Crick-2023 - Speaker Deck

Slide 1

Slide 1 text

@lcolladotor lcolladotor.github.io lcolladotor.github.io/bioc_team_ds Lessons from working on the edge of human brain transcriptomics with spatially-resolved transcriptomics and deconvolution Leonardo Collado Torres, Investigator The Francis Crick Institute May 23 2023 Slides available at speakerdeck.com/lcolladotor

Slide 2

Slide 2 text

doi.org/10.1016/j.biopsych.2020.06.005 Michael Gandal @mikejg84 Transcriptomic Insight Into the Polygenic Mechanisms Underlying Psychiatric Disorders

Slide 3

Slide 3 text

Background: Human DLPFC 3 slideshare.net Louise A Huuki-Myers @lahuuki

Slide 4

Slide 4 text

doi.org/10.1186/s12859-021-04142-3 Nicholas J Eagles @Nick-Eagles (GitHub) Upcoming LIBD Data portal built on top of SPEAQeasy & PopTop & BiocMAP

Slide 5

Slide 5 text

https://twitter.com/lcolladotor/status/1506998412809412612 Keri Martinowich @martinowk

Slide 6

Slide 6 text

Zoom in: snRNA-seq → deconvolution of bulk RNA-seq Matthew N Tran @mattntran Kristen R Maynard @kr_maynard Louise A Huuki-Myers @lahuuki Keri Martinowich @martinowk Stephanie C Hicks @stephaniehicks

Slide 7

Slide 7 text

What is Deconvolution? ● Inferring the composition of different cell types in a bulk RNA-seq data Louise A Huuki-Myers @lahuuki

Slide 8

Slide 8 text

Interaction eQTLs with cell type proportions github.com/LieberInstitute/goesHyde_mdd_rnaseq/tree/master/eqtl/code

Slide 9

Slide 9 text

Reference Single Cell Data 9 deconvolution(Y, Z) = Proportion of Cell Types Louise A Huuki-Myers @lahuuki

Slide 10

Slide 10 text

10x snRNA-seq Reference Data Tran, Maynard et al., Neuron, 2021 AMY DLPFC HPC NAc sACC Astro 1638 782 1170 1099 907 Endo 31 0 0 0 0 Macro 0 10 0 22 0 Micro 1168 388 1126 492 784 Mural 39 18 43 0 0 Oligo 6080 5455 5912 6134 4584 OPC 1459 572 838 669 911 Tcell 31 9 26 0 0 Excit 443 2388 623 0 4163 Inhib 3117 1580 366 11476 3974 @mattntran Matthew N Tran

Slide 11

Slide 11 text

Marker Finding 11 deconvolution(Y, Z) = Proportion of Cell Types Louise A Huuki-Myers @lahuuki

Slide 12

Slide 12 text

1vAll Markers vs. Mean Ratio Markers 12 Louise A Huuki-Myers @lahuuki research.libd.org/DeconvoBuddies/

Slide 13

Slide 13 text

1vAll Markers vs. Mean Ratio Markers 13 Louise A Huuki-Myers @lahuuki research.libd.org/DeconvoBuddies/

Slide 14

Slide 14 text

Methods 14 deconvolution(Y, Z) = Proportion of Cell Types Louise A Huuki-Myers @lahuuki

Slide 15

Slide 15 text

Method Summary Method Regression Correction for Technical Variation Other Features MuSiC Wang et al, Nature Communications, 2019 W-NNLS regression (Weighted - Non-negative least squares) None Tree guided deconvolution, good for closely related cell types Bisque Jew et al, Nature Communications, 2020 NNLS regresion Gene specific transformation of bulk data Leverage overlapping bulk & sc data SCDC Dong et al, Briefings in Bioinformatics, 2020 W-NNLS framework proposed by MuSiC Option for Gene specific transformation of bulk data (from Bisque) Multiple reference datasets can be used, results combined with ENSEMBL weights DWLS Tsoucas, Nature Communications, 2019 Dampened Weighted least squares None 15

Slide 16

Slide 16 text

Method Regression Method Run Time Marker Evaluation Adjust for snRNA-seq vs. Bulk Tissues Tested Consider Cell Size Reference Set MuSiC W-NNLS Min. Internal Weighting No Pancreatic Islet, Rat & Mouse Kidney Yes Bisque NNLS Min. No Yes Adipose, DLPFC Recommend 3+ donors SCDC W-NNLS Min. Internal Weighting Yes Pancreatic Islet, mouse mammary Can input multiple references DWLS DWLS Hours Internal Selection No Mouse kidney, lung, liver, small intestine 16

