Machine Learning Enables Highly Accurate Predictions of Photophysical Properties of Organic Fluorescent Materials: Emission Wavelengths and Quantum Yields

Predicting Serotonin Detection with DNA-Carbon Nanotube Sensors across Multiple Spectral Wavelengths

Owing to the value of DNA-wrapped single-walled carbon nanotube (SWNT)-based sensors for chemically specific imaging in biology, we explore machine learning (ML) predictions DNA-SWNT serotonin sensor responsivity as a function of DNA sequence based on the whole SWNT fluorescence spectra. Our analysis reveals the crucial role of DNA sequence in the binding modes of DNA-SWNTs to serotonin, with a smaller influence of SWNT chirality. Regression ML models trained on existing data sets predict the change in the fluorescence emission in response to serotonin, ΔF/F, at over a hundred wavelengths for new DNA-SWNT conjugates, successfully identifying some high- and low-response DNA sequences. Despite successful predictions, we also show that the finite size of the training data set leads to limitations on prediction accuracy. Nevertheless, incorporating entire spectra into ML models enhances prediction robustness and facilitates the discovery of novel DNA-SWNT sensors. Our approaches show promise for identifying new chemical systems with specific sensing response characteristics, marking a valuable advancement in DNA-based system discovery.

Machine-Learning-Assisted Rational Design of Si─Rhodamine as Cathepsin-pH-Activated Probe for Accurate Fluorescence Navigation

High-performance fluorescent probes stand as indispensable tools in fluorescence-guided imaging, and are crucial for precise delineation of focal tissue while minimizing unnecessary removal of healthy tissue. Herein, machine-learning-assisted strategy to investigate the current available xanthene dyes is first proposed, and a quantitative prediction model to guide the rational synthesis of novel fluorescent molecules with the desired pH responsivity is constructed. Two novel Si─rhodamine derivatives are successfully achieved and the cathepsin/pH sequentially activated probe Si─rhodamine─cathepsin-pH (SiR─CTS-pH) is constructed. The results reveal that SiR─CTS-pH exhibits higher signal-to-noise ratio of fluorescence imaging, compared to single pH or cathepsin-activated probe. Moreover, SiR─CTS-pH shows strong differentiation abilities for tumor cells and tissues and accurately discriminates the complex hepatocellular carcinoma tissues from normal ones, indicating its significant application potential in clinical practice. Therefore, the continuous development of xanthene dyes and the rational design of superior fluorescent molecules through machine-learning-assisted model broaden the path and provide more advanced methods to researchers.

Predicting Emission Spectra of Heteroleptic Iridium Complexes Using Artificial Chemical Intelligence

We report a deep learning-based approach to accurately predict the emission spectra of phosphorescent heteroleptic [Ir(C ∧ N ${{\rm{C}}^\wedge {\rm{N}}}$ )2(N ∧ N ${{\rm{N}}^\wedge {\rm{N}}}$ )]+ complexes, enabling the rapid discovery of novel Ir(III) chromophores for diverse applications including organic light-emitting diodes and solar fuel cells. The deep learning models utilize graph neural networks and other chemical features in architectures that reflect the inherent structure of the heteroleptic complexes, composed ofC ∧ N ${{\rm{C}}^\wedge {\rm{N}}}$ andN ∧ N ${{\rm{N}}^\wedge {\rm{N}}}$ ligands, and are thus geared towards efficient training over the dataset. By leveraging experimental emission data, our models reliably predict the full emission spectra of these complexes across various emission profiles, surpassing the accuracy of conventional DFT and correlated wavefunction methods, while simultaneously achieving robustness to the presence of imperfect (noisy, low-quality) training spectra. We showcase the potential applications for these and related models for in silico prediction of complexes with tailored emission properties, as well as in "design of experiment" contexts to reduce the synthetic burden of high-throughput screening. In the latter case, we demonstrate that the models allow us to exploit a limited amount of experimental data to explore a wide range of chemical space, thus leveraging a modest synthetic effort.

Machine Learning Prediction of Quantum Yields and Wavelengths of Aggregation-Induced Emission Molecules

The aggregation-induced emission (AIE) effect exhibits a significant influence on the development of luminescent materials and has made remarkable progress over the past decades. The advancement of high-performance AIE materials requires fast and accurate predictions of their photophysical properties, which is impeded by the inherent limitations of quantum chemical calculations. In this work, we present an accurate machine learning approach for the fast predictions of quantum yields and wavelengths to screen out AIE molecules. A database of about 563 organic luminescent molecules with quantum yields and wavelengths in the monomeric/aggregated states was established. Individual/combined molecular fingerprints were selected and compared elaborately to attain appropriate molecular descriptors. Different machine learning algorithms combined with favorable molecular fingerprints were further screened to achieve more accurate prediction models. The simulation results indicate that combined molecular fingerprints yield more accurate predictions in the aggregated states, and random forest and gradient boosting regression algorithms show the best predictions in quantum yields and wavelengths, respectively. Given the successful applications of machine learning in quantum yields and wavelengths, it is reasonable to anticipate that machine learning can serve as a complementary strategy to traditional experimental/theoretical methods in the investigation of aggregation-induced luminescent molecules to facilitate the discovery of luminescent materials.

Ground-State Orbital Descriptors for Accelerated Development of Organic Room-Temperature Phosphorescent Materials

Organic materials with room-temperature phosphorescence (RTP) are in high demand for optoelectronics and bioelectronics. Developing RTP materials highly relies on expert experience and costly excited-state calculations. It is a challenge to find a tool for effectively screening RTP materials. Herein we first establish ground-state orbital descriptors (πFMOs ) derived from the π-electron component of the frontier molecular orbitals to characterize the RTP lifetime (τp ), achieving a balance in screening efficiency and accuracy. Using the πFMOs , a data-driven machine learning model gains a high accuracy in classifying long τp , filtering out 836 candidates with long-lived RTP from a virtual library of 19,295 molecules. With the aid of the excited-state calculations, 287 compounds are predicted with high RTP efficiency. Impressively, experiments further confirm the reliability of this workflow, opening a novel avenue for designing high-performance RTP materials for potential applications.

