Development and homeostasis in multicellular systems require exquisite control over spatial molecular pattern formation and maintenance. Advances in spatially resolved and high-throughput molecular imaging methods such as multiplexed immunofluorescence and spatial transcriptomics (ST) provide exciting new opportunities to augment our fundamental understanding of these processes in health and disease. The large and complex datasets from these techniques, particularly ST, have led to the rapid development of innovative machine learning (ML) tools in this domain. These tools are now increasingly featured in integrated experimental and computational workflows to disentangle signals from noise in complex biological systems. Method development for spatial biology data analysis draws on diverse subfields and perspectives, and it can be challenging to understand the primary computational considerations of ML in ST. To address this, we highlight some ST analysis goals that ML can help address. We also describe four major data science concepts and related heuristics that can help practitioners choose the right tools for the right biological questions.
Get full access to this article
View all access options for this article.
References
1.
ChenKH, BoettigerAN, MoffittJR, et al.Spatially resolved, highly multiplexed RNA profiling in single cells. Science, 2015; 348(6233):aaa6090; doi: 10.1126/science.aaa6090
2.
FeminoAM, FayFS, FogartyK, et al.Visualization of single RNA transcripts in Situ. Science, 1998; 280(5363):585–590; doi: 10.1126/science.280.5363.585
3.
RajA, van den BogaardP, RifkinSA, et al.Imaging individual mRNA molecules using multiple singly labeled probes. Nat Methods, 2008; 5(10):877–879; doi: 10.1038/nmeth.1253
ZollingerDR, LingleSE, SorgK, et al.GeoMxTM RNA Assay: High multiplex, digital, spatial analysis of RNA in FFPE tissue. In: In Situ Hybridization Protocols. (NielsenBS, JonesJ eds) Springer. US: New York, NY; 2020; pp. 331–345; doi: 10.1007/978-1-0716-0623-0_21
6.
LeeY, BogdanoffD, WangY, et al.XYZeq: Spatially resolved single-cell RNA sequencing reveals expression heterogeneity in the tumor microenvironment. Sci Adv, 2021; 7(17); doi: 10.1126/sciadv.abg4755
7.
TianL, ChenF, MacoskoEZ. The expanding vistas of spatial transcriptomics. Nat Biotechnol, 2022; 41(6):773–782; doi: 10.1038/s41587-022-01448-2
8.
MarxV. Method of the year: Spatially resolved transcriptomics. Nat Methods, 2021; 18(1):9–14; doi: 10.1038/s41592-020-01033-y
9.
AngermuellerC, PärnamaaT, PartsL, et al.Deep learning for computational biology. Mol Syst Biol, 2016; 12(7):878; doi: 10.15252/msb.20156651
10.
MahmudM, KaiserMS, HussainA, et al.Applications of deep learning and reinforcement learning to biological data. IEEE Trans Neural Netw Learn Syst, 2018; 29(6):2063–2079; doi: 10.1109/TNNLS.2018.2790388
11.
MahmudM, KaiserMS, McGinnityTM, et al.Deep learning in mining biological data. Cognit Comput, 2021; 13(1):1–33; doi: 10.1007/s12559-020-09773-x
12.
JumperJ, EvansR, PritzelA, et al.Highly accurate protein structure prediction with AlphaFold. Nature, 2021; 596(7873):583–589; doi: 10.1038/s41586-021-03819-2
13.
AffonsoC, RossiALD, VieiraFHA, et al.Deep learning for biological image classification. Expert Systems with Applications, 2017; 85:114–122; doi: 10.1016/j.eswa.2017.05.039
14.
MoenE, BannonD, KudoT, et al.Deep learning for cellular image analysis. Nat Methods, 2019; 16(12):1233–1246; doi: 10.1038/s41592-019-0403-1
15.
CamachoDM, CollinsKM, PowersRK, et al.Next-generation machine learning for biological networks. Cell, 2018; 173(7):1581–1592; doi: 10.1016/j.cell.2018.05.015
16.
JinS, ZengX, XiaF, et al.Application of deep learning methods in biological networks. Brief Bioinform, 2021; 22(2):1902–1917; doi: 10.1093/bib/bbaa043
17.
