Bayesian Edge Regression in Undirected Graphical Models to Characterize Interpatient Heterogeneity in Cancer.

It is well-established that interpatient heterogeneity in cancer may significantly affect genomic data analyses and in particular, network topologies. Most existing graphical model methods estimate a single population-level graph for genomic or proteomic network. In many investigations, these networks depend on patient-specific indicators that characterize the heterogeneity of individual networks across subjects with respect to subject-level covariates. Examples include assessments of how the network varies with patient-specific prognostic scores or comparisons of tumor and normal graphs while accounting for tumor purity as a continuous predictor. In this paper, we propose a novel edge regression model for undirected graphs, which estimates conditional dependencies as a function of subject-level covariates. We evaluate our model performance through simulation studies focused on comparing tumor and normal graphs while adjusting for tumor purity. In application to a dataset of proteomic measurements on plasma samples from patients with hepatocellular carcinoma (HCC), we ascertain how blood protein networks vary with disease severity, as measured by HepatoScore, a novel biomarker signature measuring disease severity. Our case study shows that the network connectivity increases with HepatoScore and a set of hub genes as well as important gene connections are identified under different HepatoScore, which may provide important biological insights to the development of precision therapies for HCC.

DNB: A Joint Learning Framework for Deep Bayesian Nonparametric Clustering.

Clustering algorithms based on deep neural networks have been widely studied for image analysis. Most existing methods require partial knowledge of the true labels, namely, the number of clusters, which is usually not available in practice. In this article, we propose a Bayesian nonparametric framework, deep nonparametric Bayes (DNB), for jointly learning image clusters and deep representations in a doubly unsupervised manner. In doubly unsupervised learning, we are dealing with the problem of "unknown unknowns," where we estimate not only the unknown image labels but also the unknown number of labels as well. The proposed algorithm alternates between generating a potentially unbounded number of clusters in the forward pass and learning the deep networks in the backward pass. With the help of the Dirichlet process mixtures, the proposed method is able to partition the latent representations space without specifying the number of clusters a priori. An important feature of this work is that all the estimation is realized with an end-to-end solution, which is very different from the methods that rely on post hoc analysis to select the number of clusters. Another key idea in this article is to provide a principled solution to the problem of "trivial solution" for deep clustering, which has not been much studied in the current literature. With extensive experiments on benchmark datasets, we show that our doubly unsupervised method achieves good clustering performance and outperforms many other unsupervised image clustering methods.

SODA: Detecting COVID-19 in Chest X-rays with Semi-supervised Open Set Domain Adaptation.

Due to the shortage of COVID-19 viral testing kits, radiology is used to complement the screening process. Deep learning methods are promising in automatically detecting COVID-19 disease in chest x-ray images. Most of these works first train a Convolutional Neural Network (CNN) on an existing large-scale chest x-ray image dataset and then fine-tune the model on the newly collected COVID-19 chest x-ray dataset, often at a much smaller scale. However, simple fine-tuning may lead to poor performance due to two issues, firstly the large domain shift present in chest x-ray datasets and secondly the relatively small scale of the COVID-19 chest x-ray dataset. In an attempt to address these issues, we formulate the problem of COVID-19 chest x-ray image classification in a semi-supervised open set domain adaptation setting and propose a novel domain adaptation method, Semi-supervised Open set Domain Adversarial network (SODA). SODA is designed to align the data distributions across different domains in the general domain space and also in the common subspace of source and target data. In our experiments, SODA achieves a leading classification performance compared with recent state-of-the-art models in separating COVID-19 with common pneumonia. We also present results showing that SODA produces better pathology localizations.

HepatoScore-14: Measures of Biological Heterogeneity Significantly Improve Prediction of Hepatocellular Carcinoma Risk.

BACKGROUND AND AIMS: Therapeutic, clinical trial entry and stratification decisions for hepatocellular carcinoma (HCC) are made based on prognostic assessments, using clinical staging systems based on small numbers of empirically selected variables that insufficiently account for differences in biological characteristics of individual patients' disease. APPROACH AND RESULTS: We propose an approach for constructing risk scores from circulating biomarkers that produce a global biological characterization of individual patient's disease. Plasma samples were collected prospectively from 767 patients with HCC and 200 controls, and 317 proteins were quantified in a Clinical Laboratory Improvement Amendments-certified biomarker testing laboratory. We constructed a circulating biomarker aberration score for each patient, a score between 0 and 1 that measures the degree of aberration of his or her biomarker panel relative to normal, which we call HepatoScore. We used log-rank tests to assess its ability to substratify patients within existing staging systems/prognostic factors. To enhance clinical application, we constructed a single-sample score, HepatoScore-14, which requires only a subset of 14 representative proteins encompassing the global biological effects. Patients with HCC were split into three distinct groups (low, medium, and high HepatoScore) with vastly different prognoses (medial overall survival 38.2/18.3/7.1 months; P < 0.0001). Furthermore, HepatoScore accurately substratified patients within levels of existing prognostic factors and staging systems (P < 0.0001 for nearly all), providing substantial and sometimes dramatic refinement of expected patient outcomes with strong therapeutic implications. These results were recapitulated by HepatoScore-14, rigorously validated in repeated training/test splits, concordant across Myriad RBM (Austin, TX) and enzyme-linked immunosorbent assay kits, and established as an independent prognostic factor. CONCLUSIONS: HepatoScore-14 augments existing HCC staging systems, dramatically refining patient prognostic assessments and therapeutic decision making and enrollment in clinical trials. The underlying strategy provides a global biological characterization of disease, and can be applied broadly to other disease settings and biological media.

