ABSTRACT
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.
ABSTRACT
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.
Subject(s)
Computational Biology , Machine Learning , Computational Biology/methods , Models, Biological , Computer Simulation , Algorithms , Humans , Regression AnalysisABSTRACT
Owing to their distinct physical and chemical properties, inorganic nanoparticles (NPs) have shown promising results in preclinical cancer therapy, but designing and engineering them for effective therapeutic purposes remains a challenge. Although a comprehensive database of inorganic NP research is not currently available, it is crucial for developing effective cancer therapies. In this context, machine learning (ML) has emerged as a transformative tool, but its adaptation to nanomedicine is hindered by inexistent or small datasets. Here we assembled a large database of inorganic NPs, comprising experimental datasets from 745 preclinical studies in cancer nanomedicine. Using descriptive statistics and explainable ML models we mined this database to gain knowledge of inorganic NP design patterns and inform future NP research for cancer treatment. Our analyses suggest that NP shape and therapy type are prominent features in determining in vivo efficacy, measured as a percentage of tumour reduction. Moreover, our database provides a large-scale open-access resource for discriminative ML that the broader nanotechnology community can utilize. Our work blueprints data mining for translational cancer research and offers evidence for standardizing NP reporting to accelerate and de-risk inorganic NP-based drug delivery, which may help to improve patient outcomes in clinical settings.
Subject(s)
Machine Learning , Nanomedicine , Nanoparticles , Neoplasms , Nanoparticles/chemistry , Humans , Neoplasms/drug therapy , Animals , Nanomedicine/methods , Mice , Databases, Factual , Antineoplastic Agents/chemistry , Antineoplastic Agents/therapeutic use , Antineoplastic Agents/administration & dosageABSTRACT
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.
Subject(s)
Prodrugs , Prodrugs/pharmacology , Prodrugs/chemistry , Humans , Animals , Drug Design , Drug Development/methodsABSTRACT
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.
Subject(s)
Algorithms , Drug Industry , Drug DevelopmentABSTRACT
In vitro systems that accurately model in vivo conditions in the gastrointestinal tract may aid the development of oral drugs with greater bioavailability. Here we show that the interaction profiles between drugs and intestinal drug transporters can be obtained by modulating transporter expression in intact porcine tissue explants via the ultrasound-mediated delivery of small interfering RNAs and that the interaction profiles can be classified via a random forest model trained on the drug-transporter relationships. For 24 drugs with well-characterized drug-transporter interactions, the model achieved 100% concordance. For 28 clinical drugs and 22 investigational drugs, the model identified 58 unknown drug-transporter interactions, 7 of which (out of 8 tested) corresponded to drug-pharmacokinetic measurements in mice. We also validated the model's predictions for interactions between doxycycline and four drugs (warfarin, tacrolimus, digoxin and levetiracetam) through an ex vivo perfusion assay and the analysis of pharmacologic data from patients. Screening drugs for their interactions with the intestinal transportome via tissue explants and machine learning may help to expedite drug development and the evaluation of drug safety.
Subject(s)
Intestines , Machine Learning , Humans , Animals , Mice , Swine , Pharmaceutical Preparations/metabolism , Drug Interactions , Biological AvailabilityABSTRACT
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.
