Integrating Clinical Variability into PBPK Models for Virtual Bioequivalence of Single and Multiple Doses of Tofacitinib Modified-Release Dosage Form.

Tofacitinib is a potent, selective inhibitor of the Janus kinase (JAK) family of kinases with a high degree of selectivity within the human genome's set of protein kinases. Currently approved formulations for tofacitinib citrate are immediate-release (IR) tablets, modified-release (MR) tablets, and IR solution. A once daily MR microsphere formulation was developed for use in pediatric patients. Demonstration of bioequivalence (BE) between the 10 mg once daily (q.d.) MR microsphere formulation and 5 mg twice daily (b.i.d.) IR solution is needed to enable the exposure-response analyses-based bridging to support regulatory approval. To assess BE between MR microsphere and IR solution, an innovative approach was utilized with physiologically-based pharmacokinetic (PBPK) virtual BE trials (VBE) in lieu of a clinical BE trial. A PBPK model was developed to characterize the absorption of different formulations of tofacitinib using Simcyp ADAM module. VBE trials were conducted by simulating PK profiles using the verified PBPK model and integrating the clinically observed intrasubject coefficient of variation (ICV) where BE was assessed with a predetermined sample size and prespecified criteria. The VBE trials demonstrated BE between IR solution 5 mg b.i.d. and MR microsphere 10 mg q.d. after a single dose on day 1 and after multiple doses on day 5. This research presents an innovative approach that incorporates clinically observed ICV in PBPK model-based VBE trials, which could reduce unnecessary drug exposure to healthy volunteers and streamline new formulation development strategies.

Adaptive language model training for molecular design.

The vast size of chemical space necessitates computational approaches to automate and accelerate the design of molecular sequences to guide experimental efforts for drug discovery. Genetic algorithms provide a useful framework to incrementally generate molecules by applying mutations to known chemical structures. Recently, masked language models have been applied to automate the mutation process by leveraging large compound libraries to learn commonly occurring chemical sequences (i.e., using tokenization) and predict rearrangements (i.e., using mask prediction). Here, we consider how language models can be adapted to improve molecule generation for different optimization tasks. We use two different generation strategies for comparison, fixed and adaptive. The fixed strategy uses a pre-trained model to generate mutations; the adaptive strategy trains the language model on each new generation of molecules selected for target properties during optimization. Our results show that the adaptive strategy allows the language model to more closely fit the distribution of molecules in the population. Therefore, for enhanced fitness optimization, we suggest the use of the fixed strategy during an initial phase followed by the use of the adaptive strategy. We demonstrate the impact of adaptive training by searching for molecules that optimize both heuristic metrics, drug-likeness and synthesizability, as well as predicted protein binding affinity from a surrogate model. Our results show that the adaptive strategy provides a significant improvement in fitness optimization compared to the fixed pre-trained model, empowering the application of language models to molecular design tasks.

Tratamiento con atovacuona-proguanil para casos de malaria por Plasmodium falciparum sin complicaciones / Atovaquone-proguanil for treating uncomplicated Plasmodium falciparum malaria

Pregunta. ¿Cuáles son los beneficios y los riesgos de la atovacuona-proguanil para tratar los casos sin complicaciones de malaria provocada por el parásito Plasmodium falciparum?Fundamento. El tipo de malaria más común y grave es el causado por Plasmodium falciparum. En su forma menos agresiva (sin complicaciones), los síntomas son fiebre, dolores de cabeza, dolor muscular y vómitos. La enfermedad puede convertirse en grave y mortal si no se la trata con rapidez o con la medicación adecuada. Esta revisión tiene por objetivo descubrir si la atovacuona-proguanil es efectiva y segura para tratar los casos de malaria por Plasmodium falciparum sin complicaciones. El procedimiento fue comparar los resultados de estudios que comparaban la atovacuona-proguanil con otros tratamientos. Como mensajes clave destacamos que la atovacuona-proguanil es tan efectiva para tratar los casos sin complicación de malaria por Plasmodium falciparum como el artesunato-mefloquina. Puede resultar menos efectiva que el artemeter-lumefantrine, artesunato-amodiaquino y artesunato-atovacuona-proguanil, pero hacen falta evidencias más robustas para confirmarlo. Los efectos secundarios parecen similares con la atovacuona-proguanil.Fecha de investigación. Las evidencias de esta revisión están actualizadas hasta el 30 de enero de 2020. (AU)

