RESUMO
A drug's pharmacokinetic (PK) profile will determine its dose and the frequency of administration as well as the likelihood of observing any adverse drug reactions.It is important to understand these PK properties as early as possible in the drug discovery process, ideally, to accurately predict these prior to synthesising the molecule leading to significant improvements in efficiency.In this paper, we describe the approaches used within AstraZeneca to improve our ability of predicting the preclinical and human pharmacokinetic profiles of novel molecules using machine learning and artificial intelligence.We will show how combining chemical structure-based approaches with experimentally derived properties enables improved predictions of in vivo pharmacokinetics and can be extended to molecules that go beyond the classical Lipinski's rule-of-five space.We will also discuss how combining these in vitro and in vivo predictive models could ultimately improve our ability to predict the human outcome at the point of chemical design.
Assuntos
Aprendizado de Máquina , Humanos , Farmacocinética , Descoberta de Drogas/métodos , Preparações Farmacêuticas/metabolismo , Preparações Farmacêuticas/química , Inteligência ArtificialRESUMO
Structural cardiotoxicity (SCT) presents a high-impact risk that is poorly tolerated in drug discovery unless significant benefit is anticipated. Therefore, we aimed to improve the mechanistic understanding of SCT. First, we combined machine learning methods with a modified calcium transient assay in human-induced pluripotent stem cell-derived cardiomyocytes to identify nine parameters that could predict SCT. Next, we applied transcriptomic profiling to human cardiac microtissues exposed to structural and non-structural cardiotoxins. Fifty-two genes expressed across the three main cell types in the heart (cardiomyocytes, endothelial cells, and fibroblasts) were prioritised in differential expression and network clustering analyses and could be linked to known mechanisms of SCT. This transcriptomic fingerprint may prove useful for generating strategies to mitigate SCT risk in early drug discovery.
Assuntos
Cardiotoxicidade , Perfilação da Expressão Gênica , Células-Tronco Pluripotentes Induzidas , Miócitos Cardíacos , Transcriptoma , Humanos , Cardiotoxicidade/genética , Transcriptoma/efeitos dos fármacos , Transcriptoma/genética , Miócitos Cardíacos/efeitos dos fármacos , Miócitos Cardíacos/metabolismo , Células-Tronco Pluripotentes Induzidas/efeitos dos fármacos , Células-Tronco Pluripotentes Induzidas/metabolismo , Perfilação da Expressão Gênica/métodos , Biologia Computacional/métodos , Aprendizado de Máquina , Cardiotoxinas/toxicidade , Fibroblastos/efeitos dos fármacos , Fibroblastos/metabolismo , Células Endoteliais/efeitos dos fármacos , Células Endoteliais/metabolismoRESUMO
Accurate methods to predict solubility from molecular structure are highly sought after in the chemical sciences. To assess the state of the art, the American Chemical Society organized a "Second Solubility Challenge" in 2019, in which competitors were invited to submit blinded predictions of the solubilities of 132 drug-like molecules. In the first part of this article, we describe the development of two models that were submitted to the Blind Challenge in 2019 but which have not previously been reported. These models were based on computationally inexpensive molecular descriptors and traditional machine learning algorithms and were trained on a relatively small data set of 300 molecules. In the second part of the article, to test the hypothesis that predictions would improve with more advanced algorithms and higher volumes of training data, we compare these original predictions with those made after the deadline using deep learning models trained on larger solubility data sets consisting of 2999 and 5697 molecules. The results show that there are several algorithms that are able to obtain near state-of-the-art performance on the solubility challenge data sets, with the best model, a graph convolutional neural network, resulting in an RMSE of 0.86 log units. Critical analysis of the models reveals systematic differences between the performance of models using certain feature sets and training data sets. The results suggest that careful selection of high quality training data from relevant regions of chemical space is critical for prediction accuracy but that other methodological issues remain problematic for machine learning solubility models, such as the difficulty in modeling complex chemical spaces from sparse training data sets.
