RESUMEN
Multi-factor screenings are commonly used in diverse applications in medicine and bioengineering, including optimizing combination drug treatments and microbiome engineering. Despite the advances in high-throughput technologies, large-scale experiments typically remain prohibitively expensive. Here we introduce a machine learning platform, structure-augmented regression (SAR), that exploits the intrinsic structure of each biological system to learn a high-accuracy model with minimal data requirement. Under different environmental perturbations, each biological system exhibits a unique, structured phenotypic response. This structure can be learned based on limited data and once learned, can constrain subsequent quantitative predictions. We demonstrate that SAR requires significantly fewer data comparing to other existing machine-learning methods to achieve a high prediction accuracy, first on simulated data, then on experimental data of various systems and input dimensions. We then show how a learned structure can guide effective design of new experiments. Our approach has implications for predictive control of biological systems and an integration of machine learning prediction and experimental design.
Asunto(s)
Biología Computacional , Aprendizaje Automático , Biología Computacional/métodos , Modelos Biológicos , Simulación por Computador , Algoritmos , Humanos , Análisis de RegresiónRESUMEN
Active learning allows algorithms to steer iterative experimentation to accelerate and de-risk molecular optimizations, but actively trained models might still exhibit poor performance during early project stages where the training data is limited and model exploitation might lead to analog identification with limited scaffold diversity. Here, we present ActiveDelta, an adaptive approach that leverages paired molecular representations to predict improvements from the current best training compound to prioritize further data acquisition. We apply the ActiveDelta concept to both graph-based deep (Chemprop) and tree-based (XGBoost) models during exploitative active learning for 99 Ki benchmarking datasets. We show that both ActiveDelta implementations excel at identifying more potent inhibitors compared to the standard exploitative active learning implementations of Chemprop, XGBoost, and Random Forest. The ActiveDelta approach is also able to identify more chemically diverse inhibitors in terms of their Murcko scaffolds. Finally, deep models such as Chemprop trained on data selected through ActiveDelta approaches can more accurately identify inhibitors in test data created through simulated time-splits. Overall, this study highlights the large potential for molecular pairing approaches to further improve popular active learning strategies in low data regimes by enabling faster and more accurate identification of more diverse molecular hits against critical drug targets.
RESUMEN
Marginalized graph kernels have shown competitive performance in molecular machine learning tasks but currently lack measures of interpretability, which are important to improve trust in the models, detect biases, and inform molecular optimization campaigns. We here conceive and implement two interpretability measures for Gaussian process regression using a marginalized graph kernel (GPR-MGK) to quantify (1) the contribution of specific training data to the prediction and (2) the contribution of specific nodes of the graph to the prediction. We demonstrate the applicability of these interpretability measures for molecular property prediction. We compare GPR-MGK to graph neural networks on four logic and two real-world toxicology data sets and find that the atomic attribution of GPR-MGK generally outperforms the atomic attribution of graph neural networks. We also perform a detailed molecular attribution analysis using the FreeSolv data set, showing how molecules in the training set influence machine learning predictions and why Morgan fingerprints perform poorly on this data set. This is the first systematic examination of the interpretability of GPR-MGK and thereby is an important step in the further maturation of marginalized graph kernel methods for interpretable molecular predictions.
RESUMEN
PURPOSE: A multitude of different versions of the same medication with different inactive ingredients are currently available. It has not been quantified how this has evolved historically. Furthermore, it is unknown whether healthcare professionals consider the inactive ingredient portion when prescribing medications to patients. METHODS: We used data mining to track the number of available formulations for the same medication over time and correlate the number of available versions in 2019 to the number of manufacturers, the years since first approval, and the number of prescriptions. A focused survey among healthcare professionals was conducted to query their consideration of the inactive ingredient portion of a medication when writing prescriptions. RESULTS: The number of available versions of a single medication have dramatically increased in the last 40 years. The number of available, different versions of medications are largely determined by the number of manufacturers producing this medication. Healthcare providers commonly do not consider the inactive ingredient portion when prescribing a medication. CONCLUSIONS: A multitude of available versions of the same medications provides a potentially under-recognized opportunity to prescribe the most suitable formulation to a patient as a step towards personalized medicine and mitigate potential adverse events from inactive ingredients.
