Predicting Antimicrobial Activity of Conjugated Oligoelectrolyte Molecules via Machine Learning.

New antibiotics are needed to battle growing antibiotic resistance, but the development process from hit, to lead, and ultimately to a useful drug takes decades. Although progress in molecular property prediction using machine-learning methods has opened up new pathways for aiding the antibiotics development process, many existing solutions rely on large data sets and finding structural similarities to existing antibiotics. Challenges remain in modeling unconventional antibiotic classes that are drawing increasing research attention. In response, we developed an antimicrobial activity prediction model for conjugated oligoelectrolyte molecules, a new class of antibiotics that lacks extensive prior structure-activity relationship studies. Our approach enables us to predict the minimum inhibitory concentration for E. coli K12, with 21 molecular descriptors selected by recursive elimination from a set of 5305 descriptors. This predictive model achieves an R2 of 0.65 with no prior knowledge of the underlying mechanism. We find the molecular representation optimum for the domain is the key to good predictions of antimicrobial activity. In the case of conjugated oligoelectrolytes, a representation reflecting the three-dimensional shape of the molecules is most critical. Although it is demonstrated with a specific example of conjugated oligoelectrolytes, our proposed approach for creating the predictive model can be readily adapted to other novel antibiotic candidate domains.

Analysis of dye degradation products and assessment of the dye purity in dye-sensitized solar cells.

RATIONALE: For commercialization of dye-sensitized solar cells (DSSCs), improvement of their long-term stability and efficiency is important. A key component in solar cells is the dye, its high purity and high stability. Here, methods for dye extraction and purification, and for determination of dye purity and dye degradation in DSSCs, were developed. METHODS: A method was developed for extraction of the dye Z907 from intact solar cells using a water/ethanol mixture containing tetrabutylammonium hydroxide. The N719 dye synthesized in our laboratory was purified by gel filtration on Sephadex LH20. These dyes, along with the dyes N3 and RuL2 (NC)2, were analyzed using nuclear magnetic resonance (NMR) spectroscopy and liquid chromatography coupled to an electrospray ionization quadrupole-time-of-flight mass analyzer (LC/MS) operating in negative ionization mode. RESULTS: Purification of the synthesized N719 removed several impurities, including its undesired isomer with the thiocyanate ligand attached to ruthenium through sulfur instead of nitrogen. The dyes N719 and Z907 were successfully extracted from solar cells and together with N3 and RuL2 (NC)2 analyzed by LC/MS, although N719 isomerized almost immediately in basic aqueous solution. The [M-H](-1) ions were observed and the measured mass was within a ±6 ppm range from the exact mass. CONCLUSIONS: LC/MS in combination with NMR spectroscopy was shown to provide useful information on dye structure, purity, and on the efficiency of the purification methods. These methods allow for further studies of solar cell dyes, which may provide the detailed information needed for the improvement and eventual commercialization of the solar cell technology.

Using scalable computer vision to automate high-throughput semiconductor characterization.

High-throughput materials synthesis methods, crucial for discovering novel functional materials, face a bottleneck in property characterization. These high-throughput synthesis tools produce 104 samples per hour using ink-based deposition while most characterization methods are either slow (conventional rates of 101 samples per hour) or rigid (e.g., designed for standard thin films), resulting in a bottleneck. To address this, we propose automated characterization (autocharacterization) tools that leverage adaptive computer vision for an 85x faster throughput compared to non-automated workflows. Our tools include a generalizable composition mapping tool and two scalable autocharacterization algorithms that: (1) autonomously compute the band gaps of 200 compositions in 6 minutes, and (2) autonomously compute the environmental stability of 200 compositions in 20 minutes, achieving 98.5% and 96.9% accuracy, respectively, when benchmarked against domain expert manual evaluation. These tools, demonstrated on the formamidinium (FA) and methylammonium (MA) mixed-cation perovskite system FA1-xMAxPbI3, 0 ≤ x ≤ 1, significantly accelerate the characterization process, synchronizing it closer to the rate of high-throughput synthesis.

How machine learning can help select capping layers to suppress perovskite degradation.

Environmental stability of perovskite solar cells (PSCs) has been improved by trial-and-error exploration of thin low-dimensional (LD) perovskite deposited on top of the perovskite absorber, called the capping layer. In this study, a machine-learning framework is presented to optimize this layer. We featurize 21 organic halide salts, apply them as capping layers onto methylammonium lead iodide (MAPbI3) films, age them under accelerated conditions, and determine features governing stability using supervised machine learning and Shapley values. We find that organic molecules' low number of hydrogen-bonding donors and small topological polar surface area correlate with increased MAPbI3 film stability. The top performing organic halide, phenyltriethylammonium iodide (PTEAI), successfully extends the MAPbI3 stability lifetime by 4 ± 2 times over bare MAPbI3 and 1.3 ± 0.3 times over state-of-the-art octylammonium bromide (OABr). Through characterization, we find that this capping layer stabilizes the photoactive layer by changing the surface chemistry and suppressing methylammonium loss.

Author Correction: How machine learning can help select capping layers to suppress perovskite degradation.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

Gel Electrolytes with Polyamidopyridine Dendron Modified Talc for Dye-Sensitized Solar Cells.

Organic-inorganic hybrid layered materials are proposed as additives in a quasi-solid gel electrolyte for dye-sensitized solar cells. Talcs could provide a low-cost and environmentally friendly, as well as abundant, option as gelators. Here, talcs were prepared by functionalizing an organotalc with three polyamidopyridine dendron generations, PAMPy-talc-Gn (n = 1, 2 and 3). PAMPy dendrons grow parallel to the lamellae plane and form an organized structure by intermolecular interactions. In addition, polyiodide-dendron charge-transfer complexes were prepared onto the organotalc by adsorption of iodine. In this work, the effect of the dendron generation of PAMPy-talc and the influence of polyiodide intercalation on solar cell performance and stability were investigated. The best results were reached with the use of lowest-generation PAMPy-talc (η = 4.5 ± 0.3%, VOC = 710 ± 19 mV, Jsc = 10.4 ± 0.9 mA cm-2, and FF = 61 ± 2%): 15% higher efficiency compared to similar liquid devices. While some previously studied talcs illustrate very strong absorption of the iodide from the electrolyte, in the case of PAMPy-talc such interfering effects were absent: In a 1000 h light soaking test, the PAMPy-talc cells both with and without polyiodide intercalation demonstrated stable performances. Furthermore, the color analysis of the electrolyte indicated that the color of the electrolyte remained stable after an initial period of stabilization, which is a good indication of the compound being stable and not absorbing charge carriers from the electrolyte. The performance and stability results indicate that PAMPy-talc has potential as a gelling method for electrolytes for dye solar cells.