HUT: Hybrid UNet transformer for brain lesion and tumour segmentation.

A supervised deep learning network like the UNet has performed well in segmenting brain anomalies such as lesions and tumours. However, such methods were proposed to perform on single-modality or multi-modality images. We use the Hybrid UNet Transformer (HUT) to improve performance in single-modality lesion segmentation and multi-modality brain tumour segmentation. The HUT consists of two pipelines running in parallel, one of which is UNet-based and the other is Transformer-based. The Transformer-based pipeline relies on feature maps in the intermediate layers of the UNet decoder during training. The HUT network takes in the available modalities of 3D brain volumes and embeds the brain volumes into voxel patches. The transformers in the system improve global attention and long-range correlation between the voxel patches. In addition, we introduce a self-supervised training approach in the HUT framework to enhance the overall segmentation performance. We demonstrate that HUT performs better than the state-of-the-art network SPiN in the single-modality segmentation on Anatomical Tracings of Lesions After Stroke (ATLAS) dataset by 4.84% of Dice score and a significant 41% in the Hausdorff Distance score. HUT also performed well on brain scans in the Brain Tumour Segmentation (BraTS20) dataset and demonstrated an improvement over the state-of-the-art network nnUnet by 0.96% in the Dice score and 4.1% in the Hausdorff Distance score.

Graph Neural Networks With Multiple Prior Knowledge for Multi-Omics Data Analysis.

With the development of biotechnology, a large amount of multi-omics data have been collected for precision medicine. There exists multiple graph-based prior biological knowledge about omics data, such as gene-gene interaction networks. Recently, there has been an increasing interest in introducing graph neural networks (GNNs) into multi-omics learning. However, existing methods have not fully exploited these graphical priors since none have been able to integrate knowledge from multiple sources simultaneously. To solve this problem, we propose a multi-omics data analysis framework by incorporating multiple prior knowledge into graph neural network (MPK-GNN). To the best of our knowledge, this is the first attempt to introduce multiple prior graphs into multi-omics data analysis. Specifically, the proposed method contains four parts: (1) a feature-level learning module to aggregate information from prior graphs; (2) a projection module to maximize the agreement among prior networks by optimizing a contrastive loss; (3) a sample-level module to learn a global representation from input multi-omics features; (4) a task-specific module to flexibly extend MPK-GNN for various downstream multi-omics analysis tasks. Finally, we verify the effectiveness of the proposed multi-omics learning algorithm on the cancer molecular subtype classification task. Experimental results show that MPK-GNN outperforms other state-of-the-art algorithms, including multi-view learning methods and multi-omics integrative approaches.

Deep learning and multi-omics approach to predict drug responses in cancer.

BACKGROUND: Cancers are genetically heterogeneous, so anticancer drugs show varying degrees of effectiveness on patients due to their differing genetic profiles. Knowing patient's responses to numerous cancer drugs are needed for personalized treatment for cancer. By using molecular profiles of cancer cell lines available from Cancer Cell Line Encyclopedia (CCLE) and anticancer drug responses available in the Genomics of Drug Sensitivity in Cancer (GDSC), we will build computational models to predict anticancer drug responses from molecular features. RESULTS: We propose a novel deep neural network model that integrates multi-omics data available as gene expressions, copy number variations, gene mutations, reverse phase protein array expressions, and metabolomics expressions, in order to predict cellular responses to known anti-cancer drugs. We employ a novel graph embedding layer that incorporates interactome data as prior information for prediction. Moreover, we propose a novel attention layer that effectively combines different omics features, taking their interactions into account. The network outperformed feedforward neural networks and reported 0.90 for [Formula: see text] values for prediction of drug responses from cancer cell lines data available in CCLE and GDSC. CONCLUSION: The outstanding results of our experiments demonstrate that the proposed method is capable of capturing the interactions of genes and proteins, and integrating multi-omics features effectively. Furthermore, both the results of ablation studies and the investigations of the attention layer imply that gene mutation has a greater influence on the prediction of drug responses than other omics data types. Therefore, we conclude that our approach can not only predict the anti-cancer drug response precisely but also provides insights into reaction mechanisms of cancer cell lines and drugs as well.

