Deep Learning Optical Spectroscopy Based on Experimental Database: Potential Applications to Molecular Design

Predicting Emission Wavelengths in Benzobisoxazole-Based OLEDs with Gradient Boosted Ensemble Models

We demonstrate the use of gradient-boosted ensemble models that accurately predict emission wavelengths in benzobis[1,2-d:4,5-d']oxazole (BBO) based fluorescent emitters. We have curated a database of 50 molecules from previously published data by the Jeffries-EL group using density functional theory (DFT) computed ground and excited state features. We consider two machine learning (ML) models based on (i) whole cruciform molecules and (ii) their constituent fragment molecules. Both ML models provide accurate predictions with root-mean-square errors between 30 and 36 nm, competitive with state-of-the-art deep learning models trained on orders of magnitude more molecules, and this accuracy holds even when tested on four new BBO emitters unseen by the models. We also provide an interpretable feature importance analysis and discuss the relevant relationships between DFT and changes in predicted emission wavelength.

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.

Optical color routing enabled by deep learning

Nano-color routing has emerged as an immensely popular and widely discussed subject in the realms of light field manipulation, image sensing, and the integration of deep learning. The conventional dye filters employed in commercial applications have long been hampered by several limitations, including subpar signal-to-noise ratio, restricted upper bounds on optical efficiency, and challenges associated with miniaturization. Nonetheless, the advent of bandpass-free color routing has opened up unprecedented avenues for achieving remarkable optical spectral efficiency and operation at sub-wavelength scales within the area of image sensing applications. This has brought about a paradigm shift, fundamentally transforming the field by offering a promising solution to surmount the constraints encountered with traditional dye filters. This review presents a comprehensive exploration of representative deep learning-driven nano-color routing structure designs, encompassing forward simulation algorithms, photonic neural networks, and various global and local topology optimization methods. A thorough comparison is drawn between the exceptional light-splitting capabilities exhibited by these methods and those of traditional design approaches. Additionally, the existing research on color routing is summarized, highlighting a promising direction for forthcoming development, delivering valuable insights to advance the field of color routing and serving as a powerful reference for future endeavors.

Concluding remarks: challenges and prospects in organic photonics and electronics

The Faraday Discussion meeting on 'challenges and prospects in organic and photonics and electronics' was held in Osaka, Japan, after the COVID pandemic and during the subsequent global difficulties, in the traditional face-to-face and condensed style, with many discussions, both after the short presentations and in front of the poster presentations. I would like to take this opportunity to thank the organising members, particularly Youhei Takeda and local professors, for their efforts in organising this meeting.

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.

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.

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.

Novel π-Extended Indolocarbazole-Based Deep-Blue Fluorescent Emitter with Remarkably Narrow Bandwidth for Solution-Processed Organic Light-Emitting Diodes

In solution-processed organic light-emitting diodes (OLEDs), achieving high color purity and efficiency is as important as that in vacuum processes. Emitters suitable for solution processing must have excellent solubility in organic solvents, high molecular weight, and compatibility with the host materials. In this study, we synthesized a deep-blue emitter that satisfies the above conditions by introducing a 1,4-bis(indolo[3,2,1-jk]carbazol-2-yl)benzene-based planar emitting core (DICz) structure and four 3,6-di-tert-butyl-9-phenyl-9H-carbazole (tCz) peripheral units, namely, 4tCz-DICz. A comparative compound, 4Hex-DICz, incorporating hexyl phenyl groups was synthesized. In contrast to 4Hex-DICz, 4tCz-DICz exhibited exceptional solubility in organic solvents and superior film-forming properties attributed to the presence of tCz units. Additionally, in the film state, the effective encapsulation of the emitting core (DICz) by the tCz units in 4tCz-DICz helps prevent undesirable molecular aggregation. The solution-processed OLEDs employing the CH-2D1 film, doped with 5 wt % 4tCz-DICz as the emitting layer, exhibited a deep-blue emission at 424 nm, characterized by a narrow bandwidth of 22 nm, and achieved a maximum external quantum efficiency (EQE) of approximately 4.0%. In contrast, the 4Hex-DICz-based device demonstrated an EQE of 2.91%. Consequently, we have successfully demonstrated that the introduction of four bulky tCz units into the DICz core is a promising molecular design strategy for the development of soluble indolocarbazole-based emitters, especially those used in high-performance deep-blue fluorescent OLEDs.