Automatic Prediction of Peak Optical Absorption Wavelengths in Molecules Using Convolutional Neural Networks

Molecular design depends heavily on optical properties for applications such as solar cells and polymer-based batteries. Accurate prediction of these properties is essential, and multiple predictive methods exist, from ab initio to data-driven techniques. Although theoretical methods, such as time-dependent density functional theory (TD-DFT) calculations, have well-established physical relevance and are among the most popular methods in computational physics and chemistry, they exhibit errors that are inherent in their approximate nature. These high-throughput electronic structure calculations also incur a substantial computational cost. With the emergence of big-data initiatives, cost-effective, data-driven methods have gained traction, although their usability is highly contingent on the degree of data quality and sparsity. In this study, we present a workflow that employs deep residual convolutional neural networks (DR-CNN) and gradient boosting feature selection to predict peak optical absorption wavelengths (λmax) exclusively from SMILES representations of dye molecules and solvents; one would normally measure λmax using UV-vis absorption spectroscopy. We use a multifidelity modeling approach, integrating 34,893 DFT calculations and 26,395 experimentally derived λmax data, to deliver more accurate predictions via a Bayesian-optimized gradient boosting machine. Our approach is benchmarked against the state of the art that is reported in the scientific literature; results demonstrate that learnt representations via a DR-CNN workflow that is integrated with other machine learning methods can accelerate the design of molecules for specific optical characteristics.

Optimized Machine learning techniques Enable prediction of organic dyes photophysical Properties: Absorption Wavelengths, emission Wavelengths, and quantum yields

Applications of organic dyes, ranging from basic research to industry, are functions of their photophysical properties. Two important aspects- (1) knowledge of the photophysical properties of existing dyes long before real applications and (2) discovery of new organic dyes with desired photophysical properties for either upgradation of existing or development of new applications-are needed to be addressed. These two cases are coupled together with the common goal of estimating photophysical properties with high accuracy at the minimum cost of time and money long before the hard-core laboratory experiment. For this purpose, machine learning-based techniques are the most suitable approach. In this study, we used optimized machine-learning techniques to assess a dataset of 3066 organic dyes, which were evaluated using three evaluation parameters: Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R2). The Quadratic Support Vector Machine (QSVM) was the best predictive model for RMSE-16.614, MAE-10.837, and R2-0.961 for absorption wavelengths and RMSE-23.636, MAE-16.278, and R2-0.929 for emission wavelengths. These R2 values are 0.7% and 0.4% greater than the Gradient Boost Regression Tree (GBRT) model's recently reported values of 0.954 and 0.925 for absorption and emission wavelengths, respectively. Furthermore, we estimated the quantum yield and found that the Coarse Gaussian Support Vector Machine (CGSVM) outperformed all examined models. For more validation of these models, we compared the predicted results with the experimental results of selective dyes. The proposed automated approach can be used for predicting photophysical properties without much computer programming knowledge.

Accurate Electronic and Optical Properties of Organic Doublet Radicals Using Machine Learned Range-Separated Functionals

Luminescent organic semiconducting doublet-spin radicals are unique and emergent optical materials because their fluorescent quantum yields (Φfl) are not compromised by the spin-flipping intersystem crossing (ISC) into a dark high-spin state. The multiconfigurational nature of these radicals challenges their electronic structure calculations in the framework of single-reference density functional theory (DFT) and introduces room for method improvement. In the present study, we extended our earlier development of ML-ωPBE [J. Phys. Chem. Lett., 2021, 12, 9516-9524], a range-separated hybrid (RSH) exchange-correlation (XC) functional constructed using the stacked ensemble machine learning (SEML) algorithm, from closed-shell organic semiconducting molecules to doublet-spin organic semiconducting radicals. We assessed its performance for a new test set of 64 doublet-spin radicals from five categories while placing all previously compiled 3926 closed-shell molecules in the new training set. Interestingly, ML-ωPBE agrees with the nonempirical OT-ωPBE functional regarding the prediction of the molecule-dependent range-separation parameter (ω), with a small mean absolute error (MAE) of 0.0197 a0-1, but saves the computational cost by 2.46 orders of magnitude. This result demonstrates an outstanding domain adaptation capacity of ML-ωPBE for diverse organic semiconducting species. To further assess the predictive power of ML-ωPBE in experimental observables, we also applied it to evaluate absorption and fluorescence energies (Eabs and Efl) using linear-response time-dependent DFT (TDDFT), and we compared its behavior with nine popular XC functionals. For most radicals, ML-ωPBE reproduces experimental measurements of Eabs and Efl with small MAEs of 0.299 and 0.254 eV, only marginally different from those of OT-ωPBE. Our work illustrates a successful extension of the SEML framework from closed-shell molecules to doublet-spin radicals and will open the venue for calculating optical properties for organic semiconductors using single-reference TDDFT.

Understanding the effects of sulfur di-oxidation and side chain engineering on absorption and fluorescence of oligothiophene: A theoretical study

Oligothiophene and its derivatives have broad applications in organic electronics because of its stability, easy functionalization, and broad color adjustability, and excellent charge carrier mobility. However, the effects of sulfur di-oxidation and side alkyl chains on the absorption and fluorescence of oligothiophene are still not well understood. In this article, we have applied density functional theory (DFT) and time-dependent DFT (TDDFT) to study a series of quinquethiophene compounds functionalized with S,S-dioxide and side alkyl chains, which were experimentally synthesized. Through benchmark calculations, we have found a reliable computational method, and successfully reproduced experimental UV-Vis absorption and fluorescence emission spectra well. Furthermore, the calculated reorganization energy of these molecules could explain the energy differences between absorption and emission spectra. Last but not lease, we also have calculated the fluorescence quantum yield efficiency (Фfl) of two compounds with good planarity in this series, and the trend of calculated values is consistent with experiment. Our work gives an insight to the effects of sulfur di-oxidation and side chain engineering on absorption and fluorescence of oligothiophene.