Slide 17

Slide 17 text

Which Method is the Most Accurate? ● Benchmarking shows that different methods perform best on different data sets (Cobos et al, Nature Communications, 2020) ● Benchmarking results from different papers on “real” data ○ MuSiC paper: MuSiC > NNLS > BSEQ-sx > CIBERSORT ■ Pancreatic Islet: Beta cells vs. HbA1c (Fig 2a) ○ Bisque paper: Bisque > MuSiC > CIBERSORT ■ DLPFC: Microglia vs. Braak stage, Neuron vs. Cognitive diagnostic category (Fig 4) ○ SCDC paper: SCDC > MuSiC > Bisque > DWLS > CIBERSORT ■ Pancreatic Islet: Beta cells vs. HbA1c (Fig 4b) ○ Cobos benchmark: DWLS > MuSiC > Bisque > deconvoSeq ■ Human PMBC ﬂow sorted (Fig 7) 17 Louise A Huuki-Myers @lahuuki

Slide 18

Slide 18 text

Results + Validation 18 deconvolution(Y, Z) = Proportion of Cell Types Louise A Huuki-Myers @lahuuki

Slide 19

Slide 19 text

Mean Proportions By Region: Tran et al, bioRxiv, 2020 (5 donors, 6 cell types) Louise A Huuki-Myers @lahuuki

Slide 20

Slide 20 text

Peric = Mural + Endo Mean Proportions By Region: Tran et al, Neuron, 2021 (8 donors, 10 cell types) Louise A Huuki-Myers @lahuuki

Slide 21

Slide 21 text

● Run with set of 20 & 25 marker genes per cell type ● Bisque is more robust to changes in the marker set than MuSiC Method Sensitivity to Marker Set 25 vs. 20 Genes Louise A Huuki-Myers @lahuuki

Slide 22

Slide 22 text

Sean Maden @MadenSean Sang Ho Kwon @sanghokwon17 #deconvochallenge doi.org/10.48550/arXiv.2305.06501

Slide 23

Slide 23 text

#deconvochallenge Challenges and opportunities to computationally deconvolve heterogeneous tissue with varying cell sizes using single cell RNA-sequencing datasets doi.org/10.48550/arXiv.2305.06501 Sean Maden @MadenSean

Slide 24

Slide 24 text

Sean Maden @MadenSean Sang Ho Kwon @sanghokwon17 #deconvochallenge doi.org/10.48550/arXiv.2305.06501

Slide 25

Slide 25 text

Motivation ● Improve Deconvolution algorithms by considering differences in size and RNA content between cell types ● Use smFISH with RNAscope to establish data set of: ○ Cellular composition ○ Nuclei sizes of major cell types ○ Average nuclei RNA content of major cell types How do we measure total RNA content of a cell if we can only observe a few genes at a time? Use a TREG Data-driven Identiﬁcation of Total RNA Expression Genes (TREGs) for Estimation of RNA Abundance in Heterogeneous Cell Types research.libd.org/TREG/ doi.org/10.1101/2022.04.28.489923 Louise A Huuki-Myers @lahuuki #TREG

Slide 26

Slide 26 text

What is a TREG? ● Total RNA Expression Gene ● Expression is proportional to the overall RNA expression in a nucleus ● In smFISH the count of TREG puncta in a nucleus can estimate the RNA content Data-driven Identiﬁcation of Total RNA Expression Genes (TREGs) for Estimation of RNA Abundance in Heterogeneous Cell Types research.libd.org/TREG/ doi.org/10.1101/2022.04.28.489923 #TREG

Slide 27

Slide 27 text

Validate with RNAscope ● DLPFC from control, sectioned at 10μm ● 3 slides with 3 sections each ○ TREG candidate + cell type marker genes ● Images analyzed with HALO TREG Gene AKT3 ARID1B MALAT1/ POLR2A Cell Type Markers GAD1, SLC17A7, MBP GAD1, SLC17A7, MBP SLC17A7, MBP Cell Type Marker Excit SLC17A7 Inhib GAD1 Oligo MBP Kelsey D Montgomery Sang Ho Kwon research.libd.org/TREG/ doi.org/10.1101/2022.04.28.489923