Data-driven tailoring of molecular dipole polarizability and frontier orbital energies in chemical compound space

Understanding correlations - or lack thereof - between molecular properties is crucial for enabling fast and accurate molecular design strategies. In this contribution, we explore the relation between two key quantities describing the electronic structure and chemical properties of molecular systems: the energy gap between the frontier orbitals and the dipole polarizability. Based on the recently introduced QM7-X dataset, augmented with accurate molecular polarizability calculations as well as analysis of functional group compositions, we show that polarizability and HOMO-LUMO gap are uncorrelated when considering sufficiently extended subsets of the chemical compound space. The relation between these two properties is further analyzed on specific examples of molecules with similar composition as well as homooligomers. Remarkably, the freedom brought by the lack of correlation between molecular polarizability and HOMO-LUMO gap enables the design of novel materials, as we demonstrate on the example of organic photodetector candidates.

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.

Machine Learning for Bridging the Gap between Density Functional Theory and Coupled Cluster Energies

Accurate electronic energies and properties are crucial for successful reaction design and mechanistic investigations. Computing energies and properties of molecular structures has proven extremely useful, and, with increasing computational power, the limits of high-level approaches (such as coupled cluster theory) are expanding to ever larger systems. However, because scaling is highly unfavorable, these methods are still not universally applicable to larger systems. To address the need for fast and accurate electronic energies of larger systems, we created a database of around 8000 small organic monomers (2000 dimers) optimized at the B3LYP-D3(BJ)/cc-pVTZ level of theory. This database also includes single-point energies computed at various levels of theory, including PBE1PBE, ωΒ97Χ, M06-2X, revTPSS, B3LYP, and BP86, for density functional theory as well as DLPNO-CCSD(T) and CCSD(T) for coupled cluster theory, all in conjunction with a cc-pVTZ basis. We used this database to train machine learning models based on graph neural networks using two different graph representations. Our models are able to make energy predictions from B3LYP-D3(BJ)/cc-pVTZ inputs to CCSD(T)/cc-pVTZ outputs with a mean absolute error of 0.78 and to DLPNO-CCSD(T)/cc-pVTZ with an mean absolute error of 0.50 and 0.18 kcal mol^-1 for monomers and dimers, respectively. The model for dimers was further validated on the S22 database, and the monomer model was tested on challenging systems, including those with highly conjugated or functionally complex molecules.

The landscape of computational approaches for artificial photosynthesis

Artificial photosynthesis is an attractive strategy for converting solar energy into fuels, largely because the Earth receives enough solar energy in one hour to meet humanity's energy needs for an entire year. However, developing devices for artificial photosynthesis remains difficult and requires computational approaches to guide and assist the interpretation of experiments. In this Perspective, we discuss current and future computational approaches, as well as the challenges of designing and characterizing molecular assemblies that absorb solar light, transfer electrons between interfaces, and catalyze water-splitting and fuel-forming reactions.

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.

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%.

Extracting Polaron Recombination from Electroluminescence in Organic Light-Emitting Diodes by Artificial Intelligence

Direct exploring the electroluminescence (EL) of organic light-emitting diodes (OLEDs) is a challenge due to the complicated processes of polarons, excitons, and their interactions. This study demonstrated the extraction of the polaron dynamics from transient EL by predicting the recombination coefficient via artificial intelligence, overcoming multivariable kinetics problems. The performance of a machine learning (ML) model trained by various EL decay curves is significantly improved using a novel featurization method and input node optimization, achieving an R² value of 0.947. The optimized ML model successfully predicts the recombination coefficients of actual OLEDs based on an exciplex-forming cohost, enabling the quantitative understanding of the overall polaron behavior under various electrical excitation conditions.

