Explore the vast range of titles available.

Allosteric drugs have the potential to revolutionize biomedicine due to their enhanced selectivity and protection against overdosage. However, we need to better understand allosteric mechanisms in order to fully harness their potential in drug discovery. In this study, molecular dynamics simulations and nuclear magnetic resonance spectroscopy are used to investigate how increases in temperature affect allostery in imidazole glycerol phosphate synthase. Results demonstrate that temperature increase triggers a cascade of local amino acid-to-amino acid dynamics that remarkably resembles the allosteric activation that takes place upon effector binding. The differences in the allosteric response elicited by temperature increase as opposed to effector binding are conditional to the alterations of collective motions induced by either mode of activation. This work provides an atomistic picture of temperature-dependent allostery, which could be harnessed to more precisely control enzyme function. Using a combination of MD simulations and NMR, the authors investigate how temperature affects allostery in imidazole glycerol phosphate synthase (IGPS), revealing that increase of temperature triggers local amino acid dynamics and providing insights into mechanism of allosteric regulation.

The link between in vitro hERG ion channel inhibition and subsequent in vivo QT interval prolongation, a critical risk factor for the development of arrythmias such as Torsade de Pointes, is so well established that in vitro hERG activity alone is often sufficient to end the development of an otherwise promising drug candidate. It is therefore of tremendous interest to develop advanced methods for identifying hERG-active compounds in the early stages of drug development, as well as for proposing redesigned compounds with reduced hERG liability and preserved primary pharmacology. In this work, we present CardioGenAI, a machine learning-based framework for re-engineering both developmental and commercially available drugs for reduced hERG activity while preserving their pharmacological activity. The framework incorporates novel state-of-the-art discriminative models for predicting hERG channel activity, as well as activity against the voltage-gated Na V 1.5 and Ca V 1.2 channels due to their potential implications in modulating the arrhythmogenic potential induced by hERG channel blockade. We applied the complete framework to pimozide, an FDA-approved antipsychotic agent that demonstrates high affinity to the hERG channel, and generated 100 refined candidates. Remarkably, among the candidates is fluspirilene, a compound which is of the same class of drugs as pimozide (diphenylmethanes) and therefore has similar pharmacological activity, yet exhibits over 700-fold weaker binding to hERG. Furthermore, we demonstrated the framework's ability to optimize hERG, Na V 1.5 and Ca V 1.2 profiles of multiple FDA-approved compounds while maintaining the physicochemical nature of the original drugs. We envision that this method can effectively be applied to developmental compounds exhibiting hERG liabilities to provide a means of rescuing drug development programs that have stalled due to hERG-related safety concerns. Additionally, the discriminative models can also serve independently as effective components of virtual screening pipelines. We have made all of our software open-source at https://github.com/gregory-kyro/CardioGenAI to facilitate integration of the CardioGenAI framework for molecular hypothesis generation into drug discovery workflows. Scientific contribution This work introduces CardioGenAI, an open-source machine learning-based framework designed to re-engineer drugs for reduced hERG liability while preserving their pharmacological activity. The complete CardioGenAI framework can be applied to developmental compounds exhibiting hERG liabilities to provide a means of rescuing drug discovery programs facing hERG-related challenges. In addition, the framework incorporates novel state-of-the-art discriminative models for predicting hERG, Na V 1.5 and Ca V 1.2 channel activity, which can function independently as effective components of virtual screening pipelines.

Artificial photosynthesis is an attractive strategy for converting solar energy into fuels, largely because the Earth receives enough solar energy in one hour to meet humanity's energy needs for an entire year. However, developing devices for artificial photosynthesis remains difficult and requires computational approaches to guide and assist the interpretation of experiments. In this Perspective, we discuss current and future computational approaches, as well as the challenges of designing and characterizing molecular assemblies that absorb solar light, transfer electrons between interfaces, and catalyze water-splitting and fuel-forming reactions.