Perspectives on development of optoelectronic materials in artificial intelligence age

Optoelectronic devices, such as light-emitting diodes, have been demonstrated as one of the most demanded forthcoming display and lighting technologies because of their low cost, low power consumption, high brightness, and high contrast. The improvement of device performance relies on advances in precisely designing novelty functional materials, including light-emitting materials, hosts, hole/electron transport materials, and yet which is a time-consuming, laborious and resource-intensive task. Recently, machine learning (ML) has shown great prospects to accelerate material discovery and property enhancement. This review will summarize the workflow of ML in optoelectronic materials discovery, including data collection, feature engineering, model selection, model evaluation and model application. We highlight multiple recent applications of machine-learned potentials in various optoelectronic functional materials, ranging from semiconductor quantum dots (QDs) or perovskite QDs, organic molecules to carbon-based nanomaterials. We furthermore discuss the current challenges to fully realize the potential of ML-assisted materials design for optoelectronics applications. It is anticipated that this review will provide critical insights to inspire new exciting discoveries on ML-guided of high-performance optoelectronic devices with a combined effort from different disciplines.

Artificial Intelligence for Surface-Enhanced Raman Spectroscopy

Surface-enhanced Raman spectroscopy (SERS), well acknowledged as a fingerprinting and sensitive analytical technique, has exerted high applicational value in a broad range of fields including biomedicine, environmental protection, food safety among the others. In the endless pursuit of ever-sensitive, robust, and comprehensive sensing and imaging, advancements keep emerging in the whole pipeline of SERS, from the design of SERS substrates and reporter molecules, synthetic route planning, instrument refinement, to data preprocessing and analysis methods. Artificial intelligence (AI), which is created to imitate and eventually exceed human behaviors, has exhibited its power in learning high-level representations and recognizing complicated patterns with exceptional automaticity. Therefore, facing up with the intertwining influential factors and explosive data size, AI has been increasingly leveraged in all the above-mentioned aspects in SERS, presenting elite efficiency in accelerating systematic optimization and deepening understanding about the fundamental physics and spectral data, which far transcends human labors and conventional computations. In this review, the recent progresses in SERS are summarized through the integration of AI, and new insights of the challenges and perspectives are provided in aim to better gear SERS toward the fast track.

Modeling the Fluorescence Quantum Yields of Aromatic Compounds: Benchmarking the Machinery to Compute Intersystem Crossing Rates

The from-first-principles calculation of fluorescence quantum yields (FQYs) and lifetimes of organic dyes remains very challenging. In this article, we extensively test the machinery to calculate FQYs. Specifically, we perform an extensive analysis on the parameters influencing the intersystem crossing (ISC), internal conversion (IC), and fluorescence rate constants calculations. The impact of (i) the electronic structure (chosen exchange-correlation functional and spin-orbit Hamiltonian), (ii) the vibronic parameters (coordinate system, broadening function, and dipole expansion), and (iii) the excited-state kinetic models are systematically assessed for a series of seven rigid aromatic molecules. Our studies provide more insights into the choice of parameters and the expected accuracy for the computational protocols aiming to deliver FQY values. Some challenges are highlighted, such as, on the one hand, the difficulty to benchmark against the experimental nonradiative rate constants, for which the separation between the IC and ISC contributions is often not provided in the literature and, on the other hand, the need to go beyond the harmonic approximation for the calculation of the IC rates.

Autonomous, multiproperty-driven molecular discovery: From predictions to measurements and back

A closed-loop, autonomous molecular discovery platform driven by integrated machine learning tools was developed to accelerate the design of molecules with desired properties. We demonstrated two case studies on dye-like molecules, targeting absorption wavelength, lipophilicity, and photooxidative stability. In the first study, the platform experimentally realized 294 unreported molecules across three automatic iterations of molecular design-make-test-analyze cycles while exploring the structure-function space of four rarely reported scaffolds. In each iteration, the property prediction models that guided exploration learned the structure-property space of diverse scaffold derivatives, which were realized with multistep syntheses and a variety of reactions. The second study exploited property models trained on the explored chemical space and previously reported molecules to discover nine top-performing molecules within a lightly explored structure-property space.

First-Principles Calculations of Excited-State Decay Rate Constants in Organic Fluorophores

In this Perspective, we discuss recent advances made to evaluate from first-principles the excited-state decay rate constants of organic fluorophores, focusing on the so-called static strategy. In this strategy, one essentially takes advantage of Fermi's golden rule (FGR) to evaluate rate constants at key points of the potential energy surfaces, a procedure that can be refined in a variety of ways. In this way, the radiative rate constant can be straightforwardly obtained by integrating the fluorescence line shape, itself determined from vibronic calculations. Likewise, FGR allows for a consistent calculation of the internal conversion (related to the non-adiabatic couplings) in the weak-coupling regime and intersystem crossing rates, therefore giving access to estimates of the emission yields when no complex photophysical phenomenon is at play. Beyond outlining the underlying theories, we summarize here the results of benchmarks performed for various types of rates, highlighting that both the quality of the vibronic calculations and the accuracy of the relative energies are crucial to reaching semiquantitative estimates. Finally, we illustrate the successes and challenges in determining the fluorescence quantum yields using a series of organic fluorophores.

Ground-State Orbital Analysis Predicts S1 Charge Transfer in Donor-Acceptor Materials

Donor-acceptor (D-A) materials can exhibit a wide range of unique photophysical properties with applications in next-generation optoelectronics. Electronic structure calculations of D-A dimers are often employed to predict the properties of D-A materials. One of the most important D-A dimer quantities is the degree of charge transfer (DCT) in the S1 state, which correlates with properties such as fluorescence lifetimes and intersystem crossing rates in D-A materials. While predictive metrics of the S1 DCT generally require an excited-state quantum chemistry calculation, presented here is a novel metric that predicts S1 DCT solely with ground-state orbital analysis. This metric quantifies the similarity of the orbitals between a dimer complex and its monomer components. A linear relationship is found between this similarity metric and the S1 DCT, calculated using a data set of 31 D-A dimers. Best practices for integrating this novel orbital structure-function relationship into high-throughput screening methods are discussed.

