Origin of the p-type characteristics of organic semiconductors

Organic semiconductors (OSC) are generally considered intrinsic (undoped), an assumption which underpins our understanding of the charge transport in this promising class of materials. However, this premise conflicts with a variety of experimental observations, that suggest the presence of excess holes carriers in OSCs at room temperature. Here, using a low-power plasma de-doping method, we report that trace amounts (~1015 cm-3) of oxygen-induced organic radical cations (OIORCs) are inherent in the lattice of OSCs as innate hole carriers, and that this is the origin of the p-type characteristics exhibited by the majority of these materials. This finding clarifies previously unexplained organic electronics phenomena and provides a foundation upon which to re-understand charge transport in OSCs. Furthermore, the de-doping method can eliminate the trace OIORCs, resulting in the complete disappearance of p-type behavior, while re-doping (under light irradiation in O2), reverses the process. These methods can precisely modulate key electronic characteristics (e.g., conductivity, polarity, and threshold voltage) in a nondestructive way, expanding the explorable charge transport property space for all known OSC materials. Accordingly, we conclude that our tailorable OIORC doping strategy, requiring only off-the-shelf equipment and a glovebox, will become a core technology in the burgeoning organic electronics industry.

Analysis of the uncharted, druglike property space by self-organizing maps

Physicochemical properties are fundamental to predict the pharmacokinetic and pharmacodynamic behavior of drug candidates. Easily calculated descriptors such as molecular weight and logP have been found to correlate with the success rate of clinical trials. These properties have been previously shown to highlight a sweet-spot in the chemical space associated with favorable pharmacokinetics, which is superior against other regions during hit identification and optimization. In this study, we applied self-organizing maps (SOMs) trained on sixteen calculated properties of a subset of known drugs for the analysis of commercially available compound databases, as well as public biological and chemical databases frequently used for drug discovery. Interestingly, several regions of the property space have been identified that are highly overrepresented by commercially available chemical libraries, while we found almost completely unoccupied regions of the maps (commercially neglected chemical space resembling the properties of known drugs). Moreover, these underrepresented portions of the chemical space are compatible with most rigorous property filters applied by the pharma industry in medicinal chemistry optimization programs. Our results suggest that SOMs may be directly utilized in the strategy of library design for drug discovery to sample previously unexplored parts of the chemical space to aim at yet-undruggable targets. Graphic abstract

Quantum Mechanics Enables "Freedom of Design" in Molecular Property Space

Rational design of molecules with targeted properties requires understanding quantum-mechanical (QM) structure-property/property-property relationships (SPR/PPR) across chemical compound space. We analyze these relationships using the QM7-X dataset---which includes multiple QM properties for ~4.2 M equilibrium and non-equilibrium structures of small (primarily organic) molecules. Instead of providing simple SPR/PPR that strictly follow physicochemical intuition, our analysis uncovers substantial flexibility in molecular property space (MPS) when searching for a single molecule with a desired pair of QM properties or distinct molecules with a targeted set of QM properties. As proof-of-concept, we used Pareto multi-property optimization to search for the most promising (i.e., highly polarizable and electrically stable) molecules for polymeric battery materials; without prior knowledge of this complex manifold of MPS, Pareto front analysis reflected this intrinsic flexibility and identified small directed structural/compositional changes that simultaneously optimize these properties. Our analysis of such extensive QM property data provides compelling evidence for an intrinsic “freedom of design” in MPS, and indicates that rational design of molecules with a diverse array of targeted QM properties is quite feasible.

Fragment-based Sequential Translation for Molecular Optimization

Searching for novel molecular compounds with desired properties is an important problem in drug discovery. Many existing frameworks generate molecules one atom at a time. We instead propose a flexible editing paradigm that generates molecules using learned molecular fragments---meaningful substructures of molecules. To do so, we train a variational autoencoder (VAE) to encode molecular fragments in a coherent latent space, which we then utilize as a vocabulary for editing molecules to explore the complex chemical property space. Equipped with the learned fragment vocabulary, we propose Fragment-based Sequential Translation (FaST), which learns a reinforcement learning (RL) policy to iteratively translate model-discovered molecules into increasingly novel molecules while satisfying desired properties. Empirical evaluation shows that FaST significantly improves over state-of-the-art methods on benchmark single/multi-objective molecular optimization tasks.

Fragment-based Sequential Translation for Molecular Optimization

Searching for novel molecular compounds with desired properties is an important problem in drug discovery. Many existing frameworks generate molecules one atom at a time. We instead propose a flexible editing paradigm that generates molecules using learned molecular fragments---meaningful substructures of molecules. To do so, we train a variational autoencoder (VAE) to encode molecular fragments in a coherent latent space, which we then utilize as a vocabulary for editing molecules to explore the complex chemical property space. Equipped with the learned fragment vocabulary, we propose Fragment-based Sequential Translation (FaST), which learns a reinforcement learning (RL) policy to iteratively translate model-discovered molecules into increasingly novel molecules while satisfying desired properties. Empirical evaluation shows that FaST significantly improves over state-of-the-art methods on benchmark single/multi-objective molecular optimization tasks.

