references.bib

@article{Danaher2022,
	author = {Danaher, Patrick and Zhao, Edward and Yang, Zhi and Ross, David and Gregory, Mark and Reitz, Zach and Kim, Tae K. and Baxter, Sarah and Jackson, Shaun and He, Shanshan and Henderson, Dave and Beechem, Joseph M.},
	title = {Insitutype: likelihood-based cell typing for single cell spatial transcriptomics},
	elocation-id = {2022.10.19.512902},
	year = {2022},
	doi = {10.1101/2022.10.19.512902},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Accurate cell typing is fundamental to analysis of spatial single-cell transcriptomics, but legacy scRNA-seq algorithms can underperform in this new type of data. We have developed a cell typing algorithm, Insitutype, designed for statistical and computational efficiency in spatial transcriptomics data.Insitutype is based on a likelihood model that weighs the evidence from every expression value, extracting all the information available in each cell{\textquoteright}s expression profile. This likelihood model underlies a Bayes classifier for supervised cell typing, and an Expectation-Maximization algorithm for unsupervised and semi-supervised clustering. Insitutype also leverages alternative data types collected in spatial studies, such as cell images and spatial context, by using them to inform prior probabilities of cell type calls. We demonstrate rapid clustering of millions of cells and accurate fine-grained cell typing of kidney and non-small cell lung cancer samples.Competing Interest StatementPD, EZ, ZY, DR, MG, ZR, TKK, SH, DH and JMB are current/former employees and shareholders of NanoString.},
	URL = {https://www.biorxiv.org/content/early/2022/10/21/2022.10.19.512902},
	eprint = {https://www.biorxiv.org/content/early/2022/10/21/2022.10.19.512902.full.pdf},
	journal = {bioRxiv}
}
@article{Lause2021,
   author = {Jan Lause and Philipp Berens and Dmitry Kobak},
   doi = {10.1186/s13059-021-02451-7},
   issn = {1474-760X},
   issue = {1},
   journal = {Genome Biology},
   month = {9},
   pages = {258},
   title = {Analytic Pearson residuals for normalization of single-cell RNA-seq UMI data},
   volume = {22},
   year = {2021},
}
@article{He2022,
   abstract = {Resolving the spatial distribution of RNA and protein in tissues at subcellular resolution is a challenge in the field of spatial biology. We describe spatial molecular imaging, a system that measures RNAs and proteins in intact biological samples at subcellular resolution by performing multiple cycles of nucleic acid hybridization of fluorescent molecular barcodes. We demonstrate that spatial molecular imaging has high sensitivity (one or two copies per cell) and very low error rate (0.0092 false calls per cell) and background (~0.04 counts per cell). The imaging system generates three-dimensional, super-resolution localization of analytes at ~2 million cells per sample. Cell segmentation is morphology based using antibodies, compatible with formalin-fixed, paraffin-embedded samples. We measured multiomic data (980 RNAs and 108 proteins) at subcellular resolution in formalin-fixed, paraffin-embedded tissues (nonsmall cell lung and breast cancer) and identified >18 distinct cell types, ten unique tumor microenvironments and 100 pairwise ligand-receptor interactions. Data on >800,000 single cells and ~260 million transcripts can be accessed at http://nanostring.com/CosMx-dataset .},
   author = {Shanshan He and Ruchir Bhatt and Carl Brown and Emily A Brown and Derek L Buhr and Kan Chantranuvatana and Patrick Danaher and Dwayne Dunaway and Ryan G Garrison and Gary Geiss and Mark T Gregory and Margaret L Hoang and Rustem Khafizov and Emily E Killingbeck and Dae Kim and Tae Kyung Kim and Youngmi Kim and Andrew Klock and Mithra Korukonda and Alecksandr Kutchma and Zachary R Lewis and Yan Liang and Jeffrey S Nelson and Giang T Ong and Evan P Perillo and Joseph C Phan and Tien Phan-Everson and Erin Piazza and Tushar Rane and Zachary Reitz and Michael Rhodes and Alyssa Rosenbloom and David Ross and Hiromi Sato and Aster W Wardhani and Corey A Williams-Wietzikoski and Lidan Wu and Joseph M Beechem},
   doi = {10.1038/s41587-022-01483-z},
   issn = {1546-1696},
   issue = {12},
   journal = {Nature biotechnology},
   month = {12},
   pages = {1794-1806},
   pmid = {36203011},
   title = {High-plex imaging of RNA and proteins at subcellular resolution in fixed tissue by spatial molecular imaging.},
   volume = {40},
   year = {2022},
}
@article{Palla2022,
   abstract = {Spatial omics data are advancing the study of tissue organization and cellular communication at an unprecedented scale. Flexible tools are required to store, integrate and visualize the large diversity of spatial omics data. Here, we present Squidpy, a Python framework that brings together tools from omics and image analysis to enable scalable description of spatial molecular data, such as transcriptome or multivariate proteins. Squidpy provides efficient infrastructure and numerous analysis methods that allow to efficiently store, manipulate and interactively visualize spatial omics data. Squidpy is extensible and can be interfaced with a variety of already existing libraries for the scalable analysis of spatial omics data.},
   author = {Giovanni Palla and Hannah Spitzer and Michal Klein and David Fischer and Anna Christina Schaar and Louis Benedikt Kuemmerle and Sergei Rybakov and Ignacio L. Ibarra and Olle Holmberg and Isaac Virshup and Mohammad Lotfollahi and Sabrina Richter and Fabian J. Theis},