MuzioG, O’BrayL, BorgwardtK. Biological network analysis with deep learning. Brief Bioinform, 2021; 22(2):1515–1530; doi: 10.1093/bib/bbaa257
18.
YuB, KumbierK. Veridical data science. Proc Natl Acad Sci USA, 2020; 117(8):3920–3929.
19.
MurdochWJ, SinghC, KumbierK, et al.Definitions, methods, and applications in interpretable machine learning. Proc Natl Acad Sci USA, 2019; 116(44):22071–22080.
20.
ZengZ, LiY, LiY, et al.Statistical and machine learning methods for spatially resolved transcriptomics data analysis. Genome Biol, 2022; 23(1):83; doi: 10.1186/s13059-022-02653-7
21.
PallaG, FischerDS, RegevA, et al.Spatial components of molecular tissue biology. Nat Biotechnol, 2022; 40(3):308–318; doi: 10.1038/s41587-021-01182-1
22.
MosesL, PachterL. Museum of spatial transcriptomics. Nat Methods, 2022; 19(5):534–546; doi: 10.1038/s41592-022-01409-2
23.
DuJ, YangY-C, AnZ-J, et al.Advances in spatial transcriptomics and related data analysis strategies. J Transl Med, 2023; 21(1):330; doi: 10.1186/s12967-023-04150-2
24.
AlexandrovT, Saez‐RodriguezJ, SakaSK. Enablers and challenges of spatial omics, a melting pot of technologies. Mol Syst Biol, 2023; 19(11):e10571; doi: 10.15252/msb.202110571
25.
BiancalaniT, ScaliaG, BuffoniL, et al.Deep learning and alignment of spatially resolved single-cell transcriptomes with Tangram. Nat Methods, 2021; 18(11):1352–1362; doi: 10.1038/s41592-021-01264-7
26.
Elosua-BayesM, NietoP, MereuE, et al.SPOTlight: Seeded NMF regression to deconvolute spatial transcriptomics spots with single-cell transcriptomes. Nucleic Acids Res, 2021; 49(9):e50; doi: 10.1093/nar/gkab043
27.
KleshchevnikovV, ShmatkoA, DannE, et al.Cell2location maps fine-grained cell types in spatial transcriptomics. Nat Biotechnol, 2022; 40(5):661–671; doi: 10.1038/s41587-021-01139-4
28.
CableDM, MurrayE, ZouLS, et al.Robust decomposition of cell type mixtures in spatial transcriptomics. Nat Biotechnol, 2022; 40(4):517–526; doi: 10.1038/s41587-021-00830-w
29.
BrbićM, CaoK, HickeyJW, et al.Annotation of spatially resolved single-cell data with STELLAR. Nat Methods, 2022; 19(11):1411–1418; doi: 10.1038/s41592-022-01651-8
30.
CangZ, ZhaoY, AlmetAA, et al.Screening cell–cell communication in spatial transcriptomics via collective optimal transport. Nat Methods, 2023; 20(2):218–228; doi: 10.1038/s41592-022-01728-4
31.
BrowaeysR, SaelensW, SaeysY. NicheNet: Modeling intercellular communication by linking ligands to target genes. Nat Methods, 2020; 17(2):159–162; doi: 10.1038/s41592-019-0667-5
32.
EfremovaM, Vento-TormoM, TeichmannSA, et al.CellPhoneDB: Inferring cell–cell communication from combined expression of multi-subunit ligand–receptor complexes. Nat Protoc, 2020; 15(4):1484–1506; doi: 10.1038/s41596-020-0292-x
33.
PhamD, TanX, BaldersonB, et al.Robust mapping of spatiotemporal trajectories and cell–cell interactions in healthy and diseased tissues. Nat Commun, 2023; 14(1):7739; doi: 10.1038/s41467-023-43120-6
34.
FischerDS, SchaarAC, TheisFJ. Modeling intercellular communication in tissues using spatial graphs of cells. Nat Biotechnol, 2023; 41(3):332–336; doi: 10.1038/s41587-022-01467-z
35.
