Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning.
Uloženo v:
| Název: | Accurate single-molecule spot detection for image-based spatial transcriptomics with weakly supervised deep learning. |
|---|---|
| Autoři: | Laubscher E; Division of Chemistry and Chemical Engineering, Caltech, Pasadena, CA 91125, USA., Wang X; Division of Biology and Biological Engineering, Caltech, Pasadena, CA 91125, USA., Razin N; Division of Biology and Biological Engineering, Caltech, Pasadena, CA 91125, USA., Dougherty T; Division of Biology and Biological Engineering, Caltech, Pasadena, CA 91125, USA., Xu RJ; Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA 02115, USA; Department of Microbiology, Blavatnik Institute, Harvard Medical School, Boston, MA 02115, USA; Department of Chemistry and Chemical Biology, Harvard University, Cambridge, MA 02115, USA., Ombelets L; Division of Chemistry and Chemical Engineering, Caltech, Pasadena, CA 91125, USA., Pao E; Division of Biology and Biological Engineering, Caltech, Pasadena, CA 91125, USA., Graf W; Division of Biology and Biological Engineering, Caltech, Pasadena, CA 91125, USA., Moffitt JR; Program in Cellular and Molecular Medicine, Boston Children's Hospital, Boston, MA 02115, USA; Department of Microbiology, Blavatnik Institute, Harvard Medical School, Boston, MA 02115, USA; Broad Institute of Harvard and MIT, Cambridge, MA, USA., Yue Y; Division of Computational and Mathematical Sciences, Caltech, Pasadena, CA 91125, USA., Van Valen D; Division of Biology and Biological Engineering, Caltech, Pasadena, CA 91125, USA; Howard Hughes Medical Institute, Chevy Chase, MD 20815, USA. Electronic address: vanvalen@caltech.edu. |
| Zdroj: | Cell systems [Cell Syst] 2024 May 15; Vol. 15 (5), pp. 475-482.e6. |
| Způsob vydávání: | Journal Article |
| Jazyk: | English |
| Informace o časopise: | Publisher: Cell Press Country of Publication: United States NLM ID: 101656080 Publication Model: Print Cited Medium: Internet ISSN: 2405-4720 (Electronic) Linking ISSN: 24054712 NLM ISO Abbreviation: Cell Syst Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: [Cambridge, MA] : Cell Press, [2015]- |
| Výrazy ze slovníku MeSH: | In Situ Hybridization, Fluorescence*/methods , Transcriptome*/genetics , Gene Expression Profiling*/methods , Deep Learning*, Single-Cell Analysis/methods ; Image Processing, Computer-Assisted/methods ; Single Molecule Imaging/methods ; Software ; Humans ; Animals ; Supervised Machine Learning |
| Abstrakt: | Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep-learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from multiplexed error-robust FISH (MERFISH), sequential fluorescence in situ hybridization (seqFISH), or in situ RNA sequencing (ISS) experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org. (Copyright © 2024. Published by Elsevier Inc.) |
| Competing Interests: | Declaration of interests D.V.V. is a co-founder of Barrier Biosciences and holds equity in the company. D.V.V., E.L., and N.R. filed a patent for weakly supervised deep learning for spot detection. J.R.M. is co-founder and scientific advisor to Vizgen and holds equity in the company. J.R.M. is an inventor of patents related to MERFISH filed on his behalf by Harvard University and Boston Children’s Hospital. |
| Komentáře: | Update of: bioRxiv. 2024 Feb 05:2023.09.03.556122. doi: 10.1101/2023.09.03.556122.. (PMID: 37732188) |