Assuntos
Aprendizado Profundo , Solubilidade , Redes Neurais de Computação , Aprendizado de Máquina , AlgoritmosRESUMO
Optimization of compound metabolic stability is a highly topical issue in pharmaceutical research. Accordingly, application of predictive in silico models can potentially reduce the number of design-make-test-analyze iterations and consequently speed up the progression of novel candidate molecules. Herein, we have investigated the question if multiple in vitro clearance endpoints could be accurately predicted from image-based molecular representations. Thus, compound measurements for four commonly investigated clearance endpoints were curated from AstraZeneca internal sources, providing a sound basis for building multi-task convolutional neural network models. Application of several increasingly challenging data splitting strategies confirmed that convolutional neural network models were successful at capturing implicit chemical relationships contained in training and test data, similar to what is commonly observed for structural fingerprints. Furthermore, model benchmarking against state-of-the-art machine learning methods, including deep neural networks and graph convolutional neural networks, trained with structure- and graph-based representations, respectively, revealed on par or increased accuracy of convolutional neural networks with clear benefit of multi-task learning across all clearance endpoints. Our findings indicate that image-based molecular representations can be applied to predict multiple clearance endpoints, suggesting a potential follow-up to investigate model interpretability from molecular images.
Assuntos
Algoritmos , Redes Neurais de Computação , CinéticaRESUMO
Prostate cancer is the second most occurring cancer in men worldwide. To better understand the mechanisms of tumorigenesis and possible treatment responses, we developed a mathematical model of prostate cancer which considers the major signalling pathways known to be deregulated. We personalised this Boolean model to molecular data to reflect the heterogeneity and specific response to perturbations of cancer patients. A total of 488 prostate samples were used to build patient-specific models and compared to available clinical data. Additionally, eight prostate cell line-specific models were built to validate our approach with dose-response data of several drugs. The effects of single and combined drugs were tested in these models under different growth conditions. We identified 15 actionable points of interventions in one cell line-specific model whose inactivation hinders tumorigenesis. To validate these results, we tested nine small molecule inhibitors of five of those putative targets and found a dose-dependent effect on four of them, notably those targeting HSP90 and PI3K. These results highlight the predictive power of our personalised Boolean models and illustrate how they can be used for precision oncology.
Assuntos
Medicina de Precisão , Neoplasias da Próstata , Carcinogênese , Proteínas de Choque Térmico HSP90 , Humanos , Masculino , Medicina de Precisão/métodos , Neoplasias da Próstata/tratamento farmacológico , Neoplasias da Próstata/genética , Transdução de SinaisRESUMO
The potential to predict solvation free energies (SFEs) in any solvent using a machine learning (ML) model based on thermodynamic output, extracted exclusively from 3D-RISM simulations in water is investigated. The models on multiple solvents take into account both the solute and solvent description and offer the possibility to predict SFEs of any solute in any solvent with root mean squared errors less than 1 kcal/mol. Validations that involve exclusion of fractions or clusters of the solutes or solvents exemplify the model's capability to predict SFEs of novel solutes and solvents with diverse chemical profiles. In addition to being predictive, our models can identify the solute and solvent features that influence SFE predictions. Furthermore, using 3D-RISM hydration thermodynamic output to predict SFEs in any organic solvent reduces the need to run 3D-RISM simulations in all these solvents. Altogether, our multisolvent models for SFE predictions that take advantage of the solvation effects are expected to have an impact in the property prediction space.
Assuntos
Água , Entropia , Soluções , Solventes , TermodinâmicaRESUMO
In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: compounds' structure in the form of a SMILES sequence, gene expression profiles of tumors, and prior knowledge on intracellular interactions from protein-protein interaction networks. We demonstrate that our multiscale convolutional attention-based encoder significantly outperforms a baseline model trained on Morgan fingerprints and a selection of encoders based on SMILES, as well as the previously reported state-of-the-art for multimodal drug sensitivity prediction (R2 = 0.86 and RMSE = 0.89). Moreover, the explainability of our approach is demonstrated by a thorough analysis of the attention weights. We show that the attended genes significantly enrich apoptotic processes and that the drug attention is strongly correlated with a standard chemical structure similarity index. Finally, we report a case study of two receptor tyrosine kinase (RTK) inhibitors acting on a leukemia cell line, showcasing the ability of the model to focus on informative genes and submolecular regions of the two compounds. The demonstrated generalizability and the interpretability of our model testify to its potential for in silico prediction of anticancer compound efficacy on unseen cancer cells, positioning it as a valid solution for the development of personalized therapies as well as for the evaluation of candidate compounds in de novo drug design.