DrDimont: explainable drug response prediction from differential analysis of multi-omics networks.

MOTIVATION: While it has been well established that drugs affect and help patients differently, personalized drug response predictions remain challenging. Solutions based on single omics measurements have been proposed, and networks provide means to incorporate molecular interactions into reasoning. However, how to integrate the wealth of information contained in multiple omics layers still poses a complex problem. RESULTS: We present DrDimont, Drug response prediction from Differential analysis of multi-omics networks. It allows for comparative conclusions between two conditions and translates them into differential drug response predictions. DrDimont focuses on molecular interactions. It establishes condition-specific networks from correlation within an omics layer that are then reduced and combined into heterogeneous, multi-omics molecular networks. A novel semi-local, path-based integration step ensures integrative conclusions. Differential predictions are derived from comparing the condition-specific integrated networks. DrDimont's predictions are explainable, i.e. molecular differences that are the source of high differential drug scores can be retrieved. We predict differential drug response in breast cancer using transcriptomics, proteomics, phosphosite and metabolomics measurements and contrast estrogen receptor positive and receptor negative patients. DrDimont performs better than drug prediction based on differential protein expression or PageRank when evaluating it on ground truth data from cancer cell lines. We find proteomic and phosphosite layers to carry most information for distinguishing drug response. AVAILABILITY AND IMPLEMENTATION: DrDimont is available on CRAN: https://cran.r-project.org/package=DrDimont. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Network-based integration of multi-omics data for clinical outcome prediction in neuroblastoma.

Multi-omics data are increasingly being gathered for investigations of complex diseases such as cancer. However, high dimensionality, small sample size, and heterogeneity of different omics types pose huge challenges to integrated analysis. In this paper, we evaluate two network-based approaches for integration of multi-omics data in an application of clinical outcome prediction of neuroblastoma. We derive Patient Similarity Networks (PSN) as the first step for individual omics data by computing distances among patients from omics features. The fusion of different omics can be investigated in two ways: the network-level fusion is achieved using Similarity Network Fusion algorithm for fusing the PSNs derived for individual omics types; and the feature-level fusion is achieved by fusing the network features obtained from individual PSNs. We demonstrate our methods on two high-risk neuroblastoma datasets from SEQC project and TARGET project. We propose Deep Neural Network and Machine Learning methods with Recursive Feature Elimination as the predictor of survival status of neuroblastoma patients. Our results indicate that network-level fusion outperformed feature-level fusion for integration of different omics data whereas feature-level fusion is more suitable incorporating different feature types derived from same omics type. We conclude that the network-based methods are capable of handling heterogeneity and high dimensionality well in the integration of multi-omics.

A deep neural network approach to predicting clinical outcomes of neuroblastoma patients.

BACKGROUND: The availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the "small n large p" problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process. METHODS: We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients' omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers. RESULTS: We apply this strategy to four neuroblastoma datasets and observe that models based on neural networks are more accurate than state of the art models (DNN: 85%-87%, SVM/RF: 75%-82%). We explore how different parameters and configurations are selected in order to overcome the effects of the small data problem as well as the curse of dimensionality. CONCLUSIONS: Our results indicate that the deep neural networks capture complex features in the data that help predicting patient clinical outcomes.

Analysis of correlation-based biomolecular networks from different omics data by fitting stochastic block models.