Subject(s)
Fibroins , Humans , Pancreatin , Drug Delivery Systems , Polymethacrylic Acids , Polymers , SilkABSTRACT
Established molecular machine learning models process individual molecules as inputs to predict their biological, chemical, or physical properties. However, such algorithms require large datasets and have not been optimized to predict property differences between molecules, limiting their ability to learn from smaller datasets and to directly compare the anticipated properties of two molecules. Many drug and material development tasks would benefit from an algorithm that can directly compare two molecules to guide molecular optimization and prioritization, especially for tasks with limited available data. Here, we develop DeepDelta, a pairwise deep learning approach that processes two molecules simultaneously and learns to predict property differences between two molecules from small datasets. On 10 ADMET benchmark tasks, our DeepDelta approach significantly outperforms two established molecular machine learning algorithms, the directed message passing neural network (D-MPNN) ChemProp and Random Forest using radial fingerprints, for 70% of benchmarks in terms of Pearson's r, 60% of benchmarks in terms of mean absolute error (MAE), and all external test sets for both Pearson's r and MAE. We further analyze our performance and find that DeepDelta is particularly outperforming established approaches at predicting large differences in molecular properties and can perform scaffold hopping. Furthermore, we derive mathematically fundamental computational tests of our models based on mathematical invariants and show that compliance to these tests correlates with overall model performance - providing an innovative, unsupervised, and easily computable measure of expected model performance and applicability. Taken together, DeepDelta provides an accurate approach to predict molecular property differences by directly training on molecular pairs and their property differences to further support fidelity and transparency in molecular optimization for drug development and the chemical sciences.
ABSTRACT
Developments in computational omics technologies have provided new means to access the hidden diversity of natural products, unearthing new potential for drug discovery. In parallel, artificial intelligence approaches such as machine learning have led to exciting developments in the computational drug design field, facilitating biological activity prediction and de novo drug design for molecular targets of interest. Here, we describe current and future synergies between these developments to effectively identify drug candidates from the plethora of molecules produced by nature. We also discuss how to address key challenges in realizing the potential of these synergies, such as the need for high-quality datasets to train deep learning algorithms and appropriate strategies for algorithm validation.
Subject(s)
Artificial Intelligence , Biological Products , Humans , Algorithms , Machine Learning , Drug Discovery , Drug Design , Biological Products/pharmacologyABSTRACT
BACKGROUND: Patients undergoing cardiac surgery are prone to numerous complications. Increased vascular permeability may be associated with morbidity and mortality due to hemodynamic instability, fluid overload, and edema formation. We hypothesized that markers of endothelial injury and inflammation are associated with capillary leak, ultimately increasing the risk of postoperative complications. METHODS: In this prospective, observational, multidisciplinary cohort study at our tertiary academic medical center, we recruited 405 cardiac surgery patients. Patients were assessed daily using body impedance electrical analysis, ultrasound, sublingual intravital microscopy, and analysis of serum biomarkers. Multivariable models, as well as machine learning, were used to study the association of angiopoietin-2 with extracellular water as well as common complications after cardiac surgery. RESULTS: The majority of patients underwent coronary artery bypass grafting, valvular, or aortic surgeries. Across the groups, extracellular water increased postoperatively (20 ± 6 preoperatively to 29 ± 7L on postoperative day 2; P < 0.001). Concomitantly, the levels of the biomarker angiopoietin-2 rose, showing a strong correlation based on the time points of measurements (r = 0.959, P = 0.041). Inflammatory (IL-6, IL-8, CRP) and endothelial biomarkers (VE-Cadherin, syndecan-1, ICAM-1) suggestive of capillary leak were increased. After controlling for common risk factors of edema formation, we found that an increase of 1 ng/mL in angiopoietin-2 was associated with a 0.24L increase in extracellular water (P < 0.001). Angiopoietin-2 showed increased odds for the development of acute kidney injury (OR 1.095 [95% CI 1.032, 1.169]; P = 0.004) and was furthermore associated with delayed extubation, longer time in the ICU, and a higher chance of prolonged dependence on vasoactive medication. Machine learning predicted postoperative complications when capillary leak was added to standard risk factors. CONCLUSIONS: Capillary leak and subsequent edema formation are relevant problems after cardiac surgery. Levels of angiopoietin-2 in combination with extracellular water show promising potential to predict postoperative complications after cardiac surgery. TRIAL REGISTRATION NUMBER: German Clinical Trials Registry (DRKS No. 00017057), Date of registration 05/04/2019, www.drks.de.
ABSTRACT
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.