Evolution of organic phosphor through precision regulation of nonradiative decay

Development of single-component organic phosphor attracts increasing interest due to its wide applications in optoelectronic technologies. Theoretically, activating efficient intersystem crossing (ISC) via 1(π, π*) to 3(π, π*) transitions, rather than 1(n, π*) → 3(π, π*) transitions, is an alternative access to purely organic phosphors but remains challenging. Herein, we designed and successfully synthesized the sila-8-membered ring fused biaryl benzoskeleton by transition metal catalysis, which served as a new organic phosphor with efficient 1(π, π*) to 3(π, π*) ISC. We first found that such a compound exhibits a record-long phosphorescence lifetime of 6.5 s at low temperature for single-component organic systems. Then, we developed two strategies to tune their decay channels to evolve such nonemissive molecules into bright phosphors with elongated lifetimes at room temperature: 1) Physic-based design, where quantitative analyses of electron-phonon coupling led us to reveal and hinder the major nonradiative channels, thus lighted up room temperature phosphorescence (RTP) with a lifetime of 480 ms at 298 K; 2) chemical geometry-driven molecular engineering, where a geometry-based descriptor ΔΘT1-S0/ΘS0 was developed for rational screening RTP candidates and further improved the RTP lifetime to 794 ms. This study clearly shows the power of interdiscipline among synthetic methodology, physics-based rational design, and computational modeling, which represents a paradigm for the development of an organic emitter.

Extensive Analysis of the Parameters Influencing Radiative Rates Obtained through Vibronic Calculations

Defining a theoretical model systematically delivering accurate ab initio predictions of the fluorescence quantum yields of organic dyes is highly desirable for designing improved fluorophores in a systematic rather than trial-and-error way. To this end, the first required step is to obtain reliable radiative rates (kr), as low kr typically precludes effective emission. In the present contribution, using a series of 10 substituted phenyls with known experimental kr, we analyze the impact of the computational protocol on the kr determined through the thermal vibration correlation function (TVCF) approach on the basis of time-dependent density functional theory (TD-DFT) calculations of the energies, structures, and vibrational parameters. Both the electronic structure (selected exchange-correlation functional, application or not of the Tamm-Dancoff approximation) and the vibronic parameters (line-shape formalism, coordinate system, potential energy surface model, and dipole expansion) are tackled. Considering all possible combinations yields more than 3500 cases, allowing to extract statistically-relevant information regarding the impact of each computational parameter on the magnitude of the estimated kr. It turns out that the selected vibronic model can have a significant impact on the computed kr, especially the potential energy surface model. This effect is of the same order of magnitude as the difference noted between B3LYP and CAM-B3LYP estimates. For the treated compounds, all evaluated functionals do deliver reasonable trends, fitting the experimental values.

Two excited-state datasets for quantum chemical UV-vis spectra of organic molecules

We present two open-source datasets that provide time-dependent density-functional tight-binding (TD-DFTB) electronic excitation spectra of organic molecules. These datasets represent predictions of UV-vis absorption spectra performed on optimized geometries of the molecules in their electronic ground state. The GDB-9-Ex dataset contains a subset of 96,766 organic molecules from the original open-source GDB-9 dataset. The ORNL_AISD-Ex dataset consists of 10,502,904 organic molecules that contain between 5 and 71 non-hydrogen atoms. The data reveals the close correlation between the magnitude of the gaps between the highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO), and the excitation energy of the lowest singlet excited state energies quantitatively. The chemical variability of the large number of molecules was examined with a topological fingerprint estimation based on extended-connectivity fingerprints (ECFPs) followed by uniform manifold approximation and projection (UMAP) for dimension reduction. Both datasets were generated using the DFTB+ software on the "Andes" cluster of the Oak Ridge Leadership Computing Facility (OLCF).

Accurate prediction of global-density-dependent range-separation parameters based on machine learning

In this work, we develop an accurate and efficient XGBoost machine learning model for predicting the global-density-dependent range-separation parameter, ωGDD, for long-range corrected functional (LRC)-ωPBE. This ωGDDML model has been built using a wide range of systems (11 466 complexes, ten different elements, and up to 139 heavy atoms) with fingerprints for the local atomic environment and histograms of distances for the long-range atomic correlation for mapping the quantum mechanical range-separation values. The promising performance on the testing set with 7046 complexes shows a mean absolute error of 0.001 117 a0-1 and only five systems (0.07%) with an absolute error larger than 0.01 a0-1, which indicates the good transferability of our ωGDDML model. In addition, the only required input to obtain ωGDDML is the Cartesian coordinates without electronic structure calculations, thereby enabling rapid predictions. LRC-ωPBE(ωGDDML) is used to predict polarizabilities for a series of oligomers, where polarizabilities are sensitive to the asymptotic density decay and are crucial in a variety of applications, including the calculations of dispersion corrections and refractive index, and surpasses the performance of all other popular density functionals except for the non-tuned LRC-ωPBE. Finally, LRC-ωPBE (ωGDDML) combined with (extended) symmetry-adapted perturbation theory is used in calculating noncovalent interactions to further show that the traditional ab initio system-specific tuning procedure can be bypassed. The present study not only provides an accurate and efficient way to determine the range-separation parameter for LRC-ωPBE but also shows the synergistic benefits of fusing the power of physically inspired density functional LRC-ωPBE and the data-driven ωGDDML model.

Enhanced Predictions for the Experimental Photophysical Data Using the Featurized Schnet-Bondstep Approach

An assessment of modifying the SchNET model for the predictions of experimental molecular photophysical properties, including absorption energy (ΔE_abs), emission energy (ΔE_emi), and photoluminescence quantum yield (PLQY), was reported. The solution environment was properly introduced outside the interaction layers of SchNET for not overly amplifying the solute-solvent interactions, particularly being supported by the changes of prediction errors between the presence and absence of the solvent effect. Two featurization schemes under the framework of the Schnet-bondstep approach, with featuring the concepts of reduced-atomic-number and reduced-atomic-neighbor, were demonstrated. These featurized models can consequently provide fine predictions for ΔE_abs and ΔE_emi with errors less than 0.1 eV. The corresponding predictions of PLQY were shown to be comparable to the previous graph convolution network model.

