCI-1299 (lung carcinoma), HeLa (cervical cancer cell), and HT-29 (colon adenocarcinoma). Moreover, 3-(n-henicosyloxy)propane-1,2-diol revealed moderate cytotoxicity against the HeLa cell lines with an IC50 value of 24.1 μM, while showing inactivity against the remaining cell lines (IC50 >100 μM).

Stannane in extreme ultraviolet lithography and vacuum technology: Synthesis and characterization

In extreme ultraviolet (EUV) lithography, tin droplets evaporate and subsequently coat various surfaces including the collector mirrors. To clean off the tin, a hydrogen plasma is often used, but as a result, an unstable by-product, stannane (SnH4) is formed. The physicochemical characteristics of this gas, its formation in a plasma process, and its interaction with various materials have not been explored and understood completely. Here, the electron ionization mass spectrum of SnH4 is presented. All ten natural abundance isotopes were observed experimentally for each fragment, i.e., Sn+, SnH+, SnH2+, and SnH3+. Density functional electronic structure theory was used to calculate the optimized ground state geometries of these gas phase species and their relative stabilities and helped explain the absence of SnH4+ in the observed signals. The density of the liquid, its cracking pattern, and the surface morphology of its deposits were examined. The surface of the deposited tin film resulting from the decomposition and subsequent oxidation was characterized by x-ray photoelectron spectroscopy. The main species found at the surface were metallic tin and tin (II) oxide (SnO). The detailed characterization of stannane should help correctly identify it in EUV lithographic processes and develop approaches in the future to mitigate its decomposition and redeposition on the collector mirrors or vacuum chamber walls.

Inferring the Nominal Molecular Mass of an Analyte from Its Electron Ionization Mass Spectrum.

The performance of three algorithms for predicting nominal molecular mass from an analyte's electron ionization mass spectrum is presented. The Peak Interpretation Method (PIM) attempts to quantify the likelihood that a molecular ion peak is contained in the mass spectrum, whereas the Simple Search Hitlist Method (SS-HM) and iterative Hybrid Search Hitlist Method (iHS-HM) leverage results from mass spectral library searching. These predictions can be employed in combination (recommended) or independently. The methods were tested on two sets of query mass spectra searched against libraries that did not contain the reference mass spectra of the same compounds: 19,074 spectra of various organic molecules searched against the NIST17 mass spectral library and 162 spectra of small molecule drugs searched against SWGDRUG version 3.3. Individually, each molecular mass prediction method had computed precisions (the fraction of positive predictions that were correct) of 91, 89, and 74%, respectively. The methods become more valuable when predictions are taken together. When all three predictions were identical, which occurred in 33% of the test cases, the predicted molecular mass was almost always correct (>99%).

On the challenge of unambiguous identification of fentanyl analogs: Exploring measurement diversity using standard reference mass spectral libraries.

Fentanyl analogs are a class of designer drugs that are particularly challenging to unambiguously identify due to the mass spectral and retention time similarities of unique compounds. In this paper, we use agglomerative hierarchical clustering to explore the measurement diversity of fentanyl analogs and better understand the challenge of unambiguous identifications using analytical techniques traditionally available to drug chemists. We consider four measurements in particular: gas chromatography retention indices, electron ionization mass spectra, electrospray ionization tandem mass spectra, and direct analysis in real time mass spectra. Our analysis demonstrates how simultaneously considering data from multiple measurement techniques increases the observable measurement diversity of fentanyl analogs, which can reduce identification ambiguity. This paper further supports the use of multiple analytical techniques to identify fentanyl analogs (among other substances), as is recommended by the Scientific Working Group for the Analysis of Seized Drugs (SWGDRUG).

Comparative Evaluation of Electron Ionization Mass Spectral Prediction Methods.

During the past decade promising methods for computational prediction of electron ionization mass spectra have been developed. The most prominent ones are based on quantum chemistry (QCEIMS) and machine learning (CFM-EI, NEIMS). Here we provide a threefold comparison of these methods with respect to spectral prediction and compound identification. We found that there is no unambiguous way to determine the best of these three methods. Among other factors, we find that the choice of spectral distance functions play an important role regarding the performance for compound identification.

Array-Based Machine Learning for Functional Group Detection in Electron Ionization Mass Spectrometry.