WGAN domain adaptation for the joint optic disc-and-cup segmentation in fundus images.

PURPOSE: The cup-to-disc ratio (CDR), a clinical metric of the relative size of the optic cup to the optic disc, is a key indicator of glaucoma, a chronic eye disease leading to loss of vision. CDR can be measured from fundus images through the segmentation of optic disc and optic cup . Deep convolutional networks have been proposed to achieve biomedical image segmentation with less time and more accuracy, but requires large amounts of annotated training data on a target domain, which is often unavailable. Unsupervised domain adaptation framework alleviates this problem through leveraging off-the-shelf labeled data from its relevant source domains, which is realized by learning domain invariant features and improving the generalization capabilities of the segmentation model. METHODS: In this paper, we propose a WGAN domain adaptation framework for detecting optic disc-and-cup boundary in fundus images. Specifically, we build a novel adversarial domain adaptation framework that is guided by Wasserstein distance, therefore with better stability and convergence than typical adversarial methods. We finally evaluate our approach on publicly available datasets. RESULTS: Our experiments show that the proposed approach improves Intersection-over-Union score for optic disc-and-cup segmentation, Dice score and reduces the root-mean-square error of cup-to-disc ratio, when we compare it with direct transfer learning and other state-of-the-art adversarial domain adaptation methods. CONCLUSION: With this work, we demonstrate that WGAN guided domain adaptation obtains a state-of-the-art performance for the joint optic disc-and-cup segmentation in fundus images.

Complex resistivity characteristics of saltwater-intruded sand contaminated by heavy metal.

Different pollutants affect electrical characteristics of soil, e.g., electric resistivity and capacity. The most extensively used non-intrusive methods in mapping these physical characteristics are electrical method. To better understand the effect of different hydrogeological and environmental process on resistivity and phase of complex resistivity under water-saturated soil, we carried out a controlled laboratory experiment where the host material was simulated by sand soil and the hydrogeological and environmental processes by groundwater table rise, seawater intrusion and heavy metal contamination. The experiment measured the resistivity and phase of soil saturated and unsaturated, with different pollutants added, together with their time-lapse change in a well-controlled column. With the involvement of more measurement parameters, complex resistivity method can provide more information than resistivity method, thereby having better performance in the detection and monitoring of changes in electrical properties of complex contaminated sites. For example, it is capable of discriminating the different contamination process, in this case, e.g., seawater intrusion and heavy metal contamination. In addition, it is still sensitive to the change of pollutant concentration even in site with high added concentration. Furthermore, simulating the saltwater-intruded site contaminated by manganese, it was found that the change of resistivity (ρ) can hardly be observed, while the responses of phase (φ) are so obvious that can be clearly observed.

Transcriptome Deconvolution of Heterogeneous Tumor Samples with Immune Infiltration.

Transcriptome deconvolution in cancer and other heterogeneous tissues remains challenging. Available methods lack the ability to estimate both component-specific proportions and expression profiles for individual samples. We present DeMixT, a new tool to deconvolve high-dimensional data from mixtures of more than two components. DeMixT implements an iterated conditional mode algorithm and a novel gene-set-based component merging approach to improve accuracy. In a series of experimental validation studies and application to TCGA data, DeMixT showed high accuracy. Improved deconvolution is an important step toward linking tumor transcriptomic data with clinical outcomes. An R package, scripts, and data are available: https://github.com/wwylab/DeMixTallmaterials.

RNA-seq mixology: designing realistic control experiments to compare protocols and analysis methods.

Carefully designed control experiments provide a gold standard for benchmarking different genomics research tools. A shortcoming of many gene expression control studies is that replication involves profiling the same reference RNA sample multiple times. This leads to low, pure technical noise that is atypical of regular studies. To achieve a more realistic noise structure, we generated a RNA-sequencing mixture experiment using two cell lines of the same cancer type. Variability was added by extracting RNA from independent cell cultures and degrading particular samples. The systematic gene expression changes induced by this design allowed benchmarking of different library preparation kits (standard poly-A versus total RNA with Ribozero depletion) and analysis pipelines. Data generated using the total RNA kit had more signal for introns and various RNA classes (ncRNA, snRNA, snoRNA) and less variability after degradation. For differential expression analysis, voom with quality weights marginally outperformed other popular methods, while for differential splicing, DEXSeq was simultaneously the most sensitive and the most inconsistent method. For sample deconvolution analysis, DeMix outperformed IsoPure convincingly. Our RNA-sequencing data set provides a valuable resource for benchmarking different protocols and data pre-processing workflows. The extra noise mimics routine lab experiments more closely, ensuring any conclusions are widely applicable.