Asunto(s)
Competencia Clínica/estadística & datos numéricos , Composición de Medicamentos/historia , Excipientes Farmacéuticos/efectos adversos , Medicamentos bajo Prescripción/química , Prescripciones de Medicamentos , Historia del Siglo XX , Historia del Siglo XXI , Humanos , Excipientes Farmacéuticos/química , Excipientes Farmacéuticos/historia , Medicamentos bajo Prescripción/efectos adversos , Medicamentos bajo Prescripción/historia , Encuestas y Cuestionarios/estadística & datos numéricosRESUMEN
Active machine learning enables the automated selection of the most valuable next experiments to improve predictive modelling and hasten active retrieval in drug discovery. Although a long established theoretical concept and introduced to drug discovery approximately 15 years ago, the deployment of active learning technology in the discovery pipelines across academia and industry remains slow. With the recent re-discovered enthusiasm for artificial intelligence as well as improved flexibility of laboratory automation, active learning is expected to surge and become a key technology for molecular optimizations. This review recapitulates key findings from previous active learning studies to highlight the challenges and opportunities of applying adaptive machine learning to drug discovery. Specifically, considerations regarding implementation, infrastructural integration, and expected benefits are discussed. By focusing on these practical aspects of active learning, this review aims at providing insights for scientists planning to implement active learning workflows in their discovery pipelines.
Asunto(s)
Descubrimiento de Drogas , Aprendizaje Automático Supervisado , HumanosRESUMEN
De novo molecular design and in silico prediction of polypharmacological profiles are emerging research topics that will profoundly affect the future of drug discovery and chemical biology. The goal is to identify the macromolecular targets of new chemical agents. Although several computational tools for predicting such targets are publicly available, none of these methods was explicitly designed to predict target engagement by de novo-designed molecules. Here we present the development and practical application of a unique technique, self-organizing map-based prediction of drug equivalence relationships (SPiDER), that merges the concepts of self-organizing maps, consensus scoring, and statistical analysis to successfully identify targets for both known drugs and computer-generated molecular scaffolds. We discovered a potential off-target liability of fenofibrate-related compounds, and in a comprehensive prospective application, we identified a multitarget-modulating profile of de novo designed molecules. These results demonstrate that SPiDER may be used to identify innovative compounds in chemical biology and in the early stages of drug discovery, and help investigate the potential side effects of drugs and their repurposing options.
Asunto(s)
Ingeniería Química/métodos , Descubrimiento de Drogas/métodos , Reposicionamiento de Medicamentos/métodos , Sustancias Macromoleculares/química , Programas Informáticos , Inteligencia Artificial , PolifarmacologíaRESUMEN
The cyclodepsipeptide doliculide is a marine natural product with strong actin-polymerizing and anticancer activities. Evidence for doliculide acting as a potent and subtype-selective antagonist of prostanoidâ E receptor 3 (EP3) is presented. Computational target prediction suggested that this membrane receptor is a likely macromolecular target and enabled immediate inâ vitro validation. This proof-of-concept study demonstrates the inâ silico deorphanization of phenotypic screening hits as a viable concept for future natural-product-inspired chemical biology and drug discovery efforts.
Asunto(s)
Productos Biológicos/metabolismo , Depsipéptidos/metabolismo , Productos Biológicos/química , Depsipéptidos/síntesis química , Depsipéptidos/química , Diseño de Fármacos , Células HEK293 , Humanos , Cinética , Ligandos , Subtipo EP3 de Receptores de Prostaglandina E/antagonistas & inhibidores , Subtipo EP3 de Receptores de Prostaglandina E/genética , Subtipo EP3 de Receptores de Prostaglandina E/metabolismoRESUMEN
We present the application of the generative topographic map algorithm to visualize the chemical space populated by natural products and synthetic drugs. Generative topographic maps may be used for nonlinear dimensionality reduction and probabilistic modeling. For compound mapping, we represented the molecules by two-dimensional pharmacophore features (chemically advanced template search descriptor). The results obtained suggest a close resemblance of synthetic drugs with natural products in terms of their pharmacophore features, despite pronounced differences in chemical structure. Generative topographic map-based cluster analysis revealed both known and new potential activities of natural products and drug-like compounds. We conclude that the generative topographic map method is suitable for inferring functional similarities between these two classes of compounds and predicting macromolecular targets of natural products.
Asunto(s)
Productos Biológicos/química , Análisis por Conglomerados , Análisis de Componente Principal , ProbabilidadRESUMEN
Fragment-like natural products were identified as ligand-efficient chemical matter for hit-to-lead development and chemical-probe discovery. Relying on a computational method using a topological pharmacophore descriptor and a drug database, several macromolecular targets from distinct protein families were expeditiously retrieved for structurally unrelated chemotypes. The selected fragments feature structural dissimilarity to the reference compounds and suitable target affinity, and they offer opportunities for chemical optimization. Experimental confirmation of hitherto unknown macromolecular targets for the selected molecules corroborate the usefulness of the computational approach and suggests broad applicability to chemical biology and molecular medicine.