Slide 28

Slide 28 text

Patterns of Observed Puncta ● TREGs were expressed in most cells ● AKT3 tracks really well with pattern of expression seen in snRNA-seq (ARID1B is also pretty good) snRNA-seq RNAscope Gene Mean Prop. Cells with Expression Prop. non-zero in DLPFC snRNA Standardized β (95% CI) AKT3 0.948 0.92 -1.38 (-1.39,-1.37) ARID1B 0.908 0.94 -0.62 (-0.62,-0.61) MALAT1 0.910 1.00 -0.11 (-0.12,-0.11) POLR2A 0.853 0.30 -0.98 (-0.99,-0.98) snRNA-seq NA NA -1.33 (-1.35,-1.31) Remember: MALAT1’s puncta data is unreliable research.libd.org/TREG/ doi.org/10.1101/2022.04.28.489923

Slide 29

Slide 29 text

research.libd.org/TREG/ doi.org/10.1101/2022.04.28.489923 Louise A Huuki-Myers @lahuuki

Slide 30

Slide 30 text

Slide 31

Slide 31 text

Sean Maden @MadenSean #deconvochallenge doi.org/10.48550/arXiv.2305.06501

Slide 32

Slide 32 text

Zoom in: spatial omics Kristen R Maynard @kr_maynard Keri Martinowich @martinowk Stephanie C Hicks @stephaniehicks Andrew E Jaffe @andrewejaffe Stephanie C Page @CerceoPage

Slide 33

Slide 33 text

Visium Platform for Spatial Gene Expression Image from 10x Genomics - A slide contains 4 capture areas, each full of thousands of 55um-wide “spots” (often containing 1-10 cells) - Unique barcodes in each spot bind to particular genes; after sequencing, gene expression can be tied back to exact spots, forming a spatial map Kristen R. Maynard 33

Slide 34

Slide 34 text

bioconductor.org/packages/spatialLIBD Pardo et al, 2022 DOI 10.1186/s12864-022-08601-w Maynard, Collado-Torres, 2021 DOI 10.1038/s41593-020-00787-0 Brenda Pardo Abby Spangler @PardoBree @abspangler Louise A. Huuki-Myers @lahuuki

Slide 35

Slide 35 text

2 pairs spatial adjacent replicates x subject = 12 sections 35 Subject 1 Subject 2 Subject 3 Adjacent spatial replicates (0μm) Adjacent spatial replicates (300μm) PCP4 Maynard, Collado-Torres, et al, Nat Neuro, 2021

Slide 36

Slide 36 text

“Pseudo-bulking” collapses data: spot to layer level 36 Maynard, Collado-Torres, et al, Nat Neuro, 2021

Slide 37

Slide 37 text

DOI: 10.1038/s41593-020-00787-0 twitter.com/lcolladotor/status/1233661576433061888 from 2020-02-29 Andrew E Jaffe @andrewejaffe Kristen R Maynard @kr_maynard Keri Martinowich @martinowk

Slide 38

Slide 38 text

DOI: 10.1038/s41593-020-00787-0 twitter.com/lcolladotor/status/1233661576433061888 from 2020-02-29 DOI 10.1093/bioinformatics/btac299 Since Feb 2020 spatialLIBD::fetch_data() provides access to SpatialExperiment R/Bioconductor objects Stephanie C Hicks @stephaniehicks Lukas M Weber @lmweber

Slide 39

Slide 39 text

DOI: 10.1038/s41593-020-00787-0 twitter.com/lcolladotor/status/1233661576433061888 from 2020-02-29 twitter.com/CrowellHL/status/1597579271945715717 DOI 10.1093/bioinformatics/btac299 Since Feb 2020 spatialLIBD::fetch_data() provides access to SpatialExperiment R/Bioconductor objects

Slide 40

Slide 40 text

#spatialDLPFC 40 doi.org/10.1101/2023.02.15.528722 Louise A Huuki-Myers @lahuuki Abby Spangler @abspangler Nicholas J Eagles @Nick-Eagles (GitHub)

Slide 41

Slide 41 text

BayesSpace clustering with batch correction worked best for multiple samples 41 doi.org/10.1101/2023.02.15.528722 twitter.com/CrowellHL/status/1597579271945715717

