BRAIxDet: Learning to detect malignant breast lesion with incomplete annotations.

Methods to detect malignant lesions from screening mammograms are usually trained with fully annotated datasets, where images are labelled with the localisation and classification of cancerous lesions. However, real-world screening mammogram datasets commonly have a subset that is fully annotated and another subset that is weakly annotated with just the global classification (i.e., without lesion localisation). Given the large size of such datasets, researchers usually face a dilemma with the weakly annotated subset: to not use it or to fully annotate it. The first option will reduce detection accuracy because it does not use the whole dataset, and the second option is too expensive given that the annotation needs to be done by expert radiologists. In this paper, we propose a middle-ground solution for the dilemma, which is to formulate the training as a weakly- and semi-supervised learning problem that we refer to as malignant breast lesion detection with incomplete annotations. To address this problem, our new method comprises two stages, namely: (1) pre-training a multi-view mammogram classifier with weak supervision from the whole dataset, and (2) extending the trained classifier to become a multi-view detector that is trained with semi-supervised student-teacher learning, where the training set contains fully and weakly-annotated mammograms. We provide extensive detection results on two real-world screening mammogram datasets containing incomplete annotations and show that our proposed approach achieves state-of-the-art results in the detection of malignant breast lesions with incomplete annotations.

De novo transcriptome assembly and genome annotation of the fat-tailed dunnart (Sminthopsis crassicaudata).

Marsupials exhibit distinctive modes of reproduction and early development that set them apart from their eutherian counterparts and render them invaluable for comparative studies. However, marsupial genomic resources still lag far behind those of eutherian mammals. We present a series of novel genomic resources for the fat-tailed dunnart (Sminthopsis crassicaudata), a mouse-like marsupial that, due to its ease of husbandry and ex-utero development, is emerging as a laboratory model. We constructed a highly representative multi-tissue de novo transcriptome assembly of dunnart RNA-seq reads spanning 12 tissues. The transcriptome includes 2,093,982 assembled transcripts and has a mammalian transcriptome BUSCO completeness score of 93.3%, the highest amongst currently published marsupial transcriptomes. This global transcriptome, along with ab initio predictions, supported annotation of the existing dunnart genome, revealing 21,622 protein-coding genes. Altogether, these resources will enable wider use of the dunnart as a model marsupial and deepen our understanding of mammalian genome evolution.

Demuxafy: improvement in droplet assignment by integrating multiple single-cell demultiplexing and doublet detection methods.

Recent innovations in single-cell RNA-sequencing (scRNA-seq) provide the technology to investigate biological questions at cellular resolution. Pooling cells from multiple individuals has become a common strategy, and droplets can subsequently be assigned to a specific individual by leveraging their inherent genetic differences. An implicit challenge with scRNA-seq is the occurrence of doublets-droplets containing two or more cells. We develop Demuxafy, a framework to enhance donor assignment and doublet removal through the consensus intersection of multiple demultiplexing and doublet detecting methods. Demuxafy significantly improves droplet assignment by separating singlets from doublets and classifying the correct individual.

Cell-type-specific and disease-associated expression quantitative trait loci in the human lung.

Common genetic variants confer substantial risk for chronic lung diseases, including pulmonary fibrosis. Defining the genetic control of gene expression in a cell-type-specific and context-dependent manner is critical for understanding the mechanisms through which genetic variation influences complex traits and disease pathobiology. To this end, we performed single-cell RNA sequencing of lung tissue from 66 individuals with pulmonary fibrosis and 48 unaffected donors. Using a pseudobulk approach, we mapped expression quantitative trait loci (eQTLs) across 38 cell types, observing both shared and cell-type-specific regulatory effects. Furthermore, we identified disease interaction eQTLs and demonstrated that this class of associations is more likely to be cell-type-specific and linked to cellular dysregulation in pulmonary fibrosis. Finally, we connected lung disease risk variants to their regulatory targets in disease-relevant cell types. These results indicate that cellular context determines the impact of genetic variation on gene expression and implicates context-specific eQTLs as key regulators of lung homeostasis and disease.

A comparison of marker gene selection methods for single-cell RNA sequencing data.