Background: Biological entities such as genes, promoters, mRNA, metabolites or proteins do not act alone, but in concert in their network context. Modules, i.e., groups of nodes with similar topological properties in these networks characterize important biological functions of the underlying biomolecular system. Edges in such molecular networks represent regulatory and physical interactions, and comparing them between conditions provides valuable information on differential molecular mechanisms. However, biological data is inherently noisy and network reduction techniques can propagate errors particularly to the level of edges. We aim to improve the analysis of networks of biological molecules by deriving modules together with edge relevance estimations that are based on global network characteristics.  Methods: We propose to fit the networks to stochastic block models (SBM), a method that has not yet been investigated for the analysis of biomolecular networks. This procedure both delivers modules of the networks and enables the derivation of edge confidence scores. We apply it to correlation-based networks of breast cancer data originating from high-throughput measurements of diverse molecular layers such as transcriptomics, proteomics, and metabolomics. The networks were reduced by thresholding for correlation significance or by requirements on scale-freeness.  Results and discussion: We find that the networks are best represented by the hierarchical version of the SBM, and many of the predicted blocks have a biological meaning according to functional annotation. The edge confidence scores are overall in concordance with the biological evidence given by the measurements. As they are based on global network connectivity characteristics and potential hierarchies within the biomolecular networks are taken into account, they could be used as additional, integrated features in network-based data comparisons. Their tight relationship to edge existence probabilities can be exploited to predict missing or spurious edges in order to improve the network representation of the underlying biological system.

Human Wharton's Jelly Mesenchymal Stem Cells Show Unique Gene Expression Compared with Bone Marrow Mesenchymal Stem Cells Using Single-Cell RNA-Sequencing.

Human Wharton's jelly stem cells (hWJSCs) isolated from the human umbilical cord are a unique population of mesenchymal stem cells (MSCs) with significant clinical utility. Their broad differentiation potential, high rate of proliferation, ready availability from discarded cords, and prolonged maintenance of stemness properties in culture make them an attractive alternative source of MSCs with therapeutic value compared with human bone marrow MSCs (hBMMSCs). We aimed to characterize the differences in gene expression profiles between these two stem cell types using single-cell RNA sequencing (scRNA-Seq) to determine which pathways are involved in conferring hWJSCs with their unique properties. We identified 436 significantly differentially expressed genes between the two cell types, playing roles in processes, including immunomodulation, angiogenesis, wound healing, apoptosis, antitumor activity, and chemotaxis. Expression of immune molecules is particularly high in hWJSCs compared with hBMMSCs. These differences in gene expression may help to explain many of the advantages that hWJSCs have over hBMMSCs for clinical application. Although cell surface protein marker expression indicates that isolated hWJSCs and hBMMSCs are both homogenous populations, using scRNA-Seq we can clearly identify extreme variability in expression levels between individual cells within a certain cell type. If the cells are examined as bulk populations, it is not possible to appreciate that a single cell may be making a major unique contribution to the apparent overall expression level. We demonstrated how the fine tuning of expression within hWJSCs and hBMMSCs may be achieved by expression of molecules with opposing function between two cells. We hypothesize that a greater understanding of these differences in gene expression between the two cell types may aid in the development of new therapies using hWJSCs.

Predicting clinical outcome of neuroblastoma patients using an integrative network-based approach.

BACKGROUND: One of the main current challenges in computational biology is to make sense of the huge amounts of multidimensional experimental data that are being produced. For instance, large cohorts of patients are often screened using different high-throughput technologies, effectively producing multiple patient-specific molecular profiles for hundreds or thousands of patients. RESULTS: We propose and implement a network-based method that integrates such patient omics data into Patient Similarity Networks. Topological features derived from these networks were then used to predict relevant clinical features. As part of the 2017 CAMDA challenge, we have successfully applied this strategy to a neuroblastoma dataset, consisting of genomic and transcriptomic data. In particular, we observe that models built on our network-based approach perform at least as well as state of the art models. We furthermore explore the effectiveness of various topological features and observe, for instance, that redundant centrality metrics can be combined to build more powerful models. CONCLUSION: We demonstrate that the networks inferred from omics data contain clinically relevant information and that patient clinical outcomes can be predicted using only network topological data. REVIEWERS: This article was reviewed by Yang-Yu Liu, Tomislav Smuc and Isabel Nepomuceno.