| References: | Science. 2016 Jul 1;353(6294):78-82. (PMID: 27365449) Biophys J. 2002 May;82(5):2775-83. (PMID: 11964263) Genome Biol. 2022 May 18;23(1):118. (PMID: 35585605) Med Image Anal. 2021 May;70:102019. (PMID: 33730623) Nat Biotechnol. 2022 Mar;40(3):345-354. (PMID: 34650268) Nat Methods. 2019 Oct;16(10):987-990. (PMID: 31501547) Science. 2015 Apr 24;348(6233):aaa6090. (PMID: 25858977) Science. 2019 Mar 29;363(6434):1463-1467. (PMID: 30923225) Nucleic Acids Res. 2021 Jul 21;49(13):7292-7297. (PMID: 34197605) IEEE Trans Med Imaging. 2010 Feb;29(2):282-301. (PMID: 19556194) VLDB J. 2020;29(2):709-730. (PMID: 32214778) Proc Natl Acad Sci U S A. 2016 Sep 27;113(39):11046-51. (PMID: 27625426) Bioessays. 2020 Oct;42(10):e1900221. (PMID: 32363691) BMC Bioinformatics. 2010 May 13;11:248. (PMID: 20465797) Nat Methods. 2022 Feb;19(2):171-178. (PMID: 35102346) Life Sci Alliance. 2022 Dec 16;6(1):. (PMID: 36526371) Proc Natl Acad Sci U S A. 2018 Mar 6;115(10):E2183-E2192. (PMID: 29463736) Nat Methods. 2018 Nov;15(11):932-935. (PMID: 30377364) PeerJ. 2014 Jun 19;2:e453. (PMID: 25024921) PLoS Comput Biol. 2016 Nov 4;12(11):e1005177. (PMID: 27814364) Nat Methods. 2020 Jul;17(7):689-693. (PMID: 32541852) Nat Methods. 2011 Feb;8(2):165-70. (PMID: 21240280) Nat Methods. 2022 Dec;19(12):1634-1641. (PMID: 36344832) Nat Methods. 2013 Sep;10(9):857-60. (PMID: 23852452) Cell. 2020 Dec 23;183(7):1930-1945.e23. (PMID: 33188777) Cold Spring Harb Symp Quant Biol. 2017;82:57-70. (PMID: 29183987) Cell. 2019 Oct 17;179(3):787-799.e17. (PMID: 31626775) Nat Biotechnol. 2022 Apr;40(4):555-565. (PMID: 34795433) Nat Biotechnol. 2021 Mar;39(3):313-319. (PMID: 33288904) Nat Methods. 2021 Jan;18(1):100-106. (PMID: 33318659) Nature. 2019 Apr;568(7751):235-239. (PMID: 30911168) Cell Genom. 2023 Aug 21;3(9):100384. (PMID: 37719153) Signal Transduct Target Ther. 2022 Apr 1;7(1):111. (PMID: 35365599) Nat Biotechnol. 2015 May;33(5):495-502. (PMID: 25867923) |
| Grant Information: | DP2 GM149556 United States GM NIGMS NIH HHS |
| Contributed Indexing: | Keywords: deep learning; image analysis; spatial transcriptomics; spot detection |
| Entry Date(s): | Date Created: 20240516 Date Completed: 20240516 Latest Revision: 20250516 |
| Update Code: | 20260130 |
| PubMed Central ID: | PMC11995858 |
| DOI: | 10.1016/j.cels.2024.04.006 |
| PMID: | 38754367 |
| Databáze: | MEDLINE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstrakt: | Image-based spatial transcriptomics methods enable transcriptome-scale gene expression measurements with spatial information but require complex, manually tuned analysis pipelines. We present Polaris, an analysis pipeline for image-based spatial transcriptomics that combines deep-learning models for cell segmentation and spot detection with a probabilistic gene decoder to quantify single-cell gene expression accurately. Polaris offers a unifying, turnkey solution for analyzing spatial transcriptomics data from multiplexed error-robust FISH (MERFISH), sequential fluorescence in situ hybridization (seqFISH), or in situ RNA sequencing (ISS) experiments. Polaris is available through the DeepCell software library (https://github.com/vanvalenlab/deepcell-spots) and https://www.deepcell.org.<br /> (Copyright © 2024. Published by Elsevier Inc.) |
|---|---|
| ISSN: | 2405-4720 |
| DOI: | 10.1016/j.cels.2024.04.006 |