BACKGROUND: The development of single-cell RNA sequencing (scRNA-seq) has enabled scientists to catalog and probe the transcriptional heterogeneity of individual cells in unprecedented detail. A common step in the analysis of scRNA-seq data is the selection of so-called marker genes, most commonly to enable annotation of the biological cell types present in the sample. In this paper, we benchmark 59 computational methods for selecting marker genes in scRNA-seq data. RESULTS: We compare the performance of the methods using 14 real scRNA-seq datasets and over 170 additional simulated datasets. Methods are compared on their ability to recover simulated and expert-annotated marker genes, the predictive performance and characteristics of the gene sets they select, their memory usage and speed, and their implementation quality. In addition, various case studies are used to scrutinize the most commonly used methods, highlighting issues and inconsistencies. CONCLUSIONS: Overall, we present a comprehensive evaluation of methods for selecting marker genes in scRNA-seq data. Our results highlight the efficacy of simple methods, especially the Wilcoxon rank-sum test, Student's t-test, and logistic regression.

An Interpretable and Accurate Deep-Learning Diagnosis Framework Modeled With Fully and Semi-Supervised Reciprocal Learning.

The deployment of automated deep-learning classifiers in clinical practice has the potential to streamline the diagnosis process and improve the diagnosis accuracy, but the acceptance of those classifiers relies on both their accuracy and interpretability. In general, accurate deep-learning classifiers provide little model interpretability, while interpretable models do not have competitive classification accuracy. In this paper, we introduce a new deep-learning diagnosis framework, called InterNRL, that is designed to be highly accurate and interpretable. InterNRL consists of a student-teacher framework, where the student model is an interpretable prototype-based classifier (ProtoPNet) and the teacher is an accurate global image classifier (GlobalNet). The two classifiers are mutually optimised with a novel reciprocal learning paradigm in which the student ProtoPNet learns from optimal pseudo labels produced by the teacher GlobalNet, while GlobalNet learns from ProtoPNet's classification performance and pseudo labels. This reciprocal learning paradigm enables InterNRL to be flexibly optimised under both fully- and semi-supervised learning scenarios, reaching state-of-the-art classification performance in both scenarios for the tasks of breast cancer and retinal disease diagnosis. Moreover, relying on weakly-labelled training images, InterNRL also achieves superior breast cancer localisation and brain tumour segmentation results than other competing methods.

Fancm has dual roles in the limiting of meiotic crossovers and germ cell maintenance in mammals.

Meiotic crossovers are required for accurate chromosome segregation and producing new allelic combinations. Meiotic crossover numbers are tightly regulated within a narrow range, despite an excess of initiating DNA double-strand breaks. Here, we reveal the tumor suppressor FANCM as a meiotic anti-crossover factor in mammals. We use unique large-scale crossover analyses with both single-gamete sequencing and pedigree-based bulk-sequencing datasets to identify a genome-wide increase in crossover frequencies in Fancm-deficient mice. Gametogenesis is heavily perturbed in Fancm loss-of-function mice, which is consistent with the reproductive defects reported in humans with biallelic FANCM mutations. A portion of the gametogenesis defects can be attributed to the cGAS-STING pathway after birth. Despite the gametogenesis phenotypes in Fancm mutants, both sexes are capable of producing offspring. We propose that the anti-crossover function and role in gametogenesis of Fancm are separable and will inform diagnostic pathways for human genomic instability disorders.

ADMANI: Annotated Digital Mammograms and Associated Non-Image Datasets.

Supplemental material is available for this article. Keywords: Mammography, Screening, Convolutional Neural Network (CNN) Published under a CC BY 4.0 license. See also the commentary by Cadrin-Chênevert in this issue.

Cell type-specific and disease-associated eQTL in the human lung.

