Machine Learning Methods to Predict Density Functional Theory B3LYP Energies of HOMO and LUMO Orbitals

Database-aided ultrahigh-performance liquid chromatography Q-Exactive-Orbitrap tandem mass spectrometry putatively identifies 16 unexpected compounds and three anticounterfeiting pharmacopoeia quality markers for Perillae Fructus

RATIONALE

Perillae Fructus (PF) is a common traditional Chinese medicine (TCM) for the treatment of asthma. It has not been effectively characterized by rosmarinic acid (RosA), which is currently designed as the sole quality indicator in the Chinese Pharmacopoeia.

METHODS

This study introduced a database-aided ultrahigh-performance liquid chromatography equipped with quadrupole-Exactive-Orbitrap mass spectrometry (UHPLC/Q-Exactive-Orbitrap MS/MS) technology to putatively identify the compounds in PF, followed by literature research, quantum chemical calculation, and molecular docking to screen potential quality markers (Q-markers) of PF.

RESULTS

A total of 27 compounds were putatively identified, 16 of which had not been previously found from PF. In particular, matrine, scopolamine, and RosA showed relatively high levels of content, stability, and drug-likeness. They exhibited interactions with the asthma-related target and demonstrated the TCM properties of PF.

CONCLUSIONS

The database-aided UHPLC/Q-Exactive-Orbitrap MS/MS can identify at least 27 compounds in PF. Of these, 16 compounds are unexpected, and three compounds (matrine, scopolamine, and RosA) should be considered anticounterfeiting pharmacopoeia Q-markers of PF.

Repurposing the antihistamine drug bilastine as an anti-cancer metallic drug entity: synthesis and single-crystal X-ray structure analysis of metal-based bilastine and phen [Co(II), Cu(II) and Zn(II)] tailored anticancer chemotherapeutic agents against resistant cancer cells

Bilastine (BLA), 2-(4-(2-(4-(1-(2-ethoxyethyl)-1H-benzo[d]imidazole-2-yl)-piperidin-1-yl)-ethyl)-phenyl)-2-methylpropanoic acid, is an active antihistamine drug. With the idea of repurposing drugs from the existing pool of 'active' pharmaceutical ingredients, the therapeutic potency of bilastine as an anticancer agent was investigated via the tailored synthesis of a metal-based anticancer drug formulation of the type [BLA(phen)2M(II)]+·X-, where M = Co, Cu, and Zn and X- = NO3 and ClO4. The synthesized metal-based chemotherapeutics derived from the bilastine drug that acts as a ligand were thoroughly characterized using spectroscopic techniques, namely, UV-vis, FT-IR, and EPR (in the case of 1 and 2); 1H-NMR and 13C-NMR (in the case of 3); ESI-MS and single-crystal X-ray diffraction studies. Comprehensive biological studies (DNA binding, cleavage, and cytotoxic activity) using various biophysical and gel electrophoretic methods were carried out to validate their potential as anticancer agents. The cytotoxic activity of 'therapeutically promising' copper(II)-based drug candidate 2 was evaluated against MCF-7, MBA-MD-231, HeLa, HepG2, and Mia-PaCa-2 cancer cells via an SRB assay, and the results demonstrated 2 as a potent anticancer agent at low nanomolar concentrations against all tested cancer cells, preferably with a much superior anticancer efficacy against human pancreatic cancer cells.

Effect of chalcogen atoms on the electronic band gaps of the quinoxaline containing donor-acceptor-donor type semiconducting polymers: a systematic DFT investigation

CONTEXT

Due to the widely known positive contributions of the quinoxaline group in organic semiconductors, we conducted a fully computational study using quantum mechanical methods to investigate the effect of quinoxaline in the electron acceptor unit with the combination of different chalcogen atoms on the band gap of a series of donor-acceptor-donor type conjugated polymers. Using density functional theory, we mainly calculated the electronic band gap values of the structures containing four different chalcogen atoms (O, S, Se, and Te) in the electron donor and acceptor units. While chalcogendiazoloquinoxaline groups were used as the electron acceptor units, furan, thiophene, selenophene, and tellurophene were used as the donor units. Our theoretical results showed that the use of heavy chalcogen atoms in both donor and acceptor units resulted in a low band gap. Besides this, the effect of heavy chalcogen atoms used in the electron donor units is much more pronounced compared to the ones used in the acceptor units. More importantly, our findings proved that the inclusion of the chalcogendiazoloquinoxaline group instead of benzochalcogenadiazole as the acceptor unit significantly decreases the electronic band gap of the conjugated polymer. The lowest band gap was found to be 0.10 eV for the 4,9-di(tellurophen-2-yl)-[1,2,5]telluradiazolo[3,4-g]quinoxaline polymer.

METHODS

Conformational analysis of the monomers and their corresponding oligomers was performed at the B3LYP/LANL2DZ level of theory. Then, long-range corrected hybrid functional LC-BLYP in a combination with the LANL2DZ basis set was utilized for the calculation of electronic properties and HOMO and LUMO energy gaps of monomers and oligomers through the reoptimization of the lowest energy conformers obtained from the B3LYP/LANL2DZ calculations in the previous step. All energy minimum structures were confirmed through vibrational frequency analysis at both calculation levels. The Gaussian 09 rev. D.01 software was used for all calculations, and GaussView 5.0.9 for visualizations.

Novel isatin-triazole based thiosemicarbazones as potential anticancer agents: synthesis, DFT and molecular docking studies

Thiosemicarbazones of isatin have been found to exhibit versatile bioactivities. In this study, two distinct types of isatin-triazole hybrids 3a and 3b were accessed via copper-catalyzed azide-alkyne cycloaddition reaction (CuAAC), together with their mono and bis-thiosemicarbazone derivatives 4a-h and 5a-h. In addition to the characterization by physical, spectral and analytical data, a DFT study was carried out to obtain the optimized geometries of all thiosemicarbazones. The global reactivity values showed that among the synthesized derivatives, 4c, 4g and 5c having nitro substituents are the most soft compounds, with compound 5c having the highest electronegativity and electrophilicity index values among the synthesized series, thus possessing strong binding ability with biomolecules. Molecular docking studies were performed to explore the inhibitory ability of the selected compounds against the active sites of the anticancer protein of phosphoinositide 3-kinase (PI3K). Among the synthesized derivatives, 4-nitro substituted bisthiosemicarbazone 5c showed the highest binding energy of -10.3 kcal mol-1. These findings demonstrated that compound 5c could be used as a favored anticancer scaffold via the mechanism of inhibition against the PI3K signaling pathways.

