SCALE method for single-cell ATAC-seq analysis via latent feature extraction

A Bibliometric Analysis of the Spatial Transcriptomics Literature from 2006 to 2023

In recent years, spatial transcriptomics (ST) research has become a popular field of study and has shown great potential in medicine. However, there are few bibliometric analyses in this field. Thus, in this study, we aimed to find and analyze the frontiers and trends of this medical research field based on the available literature. A computerized search was applied to the WoSCC (Web of Science Core Collection) Database for literature published from 2006 to 2023. Complete records of all literature and cited references were extracted and screened. The bibliometric analysis and visualization were performed using CiteSpace, VOSviewer, Bibliometrix R Package software, and Scimago Graphica. A total of 1467 papers and reviews were included. The analysis revealed that the ST publication and citation results have shown a rapid upward trend over the last 3 years. Nature Communications and Nature were the most productive and most co-cited journals, respectively. In the comprehensive global collaborative network, the United States is the country with the most organizations and publications, followed closely by China and the United Kingdom. The author Joakim Lundeberg published the most cited paper, while Patrik L. Ståhl ranked first among co-cited authors. The hot topics in ST are tissue recognition, cancer, heterogeneity, immunotherapy, differentiation, and models. ST technologies have greatly contributed to in-depth research in medical fields such as oncology and neuroscience, opening up new possibilities for the diagnosis and treatment of diseases. Moreover, artificial intelligence and big data drive additional development in ST fields.

Dependency-aware deep generative models for multitasking analysis of spatial omics data

Spatially resolved transcriptomics (SRT) technologies have significantly advanced biomedical research, but their data analysis remains challenging due to the discrete nature of the data and the high levels of noise, compounded by complex spatial dependencies. Here, we propose spaVAE, a dependency-aware, deep generative spatial variational autoencoder model that probabilistically characterizes count data while capturing spatial correlations. spaVAE introduces a hybrid embedding combining a Gaussian process prior with a Gaussian prior to explicitly capture spatial correlations among spots. It then optimizes the parameters of deep neural networks to approximate the distributions underlying the SRT data. With the approximated distributions, spaVAE can contribute to several analytical tasks that are essential for SRT data analysis, including dimensionality reduction, visualization, clustering, batch integration, denoising, differential expression, spatial interpolation, resolution enhancement and identification of spatially variable genes. Moreover, we have extended spaVAE to spaPeakVAE and spaMultiVAE to characterize spatial ATAC-seq (assay for transposase-accessible chromatin using sequencing) data and spatial multi-omics data, respectively.

Discrete latent embedding of single-cell chromatin accessibility sequencing data for uncovering cell heterogeneity

Single-cell epigenomic data has been growing continuously at an unprecedented pace, but their characteristics such as high dimensionality and sparsity pose substantial challenges to downstream analysis. Although deep learning models-especially variational autoencoders-have been widely used to capture low-dimensional feature embeddings, the prevalent Gaussian assumption somewhat disagrees with real data, and these models tend to struggle to incorporate reference information from abundant cell atlases. Here we propose CASTLE, a deep generative model based on the vector-quantized variational autoencoder framework to extract discrete latent embeddings that interpretably characterize single-cell chromatin accessibility sequencing data. We validate the performance and robustness of CASTLE for accurate cell-type identification and reasonable visualization compared with state-of-the-art methods. We demonstrate the advantages of CASTLE for effective incorporation of existing massive reference datasets in a weakly supervised or supervised manner. We further demonstrate CASTLE's capacity for intuitively distilling cell-type-specific feature spectra that unveil cell heterogeneity and biological implications quantitatively.

Data-driven clustering approach to identify novel clusters of high cognitive impairment risk among Chinese community-dwelling elderly people with normal cognition: A national cohort study

Background

Cognitive impairment is a highly heterogeneous disorder that necessitates further investigation into the distinct characteristics of populations at varying risk levels of cognitive impairment. Using a large-scale registry cohort of elderly individuals, we applied a data-driven approach to identify novel clusters based on diverse sociodemographic features.

Methods

A prospective cohort of 6398 elderly people from the Chinese Longitudinal Healthy Longevity Survey, followed between 2008-14, was used to develop and validate the model. Participants were aged ≥60 years, community-dwelling, and the Chinese version of the Mini-Mental State Examination (MMSE) score ≥18 were included. Sixty-nine sociodemographic features were included in the analysis. The total population was divided into two-thirds for the derivation cohort (n = 4265) and one-third for the validation cohort (n = 2133). In the derivation cohort, an unsupervised Gaussian mixture model was applied to categorise participants into distinct clusters. A classifier was developed based on the most important 10 factors and was applied to categorise participants into their corresponding clusters in a validation cohort. The difference in the three-year risk of cognitive impairment was compared across the clusters.

Results

We identified four clusters with distinct features in the derivation cohort. Cluster 1 was associated with the worst life independence, longest sleep duration, and the oldest age. Cluster 2 demonstrated the highest loneliness, characterised by non-marital status and living alone. Cluster 3 was characterised by the lowest sense of loneliness and the highest proportions in marital status and family co-residence. Cluster 4 demonstrated heightened engagement in exercise and leisure activity, along with independent decision-making, hygiene, and a diverse diet. In comparison to Cluster 4, Cluster 1 exhibited the highest three-year cognitive impairment risk (adjusted odds ratio (aOR) = 3.31; 95% confidence interval (CI) = 1.81-6.05), followed by Cluster 2 and Cluster 3 after adjustment for baseline MMSE, residence, sex, age, years of education, drinking, smoking, hypertension, diabetes, heart disease and stroke or cardiovascular diseases.

Conclusions

A data-driven approach can be instrumental in identifying individuals at high risk of cognitive impairment among cognitively normal elderly populations. Based on various sociodemographic features, these clusters can suggest individualised intervention plans.

Deciphering cell types by integrating scATAC-seq data with genome sequences

The single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) technology provides insight into gene regulation and epigenetic heterogeneity at single-cell resolution, but cell annotation from scATAC-seq remains challenging due to high dimensionality and extreme sparsity within the data. Existing cell annotation methods mostly focus on the cell peak matrix without fully utilizing the underlying genomic sequence. Here we propose a method, SANGO, for accurate single-cell annotation by integrating genome sequences around the accessibility peaks within scATAC data. The genome sequences of peaks are encoded into low-dimensional embeddings, and then iteratively used to reconstruct the peak statistics of cells through a fully connected network. The learned weights are considered as regulatory modes to represent cells, and utilized to align the query cells and the annotated cells in the reference data through a graph transformer network for cell annotations. SANGO was demonstrated to consistently outperform competing methods on 55 paired scATAC-seq datasets across samples, platforms and tissues. SANGO was also shown to be able to detect unknown tumor cells through attention edge weights learned by the graph transformer. Moreover, from the annotated cells, we found cell-type-specific peaks that provide functional insights/biological signals through expression enrichment analysis, cis-regulatory chromatin interaction analysis and motif enrichment analysis.

