Digital discovery最新文献

Plastic pollution, particularly microplastics (MPs), poses a significant global threat to ecosystems and human health, necessitating innovative remediation strategies. Biocompatible and biodegradable plastic-binding peptides (PBPs) offer a potential solution through targeted adsorption and subsequent MP detection or removal from the environment. A challenge in discovering plastic-binding peptides is the vast combinatorial space of possible peptides (i.e., over 10¹⁵ for 12-mer peptides), which far exceeds the sample sizes typically reachable by experiments or biophysics-based computational methods. One step towards addressing this issue is to train deep learning models on experimental or biophysical datasets, permitting faster and cheaper evaluations of peptides. However, deep learning predictions are not always accurate, which could waste time and money due to synthesizing and evaluating false positives. Here, we resolve this issue by combining biophysical modeling data from Peptide Binder Design (PepBD) algorithm, the predictive power and uncertainty quantification of evidential deep learning, and metaheuristic search methods to identify high-affinity PBPs for several common plastics. Molecular dynamics simulations show that the discovered PBPs have greater median adsorption free energies for polyethylene (5%), polypropylene (18%), and polystyrene (34%) relative to PBPs previously designed by PepBD. The impact of including uncertainty quantification in peptide design is demonstrated by the increasing improvement in the median adsorption free energy with decreasing uncertainty. This robust framework accelerates peptide discovery, paving the way for effective, bio-inspired solutions to MP remediation.

Predicting reaction barriers for arbitrary configurations based on only a limited set of density functional theory (DFT) calculations would render the design of catalysts or the simulation of reactions within complex materials highly efficient. We here propose Gaussian process regression (GPR) as a method of choice if DFT calculations are limited to hundreds or thousands of barrier calculations. For the case of hydrogen atom transfer in proteins, an important reaction in chemistry and biology, we obtain a mean absolute error of 3.23 kcal mol^-1 for the range of barriers in the data set using SOAP descriptors and similar values using the marginalized graph kernel. Thus, the two GPR models can robustly estimate reaction barriers within the large chemical and conformational space of proteins. Their predictive power is comparable to a graph neural network-based model, and GPR even outcompetes the latter in the low data regime. We propose GPR as a valuable tool for an approximate but data-efficient model of chemical reactivity in a complex and highly variable environment.

FEgrow is an open-source software package for building congeneric series of compounds in protein binding pockets. For a given ligand core and receptor structure, it employs hybrid machine learning/molecular mechanics potential energy functions to optimise the bioactive conformers of supplied linkers and functional groups. Here, we introduce significant new functionality to automate, parallelise and accelerate the building and scoring of compound suggestions, such that it can be used for automated de novo design. We interface the workflow with active learning to improve the efficiency of searching the combinatorial space of possible linkers and functional groups, make use of interactions formed by crystallographic fragments in scoring compound designs, and introduce the option to seed the chemical space with molecules available from on-demand chemical libraries. As a test case, we target the main protease (Mpro) of SARS-CoV-2, identifying several small molecules with high similarity to molecules discovered by the COVID moonshot effort, using only structural information from a fragment screen in a fully automated fashion. Finally, we order and test 19 compound designs, of which three show weak activity in a fluorescence-based Mpro assay, but work is needed to further optimise the prioritisation of compounds for purchase. The FEgrow package and full tutorials demonstrating the active learning workflow are available at https://github.com/cole-group/FEgrow.

The analysis of nonadiabatic molecular dynamics (NAMD) data presents significant challenges due to its high dimensionality and complexity. To address these issues, we introduce ULaMDyn, a Python-based, open-source package designed to automate the unsupervised analysis of large datasets generated by NAMD simulations. ULaMDyn integrates seamlessly with the Newton-X platform and employs advanced dimensionality reduction and clustering techniques to uncover hidden patterns in molecular trajectories, enabling a more intuitive understanding of excited-state processes. Using the photochemical dynamics of fulvene as a test case, we demonstrate how ULaMDyn efficiently identifies critical molecular geometries and critical nonadiabatic transitions. The package offers a streamlined, scalable solution for interpreting large NAMD datasets. It is poised to facilitate advances in the study of excited-state dynamics across a wide range of molecular systems.

Automated chemistry platforms hold the potential to enable large-scale organic synthesis campaigns, such as producing a library of compounds for biological evaluation. The efficiency of such platforms will depend on the schedule according to which the synthesis operations are executed. In this work, we study the scheduling problem for chemical library synthesis, where operations from interdependent synthetic routes are scheduled to minimize the makespan-the total duration of the synthesis campaign. We formalize this problem as a flexible job-shop scheduling problem with chemistry-relevant constraints in the form of a mixed integer linear program (MILP), which we then solve in order to design an optimized schedule. The scheduler's ability to produce valid, optimal schedules is demonstrated by 720 simulated scheduling instances for realistically accessible chemical libraries. Reductions in makespan up to 58%, with an average reduction of 20%, are observed compared to the baseline scheduling approach.

Deep learning has significantly accelerated drug discovery, with 'chemical language' processing (CLP) emerging as a prominent approach. CLP approaches learn from molecular string representations (e.g., Simplified Molecular Input Line Entry Systems [SMILES] and Self-Referencing Embedded Strings [SELFIES]) with methods akin to natural language processing. Despite their growing importance, training predictive CLP models is far from trivial, as it involves many 'bells and whistles'. Here, we analyze the key elements of CLP and provide guidelines for newcomers and experts. Our study spans three neural network architectures, two string representations, three embedding strategies, across ten bioactivity datasets, for both classification and regression purposes. This 'hitchhiker's guide' not only underscores the importance of certain methodological decisions, but it also equips researchers with practical recommendations on ideal choices, e.g., in terms of neural network architectures, molecular representations, and hyperparameter optimization.

