references.bib

@article{Lun2019,
author = {Lun, Aaron and Riesenfeld, Samantha and Andrews, Tallulah and Dao, The and Gomes, Tomas and Marioni, John},
year = {2019},
month = {03},
pages = {63},
title = {EmptyDrops: Distinguishing cells from empty droplets in droplet-based single-cell RNA sequencing data},
volume = {20},
journal = {Genome Biology},
doi = {10.1186/s13059-019-1662-y}
}

@article{VanDijk2018,
abstract = {Single-cell RNA sequencing technologies suffer from many sources of technical noise, including under-sampling of mRNA molecules, often termed “dropout,” which can severely obscure important gene-gene relationships. To address this, we developed MAGIC (Markov affinity-based graph imputation of cells), a method that shares information across similar cells, via data diffusion, to denoise the cell count matrix and fill in missing transcripts. We validate MAGIC on several biological systems and find it effective at recovering gene-gene relationships and additional structures. Applied to the epithilial to mesenchymal transition, MAGIC reveals a phenotypic continuum, with the majority of cells residing in intermediate states that display stem-like signatures, and infers known and previously uncharacterized regulatory interactions, demonstrating that our approach can successfully uncover regulatory relations without perturbations. A new algorithm overcomes limitations of data loss in single-cell sequencing experiments.},
author = {van Dijk, David and Sharma, Roshan and Nainys, Juozas and Yim, Kristina and Kathail, Pooja and Carr, Ambrose J. and Burdziak, Cassandra and Moon, Kevin R. and Chaffer, Christine L. and Pattabiraman, Diwakar and Bierie, Brian and Mazutis, Linas and Wolf, Guy and Krishnaswamy, Smita and Pe'er, Dana},
doi = {10.1016/j.cell.2018.05.061},
file = {::},
issn = {10974172},
journal = {Cell},
keywords = {EMT,imputation,manifold learning,regulatory networks,single-cell RNA sequencing},
month = {jul},
number = {3},
pages = {716--729.e27},
pmid = {29961576},
publisher = {Cell},
title = {{Recovering Gene Interactions from Single-Cell Data Using Data Diffusion}},
url = {https://pubmed.ncbi.nlm.nih.gov/29961576/},
volume = {174},
year = {2018}
}

@article{Andrews2018,
abstract = {Background: Single-cell RNASeq is a powerful tool for measuring gene expression at the resolution of individual cells. A significant challenge in the analysis of this data is the large amount of zero values, representing either missing data or no expression. Several imputation approaches have been proposed to deal with this issue, but since these methods generally rely on structure inherent to the dataset under consideration they may not provide any additional information. Methods: We evaluated the risk of generating false positive or irreproducible results when imputing data with five different methods. We applied each method to a variety of simulated datasets as well as to permuted real single-cell RNASeq datasets and consider the number of false positive gene-gene correlations and differentially expressed genes. Using matched 10X Chromium and Smartseq2 data from the Tabula Muris database we examined the reproducibility of markers before and after imputation. Results: The extent of false-positive signals introduced by imputation varied considerably by method. Data smoothing based methods, MAGIC and knn-smooth, generated a very high number of false-positives in both real and simulated data. Model-based imputation methods typically generated fewer false-positives but this varied greatly depending on how well datasets conformed to the underlying model. Furthermore, only SAVER exhibited reproducibility comparable to unimputed data across matched data. Conclusions: Imputation of single-cell RNASeq data introduces circularity that can generate false-positive results. Thus, statistical tests applied to imputed data should be treated with care. Additional filtering by effect size can reduce but not fully eliminate these effects. Of the methods we considered, SAVER was the least likely to generate false or irreproducible results, thus should be favoured over alternatives if imputation is necessary.},
author = {Andrews, Tallulah S. and Hemberg, Martin},
doi = {10.12688/f1000research.16613.1},
issn = {20461402},
journal = {F1000Research},
keywords = {Gene expression,Imputation,RNA-seq,Reproducibility,Type 1 errors,single-cell},
pages = {1740},
pmid = {30906525},
publisher = {F1000 Research Ltd},
title = {{False signals induced by single-cell imputation}},
url = {https://pubmed.ncbi.nlm.nih.gov/30906525/},
volume = {7},
year = {2018}
}