Joint Representation Learning for Retrieval and Annotation of Genomic Interval Sets

As available genomic interval data increase in scale, we require fast systems to search them. A common approach is simple string matching to compare a search term to metadata, but this is limited by incomplete or inaccurate annotations. An alternative is to compare data directly through genomic region overlap analysis, but this approach leads to challenges like sparsity, high dimensionality, and computational expense. We require novel methods to quickly and flexibly query large, messy genomic interval databases. Here, we develop a genomic interval search system using representation learning. We train numerical embeddings for a collection of region sets simultaneously with their metadata labels, capturing similarity between region sets and their metadata in a low-dimensional space. Using these learned co-embeddings, we develop a system that solves three related information retrieval tasks using embedding distance computations: retrieving region sets related to a user query string, suggesting new labels for database region sets, and retrieving database region sets similar to a query region set. We evaluate these use cases and show that jointly learned representations of region sets and metadata are a promising approach for fast, flexible, and accurate genomic region information retrieval.

Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges

Machine learning (ML), particularly deep learning (DL), has made rapid and substantial progress in synthetic biology in recent years. Biotechnological applications of biosystems, including pathways, enzymes, and whole cells, are being probed frequently with time. The intricacy and interconnectedness of biosystems make it challenging to design them with the desired properties. ML and DL have a synergy with synthetic biology. Synthetic biology can be employed to produce large data sets for training models (for instance, by utilizing DNA synthesis), and ML/DL models can be employed to inform design (for example, by generating new parts or advising unrivaled experiments to perform). This potential has recently been brought to light by research at the intersection of engineering biology and ML/DL through achievements like the design of novel biological components, best experimental design, automated analysis of microscopy data, protein structure prediction, and biomolecular implementations of ANNs (Artificial Neural Networks). I have divided this review into three sections. In the first section, I describe predictive potential and basics of ML along with myriad applications in synthetic biology, especially in engineering cells, activity of proteins, and metabolic pathways. In the second section, I describe fundamental DL architectures and their applications in synthetic biology. Finally, I describe different challenges causing hurdles in the progress of ML/DL and synthetic biology along with their solutions.

scAuto as a comprehensive framework for single-cell chromatin accessibility data analysis

Interpreting single-cell chromatin accessibility data is crucial for understanding intercellular heterogeneity regulation. Despite the progress in computational methods for analyzing this data, there is still a lack of a comprehensive analytical framework and a user-friendly online analysis tool. To fill this gap, we developed a pre-trained deep learning-based framework, single-cell auto-correlation transformers (scAuto), to overcome the challenge. Following DNABERT's methodology of pre-training and fine-tuning, scAuto learns a general understanding of DNA sequence's grammar by being pre-trained on unlabeled human genome via self-supervision; it is then transferred to the single-cell chromatin accessibility analysis task of scATAC-seq data for supervised fine-tuning. We extensively validated scAuto on the Buenrostro2018 dataset, demonstrating its superior performance on chromatin accessibility prediction, single-cell clustering, and data denoising. Based on scAuto, we further developed an interactive web server for single-cell chromatin accessibility data analysis. It integrates tutorial-style interfaces for those with limited programming skills. The platform is accessible at http://zhanglab.icaup.cn. To our knowledge, this work is expected to help analyze single-cell chromatin accessibility data and facilitate the development of precision medicine.

scCASE: accurate and interpretable enhancement for single-cell chromatin accessibility sequencing data

Single-cell chromatin accessibility sequencing (scCAS) has emerged as a valuable tool for interrogating and elucidating epigenomic heterogeneity and gene regulation. However, scCAS data inherently suffers from limitations such as high sparsity and dimensionality, which pose significant challenges for downstream analyses. Although several methods are proposed to enhance scCAS data, there are still challenges and limitations that hinder the effectiveness of these methods. Here, we propose scCASE, a scCAS data enhancement method based on non-negative matrix factorization which incorporates an iteratively updating cell-to-cell similarity matrix. Through comprehensive experiments on multiple datasets, we demonstrate the advantages of scCASE over existing methods for scCAS data enhancement. The interpretable cell type-specific peaks identified by scCASE can provide valuable biological insights into cell subpopulations. Moreover, to leverage the large compendia of available omics data as a reference, we further expand scCASE to scCASER, which enables the incorporation of external reference data to improve enhancement performance.

A fast, scalable and versatile tool for analysis of single-cell omics data

Single-cell omics technologies have revolutionized the study of gene regulation in complex tissues. A major computational challenge in analyzing these datasets is to project the large-scale and high-dimensional data into low-dimensional space while retaining the relative relationships between cells. This low dimension embedding is necessary to decompose cellular heterogeneity and reconstruct cell-type-specific gene regulatory programs. Traditional dimensionality reduction techniques, however, face challenges in computational efficiency and in comprehensively addressing cellular diversity across varied molecular modalities. Here we introduce a nonlinear dimensionality reduction algorithm, embodied in the Python package SnapATAC2, which not only achieves a more precise capture of single-cell omics data heterogeneities but also ensures efficient runtime and memory usage, scaling linearly with the number of cells. Our algorithm demonstrates exceptional performance, scalability and versatility across diverse single-cell omics datasets, including single-cell assay for transposase-accessible chromatin using sequencing, single-cell RNA sequencing, single-cell Hi-C and single-cell multi-omics datasets, underscoring its utility in advancing single-cell analysis.

Representing and extracting knowledge from single-cell data

Single-cell analysis is currently one of the most high-resolution techniques to study biology. The large complex datasets that have been generated have spurred numerous developments in computational biology, in particular the use of advanced statistics and machine learning. This review attempts to explain the deeper theoretical concepts that underpin current state-of-the-art analysis methods. Single-cell analysis is covered from cell, through instruments, to current and upcoming models. The aim of this review is to spread concepts which are not yet in common use, especially from topology and generative processes, and how new statistical models can be developed to capture more of biology. This opens epistemological questions regarding our ontology and models, and some pointers will be given to how natural language processing (NLP) may help overcome our cognitive limitations for understanding single-cell data.