Slide 42

Slide 42 text

Different Resolutions of BayesSpace Clustering k = number of clusters ● k=2: separate white vs. grey matter ● k=9: best reiterated histological layers ● k=16: data-driven optimal k based on fast H+ statistic 42 More Clusters = More Complexity doi.org/10.1101/2023.02.15.528722

Slide 43

Slide 43 text

Spatial Registration Adds Anatomical Context ● Validate detection of laminar structure ● Correlate enrichment t-statistics for top marker genes of reference ○ Cluster vs. manual annotation ● Annotate with strongly associated histological layer 43 Sp k D d ~L doi.org/10.1101/2023.02.15.528722

Slide 44

Slide 44 text

Spatial Registration of Spatial Domains ● Map SpDs to Maynard et al. manual annotated layers ● Highlight most strongly associated histological layer to add biological context 44 doi.org/10.1101/2023.02.15.528722

Slide 45

Slide 45 text

Identify Layer Associated Neuron Populations 45 ● Apply Spatial Registration with manual layers ● 13 layer-level cell types ○ Assign Excitatory Neurons histological layers ○ Pool other cell type groups Kelsey D Montgomery

Slide 46

Slide 46 text

Layer-level Cell Type Marker genes 46 Louise A Huuki-Myers @lahuuki

Slide 47

Slide 47 text

Spot Deconvolution 47 Cell 1 Cell 2 … Cell N Gene 1 0 0 … 0 Gene 2 2 5 … 3 … … … … … Gene i 1 0 … 0 Spot 1 Spot 2 … Spot M Gene 1 1 0 … 3 Gene 2 0 1 … 0 … … … … … Gene j 4 2 … 2 Astro Excit … Inhib Spot 1 1 1 … 1 Spot 2 … … … … … … Spot N 1 0 … 2 Single- Nucleus Spatial Deconvolved Results Spot 1 Nicholas J Eagles @Nick-Eagles (GitHub)

Slide 48

Slide 48 text

Existing Spot Deconvolution Software - Explored 3 novel software methods from the literature Software name Overall approach Input Cell Counts Output Tangram (Biancalani et al.) Mapping individual cells Every spot Integer counts Cell2location (Kleshchevnikov et al.) Matching gene-expression profile Average across spots Decimal counts SPOTlight (Elosua-Bayes et al.) Matching gene-expression profile Not used Proportions 48 Excit L5 Counts

Slide 49

Slide 49 text

Benchmarking Spot Deconvolution Software: Theory - How do we measure performance or accuracy of cell-type predictions? - Make orthogonal measurements*: image-derived counts - Leverage prior knowledge: neurons localize to gray matter? - Self-consistency of results: broad vs. ﬁne cell-type results 49 Nicholas J Eagles @Nick-Eagles (GitHub) doi.org/10.1101/2023.02.15.528722

Slide 50

Slide 50 text

Visium Spatial Proteogenomics (SPG) Images as an Orthogonal Measurement 50

Slide 51

Slide 51 text

Visium Spatial Proteogenomics (Visium-SPG) Visium-SPG = Visium SRT + immunofluorescence (using identical tissue samples) Sang Ho Kwon @sanghokwon17

Slide 52

Slide 52 text

Visium-SPG for Paired Imaging and Gene Expression - Channels measure proteins marking for broad cell types: microglia, neurons, oligodendrocytes, and astrocytes Kristen R. Maynard doi.org/10.1101/2023.02.15.528722

Slide 53

Slide 53 text

Using IF to Quantify Cell Types - Visium-SPG IF images mark for several proteins - Fluorescence in image channels correlates with counts of measured cell types Can measure 5 distinct cell types: 53 ● Astrocyte (GFAP) ● Neuron (NeuN) ● Oligodendrocyte (OLIG2) ● Microglia (TMEM119) ● Other (low signal in all channels) doi.org/10.1101/2023.01.28.525943 Sriworarat, 2023. samuibrowser.com Sang Ho Kwon @sanghokwon17

Slide 54

Slide 54 text

Segmenting Cells on Visium-SPG IF Images 1. Segment cells on IF image 2. Manually label N cells 3. Train cell-type classiﬁer and apply on remaining data Sriworarat, 2023. samuibrowser.com 54 Nicholas J Eagles @Nick-Eagles (GitHub) doi.org/10.1101/2023.01.28.525943

Slide 55

Slide 55 text

Constructing Dataset of Labeled Cells 1. Segment cells on IF image 2. Manually label example cells 3. Train cell-type classiﬁer and apply on remaining data Image Channels Classified Cell Type Cell Mask 55 Annie B. Nguyen

