setup python reqs and finish section on workflow

chapters/workflow.qmd

@@ -2,20 +2,96 @@
 engine: knitr
 ---
 
+# Interchange data between Python and R
+
+In this section, we will demonstrate a workflow that stores genomic data in language agnostic formats to provide easy access to datasets and analysis results across multiple programming frameworks such as R and Python. This functionality is provided by the [ArtifactDB](https://github.com/artifactdb) framework.
+
+To get started, we will download the zilionis lung  dataset from the [scRNAseq](https://bioconductor.org/packages/release/data/experiment/html/scRNAseq.html) package. Then, we will store this dataset in language agnostic format using the [alabaster suite](https://github.com/ArtifactDB/alabaster.base) of R packages.
+
 ```{r}
 library(scRNAseq)
+library(alabaster)
 
 sce <- ZilionisLungData()
-
-library(alabaster)
-# dir_path <- paste(getwd(), "datasets", sep="/")
 saveObject(sce, path=paste(getwd(), "zilinoislung", sep="/"))
 ```
 
+:::{.callout-note}
+You can also save this dataset as an RDS object and access it in Python. Check out the [interop with R](./interop.qmd) section for more details.
+:::
+
+We can now load this dataset in Python using the [dolomite suite](https://github.com/ArtifactDB/dolomite-base) of Python packages. Both dolomite and alabaster are part of the ArtifactDB ecosystem to read artifacts stored in language agnostic formats.
 
 ```{python}
 from dolomite_base import read_object
 
-obj = read_object("./zilinoislung")
-print(obj)
-```
+data = read_object("./zilinoislung")
+print(data)
+```
+
+To illustrate this workflow, we will use the [CellTypist](https://github.com/Teichlab/celltypist) model to annotate cell types for this dataset. CellTypist works on an `AnnData` representation.
+
+```{python}
+adata = data.to_anndata()
+```
+
+Before we annotate, lets download the human lung atlas model from celltypist.
+
+```{python}
+import celltypist
+from celltypist import models
+
+models.download_models()
+model_name = "Human_Lung_Atlas.pkl"
+model = models.Model.load(model = model_namel)
+print(model)
+```
+
+Now lets annotate our dataset
+
+```{python}
+predictions = celltypist.annotate(adata, model = model_name, majority_voting = True)
+print(predictions.predicted_labels)
+```
+
+:::{.callout-note}
+The celltypist workflow is based on the tutorial described [here](https://colab.research.google.com/github/Teichlab/celltypist/blob/main/docs/notebook/celltypist_tutorial.ipynb#scrollTo=postal-chicken).
+:::
+
+Now lets get the `AnnData` object with the predicted labels embedded into the `obs` dataframe. 
+
+```{python}
+adata = predictions.to_adata()
+```
+
+We can now reverse the workflow and save this object into an Artifactdb format from Python. But first the object needs to be converted to a `SingleCellExperiment` class.
+
+```{python}
+from singlecellexperiment import SingleCellExperiment
+
+sce = SingleCellExperiment.from_anndata(adata)
+print(sce)
+```
+
+We now use the dolomite package to save it into language agnostic format.
+
+```{python}
+import dolomite_base
+
+dolomite_base.save_object(df, "./zilinoislung_with_celltypist")
+```
+
+Finally read the object back in R.
+
+```{r}
+sce_with_celltypist = readObject(path=paste(getwd(), "zilinoislung_with_celltypist", sep="/"))
+sce_with_celltypist
+```
+
+and that's it. Using these two generics read: `readObject`(R), `read_object`(Python), and save: `saveObject`(R), `save_object`(Python), you can save most Bioconductor objects into language agnostic formats. 
+
+----
+
+## Further reading
+
+- ArtifactDB GitHub organization - https://github.com/ArtifactDB.

requirements.txt

@@ -21,4 +21,6 @@ mudata
 delayedarray[dask]
 joblib
 dolomite
-hdf5array
+hdf5array
+celltypist
+rpy2