Transfer learning across different chemical domains: virtual screening of organic materials with deep learning models pretrained on small molecule and chemical reaction data

Machine learning is becoming a preferred method for the virtual screening of organic materials due to its cost-effectiveness over traditional computationally demanding techniques. However, the scarcity of labeled data for organic materials poses a significant challenge for training advanced machine learning models. This study showcases the potential of utilizing databases of drug-like small molecules and chemical reactions to pretrain the BERT model, enhancing its performance in the virtual screening of organic materials. By fine-tuning the BERT models with data from five virtual screening tasks, the version pretrained with the USPTO-SMILES dataset achieved R2 scores exceeding 0.94 for three tasks and over 0.81 for two others. This performance surpasses that of models pretrained on the small molecule or organic materials databases and outperforms three traditional machine learning models trained directly on virtual screening data. The success of the USPTO-SMILES pretrained BERT model can be attributed to the diverse array of organic building blocks in the USPTO database, offering a broader exploration of the chemical space. The study further suggests that accessing a reaction database with a wider range of reactions than the USPTO could further enhance model performance. Overall, this research validates the feasibility of applying transfer learning across different chemical domains for the efficient virtual screening of organic materials.Scientific contributionThis study verifies the feasibility of applying transfer learning to large language models in different chemical fields to help organic materials perform virtual screening. Through the comparison of transfer learning from different chemical fields to a variety of organic material molecules, the high precision virtual screening of organic materials is realized.

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.

Exploring Deep Learning for Metalloporphyrins: Databases, Molecular Representations, and Model Architectures

Metalloporphyrins have been studied as biomimetic catalysts for more than 120 years and have accumulated a large amount of data, which provides a solid foundation for deep learning to discover chemical trends and structure–function relationships. In this study, key components of deep learning of metalloporphyrins, including databases, molecular representations, and model architectures, were systematically investigated. A protocol to construct canonical SMILES for metalloporphyrins was proposed, which was then used to represent the two-dimensional structures of over 10,000 metalloporphyrins in an existing computational database. Subsequently, several state-of-the-art chemical deep learning models, including graph neural network-based models and natural language processing-based models, were employed to predict the energy gaps of metalloporphyrins. Two models showed satisfactory predictive performance (R2 0.94) with canonical SMILES as the only source of structural information. In addition, an unsupervised visualization algorithm was used to interpret the molecular features learned by the deep learning models.

Organic materials repurposing, a data set for theoretical predictions of new applications for existing compounds

We present a data set of 48182 organic semiconductors, constituted of molecules that were prepared with a documented synthetic pathway and are stable in solid state. We based our search on the Cambridge Structural Database, from which we selected semiconductors with a computational funnel procedure. For each entry we provide a set of electronic properties relevant for organic materials research, and the electronic wavefunction for further calculations and/or analyses. This data set has low bias because it was not built from a set of materials designed for organic electronics, and thus it provides an excellent starting point in the search of new applications for known materials, with a great potential for novel physical insight. The data set contains molecules used as benchmarks in many fields of organic materials research, allowing to test the reliability of computational screenings for the desired application, "rediscovering" well-known molecules. This is demonstrated by a series of different applications in the field of organic materials, confirming the potential for the repurposing of known organic molecules.

Effects of interfacial adsorption configurations on dye-sensitized solar cell performance at the stoichiometric and defective TiO2 anatase (101) surfaces: a theoretical investigation

Interfacial adsorption configuration plays a crucial role in influencing the photovoltaic performance of dye-sensitized solar cells (DSSCs), and thus, theoretical investigations are needed to further understand the impacts of different absorption configurations on stoichiometric and defective TiO2(101) surfaces on the short-circuit photocurrent density (JSC) and open-circuit voltage (VOC) of DSSCs. Herein, calculations of isolated dyes and dye/TiO2 systems were performed on the donor-π bridge-acceptor (D-π-A) type porphyrin sensitizers bearing different donor moieties and an α-cyanoacrylic acid anchoring group (T1-3), using DFT and TD-DFT methods. And, for the first time, comparative analysis of interfacial electron transfer (IET) and density of states (DOS) were carried out on dye/TiO2 systems with stoichiometric and defective surfaces to provide further insight into the electronic factors influencing the efficiency of DSSCs, which can well explain the experimental variation trends of JSC and VOC values. It turned out that attachment via the carboxyl and cynao groups in a tridentate binding mode can result in more efficient IET rates and an upshifted conduction band in comparison with those of the bidentate attachment. More interestingly, we found that the adsorption configuration on defective surfaces containing an O2c vacancy induced more upshifted CBM and relatively fast IET, especially for the bonding mode through two O atoms of the carboxyl group.

Accurate description of the electronic structure of organic semiconductors by GW methods

Electronic properties associated with charged excitations, such as the ionization potential (IP), the electron affinity (EA), and the energy level alignment at interfaces, are critical parameters for the performance of organic electronic devices. To computationally design organic semiconductors and functional interfaces with tailored properties for target applications it is necessary to accurately predict these properties from first principles. Many-body perturbation theory is often used for this purpose within the GW approximation, where G is the one particle Green's function and W is the dynamically screened Coulomb interaction. Here, the formalism of GW methods at different levels of self-consistency is briefly introduced and some recent applications to organic semiconductors and interfaces are reviewed.