Incorporating network diffusion and peak location information for better single-cell ATAC-seq data analysis

Single-cell assay for transposase-accessible chromatin using sequencing (scATAC-seq) data provided new insights into the understanding of epigenetic heterogeneity and transcriptional regulation. With the increasing abundance of dataset resources, there is an urgent need to extract more useful information through high-quality data analysis methods specifically designed for scATAC-seq. However, analyzing scATAC-seq data poses challenges due to its near binarization, high sparsity and ultra-high dimensionality properties. Here, we proposed a novel network diffusion-based computational method to comprehensively analyze scATAC-seq data, named Single-Cell ATAC-seq Analysis via Network Refinement with Peaks Location Information (SCARP). SCARP formulates the Network Refinement diffusion method under the graph theory framework to aggregate information from different network orders, effectively compensating for missing signals in the scATAC-seq data. By incorporating distance information between adjacent peaks on the genome, SCARP also contributes to depicting the co-accessibility of peaks. These two innovations empower SCARP to obtain lower-dimensional representations for both cells and peaks more effectively. We have demonstrated through sufficient experiments that SCARP facilitated superior analyses of scATAC-seq data. Specifically, SCARP exhibited outstanding cell clustering performance, enabling better elucidation of cell heterogeneity and the discovery of new biologically significant cell subpopulations. Additionally, SCARP was also instrumental in portraying co-accessibility relationships of accessible regions and providing new insight into transcriptional regulation. Consequently, SCARP identified genes that were involved in key Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways related to diseases and predicted reliable cis-regulatory interactions. To sum up, our studies suggested that SCARP is a promising tool to comprehensively analyze the scATAC-seq data.

scMLC: an accurate and robust multiplex community detection method for single-cell multi-omics data

Clustering cells based on single-cell multi-modal sequencing technologies provides an unprecedented opportunity to create high-resolution cell atlas, reveal cellular critical states and study health and diseases. However, effectively integrating different sequencing data for cell clustering remains a challenging task. Motivated by the successful application of Louvain in scRNA-seq data, we propose a single-cell multi-modal Louvain clustering framework, called scMLC, to tackle this problem. scMLC builds multiplex single- and cross-modal cell-to-cell networks to capture modal-specific and consistent information between modalities and then adopts a robust multiplex community detection method to obtain the reliable cell clusters. In comparison with 15 state-of-the-art clustering methods on seven real datasets simultaneously measuring gene expression and chromatin accessibility, scMLC achieves better accuracy and stability in most datasets. Synthetic results also indicate that the cell-network-based integration strategy of multi-omics data is superior to other strategies in terms of generalization. Moreover, scMLC is flexible and can be extended to single-cell sequencing data with more than two modalities.

Uniform quantification of single-nucleus ATAC-seq data with Paired-Insertion Counting (PIC) and a model-based insertion rate estimator

Existing approaches to scoring single-nucleus assay for transposase-accessible chromatin with sequencing (snATAC-seq) feature matrices from sequencing reads are inconsistent, affecting downstream analyses and displaying artifacts. We show that, even with sparse single-cell data, quantitative counts are informative for estimating the regulatory state of a cell, which calls for a consistent treatment. We propose Paired-Insertion Counting as a uniform method for snATAC-seq feature characterization and provide a probability model for inferring latent insertion dynamics from snATAC-seq count matrices.

Modeling fragment counts improves single-cell ATAC-seq analysis

Single-cell ATAC sequencing coverage in regulatory regions is typically binarized as an indicator of open chromatin. Here we show that binarization is an unnecessary step that neither improves goodness of fit, clustering, cell type identification nor batch integration. Fragment counts, but not read counts, should instead be modeled, which preserves quantitative regulatory information. These results have immediate implications for single-cell ATAC sequencing analysis.

Cofea: correlation-based feature selection for single-cell chromatin accessibility data

Single-cell chromatin accessibility sequencing (scCAS) technologies have enabled characterizing the epigenomic heterogeneity of individual cells. However, the identification of features of scCAS data that are relevant to underlying biological processes remains a significant gap. Here, we introduce a novel method Cofea, to fill this gap. Through comprehensive experiments on 5 simulated and 54 real datasets, Cofea demonstrates its superiority in capturing cellular heterogeneity and facilitating downstream analysis. Applying this method to identification of cell type-specific peaks and candidate enhancers, as well as pathway enrichment analysis and partitioned heritability analysis, we illustrate the potential of Cofea to uncover functional biological process.

scATAC-seq preprocessing and imputation evaluation system for visualization, clustering and digital footprinting

Single-cell ATAC-seq (scATAC-seq) is a recently developed approach that provides means to investigate open chromatin at single cell level, to assess epigenetic regulation and transcription factors binding landscapes. The sparsity of the scATAC-seq data calls for imputation. Similarly, preprocessing (filtering) may be required to reduce computational load due to the large number of open regions. However, optimal strategies for both imputation and preprocessing have not been yet evaluated together. We present SAPIEnS (scATAC-seq Preprocessing and Imputation Evaluation System), a benchmark for scATAC-seq imputation frameworks, a combination of state-of-the-art imputation methods with commonly used preprocessing techniques. We assess different types of scATAC-seq analysis, i.e. clustering, visualization and digital genomic footprinting, and attain optimal preprocessing-imputation strategies. We discuss the benefits of the imputation framework depending on the task and the number of the dataset features (peaks). We conclude that the preprocessing with the Boruta method is beneficial for the majority of tasks, while imputation is helpful mostly for small datasets. We also implement a SAPIEnS database with pre-computed transcription factor footprints based on imputed data with their activity scores in a specific cell type. SAPIEnS is published at: https://github.com/lab-medvedeva/SAPIEnS. SAPIEnS database is available at: https://sapiensdb.com.

Deep Learning Methods for Omics Data Imputation

One common problem in omics data analysis is missing values, which can arise due to various reasons, such as poor tissue quality and insufficient sample volumes. Instead of discarding missing values and related data, imputation approaches offer an alternative means of handling missing data. However, the imputation of missing omics data is a non-trivial task. Difficulties mainly come from high dimensionality, non-linear or non-monotonic relationships within features, technical variations introduced by sampling methods, sample heterogeneity, and the non-random missingness mechanism. Several advanced imputation methods, including deep learning-based methods, have been proposed to address these challenges. Due to its capability of modeling complex patterns and relationships in large and high-dimensional datasets, many researchers have adopted deep learning models to impute missing omics data. This review provides a comprehensive overview of the currently available deep learning-based methods for omics imputation from the perspective of deep generative model architectures such as autoencoder, variational autoencoder, generative adversarial networks, and Transformer, with an emphasis on multi-omics data imputation. In addition, this review also discusses the opportunities that deep learning brings and the challenges that it might face in this field.

