An official website of the United States government
Tandem mass spectrometry (MS/MS) is crucial for small-molecule analysis; however, traditional computational methods are limited by incomplete reference libraries and complex data processing. Machine learning (ML) is transforming small-molecule mass spectrometry in three key directions: (a) predicting MS/MS spectra and related physicochemical properties to expand reference libraries, (b) improving spectral matching through automated pattern extraction, and (c) predicting molecular structures of compounds directly from their MS/MS spectra. We review ML approaches for molecular representations [descriptors, simplified molecular-input line-entry (SMILE) strings, and graphs] and MS/MS spectra representations (using binned vectors and peak lists) along with recent advances in spectra prediction, retention time, collision cross sections, and spectral matching. Finally, we discuss ML-integrated workflows for chemical formula identification. By addressing the limitations of current methods for compound identification, these ML approaches can greatly enhance the understanding of biological processes and the development of diagnostic and therapeutic tools.
more »
« less
Improved vapor pressure predictions using group contribution-assisted graph convolutional neural networks (GC 2 NN)
Abstract. The vapor pressures (pvap) of organic molecules play a crucial role in the partitioning of secondary organic aerosol (SOA). Given the vast diversity of atmospheric organic compounds, experimentally determining pvap of each compound is unfeasible. Machine Learning (ML) algorithms allow the prediction of physicochemical properties based on complex representations of molecular structure, but their performance crucially depends on the availability of sufficient training data. We propose a novel approach to predict pvap using group contribution-assisted graph convolutional neural networks (GC2NN). The models use molecular descriptors like molar mass alongside molecular graphs containing atom and bond features as representations of molecular structure. The model's group contribution component is a shallow fully-connected neural network which processes numerical molecular descriptors and complements the model's graph component. Molecular graphs allow the ML model to better infer molecular connectivity compared to methods using other, non-structural embeddings. We achieve best results with an adaptive-depth GC2NN, where the number of evaluated graph layers depends on molecular size. We present two vapor pressure estimation models that achieve strong agreement between predicted and experimentally-determined pvap. The first is a general model with broad scope that is suitable for both organic and inorganic molecules and achieves a mean absolute error (MAE) of 0.69 log-units (R2= 0.86). The second model is specialized on organic compounds with functional groups often encountered in atmospheric SOA, achieving an even stronger correlation with the test data (MAE = 0.37 log-units, R2= 0.94). The adaptive-depth GC2NN models clearly outperform existing methods, including parameterizations and group-contribution methods, demonstrating that graph-based ML techniques are powerful tools for the estimation of physicochemical properties, even when experimental data are scarce.
more »
« less
- Award ID(s):
- 2246502
- PAR ID:
- 10679580
- Publisher / Repository:
- Copernicus
- Date Published:
- Journal Name:
- Geoscientific Model Development
- Volume:
- 18
- Issue:
- 20
- ISSN:
- 1991-9603
- Page Range / eLocation ID:
- 7357 to 7371
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Gas-particle partitioning of secondary organic aerosols is impacted by particle phase state and viscosity, which can be inferred from the glass transition temperature ( T g ) of the constituting organic compounds. Several parametrizations were developed to predict T g of organic compounds based on molecular properties and elemental composition, but they are subject to relatively large uncertainties as they do not account for molecular structure and functionality. Here we develop a new T g prediction method powered by machine learning and “molecular embeddings”, which are unique numerical representations of chemical compounds that retain information on their structure, inter atomic connectivity and functionality. We have trained multiple state-of-the-art machine learning models on databases of experimental T g of organic compounds and their corresponding molecular embeddings. The best prediction model is the tgBoost model built with an Extreme Gradient Boosting (XGBoost) regressor trained via a nested cross-validation method, reproducing experimental data very well with a mean absolute error of 18.3 K. It can also quantify the influence of number and location of functional groups on the T g of organic molecules, while accounting for atom connectivity and predicting different T g for compositional isomers. The tgBoost model suggests the following trend for sensitivity of T g to functional group addition: –COOH (carboxylic acid) > –C(O)OR (ester) ≈ –OH (alcohol) > –C(O)R (ketone) ≈ –COR (ether) ≈ –C(O)H (aldehyde). We also developed a model to predict the melting point ( T m ) of organic compounds by training a deep neural network on a large dataset of experimental T m . The model performs reasonably well against the available dataset with a mean absolute error of 31.0 K. These new machine learning powered models can be applied to field and laboratory measurements as well as atmospheric aerosol models to predict the T g and T m of SOA compounds for evaluation of the phase state and viscosity of SOA.more » « less
