Critical benchmarking of popular composite thermochemistry models and density functional approximations on a probabilistically pruned benchmark dataset of formation enthalpies

COMPAS-2: a dataset of cata-condensed hetero-polycyclic aromatic systems

Polycyclic aromatic systems are highly important to numerous applications, in particular to organic electronics and optoelectronics. High-throughput screening and generative models that can help to identify new molecules to advance these technologies require large amounts of high-quality data, which is expensive to generate. In this report, we present the largest freely available dataset of geometries and properties of cata-condensed poly(hetero)cyclic aromatic molecules calculated to date. Our dataset contains ~500k molecules comprising 11 types of aromatic and antiaromatic building blocks calculated at the GFN1-xTB level and is representative of a highly diverse chemical space. We detail the structure enumeration process and the methods used to provide various electronic properties (including HOMO-LUMO gap, adiabatic ionization potential, and adiabatic electron affinity). Additionally, we benchmark against a ~50k dataset calculated at the CAM-B3LYP-D3BJ/def2-SVP level and develop a fitting scheme to correct the xTB values to higher accuracy. These new datasets represent the second installment in the COMputational database of Polycyclic Aromatic Systems (COMPAS) Project.

Stereo-electronic factors influencing the stability of hydroperoxyalkyl radicals: transferability of chemical trends across hydrocarbons and ab initio methods

The hydroperoxyalkyl radicals (˙QOOH) are known to play a significant role in combustion and tropospheric processes, yet their direct spectroscopic detection remains challenging. In this study, we investigate molecular stereo-electronic effects influencing the kinetic and thermodynamic stability of a ˙QOOH along its formation path from the precursor, alkylperoxyl radical (ROO˙), and the depletion path resulting in the formation of cyclic ether + ˙OH. We focus on reactive intermediates encountered in the oxidation of acyclic hydrocarbon radicals: ethyl, isopropyl, isobutyl, tert-butyl, neopentyl, and their alicyclic counterparts: cyclohexyl, cyclohexenyl, and cyclohexadienyl. We report reaction energies and barriers calculated with the highly accurate method Weizmann-1 (W1) for the channels: ROO˙ ⇌ ˙QOOH, ROO˙ ⇌ alkene + ˙OOH, ˙QOOH ⇌ alkene + ˙OOH, and ˙QOOH ⇌ cyclic ether + ˙OH. Using W1 results as a reference, we have systematically benchmarked the accuracy of popular density functional theory (DFT), composite thermochemistry methods, and an explicitly correlated coupled-cluster method. We ascertain inductive, resonance, and steric effects on the overall stability of ˙QOOH and computationally investigate the possibility of forming more stable species. With new reactions as test cases, we probe the capacity of various ab initio methods to yield quantitative insights on the elementary steps of combustion.

Toward Chemical Accuracy in Predicting Enthalpies of Formation with General-Purpose Data-Driven Methods

Enthalpies of formation and reaction are important thermodynamic properties that have a crucial impact on the outcome of chemical transformations. Here we implement the calculation of enthalpies of formation with a general-purpose ANI-1ccx neural network atomistic potential. We demonstrate on a wide range of benchmark sets that both ANI-1ccx and our other general-purpose data-driven method AIQM1 approach the coveted chemical accuracy of 1 kcal/mol with the speed of semiempirical quantum mechanical methods (AIQM1) or faster (ANI-1ccx). It is remarkably achieved without specifically training the machine learning parts of ANI-1ccx or AIQM1 on formation enthalpies. Importantly, we show that these data-driven methods provide statistical means for uncertainty quantification of their predictions, which we use to detect and eliminate outliers and revise reference experimental data. Uncertainty quantification may also help in the systematic improvement of such data-driven methods.