MultiDCoX: Multi-factor analysis of differential co-expression.

BACKGROUND: Differential co-expression (DCX) signifies change in degree of co-expression of a set of genes among different biological conditions. It has been used to identify differential co-expression networks or interactomes. Many algorithms have been developed for single-factor differential co-expression analysis and applied in a variety of studies. However, in many studies, the samples are characterized by multiple factors such as genetic markers, clinical variables and treatments. No algorithm or methodology is available for multi-factor analysis of differential co-expression. RESULTS: We developed a novel formulation and a computationally efficient greedy search algorithm called MultiDCoX to perform multi-factor differential co-expression analysis. Simulated data analysis demonstrates that the algorithm can effectively elicit differentially co-expressed (DCX) gene sets and quantify the influence of each factor on co-expression. MultiDCoX analysis of a breast cancer dataset identified interesting biologically meaningful differentially co-expressed (DCX) gene sets along with genetic and clinical factors that influenced the respective differential co-expression. CONCLUSIONS: MultiDCoX is a space and time efficient procedure to identify differentially co-expressed gene sets and successfully identify influence of individual factors on differential co-expression.

Quantification of liver fibrosis via second harmonic imaging of the Glisson's capsule from liver surface.

Liver surface is covered by a collagenous layer called the Glisson's capsule. The structure of the Glisson's capsule is barely seen in the biopsy samples for histology assessment, thus the changes of the collagen network from the Glisson's capsule during the liver disease progression are not well studied. In this report, we investigated whether non-linear optical imaging of the Glisson's capsule at liver surface would yield sufficient information to allow quantitative staging of liver fibrosis. In contrast to conventional tissue sections whereby tissues are cut perpendicular to the liver surface and interior information from the liver biopsy samples were used, we have established a capsule index based on significant parameters extracted from the second harmonic generation (SHG) microscopy images of capsule collagen from anterior surface of rat livers. Thioacetamide (TAA) induced liver fibrosis animal models was used in this study. The capsule index is capable of differentiating different fibrosis stages, with area under receiver operating characteristics curve (AUC) up to 0.91, making it possible to quantitatively stage liver fibrosis via liver surface imaging potentially with endomicroscopy.

qFibrosis: a fully-quantitative innovative method incorporating histological features to facilitate accurate fibrosis scoring in animal model and chronic hepatitis B patients.

BACKGROUND & AIMS: There is increasing need for accurate assessment of liver fibrosis/cirrhosis. We aimed to develop qFibrosis, a fully-automated assessment method combining quantification of histopathological architectural features, to address unmet needs in core biopsy evaluation of fibrosis in chronic hepatitis B (CHB) patients. METHODS: qFibrosis was established as a combined index based on 87 parameters of architectural features. Images acquired from 25 Thioacetamide-treated rat samples and 162 CHB core biopsies were used to train and test qFibrosis and to demonstrate its reproducibility. qFibrosis scoring was analyzed employing Metavir and Ishak fibrosis staging as standard references, and collagen proportionate area (CPA) measurement for comparison. RESULTS: qFibrosis faithfully and reliably recapitulates Metavir fibrosis scores, as it can identify differences between all stages in both animal samples (p<0.001) and human biopsies (p<0.05). It is robust to sampling size, allowing for discrimination of different stages in samples of different sizes (area under the curve (AUC): 0.93-0.99 for animal samples: 1-16 mm(2); AUC: 0.84-0.97 for biopsies: 10-44 mm in length). qFibrosis can significantly predict staging underestimation in suboptimal biopsies (<15 mm) and under- and over-scoring by different pathologists (p<0.001). qFibrosis can also differentiate between Ishak stages 5 and 6 (AUC: 0.73, p=0.008), suggesting the possibility of monitoring intra-stage cirrhosis changes. Best of all, qFibrosis demonstrates superior performance to CPA on all counts. CONCLUSIONS: qFibrosis can improve fibrosis scoring accuracy and throughput, thus allowing for reproducible and reliable analysis of efficacies of anti-fibrotic therapies in clinical research and practice.