Drug discovery is a challenging endeavor for multiple reasons including the complexity of protein-ligand interactions at the molecular-level, the vastness of chemical space, and safety constraints related to unintended biological effects. In this dissertation, I present a suite of novel deep learning approaches that address these challenges from multiple angles. I first introduce HAC-Net— a deep learning model that, at the time, was the state of the art for predicting protein-ligand binding affinity—which was used to identify a potential inhibitor of a G protein-coupled receptor whose overexpression leads to cancer, diabetes, and multiple sclerosis, as well as a potential antivirulence drug for drug-resistant staphylococcal infections. HAC-Net provides chemists with a predictive tool for rational drug design by enabling accurate modeling of molecular interactions in biochemically relevant systems.Building upon that work, I developed T-ALPHA—the current state-of-the-art deep learning model for predicting protein-ligand binding affinity—which incorporates an uncertainty-aware self-learning method for protein-specific alignment. T-ALPHA not only improves upon HAC-Net by offering superior predictive accuracy on experimental structures, but, importantly, retains state-of-the-art performance on generated structures, enabling chemists to obtain accurate binding affinity estimates even in the absence of experimentally determined structures. Beyond discriminative tasks, I demonstrate the ability of generative machine learning methods to intelligently navigate chemical space to locate desirable regions. I created ChemSpaceAL—the first active learning methodology for fine-tuning a molecular generative model toward a specified protein target—which is particularly applicable to the creation of protein target-specific molecular libraries and is designed to be computationally efficient. We are currently utilizing this methodology in collaboration with the Lisi group at Brown University to design small-molecule binders to the HNH domain of CRISPR-Cas9 to enhance its specificity for target DNA sequences.Recognizing the importance of considering off-target safety effects in addition to on-target potency, I created CardioGenAI—a generative machine learning-based framework for re-engineering drugs for reduced hERG-related cardiotoxicity while preserving their primary pharmacology—which I applied to specific programs within Pfizer R&D that were dealing with hERG liabilities. This framework is particularly valuable for medicinal chemists seeking to optimize lead compounds for reduced cardiotoxicity early in the drug discovery pipeline. Collectively, these efforts advance early-stage drug discovery by providing chemists with computation tools that complement experimental approaches, facilitating the investigation of biochemically significant systems at the molecular level.

The incredible capabilities of generative artificial intelligence models have inevitably led to their application in the domain of drug discovery. Within this domain, the vastness of chemical space motivates the development of more efficient methods for identifying regions with molecules that exhibit desired characteristics. In this work, we present a computationally efficient active learning methodology that requires evaluation of only a subset of the generated data in the constructed sample space to successfully align a generative model with respect to a specified objective. We demonstrate the applicability of this methodology to targeted molecular generation by fine-tuning a GPT-based molecular generator toward a protein with FDA-approved small-molecule inhibitors, c-Abl kinase. Remarkably, the model learns to generate molecules similar to the inhibitors without prior knowledge of their existence, and even reproduces two of them exactly. We also show that the methodology is effective for a protein without any commercially available small-molecule inhibitors, the HNH domain of the CRISPR-associated protein 9 (Cas9) enzyme. We believe that the inherent generality of this method ensures that it will remain applicable as the exciting field of in silico molecular generation evolves. To facilitate implementation and reproducibility, we have made all of our software available through the open-source ChemSpaceAL Python package.