   doi = {10.1038/s41592-021-01358-2},
   issn = {1548-7091},
   issue = {2},
   journal = {Nature Methods},
   month = {2},
   pages = {171-178},
   title = {Squidpy: a scalable framework for spatial omics analysis},
   volume = {19},
   year = {2022},
}
@article{Hao2024,
   author = {Yuhan Hao and Tim Stuart and Madeline H. Kowalski and Saket Choudhary and Paul Hoffman and Austin Hartman and Avi Srivastava and Gesmira Molla and Shaista Madad and Carlos Fernandez-Granda and Rahul Satija},
   doi = {10.1038/s41587-023-01767-y},
   issn = {1087-0156},
   issue = {2},
   journal = {Nature Biotechnology},
   month = {2},
   pages = {293-304},
   title = {Dictionary learning for integrative, multimodal and scalable single-cell analysis},
   volume = {42},
   year = {2024},
}
@article{Dries2021,
   abstract = {Spatial transcriptomic and proteomic technologies have provided new opportunities to investigate cells in their native microenvironment. Here we present Giotto, a comprehensive and open-source toolbox for spatial data analysis and visualization. The analysis module provides end-to-end analysis by implementing a wide range of algorithms for characterizing tissue composition, spatial expression patterns, and cellular interactions. Furthermore, single-cell RNAseq data can be integrated for spatial cell-type enrichment analysis. The visualization module allows users to interactively visualize analysis outputs and imaging features. To demonstrate its general applicability, we apply Giotto to a wide range of datasets encompassing diverse technologies and platforms.},
   author = {Ruben Dries and Qian Zhu and Rui Dong and Chee-Huat Linus Eng and Huipeng Li and Kan Liu and Yuntian Fu and Tianxiao Zhao and Arpan Sarkar and Feng Bao and Rani E. George and Nico Pierson and Long Cai and Guo-Cheng Yuan},
   doi = {10.1186/s13059-021-02286-2},
   issn = {1474-760X},
   issue = {1},
   journal = {Genome Biology},
   month = {12},
   pages = {78},
   title = {Giotto: a toolbox for integrative analysis and visualization of spatial expression data},
   volume = {22},
   year = {2021},
}
@article{Wolf2018,
   abstract = {Scanpy is a scalable toolkit for analyzing single-cell gene expression data. It includes methods for preprocessing, visualization, clustering, pseudotime and trajectory inference, differential expression testing, and simulation of gene regulatory networks. Its Python-based implementation efficiently deals with data sets of more than one million cells (https://github.com/theislab/Scanpy). Along with Scanpy, we present AnnData, a generic class for handling annotated data matrices (https://github.com/theislab/anndata).},
   author = {F Alexander Wolf and Philipp Angerer and Fabian J Theis},
   doi = {10.1186/s13059-017-1382-0},
   issn = {1474-760X},
   issue = {1},
   journal = {Genome Biology},
   pages = {15},
   title = {SCANPY: large-scale single-cell gene expression data analysis},
   volume = {19},
   url = {https://doi.org/10.1186/s13059-017-1382-0},
   year = {2018},
}
@article{Tian2021,
   abstract = {Mitochondria, independent double-membrane organelles, are intracellular power plants that feed most eukaryotic cells with the ATP produced via the oxidative phosphorylation (OXPHOS). Consistently, cytochrome c oxidase (COX) catalyzes the electron transfer chain's final step. Electrons are transferred from reduced cytochrome c to molecular oxygen and play an indispensable role in oxidative phosphorylation of cells. Cytochrome c oxidase subunit 6c (COX6C) is encoded by the nuclear genome in the ribosome after translation and is transported to mitochondria via different pathways, and eventually forms the COX complex. In recent years, many studies have shown the abnormal level of COX6C in familial hypercholesterolemia, chronic kidney disease, diabetes, breast cancer, prostate cancer, uterine leiomyoma, follicular thyroid cancer, melanoma tissues, and other conditions. Its underlying mechanism may be related to the cellular oxidative phosphorylation pathway in tissue injury disease. Here reviews the varied function of COX6C in non-tumor and tumor diseases.},
   author = {Bi-Xia Tian and Wei Sun and Shu-Hong Wang and Pei-Jun Liu and Yao-Chun Wang},
   issn = {1943-8141},
   issue = {1},
   journal = {American journal of translational research},
   pages = {1-10},
   pmid = {33527004},
   title = {Differential expression and clinical significance of COX6C in human diseases.},
   volume = {13},
   year = {2021},
}
@article{Fu2024,
   abstract = {Recent advances in subcellular imaging transcriptomics platforms have enabled high-resolution spatial mapping of gene expression, while also introducing significant analytical challenges in accurately identifying cells and assigning transcripts. Existing methods grapple with cell segmentation, frequently leading to fragmented cells or oversized cells that capture contaminated expression. To this end, we present BIDCell, a self-supervised deep learning-based framework with biologically-informed loss functions that learn relationships between spatially resolved gene expression and cell morphology. BIDCell incorporates cell-type data, including single-cell transcriptomics data from public repositories, with cell morphology information. Using a comprehensive evaluation framework consisting of metrics in five complementary categories for cell segmentation performance, we demonstrate that BIDCell outperforms other state-of-the-art methods according to many metrics across a variety of tissue types and technology platforms. Our findings underscore the potential of BIDCell to significantly enhance single-cell spatial expression analyses, enabling great potential in biological discovery.},