Common genetic variants confer substantial risk for chronic lung diseases, including pulmonary fibrosis (PF). Defining the genetic control of gene expression in a cell-type-specific and context-dependent manner is critical for understanding the mechanisms through which genetic variation influences complex traits and disease pathobiology. To this end, we performed single-cell RNA-sequencing of lung tissue from 67 PF and 49 unaffected donors. Employing a pseudo-bulk approach, we mapped expression quantitative trait loci (eQTL) across 38 cell types, observing both shared and cell type-specific regulatory effects. Further, we identified disease-interaction eQTL and demonstrated that this class of associations is more likely to be cell-type specific and linked to cellular dysregulation in PF. Finally, we connected PF risk variants to their regulatory targets in disease-relevant cell types. These results indicate that cellular context determines the impact of genetic variation on gene expression, and implicates context-specific eQTL as key regulators of lung homeostasis and disease.

Image-based spatial transcriptomics identifies molecular niche dysregulation associated with distal lung remodeling in pulmonary fibrosis.

The human lung is structurally complex, with a diversity of specialized epithelial, stromal and immune cells playing specific functional roles in anatomically distinct locations, and large-scale changes in the structure and cellular makeup of this distal lung is a hallmark of pulmonary fibrosis (PF) and other progressive chronic lung diseases. Single-cell transcriptomic studies have revealed numerous disease-emergent/enriched cell types/states in PF lungs, but the spatial contexts wherein these cells contribute to disease pathogenesis has remained uncertain. Using sub-cellular resolution image-based spatial transcriptomics, we analyzed the gene expression of more than 1 million cells from 19 unique lungs. Through complementary cell-based and innovative cell-agnostic analyses, we characterized the localization of PF-emergent cell-types, established the cellular and molecular basis of classical PF histopathologic disease features, and identified a diversity of distinct molecularly-defined spatial niches in control and PF lungs. Using machine-learning and trajectory analysis methods to segment and rank airspaces on a gradient from normal to most severely remodeled, we identified a sequence of compositional and molecular changes that associate with progressive distal lung pathology, beginning with alveolar epithelial dysregulation and culminating with changes in macrophage polarization. Together, these results provide a unique, spatially-resolved characterization of the cellular and molecular programs of PF and control lungs, provide new insights into the heterogeneous pathobiology of PF, and establish analytical approaches which should be broadly applicable to other imaging-based spatial transcriptomic studies.

Trade-off between conservation of biological variation and batch effect removal in deep generative modeling for single-cell transcriptomics.

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) technology has contributed significantly to diverse research areas in biology, from cancer to development. Since scRNA-seq data is high-dimensional, a common strategy is to learn low-dimensional latent representations better to understand overall structure in the data. In this work, we build upon scVI, a powerful deep generative model which can learn biologically meaningful latent representations, but which has limited explicit control of batch effects. Rather than prioritizing batch effect removal over conservation of biological variation, or vice versa, our goal is to provide a bird's eye view of the trade-offs between these two conflicting objectives. Specifically, using the well established concept of Pareto front from economics and engineering, we seek to learn the entire trade-off curve between conservation of biological variation and removal of batch effects. RESULTS: A multi-objective optimisation technique known as Pareto multi-task learning (Pareto MTL) is used to obtain the Pareto front between conservation of biological variation and batch effect removal. Our results indicate Pareto MTL can obtain a better Pareto front than the naive scalarization approach typically encountered in the literature. In addition, we propose to measure batch effect by applying a neural-network based estimator called Mutual Information Neural Estimation (MINE) and show benefits over the more standard maximum mean discrepancy measure. CONCLUSION: The Pareto front between conservation of biological variation and batch effect removal is a valuable tool for researchers in computational biology. Our results demonstrate the efficacy of applying Pareto MTL to estimate the Pareto front in conjunction with applying MINE to measure the batch effect.

sgcocaller and comapr: personalised haplotype assembly and comparative crossover map analysis using single-gamete sequencing data.

Profiling gametes of an individual enables the construction of personalised haplotypes and meiotic crossover landscapes, now achievable at larger scale than ever through the availability of high-throughput single-cell sequencing technologies. However, high-throughput single-gamete data commonly have low depth of coverage per gamete, which challenges existing gamete-based haplotype phasing methods. In addition, haplotyping a large number of single gametes from high-throughput single-cell DNA sequencing data and constructing meiotic crossover profiles using existing methods requires intensive processing. Here, we introduce efficient software tools for the essential tasks of generating personalised haplotypes and calling crossovers in gametes from single-gamete DNA sequencing data (sgcocaller), and constructing, visualising, and comparing individualised crossover landscapes from single gametes (comapr). With additional data pre-possessing, the tools can also be applied to bulk-sequenced samples. We demonstrate that sgcocaller is able to generate impeccable phasing results for high-coverage datasets, on which it is more accurate and stable than existing methods, and also performs well on low-coverage single-gamete sequencing datasets for which current methods fail. Our tools achieve highly accurate results with user-friendly installation, comprehensive documentation, efficient computation times and minimal memory usage.