-
Heterogeneous hydroxyl radical (•OH) oxidation is an important aging process for isoprene epoxydiol-derived secondary organic aerosol (IEPOX-SOA) that alters its chemical composition. It was recently demonstrated that heterogeneous •OH oxidation can age single-component particulate methyltetrol sulfates (MTSs), causing ∼55% of the SOA mass loss. However, our most recent study of freshly generated IEPOX-SOA particulate mixtures suggests that the lifetime of the complete IEPOX-SOA mixture against heterogeneous •OH oxidation can be prolonged through the fragmentation of higher-order oligomers. Published studies suggest that the heterogeneous •OH oxidation of IEPOX SOA could affect the organic atmospheric aerosol budget at varying rates, depending on aerosol chemical composition. However, heterogeneous •OH oxidation kinetics for the full IEPOX-SOA particulate mixture have not been reported. Here, we exposed freshly generated IEPOX-SOA particles to heterogeneous oxidation by •OH under humid conditions (relative humidity ∼57%) for 0−15 atmospheric-equivalent days of aging and derived an effective heterogeneous •OH rate coefficient (kOH) of 2.64 ± 0.4 × 10−13 cm^3 molecules−1 s−1. While ∼44% of particulate organic mass of nonoxidized IEPOX-SOA was consumed over the entire 15 day aging period, only <7% was consumed during the initial 10 aging days. By molecular-level chemical analysis, we determined oligomers were consumed at a faster rate (by a factor of 2−4) than monomers. Analysis of aerosol physicochemical properties shows that IEPOX-SOA has a core−shell morphology, and the shell becomes thinner with •OH oxidation. In summary, this study demonstrates that heterogeneous •OH oxidation of IEPOX-SOA particles is a dynamic process in which aerosol chemical composition and physicochemical properties play important roles.more » « less
-
Predicting molecular self-diffusion coefficients (D*) across chemical space remains challenging due to sparse experimental data and the high computational cost of molecular simulations. We present a data-centric machine learning framework that integrates experimental diffusion measurements with molecular dynamics simulations through a semisupervised distillation strategy. Unlike conventional approaches that treat limited experiments or simulations as direct ground truth, our method selectively incorporates simulation-derived D* only when they align with the uncertainty bounds of a Random Forest model initially trained on experimental D*. This enables controlled data set expansion, from 130 unique experimentally measured molecules to over 1,000 unique substances, while preserving label reliability. We further employ pretrained large language model embeddings to encode transferable chemical context beyond conventional descriptors, reducing predictive variance and improving generalization across chemically diverse systems. The resulting model achieves improved accuracy, with a held-out test set R2 of 0.87, an overall R2 of 0.92, and a test set mean absolute error of 0.13 × 10–9 m2 s–1 after iterative distillation across more than 1,000 chemically diverse molecules under near-ambient conditions (295–300 K). We further demonstrate that learned D* act as transferable, physically interpretable descriptors in skin permeability modeling, where their inclusion reduces test set error and improves correlation relative to models relying solely on conventional physicochemical descriptors. This work establishes a scalable framework for bridging sparse experimental measurements with broadly generalizable predictions, enabling interpretable and transferable modeling across distinct molecular transport phenomena.more » « less
-
Laboratory chambers, invaluable in atmospheric chemistry and aerosol formation studies, are subject to particle and vapor wall deposition, processes that need to be accounted for in order to accurately determine secondary organic aerosol (SOA) mass yields. Although particle wall deposition is reasonably well understood and usually accounted for, vapor wall deposition is less so. The effects of vapor wall deposition on SOA mass yields in chamber experiments can be constrained experimentally by increasing the seed aerosol surface area to promote the preferential condensation of SOA-forming vapors onto seed aerosol. Here, we study the influence of seed aerosol surface area and oxidation rate on SOA formation in α-pinene ozonolysis. The observations are analyzed using a coupled vapor–particle dynamics model to interpret the roles of gas–particle partitioning (quasi-equilibrium vs. kinetically limited SOA growth) and α-pinene oxidation rate in influencing vapor wall deposition. We find that the SOA growth rate and mass yields are independent of seed surface area within the range of seed surface area concentrations used in this study. This behavior arises when the condensation of SOA-forming vapors is dominated by quasi-equilibrium growth. Faster α-pinene oxidation rates and higher SOA mass yields are observed at increasing O3 concentrations for the same initial α-pinene concentration. When the α-pinene oxidation rate increases relative to vapor wall deposition, rapidly produced SOA-forming oxidation products condense more readily onto seed aerosol particles, resulting in higher SOA mass yields. Our results indicate that the extent to which vapor wall deposition affects SOA mass yields depends on the particular volatility organic compound system and can be mitigated through the use of excess oxidant concentrations.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.5194/gmd-18-7357-2025
