KODAMA

workflowr

• Summary
• Checks
• Past versions

Last updated: 2025-04-13

Checks: 2 0

Knit directory: KODAMA-Analysis/

This reproducible R Markdown analysis was created with workflowr (version 1.7.1). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.

---

R Markdown file: up-to-date

Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.

Repository version: 5f5ac63

Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility.

The results in this page were generated with repository version 5f5ac63. See the Past versions tab to see a history of the changes made to the R Markdown and HTML files.

Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated:

Ignored files:
    Ignored:    .RData
    Ignored:    .Rhistory
    Ignored:    .Rproj.user/

Untracked files:
    Untracked:  KODAMA.svg
    Untracked:  analysis/singlecell_datamatrix.Rmd
    Untracked:  analysis/singlecell_seurat.Rmd
    Untracked:  code/Acinar_Cell_Carcinoma.ipynb
    Untracked:  code/Adenocarcinoma.ipynb
    Untracked:  code/Adjacent_normal_section.ipynb
    Untracked:  code/DLFPC_preprocessing.R
    Untracked:  code/DLPFC - BANKSY.R
    Untracked:  code/DLPFC - BASS.R
    Untracked:  code/DLPFC - BAYESPACE.R
    Untracked:  code/DLPFC - Nonspatial.R
    Untracked:  code/DLPFC - PRECAST.R
    Untracked:  code/DLPFC_comparison.R
    Untracked:  code/DLPFC_results_analysis.R
    Untracked:  code/MERFISH - BANKSY.R
    Untracked:  code/MERFISH - BASS.R
    Untracked:  code/MERFISH - BAYESPACE.R
    Untracked:  code/MERFISH - Nonspatial.R
    Untracked:  code/MERFISH - PRECAST.R
    Untracked:  code/MERFISH_comparison.R
    Untracked:  code/MERFISH_results_analysis.R
    Untracked:  code/VisiumHD-CRC.ipynb
    Untracked:  code/VisiumHDassignment.py
    Untracked:  code/deep learning code DLPFC.R
    Untracked:  code/save tiles.py
    Untracked:  data/Adenocarcinoma.csv
    Untracked:  data/Annotations/
    Untracked:  data/DLFPC-Br5292-input.RData
    Untracked:  data/DLFPC-Br5595-input.RData
    Untracked:  data/DLFPC-Br8100-input.RData
    Untracked:  data/DLPFC-general.RData
    Untracked:  data/MERFISH-input.RData
    Untracked:  data/spots_classification_ALL.csv
    Untracked:  data/spots_classification_Acinar_Cell_Carcinoma.csv
    Untracked:  data/spots_classification_IF.csv
    Untracked:  data/spots_classification_Normal_prostate.csv
    Untracked:  data/trajectories.RData
    Untracked:  data/trajectories_VISIUMHD.RData
    Untracked:  output/BANSKY-results.RData
    Untracked:  output/BASS-results.RData
    Untracked:  output/BayesSpace-results.RData
    Untracked:  output/CRC-image.RData
    Untracked:  output/CRC-image2.RData
    Untracked:  output/CRC.png
    Untracked:  output/CRC2.png
    Untracked:  output/CRC7.png
    Untracked:  output/CRC8.png
    Untracked:  output/CRC_boxplot.png
    Untracked:  output/CRC_boxplot.svg
    Untracked:  output/CRC_boxplot2.svg
    Untracked:  output/CRC_linee.svg
    Untracked:  output/DL.RData
    Untracked:  output/DLFPC-All-2.RData
    Untracked:  output/DLFPC-All.RData
    Untracked:  output/DLFPC-Br5292.RData
    Untracked:  output/DLFPC-Br5595.RData
    Untracked:  output/DLFPC-Br8100.RData
    Untracked:  output/DLFPC-variablesXdeeplearning.RData
    Untracked:  output/DLPFC-BANSKY-results.RData
    Untracked:  output/DLPFC-BASS-results.RData
    Untracked:  output/DLPFC-BayesSpace-results.RData
    Untracked:  output/DLPFC-Nonspatial-results.RData
    Untracked:  output/DLPFC-PRECAST-results.RData
    Untracked:  output/DLPFC_all_cluster.svg
    Untracked:  output/DLPFCpathway.RData
    Untracked:  output/Figure 1 - boxplot.pdf
    Untracked:  output/Figure 2 - DLPFC 10.pdf
    Untracked:  output/Figures/
    Untracked:  output/KODAMA-results.RData
    Untracked:  output/KODAMA_DLPFC_All_original.svg
    Untracked:  output/KODAMA_DLPFC_Br5595.svg
    Untracked:  output/KODAMA_DLPFC_Br5595_slide.svg
    Untracked:  output/Loupe.csv
    Untracked:  output/MERFISH-BANSKY-results.RData
    Untracked:  output/MERFISH-BASS-results.RData
    Untracked:  output/MERFISH-BayesSpace-results.RData
    Untracked:  output/MERFISH-KODAMA-results.RData
    Untracked:  output/MERFISH-Nonspatial-results.RData
    Untracked:  output/MERFISH-PRECAST-results.RData
    Untracked:  output/MERFISH.RData
    Untracked:  output/Nonspatial-results.RData
    Untracked:  output/Prostate.RData
    Untracked:  output/VisiumHD-RNA.RData
    Untracked:  output/VisiumHD-genes.pdf
    Untracked:  output/VisiumHD.RData
    Untracked:  output/boh.svg
    Untracked:  output/desmoplastic_distance_carcinoma.csv
    Untracked:  output/image.RData
    Untracked:  output/pp.RData
    Untracked:  output/pp2.RData
    Untracked:  output/pp3.RData
    Untracked:  output/pp4.RData
    Untracked:  output/pp5.RData
    Untracked:  output/prostate1.svg
    Untracked:  output/prostate2.svg
    Untracked:  output/prostate3.svg
    Untracked:  output/prostate4.svg
    Untracked:  output/prostate5.svg
    Untracked:  output/prostate6.svg
    Untracked:  output/prostate7.svg
    Untracked:  output/subclusters1.csv
    Untracked:  output/subclusters2.csv
    Untracked:  output/subclusters3.csv
    Untracked:  output/tight_boundary.geojson
    Untracked:  output/trajectory.csv