Prognostic Model Construction of Disulfidptosis-Related Genes and Targeted Anticancer Drug Research in Pancreatic Cancer

Pancreatic cancer stands as one of the most lethal malignancies, characterized by delayed diagnosis, high mortality rates, limited treatment efficacy, and poor prognosis. Disulfidptosis, a recently unveiled modality of cell demise induced by disulfide stress, has emerged as a critical player intricately associated with the onset and progression of various cancer types. It has emerged as a promising candidate biomarker for cancer diagnosis, prognosis assessment, and treatment strategies. In this study, we have effectively established a prognostic risk model for pancreatic cancer by incorporating multiple differentially expressed long non-coding RNAs (DElncRNAs) closely linked to disulfide-driven cell death. Our investigation delved into the nuanced relationship between the DElncRNA-based predictive model for disulfide-driven cell death and the therapeutic responses to anticancer agents. Our findings illuminate that the high-risk subgroup exhibits heightened susceptibility to the small molecule compound AZD1208, positioning it as a prospective therapeutic agent for pancreatic cancer. Finally, we have elucidated the underlying mechanistic potential of AZD1208 in ameliorating pancreatic cancer through its targeted inhibition of the peroxisome proliferator-activated receptor-γ (PPARG) protein, employing an array of comprehensive analytical methods, including molecular docking and molecular dynamics (MD) simulations. This study explores disulfidptosis-related genes, paving the way for the development of targeted therapies for pancreatic cancer and emphasizing their significance in the field of oncology. Furthermore, through computational biology approaches, the drug AZD1208 was identified as a potential treatment targeting the PPARG protein for pancreatic cancer. This discovery opens new avenues for exploring targets and screening drugs for pancreatic cancer.

Synthesis, crystal structure and in-silico evaluation of arylsulfonamide Schiff bases for potential activity against colon cancer

This report presents a comprehensive investigation into the synthesis and characterization of Schiff base compounds derived from benzenesulfonamide. The synthesis process, involved the reaction between N-cycloamino-2-sulfanilamide and various substituted o-salicylaldehydes, resulted in a set of compounds that were subjected to rigorous characterization using advanced spectral techniques, including 1H NMR, 13C NMR and FT-IR spectroscopy, and single-crystal X-ray diffraction. Furthermore, an in-depth assessment of the synthesized compounds was conducted through Absorption, Distribution, Metabolism, Excretion and Toxicity (ADMET) analysis, in conjunction with docking studies, to elucidate their pharmacokinetic profiles and potential. Impressively, the ADMET analysis showcased encouraging drug-likeness properties of the newly synthesized Schiff bases. These computational findings were substantiated by molecular properties derived from density functional theory (DFT) calculations using the B3LYP/6-31G* method within the Jaguar Module of Schrödinger 2023-2 from Maestro (Schrodinger LLC, New York, USA). The exploration of frontier molecular orbitals (HOMO and LUMO) enabled the computation of global reactivity descriptors (GRDs), encompassing charge separation (Egap) and global softness (S). Notably, within this analysis, one Schiff base, namely, 4-bromo-2-{N-[2-(pyrrolidine-1-sulfonyl)phenyl]carboximidoyl}phenol, 20, emerged with the smallest charge separation (ΔEgap = 3.5780 eV), signifying heightened potential for biological properties. Conversely, 4-bromo-2-{N-[2-(piperidine-1-sulfonyl)phenyl]carboximidoyl}phenol, 17, exhibited the largest charge separation (ΔEgap = 4.9242 eV), implying a relatively lower propensity for biological activity. Moreover, the synthesized Schiff bases displayed remarkeable inhibition of tankyrase poly(ADP-ribose) polymerase enzymes, integral in colon cancer, surpassing the efficacy of a standard drug used for the same purpose. Additionally, their bioavailability scores aligned closely with established medications such as trifluridine and 5-fluorouracil. The exploration of molecular electrostatic potential through colour mapping delved into the electronic behaviour and reactivity tendencies intrinsic to this diverse range of molecules.

The Case for a Defect Genome Initiative

The Materials Genome Initiative (MGI) has streamlined the materials discovery effort by leveraging generic traits of materials, with focus largely on perfect solids. Defects such as impurities and perturbations, however, drive many attractive functional properties of materials. The rich tapestry of charge, spin, and bonding states hosted by defects are not accessible to elements and perfect crystals, and defects can thus be viewed as another class of "elements" that lie beyond the periodic table. Accordingly, a Defect Genome Initiative (DGI) to accelerate functional defect discovery for energy, quantum information, and other applications is proposed. First, major advances made under the MGI are highlighted, followed by a delineation of pathways for accelerating the discovery and design of functional defects under the DGI. Near-term goals for the DGI are suggested. The construction of open defect platforms and design of data-driven functional defects, along with approaches for fabrication and characterization of defects, are discussed. The associated challenges and opportunities are considered and recent advances towards controlled introduction of functional defects at the atomic scale are reviewed. It is hoped this perspective will spur a community-wide interest in undertaking a DGI effort in recognition of the importance of defects in enabling unique functionalities in materials.