Scalable training of graph convolutional neural networks for fast and accurate predictions of HOMO-LUMO gap in molecules.

Graph Convolutional Neural Network (GCNN) is a popular class of deep learning (DL) models in material science to predict material properties from the graph representation of molecular structures. Training an accurate and comprehensive GCNN surrogate for molecular design requires large-scale graph datasets and is usually a time-consuming process. Recent advances in GPUs and distributed computing open a path to reduce the computational cost for GCNN training effectively. However, efficient utilization of high performance computing (HPC) resources for training requires simultaneously optimizing large-scale data management and scalable stochastic batched optimization techniques. In this work, we focus on building GCNN models on HPC systems to predict material properties of millions of molecules. We use HydraGNN, our in-house library for large-scale GCNN training, leveraging distributed data parallelism in PyTorch. We use ADIOS, a high-performance data management framework for efficient storage and reading of large molecular graph data. We perform parallel training on two open-source large-scale graph datasets to build a GCNN predictor for an important quantum property known as the HOMO-LUMO gap. We measure the scalability, accuracy, and convergence of our approach on two DOE supercomputers: the Summit supercomputer at the Oak Ridge Leadership Computing Facility (OLCF) and the Perlmutter system at the National Energy Research Scientific Computing Center (NERSC). We present our experimental results with HydraGNN showing (i) reduction of data loading time up to 4.2 times compared with a conventional method and (ii) linear scaling performance for training up to 1024 GPUs on both Summit and Perlmutter.

Using ensembles and distillation to optimize the deployment of deep learning models for the classification of electronic cancer pathology reports.

Objective: We aim to reduce overfitting and model overconfidence by distilling the knowledge of an ensemble of deep learning models into a single model for the classification of cancer pathology reports. Materials and Methods: We consider the text classification problem that involves 5 individual tasks. The baseline model consists of a multitask convolutional neural network (MtCNN), and the implemented ensemble (teacher) consists of 1000 MtCNNs. We performed knowledge transfer by training a single model (student) with soft labels derived through the aggregation of ensemble predictions. We evaluate performance based on accuracy and abstention rates by using softmax thresholding. Results: The student model outperforms the baseline MtCNN in terms of abstention rates and accuracy, thereby allowing the model to be used with a larger volume of documents when deployed. The highest boost was observed for subsite and histology, for which the student model classified an additional 1.81% reports for subsite and 3.33% reports for histology. Discussion: Ensemble predictions provide a useful strategy for quantifying the uncertainty inherent in labeled data and thereby enable the construction of soft labels with estimated probabilities for multiple classes for a given document. Training models with the derived soft labels reduce model confidence in difficult-to-classify documents, thereby leading to a reduction in the number of highly confident wrong predictions. Conclusions: Ensemble model distillation is a simple tool to reduce model overconfidence in problems with extreme class imbalance and noisy datasets. These methods can facilitate the deployment of deep learning models in high-risk domains with low computational resources where minimizing inference time is required.

Optimal vocabulary selection approaches for privacy-preserving deep NLP model training for information extraction and cancer epidemiology.