@article{10xGenomics2019,
author = {10xGenomics},
journal = {10xGenomics},
pages = {5--9},
title = {{Single-Cell RNA-Seq: An Introductory Overview and Tools for Getting Started. Retrieved 06-08-2019. https://community.10xgenomics.com/t5/10x-Blog/Single-Cell-RNA-Seq-An-Introductory-Overview-and-Tools-for/ba-p/547}},
url = {https://www.10xgenomics.com/blog/single-cell-rna-seq-an-introductory-overview-and-tools-for-getting-started},
year = {2019}
}

@misc{Nature2013,
abstract = {Methods to sequence the DNA and RNA of single cells are poised to transform many areas of biology and medicine.},
booktitle = {Nature Methods},
doi = {10.1038/nmeth.2801},
file = {:C\:/Users/ibgun/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Unknown - 2014 - Method of the Year 2013.pdf:pdf},
issn = {15487105},
keywords = {DNA sequencing,RNA sequencing,Transcriptomics,Whole genome amplification},
month = {dec},
number = {1},
pages = {1},
pmid = {24524124},
publisher = {Nature Publishing Group},
title = {{Method of the Year 2013}},
url = {https://www.nature.com/articles/nmeth.2801},
volume = {11},
year = {2014}
}

@misc{Svensson2018,
abstract = {Measurement of the transcriptomes of single cells has been feasible for only a few years, but it has become an extremely popular assay. While many types of analysis can be carried out and various questions can be answered by single-cell RNA-seq, a central focus is the ability to survey the diversity of cell types in a sample. Unbiased and reproducible cataloging of gene expression patterns in distinct cell types requires large numbers of cells. Technological developments and protocol improvements have fueled consistent and exponential increases in the number of cells that can be studied in single-cell RNA-seq analyses. In this Perspective, we highlight the key technological developments that have enabled this growth in the data obtained from single-cell RNA-seq experiments.},
archivePrefix = {arXiv},
arxivId = {1704.01379},
author = {Svensson, Valentine and Vento-Tormo, Roser and Teichmann, Sarah A.},
booktitle = {Nature Protocols},
doi = {10.1038/nprot.2017.149},
eprint = {1704.01379},
issn = {17502799},
keywords = {Next,RNA sequencing,Transcriptomics,generation sequencing},
month = {mar},
number = {4},
pages = {599--604},
pmid = {29494575},
publisher = {Nature Publishing Group},
title = {{Exponential scaling of single-cell RNA-seq in the past decade}},
url = {https://www.nature.com/articles/nprot.2017.149},
volume = {13},
year = {2018}
}


@article{Macosko2015,
title = {Highly Parallel Genome-wide Expression Profiling of Individual Cells Using Nanoliter Droplets},
journal = {Cell},
volume = {161},
number = {5},
pages = {1202-1214},
year = {2015},
issn = {0092-8674},
doi = {https://doi.org/10.1016/j.cell.2015.05.002},
url = {https://www.sciencedirect.com/science/article/pii/S0092867415005498},
author = {Evan Z. Macosko and Anindita Basu and Rahul Satija and James Nemesh and Karthik Shekhar and Melissa Goldman and Itay Tirosh and Allison R. Bialas and Nolan Kamitaki and Emily M. Martersteck and John J. Trombetta and David A. Weitz and Joshua R. Sanes and Alex K. Shalek and Aviv Regev and Steven A. McCarroll},
abstract = {Summary
Cells, the basic units of biological structure and function, vary broadly in type and state. Single-cell genomics can characterize cell identity and function, but limitations of ease and scale have prevented its broad application. Here we describe Drop-seq, a strategy for quickly profiling thousands of individual cells by separating them into nanoliter-sized aqueous droplets, associating a different barcode with each cell’s RNAs, and sequencing them all together. Drop-seq analyzes mRNA transcripts from thousands of individual cells simultaneously while remembering transcripts’ cell of origin. We analyzed transcriptomes from 44,808 mouse retinal cells and identified 39 transcriptionally distinct cell populations, creating a molecular atlas of gene expression for known retinal cell classes and novel candidate cell subtypes. Drop-seq will accelerate biological discovery by enabling routine transcriptional profiling at single-cell resolution.
Video Abstract
}
}