SnapATAC2: a fast, scalable and versatile tool for analysis of single-cell omics data

Single-cell omics technologies have ushered in a new era for the study of dynamic gene regulation in complex tissues during development and disease pathogenesis. A major computational challenge in analyzing these datasets is to project the large-scale and high dimensional data into low-dimensional space while retaining the relative relationships between cells in order to decompose the cellular heterogeneity and reconstruct cell-type-specific gene regulatory programs. Conventional dimensionality reduction methods suffer from computational inefficiency, difficulty to capture the full spectrum of cellular heterogeneity, or inability to apply across diverse molecular modalities. Here, we report a fast and nonlinear dimensionality reduction algorithm that not only more accurately captures the heterogeneities of single-cell omics data, but also features runtime and memory usage that is computational efficient and linearly proportional to cell numbers. We implement this algorithm in a Python package named SnapATAC2, and demonstrate its superior performance, remarkable scalability and general adaptability using an array of single-cell omics data types, including single-cell ATAC-seq, single-cell RNA-seq, single-cell Hi-C, and single-cell multiomics datasets.

Deep learning applications in single-cell genomics and transcriptomics data analysis

Traditional bulk sequencing methods are limited to measuring the average signal in a group of cells, potentially masking heterogeneity, and rare populations. The single-cell resolution, however, enhances our understanding of complex biological systems and diseases, such as cancer, the immune system, and chronic diseases. However, the single-cell technologies generate massive amounts of data that are often high-dimensional, sparse, and complex, thus making analysis with traditional computational approaches difficult and unfeasible. To tackle these challenges, many are turning to deep learning (DL) methods as potential alternatives to the conventional machine learning (ML) algorithms for single-cell studies. DL is a branch of ML capable of extracting high-level features from raw inputs in multiple stages. Compared to traditional ML, DL models have provided significant improvements across many domains and applications. In this work, we examine DL applications in genomics, transcriptomics, spatial transcriptomics, and multi-omics integration, and address whether DL techniques will prove to be advantageous or if the single-cell omics domain poses unique challenges. Through a systematic literature review, we have found that DL has not yet revolutionized the most pressing challenges of the single-cell omics field. However, using DL models for single-cell omics has shown promising results (in many cases outperforming the previous state-of-the-art models) in data preprocessing and downstream analysis. Although developments of DL algorithms for single-cell omics have generally been gradual, recent advances reveal that DL can offer valuable resources in fast-tracking and advancing research in single-cell.

Deep learning exploration of single-cell and spatially resolved cancer transcriptomics to unravel tumour heterogeneity

Tumour heterogeneity is one of the critical confounding aspects in decoding tumour growth. Malignant cells display variations in their gene transcription profiles and mutation spectra even when originating from a single progenitor cell. Single-cell and spatial transcriptomics sequencing have recently emerged as key technologies for unravelling tumour heterogeneity. Single-cell sequencing promotes individual cell-type identification through transcriptome-wide gene expression measurements of each cell. Spatial transcriptomics facilitates identification of cell-cell interactions and the structural organization of heterogeneous cells within a tumour tissue through associating spatial RNA abundance of cells at distinct spots in the tissue section. However, extracting features and analyzing single-cell and spatial transcriptomics data poses challenges. Single-cell transcriptome data is extremely noisy and its sparse nature and dropouts can lead to misinterpretation of gene expression and the misclassification of cell types. Deep learning predictive power can overcome data challenges, provide high-resolution analysis and enhance precision oncology applications that involve early cancer prognosis, diagnosis, patient survival estimation and anti-cancer therapy planning. In this paper, we provide a background to and review of the recent progress of deep learning frameworks to investigate tumour heterogeneity using both single-cell and spatial transcriptomics data types.

A benchmark of computational pipelines for single-cell histone modification data

BACKGROUND

Single-cell histone post translational modification (scHPTM) assays such as scCUT&Tag or scChIP-seq allow single-cell mapping of diverse epigenomic landscapes within complex tissues and are likely to unlock our understanding of various mechanisms involved in development or diseases. Running scHTPM experiments and analyzing the data produced remains challenging since few consensus guidelines currently exist regarding good practices for experimental design and data analysis pipelines.

RESULTS

We perform a computational benchmark to assess the impact of experimental parameters and data analysis pipelines on the ability of the cell representation to recapitulate known biological similarities. We run more than ten thousand experiments to systematically study the impact of coverage and number of cells, of the count matrix construction method, of feature selection and normalization, and of the dimension reduction algorithm used. This allows us to identify key experimental parameters and computational choices to obtain a good representation of single-cell HPTM data. We show in particular that the count matrix construction step has a strong influence on the quality of the representation and that using fixed-size bin counts outperforms annotation-based binning. Dimension reduction methods based on latent semantic indexing outperform others, and feature selection is detrimental, while keeping only high-quality cells has little influence on the final representation as long as enough cells are analyzed.

CONCLUSIONS

This benchmark provides a comprehensive study on how experimental parameters and computational choices affect the representation of single-cell HPTM data. We propose a series of recommendations regarding matrix construction, feature and cell selection, and dimensionality reduction algorithms.

Ensemble deep learning of embeddings for clustering multimodal single-cell omics data

MOTIVATION

Recent advances in multimodal single-cell omics technologies enable multiple modalities of molecular attributes, such as gene expression, chromatin accessibility, and protein abundance, to be profiled simultaneously at a global level in individual cells. While the increasing availability of multiple data modalities is expected to provide a more accurate clustering and characterization of cells, the development of computational methods that are capable of extracting information embedded across data modalities is still in its infancy.

RESULTS

We propose SnapCCESS for clustering cells by integrating data modalities in multimodal single-cell omics data using an unsupervised ensemble deep learning framework. By creating snapshots of embeddings of multimodality using variational autoencoders, SnapCCESS can be coupled with various clustering algorithms for generating consensus clustering of cells. We applied SnapCCESS with several clustering algorithms to various datasets generated from popular multimodal single-cell omics technologies. Our results demonstrate that SnapCCESS is effective and more efficient than conventional ensemble deep learning-based clustering methods and outperforms other state-of-the-art multimodal embedding generation methods in integrating data modalities for clustering cells. The improved clustering of cells from SnapCCESS will pave the way for more accurate characterization of cell identity and types, an essential step for various downstream analyses of multimodal single-cell omics data.

AVAILABILITY AND IMPLEMENTATION

SnapCCESS is implemented as a Python package and is freely available from https://github.com/PYangLab/SnapCCESS under the open-source license of GPL-3. The data used in this study are publicly available (see section 'Data availability').

