Drug safety assessment by machine learning models.

The evaluation of drug-induced Torsades de pointes (TdP) risks is crucial in drug safety assessment. In this study, we discuss machine learning approaches in the prediction of drug-induced TdP risks using preclinical data. Specifically, a random forest model was trained on the dataset generated by the rabbit ventricular wedge assay. The model prediction performance was measured on 28 drugs from the Comprehensive In Vitro Proarrhythmia Assay initiative. Leave-one-drug-out cross-validation provided an unbiased estimation of model performance. Stratified bootstrap revealed the uncertainty in the asymptotic model prediction. Our study validated the utility of machine learning approaches in predicting drug-induced TdP risks from preclinical data. Our methods can be extended to other preclinical protocols and serve as a supplementary evaluation in drug safety assessment.

Alveolar Type 2 Epithelial Cell Organoids: Focus on Culture Methods.

Lung diseases rank third in terms of mortality and represent a significant economic burden globally. Scientists have been conducting research to better understand respiratory diseases and find treatments for them. An ideal in vitro model must mimic the in vivo organ structure, physiology, and pathology. Organoids are self-organizing, three-dimensional (3D) structures originating from adult stem cells, embryonic lung bud progenitors, embryonic stem cells (ESCs), and induced pluripotent stem cells (iPSCs). These 3D organoid cultures may provide a platform for exploring tissue development, the regulatory mechanisms related to the repair of lung epithelia, pathophysiological and immunomodulatory responses to different respiratory conditions, and screening compounds for new drugs. To create 3D lung organoids in vitro, both co-culture and feeder-free methods have been used. However, there exists substantial heterogeneity in the organoid culture methods, including the sources of AT2 cells, media composition, and feeder cell origins. This article highlights the currently available methods for growing AT2 organoids and prospective improvements to improve the available culture techniques/conditions. Further, we discuss various applications, particularly those aimed at modeling human distal lung diseases and cell therapy.

Regenerative Signatures in Bronchioalveolar Lavage of Acute Respiratory Distress Syndrome.

Background: In patients with severe acute respiratory distress syndrome (ARDS) associated with sepsis, lung recovery is considerably delayed, and mortality is much high. More insight into the process of lung regeneration in ARDS patients is needed. Exosomes are important cargos for intercellular communication by serving as autocrine and/or paracrine. Cutting-edge exomics (exosomal proteomics) makes it possible to study the mechanisms of re-alveolarization in ARDS lungs. Aims: This study aimed to identify potential regenerative niches by characterizing differentially expressed proteins in the exosomes of bronchioalveolar lavage (BAL) in ARDS patients. Methods: We purified exosomes from BAL samples collected from ARDS patients by NIH-supported ALTA and SPIROMICS trials. The abundance of exosomal proteins/peptides was quantified using liquid chromatography-mass spectrometry (LC-MS). Differentially expressed exosomal proteins between healthy controls and ARDS patients were profiled for functional annotations, cell origins, signaling pathways, networks, and clinical correlations. Results: Our results show that more exosomal proteins were identified in the lungs of late-stage ARDS patients. Immune cells and lung epithelial stem cells were major contributors to BAL exosomes in addition to those from other organs. We enriched a wide range of functions, stem cell signals, growth factors, and immune niches in both mild and severe patients. The differentially expressed proteins that we identified were associated with key clinical variables. The severity-associated differences in protein-protein interaction, RNA crosstalk, and epigenetic network were observed between mild and severe groups. Moreover, alveolar type 2 epithelial cells could serve as both exosome donors and recipients via autocrine and paracrine mechanisms. Conclusions: This study identifies novel exosomal proteins associated with diverse functions, signaling pathways, and cell origins in ARDS lavage samples. These differentiated proteins may serve as regenerative niches for re-alveolarization in injured lungs.

Exploring the optimization of autoencoder design for imputing single-cell RNA sequencing data.

Autoencoders are the backbones of many imputation methods that aim to relieve the sparsity issue in single-cell RNA sequencing (scRNA-seq) data. The imputation performance of an autoencoder relies on both the neural network architecture and the hyperparameter choice. So far, literature in the single-cell field lacks a formal discussion on how to design the neural network and choose the hyperparameters. Here, we conducted an empirical study to answer this question. Our study used many real and simulated scRNA-seq datasets to examine the impacts of the neural network architecture, the activation function, and the regularization strategy on imputation accuracy and downstream analyses. Our results show that (i) deeper and narrower autoencoders generally lead to better imputation performance; (ii) the sigmoid and tanh activation functions consistently outperform other commonly used functions including ReLU; (iii) regularization improves the accuracy of imputation and downstream cell clustering and DE gene analyses. Notably, our results differ from common practices in the computer vision field regarding the activation function and the regularization strategy. Overall, our study offers practical guidance on how to optimize the autoencoder design for scRNA-seq data imputation.