@article{Zheng2017,
author = {Zheng, Grace and Terry, Jessica and Belgrader, Phillip and Ryvkin, Paul and Bent, Zachary and Wilson, Ryan and Ziraldo, Solongo and Wheeler, Tobias and Mcdermott, Geoffrey and Zhu, Junjie and Gregory, Mark and Shuga, Joe and Montesclaros, Luz and Underwood, Jason and Masquelier, Donald and Nishimura, Stefanie and Schnall-Levin, Michael and Wyatt, Paul and Hindson, Christopher and Bielas, Jason},
year = {2017},
month = {01},
pages = {14049},
title = {Massively parallel digital transcriptional profiling of single cells},
volume = {8},
journal = {Nature Communications},
doi = {10.1038/ncomms14049}
}

@article{Jaitin2014,
author = {Jaitin, Diego and Kenigsberg, Ephraim and Keren-Shaul, Hadas and Elefant, Naama and Paul, Franziska and Zaretsky, Irina and Mildner, Alexander and Cohen, Nadav and Jung, Steffen and Tanay, Amos and Amit, Ido},
year = {2014},
month = {02},
pages = {776-9},
title = {Massively Parallel Single-Cell RNA-Seq for Marker-Free Decomposition of Tissues into Cell Types},
volume = {343},
journal = {Science (New York, N.Y.)},
doi = {10.1126/science.1247651}
}


@misc{Anders2010,
abstract = {FastQC aims to provide a simple way to do some quality control checks on raw sequence data coming from high throughput sequencing pipelines. It provides a modular set of analyses which you can use to give a quick impression of whether your data has any problems of which you should be aware before doing any further analysis.},
author = {Anders, Simon},
booktitle = {Soil},
number = {1},
title = {{Babraham Bioinformatics - FastQC A Quality Control tool for High Throughput Sequence Data}},
url = {https://www.bioinformatics.babraham.ac.uk/projects/fastqc/},
urldate = {2021-12-31},
volume = {5},
year = {2010}
}


@article{Zhang2018,
author = {Zhang, Xiannian and Li, Tianqi and Liu, Feng and Chen, Yaqi and Yao, Jiacheng and Li, Zeyao and Huang, Yanyi and Wang, Jianbin},
year = {2018},
month = {11},
pages = {},
title = {Comparative Analysis of Droplet-Based Ultra-High-Throughput Single-Cell RNA-Seq Systems},
volume = {73},
journal = {Molecular Cell},
doi = {10.1016/j.molcel.2018.10.020}
}

@article{Dobin2013,
abstract = {Motivation: Accurate alignment of high-throughput RNA-seq data is a challenging and yet unsolved problem because of the non-contiguous transcript structure, relatively short read lengths and constantly increasing throughput of the sequencing technologies. Currently available RNA-seq aligners suffer from high mapping error rates, low mapping speed, read length limitation and mapping biases.Results: To align our large (>80 billon reads) ENCODE Transcriptome RNA-seq dataset, we developed the Spliced Transcripts Alignment to a Reference (STAR) software based on a previously undescribed RNA-seq alignment algorithm that uses sequential maximum mappable seed search in uncompressed suffix arrays followed by seed clustering and stitching procedure. STAR outperforms other aligners by a factor of >50 in mapping speed, aligning to the human genome 550 million 2 × 76 bp paired-end reads per hour on a modest 12-core server, while at the same time improving alignment sensitivity and precision. In addition to unbiased de novo detection of canonical junctions, STAR can discover non-canonical splices and chimeric (fusion) transcripts, and is also capable of mapping full-length RNA sequences. Using Roche 454 sequencing of reverse transcription polymerase chain reaction amplicons, we experimentally validated 1960 novel intergenic splice junctions with an 80-90% success rate, corroborating the high precision of the STAR mapping strategy. {\textcopyright} The Author(s) 2012. Published by Oxford University Press.},
author = {Dobin, Alexander and Davis, Carrie A. and Schlesinger, Felix and Drenkow, Jorg and Zaleski, Chris and Jha, Sonali and Batut, Philippe and Chaisson, Mark and Gingeras, Thomas R.},
doi = {10.1093/bioinformatics/bts635},
file = {:C\:/Users/ibgun/AppData/Local/Mendeley Ltd./Mendeley Desktop/Downloaded/Dobin et al. - 2013 - STAR ultrafast universal RNA-seq aligner.pdf:pdf},
issn = {13674803},
journal = {Bioinformatics},
keywords = {Alexander Dobin,Algorithms,Carrie A Davis,Cluster Analysis,Evaluation Study,Extramural,Gene Expression Profiling,Genome,Human,Humans,MEDLINE,N.I.H.,NCBI,NIH,NLM,National Center for Biotechnology Information,National Institutes of Health,National Library of Medicine,PMC3530905,PubMed Abstract,RNA / methods,RNA Splicing,Research Support,Sequence Alignment / methods*,Sequence Analysis,Software*,Thomas R Gingeras,doi:10.1093/bioinformatics/bts635,pmid:23104886},
month = {jan},
number = {1},
pages = {15--21},
pmid = {23104886},
publisher = {Bioinformatics},
title = {{STAR: Ultrafast universal RNA-seq aligner}},
url = {https://pubmed.ncbi.nlm.nih.gov/23104886/},
volume = {29},
year = {2013}
}