   author = {Xiaohang Fu and Yingxin Lin and David M. Lin and Daniel Mechtersheimer and Chuhan Wang and Farhan Ameen and Shila Ghazanfar and Ellis Patrick and Jinman Kim and Jean Y. H. Yang},
   doi = {10.1038/s41467-023-44560-w},
   issn = {2041-1723},
   issue = {1},
   journal = {Nature Communications},
   month = {1},
   pages = {509},
   title = {BIDCell: Biologically-informed self-supervised learning for segmentation of subcellular spatial transcriptomics data},
   volume = {15},
   year = {2024},
}
@article {Maher2023,
	author = {Maher, Kamal and Wu, Morgan and Zhou, Yiming and Huang, Jiahao and Zhang, Qiangge and Wang, Xiao},
	title = {Mitigating autocorrelation during spatially resolved transcriptomics data analysis},
	elocation-id = {2023.06.30.547258},
	year = {2023},
	doi = {10.1101/2023.06.30.547258},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Several computational methods have recently been developed for characterizing molecular tissue regions in spatially resolved transcriptomics (SRT) data. However, each method fundamentally relies on spatially smoothing transcriptomic features across neighboring cells. Here, we demonstrate that smoothing increases autocorrelation between neighboring cells, causing latent space to encode physical adjacency rather than spatial transcriptomic patterns. We find that randomly sub-sampling neighbors before smoothing mitigates autocorrelation, improving the performance of existing methods and further enabling a simpler, more efficient approach that we call spatial integration (SPIN). SPIN leverages the conventional single-cell toolkit, yielding spatial analogies to each tool: clustering identifies molecular tissue regions; differentially expressed gene analysis calculates region marker genes; trajectory inference reveals continuous, molecularly defined ana tomical axes; and integration allows joint analysis across multiple SRT datasets, regardless of tissue morphology, spatial resolution, or experimental technology. We apply SPIN to SRT datasets from mouse and marmoset brains to calculate shared and species-specific region marker genes as well as a molecularly defined neocortical depth axis along which several genes and cell types differ across species.Competing Interest StatementThe authors have declared no competing interest.},
	URL = {https://www.biorxiv.org/content/early/2023/07/02/2023.06.30.547258},
	eprint = {https://www.biorxiv.org/content/early/2023/07/02/2023.06.30.547258.full.pdf},
	journal = {bioRxiv}
}
@article {Wu2024,
	author = {Wu, Lidan and Beechem, Joseph M and Danaher, Patrick},
	title = {FastReseg: using transcript locations to refine image-based cell segmentation results in spatial transcriptomics},
	elocation-id = {2024.12.05.627051},
	year = {2024},
	doi = {10.1101/2024.12.05.627051},
	publisher = {Cold Spring Harbor Laboratory},
	abstract = {Spatial transcriptomics (ST) is a rapidly advancing field, yet it is challenged by persistent issues with cell segmentation accuracy, which can bias biological interpretations by making cells appear more similar to their neighbors than they truly are. FastReseg introduces a novel class of algorithm that employs transcriptomic data not to redefine cell boundaries but to rectify inaccuracies within existing image-based segmentation outputs. By combining the rich information from image-based methods with the 3D precision of transcriptomic analysis, FastReseg enhances cell segmentation accuracy. A key innovation of FastReseg approach is its transcript scoring system, which scores each transcript for its goodness-of-fit within host cell using log-likelihood ratio. This scoring system facilitates the quick identification and correction of spatial doublets, i.e. cells erroneously segmented due to close proximity or spatial overlap in 2D. FastReseg approach offers several advantages: it reduces the risks of circularity in deriving cell boundaries from expression data and minimizes spatial-dependent biases arising from erroneous segmentation. It also addresses computational challenges often associated with existing transcript-based methods by introducing a heuristic, modular workflow that efficiently processes large datasets, a critical feature given the increasing size of spatial transcriptomics datasets. Its modular workflow allows for individual components to be optimized and seamlessly integrated back into the overall pipeline, accommodating ongoing advancements in segmentation technology. By enabling efficient management of large datasets and providing a scalable solution for refining cell segmentation, FastReseg is poised to enhance the quality and interpretability of spatial transcriptomics data even as underlying image-based cell segmentation techniques evolve.},
	URL = {http://biorxiv.org/content/early/2024/12/10/2024.12.05.627051},
	eprint = {https://www.biorxiv.org/content/10.1101/2024.12.05.627051v1.full.pdf},
	journal = {bioRxiv}
}