Slide 56

Slide 56 text

Constructing Dataset of Labeled Cells 56 1. Segment cells on IF image 2. Manually label N cells 3. Train cell-type classiﬁer and apply on remaining data Annie B. Nguyen 4 sections * 5 cell types * 30 cells = 600 manually labeled cells doi.org/10.1101/2023.01.28.525943 Sriworarat, 2023. samuibrowser.com

Slide 57

Slide 57 text

Addressing Bias in Cell Selection - Trained logistic regression model on 600-cell dataset - Broke cells into 4 quartiles based on model conﬁdence - Labelled 320 more cells, evenly sampled from all 4 quartiles 57 Cell Type Probability Astro 0.2 Oligo 0.3 Micro 0.1 Neuron 0.45 Other 0.05 4 quartiles * 4 sections * 5 cell types * 4 cells = 320 new cells total 600 old cells + 320 new cells = 920 labeled cells Nicholas J Eagles @Nick-Eagles (GitHub)

Slide 58

Slide 58 text

Training Cell-Type Classiﬁer 58 Model Test Precision Test Recall Decision tree 0.86 0.87 Dataset # Training # Test Split Old 600 480 120 80/20 New 320 240 80 75/25 Combined 920 720 200 ~78/22 1. Segment cells on IF image 2. Manually label N cells 3. Train cell-type classiﬁer and apply on remaining data Grid search with 5-fold CV for each model to select hyperparameters Data Model Final model chosen

Slide 59

Slide 59 text

Benchmark Results: Make Orthogonal Measurements 59 Micro (Br6522_Ant_IF) All points in A -> one point in B

Slide 60

Slide 60 text

Layer-level: collapse Excit_L* into 1 for broad-level 60 Then combine Excitatory and Inhibitory into Neurons to compare vs CART-calculated counts from Visium_SPG

Slide 61

Slide 61 text

Benchmark Results: Make Orthogonal Measurements 61 Broad cell type level Layer level (Excit by layer)

Slide 62

Slide 62 text

Benchmark Results: Leverage Prior Knowledge - Manually annotate spots with histological layer - Explore how cell-type predictions map to annotated layers Kristen R. Maynard A B C

Slide 63

Slide 63 text

Benchmark Results: Self-Consistency of Results Counts from software results using both broad and layer-level cell types were compared, by “collapsing” onto just 4 major cell types. We expect results perfectly on the diagonal! 63

Slide 64

Slide 64 text

Viewing Spot Deconvolution Results: Samui Browser - View: - Fluorescence channels - Spot deconvo results - Segmented cells - Gene expression - Interactive - Quickly zoom/scroll - Full-resolution images samuibrowser.com/from?url=data2.loopybrowser.com/VisiumIF/&s=Br2720_Ant_IF&s=Br6432_Ant_IF&s=Br6522_Ant_IF&s=Br8667_Post_IF Sriworarat, 2023. 64

Slide 65

Slide 65 text

Viewing Spot Deconvolution Results: spatialLIBD apps - View: - spot deconvolution results - spatial domains/ clusters - gene expression - Huge amount of aesthetic customization 65 https://libd.shinyapps.io/spatialDLPFC_Visium_SPG/

Slide 66

Slide 66 text

How Spot Deconvolution Results Were Used A. Better characterize unsupervised spatial domains B. Cell-cell communication; cell-type-informed ligand-receptor interactions in the context of schizophrenia risk A 66 Boyi Guo Melissa Grant-Peters

Slide 67

Slide 67 text

Visium spatial clustering works for variables with high % variance explained. But what about other ones? DOI: 10.1038/s41593-020-00787-0

Slide 68

Slide 68 text

twitter.com/sanghokwon17/status/1650589385379962881 from 2023-04-24 Sang Ho Kwon @sanghokwon17 DOI: 10.1101/2023.04.20.537710 #Visium_SPG_AD

Slide 69

Slide 69 text

Experimental design & study overview Braak V-VI & CERAD frequent Sang Ho Kwon

Slide 70

Slide 70 text

AD pathology signal is too small to detect by spatially-resolved gene expression alone research.libd.org/Visium_SPG_AD/

Slide 71

Slide 71 text

Identifying transcriptional signatures of AD-related neuropathology Sang Ho Kwon

Slide 72

Slide 72 text

Some challenges ⚠ with Visium 72

Slide 73

Slide 73 text

sc/snRNA-seq QC metrics such as # detected genes, # UMI, mitochondria expression % are likely biologically related!