Machine Learning Spectroscopy Using a 2-Stage, Generalized Constituent Contribution Protocol

A corrected group contribution (CGC)-molecule contribution (MC)-Bayesian neural network (BNN) protocol for accurate prediction of absorption spectra is presented. Upon combination of BNN with CGC methods, the full absorption spectra of various molecules are afforded accurately and efficiently-by using only a small dataset for training. Here, with a small training sample (<100), accurate prediction of maximum wavelength for single molecules is afforded with the first stage of the protocol; by contrast, previously reported machine learning (ML) methods require >1,000 samples to ensure the accuracy of prediction. Furthermore, with <500 samples, the mean square error in the prediction of full ultraviolet spectra reaches <2%; for comparison, ML models with molecular SMILES for training require a much larger dataset (>2,000) to achieve comparable accuracy. Moreover, by employing an MC method designed specifically for CGC that properly interprets the mixing rule, the spectra of mixtures are obtained with high accuracy. The logical origins of the good performance of the protocol are discussed in detail. Considering that such a constituent contribution protocol combines chemical principles and data-driven tools, most likely, it will be proven efficient to solve molecular-property-relevant problems in wider fields.

Cost-Effective Simulations of Vibrationally-Resolved Absorption Spectra of Fluorophores with Machine-Learning-Based Inhomogeneous Broadening

The results of electronic and vibrational structure simulations are an invaluable support for interpreting experimental absorption/emission spectra, which stimulates the development of reliable and cost-effective computational protocols. In this work, we contribute to these efforts and propose an efficient first-principle protocol for simulating vibrationally-resolved absorption spectra, including nonempirical estimations of the inhomogeneous broadening. To this end, we analyze three key aspects: (i) a metric-based selection of density functional approximation (DFA) so to benefit from the computational efficiency of time-dependent density function theory (TD-DFT) while safeguarding the accuracy of the vibrationally-resolved spectra, (ii) an assessment of two vibrational structure schemes (vertical gradient and adiabatic Hessian) to compute the Franck-Condon factors, and (iii) the use of machine learning to speed up nonempirical estimations of the inhomogeneous broadening. In more detail, we predict the absorption band shapes for a set of 20 medium-sized fluorescent dyes, focusing on the bright ππ^★ S₀ → S₁ transition and using experimental results as references. We demonstrate that, for the studied 20-dye set which includes structures with large structural variability, the preselection of DFAs based on an easily accessible metric ensures accurate band shapes with respect to the reference approach and that range-separated functionals show the best performance when combined with the vertical gradient model. As far as band widths are concerned, we propose a new machine-learning-based approach for determining the inhomogeneous broadening induced by the solvent microenvironment. This approach is shown to be very robust offering inhomogeneous broadenings with errors as small as 2 cm^-1 with respect to genuine electronic-structure calculations, with a total CPU time reduced by 98%.

Machine-learning screening of luminogens with aggregation-induced emission characteristics for fluorescence imaging

Due to the excellent biocompatible physicochemical performance, luminogens with aggregation-induced emission (AIEgens) characteristics have played a significant role in biomedical fluorescence imaging recently. However, screening AIEgens for special applications takes a lot of time and efforts by using conventional chemical synthesis route. Fortunately, artificial intelligence techniques that could predict the properties of AIEgen molecules would be helpful and valuable for novel AIEgens design and synthesis. In this work, we applied machine learning (ML) techniques to screen AIEgens with expected excitation and emission wavelength for biomedical deep fluorescence imaging. First, a database of various AIEgens collected from the literature was established. Then, by extracting key features using molecular descriptors and training various state-of-the-art ML models, a multi-modal molecular descriptors strategy has been proposed to extract the structure-property relationships of AIEgens and predict molecular absorption and emission wavelength peaks. Compared to the first principles calculations, the proposed strategy provided greater accuracy at a lower computational cost. Finally, three newly predicted AIEgens with desired absorption and emission wavelength peaks were synthesized successfully and applied for cellular fluorescence imaging and deep penetration imaging. All the results were consistent successfully with our expectations, which demonstrated the above ML has a great potential for screening AIEgens with suitable wavelengths, which could boost the design and development of novel organic fluorescent materials.

Machine Learning Models for Predicting Molecular UV-Vis Spectra with Quantum Mechanical Properties

Accurate understanding of ultraviolet-visible (UV-vis) spectra is critical for the high-throughput synthesis of compounds for drug discovery. Experimentally determining UV-vis spectra can become expensive when dealing with a large quantity of novel compounds. This provides us an opportunity to drive computational advances in molecular property predictions using quantum mechanics and machine learning methods. In this work, we use both quantum mechanically (QM) predicted and experimentally measured UV-vis spectra as input to devise four different machine learning architectures, UVvis-SchNet, UVvis-DTNN, UVvis-Transformer, and UVvis-MPNN, and assess the performance of each method. We find that the UVvis-MPNN model outperforms the other models when using optimized 3D coordinates and QM predicted spectra as input features. This model has the highest performance for predicting UV-vis spectra with a training RMSE of 0.06 and validation RMSE of 0.08. Most importantly, our model can be used for the challenging task of predicting differences in the UV-vis spectral signatures of regioisomers.

Low-cost machine learning prediction of excited state properties of iridium-centered phosphors

Prediction of the excited state properties of photoactive iridium complexes challenges ab initio methods such as time-dependent density functional theory (TDDFT) both from the perspective of accuracy and of computational cost, complicating high-throughput virtual screening (HTVS). We instead leverage low-cost machine learning (ML) models and experimental data for 1380 iridium complexes to perform these prediction tasks. We find the best-performing and most transferable models to be those trained on electronic structure features from low-cost density functional tight binding calculations. Using artificial neural network (ANN) models, we predict the mean emission energy of phosphorescence, the excited state lifetime, and the emission spectral integral for iridium complexes with accuracy competitive with or superseding that of TDDFT. We conduct feature importance analysis to determine that high cyclometalating ligand ionization potential correlates to high mean emission energy, while high ancillary ligand ionization potential correlates to low lifetime and low spectral integral. As a demonstration of how our ML models can be used for HTVS and the acceleration of chemical discovery, we curate a set of novel hypothetical iridium complexes and use uncertainty-controlled predictions to identify promising ligands for the design of new phosphors while retaining confidence in the quality of the ANN predictions.