Strategies to Improve the Quantum Computation Accuracy for Electrochemical Windows of Ionic Liquids

Rational design of ionic liquids (ILs) with wide electrochemical windows (ECWs) for high-voltage cathodes is essential to elevating the energy density of current rechargeable batteries. It is significant to determine appropriate strategies for accurately predicting the ECWs of ILs. In this study, we compare the calculated ECWs based on three quantum methods, including the highest occupied molecular orbital-lowest unoccupied molecular orbital (HOMO-LUMO) method, the ionization potential-electron affinity (IP-EA) method, and the thermodynamic method, under four unique combinations of simulation environments, and assess the discrepancies between the calculated and the experimental results of ECWs. For the three quantum methods, although HOMO-LUMO and IP-EA methods show limited prediction accuracy compared to the experimental values, they can qualitatively rank the anodic limits of anions and the cathodic limits of cations. For the thermodynamic method, we demonstrate that the highest accuracy can be achieved by considering the most rational redox reaction process. By varying the calculation environments, the calculated ECWs tend to be underestimated by considering separate cations and anions of ILs under gas phase, whereas they always exhibit overestimated results when calculating based on the cation-anion pairs. When the computation considers isolated ions with the solvent model plus proper thermodynamic corrections, we observe improved consistency with the experimental results. Though all methods have limitations to achieving perfect predictions of ECWs, we believe rational selection of calculation methods based on application-oriented scenarios can balance the efficiency and accuracy of the results for the development of a high-throughput and accurate database of ECWs for ILs.

Machine Learning Models for Predicting Zirconocene Properties and Barriers

Zr metallocenes have significant potential to be highly tunable polyethylene catalysts through modification of the aromatic ligand framework. Here we report the development of multiple machine learning models using a large library (>700 systems) of DFT-calculated zirconocene properties and barriers for ethylene polymerization. We show that very accurate machine learning models are possible for HOMO-LUMO gaps of precatalysts but the performance significantly depends on the machine learning algorithm and type of featurization, such as fingerprints, Coulomb matrices, smooth overlap of atomic positions, or persistence images. Surprisingly, the description of the bonding hapticity, the number of direct connections between Zr and the ligand aromatic carbons, only has a moderate influence on the performance of most models. Despite robust models for HOMO-LUMO gaps, these types of machine learning models based on structure connectivity type features perform poorly in predicting ethylene migratory insertion barrier heights. Therefore, we developed several relatively robust and accurate machine learning models for barrier heights that are based on quantum-chemical descriptors (QCDs). The quantitative accuracy of these models depends on which potential energy surface structure QCDs were harvested from. This revealed a Hammett-type principle to naturally emerge showing that QCDs from the π-coordination complexes provide much better descriptions of the transition states than other potential-energy structures. Feature importance analysis of the QCDs provides several fundamental principles that influence zirconocene catalyst reactivity.

Invariant Molecular Representations for Heterogeneous Catalysis

Catalyst screening is a critical step in the discovery and development of heterogeneous catalysts, which are vital for a wide range of chemical processes. In recent years, computational catalyst screening, primarily through density functional theory (DFT), has gained significant attention as a method for identifying promising catalysts. However, the computation of adsorption energies for all likely chemical intermediates present in complex surface chemistries is computationally intensive and costly due to the expensive nature of these calculations and the intrinsic idiosyncrasies of the methods or data sets used. This study introduces a novel machine learning (ML) method to learn adsorption energies from multiple DFT functionals by using invariant molecular representations (IMRs). To do this, we first extract molecular fingerprints for the reaction intermediates and later use a Siamese-neural-network-based training strategy to learn invariant molecular representations or the IMR across all available functionals. Our Siamese network-based representations demonstrate superior performance in predicting adsorption energies compared with other molecular representations. Notably, when considering mean absolute values of adsorption energies as 0.43 eV (PBE-D3), 0.46 eV (BEEF-vdW), 0.81 eV (RPBE), and 0.37 eV (scan+rVV10), our IMR method has achieved the lowest mean absolute errors (MAEs) of 0.18 0.10, 0.16, and 0.18 eV, respectively. These results emphasize the superior predictive capacity of our Siamese network-based representations. The empirical findings in this study illuminate the efficacy, robustness, and dependability of our proposed ML paradigm in predicting adsorption energies, specifically for propane dehydrogenation on a platinum catalyst surface.

Copper(II)-photocatalyzed Hydrocarboxylation of Schiff bases with CO2: antimicrobial evaluation and in silico studies of Schiff bases and unnatural α-amino acids

We synthesized and characterized two copper(II) complexes: [CuL2Cl]Cl and [CuL'2Cl]Cl, where L = 2,2'-bipyridine and L' = 4,4'-dimethyl-2,2'-bipyridine. We evaluated their photocatalytic hydrocarboxylation properties on a series of synthesized Schiff bases (SBs): (E)-1-(4-((5-bromo-2-hydroxybenzylidene)amino)phenyl)ethanone (SB1), (E)-N-(4-(dimethylamino)benzylidene)benzo[d]thiazol-2-amine (SB2), (E)-4-Bromo-2-((thiazol-2-ylimino)methyl)phenol (SB3), and (E)-4-((5-bromo-2-hydroxybenzylidene)amino)-1,5-dimethyl-2-phenyl-1H-pyrazol-3(2H)-one (SB4). Under mild photocatalytic reaction conditions (room temperature, 1 atm CO2, 30-watt Blue LED light), the derivatives of α-amino acids UAA1-4 were obtained with yields ranging from 5% to 44%. Experimental results demonstrated that [CuL2Cl]Cl exhibited superior photocatalytic efficiency compared to [CuL'2Cl]Cl, attributed to favourable electronic properties. In silico studies revealed strong binding strengths with E. faecalis DHFR (4M7U) for docked Schiff bases (SB) and unnatural α-amino acids (UAAs). In vitro studies further demonstrated significant antimicrobial and antifungal activity for SB2, SB3, and SB4, while none of the synthesized UAAs exhibited such properties, primarily due to the electronic and binding properties of these molecules.Communicated by Ramaswamy H. Sarma.