Direct detection of photo-induced reactions by IR: from Brook rearrangement to photo-catalysis

In situ IR detection of photoreactions induced by the light of LEDs at appropriate wavelengths provides a simple, cost-effective, and versatile method to get insight into mechanistic details. In particular, conversions of functional groups can be selectively followed. Overlapping UV-Vis bands or fluorescence from the reactants and products and the incident light do not obstruct IR detection. Compared with in situ photo-NMR, our setup does not require tedious sample preparation (optical fibers) and offers a selective detection of reactions, even at positions where ¹H-NMR lines overlap or ¹H resonances are not clear-cut. We illustrate the applicability of our setup following the photo-Brook rearrangement of (adamant-1-yl-carbonyl)-tris(trimethylsilyl)silane, address photo-induced α-bond cleavage (1-hydroxycyclohexyl phenyl ketone), study photoreduction using tris(bipyridine)ruthenium(II), investigate photo-oxygenation of double bonds with molecular oxygen and the fluorescent 2,4,6-triphenylpyrylium photocatalyst, and address photo-polymerization. With the LED/FT-IR combination, reactions can be qualitatively followed in fluid solution, (highly) viscous environments, and in the solid state. Viscosity changes during the reaction (e.g., during a polymerization) do not obstruct the method.

A simple array integrating machine learning for identification of flavonoids in red wines

Bioactive flavonoids, the major ingredients of red wines, have been proven to prevent atherosclerosis and cardiovascular disease due to their anti-inflammatory and anti-oxidant activity. However, flavonoids have proven challenging to identify, even when multiple approaches are combined. Hereby, a simple array was constructed to detect flavonoids by employing phenylboronic acid modified perylene diimide derivatives (PDIs). Through multiple non-specific interactions (hydrophilic, hydrophobic, charged, aromatic, hydrogen-bonded and reversible covalent interactions) with flavonoids, the fluorescence of PDIs can be modulated, and variations in intensity can be used to create fingerprints of flavonoids. This array successfully discriminated 14 flavonoids of diverse structures and concentrations with 100% accuracy, based on patterns in fluorescence intensity modulation, via optimized machine learning algorithms. As a result, this array demonstrated the parallel detection of 8 different types and origins of red wines with a high accuracy, revealing the excellent potential of the sensor array in food mixtures detection.

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.

General Graph Neural Network-Based Model To Accurately Predict Cocrystal Density and Insight from Data Quality and Feature Representation

Cocrystal engineering as an effective way to modify solid-state properties has inspired great interest from diverse material fields while cocrystal density is an important property closely correlated with the material function. In order to accurately predict the cocrystal density, we develop a graph neural network (GNN)-based deep learning framework by considering three key factors of machine learning (data quality, feature presentation, and model architecture). The result shows that different stoichiometric ratios of molecules in cocrystals can significantly influence the prediction performances, highlighting the importance of data quality. In addition, the feature complementary is not suitable for augmenting the molecular graph representation in the cocrystal density prediction, suggesting that the complementary strategy needs to consider whether extra features can sufficiently supplement the lacked information in the original representation. Based on these results, 4144 cocrystals with 1:1 stoichiometry ratio are selected as the dataset, supplemented by the data augmentation of exchanging a pair of coformers. The molecular graph is determined to learn feature representation to train the GNN-based model. Global attention is introduced to further optimize the feature space and identify important atoms to realize the interpretability of the model. Benefited from the advantages, our model significantly outperforms three competitive models and exhibits high prediction accuracy for unseen cocrystals, showcasing its robustness and generality. Overall, our work not only provides a general cocrystal density prediction tool for experimental investigations but also provides useful guidelines for the machine learning application. All source codes are freely available at https://github.com/Xiao-Gua00/CCPGraph.