BACKGROUND: With the use of artificial intelligence and machine learning techniques for biomedical informatics, security and privacy concerns over the data and subject identities have also become an important issue and essential research topic. Without intentional safeguards, machine learning models may find patterns and features to improve task performance that are associated with private personal information. OBJECTIVE: The privacy vulnerability of deep learning models for information extraction from medical textural contents needs to be quantified since the models are exposed to private health information and personally identifiable information. The objective of the study is to quantify the privacy vulnerability of the deep learning models for natural language processing and explore a proper way of securing patients' information to mitigate confidentiality breaches. METHODS: The target model is the multitask convolutional neural network for information extraction from cancer pathology reports, where the data for training the model are from multiple state population-based cancer registries. This study proposes the following schemes to collect vocabularies from the cancer pathology reports; (a) words appearing in multiple registries, and (b) words that have higher mutual information. We performed membership inference attacks on the models in high-performance computing environments. RESULTS: The comparison outcomes suggest that the proposed vocabulary selection methods resulted in lower privacy vulnerability while maintaining the same level of clinical task performance.

A Keyword-Enhanced Approach to Handle Class Imbalance in Clinical Text Classification.

Recent applications ofdeep learning have shown promising results for classifying unstructured text in the healthcare domain. However, the reliability of models in production settings has been hindered by imbalanced data sets in which a small subset of the classes dominate. In the absence of adequate training data, rare classes necessitate additional model constraints for robust performance. Here, we present a strategy for incorporating short sequences of text (i.e. keywords) into training to boost model accuracy on rare classes. In our approach, we assemble a set of keywords, including short phrases, associated with each class. The keywords are then used as additional data during each batch of model training, resulting in a training loss that has contributions from both raw data and keywords. We evaluate our approach on classification of cancer pathology reports, which shows a substantial increase in model performance for rare classes. Furthermore, we analyze the impact of keywords on model output probabilities for bigrams, providing a straightforward method to identify model difficulties for limited training data.

Language models for the prediction of SARS-CoV-2 inhibitors.

The COVID-19 pandemic highlights the need for computational tools to automate and accelerate drug design for novel protein targets. We leverage deep learning language models to generate and score drug candidates based on predicted protein binding affinity. We pre-trained a deep learning language model (BERT) on ∼9.6 billion molecules and achieved peak performance of 603 petaflops in mixed precision. Our work reduces pre-training time from days to hours, compared to previous efforts with this architecture, while also increasing the dataset size by nearly an order of magnitude. For scoring, we fine-tuned the language model using an assembled set of thousands of protein targets with binding affinity data and searched for inhibitors of specific protein targets, SARS-CoV-2 Mpro and PLpro. We utilized a genetic algorithm approach for finding optimal candidates using the generation and scoring capabilities of the language model. Our generalizable models accelerate the identification of inhibitors for emerging therapeutic targets.

Developing a Biorelevant Dissolution Method for an Extrudable Core System (ECS) Osmotic Tablet.

The objective of this work is to develop a biorelevant dissolution method to support the clinical study for In Vitro In Vivo Correlation (IVIVC) of the first commercially approved single-layer extrudable core system (ECS) osmotic tablet - the 11 mg tofacitinib modified-release tablet. The dissolution conditions were selected through analysis of experimental work including several designed experiments (DoE). The Apparatus 2 (paddles) was selected over the Apparatus 1 (baskets) to minimize the dissolution test variability. The paddle speed was kept at 50 rpm to be conservative and because higher paddle speed did not offer statistically significant improvement in dissolution test variability. The buffer of 50 mM potassium phosphate at pH 6.8 was selected over other buffers at lower or acid pH as the in vivo drug release is expected to occur in the small intestinal region, where the pH is approximately neutral. Finally, the statistically designed experiments proved that use of the Japanese basket sinkers was effective in reducing dissolution variability and eliminating the artificial shift in dissolution profile caused by final pink color-coated tablets sticking to the dissolution vessel. Discriminatory power of the method was verified and the method was validated per ICH and FDA guidelines. Since a Level A IVIVC is established from the analysis of the results of both in vivo clinical study and in vitro dissolution testing, the method is proven to be biorelevant. It also serves a suitable quality control dissolution method.