Comparison of structure- and ligand-based scoring functions for deep generative models: a GPCR case study

Deep generative models have shown the ability to devise both valid and novel chemistry, which could significantly accelerate the identification of bioactive compounds. Many current models, however, use molecular descriptors or ligand-based predictive methods to guide molecule generation towards a desirable property space. This restricts their application to relatively data-rich targets, neglecting those where little data is available to sufficiently train a predictor. Moreover, ligand-based approaches often bias molecule generation towards previously established chemical space, thereby limiting their ability to identify truly novel chemotypes. In this work, we assess the ability of using molecular docking via Glide—a structure-based approach—as a scoring function to guide the deep generative model REINVENT and compare model performance and behaviour to a ligand-based scoring function. Additionally, we modify the previously published MOSES benchmarking dataset to remove any induced bias towards non-protonatable groups. We also propose a new metric to measure dataset diversity, which is less confounded by the distribution of heavy atom count than the commonly used internal diversity metric. With respect to the main findings, we found that when optimizing the docking score against DRD2, the model improves predicted ligand affinity beyond that of known DRD2 active molecules. In addition, generated molecules occupy complementary chemical and physicochemical space compared to the ligand-based approach, and novel physicochemical space compared to known DRD2 active molecules. Furthermore, the structure-based approach learns to generate molecules that satisfy crucial residue interactions, which is information only available when taking protein structure into account. Overall, this work demonstrates the advantage of using molecular docking to guide de novo molecule generation over ligand-based predictors with respect to predicted affinity, novelty, and the ability to identify key interactions between ligand and protein target. Practically, this approach has applications in early hit generation campaigns to enrich a virtual library towards a particular target, and also in novelty-focused projects, where de novo molecule generation either has no prior ligand knowledge available or should not be biased by it.

Retro Drug Design: From Target Properties to Molecular Structures

To generate drug molecules of desired properties with computational methods is the holy grail in pharmaceutical research. Here we describe an AI strategy, retro drug design, or RDD, to generate novel small molecule drugs from scratch to meet predefined requirements, including but not limited to biological activity against a drug target, and optimal range of physicochemical and ADMET properties. Traditional predictive models were first trained over experimental data for the target properties, using an atom typing based molecular descriptor system, ATP. Monte Carlo sampling algorithm was then utilized to find the solutions in the ATP space defined by the target properties, and the deep learning model of Seq2Seq was employed to decode molecular structures from the solutions. To test feasibility of the algorithm, we challenged RDD to generate novel drugs that can activate μ opioid receptor (MOR) and penetrate blood brain barrier (BBB). Starting from vectors of random numbers, RDD generated 180,000 chemical structures, of which 78% were chemically valid. About 42,000 (31%) of the valid structures fell into the property space defined by MOR activity and BBB permeability. Out of the 42,000 structures, only 267 chemicals were commercially available, indicating a high extent of novelty of the AI-generated compounds. We purchased and assayed 96 compounds, and 25 of which were found to be MOR agonists. These compounds also have excellent BBB scores. The results presented in this paper illustrate that RDD has potential to revolutionize the current drug discovery process and create novel structures with multiple desired properties, including biological functions and ADMET properties. Availability of an AI-enabled fast track in drug discovery is essential to cope with emergent public health threat, such as pandemic of COVID-19.

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

The design of molecular catalysts typically involves reconciling multiple conflicting property requirements, largely relying on human intuition and local structural searches. However, the vast number of potential catalysts requires pruning of the candidate space by efficient property prediction with quantitative structure-property relationships. Data-driven workflows embedded in a library of potential catalysts can be used to build predictive models for catalyst performance and serve as a blueprint for novel catalyst designs. Herein we introduce <i>kraken</i>, a discovery platform covering monodentate organophosphorus(III) ligands providing comprehensive physicochemical descriptors based on representative conformer ensembles. Using quantum-mechanical methods, we calculated descriptors for 1,558 ligands, including commercially available examples, and trained machine learning models to predict properties of over 300,000 new ligands. We demonstrate the application of <i>kraken</i> to systematically explore the property space of organophosphorus ligands and how existing datasets in catalysis can be used to accelerate ligand selection during reaction optimization.

A Comprehensive Discovery Platform for Organophosphorus Ligands for Catalysis

The design of molecular catalysts typically involves reconciling multiple conflicting property requirements, largely relying on human intuition and local structural searches. However, the vast number of potential catalysts requires pruning of the candidate space by efficient property prediction with quantitative structure-property relationships. Data-driven workflows embedded in a library of potential catalysts can be used to build predictive models for catalyst performance and serve as a blueprint for novel catalyst designs. Herein we introduce <i>kraken</i>, a discovery platform covering monodentate organophosphorus(III) ligands providing comprehensive physicochemical descriptors based on representative conformer ensembles. Using quantum-mechanical methods, we calculated descriptors for 1,558 ligands, including commercially available examples, and trained machine learning models to predict properties of over 300,000 new ligands. We demonstrate the application of <i>kraken</i> to systematically explore the property space of organophosphorus ligands and how existing datasets in catalysis can be used to accelerate ligand selection during reaction optimization.