Slide 74

Slide 74 text

Prashanthi Ravichandran @prashanthi-ravichandran (GH) Artifacts in general are normalized away by library size, though there are caveats

Slide 75

Slide 75 text

Diffusion issues: could be related to permeabilization step

Slide 76

Slide 76 text

Having more data is useful to provide context! Here 4 new samples have low sequencing saturation (outliers) but are within range of good samples from other studies

Slide 77

Slide 77 text

Having more data is useful to provide context! Those 4 samples have great median UMI counts per spot ^_^

Slide 78

Slide 78 text

Software keeps evolving and as leaders in the field we aim to use the best methods 78 Moses, L., Pachter, L. Museum of spatial transcriptomics. Nat Methods 19, 534–546 (2022). https://doi.org/10.1038/s41592-022-01409-2

Slide 79

Slide 79 text

The Development Process - Making a module - New, experimental software can change dramatically (function and syntax) between versions - Promotes collaboration by allowing two researchers to share exact code and instantly run software without special set-up SpatialExperiment release 3.14 SpatialExperiment devel 3.15 module load tangram/1.0.2 module load cell2location/0.8a0 module load spagcn/1.2.0 https://github.com/LieberInstitute/jhpce_mod_source https://github.com/LieberInstitute/jhpce_module_conﬁg Nicholas J Eagles @Nick-Eagles (GitHub)

Slide 80

Slide 80 text

The Development Process - Regular interaction with software authors to clarify functionality and report bugs - Documentation for code and author responsiveness on GitHub can be critical in successfully applying software to our data Nicholas J Eagles @Nick-Eagles (GitHub)

Slide 81

Slide 81 text

Documentation + wrapper functions + tests (GitHub Actions + Bioconductor) 81 bioconductor.org/packages/spatialLIBD

Slide 82

Slide 82 text

More challenges ahead Working with multiple capture areas per tissue Nicholas J Eagles @Nick-Eagles (GitHub) Prashanthi Ravichandran @prashanthi-ravichandran (GH) Spot diameter error: ~1.8 → ~1.1 Another pair: ~2.8 → ~0.76

Slide 83

Slide 83 text

lcolladotor.github.io/#projects ● Every assay has caveats ● We re-use tricks: think adding 0, multiplying by 1 ● It nearly always takes a team ● Data sharing accelerates science + democratizes access to it ● Zooming in allows us to reduce the heterogeneity ● We can learn from each other: from uniformly processing our data & re-using it → replicate / validate?

Slide 84

Slide 84 text

jhpce.jhu.edu/knowledge-base/knowledge-base-articles-from-lieber-institute/ research.libd.org/rstatsclub/ Join us Fridays at 9 AM (check the code of conduct please!)

Slide 85

Slide 85 text

www.youtube.com/@lcolladotor/playlists Videos allow us to multiply ourselves We can make you custom selections of videos for a speciﬁc problem on DSgs sessions

Slide 86

Slide 86 text

20 chapters and counting! lcolladotor.github.io/bioc_team_ds

Slide 87

Slide 87 text

Melissa Grant-Peters @mgrantpeters Endorsed by your UCL colleague:

Slide 88

Slide 88 text

lcolladotor.github.io/pkgs lcolladotor.github.io/biocthis

Slide 89

Slide 89 text

@MadhaviTippani Madhavi Tippani @HeenaDivecha Heena R Divecha @lmwebr Lukas M Weber @stephaniehicks Stephanie C Hicks @abspangler Abby Spangler @martinowk Keri Martinowich @CerceoPage Stephanie C Page @kr_maynard Kristen R Maynard @lcolladotor Leonardo Collado-Torres @Nick-Eagles (GH) Nicholas J Eagles Kelsey D Montgomery Sang Ho Kwon Image Analysis Expression Analysis Data Generation Thomas M Hyde @lahuuki Louise A Huuki-Myers @BoyiGuo Boyi Guo @mattntran Matthew N Tran @sowmyapartybun Sowmya Parthiban Slides available at speakerdeck.com /lcolladotor + Many more LIBD, JHU, and external collaborators @mgrantpeters Melissa Grant-Peters @prashanthi-ravichandran (GH) Prashanthi Ravichandran