Repulsive expansion dynamics in colony growth and gene expression.

Spatial expansion of a population of cells can arise from growth of microorganisms, plant cells, and mammalian cells. It underlies normal or dysfunctional tissue development, and it can be exploited as the foundation for programming spatial patterns. This expansion is often driven by continuous growth and division of cells within a colony, which in turn pushes the peripheral cells outward. This process generates a repulsion velocity field at each location within the colony. Here we show that this process can be approximated as coarse-grained repulsive-expansion kinetics. This framework enables accurate and efficient simulation of growth and gene expression dynamics in radially symmetric colonies with homogenous z-directional distribution. It is robust even if cells are not spherical and vary in size. The simplicity of the resulting mathematical framework also greatly facilitates generation of mechanistic insights.

Using GANs with adaptive training data to search for new molecules.

The process of drug discovery involves a search over the space of all possible chemical compounds. Generative Adversarial Networks (GANs) provide a valuable tool towards exploring chemical space and optimizing known compounds for a desired functionality. Standard approaches to training GANs, however, can result in mode collapse, in which the generator primarily produces samples closely related to a small subset of the training data. In contrast, the search for novel compounds necessitates exploration beyond the original data. Here, we present an approach to training GANs that promotes incremental exploration and limits the impacts of mode collapse using concepts from Genetic Algorithms. In our approach, valid samples from the generator are used to replace samples from the training data. We consider both random and guided selection along with recombination during replacement. By tracking the number of novel compounds produced during training, we show that updates to the training data drastically outperform the traditional approach, increasing potential applications for GANs in drug discovery.

c-Rel orchestrates energy-dependent epithelial and macrophage reprogramming in fibrosis.

Fibrosis is a common pathological feature of chronic disease. Deletion of the NF-κB subunit c-Rel limits fibrosis in multiple organs, although the mechanistic nature of this protection is unresolved. Using cell-specific gene-targeting manipulations in mice undergoing liver damage, we elucidate a critical role for c-Rel in controlling metabolic changes required for inflammatory and fibrogenic activities of hepatocytes and macrophages and identify Pfkfb3 as the key downstream metabolic mediator of this response. Independent deletions of Rel in hepatocytes or macrophages suppressed liver fibrosis induced by carbon tetrachloride, while combined deletion had an additive anti-fibrogenic effect. In transforming growth factor-ß1-induced hepatocytes, c-Rel regulates expression of a pro-fibrogenic secretome comprising inflammatory molecules and connective tissue growth factor, the latter promoting collagen secretion from HMs. Macrophages lacking c-Rel fail to polarize to M1 or M2 states, explaining reduced fibrosis in RelΔLysM mice. Pharmacological inhibition of c-Rel attenuated multi-organ fibrosis in both murine and human fibrosis. In conclusion, activation of c-Rel/Pfkfb3 in damaged tissue instigates a paracrine signalling network among epithelial, myeloid and mesenchymal cells to stimulate fibrogenesis. Targeting the c-Rel-Pfkfb3 axis has potential for therapeutic applications in fibrotic disease.

Development and validation of a Level A in-vitro in-vivo correlation for tofacitinib modified-release tablets using extrudable core system osmotic delivery technology.