Tensor decomposition discriminates tissues using scATAC-seq

ATAC-seq is a powerful tool for measuring the landscape structure of a chromosome. scATAC-seq is a recently updated version of ATAC-seq performed in a single cell. The problem with scATAC-seq is data sparsity and most of the genomic sites are inaccessible. Here, tensor decomposition (TD) was used to fill in missing values. In this study, TD was applied to massive scATAC-seq datasets generated by approximately 200 bp intervals, and this number can reach 13,627,618. Currently, no other methods can deal with large sparse matrices. The proposed method could not only provide UMAP embedding that coincides with tissue specificity, but also select genes associated with various biological enrichment terms and transcription factor targeting. This suggests that TD is a useful tool to process a large sparse matrix generated from scATAC-seq.

Cell-specific clock-controlled gene expression program regulates rhythmic fiber cell growth in cotton

BACKGROUND

The epidermis of cotton ovule produces fibers, the most important natural cellulose source for the global textile industry. However, the molecular mechanism of fiber cell growth is still poorly understood.

RESULTS

Here, we develop an optimized protoplasting method, and integrate single-cell RNA sequencing (scRNA-seq) and single-cell ATAC sequencing (scATAC-seq) to systematically characterize the cells of the outer integument of ovules from wild type and fuzzless/lintless (fl) cotton (Gossypium hirsutum). By jointly analyzing the scRNA-seq data from wildtype and fl, we identify five cell populations including the fiber cell type and construct the development trajectory for fiber lineage cells. Interestingly, by time-course diurnal transcriptomic analysis, we demonstrate that the primary growth of fiber cells is a highly regulated circadian rhythmic process. Moreover, we identify a small peptide GhRALF1 that circadian rhythmically controls fiber growth possibly through oscillating auxin signaling and proton pump activity in the plasma membrane. Combining with scATAC-seq, we further identify two cardinal cis-regulatory elements (CREs, TCP motif, and TCP-like motif) which are bound by the trans factors GhTCP14s to modulate the circadian rhythmic metabolism of mitochondria and protein translation through regulating approximately one third of genes that are highly expressed in fiber cells.

CONCLUSIONS

We uncover a fiber-specific circadian clock-controlled gene expression program in regulating fiber growth. This study unprecedentedly reveals a new route to improve fiber traits by engineering the circadian clock of fiber cells.

A Unified Deep Learning Framework for Single-Cell ATAC-Seq Analysis Based on ProdDep Transformer Encoder

Recent advances in single-cell sequencing assays for the transposase-accessibility chromatin (scATAC-seq) technique have provided cell-specific chromatin accessibility landscapes of cis-regulatory elements, providing deeper insights into cellular states and dynamics. However, few research efforts have been dedicated to modeling the relationship between regulatory grammars and single-cell chromatin accessibility and incorporating different analysis scenarios of scATAC-seq data into the general framework. To this end, we propose a unified deep learning framework based on the ProdDep Transformer Encoder, dubbed PROTRAIT, for scATAC-seq data analysis. Specifically motivated by the deep language model, PROTRAIT leverages the ProdDep Transformer Encoder to capture the syntax of transcription factor (TF)-DNA binding motifs from scATAC-seq peaks for predicting single-cell chromatin accessibility and learning single-cell embedding. Based on cell embedding, PROTRAIT annotates cell types using the Louvain algorithm. Furthermore, according to the identified likely noises of raw scATAC-seq data, PROTRAIT denoises these values based on predated chromatin accessibility. In addition, PROTRAIT employs differential accessibility analysis to infer TF activity at single-cell and single-nucleotide resolution. Extensive experiments based on the Buenrostro2018 dataset validate the effeteness of PROTRAIT for chromatin accessibility prediction, cell type annotation, and scATAC-seq data denoising, therein outperforming current approaches in terms of different evaluation metrics. Besides, we confirm the consistency between the inferred TF activity and the literature review. We also demonstrate the scalability of PROTRAIT to analyze datasets containing over one million cells.

siVAE: interpretable deep generative models for single-cell transcriptomes

Neural networks such as variational autoencoders (VAE) perform dimensionality reduction for the visualization and analysis of genomic data, but are limited in their interpretability: it is unknown which data features are represented by each embedding dimension. We present siVAE, a VAE that is interpretable by design, thereby enhancing downstream analysis tasks. Through interpretation, siVAE also identifies gene modules and hubs without explicit gene network inference. We use siVAE to identify gene modules whose connectivity is associated with diverse phenotypes such as iPSC neuronal differentiation efficiency and dementia, showcasing the wide applicability of interpretable generative models for genomic data analysis.

Matching queried single-cell open-chromatin profiles to large pools of single-cell transcriptomes and epigenomes for reference supported analysis

The true benefits of large single-cell transcriptome and epigenome data sets can be realized only with the development of new approaches and search tools for annotating individual cells. Matching a single-cell epigenome profile to a large pool of reference cells remains a major challenge. Here, we present scEpiSearch, which enables searching, comparison, and independent classification of single-cell open-chromatin profiles against a large reference of single-cell expression and open-chromatin data sets. Across performance benchmarks, scEpiSearch outperformed multiple methods in accuracy of search and low-dimensional coembedding of single-cell profiles, irrespective of platforms and species. Here we also demonstrate the unconventional utilities of scEpiSearch by applying it on single-cell epigenome profiles of K562 cells and samples from patients with acute leukaemia to reveal different aspects of their heterogeneity, multipotent behavior, and dedifferentiated states. Applying scEpiSearch on our single-cell open-chromatin profiles from embryonic stem cells (ESCs), we identified ESC subpopulations with more activity and poising for endoplasmic reticulum stress and unfolded protein response. Thus, scEpiSearch solves the nontrivial problem of amalgamating information from a large pool of single cells to identify and study the regulatory states of cells using their single-cell epigenomes.

Applications of deep learning in understanding gene regulation

Gene regulation is a central topic in cell biology. Advances in omics technologies and the accumulation of omics data have provided better opportunities for gene regulation studies than ever before. For this reason deep learning, as a data-driven predictive modeling approach, has been successfully applied to this field during the past decade. In this article, we aim to give a brief yet comprehensive overview of representative deep-learning methods for gene regulation. Specifically, we discuss and compare the design principles and datasets used by each method, creating a reference for researchers who wish to replicate or improve existing methods. We also discuss the common problems of existing approaches and prospectively introduce the emerging deep-learning paradigms that will potentially alleviate them. We hope that this article will provide a rich and up-to-date resource and shed light on future research directions in this area.

