Motivation: Precise prediction of cancer subtypes is of significant importance in cancer diagnosis and treatment. Disease etiology is complicated existing at different omics levels; hence integrative analysis provides a very effective way to improve our understanding of cancer. Results: We propose a novel computational framework, named Deep Subspace Mutual Learning (DSML). DSML has the capability to simultaneously learn the subspace structures in each available omics data and in overall multi-omics data by adopting deep neural networks, which thereby facilitates the subtype’s prediction via clustering on multi-level, single-level and partial-level omics data. Extensive experiments are performed in five different cancers on three levels of omics data from The Cancer Genome Atlas. The experimental analysis demonstrates that DSML delivers comparable or even better results than many state-of-the-art integrative methods. Availability and implementation: An implementation and documentation of the DSML is publicly available at https://github.com/polytechnicXTT/Deep-Subspace-Mutual-Learning.git.

Prediction of cancer-specific drug responses as well as identification of the corresponding drug-sensitive genes and pathways remains a major biological and clinical challenge. Deep learning models hold immense promise for better drug response predictions, but most of them cannot provide biological and clinical interpretability. Visible neural network (VNN) models have emerged to solve the problem by giving neurons biological meanings and directly casting biological networks into the models. However, the biological networks used in VNNs are often redundant and contain components that are irrelevant to the downstream predictions. Therefore, the VNNs using these redundant biological networks are overparameterized, which significantly limits VNNs’ predictive and explanatory power. To overcome the problem, we treat the edges and nodes in biological networks used in VNNs as features and develop a sparse learning framework ParsVNN to learn parsimony VNNs with only edges and nodes that contribute the most to the prediction task. We applied ParsVNN to build cancer-specific VNN models to predict drug response for five different cancer types. We demonstrated that the parsimony VNNs built by ParsVNN are superior to other state-of-the-art methods in terms of prediction performance and identification of cancer driver genes. Furthermore, we found that the pathways selected by ParsVNN have great potential to predict clinical outcomes as well as recommend synergistic drug combinations.

Quantitative assessment of single cell fluxome is critical for understanding the metabolic heterogeneity in diseases. Unfortunately, laboratory-based single cell fluxomics is currently impractical, and the current computational tools for flux estimation are not designed for single cell-level prediction. Given the well-established link between transcriptomic and metabolomic profiles, leveraging single cell transcriptomics data to predict single cell fluxome is not only feasible but also an urgent task. In this study, we present FLUXestimator, an online platform for predicting metabolic fluxome and variations using single cell or general transcriptomics data of large sample-size. The FLUXestimator webserver implements a recently developed unsupervised approach called single cell flux estimation analysis (scFEA), which uses a new neural network architecture to estimate reaction rates from transcriptomics data. To the best of our knowledge, FLUXestimator is the first web-based tool dedicated to predicting cell-/sample-wise metabolic flux and metabolite variations using transcriptomics data of human, mouse and 15 other common experimental organisms. The FLUXestimator webserver is available at http://scFLUX.org/, and stand-alone tools for local use are available at https://github.com/changwn/scFEA. Our tool provides a new avenue for studying metabolic heterogeneity in diseases and has the potential to facilitate the development of new therapeutic strategies.

The inference of Gene Regulatory Networks (GRNs) is one of the key challenges in systems biology. Leading algorithms utilize, in addition to gene expression, prior knowledge such as Transcription Factor (TF) DNA binding motifs or results of TF binding experiments. However, such prior knowledge is typically incomplete, therefore, integrating it with gene expression to infer GRNs remains difficult. To address this challenge, we introduce NetREX-CF—Regulatory Network Reconstruction using EXpression and Collaborative Filtering—a GRN reconstruction approach that brings together Collaborative Filtering to address the incompleteness of the prior knowledge and a biologically justified model of gene expression (sparse Network Component Analysis based model). We validated the NetREX-CF using Yeast data and then used it to construct the GRN for Drosophila Schneider 2 (S2) cells. To corroborate the GRN, we performed a large-scale RNA-Seq analysis followed by a high-throughput RNAi treatment against all 465 expressed TFs in the cell line. Our knockdown result has not only extensively validated the GRN we built, but also provides a benchmark that our community can use for evaluating GRNs. Finally, we demonstrate that NetREX-CF can infer GRNs using single-cell RNA-Seq, and outperforms other methods, by using previously published human data.

Introduction: Existing large-scale preclinical cancer drug response databases provide us with a great opportunity to identify and predict potentially effective drugs to combat cancers. Deep learning models built on these databases have been developed and applied to tackle the cancer drug-response prediction task. Their prediction has been demonstrated to significantly outperform traditional machine learning methods. However, due to the “black box” characteristic, biologically faithful explanations are hardly derived from these deep learning models. Interpretable deep learning models that rely on visible neural networks (VNNs) have been proposed to provide biological justification for the predicted outcomes. However, their performance does not meet the expectation to be applied in clinical practice.Methods: In this paper, we develop an XMR model, an eXplainable Multimodal neural network for drug Response prediction. XMR is a new compact multimodal neural network consisting of two sub-networks: a visible neural network for learning genomic features and a graph neural network (GNN) for learning drugs’ structural features. Both sub-networks are integrated into a multimodal fusion layer to model the drug response for the given gene mutations and the drug’s molecular structures. Furthermore, a pruning approach is applied to provide better interpretations of the XMR model. We use five pathway hierarchies (cell cycle, DNA repair, diseases, signal transduction, and metabolism), which are obtained from the Reactome Pathway Database, as the architecture of VNN for our XMR model to predict drug responses of triple negative breast cancer.Results: We find that our model outperforms other state-of-the-art interpretable deep learning models in terms of predictive performance. In addition, our model can provide biological insights into explaining drug responses for triple-negative breast cancer.Discussion: Overall, combining both VNN and GNN in a multimodal fusion layer, XMR captures key genomic and molecular features and offers reasonable interpretability in biology, thereby better predicting drug responses in cancer patients. Our model would also benefit personalized cancer therapy in the future.

With increasingly “big” data available in biomedical research, deriving accurate and reproducible biology knowledge from such big data imposes enormous computational challenges. In this paper, motivated by recently developed stochastic block coordinate algorithms, we propose a highly scalable randomized block coordinate Frank-Wolfe algorithm for convex optimization with general compact convex constraints, which has diverse applications in analyzing biomedical data for better understanding cellular and disease mechanisms. We focus on implementing the derived stochastic block coordinate algorithm to align protein-protein interaction networks for identifying conserved functional pathways based on the IsoRank framework. Our derived stochastic block coordinate Frank-Wolfe (SBCFW) algorithm has the convergence guarantee and naturally leads to the decreased computational cost (time and space) for each iteration. Our experiments for querying conserved functional protein complexes in yeast networks confirm the effectiveness of this technique for analyzing large-scale biological networks.