Formulation Graphs for Mapping Structure-Composition of Battery Electrolytes to Device Performance

Advanced computational methods are being actively sought to address the challenges associated with the discovery and development of new combinatorial materials, such as formulations. A widely adopted approach involves domain-informed high-throughput screening of individual components that can be combined together to form a formulation. This manages to accelerate the discovery of new compounds for a target application but still leaves the process of identifying the right "formulation" from the shortlisted chemical space largely a laboratory experiment-driven process. We report a deep learning model, the Formulation Graph Convolution Network (F-GCN), that can map the structure-composition relationship of the formulation constituents to the property of liquid formulation as a whole. Multiple GCNs are assembled in parallel that featurize formulation constituents domain-intuitively on the fly. The resulting molecular descriptors are scaled based on the respective constituent's molar percentage in the formulation, followed by integration into a combined formulation descriptor that represents the complete formulation to an external learning architecture. The use case of the proposed formulation learning model is demonstrated for battery electrolytes by training and testing it on two exemplary data sets representing electrolyte formulations vs battery performance: one data set is sourced from the literature about Li/Cu half-cells, while the other is obtained by lab experiments related to lithium-iodide full-cell chemistry. The model is shown to predict performance metrics such as Coulombic efficiency (CE) and specific capacity of new electrolyte formulations with the lowest reported errors. The best-performing F-GCN model uses molecular descriptors derived from molecular graphs (GCNs) that are informed with HOMO-LUMO and electric moment properties of the molecules using a knowledge transfer technique.

Deep learning workflow for the inverse design of molecules with specific optoelectronic properties

The inverse design of novel molecules with a desirable optoelectronic property requires consideration of the vast chemical spaces associated with varying chemical composition and molecular size. First principles-based property predictions have become increasingly helpful for assisting the selection of promising candidate chemical species for subsequent experimental validation. However, a brute-force computational screening of the entire chemical space is decidedly impossible. To alleviate the computational burden and accelerate rational molecular design, we here present an iterative deep learning workflow that combines (i) the density-functional tight-binding method for dynamic generation of property training data, (ii) a graph convolutional neural network surrogate model for rapid and reliable predictions of chemical and physical properties, and (iii) a masked language model. As proof of principle, we employ our workflow in the iterative generation of novel molecules with a target energy gap between the highest occupied molecular orbital (HOMO) and the lowest unoccupied molecular orbital (LUMO).

PubChemQC B3LYP/6-31G*//PM6 Data Set: The Electronic Structures of 86 Million Molecules Using B3LYP/6-31G* Calculations

The presented "PubChemQC B3LYP/6-31G*//PM6" data set is composed of the electronic properties of 85,938,443 molecules, encompassing a broad spectrum of molecules from essential compounds to biomolecules with a molecular weight up to 1000. These molecules account for 94.0% of the original PubChem Compound catalog as of August 29, 2016. The electronic properties, including orbitals, orbital energies, total energies, dipole moments, and other pertinent properties, were computed by using the B3LYP/6-31G* and PM6 methods. The data set, available in three formats, namely, GAMESS quantum chemistry program files, selected JSON output files, and a PostgreSQL database, provides researchers with the ability to query molecular properties. It is further subdivided into five subdata sets for more specific data. The first two subsets encompass molecules with carbon, hydrogen, oxygen, and nitrogen with molecular weights under 300 and 500, respectively. The third and fourth subsets incorporate molecules with carbon, hydrogen, nitrogen, oxygen, phosphorus, sulfur, fluorine, and chlorine, with molecular weights under 300 and 500, respectively. The fifth subset comprises molecules with carbon, hydrogen, nitrogen, oxygen, phosphorus, sulfur, fluorine, chlorine, sodium, potassium, magnesium, and calcium, with a molecular weight of under 500. The coefficients of determination for the highest occupied molecular orbital-lowest unoccupied molecular orbital energy gap range from 0.892 (for CHON500) to 0.803 (for the whole data set). These comprehensive results pave the way for applications in drug discovery and materials science, among others. The data sets can be accessed under the Creative Commons Attribution 4.0 International license at the following web address: https://nakatamaho.riken.jp/pubchemqc.riken.jp/b3lyp_pm6_datasets.html.

QSAR analysis of five generations of cephalosporins to establish the structural basis of activity against methicillin-resistant and methicillin-sensitive Staphylococcus aureus

Solving the worldwide problem of growing bacterial drug resistance will require a short-run and medium-term strategy. Structure-activity relationship (SAR) and quantitative SAR (QSAR) analyses have recently been utilized to reveal the molecular basis of the antibacterial activity and antibacterial spectrum of penicillins, the use of which is no longer solely empirical. Likewise, a more rational drug design can be achieved with cephalosporins, the largest group of β-lactam antibiotics. The current contribution aimed to establish the molecular and physicochemical basis of the antibacterial activity of five generations of cephalosporins on methicillin-sensitive (MSSA) and methicillin-resistant Staphylococcus aureus (MRSA). With SAR and QSAR analyses, the molecular portions that provide essential and additional antibacterial activity were identified. The substitutions with greater volume and polarity on the R2 side chain of the cephem nucleus increase potency on MSSA. The best effect is produced by substitutions with polar nitrogen atoms at the alpha-carbon (Cα). Substitutions with greater volume and polarity on the R1 side chain further enhance antibacterial activity. In contrast, the effect against MRSA seems to be independent of any substitution on R2 or at the Cα, while depending on the accessory portions with greater volume and polarity on R1.

First Principles Study of the Photoelectric Properties of Alkaline Earth Metal (Be/Mg/Ca/Sr/Ba)-Doped Monolayers of MoS2

The energy band structure, density of states, and optical properties of monolayers of MoS2 doped with alkaline earth metals (Be/Mg/Ca/Sr/Ba) are systematically studied based on first principles. The results indicate that all the doped systems have a great potential to be formed and structurally stable. In comparison to monolayer MoS2, doping alkaline earth metals results in lattice distortions in the doped system. Therefore, the recombination of photogenerated hole-electron pairs is suppressed effectively. Simultaneously, the introduction of dopants reduces the band gap of the systems while creating impurity levels. Hence, the likelihood of electron transfer from the valence to the conduction band is enhanced, which means a reduction in the energy required for such a transfer. Moreover, doping monolayer MoS2 with alkaline earth metals increases the static dielectric constant and enhances its polarizability. Notably, the Sr-MoS2 system exhibits the highest value of static permittivity, demonstrating the strongest polarization capability. The doped systems exhibit a red-shifted absorption spectrum in the low-energy region. Consequently, the Be/Mg/Ca-MoS2 systems demonstrate superior visible absorption properties and a favorable band gap, indicating their potential as photo-catalysts for water splitting.