RefTM: reference-guided topic modeling of single-cell chromatin accessibility data

Single-cell analysis is a valuable approach for dissecting the cellular heterogeneity, and single-cell chromatin accessibility sequencing (scCAS) can profile the epigenetic landscapes for thousands of individual cells. It is challenging to analyze scCAS data, because of its high dimensionality and a higher degree of sparsity compared with scRNA-seq data. Topic modeling in single-cell data analysis can lead to robust identification of the cell types and it can provide insight into the regulatory mechanisms. Reference-guided approach may facilitate the analysis of scCAS data by utilizing the information in existing datasets. We present RefTM (Reference-guided Topic Modeling of single-cell chromatin accessibility data), which not only utilizes the information in existing bulk chromatin accessibility and annotated scCAS data, but also takes advantage of topic models for single-cell data analysis. RefTM simultaneously models: (1) the shared biological variation among reference data and the target scCAS data; (2) the unique biological variation in scCAS data; (3) other variations from known covariates in scCAS data.

Characterizing cis-regulatory elements using single-cell epigenomics

Cell type-specific gene expression patterns and dynamics during development or in disease are controlled by cis-regulatory elements (CREs), such as promoters and enhancers. Distinct classes of CREs can be characterized by their epigenomic features, including DNA methylation, chromatin accessibility, combinations of histone modifications and conformation of local chromatin. Tremendous progress has been made in cataloguing CREs in the human genome using bulk transcriptomic and epigenomic methods. However, single-cell epigenomic and multi-omic technologies have the potential to provide deeper insight into cell type-specific gene regulatory programmes as well as into how they change during development, in response to environmental cues and through disease pathogenesis. Here, we highlight recent advances in single-cell epigenomic methods and analytical tools and discuss their readiness for human tissue profiling.

scVAEBGM: Clustering Analysis of Single-Cell ATAC-seq Data Using a Deep Generative Model

A surge in research has occurred because of current developments in single-cell technologies. Above all, single-cell Assay for Transposase-Accessible Chromatin with high throughput sequencing (scATAC-seq) is a popular approach of analyzing chromatin accessibility differences at the level of single cell, either within or between groups. As a result, it is critical to examine cell heterogeneity at a previously unseen level and to identify both recognized and unknown cell types. However, with the ever-increasing number of cells engendered by technological development and the characteristics of the data, such as high noise, sparsity and dimension, challenges in distinguishing cell types have emerged. We propose scVAEBGM, which integrates a Variational Autoencoder (VAE) with a Bayesian Gaussian-mixture model (BGM) to process and analyze scATAC-seq data. This method combines and takes benefits of a Bayesian Gaussian mixture model to estimate the number of cell types without determining the cluster number in a beforehand. In other words, the size of the clusters is inferred from the data, thus avoiding biases introduced by subjective assessments when manually determining the size of the clusters. Additionally, the method is more robust to noise and can better represent single-cell data in lower dimensions. We also create a further clustering strategy. It is indicated by experiments that further clustering based on the already completed clustering can improve the clustering accuracy again. We test on six public datasets, and scVAEBGM outperforms various dimension reduction baselines. In downstream applications, scVAEBGM can reveal biological cell types.

Advances in Single-Cell Sequencing Technology and Its Application in Poultry Science

Single-cell sequencing (SCS) uses a single cell as the research material and involves three dimensions: genes, phenotypes and cell biological mechanisms. This type of research can locate target cells, analyze the dynamic changes in the target cells and the relationships between the cells, and pinpoint the molecular mechanism of cell formation. Currently, a common problem faced by animal husbandry scientists is how to apply existing science and technology to promote the production of high-quality livestock and poultry products and to breed livestock for disease resistance; this is also a bottleneck for the sustainable development of animal husbandry. In recent years, although SCS technology has been successfully applied in the fields of medicine and bioscience, its application in poultry science has been rarely reported. With the sustainable development of science and technology and the poultry industry, SCS technology has great potential in the application of poultry science (or animal husbandry). Therefore, it is necessary to review the innovation of SCS technology and its application in poultry science. This article summarizes the current main technical methods of SCS and its application in poultry, which can provide potential references for its future applications in precision breeding, disease prevention and control, immunity, and cell identification.

scAWMV: an adaptively weighted multi-view learning framework for the integrative analysis of parallel scRNA-seq and scATAC-seq data

MOTIVATION

Technological advances have enabled us to profile single-cell multi-omics data from the same cells, providing us with an unprecedented opportunity to understand the cellular phenotype and links to its genotype. The available protocols and multi-omics datasets [including parallel single-cell RNA sequencing (scRNA-seq) and single-cell ATAC sequencing (scATAC-seq) data profiled from the same cell] are growing increasingly. However, such data are highly sparse and tend to have high level of noise, making data analysis challenging. The methods that integrate the multi-omics data can potentially improve the capacity of revealing the cellular heterogeneity.

RESULTS

We propose an adaptively weighted multi-view learning (scAWMV) method for the integrative analysis of parallel scRNA-seq and scATAC-seq data profiled from the same cell. scAWMV considers both the difference in importance across different modalities in multi-omics data and the biological connection of the features in the scRNA-seq and scATAC-seq data. It generates biologically meaningful low-dimensional representations for the transcriptomic and epigenomic profiles via unsupervised learning. Application to four real datasets demonstrates that our framework scAWMV is an efficient method to dissect cellular heterogeneity for single-cell multi-omics data.

AVAILABILITY AND IMPLEMENTATION

The software and datasets are available at https://github.com/pengchengzeng/scAWMV.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Multimodal Single-Cell Translation and Alignment with Semi-Supervised Learning

Single-cell multi-omics technologies enable comprehensive interrogation of cellular regulation, yet most single-cell assays measure only one type of activity-such as transcription, chromatin accessibility, DNA methylation, or 3D chromatin architecture-for each cell. To enable a multimodal view for individual cells, we propose Polarbear, a semi-supervised machine learning framework that facilitates missing modality profile prediction and single-cell cross-modality alignment. Polarbear learns to translate between modalities by using data from co-assay measurements coupled with the large quantity of single-assay data available in public databases. This semi-supervised scheme mitigates issues related to low cell quantities and high sparsity in co-assay data. Polarbear first pre-trains a beta-variational autoencoder for each modality using both co-assay and single-assay profiles to learn robust representations of individual cells, and it then uses the co-assay labels to train a translator between these cell representations. This semi-supervised framework enables us to predict missing modality profiles and match single cells across modalities with improved accuracy compared with fully supervised methods, thus facilitating multimodal data integration.

Data-driven clustering approach to identify novel phenotypes using multiple biomarkers in acute ischaemic stroke: A retrospective, multicentre cohort study

BACKGROUND

Acute ischaemic stroke (AIS) is a highly heterogeneous disorder and warrants further investigation to stratify patients with different outcomes and treatment responses. Using a large-scale stroke registry cohort, we applied data-driven approach to identify novel phenotypes based on multiple biomarkers.