Multiclass gene selection using Pareto-fronts.

Filter methods are often used for selection of genes in multiclass sample classification by using microarray data. Such techniques usually tend to bias toward a few classes that are easily distinguishable from other classes due to imbalances of strong features and sample sizes of different classes. It could therefore lead to selection of redundant genes while missing the relevant genes, leading to poor classification of tissue samples. In this manuscript, we propose to decompose multiclass ranking statistics into class-specific statistics and then use Pareto-front analysis for selection of genes. This alleviates the bias induced by class intrinsic characteristics of dominating classes. The use of Pareto-front analysis is demonstrated on two filter criteria commonly used for gene selection: F-score and KW-score. A significant improvement in classification performance and reduction in redundancy among top-ranked genes were achieved in experiments with both synthetic and real-benchmark data sets.

Spatiotemporal quantification of cell dynamics in the lung following influenza virus infection.

Lung injury caused by influenza virus infection is widespread. Understanding lung damage and repair progression post infection requires quantitative spatiotemporal information on various cell types mapping into the tissue structure. Based on high content images acquired from an automatic slide scanner, we have developed algorithms to quantify cell infiltration in the lung, loss and recovery of Clara cells in the damaged bronchioles and alveolar type II cells (AT2s) in the damaged alveolar areas, and induction of pro-surfactant protein C (pro-SPC)-expressing bronchiolar epithelial cells (SBECs). These quantitative analyses reveal: prolonged immune cell infiltration into the lung that persisted long after the influenza virus was cleared and paralleled with Clara cell recovery; more rapid loss and recovery of Clara cells as compared to AT2s; and two stages of SBECs from Scgb1a1⁺ to Scgb1a1⁻. These results provide evidence supporting a new mechanism of alveolar repair where Clara cells give rise to AT2s through the SBEC intermediates and shed light on the understanding of the lung damage and repair process. The approach and algorithms in quantifying cell-level changes in the tissue context (cell-based tissue informatics) to gain mechanistic insights into the damage and repair process can be expanded and adapted in studying other disease models.

Staging tissues with conditional random fields.

We present a framework for identifying disease states by classifying cells in the pathological regions of tissues into different categories. We use conditional random fields (CRF) to incorporate characteristics of cells and their spatial distributions. The efficacy of CRF to model cell-cell feature interactions is demonstrated by using a lung tissue dataset and a synthesized cancer tissue dataset. Comparisons with an independent cell model and a contextual model based on a Markov random field indicate that CRF effectively incorporates features of both cells and their spatial distributions for identification of pathological cells.

Correlation of cell membrane dynamics and cell motility.

BACKGROUND: Essential events of cell development and homeostasis are revealed by the associated changes of cell morphology and therefore have been widely used as a key indicator of physiological states and molecular pathways affecting various cellular functions via cytoskeleton. Cell motility is a complex phenomenon primarily driven by the actin network, which plays an important role in shaping the morphology of the cells. Most of the morphology based features are approximated from cell periphery but its dynamics have received none to scant attention. We aim to bridge the gap between membrane dynamics and cell states from the perspective of whole cell movement by identifying cell edge patterns and its correlation with cell dynamics. RESULTS: We present a systematic study to extract, classify, and compare cell dynamics in terms of cell motility and edge activity. Cell motility features extracted by fitting a persistent random walk were used to identify the initial set of cell subpopulations. We propose algorithms to extract edge features along the entire cell periphery such as protrusion and retraction velocity. These constitute a unique set of multivariate time-lapse edge features that are then used to profile subclasses of cell dynamics by unsupervised clustering. CONCLUSIONS: By comparing membrane dynamic patterns exhibited by each subclass of cells, correlated trends of edge and cell movements were identified. Our findings are consistent with published literature and we also identified that motility patterns are influenced by edge features from initial time points compared to later sampling intervals.