Calculations of the light absorption spectra of porphyrinoid chromophores for dye-sensitized solar cells

Solar power is a strong alternative to the currently used fossil fuels in order to satisfy the world's energy needs. Among them, dye-sensitized solar cells (DSSC) represent a low-cost option. Efficient and cheap dyes are currently needed to make DSSCs competitive. Computational chemistry can be used to guide the design of new light-absorbing chromophores. Here, we have computationally studied the lowest excited states of ZnPBAT, which is a recently synthesized porphyrinoid chromophore with high light-absorption efficiency. The calculations have been performed at ab initio correlated levels of theory employing second-order coupled clusters (CC2) and algebraic diagrammatic construction using second order (ADC(2)) methods and by performing density functional theory (DFT) calculations using the time-dependent DFT (TDDFT) approach for excitation energies. The ultraviolet-visible (UV-vis) spectrum calculated at the ADC(2) and CC2 levels agrees well with the experimental one. The calculations show that ZnPBAT has six electronic transitions in the visible range of the absorption spectrum. The ab initio correlated calculations and previously reported experimental data have been used to assess the performance of several well-known density functionals that have been employed in the present TDDFT study. Solvent effects have been estimated by using the conductor-like screening model (COSMO). The influence of the addition of a TiO₂ cluster to the chromophore systems has also been investigated. The results indicate that both CAM-B3LYP and Becke's "half-and-half" (BHLYP) density functionals are appropriate for the studies of excitation energies in the blue range of the visible spectrum for these kinds of porphyrinoid chromophores, whereas the excitation energies of the Q band calculated at the ab initio correlated level are more accurate than those obtained in the present TDDFT calculations. The inclusion of solvent effects has a modest influence on the spectrum of the protonated form of the studied chromophores, whereas solvent models are crucial when studying the absorption spectrum of the anionic chromophore. The calculated UV-vis spectrum for the chromophore anion is not significantly affected by attaching a TiO₂ cluster to it.

Theoretical design of triphenylamine-based derivatives with asymmetric D-D-π-A configuration for dye-sensitized solar cells

The use of theoretical techniques in the structural development of dye-sensitized solar cells helps in the efficient screening of the dyes. To properly rationalize the dye's design process, benchmark calculations were conducted using long-range corrected exchange-correlation (xc) functionals with varying separation parameters to be able to predict the excited-state energies of triphenylamine-based dyes, namely: PPS, PSP, and PSS, wherein they differ at the π-conjugated bridge using thiophene and/or phenyl moieties. The results show that LC-ωPBE xc functional with an optimized parameter provided better correlation with the experimental results compared to the other functionals. The relative shifts of the absorption spectra, light harvesting efficiency, normal dipole moments, as well as the ionization potentials and electron affinities of the dyes were well-correlated with the experimental data. A new set of dyes was designed in an effort to increase its solar cell efficiency that was patterned after PSS with an additional donor moiety such as fluorene, cyclopentaindole, and pyrene attached asymmetrically at the triphenylamine ring. Among the newly designed dyes, analogs that contain 4-phenyl-1,2,3,4-tetrahydrocyclopenta[b]indole (I) and pyrido[2,3,4-5-imn]phenanthridine-5,10(4H,9H)-dione (P2) as the additional donor moiety produced the best photophysical properties and charge-transfer characteristics for a promising dye for solar cell applications.

Electronic state dependence of heterogeneous electron transfer: injection from the S1 and S2 state of phlorin into TiO2

Ultrafast time-resolved measurements were performed on a novel pentafluorophenyl substituted 5,5-dimethyl phlorin derivative in solution and when attached to TiO2 colloidal films. The complex excited state dynamics of this porphyrinoid after S1 and S2 excitation was compared at different wavelengths and can be assigned to several subsequent relaxation mechanisms. The difference between excited state dynamics in the free molecule and when attached to an electron accepting electrode was measured. For both cases the dynamics was compared after excitation to the S1 and the S2 state. For the free molecule in solution an intermediate relaxation step was identified and assigned to a buckling motion of the tetrapyrrole ring. On the electrode, heterogeneous electron transfer (HET) times from both states were very similar and around 50 fs. Surprisingly, the large difference in the density of acceptor states that are resonant with the respective donor level of the molecule does not significantly influence HET dynamics. This result indicates that HET proceeds into intermediate transition states that are different from steady state surface states obtained from experiments or computations. The density of states (DOS) of these transient acceptor states appears not to be directly related to the corresponding surface or bulk DOS.

Design of two-photon molecular tandem architectures for solar cells by ab initio theory

We present new two-photon molecular architectures for photovoltaics where atomic precision can be obtained by synthetic chemistry.

An extensive database of spectroscopic properties of molecules from ab initio calculations is used to design molecular complexes for use in tandem solar cells that convert two photons into a single electron–hole pair, thereby increasing the output voltage while covering a wider spectral range. Three different architectures are considered: the first two involve a complex consisting of two dye molecules with appropriately matched frontier orbitals, connected by a molecular diode. Optimized combinations of dye molecules are determined by taking advantage of our computational database of the structural and energetic properties of several thousand porphyrin dyes. The third design is a molecular analogy of the intermediate band solar cell, and involves a single dye molecule with strong intersystem crossing to ensure a long lifetime of the intermediate state. Based on the calculated energy levels and molecular orbitals, energy diagrams are presented for the individual steps in the operation of such tandem solar cells. We find that theoretical open circuit voltages of up to 1.8 V can be achieved using these tandem designs. Questions about the practical implementation of prototypical devices, such as the synthesis of the tandem molecules and potential loss mechanisms, are addressed.

Saddle-shaped porphyrins for dye-sensitized solar cells: new insight into the relationship between nonplanarity and photovoltaic properties

We report on the theoretical and experimental studies of the new dye-sensitized solar cells functionalized with 5,10,15,20-tetrakis(4-carboxyphenyl)porphyrin zinc(ii) complexes bearing 2- and 8-bromo substituents at the β positions.