SSNIP-seq: A simple and rapid method for isolation of single-sperm nucleic acid for high-throughput sequencing.

We developed a simple and reliable method for the isolation of haploid nuclei from fresh and frozen testes. The described protocol uses readily available reagents in combination with flow cytometry to separate haploid and diploid nuclei. The protocol can be completed within 1 hour and the resulting individual haploid nuclei have intact morphology. The isolated nuclei are suitable for library preparation for high-throughput DNA and RNA sequencing using bulk or single nuclei. The protocol was optimised with mouse testes and we anticipate that it can be applied for the isolation of mature sperm from other mammals including humans.

Case Report: Hypoglycemia Due to a Novel Activating Glucokinase Variant in an Adult - a Molecular Approach.

We present a case of an obese 22-year-old man with activating GCK variant who had neonatal hypoglycemia, re-emerging with hypoglycemia later in life. We investigated him for asymptomatic hypoglycemia with a family history of hypoglycemia. Genetic testing yielded a novel GCK missense class 3 variant that was subsequently found in his mother, sister and nephew and reclassified as a class 4 likely pathogenic variant. Glucokinase enables phosphorylation of glucose, the rate-limiting step of glycolysis in the liver and pancreatic ß cells. It plays a crucial role in the regulation of insulin secretion. Inactivating variants in GCK cause hyperglycemia and activating variants cause hypoglycemia. Spleen-preserving distal pancreatectomy revealed diffuse hyperplastic islets, nuclear pleomorphism and periductular islets. Glucose stimulated insulin secretion revealed increased insulin secretion in response to glucose. Cytoplasmic calcium, which triggers exocytosis of insulin-containing granules, revealed normal basal but increased glucose-stimulated level. Unbiased gene expression analysis using 10X single cell sequencing revealed upregulated INS and CKB genes and downregulated DLK1 and NPY genes in ß-cells. Further studies are required to see if alteration in expression of these genes plays a role in the metabolic and histological phenotype associated with glucokinase pathogenic variant. There were more large islets in the patient's pancreas than in control subjects but there was no difference in the proportion of ß cells in the islets. His hypoglycemia was persistent after pancreatectomy, was refractory to diazoxide and improved with pasireotide. This case highlights the variable phenotype of GCK mutations. In-depth molecular analyses in the islets have revealed possible mechanisms for hyperplastic islets and insulin hypersecretion.

Key signaling networks are dysregulated in patients with the adipose tissue disorder, lipedema.

OBJECTIVES: Lipedema, a poorly understood chronic disease of adipose hyper-deposition, is often mistaken for obesity and causes significant impairment to mobility and quality-of-life. To identify molecular mechanisms underpinning lipedema, we employed comprehensive omics-based comparative analyses of whole tissue, adipocyte precursors (adipose-derived stem cells (ADSCs)), and adipocytes from patients with or without lipedema. METHODS: We compared whole-tissues, ADSCs, and adipocytes from body mass index-matched lipedema (n = 14) and unaffected (n = 10) patients using comprehensive global lipidomic and metabolomic analyses, transcriptional profiling, and functional assays. RESULTS: Transcriptional profiling revealed >4400 significant differences in lipedema tissue, with altered levels of mRNAs involved in critical signaling and cell function-regulating pathways (e.g., lipid metabolism and cell-cycle/proliferation). Functional assays showed accelerated ADSC proliferation and differentiation in lipedema. Profiling lipedema adipocytes revealed >900 changes in lipid composition and >600 differentially altered metabolites. Transcriptional profiling of lipedema ADSCs and non-lipedema ADSCs revealed significant differential expression of >3400 genes including some involved in extracellular matrix and cell-cycle/proliferation signaling pathways. One upregulated gene in lipedema ADSCs, Bub1, encodes a cell-cycle regulator, central to the kinetochore complex, which regulates several histone proteins involved in cell proliferation. Downstream signaling analysis of lipedema ADSCs demonstrated enhanced activation of histone H2A, a key cell proliferation driver and Bub1 target. Critically, hyperproliferation exhibited by lipedema ADSCs was inhibited by the small molecule Bub1 inhibitor 2OH-BNPP1 and by CRISPR/Cas9-mediated Bub1 gene depletion. CONCLUSION: We found significant differences in gene expression, and lipid and metabolite profiles, in tissue, ADSCs, and adipocytes from lipedema patients compared to non-affected controls. Functional assays demonstrated that dysregulated Bub1 signaling drives increased proliferation of lipedema ADSCs, suggesting a potential mechanism for enhanced adipogenesis in lipedema. Importantly, our characterization of signaling networks driving lipedema identifies potential molecular targets, including Bub1, for novel lipedema therapeutics.