Toward surface quantification of liver fibrosis progression.

Monitoring liver fibrosis progression by liver biopsy is important for certain treatment decisions, but repeated biopsy is invasive. We envision redefinition or elimination of liver biopsy with surface scanning of the liver with minimally invasive optical methods. This would be possible only if the information contained on or near liver surfaces accurately reflects the liver fibrosis progression in the liver interior. In our study, we acquired the second-harmonic generation and two-photon excitation fluorescence microscopy images of liver tissues from bile duct-ligated rat model of liver fibrosis. We extracted morphology-based features, such as total collagen, collagen in bile duct areas, bile duct proliferation, and areas occupied by remnant hepatocytes, and defined the capsule and subcapsular regions on the liver surface based on image analysis of features. We discovered a strong correlation between the liver fibrosis progression on the anterior surface and interior in both liver lobes, where biopsy is typically obtained. The posterior surface exhibits less correlation with the rest of the liver. Therefore, scanning the anterior liver surface would obtain similar information to that obtained from biopsy for monitoring liver fibrosis progression.

Pulse-modulated second harmonic imaging microscope quantitatively demonstrates marked increase of collagen in tumor after chemotherapy.

Pulse-modulated second harmonic imaging microscopes (PM-SHIMs) exhibit improved signal-to-noise ratio (SNR) over conventional SHIMs on sensitive imaging and quantification of weak collagen signals inside tissues. We quantify the spatial distribution of sparse collagen inside a xenograft model of human acute myeloid leukemia (AML) tumor specimens treated with a new drug against receptor tyrosine kinase (ABT-869), and observe a significant increase in collagen area percentage, collagen fiber length, fiber width, and fiber number after chemotherapy. This finding reveals new insights into tumor responses to chemotherapy and suggests caution in developing new drugs and therapeutic regimens against cancers.

A cell profiling framework for modeling drug responses from HCS imaging.

The authors present an unsupervised, scalable, and interpretable cell profiling framework that is compatible with data gathered from high-content screening. They demonstrate the effectiveness of their framework by modeling drug differential effects of IC-21 macrophages treated with microtubule and actin disrupting drugs. They identify significant features of cell phenotypes for unsupervised learning based on maximum relevancy and minimum redundancy criteria. A 2-stage clustering approach annotates, clusters cells, and then merges them together to form super-clusters. An interpretable cell profile consisting of super-cluster proportions profiled at each drug treatment, concentration, or duration is obtained. Differential changes in super-cluster profiles are the basis for understanding the drug's differential effect and biology. The authors' method is validated by significant chi-squared statistics obtained from similar drug-treated super-cluster profiles from a 5-fold cross-validation. In addition, drug profiles of 2 microtubule drugs with equivalent mechanisms of action are statistically similar. Several distinct trends are identified for the 5 cytoskeletal drugs profiled under different conditions.

SVM-RFE with MRMR filter for gene selection.

We enhance the support vector machine recursive feature elimination (SVM-RFE) method for gene selection by incorporating a minimum-redundancy maximum-relevancy (MRMR) filter. The relevancy of a set of genes are measured by the mutual information among genes and class labels, and the redundancy is given by the mutual information among the genes. The method improved identification of cancer tissues from benign tissues on several benchmark datasets, as it takes into account the redundancy among the genes during their selection. The method selected a less number of genes compared to MRMR or SVM-RFE on most datasets. Gene ontology analyses revealed that the method selected genes that are relevant for distinguishing cancerous samples and have similar functional properties. The method provides a framework for combining filter methods and wrapper methods of gene selection, as illustrated with MRMR and SVM-RFE methods.