add sgRNA stats as output

pinellolab · Jun 25, 2024 · 5ff5050 · 5ff5050
1 parent ae22bb7
commit 5ff5050
Show file tree

Hide file tree

Showing 6 changed files with 10,948 additions and 10,940 deletions.
diff --git a/bean/cli/run.py b/bean/cli/run.py
@@ -117,6 +117,7 @@ def main(args, return_data=False):
         use_bcmatch=(not args.ignore_bcmatch),
     )
     guide_index = ndata.screen.guides.index.copy()
+    assert len(guide_index) == bdata.n_obs, (len(guide_index), bdata.n_obs)
     if return_data:
         return ndata
     # Build variant dataframe
@@ -191,7 +192,11 @@ def main(args, return_data=False):
     if args.library_design == "tiling":
         # add variant into to guide_info_tbl
         guide_info_df = pd.concat(
-            [guide_info_df, _get_guide_to_variant_df(target_info_df)], axis=1
+            [
+                guide_info_df,
+                _get_guide_to_variant_df(target_info_df).reindex(guide_info_df.index),
+            ],
+            axis=1,
         )
 
     # Add user-defined prior.

diff --git a/bean/model/readwrite.py b/bean/model/readwrite.py
@@ -187,7 +187,10 @@ def write_result_table(
     else:
         a_fitted = param_hist_dict["alpha_pi"].detach().cpu().numpy()
         pi = a_fitted[..., 1:].sum(axis=1) / a_fitted.sum(axis=1)
-    guide_info_df.insert(0, "edit_rate", pi)
+    guide_info_df["edit_rate"] = pi
+    guide_info_df = guide_info_df[
+        ["edit_rate"] + [col for col in guide_info_df.columns if col != "Mid"]
+    ]
     if guide_acc is not None:
         guide_info_df.insert(1, "accessibility", guide_acc)
         scaled_pi = _scale_pi(

diff --git a/docs/example_run_output/tiling/README.md b/docs/example_run_output/tiling/README.md
@@ -34,6 +34,6 @@ These are the example output of [`bean run`](https://pinellolab.github.io/crispr
 - `edit_rate`: Effective editing rates
 - `accessibility`: (Only if you have used `--scale-by-acc`) Accessibility signal that is used for scaling of the editing rate.
 - `scaled_edit_rate`: (Only if you have used `--scale-by-acc`) Endogenous editing rate used for modeling, estimated by scaling reporter editing rate by accessibility signal
-- `LFC_[condition]`: Raw LFC with pseudocount N.
+- `[cond1]_[cond2].median_lfc`: Raw LFC with pseudocount fed in with `--guide-lfc-pseudocount` argument (default 5).
 - `variants`: Variants generated by this gRNA
 - `variant_edit_rates`: Editing rate of this gRNA for each variant it creates.