Mass spectrometry is a ubiquitous technique capable of complex chemical analysis. The fragmentation patterns that appear in mass spectrometry are an excellent target for artificial intelligence methods to automate and expedite the analysis of data to identify targets such as functional groups. To develop this approach, we trained models on electron ionization (a reproducible hard fragmentation technique) mass spectra so that not only the final model accuracies but also the reasoning behind model assignments could be evaluated. The convolutional neural network (CNN) models were trained on 2D images of the spectra using transfer learning of Inception V3, and the logistic regression models were trained using array-based data and Scikit Learn implementation in Python. Our training dataset consisted of 21,166 mass spectra from the United States' National Institute of Standards and Technology (NIST) Webbook. The data was used to train models to identify functional groups, both specific (e.g., amines, esters) and generalized classifications (aromatics, oxygen-containing functional groups, and nitrogen-containing functional groups). We found that the highest final accuracies on identifying new data were observed using logistic regression rather than transfer learning on CNN models. It was also determined that the mass range most beneficial for functional group analysis is 0-100 m/z. We also found success in correctly identifying functional groups of example molecules selected from both the NIST database and experimental data. Beyond functional group analysis, we also have developed a methodology to identify impactful fragments for the accurate detection of the models' targets. The results demonstrate a potential pathway for analyzing and screening substantial amounts of mass spectral data.

Ultra-fast and accurate electron ionization mass spectrum matching for compound identification with million-scale in-silico library

Spectrum matching is the most common method for compound identification in mass spectrometry (MS). However, some challenges limit its efficiency, including the coverage of spectral libraries, the accuracy, and the speed of matching. In this study, a million-scale in-silico EI-MS library is established. Furthermore, an ultra-fast and accurate spectrum matching (FastEI) method is proposed to substantially improve accuracy using Word2vec spectral embedding and boost the speed using the hierarchical navigable small-world graph (HNSW). It achieves 80.4% recall@10 accuracy (88.3% with 5 Da mass filter) with a speedup of two orders of magnitude compared with the weighted cosine similarity method (WCS). When FastEI is applied to identify the molecules beyond NIST 2017 library, it achieves 50% recall@1 accuracy. FastEI is packaged as a standalone and user-friendly software for common users with limited computational backgrounds. Overall, FastEI combined with a million-scale in-silico library facilitates compound identification as an accurate and ultra-fast tool.

Identifying reliable ions for the statistical differentiation of structurally similar fentanyl analogs.

Definitive identification of fentanyl analogs based on mass spectral comparison is challenging given the high degree of structural and, hence, spectral similarity. To address this, a statistical method was previously developed in which two electron-ionization (EI) mass spectra are compared using the unequal variance t-test. Normalized intensities of corresponding ions are compared, testing the null hypothesis (H0 ) that the difference in intensity is equal to zero. If H0 is accepted at all m/z values, the two spectra are statistically equivalent at the specified confidence level. If H0 is not accepted at any m/z value, then there is a significant difference in intensity at that m/z value between the two spectra. In this work, the statistical comparison method is applied to distinguish EI spectra of valeryl fentanyl, isovaleryl fentanyl, and pivaloyl fentanyl. Spectra of the three analogs were collected over a 9-month period and at different concentrations. At the 99.9% confidence level, the spectra of corresponding isomers were statistically associated. Spectra of different isomers were statistically distinct, and ions responsible for discrimination were identified in each comparison. To account for inherent instrument variations, discriminating ions for each pairwise comparison were ranked based on the magnitude of the calculated t-statistic (tcalc ) value. For a given comparison, ions with higher tcalc values are those with the greatest difference in intensity between the two spectra and, therefore, are considered more reliable for discrimination. Using these methods, objective discrimination among the spectra was achieved and ions considered most reliable for discrimination of these isomers were identified.

Expert Algorithm for Substance Identification Using Mass Spectrometry: Statistical Foundations in Unimolecular Reaction Rate Theory.

This study aims to resolve one of the longest-standing problems in mass spectrometry, which is how to accurately identify an organic substance from its mass spectrum when a spectrum of the suspected substance has not been analyzed contemporaneously on the same instrument. Part one of this two-part report describes how Rice-Ramsperger-Kassel-Marcus (RRKM) theory predicts that many branching ratios in replicate electron-ionization mass spectra will provide approximately linear correlations when analysis conditions change within or between instruments. Here, proof-of-concept general linear modeling is based on the 20 most abundant fragments in a database of 128 training spectra of cocaine collected over 6 months in an operational crime laboratory. The statistical validity of the approach is confirmed through both analysis of variance (ANOVA) of the regression models and assessment of the distributions of the residuals of the models. General linear modeling models typically explain more than 90% of the variance in normalized abundances. When the linear models from the training set are applied to 175 additional known positive cocaine spectra from more than 20 different laboratories, the linear models enabled ion abundances to be predicted with an accuracy of <2% relative to the base peak, even though the measured abundances vary by more than 30%. The same models were also applied to 716 known negative spectra, including the diastereomers of cocaine: allococaine, pseudococaine, and pseudoallococaine, and the residual errors were larger for the known negatives than for known positives. The second part of the manuscript describes how general linear regression modeling can serve as the basis for binary classification and reliable identification of cocaine from its diastereomers and all other known negatives.