Unstaged changes:
    Deleted:    analysis/D1.Rmd
    Deleted:    analysis/DLPFC-12.Rmd
    Deleted:    analysis/DLPFC-4.Rmd
    Modified:   analysis/DLPFC.Rmd
    Deleted:    analysis/DLPFC1.Rmd
    Deleted:    analysis/DLPFC10.Rmd
    Deleted:    analysis/DLPFC2.Rmd
    Deleted:    analysis/DLPFC3.Rmd
    Deleted:    analysis/DLPFC4.Rmd
    Deleted:    analysis/DLPFC5.Rmd
    Deleted:    analysis/DLPFC6.Rmd
    Deleted:    analysis/DLPFC7.Rmd
    Deleted:    analysis/DLPFC8.Rmd
    Deleted:    analysis/DLPFC9.Rmd
    Deleted:    analysis/Du1.Rmd
    Deleted:    analysis/Du10.Rmd
    Deleted:    analysis/Du11.Rmd
    Deleted:    analysis/Du12.Rmd
    Deleted:    analysis/Du13.Rmd
    Deleted:    analysis/Du14.Rmd
    Deleted:    analysis/Du15.Rmd
    Deleted:    analysis/Du16.Rmd
    Deleted:    analysis/Du17.Rmd
    Deleted:    analysis/Du18.Rmd
    Deleted:    analysis/Du19.Rmd
    Deleted:    analysis/Du2.Rmd
    Deleted:    analysis/Du20.Rmd
    Deleted:    analysis/Du3.Rmd
    Deleted:    analysis/Du4.Rmd
    Deleted:    analysis/Du5.Rmd
    Deleted:    analysis/Du6.Rmd
    Deleted:    analysis/Du7.Rmd
    Deleted:    analysis/Du8.Rmd
    Deleted:    analysis/Du9.Rmd
    Modified:   analysis/Giotto.Rmd
    Modified:   analysis/MERFISH.Rmd
    Deleted:    analysis/MERFISH1a (copy).Rmd
    Deleted:    analysis/MERFISH1a.Rmd
    Deleted:    analysis/MERFISH1b (copy).Rmd
    Deleted:    analysis/MERFISH1b.Rmd
    Deleted:    analysis/MERFISH2a (copy).Rmd
    Deleted:    analysis/MERFISH2a.Rmd
    Deleted:    analysis/MERFISH2b (copy).Rmd
    Deleted:    analysis/MERFISH2b.Rmd
    Deleted:    analysis/MERFISH3a (copy).Rmd
    Deleted:    analysis/MERFISH3a.Rmd
    Deleted:    analysis/MERFISH3b (copy).Rmd
    Deleted:    analysis/MERFISH3b.Rmd
    Deleted:    analysis/MERFISH4a (copy).Rmd
    Deleted:    analysis/MERFISH4a.Rmd
    Deleted:    analysis/MERFISH4b (copy).Rmd
    Deleted:    analysis/MERFISH4b.Rmd
    Modified:   analysis/Prostate.Rmd
    Deleted:    analysis/STARmap.Rmd
    Modified:   analysis/Seurat.Rmd
    Deleted:    analysis/Simulation.Rmd
    Deleted:    analysis/Single-cell.Rmd
    Modified:   analysis/SpatialExperiment.Rmd
    Modified:   analysis/VisiumHD.Rmd
    Modified:   code/VisiumHD_CRC_download.sh
    Deleted:    data/Pathology.csv

Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.

---

These are the previous versions of the repository in which changes were made to the R Markdown (analysis/index.Rmd) and HTML (docs/index.html) files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view the files as they were in that past version.

File	Version	Author	Date	Message
html	d1192e9	Stefano Cacciatore	2024-08-12	Build site.
html	3374e66	Stefano Cacciatore	2024-08-06	Build site.
html	35ce733	Stefano Cacciatore	2024-08-03	Build site.
html	82fe167	Stefano Cacciatore	2024-07-24	Build site.
Rmd	494b863	Stefano Cacciatore	2024-07-20	Start workflowr project.
html	6f7daac	Stefano Cacciatore	2024-07-19	Build site.
Rmd	f313037	GitHub	2024-07-16	Update index.Rmd
Rmd	7be8f59	tkcaccia	2024-07-15	updates
html	7be8f59	tkcaccia	2024-07-15	updates
html	f8ca54a	tkcaccia	2024-07-14	update
html	f4d8faa	GitHub	2024-07-08	Update index.html
html	7a870fe	GitHub	2024-07-04	Update index.html
html	ee4ee17	GitHub	2024-06-19	Add files via upload
Rmd	615fc05	GitHub	2024-06-19	Add files via upload

---

KODAMA

This website hosts the code needed to reproduce the simulation and real data application results discussed in the forthcoming paper.

Introduction to KODAMA

The KODAMA algorithm represents a peculiar approach in unsupervised machine learning, designed to effectively handle the challenges posed by noisy and high-dimensional datasets. This method distinguishes itself through its novel use of iterative refinement of clustering based on cross-validation results. By dynamically adjusting the class labels of samples that were not correctly predicted, KODAMA enhances the accuracy and reliability of the clustering outcome. This process not only improves the segmentation of data but also ensures that the final model reflects a more accurate representation of the underlying patterns and relationships within the dataset. The flexibility of KODAMA to incorporate various validation methods, such as Partial Least Squares (PLS), further adds to its robustness, making it a versatile tool for data scientists facing complex analytical challenges.

Spatially-aware KODAMA

KODAMA algorithm has been adapted to deal with spatial information obtained from spatial transcriptomics and proteomics datasets. The approach used to integrate the spatial information consist in guiding the refinement of clustering forcing “spatially close” entries to have the same label during the cross-validation accuracy maximization step of the KODAMA algorithm.