Solvatochromic Sensitivity of BODIPY Probes: A New Tool for Selecting Fluorophores and Polarity Mapping

This research work is devoted to collecting a high-quality dataset of BODIPYs in a series of 10-30 solvents. In total, 115 individual compounds in 71 solvents are represented by 1698 arrays of the spectral and photophysical properties of the fluorophore. Each dye for a series of solvents is characterized by a calculated value of solvatochromic sensitivity according to a semiempirical approach applied to a series of solvents. The whole dataset is classified into 6 and 24 clusters of solvatochromic sensitivity, from high negative to high positive solvatochromism. The results of the analysis are visualized by the polarity mapping plots depicting, in terms of wavenumbers, the absorption versus emission, stokes shift versus - (absorption maxima + emission maxima), and quantum yield versus stokes shift. An analysis of the clusters combining several dyes in an individual series of solvents shows that dyes of a high solvatochromic sensitivity demonstrate regular behaviour of the corresponding plots suitable for polarity and viscosity mapping. The fluorophores collected in this study represent a high quality dataset of pattern dyes for analytical and bioanalytical applications. The developed tools could be applied for the analysis of the applicability domain of the fluorescent sensors.

De novo creation of fluorescent molecules via adversarial generative modeling

The development of AI for fluorescent materials design is technologically demanding due to the issue of accurately forecasting fluorescent properties. Besides the huge efforts made in predicting the photoluminescent properties of organic dyes in terms of machine learning techniques, this article aims to introduce an adversarial generation paradigm for the rational design of fluorescent molecules. Molecular SMILES is employed as the input of a GRU based autoencoder, where the encoding and decoding of the string information are processed. A generative adversarial network is applied on the latent space with a generator to generate samples to mimic the latent space, and a discriminator to distinguish samples from the latent space. It is found that the excited state property distributions of generated molecules fully match those of the original samples, with the molecular synthesizability being accessible as well. Further screening of the generated samples delivers a remarkable luminescence efficiency of molecules epitomized by the significant oscillator strength and charge transfer characteristics, demonstrating the great potential of the adversarial model in enriching the fluorescent library.

Controlling the fluorescence quantum yields of benzothiazole-difluoroborates by optimal substitution

Precise tuning of the fluorescence quantum yield, vital for countless applications of fluorophores, remains exceptionally challenging due to numerous factors affecting energy dissipation phenomena often leading to its counterintuitive behavior. In contrast to the absorption and emission wavelength which can be precisely shifted to the desired range by simple structural changes, no general strategy exists for controllable modification of the fluorescence quantum yield. The rigidification of the molecular skeleton is known to usually enhance the emission and can be practically realized via the limiting molecular vibrations by aggregation. However, the subtle balance between the abundant possible radiative and non-radiative decay pathways makes the final picture exceptionally sophisticated. In the present study, a series of nine fluorophores obtained by peripheral substitution with two relatively mild electron donating and electron withdrawing groups are reported. The obtained fluorescence quantum yields range from dark to ultra-bright and the extreme values are obtained for the isomeric molecules. These severe changes in emission efficiency have been shown to arise from the complex relationship between the Franck-Condon excited state and conical intersection position. The experimental findings are rationalized by the advanced quantum chemical calculations delivering good correlation between the measured emission parameters and theoretical radiative and internal conversion rate constants. Therefore, the described substituent exchange provides a method to rigorously adjust the properties of molecular probes structurally similar to thioflavin T.

Can machine learning methods accurately predict the molar absorption coefficient of different classes of dyes?

In this article, we provide a convenient tool for all researchers to predict the value of the molar absorption coefficient for a wide number of dyes without any computer costs. The new model is based on RFR method (ALogPS, OEstate + Fragmentor + QNPR) and is able to predict the molar absorption coefficient with an accuracy (5-fold cross-validation RMSE) of 0.26 log unit. This accuracy was achieved due to the fact that the model was trained on data for more than 20,000 unique dye molecules. To our knowledge, this is the first model for predicting the molar absorption coefficient trained on such a large and diverse set of dyes. The model is available at https://ochem.eu/article/145413. We hope that the new model will allow researchers to predict dyes with practically significant spectral characteristics and verify existing experimental data.

Assembly and Applications of Macrocyclic-Confinement-Derived Supramolecular Organic Luminescent Emissions from Cucurbiturils

Cucurbit[n]urils (Q[n]s or CB[n]s), as a classical of artificial organic macrocyclic hosts, were found to have excellent advantages in the fabricating of tunable and smart organic luminescent materials in aqueous media and the solid state with high emitting efficiency under the rigid pumpkin-shaped structure-derived macrocyclic-confinement effect in recent years. This review aims to give a systematically up-to-date overview of the Q[n]-based supramolecular organic luminescent emissions from the confined spaces triggered host-guest complexes, including the assembly fashions and the mechanisms of the macrocycle-based luminescent complexes, as well as their applications. Finally, challenges and outlook are provided. Since this class of Q[n]-based supramolecular organic luminescent emissions, which have essentially derived from the cavity-dependent confinement effect and the resulting assembly fashions, emerged only a few years ago, we hope this review will provide valuable information for the further development of macrocycle-based light-emitting materials and other related research fields.

Prediction of Maximum Absorption Wavelength Using Deep Neural Networks

Fluorescent molecules are important tools in biological detection, and numerous efforts have been made to develop compounds to meet the desired photophysical properties. For example, tuning the wavelength allows an appropriate penetration depth with minimal interference from the autofluorescence/scattering for a better signal-to-noise contrast. However, there are limited guidelines to rationally design or computationally predict the optical properties from first principles, and factors like the solvent effects will make it more complicated. Herein, we established a database (SMFluo1) of 1181 solvated small-molecule fluorophores covering the ultraviolet-visible-near-infrared absorption window and developed new machine learning models based on deep neural networks for accurately predicting photophysical parameters. The optimal system was applied to 120 out-of-sample compounds, and it exhibited remarkable accuracy with a mean relative error of 1.52%. In this new paradigm, a deep learning algorithm is promising to complement conventional theoretical and experimental studies of fluorophores and to greatly accelerate the discovery of new dyes. Due to its simplicity and efficiency, data from newly developed fluorophores can be easily supplemented to this system to further improve the accuracy across various dye families.