Data-driven approach for benchmarking DFTB-approximate excited state methods

In this work we propose a chemically-informed data-driven approach to benchmark the approximate density-functional tight-binding (DFTB) excited state (ES) methods that are currently available within the DFTB+ suite. By taking advantage of the large volume of low-detail ES-data in the machine learning (ML) dataset, QM8, we were able to extract valuable insights regarding the limitations of the benchmarked methods in terms of the approximations made to the parent formalism, density-functional theory (DFT), while providing recommendations on how to overcome them. For this benchmark, we compared the first singlet-singlet vertical excitation energies (E₁) predicted by the DFTB-approximate methods with predictions of less approximate methods from the reference ML-dataset. For the nearly 21800 organic molecules in the GDB-8 chemical space, we were able to identify clear trends in the E₁ prediction error distributions, with respect to second-order approximate coupled cluster (CC2), showing a strong dependence on chemical identity.

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.

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.

Multispectral Portable Fibre-Optic Reflectometer for the Classification of the Origin of Chicken Eggshells in the Case of Mycoplasma synoviae Infections

The proper classification of the origins of food products is a crucial issue all over the world nowadays. In this paper, the authors present a device-a multispectral portable fibre-optic reflectometer and signal processing patch-together with a machine-learning algorithm for the classification of the origins of chicken eggshells in the case of Mycoplasma synoviae infection. The sensor device was developed based on previous studies with a continuous spectrum in transmittance and selected spectral lines in reflectance. In the described case, the sensor is based on the integration of reflected spectral data from short spectral bands from the VIS and NIR region, which are produced by single-colour LEDs and introduced to the sample via a fibre bundle. The measurement is carried out in a sequence, and the reflected signal is pre-processed to be put in the machine learning algorithm. The support vector machine algorithm is used together with three different types of data normalization. The obtained results of the F-score factor for classification of the origins of samples show that the percentages of eggs coming from Mycoplasma synoviae infected hens are up to 87% for white and 96% for brown eggshells.

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.

Understanding the charge dynamics in organic light-emitting diodes using convolutional neural network

Knowledge about the charge dynamics in organic light-emitting diodes (OLEDs) is a critical clue to optimize device architecture for enhancing the power efficiency and driving voltage characteristics in addition to the external quantum efficiency. In this work, we demonstrated that the charge behavior according to the operation voltage of OLEDs could be understood by introducing the convolutional neural network (CNN) of the machine learning framework without additional analysis of the unipolar charge devices. The CNN model trained using a two-dimensional (2D) modulus fingerprint simultaneously predicted the mobilities of the charge transport and emitting layers, realizing a deep understanding of the complicated data that humans cannot interpret. The machine learning model successfully describes the electrical properties of the organic layers in the actual devices configurated by different electron-transporting materials and the composition of cohosts in the emitting layer. For the first time, it was revealed that 2D fingerprints extracted using frequency- and voltage-dependent modulus spectra were effective data to represent comprehensive charge dynamics of OLEDs. The interpretation and perspective of the machine learning approach in this work were also discussed.

Identifying structure-absorption relationships and predicting absorption strength of non-fullerene acceptors for organic photovoltaics

