Models for natural language and images benefit from data scaling behavior: the more data fed into the model, the better they perform. This 'better with more' phenomenon enables the effectiveness of large-scale pre-training on vast amounts of data. However, current graph pre-training methods struggle to scale up data due to heterogeneity across graphs. To achieve effective data scaling, we aim to develop a general model that is able to capture diverse data patterns of graphs and can be utilized to adaptively help the downstream tasks. To this end, we propose UniAug, a universal graph structure augmentor built on a diffusion model. We first pre-train a discrete diffusion model on thousands of graphs across domains to learn the graph structural patterns. In the downstream phase, we provide adaptive enhancement by conducting graph structure augmentation with the help of the pre-trained diffusion model via guided generation. By leveraging the pre-trained diffusion model for structure augmentation, we consistently achieve performance improvements across various downstream tasks in a plug-and-play manner. To the best of our knowledge, this study represents the first demonstration of a data-scaling graph structure augmentor on graphs across domains.

The current state-of-the-art single-cell pre-trained models are greatly inspired by the success of large language models. They trained transformers by treating genes as tokens and cells as sentences. However, three fundamental differences between single-cell data and natural language data are overlooked: (1) scRNA-seq data are presented as bag-of-genes instead of sequences of RNAs; (2) Cell-cell relations are more intricate and important than inter-sentence relations; and (3) The quantity of single-cell data is considerably inferior to text data, and they are very noisy. In light of these characteristics, we propose a new pre-trained model, $\textit{CellPLM}$, which takes cells as tokens and tissues as sentences. In addition, we leverage spatially-resolved transcriptomic data in pre-training to facilitate learning cell-cell relationships and introduce a Gaussian prior distribution as an additional inductive bias to overcome data limitations. $\textit{CellPLM}$ is the first single-cell pre-trained transformer that encodes cell-cell relations and it consistently outperforms existing pre-trained and non-pre-trained models in diverse downstream tasks, with 100 times higher inference speed on generating cell embeddings than previous pre-trained models.

Recent advances in single-cell technologies have enabled high-resolution characterization of tissue and cancer compositions. Although numerous tools for dimension reduction and clustering are available for single-cell data analyses, these methods often fail to simultaneously preserve local cluster structure and global data geometry. To address these challenges, we developed a novel analyses framework, Single-Cell Path Metrics Profiling (scPMP), using power-weighted path metrics, which measure distances between cells in a data-driven way. Unlike Euclidean distance and other commonly used distance metrics, path metrics are density sensitive and respect the underlying data geometry. By combining path metrics with multidimensional scaling, a low dimensional embedding of the data is obtained which preserves both the global data geometry and cluster structure. We evaluate the method both for clustering quality and geometric fidelity, and it outperforms current scRNAseq clustering algorithms on a wide range of benchmarking data sets.

Single-cell technologies are revolutionizing the entire field of biology. The large volumes of data generated by single-cell technologies are high dimensional, sparse, and heterogeneous and have complicated dependency structures, making analyses using conventional machine learning approaches challenging and impractical. In tackling these challenges, deep learning often demonstrates superior performance compared to traditional machine learning methods. In this work, we give a comprehensive survey on deep learning in single-cell analysis. We first introduce background on single-cell technologies and their development, as well as fundamental concepts of deep learning including the most popular deep architectures. We present an overview of the single-cell analytic pipeline pursued in research applications while noting divergences due to data sources or specific applications. We then review seven popular tasks spanning different stages of the single-cell analysis pipeline, including multimodal integration, imputation, clustering, spatial domain identification, cell-type deconvolution, cell segmentation, and cell-type annotation. Under each task, we describe the most recent developments in classical and deep learning methods and discuss their advantages and disadvantages. Deep learning tools and benchmark datasets are also summarized for each task. Finally, we discuss the future directions and the most recent challenges. This survey will serve as a reference for biologists and computer scientists, encouraging collaborations.

The recent development of multimodal single-cell technology has made the possibility of acquiring multiple omics data from individual cells, thereby enabling a deeper understanding of cellular states and dynamics. Nevertheless, the proliferation of multimodal single-cell data also introduces tremendous challenges in modeling the complex interactions among different modalities. The recently advanced methods focus on constructing static interaction graphs and applying graph neural networks (GNNs) to learn from multimodal data. However, such static graphs can be suboptimal as they do not take advantage of the downstream task information; meanwhile GNNs also have some inherent limitations when deeply stacking GNN layers. To tackle these issues, in this work, we investigate how to leverage transformers for multimodal single-cell data in an end-to-end manner while exploiting downstream task information. In particular, we propose a scMoFormer framework which can readily incorporate external domain knowledge and model the interactions within each modality and cross modalities. Extensive experiments demonstrate that scMoFormer achieves superior performance on various benchmark datasets. Remarkably, scMoFormer won a Kaggle silver medal with the rank of 24/1221 (Top 2%) without ensemble in a NeurIPS 2022 competition1. Our implementation is publicly available at Github2.