Synthesis, experimental and molecular dynamics simulation of the ESI-CID spectrum of the nerve agent Novichok analog O-2-methoxyethyl N- [bis(dimethylamino)methylidene]-P-methylphosphonamidate

The comprehensive and accurate analysis of mass spectral data is critical for the unequivocal identification of environmental samples containing compounds short-listed by the Chemical Weapons Convention (CWC). In particular, experiments with nerve agents are limited by the high risks involved in their handling. Therefore, the possibility of studying fragmentation pathways by a theoretical approach is especially welcome. In this work, for the first time, O-2-methoxyethyl N- [bis(dimethylamino)methylidene]-P-methylphosphonamidate, an analog of the Novichok nerve agent A-242, was synthesized employing a one-pot microscale synthesis. Electron ionization (EI) and electrospray ionization (ESI) mass spectra (MS) were measured to provide data for CWC verification purposes. Considering that ESI-MS/MS is a powerful method for analyzing non-volatile, highly polar, and very water-soluble compounds, such as degradation products of nerve agents, we extensively investigated for the first time the ESI-(collision-induced dissociation) CID fragmentation pathways of the selected molecule. For this purpose, molecular dynamics simulations using the Quantum Chemical Mass Spectrometry (QCxMS) method employing the semiempirical electronic structure method GFN2-xTB were compared with Triple Quadrupole electrospray ionization (ESI) experimental spectra in positive ion mode. The base peak of the EI spectrum for this molecule was found to be m/z 151, which strongly suggests a McLafferty +1 (ML+1) rearrangement involving the 2-methoxyethyl moiety. The formation of ion the m/z 106 in the ESI-CID spectrum, according to the simulations, results from the rearrangement involving a transfer of one dimethylamino group to the phosphorus atom, a mechanism that would be difficult to identify without employing theoretical methods.

Extractive-liquid sampling electron ionization-mass spectrometry (E-LEI-MS): a new powerful combination for direct analysis

One of modern analytical chemistry main challenges is providing as fast as possible results in different application fields. In this view, real-time analysis techniques are experiencing ever-increasing success as they can provide data quickly, almost without sample preparation steps. Most of real-time approaches are based on direct mass spectrometry (DMS), a method of analyzing samples without the need for separation or pre-treatment steps. Instead, the sample is directly introduced into the mass spectrometer for analysis. In this context, ambient ionization mass spectrometry (AIMS) techniques are widely represented and successfully used. Extractive-liquid sampling electron ionization-mass spectrometry (E-LEI-MS) represents a different analytical strategy that allows coupling ambient sampling with electron ionization (EI), avoiding any sample preparation step and providing identification based on the comparison with the National Institute of Standards and Technology (NIST) library spectra. E-LEI-MS consists of a dispositive for solvent release and sampling at ambient conditions coupled with an EI source of a single quadrupole mass spectrometer. A micromanipulator allows fine (x,y,z) positioning of a sampling tip. MS can operate in scan or SIM modes depending on the application goals and requirements. Several preliminary successful results were already obtained due to the highly informative EI mass spectra generation. The system was applied to the analysis of active ingredients in pharmaceutical tablets, pesticides on fruit peel, a drug of abuse (cocaine) determination in banknotes, and analysis of unknown components on painting surfaces. Both forensic and artwork applications allowed determining the spatial distribution of the analytes. Here we present a proof-of-concept of E-LEI-MS for targeted/non-targeted analysis and semi-quantitative detection.

Mass-spectrometric study of substituted (β-hydroxy-, β-acetoxy)sulfides and -sulfones of 1,3-dioxepane series using electron ionization

The electron ionization mass spectra of substituted (β-hydroxy)sulfides, -sulfones, and their corresponding acetates of the 1,3-dioxepane series were studied. The main regularities in the pathways of fragmentation of their molecular ions were revealed. It was shown that during electron ionization, the main directions of decomposition of the studied compounds are due to the elimination of substituents in the 1,3-dioxepane ring. For 6-phenylthio-1,3-dioxepanes and 6-phenylsulfonyl-1,3-dioxepanes, the formation of ions associated with the breaking of C-S bonds with charge localization on the sulfur-containing fragment is observed.

Construction of a Mass Spectrum Library Containing Predicted Electron Ionization Mass Spectra Prepared Using a Machine Learning Model and the Development of an Efficient Search Method.