PURPOSE: To determine if a validated Level A in-vitro in-vivo correlation (IVIVC) could be achieved with the extrudable core system (ECS) osmotic tablet platform. Tofacitinib is an oral JAK inhibitor for the treatment of rheumatoid arthritis. METHODS: Fast-, medium-, and slow-release modified-release formulations of 11 mg tofacitinib ECS tablets, and one formulation of 22 mg tofacitinib ECS tablet, were manufactured. In vitro dissolution of the tofacitinib ECS tablets was performed using USP Apparatus 2 (paddles) and in vivo pharmacokinetic (PK) data were obtained from a Phase 1 study in healthy volunteers. A 5 mg immediate-release formulation tablet was included to support deconvolution of the tofacitinib ECS PK tablet data to obtain the in vivo absorption profiles. A linear, piecewise correlation and a simple linear correlation were used to build and validate two IVIVC models. RESULTS: The prediction errors (PEs) for the linear, piecewise correlation met the Food and Drug Administration's criteria for establishing a Level A IVIVC, with a maximum absolute individual internal PE of 4.6%, a maximum absolute average internal PE of 3.9%, and a maximum absolute external PE of 8.4% obtained. CONCLUSIONS: This study demonstrates that the tofacitinib ECS osmotic tablet platform can achieve a Level A IVIVC, similar to other osmotic delivery systems.

A high content, phenotypic 'scar-in-a-jar' assay for rapid quantification of collagen fibrillogenesis using disease-derived pulmonary fibroblasts.

BACKGROUND: Excessive extracellular matrix (ECM) deposition is a hallmark feature in fibrosis and tissue remodelling diseases. Typically, mesenchymal cells will produce collagens under standard 2D cell culture conditions, however these do not assemble into fibrils. Existing assays for measuring ECM production are often low throughput and not disease relevant. Here we describe a robust, high content, pseudo-3D phenotypic assay to quantify mature fibrillar collagen deposition which is both physiologically relevant and amenable to high throughput compound screening. Using pulmonary fibroblasts derived from patients with idiopathic pulmonary fibrosis (IPF), we developed the 'scar-in-a-jar' assay into a medium-throughput phenotypic assay to robustly quantify collagen type I deposition and other extracellular matrix (ECM) proteins over 72 h. RESULTS: This assay utilises macromolecular crowding to induce an excluded volume effect and enhance enzyme activity, which in combination with TGF-ß1 stimulation significantly accelerates ECM production. Collagen type I is upregulated approximately 5-fold with a negligible effect on cell number. We demonstrate the robustness of the assay achieving a Z prime of approximately 0.5, and % coefficient of variance (CV) of < 5 for the assay controls SB-525334 (ALK5 inhibitor) and CZ415 (mTOR inhibitor). This assay has been used to confirm the potency of a number of potential anti-fibrotic agents. Active compounds from the 'scar-in-a-jar' assay can be further validated for other markers of ECM deposition and fibroblast activation such as collagen type IV and α-smooth muscle actin exhibiting a 4-fold and 3-fold assay window respectively. CONCLUSION: In conclusion, we have developed 'scar -in-a-jar is' into a robust disease-relevant medium-throughput in vitro assay to accurately quantify ECM deposition. This assay may enable iterative compound profiling for IPF and other fibroproliferative and tissue remodelling diseases.

Spatial interference scale as a determinant of microbial range expansion.

In microbial communities, social interactions such as competition occur ubiquitously across multiple spatial scales from local proximity to remote distance. However, it remains unclear how such a spatial variation of interaction contributes to the structural development of microbial populations. Here, we developed synthetic consortia, biophysical theory, and simulations to elucidate the role of spatial interference scale in governing ecosystem organization during range expansion. For consortia with unidirectional interference, we discovered that, at growing fronts, the extinction time of toxin-sensitive species is reciprocal to the spatial interference scale. In contrast, for communities with bidirectional interference, their structures diverge into distinct monoculture colonies under different initial conditions, with the corresponding separatrix set by the spatial scale of interference. Near the separatrix, ecosystem development becomes noise-driven and yields opposite structures. Our results establish spatial interaction scale as a key determinant for microbial range expansion, providing insights into microbial spatial organization and synthetic ecosystem engineering.

Circuit-Host Coupling Induces Multifaceted Behavioral Modulations of a Gene Switch.