Assuntos
Algoritmos , Antineoplásicos , Aprendizado Profundo , Desenho de Fármacos , Humanos , Redes Neurais de ComputaçãoRESUMO
Transcriptional perturbation signatures are valuable data sources for functional genomics. Linking perturbation signatures to screenings opens the possibility to model cellular phenotypes from expression data and to identify efficacious drugs. We linked perturbation transcriptomics data from the LINCS-L1000 project with cell viability information upon genetic (Achilles project) and chemical (CTRP screen) perturbations yielding more than 90 000 signature-viability pairs. An integrated analysis showed that the cell viability signature is a major factor underlying perturbation signatures. The signature is linked to transcription factors regulating cell death, proliferation and division time. We used the cell viability-signature relationship to predict viability from transcriptomics signatures, and identified and validated compounds that induce cell death in tumor cell lines. We showed that cellular toxicity can lead to unexpected similarity of signatures, confounding mechanism of action discovery. Consensus compound signatures predicted cell-specific drug sensitivity, even if the signature is not measured in the same cell line, and outperformed conventional drug-specific features. Our results can help in understanding mechanisms behind cell death and removing confounding factors of transcriptomic perturbation screens. To interactively browse our results and predict cell viability in new gene expression samples, we developed CEVIChE (CEll VIability Calculator from gene Expression; https://saezlab.shinyapps.io/ceviche/).
Assuntos
Perfilação da Expressão Gênica/métodos , Redes Reguladoras de Genes/genética , Software , Transcriptoma/genética , Morte Celular/genética , Linhagem Celular Tumoral , Proliferação de Células/genética , Sobrevivência Celular/genética , Descoberta de Drogas , HumanosRESUMO
The high similarity between certain sub-pockets of serine proteases may lead to low selectivity of protease inhibitors. Therefore the application of proteochemometrics (PCM), which quantifies the relationship between protein/ligand descriptors and affinity for multiple ligands and targets simultaneously, is useful to understand and improve the selectivity profiles of potential inhibitors. In this study, protein field-based PCM that uses knowledge-based and WaterMap derived fields to describe proteins in combination with 2D (RDKit and MOE fingerprints) and 3D (4 point pharmacophoric fingerprints and GRIND) ligand descriptors was used to model the bioactivities of 24 homologous serine proteases and 5863 inhibitors in an integrated fashion. Of the multiple field-based PCM models generated based on different ligand descriptors, RDKit fingerprints showed the best performance in terms of external prediction with Rtest2 of 0.72 and RMSEP of 0.81. Further, visual interpretation of the models highlights sub-pocket specific regions that influence affinity and selectivity of serine protease inhibitors.
RESUMO
Achieving selectivity for small organic molecules toward biological targets is a main focus of drug discovery but has been proven difficult, for example, for kinases because of the high similarity of their ATP binding pockets. To support the design of more selective inhibitors with fewer side effects or with altered target profiles for improved efficacy, we developed a method combining ligand- and receptor-based information. Conventional QSAR models enable one to study the interactions of multiple ligands toward a single protein target, but in order to understand the interactions between multiple ligands and multiple proteins, we have used proteochemometrics, a multivariate statistics method that aims to combine and correlate both ligand and protein descriptions with affinity to receptors. The superimposed binding sites of 50 unique kinases were described by molecular interaction fields derived from knowledge-based potentials and Schrödinger's WaterMap software. Eighty ligands were described by Mold(2), Open Babel, and Volsurf descriptors. Partial least-squares regression including cross-terms, which describe the selectivity, was used for model building. This combination of methods allows interpretation and easy visualization of the models within the context of ligand binding pockets, which can be translated readily into the design of novel inhibitors.