Non-fullerene acceptors (NFAs) are excellent light harvesters, yet the origin of their high optical extinction is not well understood. In this work, we investigate the absorption strength of NFAs by building a database of time-dependent density functional theory (TDDFT) calculations of ∼500 π-conjugated molecules. The calculations are first validated by comparison with experimental measurements in solution and solid state using common fullerene and non-fullerene acceptors. We find that the molar extinction coefficient (ε _d,max) shows reasonable agreement between calculation in vacuum and experiment for molecules in solution, highlighting the effectiveness of TDDFT for predicting optical properties of organic π-conjugated molecules. We then perform a statistical analysis based on molecular descriptors to identify which features are important in defining the absorption strength. This allows us to identify structural features that are correlated with high absorption strength in NFAs and could be used to guide molecular design: highly absorbing NFAs should possess a planar, linear, and fully conjugated molecular backbone with highly polarisable heteroatoms. We then exploit a random decision forest algorithm to draw predictions for ε _d,max using a computational framework based on extended tight-binding Hamiltonians, which shows reasonable predicting accuracy with lower computational cost than TDDFT. This work provides a general understanding of the relationship between molecular structure and absorption strength in π-conjugated organic molecules, including NFAs, while introducing predictive machine-learning models of low computational cost.

Data-Driven and Multiscale Modeling of DNA-Templated Dye Aggregates

Dye aggregates are of interest for excitonic applications, including biomedical imaging, organic photovoltaics, and quantum information systems. Dyes with large transition dipole moments (μ) are necessary to optimize coupling within dye aggregates. Extinction coefficients (ε) can be used to determine the μ of dyes, and so dyes with a large ε (>150,000 M−1cm−1) should be engineered or identified. However, dye properties leading to a large ε are not fully understood, and low-throughput methods of dye screening, such as experimental measurements or density functional theory (DFT) calculations, can be time-consuming. In order to screen large datasets of molecules for desirable properties (i.e., large ε and μ), a computational workflow was established using machine learning (ML), DFT, time-dependent (TD-) DFT, and molecular dynamics (MD). ML models were developed through training and validation on a dataset of 8802 dyes using structural features. A Classifier was developed with an accuracy of 97% and a Regressor was constructed with an R2 of above 0.9, comparing between experiment and ML prediction. Using the Regressor, the ε values of over 18,000 dyes were predicted. The top 100 dyes were further screened using DFT and TD-DFT to identify 15 dyes with a μ relative to a reference dye, pentamethine indocyanine dye Cy5. Two benchmark MD simulations were performed on Cy5 and Cy5.5 dimers, and it was found that MD could accurately capture experimental results. The results of this study exhibit that our computational workflow for identifying dyes with a large μ for excitonic applications is effective and can be used as a tool to develop new dyes for excitonic applications.

Beyond Woodward-Fieser Rules: Design Principles of Property-Oriented Chromophores Based on Explainable Deep Learning Optical Spectroscopy

An adequate understanding of molecular structure-property relationships is important for developing new molecules with desired properties. Although deep learning optical spectroscopy (DLOS) has been successfully applied to predict the optical and photophysical properties of organic chromophores, how specific functional groups and solvents affect the optical properties is not clearly understood. Here, we employed an explainable DLOS method by applying the integrated gradients method to DLOS. The integrated gradients method allows us to obtain attributions, indicating how much the functional group contributes to the optical properties including the absorption wavelength and bandwidth, extinction coefficients, emission wavelength and bandwidth, photoluminescence quantum yield, and lifetime. The attributions of 54 functional groups and 9 solvent molecules to seven optical properties are quantified and can be used to estimate the optical properties of chromophores as in the Woodward-Fieser rule. Unlike the Woodward-Fieser rule for only the absorption wavelength, the attributions obtained in this work can be applied to estimate all seven optical properties, which makes a significant extension of the Woodward-Fieser rules. In addition, we demonstrated a strategy for utilizing the attributions in the design of molecules and in tuning the optical properties of the molecules. The design of molecular structures using attributions can revolutionize the development of optimal molecules.

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.