The field of photochemistry underpins broad scientific endeavors, encompasses diverse molecular substances, and incorporates descriptions of qualitative and quantitative properties, all of which together may be representative of many scientific disciplines. Yet finding absorption and fluorescence spectra along with companion values of the molar absorption coefficient (ε) and fluorescence quantum yield (Φ_f) for a given compound is an arduous task even with the most advanced search methods. To gauge whether chatbots could be used to reliably search the literature, the absorption and fluorescence spectra and quantitative parameters (ε and Φ_f) for 16 popular dyes and fluorophores were sought using ChatGPT 3.5, ChatGPT 4o, Microsoft Copilot, Google Gemini, Gemini advanced, and Meta AI. In most cases, the values of ε and Φ_f returned by the chatbots accurately cohered with known values from established resources, whereas the retrieval of spectra was only marginally successful. The chatbots were further challenged to find data for fictive compounds (e.g., rhodamine 7G). The results from each chatbot were categorized as follows: “fabricated” (provides numbers that do not exist in the context queried), “fooled” (mis-identifies the compound but does not return any data), “feigned” (acts as if the fictive compound is real but does not provide any data), or “faithful” (responds that the compound is not known or is not available). In summary, the present shortcomings should not cloud the view that chatbots – judiciously used – already provide a valuable resource for the challenging scientific task of finding granular data, and to lesser degree, spectral traces for known compounds.

High-entropy carbides (HECs) have garnered significant attention due to their unique mechanical properties. However, the design of novel HECs has been limited by extensive trial-and-error strategies, along with insufficient knowledge and computational capabilities. In this work, the intrinsic correlations between elements in the high-dimensional compositional space of HECs are investigated using high-throughput density functional theory calculations and two machine learning models, which enable us to predict the Young's modulus, hardness and wear resistance with only a chemical formula provided. Our models demonstrate a low root mean square error (11.5 GPa) and mean absolute error (9.0 GPa) in predicting the elastic modulus of HECs with arbitrary non-equimolar compositions. We further established a database of 566 370 HECs and identified 15 novel HECs with the best mechanical properties. Our models can rapidly explore the mechanical properties of HECs with descriptor–property correlation analysis, and hence provide an efficient method for accelerating the design of non-equimolar high-entropy materials with desired performance.

Zeolites, such as MFI, are versatile microporous aluminosilicate materials that are widely used in catalysis and adsorption processes. The location and the character of the aluminium within the zeolite framework is one of the important determinants of performance in industrial applications, and is typically probed by ²⁷Al NMR spectroscopy. However, interpretation of ²⁷Al NMR spectra is challenging, as first-principles computational modelling struggles to achieve the timescales and model complexity needed to provide reliable assignments. In this study, we deploy advanced machine learning-based methods to help bridge the time and model complexity scale by first utilizing neural network interatomic potentials to achieve significant speed-up in structure sampling compared to traditional density functional theory (DFT) approaches, and second by training regression models to cost-effectively predict the ²⁷Al chemical shifts. This allows us, for the H-MFI zeolite as a use case, to comprehensively explore the effect of various conditions relevant to catalysis, including water loading, temperature, and the aluminium concentration, on the ²⁷Al chemical shifts. We demonstrate that both water content and temperature significantly affect the chemical shift and do so in a non-trivial way that is highly T-site dependent, highlighting a need for adoption of realistic, case-specific models. We also observe that our approach is able to achieve close to quantitative agreement with relevant experimental data for such a complex zeolite as MFI, allowing for the tentative assignment of the experimental NMR peaks to specific T-sites. These findings provide a testament to the capabilities of machine learning approaches in providing reliable predictions of important spectroscopic observables for complex industrially relevant materials under realistic conditions.

Sampling high-coverage configurations and predicting adsorbate–adsorbate interactions on surfaces are highly relevant to understand realistic interfaces in heterogeneous catalysis. However, the combinatorial explosion in the number of adsorbate configurations among diverse site environments presents a considerable challenge in accurately estimating these interactions. Here, we propose a strategy combining high-throughput simulation pipelines and a neural network-based model with the MACE architecture to increase sampling efficiency and speed. By training the models on unrelaxed structures and energies, which can be quickly obtained from single-point DFT calculations, we achieve excellent performance for both in-domain and out-of-domain predictions, including generalization to different facets, coverage regimes and low-energy configurations. From this systematic understanding of model robustness, we exhaustively sample the configuration phase space of catalytic systems without active learning. In particular, by predicting binding energies for over 14 million structures within the neural network model and the simulated annealing method, we predict coverage-dependent adsorption energies for CO adsorption on six Cu facets (111, 100, 211, 331, 410 and 711) and the co-adsorption of CO and CHOH on Rh(111). When validated by targeted post-sampling relaxations, our results for CO on Cu correctly reproduce experimental interaction energies reported in the literature, and provide atomistic insights on the site occupancy of steps and terraces for the six facets at all coverage regimes. Additionally, the arrangement of CO on the Rh(111) surface is demonstrated to substantially impact the activation barriers for the CHOH bond scission, illustrating the importance of comprehensive sampling on reaction kinetics. Our findings demonstrate that simplified data generation routines and evaluating generalization of neural networks can be deployed at scale to understand lateral interactions on surfaces, paving the way towards realistic modeling of heterogeneous catalytic processes.