ABSTRACT
BACKGROUND: The concomitant occurrence of the symptoms intravascular hypovolemia, peripheral edema and hemodynamic instability is typically named Capillary Leak Syndrome (CLS) and often occurs in surgical critical ill patients. However, neither a unitary definition nor standardized diagnostic criteria exist so far. We aimed to investigate common characteristics of this phenomenon with a subsequent scoring system, determining whether CLS contributes to mortality. METHODS: We conducted this single-center, observational, multidisciplinary, prospective trial in two separately run surgical ICUs of a tertiary academic medical center. 200 surgical patients admitted to the ICU and 30 healthy volunteers were included. Patients were clinically diagnosed as CLS or No-CLS group (each N = 100) according to the grade of edema, intravascular hypovolemia, hemodynamic instability, and positive fluid balance by two independent attending physicians with > 10 years of experience in ICU. We performed daily measurements with non-invasive body impedance electrical analysis, ultrasound and analysis of serum biomarkers to generate objective diagnostic criteria. Receiver operating characteristics were used, while we developed machine learning models to increase diagnostic specifications for our scoring model. RESULTS: The 30-day mortility was increased among CLS patients (12 vs. 1%, P = 0.002), while showing higher SOFA-scores. Extracellular water was increased in patients with CLS with higher echogenicity of subcutaneous tissue [29(24-31) vs. 19(16-21), P < 0.001]. Biomarkers showed characteristic alterations, especially with an increased angiopoietin-2 concentration in CLS [9.9(6.2-17.3) vs. 3.7(2.6-5.6)ng/mL, P < 0.001]. We developed a score using seven parameters (echogenicity, SOFA-score, angiopoietin-2, syndecan-1, ICAM-1, lactate and interleukin-6). A Random Forest prediction model boosted its diagnostic characteristics (AUC 0.963, P < 0.001), while a two-parameter decision tree model showed good specifications (AUC 0.865). CONCLUSIONS: Diagnosis of CLS in critically ill patients is feasible by objective, non-invasive parameters using the CLS-Score. A simplified two-parameter diagnostic approach can enhance clinical utility. CLS contributes to mortality and should, therefore, classified as an independent entity. TRIAL REGISTRATION: German Clinical Trials Registry (DRKS No. 00012713), Date of registration 10/05/2017, www.drks.de.
ABSTRACT
Continuous monitoring in the intensive care setting has transformed the capacity to rapidly respond with interventions for patients in extremis. Noninvasive monitoring has generally been limited to transdermal or intravascular systems coupled to transducers including oxygen saturation or pressure. Here it is hypothesized that gastric fluid (GF) and gases, accessible through nasogastric (NG) tubes, commonly found in intensive care settings, can provide continuous access to a broad range of biomarkers. A broad characterization of biomarkers in swine GF coupled to time-matched serum is conducted . The relationship and kinetics of GF-derived analyte level dynamics is established by correlating these to serum levels in an acute renal failure and an inducible stress model performed in swine. The ability to monitor ketone levels and an inhaled anaesthetic agent (isoflurane) in vivo is demonstrated with novel NG-compatible sensor systems in swine. Gastric access remains a main stay in the care of the critically ill patient, and here the potential is established to harness this establishes route for analyte evaluation for clinical management.
Subject(s)
Acute Kidney Injury/metabolism , Anesthetics, Inhalation/metabolism , Gastric Juice/metabolism , Isoflurane/metabolism , Monitoring, Physiologic/methods , Animals , Biomarkers/metabolism , Disease Models, Animal , Intubation, Gastrointestinal , Ketones/metabolism , Stomach/metabolism , SwineABSTRACT
Nanoformulations of therapeutic drugs are transforming our ability to effectively deliver and treat a myriad of conditions. Often, however, they are complex to produce and exhibit low drug loading, except for nanoparticles formed via co-assembly of drugs and small molecular dyes, which display drug-loading capacities of up to 95%. There is currently no understanding of which of the millions of small-molecule combinations can result in the formation of these nanoparticles. Here we report the integration of machine learning with high-throughput experimentation to enable the rapid and large-scale identification of such nanoformulations. We identified 100 self-assembling drug nanoparticles from 2.1 million pairings, each including one of 788 candidate drugs and one of 2,686 approved excipients. We further characterized two nanoparticles, sorafenib-glycyrrhizin and terbinafine-taurocholic acid both ex vivo and in vivo. We anticipate that our platform can accelerate the development of safer and more efficacious nanoformulations with high drug-loading capacities for a wide range of therapeutics.
