Design of Molecules with Low Hole and Electron Reorganization Energy Using DFT Calculations and Bayesian Optimization.

Materials exhibiting higher mobility than conventional organic semiconducting materials, such as fullerenes and fused thiophenes, are in high demand for applications in printed electronics. To discover new molecules that might show improved charge mobility, the adaptive design of experiments (DoE) to design molecules with low reorganization energy was performed by combining density functional theory (DFT) methods and machine learning techniques. DFT-calculated values of 165 molecules were used as an initial training dataset for a Gaussian process regression (GPR) model, and five rounds of molecular designs applying the GPR model and validation via DFT calculations were executed. As a result, new molecules whose reorganization energy is smaller than the lowest value in the initial training dataset were successfully discovered.

De Novo Design of Molecules with Low Hole Reorganization Energy Based on a Quarter-Million Molecule DFT Screen: Part 2.

Organic semiconductors have many desirable properties including improved manufacturing and flexible mechanical properties. Due to the vastness of chemical space, it is essential to efficiently explore chemical space when designing new materials, including through the use of generative techniques. New generative machine learning methods for molecular design continue to be published in the literature at a significant rate but successfully adapting methods to new chemistry and problem domains remains difficult. These challenges necessitate continual method evaluation to probe method viability for use in alternative applications not covered in the original works. In continuation of our previous work, we evaluate four additional machine-learning-based de novo methods for generating molecules with high predicted hole mobility for use in semiconductor applications. The four generative methods evaluated here are (1) Molecule Deep Q-Networks (MolDQN), which utilizes Deep-Q learning to directly optimize molecular structure graphs for desired properties instead of generating SMILES, (2) Graph-based Genetic Algorithm (GraphGA), which uses a genetic algorithm for optimization where crossovers and mutations are defined in terms of RDKit's reaction SMILES, (3) Generative Tensorial Reinforcement Learning (GENTRL), which is a variational autoencoder (VAE) with a learned prior distribution and optimized using reinforcement learning, and (4) Monte Carlo tree search exploration of chemical space in conjunction with a recurrent neural network (RNN) decoder (ChemTS). The generated molecules were evaluated using density functional theory (DFT) and we discovered better performing molecules with the GraphGA method compared to the other approaches.

De Novo Design of Molecules with Low Hole Reorganization Energy Based on a Quarter-Million Molecule DFT Screen.

Materials exhibiting higher mobilities than conventional organic semiconducting materials such as fullerenes and fused thiophenes are in high demand for applications in printed electronics. To discover new molecules in the heteroacene family that might show improved hole mobility, three de novo design methods were applied. Machine learning (ML) models were generated based on previously calculated hole reorganization energies of a quarter million examples of heteroacenes, where the energies were calculated by applying density functional theory (DFT) and a massive cloud computing environment. The three generative methods applied were (1) the continuous space method, where molecular structures are converted into continuous variables by applying the variational autoencoder/decoder technique; (2) the method based on reinforcement learning of SMILES strings (the REINVENT method); and (3) the junction tree variational autoencoder method that directly generates molecular graphs. Among the three methods, the second and third methods succeeded in obtaining chemical structures whose DFT-calculated hole reorganization energy was lower than the lowest energy in the training dataset. This suggests that an extrapolative materials design protocol can be developed by applying generative modeling to a quantitative structure-property relationship (QSPR) utility function.

Magnetic resonance lymphography of sentinel lymph nodes in patients with breast cancer using superparamagnetic iron oxide: a feasibility study.

BACKGROUND: The sentinel lymph node (SLN) biopsy technique using superparamagnetic iron oxide (SPIO) as a tracer instead of radioisotopes has been described. To further advance this technique, we evaluated preoperative SPIO-MR sentinel lymphography to facilitate the accurate identification of the lymphatic pathways and primary SLN. METHODS: A prospective study was performed in ten patients with breast cancer and clinically negative axillary lymph nodes. None of the patients received preoperative chemotherapy. After 1.6 ml of SPIO (ferucarbotran) was injected in the subareolar breast tissue, sentinel axillary lymph nodes were detected by MRI in T2*-weighted gradient echo images and resected using the serial SPIO-SLN biopsy procedure with a handheld magnetometer. RESULTS: In one patient, gadolinium-enhanced MR imaging was performed at the same time as SPIO-MR lymphography, and this patient was excluded from further analysis. In all patients (9/9) SLNs were detected by SPIO-MR sentinel lymphography and successfully identified at surgery. The number of SLNs detected by lymphography (mean 2.7) significantly correlated with SLNs identified at surgery (mean 2.2). One patient had nodal metastases. In one patient, skin color changed to brown at the injection site and resolved spontaneously. There were no severe reactions to the procedure or complications in any patient. CONCLUSIONS: This is the first study to evaluate SPIO both as a contrast material in MR sentinel lymphography and as a tracer in SLN biopsy using an integrated method. The acquired three-dimensional imaging demonstrated excellent image quality and usefulness to identify SLN in conjunction with SLN biopsy.