Improving the diagnosis of thyroid cancer by machine learning and clinical data.

Thyroid cancer is a common endocrine carcinoma that occurs in the thyroid gland. Much effort has been invested in improving its diagnosis, and thyroidectomy remains the primary treatment method. A successful operation without unnecessary side injuries relies on an accurate preoperative diagnosis. Current human assessment of thyroid nodule malignancy is prone to errors and may not guarantee an accurate preoperative diagnosis. This study proposed a machine learning framework to predict thyroid nodule malignancy based on our collected novel clinical dataset. The ten-fold cross-validation, bootstrap analysis, and permutation predictor importance were applied to estimate and interpret the model performance under uncertainty. The comparison between model prediction and expert assessment shows the advantage of our framework over human judgment in predicting thyroid nodule malignancy. Our method is accurate, interpretable, and thus useable as additional evidence in the preoperative diagnosis of thyroid cancer.

Statistical learning in preclinical drug proarrhythmic assessment.

Torsades de pointes (TdP) is an irregular heart rhythm characterized by faster beat rates and potentially could lead to sudden cardiac death. Much effort has been invested in understanding the drug-induced TdP in preclinical studies. However, a comprehensive statistical learning framework that can accurately predict the drug-induced TdP risk from preclinical data is still lacking. We proposed ordinal logistic regression and ordinal random forest models to predict low-, intermediate-, and high-risk drugs based on datasets generated from two experimental protocols. Leave-one-drug-out cross-validation, stratified bootstrap, and permutation predictor importance were applied to estimate and interpret the model performance under uncertainty. The potential outlier drugs identified by our models are consistent with their descriptions in the literature. Our method is accurate, interpretable, and thus useable as supplemental evidence in the drug safety assessment.

scSampler: fast diversity-preserving subsampling of large-scale single-cell transcriptomic data.

SUMMARY: The number of cells measured in single-cell transcriptomic data has grown fast in recent years. For such large-scale data, subsampling is a powerful and often necessary tool for exploratory data analysis. However, the easiest random subsampling is not ideal from the perspective of preserving rare cell types. Therefore, diversity-preserving subsampling is required for fast exploration of cell types in a large-scale dataset. Here, we propose scSampler, an algorithm for fast diversity-preserving subsampling of single-cell transcriptomic data. AVAILABILITY AND IMPLEMENTATION: scSampler is implemented in Python and is published under the MIT source license. It can be installed by "pip install scsampler" and used with the Scanpy pipline. The code is available on GitHub: https://github.com/SONGDONGYUAN1994/scsampler. An R interface is available at: https://github.com/SONGDONGYUAN1994/rscsampler. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Protocol for executing and benchmarking eight computational doublet-detection methods in single-cell RNA sequencing data analysis.

The existence of doublets is a key confounder in single-cell RNA sequencing (scRNA-seq) data analysis. Computational techniques have been developed for detecting doublets from scRNA-seq data. We developed an R package DoubletCollection to integrate the installation and execution of eight doublet detection methods. DoubletCollection provides a unified interface to perform and visualize downstream analysis after doublet detection. Here, we present a protocol of using DoubletCollection to benchmark doublet-detection methods. This protocol can accommodate new doublet-detection methods in the fast-growing scRNA-seq field. For details on the use and execution of this protocol, please refer to Xi and Li (2020).

Benchmarking Computational Doublet-Detection Methods for Single-Cell RNA Sequencing Data.

In single-cell RNA sequencing (scRNA-seq), doublets form when two cells are encapsulated into one reaction volume. The existence of doublets, which appear to be-but are not-real cells, is a key confounder in scRNA-seq data analysis. Computational methods have been developed to detect doublets in scRNA-seq data; however, the scRNA-seq field lacks a comprehensive benchmarking of these methods, making it difficult for researchers to choose an appropriate method for specific analyses. We conducted a systematic benchmark study of nine cutting-edge computational doublet-detection methods. Our study included 16 real datasets, which contained experimentally annotated doublets, and 112 realistic synthetic datasets. We compared doublet-detection methods regarding detection accuracy under various experimental settings, impacts on downstream analyses, and computational efficiencies. Our results show that existing methods exhibited diverse performance and distinct advantages in different aspects. Overall, the DoubletFinder method has the best detection accuracy, and the cxds method has the highest computational efficiency. A record of this paper's transparent peer review process is included in the Supplemental Information.