There is significant interest in targeting disease-causing proteins with small molecule inhibitors to restore healthy cellular states. The ability to accurately predict the binding affinity of small molecules to a protein target in silico enables the rapid identification of candidate inhibitors and facilitates the optimization of on-target potency. In this work, we present T-ALPHA, a novel deep learning model that enhances protein-ligand binding affinity prediction by integrating multimodal feature representations within a hierarchical transformer framework to capture information critical to accurately predicting binding affinity. T-ALPHA outperforms all existing models reported in the literature on multiple benchmarks designed to evaluate protein-ligand binding affinity scoring functions. Remarkably, T-ALPHA maintains state-of-the-art performance when utilizing predicted structures rather than crystal structures, a powerful capability in real-world drug discovery applications where experimentally determined structures are often unavailable or incomplete. Additionally, we present an uncertainty-aware self-learning method for protein-specific alignment that does not require additional experimental data, and demonstrate that it improves T-ALPHA's ability to rank compounds by binding affinity to biologically significant targets such as the SARS-CoV-2 main protease and the epidermal growth factor receptor. To facilitate implementation of T-ALPHA and reproducibility of all results presented in this paper, we have made all of our software available at https://github.com/gregory-kyro/T-ALPHA.Competing Interest StatementThe authors have declared no competing interest.Footnotes* https://github.com/gregory-kyro/T-ALPHA* https://zenodo.org/records/14510963

As the rapidly evolving field of machine learning continues to produce incredibly useful tools and models, the potential for quantum computing to provide speed up for machine learning algorithms is becoming increasingly desirable. In particular, quantum circuits in place of classical convolutional filters for image detection-based tasks are being investigated for the ability to exploit quantum advantage. However, these attempts, referred to as quantum convolutional neural networks (QCNNs), lack the ability to efficiently process data with multiple channels and therefore are limited to relatively simple inputs. In this work, we present a variety of hardware-adaptable quantum circuit ansatzes for use as convolutional kernels, and demonstrate that the quantum neural networks we report outperform existing QCNNs on classification tasks involving multi-channel data. We envision that the ability of these implementations to effectively learn inter-channel information will allow quantum machine learning methods to operate with more complex data. This work is available as open source at https://github.com/anthonysmaldone/QCNN-Multi-Channel-Supervised-Learning.

Applying deep learning concepts from image detection and graph theory has greatly advanced protein-ligand binding affinity prediction, a challenge with enormous ramifications for both drug discovery and protein engineering. We build upon these advances by designing a novel deep learning architecture consisting of a 3-dimensional convolutional neural network utilizing channel-wise attention and two graph convolutional networks utilizing attention-based aggregation of node features. HAC-Net (Hybrid Attention-Based Convolutional Neural Network) obtains state-of-the-art results on the PDBbind v.2016 core set, the most widely recognized benchmark in the field. We extensively assess the generalizability of our model using multiple train-test splits, each of which maximizes differences between either protein structures, protein sequences, or ligand extended-connectivity fingerprints of complexes in the training and test sets. Furthermore, we perform 10-fold cross-validation with a similarity cutoff between SMILES strings of ligands in the training and test sets, and also evaluate the performance of HAC-Net on lower-quality data. We envision that this model can be extended to a broad range of supervised learning problems related to structure-based biomolecular property prediction. All of our software is available as open source at https://github.com/gregory-kyro/HAC-Net/, and the HACNet Python package is available through PyPI.

The incredible capabilities of generative artificial intelligence models have inevitably led to their application in the domain of drug discovery. Within this domain, the vastness of chemical space motivates the development of more efficient methods for identifying regions with molecules that exhibit desired characteristics. In this work, we present a computationally efficient active learning methodology that requires evaluation of only a subset of the generated data in the constructed sample space to successfully align a generative model with respect to a specified objective. We demonstrate the applicability of this methodology to targeted molecular generation by fine-tuning a GPT-based molecular generator toward a protein with FDA-approved small-molecule inhibitors, c-Abl kinase. Remarkably, the model learns to generate molecules similar to the inhibitors without prior knowledge of their existence, and even reproduces two of them exactly. We also show that the methodology is effective for a protein without any commercially available small-molecule inhibitors, the HNH domain of the CRISPR-associated protein 9 (Cas9) enzyme. We believe that the inherent generality of this method ensures that it will remain applicable as the exciting field of in silico molecular generation evolves. To facilitate implementation and reproducibility, we have made all of our software available through the open-source ChemSpaceAL Python package.