METHODS

In a nationwide, prospective, 201-hospital registry study taking place in China between August 01, 2015 and March 31, 2018, the patients with AIS who were over 18 years of age and admitted to the hospital within 7 days from symptom onset were included. 92 biomarkers were included in the analysis. In the derivation cohort (n=9539), an unsupervised Gaussian mixture model was applied to categorize patients into distinct phenotypes. A classifier was developed using the most important biomarkers and was applied to categorize patients into their corresponding phenotypes in an validation cohort (n=2496). The differences in biological features, clinical outcomes, and treatment response were compared across the phenotypes.

FINDINGS

We identified four phenotypes with distinct characteristics in 9288 patients with non-cardioembolic ischaemic stroke. Phenotype 1 was associated with abnormal glucose and lipid metabolism. Phenotype 2 was characterized by inflammation and abnormal renal function. Phenotype 3 had the least laboratory abnormalities and small infarct lesions. Phenotype 4 was characterized by disturbance in homocysteine metabolism. Findings were replicated in the validation cohort. In comparison with phenotype 3, the risk of stroke recurrence (adjusted hazard ratio [aHR] 2.02, 95% confidence intervals [CI] 1.04-3.94), and mortality (aHR 18.14, 95%CI 6.62-49.71) at 3-month post-stroke were highest in phenotype 2, followed by phenotype 4 and phenotype 1, after adjustment for age, gender, smoking, drinking, history of stroke, hypertension, diabetes mellitus, dyslipidemia, and coronary heart disease. The Monte Carlo simulation showed that the patients with phenotype 2 could benefit from high-intensity statin therapy.

INTERPRETATION

A data-driven approach could aid in the identification of patients at a higher risk of adverse clinical outcomes following non-cardioembolic ischaemic stroke. These phenotypes, based on different pathophysiology, can suggest individualized treatment plans.

FUNDING

Beijing Natural Science Foundation (grant number Z200016), Beijing Municipal Committee of Science and Technology (grant number Z201100005620010), National Natural Science Foundation of China (grant number 82101360, 92046016, 82171270), Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences (grant number 2019-I2M-5-029).

The performance of deep generative models for learning joint embeddings of single-cell multi-omics data

Recent extensions of single-cell studies to multiple data modalities raise new questions regarding experimental design. For example, the challenge of sparsity in single-omics data might be partly resolved by compensating for missing information across modalities. In particular, deep learning approaches, such as deep generative models (DGMs), can potentially uncover complex patterns via a joint embedding. Yet, this also raises the question of sample size requirements for identifying such patterns from single-cell multi-omics data. Here, we empirically examine the quality of DGM-based integrations for varying sample sizes. We first review the existing literature and give a short overview of deep learning methods for multi-omics integration. Next, we consider eight popular tools in more detail and examine their robustness to different cell numbers, covering two of the most common multi-omics types currently favored. Specifically, we use data featuring simultaneous gene expression measurements at the RNA level and protein abundance measurements for cell surface proteins (CITE-seq), as well as data where chromatin accessibility and RNA expression are measured in thousands of cells (10x Multiome). We examine the ability of the methods to learn joint embeddings based on biological and technical metrics. Finally, we provide recommendations for the design of multi-omics experiments and discuss potential future developments.

Integrating Micro and Nano Technologies for Cell Engineering and Analysis: Toward the Next Generation of Cell Therapy Workflows

The emerging field of cell therapy offers the potential to treat and even cure a diverse array of diseases for which existing interventions are inadequate. Recent advances in micro and nanotechnology have added a multitude of single cell analysis methods to our research repertoire. At the same time, techniques have been developed for the precise engineering and manipulation of cells. Together, these methods have aided the understanding of disease pathophysiology, helped formulate corrective interventions at the cellular level, and expanded the spectrum of available cell therapeutic options. This review discusses how micro and nanotechnology have catalyzed the development of cell sorting, cellular engineering, and single cell analysis technologies, which have become essential workflow components in developing cell-based therapeutics. The review focuses on the technologies adopted in research studies and explores the opportunities and challenges in combining the various elements of cell engineering and single cell analysis into the next generation of integrated and automated platforms that can accelerate preclinical studies and translational research.

Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space

Computational tools for integrative analyses of diverse single-cell experiments are facing formidable new challenges including dramatic increases in data scale, sample heterogeneity, and the need to informatively cross-reference new data with foundational datasets. Here, we present SCALEX, a deep-learning method that integrates single-cell data by projecting cells into a batch-invariant, common cell-embedding space in a truly online manner (i.e., without retraining the model). SCALEX substantially outperforms online iNMF and other state-of-the-art non-online integration methods on benchmark single-cell datasets of diverse modalities, (e.g., single-cell RNA sequencing, scRNA-seq, single-cell assay for transposase-accessible chromatin use sequencing, scATAC-seq), especially for datasets with partial overlaps, accurately aligning similar cell populations while retaining true biological differences. We showcase SCALEX's advantages by constructing continuously expandable single-cell atlases for human, mouse, and COVID-19 patients, each assembled from diverse data sources and growing with every new data. The online data integration capacity and superior performance makes SCALEX particularly appropriate for large-scale single-cell applications to build upon previous scientific insights.

Normalization and de-noising of single-cell Hi-C data with BandNorm and scVI-3D

Single-cell high-throughput chromatin conformation capture methodologies (scHi-C) enable profiling of long-range genomic interactions. However, data from these technologies are prone to technical noise and biases that hinder downstream analysis. We develop a normalization approach, BandNorm, and a deep generative modeling framework, scVI-3D, to account for scHi-C specific biases. In benchmarking experiments, BandNorm yields leading performances in a time and memory efficient manner for cell-type separation, identification of interacting loci, and recovery of cell-type relationships, while scVI-3D exhibits advantages for rare cell types and under high sparsity scenarios. Application of BandNorm coupled with gene-associating domain analysis reveals scRNA-seq validated sub-cell type identification.

Single-cell gene regulation network inference by large-scale data integration

Single-cell ATAC-seq (scATAC-seq) has proven to be a state-of-art approach to investigating gene regulation at the single-cell level. However, existing methods cannot precisely uncover cell-type-specific binding of transcription regulators (TRs) and construct gene regulation networks (GRNs) in single-cell. ChIP-seq has been widely used to profile TR binding sites in the past decades. Here, we developed SCRIP, an integrative method to infer single-cell TR activity and targets based on the integration of scATAC-seq and a large-scale TR ChIP-seq reference. Our method showed improved performance in evaluating TR binding activity compared to the existing motif-based methods and reached a higher consistency with matched TR expressions. Besides, our method enables identifying TR target genes as well as building GRNs at the single-cell resolution based on a regulatory potential model. We demonstrate SCRIP's utility in accurate cell-type clustering, lineage tracing, and inferring cell-type-specific GRNs in multiple biological systems. SCRIP is freely available at https://github.com/wanglabtongji/SCRIP.