Machine Learning Frontier Orbital Energies of Nanodiamonds

Nanodiamonds have a wide range of applications including catalysis, sensing, tribology, and biomedicine. To leverage nanodiamond design via machine learning, we introduce the new data set ND5k, consisting of 5089 diamondoid and nanodiamond structures and their frontier orbital energies. ND5k structures are optimized via tight-binding density functional theory (DFTB) and their frontier orbital energies are computed using density functional theory (DFT) with the PBE0 hybrid functional. From this data set we derive a qualitative design suggestion for nanodiamonds in photocatalysis. We also compare recent machine learning models for predicting frontier orbital energies for similar structures as they have been trained on (interpolation on ND5k), and we test their abilities to extrapolate predictions to larger structures. For both the interpolation and extrapolation task, we find the best performance using the equivariant message passing neural network PaiNN. The second best results are achieved with a message passing neural network using a tailored set of atomic descriptors proposed here.

Quantum Chemistry-Machine Learning Approach for Predicting Properties of Lewis Acid-Lewis Base Adducts

Synthetic design allowing predictive control of charge transfer and other optoelectronic properties of Lewis acid adducts remains elusive. This challenge must be addressed through complementary methods combining experimental with computational insights from first principles. Ab initio calculations for optoelectronic properties can be computationally expensive and less straightforward than those sufficient for simple ground-state properties, especially for adducts of large conjugated molecules and Lewis acids. In this contribution, we show that machine learning (ML) can accurately predict density functional theory (DFT)-calculated charge transfer and even properties associated with excited states of adducts from readily obtained molecular descriptors. Seven ML models, built from a dataset of over 1000 adducts, show exceptional performance in predicting charge transfer and other optoelectronic properties with a Pearson correlation coefficient of up to 0.99. More importantly, the influence of each molecular descriptor on predicted properties can be quantitatively evaluated from ML models. This contributes to the optimization of a priori design of Lewis adducts for future applications, especially in organic electronics.

Density Functional Theory, Molecular Dynamics and AlteQ Studies Approaches of Baimantuoluoamide A and Baimantuoluoamide B to Identify Potential Inhibitors of Mpro Proteins: a Novel Target for the Treatment of SARS COVID-19

COVID-19 has resulted in epidemi conditions over the world. Despite efforts by scientists from all over the world to develop an effective va ine against this virus, there is presently no recognized cure for COVID-19. The most succeed treatments for various ailments come from natural components found in medicinal plants, which are also rucial for the development of new medications. This study intends to understand the role of the baimantuoluoamide A and baimantuoluoamide B molecules in the treatment of Covid19. Initially, density functional theory (DFT) used to explore their electronic potentials along with the Becke3-Lee-Yang-Parr (B3LYP) 6-311 + G(d, p) basis set. A number of characteristics, including the energy gap, hardness, local softness, electronegativity, and electrophilicity, have also been calculated to discuss the reactivity of mole ules. Using natural bond orbital, the title compound's bioactive nature and stability were investigated. Further, both compounds potential inhibitors with main protease (Mpro) proteins, molecular dynamics simulations and AlteQ investigations also studied.

Supplementary Information

The online version contains supplementary material available at 10.1134/S0021364023600039.

Quantitative Prediction of Inorganic Nanomaterial Cellular Toxicity via Machine Learning

Organic chemistry has seen colossal progress due to machine learning (ML). However, the translation of artificial intelligence (AI) into materials science is challenging, where biological behavior prediction becomes even more complicated. Nanotoxicity is a critical parameter that describes their interaction with the living organisms screened in every bio-related research. To prevent excessive experiments, such properties have to be pre-evaluated. Several existing ML models partially fulfill the gap by predicting whether a nanomaterial is toxic or not. Yet, this binary categorization neglects the concentration dependencies crucial for experimental scientists. Here, an ML-based approach is proposed to the quantitative prediction of inorganic nanomaterial cytotoxicity achieving the precision expressed by 10-fold cross-validation (CV) Q²  = 0.86 with the root mean squared error (RMSE) of 12.2% obtained by the correlation-based feature selection and grid search-based model hyperparameters optimization. To provide further model flexibility, quantitative atom property-based nanomaterial descriptors are introduced allowing the model to extrapolate on unseen samples. Feature importance is calculated to find an interpretable model with optimal decision-making. These findings allow experimental scientists to perform primary in silico candidate screening and minimize the number of excessive, labor-intensive experiments enabling the rapid development of nanomaterials for medicinal purposes.

Traceability of bilberries (Vaccinium myrtillus L.) of the Baltic-Nordic region using surface-enhanced Raman spectroscopy (SERS): DFT simulation-based DNA analysis

Food traceability is a major issue in the industry. We investigated whether bilberries (Vaccinium myrtillus L.) from 4 different locations within the Baltic-Nordic region could be effectively differentiated using surface-enhanced Raman scattering (SERS) based spectral data and chemometric analyses. Furthermore, we aimed to determine if nucleobase (adenine and cytosine) methylation could be responsible for any observed variation. Our experiment was successful in that both principal component (PCA) and discriminant function analyses (DFA) showed differentiation between bilberry DNA from all 4 geographical regions. Density functional theory (DFT) based simulations allowed us to analyze whether DNA's spectral data dissimilarities may be due to nucleobase methylation. Although results were inconclusive on this, our investigation provides valuable data on simulated versus experimental DNA and DNA component spectra. Further research will be directed towards understanding what other epigenetic changes could be responsible for the observed DNA variation as well as determining the optimal parameters for using DFT simulations in upcoming projects.