Asunto(s)
Productos Biológicos/química , Sustancias Macromoleculares/químicaRESUMEN
We report a multi-objective deâ novo design study driven by synthetic tractability and aimed at the prioritization of computer-generated 5-HT2B receptor ligands with accurately predicted target-binding affinities. Relying on quantitative bioactivity models we designed and synthesized structurally novel, selective, nanomolar, and ligand-efficient 5-HT2B modulators with sustained cell-based effects. Our results suggest that seamless amalgamation of computational activity prediction and molecular design with microfluidics-assisted synthesis enables the swift generation of small molecules with the desired polypharmacology.
Asunto(s)
Ligandos , Receptor de Serotonina 5-HT2B/química , Aminas/síntesis química , Aminas/química , Diseño Asistido por Computadora , Diseño de Fármacos , Humanos , Microfluídica , Unión Proteica , Receptor de Serotonina 5-HT2B/metabolismo , Antagonistas del Receptor de Serotonina 5-HT2/química , Antagonistas del Receptor de Serotonina 5-HT2/metabolismoRESUMEN
Automated molecular deâ novo design led to the discovery of an innovative inhibitor of death-associated protein kinaseâ 3 (DAPK3). An unprecedented crystal structure of the inactive DAPK3 homodimer shows the fragment-like hit bound to the ATP pocket. Target prediction software based on machine learning models correctly identified additional macromolecular targets of the computationally designed compound and the structurally related marketed drug azosemide. The study validates computational deâ novo design as a prime method for generating chemical probes and starting points for drug discovery.
Asunto(s)
Proteínas Quinasas Asociadas a Muerte Celular/antagonistas & inhibidores , Descubrimiento de Drogas , Inhibidores de Proteínas Quinasas/farmacología , Proteínas Quinasas Asociadas a Muerte Celular/metabolismo , Relación Dosis-Respuesta a Droga , Humanos , Estructura Molecular , Inhibidores de Proteínas Quinasas/síntesis química , Inhibidores de Proteínas Quinasas/química , Relación Estructura-ActividadRESUMEN
Sustained identification of innovative chemical entities is key for the success of chemical biology and drug discovery. We report the fragment-based, computer-assisted deâ novo design of a small molecule inhibiting Helicobacter pylori HtrA protease. Molecular binding of the designed compound to HtrA was confirmed through biophysical methods, supporting its functional activity in vitro. Hit expansion led to the identification of the currently best-in-class HtrA inhibitor. The results obtained reinforce the validity of ligand-based deâ novo design and binding-kinetics-guided optimization for the efficient discovery of pioneering lead structures and prototyping drug-like chemical probes with tailored bioactivity.
Asunto(s)
Proteínas Bacterianas/antagonistas & inhibidores , Diseño de Fármacos , Infecciones por Helicobacter/tratamiento farmacológico , Helicobacter pylori/efectos de los fármacos , Péptido Hidrolasas/química , Inhibidores de Proteasas/farmacología , Bibliotecas de Moléculas Pequeñas/farmacología , Diseño Asistido por Computadora , Descubrimiento de Drogas , Infecciones por Helicobacter/microbiología , Helicobacter pylori/enzimología , Humanos , Ligandos , Relación Estructura-ActividadRESUMEN
Predicting the macromolecular targets of drug-like molecules has become everyday practice in medicinal chemistry. We present an overview of our recent research activities in the area of polypharmacology-guided drug design. A focus is put on the self-organizing map (SOM) as a tool for compound clustering and visualization. We show how the SOM can be efficiently used for target-panel prediction, drug re-purposing, and the design of focused compound libraries. We also present the concept of virtual organic synthesis in combination with quantitative estimates of ligand-receptor binding, which we used for de novo designing target-selective ligands. We expect these and related approaches to enable the future discovery of personalized medicines.