Electron ionization (EI) mass spectrum library searching is usually performed to identify a compound in gas chromatography/mass spectrometry. However, compounds whose EI mass spectra are registered in the library are still limited compared to the popular compound databases. This means that there are compounds that cannot be identified by conventional library searching but also may result in false positives. In this report, we report on the development of a machine learning model, which was trained using chemical formulae and EI mass spectra, that can predict the EI mass spectrum from the chemical structure. It allowed us to create a predicted EI mass spectrum database with predicted EI mass spectra for 100 million compounds in PubChem. We also propose a method for improving library searching time and accuracy that includes an extensive mass spectrum library.

Protocol for structure determination of unknowns by EI mass spectrometry. II. Diagnostic ions in one ring alicyclic, heterocyclic, and aromatic compounds

Electron ionization (EI) mass spectra of saturated carbocyclic hydrocarbons containing a single ring with three or more members are discussed followed by the examination of their unsaturated analogs, including aromatic hydrocarbons. Mass spectrometry characteristics of heterocyclic compounds for each cycle size with one, two, three, and more hetero-atoms in a ring are considered along with their mono- and polyunsaturated analogs. An effect of the (a) size of a cycle; (b) number, nature, and location of elements in a ring; (c) position and nature of ring substituents; and (d) nature and location of unsaturation on the dissociation is revealed. Characteristic dissociation directions of these compounds and diagnostically important ions in their spectra are identified. Basic dissociation rules for alicyclic, heterocyclic, and aromatic compounds under EI are established for further use in the analysis of complex chemicals containing these structural elements.

Proximity effects in the electron ionisation mass spectra of substituted cinnamamides.

The electron ionisation mass spectra of an extensive set of 53 ionised monosubstituted and disubstituted cinnamamides [XC6H4CH=CHCONH2, X = H, F, Cl, Br, I, CH3, CH3O, CF3, NO2, CH3CH2, (CH3)2CH and (CH3)3C; and XYC6H3CH=CHCONH2, X = Y = Cl; and X, Y = F, Cl or Br] are reported and discussed. Particular attention is paid to the significance of loss of the substituent, X, from the 2-position, via a rearrangement that is sometimes known as a proximity effect, which has been reported for a range of radical-cations, but is shown in this work to be especially important for ionised cinnamamides. When X is in the 2-position of the aromatic ring, [M - X]+ is formed to a far greater extent than [M - H]+; in contrast, when X is in the 3-position or 4-position, [M - H]+ is generally much more important than [M - X]+. Parallel trends are found in the spectra of XYC6H3CH=CHCONH2: the signal for [M - X]+ dominates that for [M - Y]+ when X is in the 2-position and Y in the 4-position or 5-position, irrespective of the nature of X and Y. Further insight is obtained by studying the competition between expulsion of X· and alternative fragmentations that may be described as simple cleavages. Loss of ·NH2 results in the formation of a substituted cinnamoyl cation, [XC6H4CH=CHCO]+ or [XYC6H3CH=CHCO]+; this process competes far less effectively with the proximity effect when X is in the 2-position than when it is in the 3-position or 4-position. Additional information has been obtained by investigating the competition between formation of [M - H]+ by the proximity effect and loss of CH3· by cleavage of a 4-alkyl group to give a benzylic cation, [R1R2CC6H4CH=CHCONH2]+ (R1, R2 = H, CH3).

Rapid Approximate Subset-Based Spectra Prediction for Electron Ionization-Mass Spectrometry.

Mass spectrometry is a vital tool in the analytical chemist's toolkit, commonly used to identify the presence of known compounds and elucidate unknown chemical structures. All of these applications rely on having previously measured spectra for known substances. Computational methods for predicting mass spectra from chemical structures can be used to augment existing spectral databases with predicted spectra from previously unmeasured molecules. In this paper, we present a method for prediction of electron ionization-mass spectra (EI-MS) of small molecules that combines physically plausible substructure enumeration and deep learning, which we term rapid approximate subset-based spectra prediction (RASSP). The first of our two models, FormulaNet, produces a probability distribution over chemical subformulae to achieve a state-of-the-art forward prediction accuracy of 92.9% weighted (Stein) dot product and database lookup recall (within top 10 ranked spectra) of 98.0% when evaluated against the NIST 2017 Mass Spectral Library. The second model, SubsetNet, produces a probability distribution over vertex subsets of the original molecule graph to achieve similar forward prediction accuracy and superior generalization in the high-resolution, low-data regime. Spectra predicted by our best model improve upon the previous state-of-the-art spectral database lookup error rate by a factor of 2.9×, reducing the lookup error (top 10) from 5.7 to 2.0%. Both models can train on and predict spectral data at arbitrary resolution. Source code and predicted EI-MS spectra for 73.2M small molecules from PubChem will be made freely accessible online.