From f25c407eabab989df9f844deb51cbbc462e19991 Mon Sep 17 00:00:00 2001
From: Kate Isaac <41767733+kweav@users.noreply.github.com>
Date: Mon, 23 Sep 2024 15:54:47 -0400
Subject: [PATCH] from devtools document

---
 NAMESPACE              |  7 +++++++
 man/calc_crispr.Rd     |  2 +-
 man/calc_gi.Rd         |  2 +-
 man/gimap_annotate.Rd  |  6 +++---
 man/gimap_normalize.Rd | 11 +++++++++--
 man/setup_data.Rd      |  9 +--------
 6 files changed, 22 insertions(+), 15 deletions(-)

diff --git a/NAMESPACE b/NAMESPACE
index a74fd5d..5e97e8e 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -7,8 +7,15 @@ export(get_example_data)
 export(gimap_annotate)
 export(gimap_filter)
 export(gimap_normalize)
+export(qc_cdf)
+export(qc_constructs_countzero_bar)
+export(qc_cor_heatmap)
+export(qc_plasmid_histogram)
+export(qc_sample_hist)
+export(qc_variance_hist)
 export(run_qc)
 export(setup_data)
+export(supported_cell_lines)
 import(dplyr)
 import(ggplot2)
 import(kableExtra)
diff --git a/man/calc_crispr.Rd b/man/calc_crispr.Rd
index 11e8650..41e4c5d 100644
--- a/man/calc_crispr.Rd
+++ b/man/calc_crispr.Rd
@@ -26,7 +26,7 @@ run_qc(gimap_dataset)
 
 gimap_dataset <- gimap_dataset \%>\%
   gimap_filter() \%>\%
-  gimap_annotate() \%>\%
+  gimap_annotate(cell_line = "HELA") \%>\%
   gimap_normalize(
     timepoints = "day",
     replicates = "rep"
diff --git a/man/calc_gi.Rd b/man/calc_gi.Rd
index bdf6809..0804afd 100644
--- a/man/calc_gi.Rd
+++ b/man/calc_gi.Rd
@@ -23,7 +23,7 @@ Create results table that has CRISPR scores, Wilcoxon rank-sum test and t tests.
 
   gimap_dataset <- gimap_dataset \%>\%
     gimap_filter() \%>\%
-    gimap_annotate() \%>\%
+    gimap_annotate(cell_line = "HELA") \%>\%
     gimap_normalize(
       timepoints = "day",
       replicates = "rep"
diff --git a/man/gimap_annotate.Rd b/man/gimap_annotate.Rd
index 828d508..6c5eff1 100644
--- a/man/gimap_annotate.Rd
+++ b/man/gimap_annotate.Rd
@@ -7,7 +7,7 @@
 gimap_annotate(
   .data = NULL,
   gimap_dataset,
-  cell_line = "HELA",
+  cell_line,
   control_genes = NULL,
   cn_annotate = TRUE,
   annotation_file = NULL
@@ -18,7 +18,7 @@ gimap_annotate(
 
 \item{gimap_dataset}{A special dataset structure that is setup using the `setup_data()` function.}
 
-\item{cell_line}{which cell line are you using? Default is "HELA"}
+\item{cell_line}{which cell line are you using? (e.g., HELA, PC9, etc.). Required argument}
 
 \item{control_genes}{A vector of gene symbols (e.g. AAMP) that should be labeled as control genes. These will be used for log fold change calculations. If no list is given then DepMap Public 23Q4 Achilles_common_essentials.csv is used https://depmap.org/portal/download/all/}
 
@@ -39,7 +39,7 @@ run_qc(gimap_dataset)
 
 gimap_dataset <- gimap_dataset \%>\%
   gimap_filter() \%>\%
-  gimap_annotate()
+  gimap_annotate(cell_line = "HELA")
 
 # To see anotations
 gimap_dataset$annotation
diff --git a/man/gimap_normalize.Rd b/man/gimap_normalize.Rd
index 571a89a..e768283 100644
--- a/man/gimap_normalize.Rd
+++ b/man/gimap_normalize.Rd
@@ -8,7 +8,9 @@ gimap_normalize(
   .data = NULL,
   gimap_dataset,
   timepoints = NULL,
-  replicates = NULL
+  replicates = NULL,
+  num_ids_wo_annot = 20,
+  rm_ids_wo_annot = TRUE
 )
 }
 \arguments{
@@ -24,6 +26,11 @@ The late timepoints will be the focus for the calculations. The column used for
 \item{replicates}{Specifies the column name of the metadata set up in `$metadata$sample_metadata`
 that has a factor that represents column that specifies replicates. These replicates will be kept separate
 for the late but the early and plasmid others will be averaged and used for normalization.}
+
+\item{num_ids_wo_annot}{default is 20; the number of pgRNA IDs to display to console if they don't have corresponding annotation data;
+ff there are more IDs without annotation data than this number, the output will be sent to a file rather than the console.}
+
+\item{rm_ids_wo_annot}{default is TRUE; whether or not to filter out pgRNA IDs from the input dataset that don't have corresponding annotation data available}
 }
 \description{
 This calculates the log fold change for a gimap dataset based on the annotation and metadata provided.
@@ -38,7 +45,7 @@ run_qc(gimap_dataset)
 
 gimap_dataset <- gimap_dataset \%>\%
   gimap_filter() \%>\%
-  gimap_annotate() \%>\%
+  gimap_annotate(cell_line = "HELA") \%>\%
   gimap_normalize(
     timepoints = "day",
     replicates = "rep"
diff --git a/man/setup_data.Rd b/man/setup_data.Rd
index b154841..4188492 100644
--- a/man/setup_data.Rd
+++ b/man/setup_data.Rd
@@ -4,20 +4,13 @@
 \alias{setup_data}
 \title{Making a new gimap dataset}
 \usage{
-setup_data(
-  counts = NULL,
-  pg_ids = NULL,
-  pg_metadata = NULL,
-  sample_metadata = NULL
-)
+setup_data(counts = NULL, pg_ids = NULL, sample_metadata = NULL)
 }
 \arguments{
 \item{counts}{a matrix of data that contains the counts where rows are each paired_guide target and columns are each sample}
 
 \item{pg_ids}{the pgRNA IDs: metadata associated with the pgRNA constructs that correspond to the rows of the counts data}
 
-\item{pg_metadata}{construct metadata}
-
 \item{sample_metadata}{metadata associated with the samples of the dataset that correspond to the columns of the counts data.
 Should include a column that has replicate information as well as a column that contains timepoint information respectively (this will be used for log fold calculations). These columns should be factors.}
 }