Asunto(s)
Química Farmacéutica , Diseño de Fármacos , Polifarmacología , Algoritmos , Descubrimiento de Drogas , Sustancias Macromoleculares , Unión ProteicaRESUMEN
The discovery of pyrrolopyrazines as potent antimalarial agents is presented, with the most effective compounds exhibiting EC50 values in the low nanomolar range against asexual blood stages of Plasmodium falciparum in human red blood cells, and Plasmodium berghei liver schizonts, with negligible HepG2 cytotoxicity. Their potential mode of action is uncovered by predicting macromolecular targets through avant-garde computer modeling. The consensus prediction method suggested a functional resemblance between ligand binding sites in non-homologous target proteins, linking the observed parasite elimination to IspD, an enzyme from the non-mevalonate pathway of isoprenoid biosynthesis, and multi-kinase inhibition. Further computational analysis suggested essential P. falciparum kinases as likely targets of our lead compound. The results obtained validate our methodology for ligand- and structure-based target prediction, expand the bioinformatics toolbox for proteome mining, and provide unique access to deciphering polypharmacological effects of bioactive chemical agents.
Asunto(s)
Antimaláricos/química , Piridazinas/química , Pirroles/química , Antimaláricos/toxicidad , Supervivencia Celular/efectos de los fármacos , Diseño de Fármacos , Eritrocitos/parasitología , Células Hep G2 , Humanos , Plasmodium berghei/efectos de los fármacos , Plasmodium falciparum/efectos de los fármacos , Proteínas Quinasas/química , Proteínas Quinasas/metabolismo , Proteínas Protozoarias/antagonistas & inhibidores , Proteínas Protozoarias/metabolismo , Piridazinas/toxicidad , Pirroles/toxicidadRESUMEN
Molecular machine learning algorithms are becoming increasingly powerful at predicting the potency of potential drug candidates to guide molecular discovery, lead series prioritization, and structural optimization. However, a substantial amount of inhibition data is bounded and inaccessible to traditional regression algorithms. Here, we develop a novel molecular pairing approach to process this data. This creates a new classification task of predicting which one of two paired molecules is more potent. This novel classification task can be accurately solved by various, established molecular machine learning algorithms, including XGBoost and Chemprop. Across 230 ChEMBL IC50 datasets, both tree-based and neural network-based "DeltaClassifiers" show improvements over traditional regression approaches in correctly classifying molecular potency improvements. The Chemprop-based deep DeltaClassifier outperformed all here evaluated regression approaches for paired molecules with shared and with distinct scaffolds, highlighting the promise of this approach for molecular optimization and scaffold-hopping.
RESUMEN
Prodrugs are derivatives with superior properties compared with the parent active pharmaceutical ingredient (API), which undergo biotransformation after administration to generate the API in situ. Although sharing this general characteristic, prodrugs encompass a wide range of different chemical structures, therapeutic indications and properties. Here we provide the first holistic analysis of the current landscape of approved prodrugs using cheminformatics and data science approaches to reveal trends in prodrug development. We highlight rationales that underlie prodrug design, their indications, mechanisms of API release, the chemistry of promoieties added to APIs to form prodrugs and the market impact of prodrugs. On the basis of this analysis, we discuss strengths and limitations of current prodrug approaches and suggest areas for future development.
Asunto(s)
Profármacos , Profármacos/farmacología , Profármacos/química , Humanos , Animales , Diseño de Fármacos , Desarrollo de Medicamentos/métodosRESUMEN
Computation promises to accelerate, de-risk and optimize drug research and development. An increasing number of companies have entered this space, specializing in the design of new algorithms, computing on proprietary data, and/or development of hardware to improve distinct drug pipeline stages. The large number of such companies and their unique strategies and deals have created a highly complex and competitive industry. We comprehensively analyze the companies in this space to highlight trends and opportunities, identifying highly occupied areas of risk and currently underrepresented niches of high value.
Asunto(s)
Algoritmos , Industria Farmacéutica , Desarrollo de MedicamentosRESUMEN
Triggerable coatings, such as pH-responsive polymethacrylate copolymers, can be used to protect the active pharmaceutical ingredients contained within oral solid dosage forms from the acidic gastric environment and to facilitate drug delivery directly to the intestine. However, gastrointestinal pH can be highly variable, which can reduce delivery efficiency when using pH-responsive drug delivery technologies. We hypothesized that biomaterials susceptible to proteolysis could be used in combination with other triggerable polymers to develop novel enteric coatings. Bioinformatic analysis suggested that silk fibroin is selectively degradable by enzymes in the small intestine, including chymotrypsin, but resilient to gastric pepsin. Based on the analysis, we developed a silk fibroin-polymethacrylate copolymer coating for oral dosage forms. In vitro and in vivo studies demonstrated that capsules coated with this novel silk fibroin formulation enable pancreatin-dependent drug release. We believe that this novel formulation and extensions thereof have the potential to produce more effective and personalized oral drug delivery systems for vulnerable populations including patients that have impaired and highly variable intestinal physiology.