Quantitative modeling of gene circuits is fundamentally important to synthetic biology, as it offers the potential to transform circuit engineering from trial-and-error construction to rational design and, hence, facilitates the advance of the field. Currently, typical models regard gene circuits as isolated entities and focus only on the biochemical processes within the circuits. However, such a standard paradigm is getting challenged by increasing experimental evidence suggesting that circuits and their host are intimately connected, and their interactions can potentially impact circuit behaviors. Here we systematically examined the roles of circuit-host coupling in shaping circuit dynamics by using a self-activating gene switch as a model circuit. Through a combination of deterministic modeling, stochastic simulation, and Fokker-Planck equation formalism, we found that circuit-host coupling alters switch behaviors across multiple scales. At the single-cell level, it slows the switch dynamics in the high protein production regime and enlarges the difference between stable steady-state values. At the population level, it favors cells with low protein production through differential growth amplification. Together, the two-level coupling effects induce both quantitative and qualitative modulations of the switch, with the primary component of the effects determined by the circuit's architectural parameters. This study illustrates the complexity and importance of circuit-host coupling in modulating circuit behaviors, demonstrating the need for a new paradigm-integrated modeling of the circuit-host system-for quantitative understanding of engineered gene networks.

An integrative circuit-host modelling framework for predicting synthetic gene network behaviours.

One fundamental challenge in synthetic biology is the lack of quantitative tools that accurately describe and predict the behaviours of engineered gene circuits. This challenge arises from multiple factors, among which the complex interdependence of circuits and their host is a leading cause. Here we present a gene circuit modelling framework that explicitly integrates circuit behaviours with host physiology through bidirectional circuit-host coupling. The framework consists of a coarse-grained but mechanistic description of host physiology that involves dynamic resource partitioning, multilayered circuit-host coupling including both generic and system-specific interactions, and a detailed kinetic module of exogenous circuits. We showed that, following training, the framework was able to capture and predict a large set of experimental data concerning the host and its foreign gene overexpression. To demonstrate its utility, we applied the framework to examine a growth-modulating feedback circuit whose dynamics is qualitatively altered by circuit-host interactions. Using an extended version of the framework, we further systematically revealed the behaviours of a toggle switch across scales from single-cell dynamics to population structure and to spatial ecology. This work advances our quantitative understanding of gene circuit behaviours and also benefits the rational design of synthetic gene networks.

Host-Microbial Interactions in Idiopathic Pulmonary Fibrosis.

RATIONALE: Changes in the respiratory microbiome are associated with disease progression in idiopathic pulmonary fibrosis (IPF). The role of the host response to the respiratory microbiome remains unknown. OBJECTIVES: To explore the host-microbial interactions in IPF. METHODS: Sixty patients diagnosed with IPF were prospectively enrolled together with 20 matched control subjects. Subjects underwent bronchoalveolar lavage (BAL), and peripheral whole blood was collected into PAXgene tubes for all subjects at baseline. For subjects with IPF, additional samples were taken at 1, 3, and 6 months and (if alive) 1 year. Gene expression profiles were generated using Affymetrix Human Gene 1.1 ST arrays. MEASUREMENTS AND MAIN RESULTS: By network analysis of gene expression data, we identified two gene modules that strongly associated with a diagnosis of IPF, BAL bacterial burden (determined by 16S quantitative polymerase chain reaction), and specific microbial operational taxonomic units, as well as with lavage and peripheral blood neutrophilia. Genes within these modules that are involved in the host defense response include NLRC4, PGLYRP1, MMP9, and DEFA4. The modules also contain two genes encoding specific antimicrobial peptides (SLPI and CAMP). Many of these particular transcripts were associated with survival and showed longitudinal overexpression in subjects experiencing disease progression, further strengthening the relationship of the transcripts with disease. CONCLUSIONS: Integrated analysis of the host transcriptome and microbial signatures demonstrated an apparent host response to the presence of an altered or more abundant microbiome. These responses remained elevated in longitudinal follow-up, suggesting that the bacterial communities of the lower airways may act as persistent stimuli for repetitive alveolar injury in IPF.