The long road to calibrated prediction uncertainty in computational chemistry

Uncertainty quantification (UQ) in computational chemistry (CC) is still in its infancy. Very few CC methods are designed to provide a confidence level on their predictions, and most users still rely improperly on the mean absolute error as an accuracy metric. The development of reliable UQ methods is essential, notably for CC to be used confidently in industrial processes. A review of the CC-UQ literature shows that there is no common standard procedure to report or validate prediction uncertainty. I consider here analysis tools using concepts (calibration and sharpness) developed in meteorology and machine learning for the validation of probabilistic forecasters. These tools are adapted to CC-UQ and applied to datasets of prediction uncertainties provided by composite methods, Bayesian ensembles methods, and machine learning and a posteriori statistical methods.

Prognostic Value of Early Fluorodeoxyglucose-Positron Emission Tomography Response Imaging and Peripheral Immunologic Biomarkers: Substudy of a Phase II Trial of Risk-Adaptive Chemoradiation for Unresectable Non-Small Cell Lung Cancer

Purpose

We sought to examine the prognostic value of fluorodeoxyglucose-positron emission tomography (PET) imaging during chemoradiation for unresectable non-small cell lung cancer for survival and hypothesized that tumor PET response is correlated with peripheral T-cell function.

Methods and Materials

Forty-five patients with American Joint Committee on Cancer version 7 stage IIB-IIIB non-small cell lung cancer enrolled in a phase II trial and received platinum-doublet chemotherapy concurrent with 6 weeks of radiation (NCT02773238). Fluorodeoxyglucose-PET was performed before treatment start and after 24 Gy of radiation (week 3). PET response status was prospectively defined by multifactorial radiologic interpretation. PET responders received 60 Gy in 30 fractions, while nonresponders received concomitant boosts to 74 Gy in 30 fractions. Peripheral blood was drawn synchronously with PET imaging, from which germline DNA sequencing, T-cell receptor sequencing, and plasma cytokine analysis were performed.

Results

Median follow-up was 18.8 months, 1-year overall survival (OS) 82%, 1-year progression-free survival 53%, and 1-year locoregional control 88%. Higher midtreatment PET total lesion glycolysis was detrimental to OS (1 year 87% vs 63%, P < .001), progression-free survival (1 year 60% vs 26%, P = .044), and locoregional control (1 year 94% vs 65%, P = .012), even after adjustment for clinical/treatment factors. Twenty-nine of 45 patients (64%) were classified as PET responders based on a priori definition. Higher tumor programmed death-ligand 1 expression was correlated with response on PET (P = .017). Higher T-cell receptor richness and clone distribution slope were associated with improved OS (P = .018-0.035); clone distribution slope was correlated with PET response (P = .031).

Conclusions

Midchemoradiation PET imaging is prognostic for survival; PET response may be linked to tumor and peripheral T-cell biomarkers.

A Fragmentation-Based Graph Embedding Framework for QM/ML

We introduce a new fragmentation-based molecular representation framework "FragGraph" for QM/ML methods involving embedding fragment-wise fingerprints onto molecular graphs. Our model is specifically designed for delta machine learning (Δ-ML) with the central goal of correcting the deficiencies of approximate methods such as DFT to achieve high accuracy. Our framework is based on a judicious combination of ideas from fragmentation, error cancellation, and a state-of-the-art deep learning architecture. Broadly, we develop a general graph-network framework for molecular machine learning by incorporating the inherent advantages prebuilt into error cancellation methods such as the generalized Connectivity-Based Hierarchy. More specifically, we develop a QM/ML representation through a fragmentation-based attributed graph representation encoded with fragment-wise molecular fingerprints. The utility of our representation is demonstrated through a graph network fingerprint encoder in which a global fingerprint is generated through message passing of local neighborhoods of fragment-wise fingerprints, effectively augmenting standard fingerprints to also include the inbuilt molecular graph structure. On the 130k-GDB9 dataset, our method predicts an out-of-sample mean absolute error significantly lower than 1 kJ/mol compared to target G4(MP2) calculated energies, rivaling current deep learning methods with reduced computational scaling.