More Is Not Always Better: Local Models Provide Accurate Predictions of Spectral Properties of Porphyrins

The development of new functional materials based on porphyrins requires fast and accurate prediction of their spectral properties. The available models in the literature for absorption wavelength and extinction coefficient of the Soret band have low accuracy for this class of compounds. We collected spectral data for porphyrins to extend the literature set and compared the performance of global and local models for their modelling using different machine learning methods. Interestingly, extension of the public database contributed models with lower accuracies compared to the models, which we built using porphyrins only. The later model calculated acceptable RMSE = 2.61 for prediction of the absorption band of 335 porphyrins synthesized in our laboratory, but had a low accuracy (RMSE = 0.52) for extinction coefficient. A development of models using only compounds from our laboratory significantly decreased errors for these compounds (RMSE = 0.5 and 0.042 for absorption band and extinction coefficient, respectively), but limited their applicability only to these homologous series. When developing models, one should clearly keep in mind their potential use and select a strategy that could contribute the most accurate predictions for the target application. The models and data are publicly available.

More Is Not Always Better: Local Models Provide Accurate Predictions of Spectral Properties of Porphyrins

The development of new functional materials based on porphyrins requires fast and accurate prediction of their spectral properties. The available models in the literature for absorption wavelength and extinction coefficient of the Soret band have low accuracy for this class of compounds. We collected spectral data for porphyrins to extend the literature set and compared the performance of global and local models for their modelling using different machine learning methods. Interestingly, extension of the public database contributed models with lower accuracies compared to the models, which we built using porphyrins only. The later model calculated acceptable RMSE = 2.61 for prediction of the absorption band of 335 porphyrins synthesized in our laboratory, but had a low accuracy (RMSE = 0.52) for extinction coefficient. A development of models using only compounds from our laboratory significantly decreased errors for these compounds (RMSE = 0.5 and 0.042 for absorption band and extinction coefficient, respectively), but limited their applicability only to these homologous series. When developing models, one should clearly keep in mind their potential use and select a strategy that could contribute the most accurate predictions for the target application. The models and data are publicly available.

More Is Not Always Better: Local Models Provide Accurate Predictions of Spectral Properties of Porphyrins

The development of new functional materials based on porphyrins requires fast and accurate prediction of their spectral properties. The available models in the literature for absorption wavelength and extinction coefficient of the Soret band have low accuracy for this class of compounds. We collected spectral data for porphyrins to extend the literature set and compared the performance of global and local models for their modelling using different machine learning methods. Interestingly, extension of the public database contributed models with lower accuracies compared to the models, which we built using porphyrins only. The later model calculated acceptable RMSE = 2.61 for prediction of the absorption band of 335 porphyrins synthesized in our laboratory, but had a low accuracy (RMSE = 0.52) for extinction coefficient. A development of models using only compounds from our laboratory significantly decreased errors for these compounds (RMSE = 0.5 and 0.042 for absorption band and extinction coefficient, respectively), but limited their applicability only to these homologous series. When developing models, one should clearly keep in mind their potential use and select a strategy that could contribute the most accurate predictions for the target application. The models and data are publicly available.

Machine learning prediction of UV-Vis spectra features of organic compounds related to photoreactive potential

Machine learning (ML) algorithms were explored for the classification of the UV-Vis absorption spectrum of organic molecules based on molecular descriptors and fingerprints generated from 2D chemical structures. Training and test data (~ 75 k molecules and associated UV-Vis data) were assembled from a database with lists of experimental absorption maxima. They were labeled with positive class (related to photoreactive potential) if an absorption maximum is reported in the range between 290 and 700 nm (UV/Vis) with molar extinction coefficient (MEC) above 1000 Lmol^-1 cm^-1, and as negative if no such a peak is in the list. Random forests were selected among several algorithms. The models were validated with two external test sets comprising 998 organic molecules, obtaining a global accuracy up to 0.89, sensitivity of 0.90 and specificity of 0.88. The ML output (UV-Vis spectrum class) was explored as a predictor of the 3T3 NRU phototoxicity in vitro assay for a set of 43 molecules. Comparable results were observed with the classification directly based on experimental UV-Vis data in the same format.