Subject(s)
Drug Carriers/chemistry , High-Throughput Screening Assays/methods , Nanoparticles/chemistry , Sorafenib/pharmacology , Terbinafine/pharmacology , Animals , Candida albicans/drug effects , Computer Simulation , Drug Carriers/chemical synthesis , Drug Design , Drug Evaluation, Preclinical/methods , Dynamic Light Scattering , Excipients/chemistry , Female , Glycyrrhizic Acid/chemistry , Humans , Machine Learning , Mice, Inbred Strains , Skin Absorption , Sorafenib/chemistry , Sorafenib/pharmacokinetics , Taurocholic Acid/chemistry , Terbinafine/chemistry , Tissue Distribution , Xenograft Model Antitumor AssaysABSTRACT
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.
Subject(s)
Clinical Competence/statistics & numerical data , Drug Compounding/history , Pharmaceutic Aids/adverse effects , Prescription Drugs/chemistry , Drug Prescriptions , History, 20th Century , History, 21st Century , Humans , Pharmaceutic Aids/chemistry , Pharmaceutic Aids/history , Prescription Drugs/adverse effects , Prescription Drugs/history , Surveys and Questionnaires/statistics & numerical dataSubject(s)
Artificial Intelligence , Drug Design , Algorithms , Big Data , Databases, Chemical , Drug Discovery , Humans , Machine LearningABSTRACT
Monolayers of cancer-derived cell lines are widely used in the modelling of the gastrointestinal (GI) absorption of drugs and in oral drug development. However, they do not generally predict drug absorption in vivo. Here, we report a robotically handled system that uses large porcine GI tissue explants that are functionally maintained for an extended period in culture for the high-throughput interrogation (several thousand samples per day) of whole segments of the GI tract. The automated culture system provided higher predictability of drug absorption in the human GI tract than a Caco-2 Transwell system (Spearman's correlation coefficients of 0.906 and 0.302, respectively). By using the culture system to analyse the intestinal absorption of 2,930 formulations of the peptide drug oxytocin, we discovered an absorption enhancer that resulted in a 11.3-fold increase in the oral bioavailability of oxytocin in pigs in the absence of cellular disruption of the intestinal tissue. The robotically handled whole-tissue culture system should help advance the development of oral drug formulations and might also be useful for drug screening applications.
Subject(s)
Drug Compounding , Drug Evaluation, Preclinical , Robotics , Tissue Culture Techniques/methods , Administration, Oral , Animals , Biological Transport/drug effects , Caco-2 Cells , Humans , Intestinal Absorption , Jejunum/physiology , Oxytocin/administration & dosage , Oxytocin/pharmacokinetics , Oxytocin/pharmacology , Permeability , Reproducibility of Results , Swine , User-Computer InterfaceABSTRACT
Inactive ingredients and generally recognized as safe compounds are regarded by the US Food and Drug Administration (FDA) as benign for human consumption within specified dose ranges, but a growing body of research has revealed that many inactive ingredients might have unknown biological effects at these concentrations and might alter treatment outcomes. To speed up such discoveries, we apply state-of-the-art machine learning to delineate currently unknown biological effects of inactive ingredients-focusing on P-glycoprotein (P-gp) and uridine diphosphate-glucuronosyltransferase-2B7 (UGT2B7), two proteins that impact the pharmacokinetics of approximately 20% of FDA-approved drugs. Our platform identifies vitamin A palmitate and abietic acid as inhibitors of P-gp and UGT2B7, respectively; in silico, in vitro, ex vivo, and in vivo validations support these interactions. Our predictive framework can elucidate biological effects of commonly consumed chemical matter with implications on food- and excipient-drug interactions and functional drug formulation development.