@misc{Piper2017,
author = {{Mistry, M. Freeman, B. Piper}, M.},
title = {{Alignment with STAR | Introduction to RNA-Seq using high-performance computing}},
url = {https://hbctraining.github.io/Intro-to-rnaseq-hpc-O2/lessons/03_alignment.html},
urldate = {2021-12-31},
year = {2017}
}

@article{Bray2016,
abstract = {We present kallisto, an RNA-seq quantification program that is two orders of magnitude faster than previous approaches and achieves similar accuracy. Kallisto pseudoaligns reads to a reference, producing a list of transcripts that are compatible with each read while avoiding alignment of individual bases. We use kallisto to analyze 30 million unaligned paired-end RNA-seq reads in <10 min on a standard laptop computer. This removes a major computational bottleneck in RNA-seq analysis.},
author = {Bray, Nicolas L. and Pimentel, Harold and Melsted, P{\'{a}}ll and Pachter, Lior},
doi = {10.1038/nbt.3519},
issn = {15461696},
journal = {Nature Biotechnology},
keywords = {Genome informatics,Software,Transcriptomics},
month = {apr},
number = {5},
pages = {525--527},
pmid = {27043002},
publisher = {Nature Publishing Group},
title = {{Near-optimal probabilistic RNA-seq quantification}},
url = {https://www.nature.com/articles/nbt.3519},
volume = {34},
year = {2016}
}

@incollection{Eding2009,
author = {Eding, Matt},
doi = {10.1201/9781439811481.ch20},
pages = {419--444},
title = {{Sparse Matrices}},
url = {https://matteding.github.io/2019/04/25/sparse-matrices/},
year = {2009}
}


@article{Hafemeister2019,
abstract = {Single-cell RNA-seq (scRNA-seq) data exhibits significant cell-to-cell variation due to technical factors, including the number of molecules detected in each cell, which can confound biological heterogeneity with technical effects. To address this, we present a modeling framework for the normalization and variance stabilization of molecular count data from scRNA-seq experiments. We propose that the Pearson residuals from "regularized negative binomial regression," where cellular sequencing depth is utilized as a covariate in a generalized linear model, successfully remove the influence of technical characteristics from downstream analyses while preserving biological heterogeneity. Importantly, we show that an unconstrained negative binomial model may overfit scRNA-seq data, and overcome this by pooling information across genes with similar abundances to obtain stable parameter estimates. Our procedure omits the need for heuristic steps including pseudocount addition or log-transformation and improves common downstream analytical tasks such as variable gene selection, dimensional reduction, and differential expression. Our approach can be applied to any UMI-based scRNA-seq dataset and is freely available as part of the R package sctransform, with a direct interface to our single-cell toolkit Seurat.},
author = {Hafemeister, Christoph and Satija, Rahul},
doi = {10.1186/S13059-019-1874-1/FIGURES/6},
issn = {1474760X},
journal = {Genome Biology},
keywords = {Normalization,Single-cell RNA-seq},
month = {dec},
number = {1},
pages = {1--15},
pmid = {31870423},
publisher = {BioMed Central Ltd.},
title = {{Normalization and variance stabilization of single-cell RNA-seq data using regularized negative binomial regression}},
url = {https://genomebiology.biomedcentral.com/articles/10.1186/s13059-019-1874-1},
volume = {20},
year = {2019}
}

@article{Stuart2019,
  author  = {Stuart, Tim and Butler, Andrew and Hoffman, Paul and Hafemeister, Christoph and Papalexi, Efthymia and Mauck III, William M and Hao, Yuhan and Stoeckius, Marlon and Smibert, Peter and Satija, Rahul},
  title   = {Comprehensive integration of single-cell data},
  journal = {Cell},
  volume  = {177},
  number  = {7},
  pages   = {1888--1902.e21},
  year    = {2019},
  doi     = {10.1016/j.cell.2019.05.031}
}