Generative model based on junction tree variational autoencoder for HOMO value prediction and molecular optimization

In this work, we provide further development of the junction tree variational autoencoder (JT VAE) architecture in terms of implementation and application of the internal feature space of the model. Pretraining of JT VAE on a large dataset and further optimization with a regression model led to a latent space that can solve several tasks simultaneously: prediction, generation, and optimization. We use the ZINC database as a source of molecules for the JT VAE pretraining and the QM9 dataset with its HOMO values to show the application case. We evaluate our model on multiple tasks such as property (value) prediction, generation of new molecules with predefined properties, and structure modification toward the property. Across these tasks, our model shows improvements in generation and optimization tasks while preserving the precision of state-of-the-art models.

Ab initio methods for the computation of physical properties and performance parameters of electrochemical energy storage devices

With the rapid development of electric vehicles and mobile technologies, there is a high demand for electrochemical energy storage devices and electrochemical energy conversion devices. Devices meeting these needs include metal-ion batteries (MIBs), supercapacitors (SCs), electrochromic devices (ECDs), and multifunctional devices such as electrochromic batteries and supercapatteries. Currently, the goal has been the enhancement of operational parameters and physical properties that results in a higher performance of these devices. In the case of batteries, SCs, and supercapatteries, scientists seek to improve the equilibrium voltage, energy density, power, capacitance, and charge rate. In the case of ECDs, the focus is on improvement of the optical modulation and coloration efficiency. However, synthesis and characterization of new materials, or of materials with optimized properties, is time consuming and highly expensive. Computational simulation of materials can expedite the experimental endeavor by modelling novel atomic structures and predicting device performance. This is possible using ab initio theories and applying physical principles that allow us to understand the underlying mechanisms governing the behavior of materials in these devices. Taking as a point of departure density functional theory (DFT), in this review, we discuss the first principles methods used for the computation of physical properties and performance parameters of electrochemical energy storage devices. A wide coverage of DFT is given, dealing with the strengths and weaknesses of the most popular functionals used in the field of electrochemical energy storage. With these tools, ab initio methods for the computation of basic properties such as effective mass, mobility, optical band gap, transmissivity, conductivity (ionic and electronic), and criteria for structure stability (cohesive energy, formation energy, adsorption energy, and phonon frequency) are addressed. We also highlight the first principles techniques for the calculation of performance parameters in MIBs, SCs, and ECDs.

Deep transfer learning for predicting frontier orbital energies of organic materials using small data and its application to porphyrin photocatalysts

A deep transfer learning approach is used to predict HOMO/LUMO energies of organic materials with a small amount of training data.

Machine Learning to Predict Homolytic Dissociation Energies of C-H Bonds: Calibration of DFT-based Models with Experimental Data

Random Forest (RF) QSPR models were developed with a data set of homolytic bond dissociation energies (BDE) previously calculated by B3LYP/6-311++G(d,p)//DFTB for 2263 sp3C-H covalent bonds. The best set of attributes consisted in 114 descriptors of the carbon atom (counts of atom types in 5 spheres around the kernel atom and ring descriptors). The optimized model predicted the DFT-calculated BDE of an independent test set of 224 bonds with MAE=2.86 kcal/mol. A new data set of 409 bonds from the iBonD database (http://ibond.nankai.edu.cn) was predicted by the RF with a modest MAE (5.36 kcal/mol) but a relatively high R² (0.75) against experimental energies. A prediction scheme was explored that corrects the RF prediction with the average deviation observed for the k nearest neighbours (KNN) in an additional memory of experimental data. The corrected predictions achieved MAE=2.22 kcal/mol for an independent test set of 145 bonds and the corresponding experimental bond energies.

Halogen Doping to Control the Band Gap of Ascorbic Acid: A Theoretical Study

Ascorbic acid is an important antioxidant agent that acts as an electron donor and is involved in many physiological processes. Structural modification in ascorbic acid is a subject of extensive biochemical research due to its involvement in a variety of relevant phenomena including electron transport, complex redox reactions, neurochemical reactions, enzymatic reactions, and chemotherapeutic potential. In this work, the structure of ascorbic acid is modified via doping with the first three members of the halogen group to investigate the changes in the electronic structure and spectroscopic parameters using first-principles methods. To obtain the lowest-energy structures, different basis sets in density functional theory (DFT) and Hartree-Fock approaches were employed in the geometry optimization process. The potential energy maps of the structures were computed to study the molecular orientations and their optical and electrical properties. The spectroscopic properties were computed via UV-vis and nuclear magnetic resonance (NMR) spectroscopies to study the effects of doping into the compound. To obtain further insights into the chemical structure, the Fourier transform infrared (FT-IR) spectra of the materials were theoretically investigated. It was found that the band gap is sensitive to doping as we moved from fluorine to chlorine and then to bromine.

Not from Scratch: Predicting Thermophysical Properties through Model-Based Transfer Learning Using Graph Convolutional Networks

In this study, a framework for the prediction of thermophysical properties based on transfer learning from existing estimation models is explored. The predictive capabilities of conventional group-contribution methods and traditional machine-learning approaches rely heavily on the availability of experimental datasets and their uncertainty. Through the use of a pretraining scheme, which leverages the knowledge established by other estimation methods, improved prediction models for thermophysical properties can be obtained after fine-tuning networks with more accurate experimental data. As our experiments show, for the case of critical properties of compounds, this pipeline not only improves the performance of the models on commonly found organic structures but can also help these models generalize to less explored areas of chemical space, where experimental data is scarce, such as inorganics and heavier organic compounds. Transfer learning from estimation models data also allows for graph-based deep learning models to create more flexible molecular features over a bigger chemical space, which leads to improved predictive capabilities and can give insights into the relationship between molecular structures and thermophysical properties. The generated molecular features can discriminate behavior discrepancy between isomers without the need of additional parameters. Also, this approach shows better robustness to outliers in experimental datasets.