BuggenthinF, BuettnerF, HoppePS, et al.Prospective identification of hematopoietic lineage choice by deep learning. Nat Methods, 2017; 14(4):403–406; doi: 10.1038/nmeth.4182
SatijaR, FarrellJA, GennertD, et al.Spatial reconstruction of single-cell gene expression data. Nat Biotechnol, 2015; 33(5):495–502; doi: 10.1038/nbt.3192
40.
DriesR, ZhuQ, DongR, et al.Giotto: A toolbox for integrative analysis and visualization of spatial expression data. Genome Biol, 2021; 22(1):78; doi: 10.1186/s13059-021-02286-2
41.
HuJ, LiX, ColemanK, et al.SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network. Nat Methods, 2021; 18(11):1342–1351; doi: 10.1038/s41592-021-01255-8
42.
LeeAJ, YaoS, LuskN, et al.Data-driven fine-grained region discovery in the mouse brain with transformers. BioRxiv, 2024.
43.
AzodiCB, TangJ, ShiuS-H. Opening the black box: Interpretable machine learning for geneticists. Trends in Genetics, 2020; 36(6):442–455; doi: 10.1016/j.tig.2020.03.005
44.
TanevskiJ, FloresROR, GaborA, et al.Explainable multiview framework for dissecting spatial relationships from highly multiplexed data. Genome Biol, 2022; 23(1):97; doi: 10.1186/s13059-022-02663-5
45.
ChangY, HeF, WangJ, et al.Define and visualize pathological architectures of human tissues from spatially resolved transcriptomics using deep learning. Comput Struct Biotechnol J, 2022; 20:4600–4617; doi: 10.1016/j.csbj.2022.08.029
46.
ChidesterB, ZhouT, AlamS, et al.SpiceMix enables integrative single-cell spatial modeling of cell identity. Nat Genet, 2023; 55(1):78–88; doi: 10.1038/s41588-022-01256-z
47.
CahillR, WangY, LeeA, et al.Unsupervised pattern discovery in spatial gene expression atlas reveals mouse brain regions beyond established ontology. bioRxiv, 2023; 2023(03.10.531984); doi: 10.1101/2023.03.10.531984
48.
WuS, JosephA, HammondsAS, et al.Stability-driven nonnegative matrix factorization to interpret spatial gene expression and build local gene networks. Proc Natl Acad Sci USA, 2016; 113(16):4290–4295.
49.
Abbasi-AslR, YuB. Interpreting convolutional neural networks through compression. In NIPS Symposium on Interpretable Machine Learning 2017.
50.
Abbasi-AslR, YuB. Structural compression of convolutional neural networks with applications in interpretability. Front Big Data, 2021; 4:704182.
PetukhovV, XuRJ, SoldatovRA, et al.Cell segmentation in imaging-based spatial transcriptomics. Nat Biotechnol, 2022; 40(3):345–354; doi: 10.1038/s41587-021-01044-w
53.
Abbasi-AslR, ChenY, BloniarzA, et al.The DeepTune framework for modeling and characterizing neurons in visual cortex area V4. bioRxiv, 2018; 465534
54.
BasuS, KumbierK, BrownJB, et al.Iterative random forests to discover predictive and stable high-order interactions. Proc Natl Acad Sci USA, 2018; 115(8):1943–1948; doi: 10.1073/pnas.1711236115
55.
ShenR, LiuL, WuZ, et al.Spatial-ID: A cell typing method for spatially resolved transcriptomics via transfer learning and spatial embedding. Nat Commun, 2022; 13(1):7640; doi: 10.1038/s41467-022-35288-0
56.
ZhangK, FengW, WangP. Identification of spatially variable genes with graph cuts. Nat Commun, 2022; 13(1):5488; doi: 10.1038/s41467-022-33182-3
57.
YaoZ, Van VelthovenCTJ, KunstM, et al.A high-resolution transcriptomic and spatial atlas of cell types in the whole mouse brain. Nature, 2023; 624(7991):317–332; doi: 10.1038/s41586-023-06812-z
58.
TibshiraniR. Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B (Methodological), 1996; 58(1):267–288.
59.
BouchardK, BujanA, RoostaF, et al.Union of intersections (UoI) for interpretable data driven discovery and prediction. In: Advances in Neural Information Processing Systems. (GuyonI, LuxburgUV, BengioS eds) Curran Associates, Glasgow; 2017.