Integrated analysis of multimodal single-cell data with structural similarity

Multimodal single-cell sequencing technologies provide unprecedented information on cellular heterogeneity from multiple layers of genomic readouts. However, joint analysis of two modalities without properly handling the noise often leads to overfitting of one modality by the other and worse clustering results than vanilla single-modality analysis. How to efficiently utilize the extra information from single cell multi-omics to delineate cell states and identify meaningful signal remains as a significant computational challenge. In this work, we propose a deep learning framework, named SAILERX, for efficient, robust, and flexible analysis of multi-modal single-cell data. SAILERX consists of a variational autoencoder with invariant representation learning to correct technical noises from sequencing process, and a multimodal data alignment mechanism to integrate information from different modalities. Instead of performing hard alignment by projecting both modalities to a shared latent space, SAILERX encourages the local structures of two modalities measured by pairwise similarities to be similar. This strategy is more robust against overfitting of noises, which facilitates various downstream analysis such as clustering, imputation, and marker gene detection. Furthermore, the invariant representation learning part enables SAILERX to perform integrative analysis on both multi- and single-modal datasets, making it an applicable and scalable tool for more general scenarios.

scBasset: sequence-based modeling of single-cell ATAC-seq using convolutional neural networks

Single-cell assay for transposase-accessible chromatin using sequencing (scATAC) shows great promise for studying cellular heterogeneity in epigenetic landscapes, but there remain important challenges in the analysis of scATAC data due to the inherent high dimensionality and sparsity. Here we introduce scBasset, a sequence-based convolutional neural network method to model scATAC data. We show that by leveraging the DNA sequence information underlying accessibility peaks and the expressiveness of a neural network model, scBasset achieves state-of-the-art performance across a variety of tasks on scATAC and single-cell multiome datasets, including cell clustering, scATAC profile denoising, data integration across assays and transcription factor activity inference.

Joint analysis of scATAC-seq datasets using epiConv

Background

Technical improvement in ATAC-seq makes it possible for high throughput profiling the chromatin states of single cells. However, data from multiple sources frequently show strong technical variations, which is referred to as batch effects. In order to perform joint analysis across multiple datasets, specialized method is required to remove technical variations between datasets while keep biological information.

Results

Here we present an algorithm named epiConv to perform joint analyses on scATAC-seq datasets. We first show that epiConv better corrects batch effects and is less prone to over-fitting problem than existing methods on a collection of PBMC datasets. In a collection of mouse brain data, we show that epiConv is capable of aligning low-depth scATAC-Seq from co-assay data (simultaneous profiling of transcriptome and chromatin) onto high-quality ATAC-seq reference and increasing the resolution of chromatin profiles of co-assay data. Finally, we show that epiConv can be used to integrate cells from different biological conditions (T cells in normal vs. germ-free mouse; normal vs. malignant hematopoiesis), which reveals hidden cell populations that would otherwise be undetectable.

Conclusions

In this study, we introduce epiConv to integrate multiple scATAC-seq datasets and perform joint analysis on them. Through several case studies, we show that epiConv removes the batch effects and retains the biological signal. Moreover, joint analysis across multiple datasets improves the performance of clustering and differentially accessible peak calling, especially when the biological signal is weak in single dataset.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04858-w.

Single-cell specific and interpretable machine learning models for sparse scChIP-seq data imputation

Motivation

Single-cell Chromatin ImmunoPrecipitation DNA-Sequencing (scChIP-seq) analysis is challenging due to data sparsity. High degree of sparsity in biological high-throughput single-cell data is generally handled with imputation methods that complete the data, but specific methods for scChIP-seq are lacking. We present SIMPA, a scChIP-seq data imputation method leveraging predictive information within bulk data from the ENCODE project to impute missing protein-DNA interacting regions of target histone marks or transcription factors.

Results

Imputations using machine learning models trained for each single cell, each ChIP protein target, and each genomic region accurately preserve cell type clustering and improve pathway-related gene identification on real human data. Results on bulk data simulating single cells show that the imputations are single-cell specific as the imputed profiles are closer to the simulated cell than to other cells related to the same ChIP protein target and the same cell type. Simulations also show that 100 input genomic regions are already enough to train single-cell specific models for the imputation of thousands of undetected regions. Furthermore, SIMPA enables the interpretation of machine learning models by revealing interaction sites of a given single cell that are most important for the imputation model trained for a specific genomic region. The corresponding feature importance values derived from promoter-interaction profiles of H3K4me3, an activating histone mark, highly correlate with co-expression of genes that are present within the cell-type specific pathways in 2 real human and mouse datasets. The SIMPA’s interpretable imputation method allows users to gain a deep understanding of individual cells and, consequently, of sparse scChIP-seq datasets.

Availability and implementation

Our interpretable imputation algorithm was implemented in Python and is available at https://github.com/salbrec/SIMPA.

Disentangling single-cell omics representation with a power spectral density-based feature extraction

Emerging single-cell technologies provide high-resolution measurements of distinct cellular modalities opening new avenues for generating detailed cellular atlases of many and diverse tissues. The high dimensionality, sparsity, and inaccuracy of single cell sequencing measurements, however, can obscure discriminatory information, mask cellular subtype variations and complicate downstream analyses which can limit our understanding of cell function and tissue heterogeneity. Here, we present a novel pre-processing method (scPSD) inspired by power spectral density analysis that enhances the accuracy for cell subtype separation from large-scale single-cell omics data. We comprehensively benchmarked our method on a wide range of single-cell RNA-sequencing datasets and showed that scPSD pre-processing, while being fast and scalable, significantly reduces data complexity, enhances cell-type separation, and enables rare cell identification. Additionally, we applied scPSD to transcriptomics and chromatin accessibility cell atlases and demonstrated its capacity to discriminate over 100 cell types across the whole organism and across different modalities of single-cell omics data.

Current progress and open challenges for applying deep learning across the biosciences

Deep Learning (DL) has recently enabled unprecedented advances in one of the grand challenges in computational biology: the half-century-old problem of protein structure prediction. In this paper we discuss recent advances, limitations, and future perspectives of DL on five broad areas: protein structure prediction, protein function prediction, genome engineering, systems biology and data integration, and phylogenetic inference. We discuss each application area and cover the main bottlenecks of DL approaches, such as training data, problem scope, and the ability to leverage existing DL architectures in new contexts. To conclude, we provide a summary of the subject-specific and general challenges for DL across the biosciences.