Recent advances in multimodal single-cell technologies have enabled simultaneous acquisitions of multiple omics data from the same cell, providing deeper insights into cellular states and dynamics. However, it is challenging to learn the joint representations from the multimodal data, model the relationship between modalities, and, more importantly, incorporate the vast amount of single-modality datasets into the downstream analyses. To address these challenges and correspondingly facilitate multimodal single-cell data analyses, three key tasks have been introduced: Modality prediction, Modality matching andJoint embedding. In this work, we present a general Graph Neural Network framework scMoGNN to tackle these three tasks and show that scMoGNN demonstrates superior results in all three tasks compared with the state-of-the-art and conventional approaches. Our method is an official winner in the overall ranking ofModality prediction from NeurIPS 2021 Competition (https://openproblems.bio/neurips_2021/), and all implementations of our methods have been integrated into DANCE package (https://github.com/OmicsML/dance).

MOTIVATION: The rapid development of scRNA-seq technologies enables us to explore the transcriptome at the cell level on a large scale. Recently, various computational methods have been developed to analyze the scRNAseq data, such as clustering and visualization. However, current visualization methods, including t-SNE and UMAP, are challenged by the limited accuracy of rendering the geometric relationship of populations with distinct functional states. Most visualization methods are unsupervised, leaving out information from the clustering results or given labels. This leads to the inaccurate depiction of the distances between the bona fide functional states. In particular, UMAP and t-SNE are not optimal to preserve the global geometric structure. They may result in a contradiction that clusters with near distance in the embedded dimensions are in fact further away in the original dimensions. Besides, UMAP and t-SNE cannot track the variance of clusters. Through the embedding of t-SNE and UMAP, the variance of a cluster is not only associated with the true variance but also is proportional to the sample size. RESULTS: We present supCPM, a robust supervised visualization method, which separates different clusters, preserves the global structure and tracks the cluster variance. Compared with six visualization methods using synthetic and real datasets, supCPM shows improved performance than other methods in preserving the global geometric structure and data variance. Overall, supCPM provides an enhanced visualization pipeline to assist the interpretation of functional transition and accurately depict population segregation. AVAILABILITY AND IMPLEMENTATION: The R package and source code are available at https://zenodo.org/record/5975977#.YgqR1PXMJjM. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

This paper extends robust principal component analysis (RPCA) to nonlinear manifolds. Suppose that the observed data matrix is the sum of a sparse component and a component drawn from some low dimensional manifold. Is it possible to separate them by using similar ideas as RPCA? Is there any benefit in treating the manifold as a whole as opposed to treating each local region independently? We answer these two questions affirmatively by proposing and analyzing an optimization framework that separates the sparse component from the manifold under noisy data. Theoretical error bounds are provided when the tangent spaces of the manifold satisfy certain incoherence conditions. We also provide a near optimal choice of the tuning parameters for the proposed optimization formulation with the help of a new curvature estimation method. The efficacy of our method is demonstrated on both synthetic and real datasets.

Gene-expression deconvolution is used to quantify different types of cells in a mixed population. It provides a highly promising solution to rapidly characterize the tumor-infiltrating immune landscape and identify cold cancers. However, a major challenge is that gene-expression data are frequently contaminated by many outliers that decrease the estimation accuracy. Thus, it is imperative to develop a robust deconvolution method that automatically decontaminates data by reliably detecting and removing outliers. We developed a new machine learning tool, Fast And Robust DEconvolution of Expression Profiles (FARDEEP), to enumerate immune cell subsets from whole tumor tissue samples. To reduce noise in the tumor gene expression datasets, FARDEEP utilizes an adaptive least trimmed square to automatically detect and remove outliers before estimating the cell compositions. We show that FARDEEP is less susceptible to outliers and returns a better estimation of coefficients than the existing methods with both numerical simulations and real datasets. FARDEEP provides an estimate related to the absolute quantity of each immune cell subset in addition to relative percentages. Hence, FARDEEP represents a novel robust algorithm to complement the existing toolkit for the characterization of tissue-infiltrating immune cell landscape. The source code for FARDEEP is implemented in R and available for download at https://github.com/YuningHao/FARDEEP.git.