Deep neural network model for highly accurate prediction of BODIPYs absorption

A possibility to accurately predict the absorption maximum wavelength of BODIPYs was investigated. We found that previously reported models had a low accuracy (40-57 nm) to predict BODIPYs due to the limited dataset sizes and/or number of BODIPYs (few hundreds). New models developed in this study were based on data of 6000-plus fluorescent dyes (including 4000-plus BODIPYs) and the deep neural network architecture. The high prediction accuracy (five-fold cross-validation room mean squared error (RMSE) of 18.4 nm) was obtained using a consensus model, which was more accurate than individual models. This model provided the excellent accuracy (RMSE of 8 nm) for molecules previously synthesized in our laboratory as well as for prospective validation of three new BODIPYs. We found that solvent properties did not significantly influence the model accuracy since only few BODIPYs exhibited solvatochromism. The analysis of large prediction errors suggested that compounds able to have intermolecular interactions with solvent or salts were likely to be incorrectly predicted. The consensus model is freely available at https://ochem.eu/article/134921 and can help the other researchers to accelerate design of new dyes with desired properties.

Multi-fidelity prediction of molecular optical peaks with deep learning

Optical properties are central to molecular design for many applications, including solar cells and biomedical imaging. A variety of ab initio and statistical methods have been developed for their prediction, each with a trade-off between accuracy, generality, and cost. Existing theoretical methods such as time-dependent density functional theory (TD-DFT) are generalizable across chemical space because of their robust physics-based foundations but still exhibit random and systematic errors with respect to experiment despite their high computational cost. Statistical methods can achieve high accuracy at a lower cost, but data sparsity and unoptimized molecule and solvent representations often limit their ability to generalize. Here, we utilize directed message passing neural networks (D-MPNNs) to represent both dye molecules and solvents for predictions of molecular absorption peaks in solution. Additionally, we demonstrate a multi-fidelity approach based on an auxiliary model trained on over 28 000 TD-DFT calculations that further improves accuracy and generalizability, as shown through rigorous splitting strategies. Combining several openly-available experimental datasets, we benchmark these methods against a state-of-the-art regression tree algorithm and compare the D-MPNN solvent representation to several alternatives. Finally, we explore the interpretability of the learned representations using dimensionality reduction and evaluate the use of ensemble variance as an estimator of the epistemic uncertainty in our predictions of molecular peak absorption in solution. The prediction methods proposed herein can be integrated with active learning, generative modeling, and experimental workflows to enable the more rapid design of molecules with targeted optical properties.

Applications of machine learning in computational nanotechnology

Machine learning (ML) has gained extensive attention in recent years due to its powerful data analysis capabilities. It has been successfully applied to many fields and helped the researchers to achieve several major theoretical and applied breakthroughs. Some of the notable applications in the field of computational nanotechnology are ML potentials, property prediction, and material discovery. This review summarizes the state-of-the-art research progress in these three fields. ML potentials bridge the efficiency versus accuracy gap between density functional calculations and classical molecular dynamics. For property predictions, ML provides a robust method that eliminates the need for repetitive calculations for different simulation setups. Material design and drug discovery assisted by ML greatly reduce the capital and time investment by orders of magnitude. In this perspective, several common ML potentials and ML models are first introduced. Using these state-of-the-art models, developments in property predictions and material discovery are overviewed. Finally, this paper was concluded with an outlook on future directions of data-driven research activities in computational nanotechnology.

Data-driven modeling of S0 → S1 excitation energy in the BODIPY chemical space: High-throughput computation, quantum machine learning, and inverse design

Derivatives of BODIPY are popular fluorophores due to their synthetic feasibility, structural rigidity, high quantum yield, and tunable spectroscopic properties. While the characteristic absorption maximum of BODIPY is at 2.5 eV, combinations of functional groups and substitution sites can shift the peak position by ±1 eV. Time-dependent long-range corrected hybrid density functional methods can model the lowest excitation energies offering a semi-quantitative precision of ±0.3 eV. Alas, the chemical space of BODIPYs stemming from combinatorial introduction of-even a few dozen-substituents is too large for brute-force high-throughput modeling. To navigate this vast space, we select 77 412 molecules and train a kernel-based quantum machine learning model providing <2% hold-out error. Further reuse of the results presented here to navigate the entire BODIPY universe comprising over 253 giga (253 × 10⁹) molecules is demonstrated by inverse-designing candidates with desired target excitation energies.

Efficient Discovery of Visible Light-Activated Azoarene Photoswitches with Long Half-Lives Using Active Search

Photoswitches are molecules that undergo a reversible, structural isomerization after exposure to certain wavelengths of light. The dynamic control offered by molecular photoswitches is favorable for materials chemistry, photopharmacology, and catalysis applications. Ideal photoswitches absorb visible light and have long-lived metastable isomers. We used high-throughput virtual screening to predict the absorption maxima (λ_max) of the E-isomer and half-life (t_1/2) of the Z-isomer. However, computing the photophysical and kinetic stabilities with density functional theory of each entry of a virtual molecular library containing thousands or millions of molecules is prohibitively time-consuming. We applied active search, a machine-learning technique, to intelligently search a chemical search space of 255 991 photoswitches based on 29 known azoarenes and their derivatives. We iteratively trained the active search algorithm on whether a candidate absorbed visible light (λ_max > 450 nm). Active search was found to triple the discovery rate compared to random search. Further, we projected 1962 photoswitches to 2D using the Uniform Manifold Approximation and Projection algorithm and found that λ_max depends on the core, which is tunable by substituents. We then incorporated a second stage of screening to predict the stabilities of the Z-isomers for the top candidates of each core. We identified four ideal photoswitches that concurrently satisfy the following criteria: λ_max > 450 nm and t_1/2 > 2 h.These candidates had λ_max and t_1/2 range from 465 to 531 nm and hours to days, respectively.