@article{Argelaguet2020,
  author  = {Argelaguet, Ricard and Arnol, Denis and Bredikhin, Dmitry and Deloro, Yann and Velten, Benedikt and Marioni, John C. and Stegle, Oliver},
  title   = {MOFA+: a statistical framework for comprehensive integration of multi-modal single-cell data},
  journal = {Genome Biology},
  volume  = {21},
  pages   = {111},
  year    = {2020},
  doi     = {10.1186/s13059-020-02015-1}
}

@article{Welch2019,
  author  = {Welch, Joshua D and Kozareva, Vanja and Ferreira, Arthur and Vanderburg, Caleb and Martin, Craig and Macosko, Evan Z},
  title   = {Single-Cell Multi-omic Integration Compares and Contrasts Features of Brain Cell Identity},
  journal = {Cell},
  volume  = {177},
  number  = {7},
  pages   = {1873--1887.e17},
  year    = {2019},
  doi     = {10.1016/j.cell.2019.05.006}
}

@article{Hao2021,
  author  = {Hao, Yuhan and Hao, Stephanie and Andersen-Nissen, Erin and Mauck III, William M and Zheng, Shiwei and Butler, Andrew and Lee, Madison J and Wilk, Aaron J and Darby, Charlotte and Zager, Melissa and others},
  title   = {Integrated analysis of multimodal single-cell data},
  journal = {Cell},
  volume  = {184},
  number  = {13},
  pages   = {3573--3587.e29},
  year    = {2021},
  doi     = {10.1016/j.cell.2021.04.048}
}

@article{Hao2022,
  author  = {Hao, Yuhan and Hao, Stephanie and Andersen-Nissen, Erin and others},
  title   = {Bridge integration of single-cell multi-omics data with dictionary learning},
  journal = {bioRxiv},
  year    = {2022},
  doi     = {10.1101/2022.02.24.481684}
}

@article{Ashuach2021,
  author  = {Ashuach, Tal and Gabitto, Mariano and Jordan, Michael I and Yosef, Nir},
  title   = {MultiVI: deep generative model for the integration of multi-modal data},
  journal = {bioRxiv},
  year    = {2021},
  doi     = {10.1101/2021.08.20.457057}
}

@article{Kang2018,
  author  = {Kang, Hyun Min and Subramaniam, Manasa and Targ, Sheila and Nguyen, Mai and Maliskova, Lenka and McCarthy, Erin and Wan, Emily and Wong, Siaw W and Byrnes, Laura and Lanata, Cristina M and Gate, David and Mostafavi, Sara and Marson, Alexander and Zaitlen, Noah and Criswell, Lindsey A and Ye, Cheng and Pritchard, Jonathan K},
  title   = {Multiplexed droplet single-cell RNA-sequencing using natural genetic variation},
  journal = {Nature Biotechnology},
  volume  = {36},
  number  = {1},
  pages   = {89--94},
  year    = {2018},
  doi     = {10.1038/nbt.4042}
}

@article{McGinnis2019,
  author  = {McGinnis, Christopher S and Murrow, Lauren M and Gartner, Zev J},
  title   = {DoubletFinder: Doublet Detection in Single-Cell RNA Sequencing Data Using Artificial Nearest Neighbors},
  journal = {Cell Systems},
  volume  = {8},
  number  = {4},
  pages   = {329--337.e4},
  year    = {2019},
  doi     = {10.1016/j.cels.2019.03.003}
}

@article{Wolock2019,
  author  = {Wolock, Samuel L and Lopez, Ramon and Klein, Allon M},
  title   = {Scrublet: computational identification of cell doublets in single-cell transcriptomic data},
  journal = {Cell Systems},
  volume  = {8},
  number  = {4},
  pages   = {281--291.e9},
  year    = {2019},
  doi     = {10.1016/j.cels.2018.11.005}
}

@article{Kharchenko2014,
  author  = {Kharchenko, Peter V and Silberstein, Lev and Scadden, David T},
  title   = {Bayesian approach to single-cell differential expression analysis},
  journal = {Nature Methods},
  volume  = {11},
  pages   = {740--742},
  year    = {2014},
  doi     = {10.1038/nmeth.2967}
}