splatPop: simulating population scale single-cell RNA sequencing data.

Population-scale single-cell RNA sequencing (scRNA-seq) is now viable, enabling finer resolution functional genomics studies and leading to a rush to adapt bulk methods and develop new single-cell-specific methods to perform these studies. Simulations are useful for developing, testing, and benchmarking methods but current scRNA-seq simulation frameworks do not simulate population-scale data with genetic effects. Here, we present splatPop, a model for flexible, reproducible, and well-documented simulation of population-scale scRNA-seq data with known expression quantitative trait loci. splatPop can also simulate complex batch, cell group, and conditional effects between individuals from different cohorts as well as genetically-driven co-expression.

Optimizing expression quantitative trait locus mapping workflows for single-cell studies.

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) has enabled the unbiased, high-throughput quantification of gene expression specific to cell types and states. With the cost of scRNA-seq decreasing and techniques for sample multiplexing improving, population-scale scRNA-seq, and thus single-cell expression quantitative trait locus (sc-eQTL) mapping, is increasingly feasible. Mapping of sc-eQTL provides additional resolution to study the regulatory role of common genetic variants on gene expression across a plethora of cell types and states and promises to improve our understanding of genetic regulation across tissues in both health and disease. RESULTS: While previously established methods for bulk eQTL mapping can, in principle, be applied to sc-eQTL mapping, there are a number of open questions about how best to process scRNA-seq data and adapt bulk methods to optimize sc-eQTL mapping. Here, we evaluate the role of different normalization and aggregation strategies, covariate adjustment techniques, and multiple testing correction methods to establish best practice guidelines. We use both real and simulated datasets across single-cell technologies to systematically assess the impact of these different statistical approaches. CONCLUSION: We provide recommendations for future single-cell eQTL studies that can yield up to twice as many eQTL discoveries as default approaches ported from bulk studies.

Personalized genome structure via single gamete sequencing.

Genetic maps have been fundamental to building our understanding of disease genetics and evolutionary processes. The gametes of an individual contain all of the information required to perform a de novo chromosome-scale assembly of an individual's genome, which historically has been performed with populations and pedigrees. Here, we discuss how single-cell gamete sequencing offers the potential to merge the advantages of short-read sequencing with the ability to build personalized genetic maps and open up an entirely new space in personalized genetics.

Tutorial: guidelines for the computational analysis of single-cell RNA sequencing data.

Single-cell RNA sequencing (scRNA-seq) is a popular and powerful technology that allows you to profile the whole transcriptome of a large number of individual cells. However, the analysis of the large volumes of data generated from these experiments requires specialized statistical and computational methods. Here we present an overview of the computational workflow involved in processing scRNA-seq data. We discuss some of the most common tasks and the tools available for addressing central biological questions. In this article and our companion website ( https://scrnaseq-course.cog.sanger.ac.uk/website/index.html ), we provide guidelines regarding best practices for performing computational analyses. This tutorial provides a hands-on guide for experimentalists interested in analyzing their data as well as an overview for bioinformaticians seeking to develop new computational methods.