Nonconventional luminophores: characteristics, advancements and perspectives

Nonconventional luminophores devoid of remarkable conjugates have attracted considerable attention due to their unique luminescence behaviors, updated luminescence mechanism of organics and promising applications in optoelectronic, biological and medical fields. Unlike classic luminogens consisting of molecular segments with greatly extended electron delocalization, these unorthodox luminophores generally possess nonconjugated structures based on subgroups such as ether (-O-), hydroxyl (-OH), halogens, carbonyl (CO), carboxyl (-COOH), cyano (CN), thioether (-S-), sulfoxide (SO), sulfone (OSO), phosphate, and aliphatic amine, as well as their grouped functionalities like amide, imide, anhydride and ureido. They can exhibit intriguing intrinsic luminescence, generally featuring concentration-enhanced emission, aggregation-induced emission, excitation-dependent luminescence and prevailing phosphorescence. Herein, we review the recent progress in exploring these nonconventional luminophores and discuss the current challenges and future perspectives. Notably, different mechanisms are reviewed and the clustering-triggered emission (CTE) mechanism is highlighted, which emphasizes the clustering of the above mentioned electron rich moieties and consequent electron delocalization along with conformation rigidification. The CTE mechanism seems widely applicable for diversified natural, synthetic and supramolecular systems.

Controlling Molecular Aggregation-Induced Emission by Controlled Polymerization

In last twenty years, the significant development of AIE materials has been witnessed. A number of small molecules, polymers and composites with AIE activity have been synthesized, with some of these exhibiting great potential in optoelectronics and biomedical applications. Compared to AIE small molecules, macromolecular systems-especially well-defined AIE polymers-have been studied relatively less. Controlled polymerization methods provide the efficient synthesis of well-defined AIE polymers with varied monomers, tunable chain lengths and narrow dispersity. In particular, the preparation of single-fluorophore polymers through AIE molecule-initiated polymerization enables the systematic investigation of the structure-property relationships of AIE polymeric systems. Here, the main polymerization techniques involved in these polymers are summarized and the key parameters that affect their photophysical properties are analyzed. The author endeavored to collect meaningful information from the descriptions of AIE polymer systems in the literature, to find connections by comparing different representative examples, and hopes eventually to provide a set of general guidelines for AIE polymer design, along with personal perspectives on the direction of future research.

Stacked Ensemble Machine Learning for Range-Separation Parameters

Density functional theory-based high-throughput materials and drug discovery has achieved tremendous success in recent decades, but its power on organic semiconducting molecules suffered catastrophically from the self-interaction error until the nonempirical but expensive optimally tuned range-separated hybrid (OT-RSH) functionals were developed. An OT-RSH transitions from a short-range (semi)local functional to a long-range Hartree-Fock exchange at a distance characterized by a molecule-specific range-separation parameter (ω). Herein, we propose a stacked ensemble machine learning model that provides an accelerated alternative of OT-RSH based on system-dependent structural and electronic configurations. We trained ML-ωPBE, the first functional in our series, using a database of 1970 molecules with sufficient structural and functional diversity, and assessed its accuracy and efficiency using another 1956 molecules. Compared with nonempirical OT-ωPBE, ML-ωPBE reaches a mean absolute error of 0.00504a₀^-1 for optimal ω's, reduces the computational cost by 2.66 orders of magnitude, and achieves comparable predictive power in optical properties.

Machine Learning for Electronically Excited States of Molecules

Electronically excited states of molecules are at the heart of photochemistry, photophysics, as well as photobiology and also play a role in material science. Their theoretical description requires highly accurate quantum chemical calculations, which are computationally expensive. In this review, we focus on not only how machine learning is employed to speed up such excited-state simulations but also how this branch of artificial intelligence can be used to advance this exciting research field in all its aspects. Discussed applications of machine learning for excited states include excited-state dynamics simulations, static calculations of absorption spectra, as well as many others. In order to put these studies into context, we discuss the promises and pitfalls of the involved machine learning techniques. Since the latter are mostly based on quantum chemistry calculations, we also provide a short introduction into excited-state electronic structure methods and approaches for nonadiabatic dynamics simulations and describe tricks and problems when using them in machine learning for excited states of molecules.

Hydrogen Evolution Prediction for Alternating Conjugated Copolymers Enabled by Machine Learning with Multidimension Fragmentation Descriptors

Hydrogen evolution by alternating conjugated copolymers has attracted much attention in recent years. To study alternating copolymers with data-driven strategies, two types of multidimension fragmentation descriptors (MDFD), structure-based MDFD (SMDFD), and electronic property-based MDFD (EPMDFD), have been developed with machine learning (ML) algorithms for the first time. The superiority of SMDFD-based models has been demonstrated by the highly accurate and universal predictions of electronic properties. Moreover, EPMDFD-based, experimental-parameter-free ML models were developed for the prediction of the hydrogen evolution reaction, displaying excellent accuracy (real-test accuracy = 0.91). The combination of explainable ML approaches and first-principles calculations was employed to explore photocatalytic dynamics, revealing the importance of electron delocalization in the excited state. Virtual designing of high-performance candidates can also be achieved. Our work illustrates the huge potential of ML-based material design in the field of polymeric photocatalysts toward high-performance photocatalysis.

Molecular excited states through a machine learning lens

Theoretical simulations of electronic excitations and associated processes in molecules are indispensable for fundamental research and technological innovations. However, such simulations are notoriously challenging to perform with quantum mechanical methods. Advances in machine learning open many new avenues for assisting molecular excited-state simulations. In this Review, we track such progress, assess the current state of the art and highlight the critical issues to solve in the future. We overview a broad range of machine learning applications in excited-state research, which include the prediction of molecular properties, improvements of quantum mechanical methods for the calculations of excited-state properties and the search for new materials. Machine learning approaches can help us understand hidden factors that influence photo-processes, leading to a better control of such processes and new rules for the design of materials for optoelectronic applications.