In machine learning, multi-view data involve multiple distinct sets of attributes (“views”) for a common set of observations; when each view has the same attributes considered in different contexts, the data are said to contain multiple views of homogeneous format, which can be conceptualized as a tensor. In this article, we describe a novel approach for integrating multiple views of heterogeneous format into a common latent space using a workflow that involves non-negative matrix and tensor factorization (NMF/NTF). This approach, which we refer to as the integrated sources model (ISM), consists of two main steps: Embedding and analysis. In the embedding step, the views are transformed into matrices with common non-negative components. In the analysis step, the transformed views are combined into a tensor and decomposed using NTF. We also present a variant of ISM; the integrated latent sources model (ILSM), which offers significant advantages over ISM in terms of computational power and in cases where the views are highly unbalanced with regard to the number of attributes per view. Noteworthy, ISM can be extended to process multi-omic and multi-view datasets even in the presence of missing views. We provide a proof-of-concept analysis using five examples, including the UCI Digits (the University of California Irvine Pen-Based Recognition of Handwritten Digits) dataset, a public cell-type gene signatures dataset, and a multi-omic single-cell dataset. These examples demonstrate that, in most cases, multi-view clustering is better achieved with ISM or its variant ILSM than with other latent space approaches. We also show how the non-negativity and sparsity of the ISM model components enable straightforward interpretations, in contrast to other approaches that involve latent factors of mixed signs. Finally, we present potential applications to single-cell multi-omics and spatial mapping, including spatial imaging, spatial transcriptomics, and computational biology, which are currently under evaluation. ISM relies on state-of-the-art algorithms invoked through a simple workflow implemented in Python.
Motivation: Molecular signatures are critical for inferring the proportions of cell types from bulk transcriptomics data. However, the identification of these signatures is based on a methodology that relies on prior biological knowledge of the cell types being studied. When working with less known biological material, a data-driven approach is required to uncover the underlying classes and generate ad hoc signatures from healthy or pathogenic tissue. Results: We present a new approach, A2Sign: Agnostic Algorithms for Signatures, based on a non-negative tensor factorization (NTF) strategy that allows us to identify cell-type-specific molecular signatures, greatly reduce collinearities and also account for inter-individual variability. We propose a global framework that can be applied to uncover molecular signatures for cell-type deconvolution in arbitrary tissues using bulk transcriptome data. We also present two new molecular signatures for deconvolution of up to 16 immune cell types using microarray or RNA-seq data. Availability and implementation: All steps of our analysis were implemented in annotated Python notebooks (https://github.com/paulfogel/A2SIGN). To perform NTF, we used the NMTF package, which can be downloaded using Python pip install. Supplementary information: Supplementary data are available at Bioinformatics online.
Background Molecular signatures for deconvolution of immune cell types have been proposed, based on a methodology that relies on the biological classification of the cell types being studied. When working with less known biological material, a data-driven approach is needed to uncover the underlying classes and construct ad hoc signatures. Results We introduce a new approach, ASigNTF: Agnostic Signature using Non-negative Tensor Factorization, to perform the deconvolution of cell types from transcriptomics data (RNAseq and microarray). ASigNTF, which is based on two complementary statistical/mathematical tools: non-negative tensor factorization (for dimensionality reduction) and the Herfindahl-Hirschman index (for signature selection), can be applied to any type of tissue as long as transcriptomic data on isolated cells is available. As a direct result of the new method, we propose two new signatures for the deconvolution of immune cell types, one consisting of a relatively small set of 415 genes, which is more compatible with microarray platforms, and a larger set of 915 genes. Using external datasets, our two signatures outperform the CIBERSORT LM22 signature in deconvolution of RNA-seq data. Our signature with 415 genes allows to recognize a larger number of cell types compared to the ABIS microarray signature. Conclusions The paper proposes a new method, ASigNTF; applies the method, and also provides a software implementation that allows to identify molecular signatures for deconvolution of complex tissues and specifically up to 16 immune cell types from micro-array or RNA-seq data. Highlights Several signatures of immune cell types have been proposed, which follow a methodology deeply rooted in the known biological classification of the investigated cell types. When working with less known biological material, a more agnostic, data-driven approach is required to uncover the underlying classes and construct ad hoc signatures. We present ASigNTF, a new agnostic approach to cell type classification and signature selection supported by an application software. We discuss the results of benchmarking our proposed signatures, ABIS-seq and CIBERSORT on external datasets.
Tyrosine kinase inhibitors (TKIs) have transformed oncogene-driven cancer treatment, but durable responses remain limited by residual disease and acquired resistance. Drug-tolerant persister (DTP) cells represent one therapy-surviving component of minimal residual disease (MRD). This Review examines experimental and computational strategies, including patient-derived xenografts, CRISPR screens, single-cell, spatial, multi-omic and artificial intelligence approaches, to define DTP states, MRD heterogeneity, microenvironmental interactions and clinically actionable vulnerabilities with greater resolution in TKI-treated cancers.
We describe a new approach for integrating multiple views of data into a common latent space using non-negative tensor factorization (NTF). This approach, which we refer to as the "Integrated Sources Model" (ISM), consists of two main steps: embedding and analysis. In the embedding step, each view is transformed into a matrix with common non-negative components. In the analysis step, the transformed views are combined into a tensor and decomposed using NTF. Noteworthy, ISM can be extended to process multi-view data sets with missing views. We illustrate the new approach using two examples: the UCI digit dataset and a public cell type gene signatures dataset, to show that multi-view clustering of digits or marker genes by their respective cell type is better achieved with ISM than with other latent space approaches. We also show how the non-negativity and sparsity of the ISM model components enable straightforward interpretations, in contrast to latent factors of mixed signs. Finally, we present potential applications to single-cell multi-omics and spatial mapping, including spatial imaging and spatial transcriptomics, and computational biology, which are currently under evaluation. ISM relies on state-of-the-art algorithms invoked via a simple workflow implemented in a Jupyter Python notebook.