Selected machine learning of HOMO-LUMO gaps with improved data-efficiency

Despite their relevance for organic electronics, quantum machine learning (QML) models of molecular electronic properties, such as HOMO-LUMO-gaps, often struggle to achieve satisfying data-efficiency as measured by decreasing prediction errors for increasing training set sizes. We demonstrate that partitioning training sets into different chemical classes prior to training results in independently trained QML models with overall reduced training data needs. For organic molecules drawn from previously published QM7 and QM9-data-sets we have identified and exploited three relevant classes corresponding to compounds containing either aromatic rings and carbonyl groups, or single unsaturated bonds, or saturated bonds The selected QML models of band-gaps (considered at GW and hybrid DFT levels of theory) reach mean absolute prediction errors of ∼0.1 eV for up to an order of magnitude fewer training molecules than for QML models trained on randomly selected molecules. Comparison to Δ-QML models of band-gaps indicates that selected QML exhibit superior data-efficiency. Our findings suggest that selected QML, e.g. based on simple classifications prior to training, could help to successfully tackle challenging quantum property screening tasks of large libraries with high fidelity and low computational burden.

Machine learning the frontier orbital energies of SubPc based triads

Organic photovoltaic devices are promising candidates for efficient energy harvesting from sunlight. Designing new dye molecules suitable for such devices is a challenging task restricted by the rapid increase of computational cost with system size. Solar cell material properties are closely related to the electronic structure of the dye, and an effective molecular orbital energy screening method for a family of dyes is therefore desired. In this work, a machine learning approach is used to sort through the chemical space of peripheral double-substituted boron-Subphthalocyanine dyes. A database of 12,102 PM6 optimized structures was built and for each of the structures time-dependent density functional theory (LC-[Formula: see text]HPBE/6-31+G(d)) calculations were performed. We investigated the changes of the molecular orbital energies of the molecular orbitals related to reduction and oxidation of the compounds. With the Electrotopological-state index moleculear representation all the tested algorithms, Support Vector Machine, Random Forest Regression, Neural Network, and Simple Linear Regression, captured the calculated frontier orbital energies with a prediction root-mean-square-error in the order of 0.05 eV. Finally, frontier orbital energies were predicted for more than 40,000 new structures by the trained Support Vector Machine algorithm. Compared to the parent boron-Subphthalocyanine structure, 237 and 132 functionalized dyes were predicted to have upshifted molecular orbital energies using the Electrotopological-state index and OneHot encoding feature vector, respectively. Out of 27 investigated donor and acceptor ligands, the acetamide and hydroxyl ligands gave rise to the desired increase in frontier molecular orbital energy.

A fundamental study on selective extraction of Li+ with dibenzo-14-crown-4 ether: Toward new technology development for lithium recovery from brines

The present study has proposed a selective Li⁺ extraction process using a novel extractant of dibenzo-14-crown-4 ether functionalized with an alkyl C16 chain (DB14C4-C16) synthesized based on the ion imprinting technology (IIT). Theoretical analysis of the possible complexes formed by DB14C4-C16 with Li⁺ and the competing ions of Na⁺, K⁺, Ca²⁺ and Mg²⁺ was performed through density functional theory (DFT) modeling. The Gibbs free energy change of the complexes of metal ions with DB14C4-C16 and water molecules were calculated to be -125.81 and -166.01 kJ/mol for lithium, -55.73 and -117.77 kJ/mol for sodium, and -196.02 and -291.52 kJ/mol for magnesium, respectively. Furthermore, the solvent extraction experiments were carried out in both single Li⁺ and multi-ions containing solutions, and the results delivered a good selectivity of DB14C4-C16 towards Li⁺ over the competing ions, showing separation coefficients of 68.09 for Ca²⁺-Li⁺, 24.53 for K⁺-Li⁺, 16.32 for Na⁺-Li⁺, and 3.99 for Mg²⁺-Li⁺ under the optimal conditions. The experimental results are generally in agreement with the theoretical calculations.

TorsionNet: A Deep Neural Network to Rapidly Predict Small-Molecule Torsional Energy Profiles with the Accuracy of Quantum Mechanics

Fast and accurate assessment of small-molecule dihedral energetics is crucial for molecular design and optimization in medicinal chemistry. Yet, accurate prediction of torsion energy profiles remains challenging as the current molecular mechanics (MM) methods are limited by insufficient coverage of drug-like chemical space and accurate quantum mechanical (QM) methods are too expensive. To address this limitation, we introduce TorsionNet, a deep neural network (DNN) model specifically developed to predict small-molecule torsion energy profiles with QM-level accuracy. We applied active learning to identify nearly 50k fragments (with elements H, C, N, O, F, S, and Cl) that maximized the coverage of our corporate compound library and leveraged massively parallel cloud computing resources for density functional theory (DFT) torsion scans of these fragments, generating a training data set of 1.2 million DFT energies. After training TorsionNet on this data set, we obtain a model that can rapidly predict the torsion energy profile of typical drug-like fragments with DFT-level accuracy. Importantly, our method also provides an uncertainty estimate for the predicted profiles without any additional calculations. In this report, we show that TorsionNet can accurately identify the preferred dihedral geometries observed in crystal structures. Our TorsionNet-based analysis of a diverse set of protein-ligand complexes with measured binding affinity shows a strong association between high ligand strain and low potency. We also present practical applications of TorsionNet that demonstrate how consideration of DNN-based strain energy leads to substantial improvement in existing lead discovery and design workflows. TorsionNet500, a benchmark data set comprising 500 chemically diverse fragments with DFT torsion profiles (12k MM- and DFT-optimized geometries and energies), has been created and is made publicly available.

Applying Neuromorphic Computing Simulation in Band Gap Prediction and Chemical Reaction Classification

The rapidly developing artificial intelligence (AI) requires revolutionary computing architectures to break the energy efficiency bottleneck caused by the traditional von Neumann computing architecture. In addition, the emerging brain-machine interface also requires computational circuitry that can conduct large parallel computational tasks with low energy cost and good biocompatibility. Neuromorphic computing, a novel computational architecture emulating human brains, has drawn significant interest for the aforementioned applications due to its low energy cost, capability to parallelly process large-scale data, and biocompatibility. Most efforts in the domain of neuromorphic computing focus on addressing traditional AI problems, such as handwritten digit recognition and file classification. Here, we demonstrate for the first time that current neuromorphic computing techniques can be used to solve key machine learning questions in cheminformatics. We predict the band gaps of small-molecule organic semiconductors and classify chemical reaction types with a simulated neuromorphic circuitry. Our work can potentially guide the design and fabrication of elementary devices and circuitry for neuromorphic computing specialized for chemical purposes.

Machine Learning-Assisted Development of Organic Solar Cell Materials: Issues, Analyses, and Outlooks

Nonfullerene, a small molecular electron acceptor, has substantially improved the power conversion efficiency of organic photovoltaics (OPVs). However, the large structural freedom of π-conjugated polymers and molecules makes it difficult to explore with limited resources. Machine learning, which is based on rapidly growing artificial intelligence technology, is a high-throughput method to accelerate the speed of material design and process optimization; however, it suffers from limitations in terms of prediction accuracy, interpretability, data collection, and available data (particularly, experimental data). This recognition motivates the present Perspective, which focuses on utilizing the experimental data set for ML to efficiently aid OPV research. This Perspective discusses the trends in ML-OPV publications, the NFA category, and the effects of data size and explanatory variables (fingerprints or Mordred descriptors) on the prediction accuracy and explainability, which broadens the scope of ML and would be useful for the development of next-generation solar cell materials.

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.

Machine learning methods to predict the cultivation age of Panacis Quinquefolii Radix

Background

American ginseng (AG) is a valuable medicine widely consumed as a herbal remedy throughout the world. Huge price difference among AG with different growth years leads to intentional adulteration for higher profits. Thus, developing reliable approaches to authenticate the cultivation ages of AG products is of great use in preventing age falsification.

Methods

A total of 106 batches of AG samples along with their 9 physicochemical features were collected and measured from experiments, which was then split into a training set and two test sets (test set 1 and 2) according to the cultivation regions. Principle component analysis (PCA) was carried out to examine the distribution of the three data sets. Four machine learning (ML) algorithms, namely elastic net, k-nearest neighbors, support vector machine and multi-layer perception (MLP) were employed to construct predictive models using the features as inputs and their growth years as outputs. In addition, a similarity-based applicability domain (AD) was defined for these models to ensure the reliability of the predictive results for AG samples produced in different regions.

Results

A positive correlation was observed between the several features and the growth years. PCA revealed diverse distributions among different cultivation regions. The most accurate model derived from MLP shows good prediction power for the fivefold cross validation and the test set 1 with mean square error (MSE) of 0.017 and 0.016 respectively, but a higher MSE value of 1.260 for the test set 2. After applying the AD, all models showed much lower prediction errors for the test samples within AD (IDs) than those outside the AD (ODs). MLP remains the best predictive model with an MSE value of 0.030 for the IDs.

Conclusion

Cultivation years have a close relationship with bioactive components of AG. The constructed models and AD are also able to predict the cultivation years and discriminate samples that have inaccurate prediction results. The AD-equipped models used in this study provide useful tools for determining the age of AG in the market and are freely available at https://github.com/dreadlesss/Panax_age_predictor.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13020-021-00511-5.

Direct Synthesis of Diamides from Dicarboxylic Acids with Amines Using Nb2O5 as a Lewis Acid Catalyst and Molecular Docking Studies as Anticancer Agents

Several Lewis and Bronsted acid catalysts were tested for the synthesis of some targeted diamides with anticancer activity from dicarboxylic acids and amines under the same reaction condition. Among those catalysts, Nb₂O₅ showed the highest catalytic activity to the corresponding diamides. Nb₂O₅ shows water- and base-tolerant properties for which it gives the highest yield of the synthesized products. Here, we present a novel and sustainable method for the direct synthesis of diamides with anticancer activity using a reusable heterogeneous catalyst Nb₂O₅. A molecular docking study was performed for all of the synthesized compounds with various therapeutical targets of cancer and found that the human epidermal growth factor receptor (HER2) has shown a significant dock score for our synthesized products. After obtaining the best pose from molecular docking, the complex is used for molecular dynamics study by running simulations for 10 ns. The root-mean-square deviations (RMSDs) of α carbon atoms of all systems are analyzed to detect their stability. This method is effective for the direct synthesis of diamides as anticancer agents from dicarboxylic acids and amines using Nb₂O₅ as a base-tolerant heterogeneous catalyst.

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.

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.

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.

Vibronic and Environmental Effects in Simulations of Optical Spectroscopy

Including both environmental and vibronic effects is important for accurate simulation of optical spectra, but combining these effects remains computationally challenging. We outline two approaches that consider both the explicit atomistic environment and the vibronic transitions. Both phenomena are responsible for spectral shapes in linear spectroscopy and the electronic evolution measured in nonlinear spectroscopy. The first approach utilizes snapshots of chromophore-environment configurations for which chromophore normal modes are determined. We outline various approximations for this static approach that assumes harmonic potentials and ignores dynamic system-environment coupling. The second approach obtains excitation energies for a series of time-correlated snapshots. This dynamic approach relies on the accurate truncation of the cumulant expansion but treats the dynamics of the chromophore and the environment on equal footing. Both approaches show significant potential for making strides toward more accurate optical spectroscopy simulations of complex condensed phase systems.

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

The development of functional organic fluorescent materials calls for fast and accurate predictions of photophysical parameters for processes such as high-throughput virtual screening, while the task is challenged by the limitations of quantum mechanical calculations. We establish a database covering >4300 solvated organic fluorescent dyes with 3000 distinct compounds and develop a new machine learning approach aimed at efficient and accurate predictions of emission wavelength and photoluminescence quantum yield (PLQY). Our feature engineering has given rise to a functionalized structure descriptor (FSD) and a comprehensive general solvent descriptor (CGSD), whereby a highly black-box computational framework is realized with consistently good accuracy across different dye families, ability of describing substitution effects and solvent effects, efficiency for large-scale predictions, and workability with on-the-fly learning. Evaluations with unseen molecules suggest a remarkable mean absolute error of 0.13 for PLQY and 0.080 eV for emission energy, the latter comparable to time-dependent density functional theory (TD-DFT) calculations. An online prediction platform was constructed based on the ensemble model to make predictions in various solvents. Our statistical learning methodology will complement quantum mechanical calculations as an efficient alternative approach for the prediction of these parameters.