(4-B/N) update and run fusion summary

analyses/fusion-summary/01-fusion-summary.Rmd

@@ -62,10 +62,10 @@ prepareOutput <- function(fuseDF, bioid) {
   fuseDF %>% 
     # some fusions have in-frame and frameshift fusion calls for a sample
     # this will make unique fusionName and Sample dataset to get 1/0 values
-    dplyr::select(Sample,FusionName) %>%
-    unique() %>%
-    reshape2::dcast(Sample ~ FusionName,fun.aggregate = length) %>%
-    right_join(data.frame(Sample = bioid)) %>%
+    distinct(Sample, FusionName) %>%
+    mutate(Count = 1) %>%
+    pivot_wider(names_from = FusionName, values_from = Count, values_fill = list(Count = 0)) %>%
+    right_join(data.frame(Sample = specimensUnion)) %>%
     replace(is.na(.), 0) %>%
     rename(Kids_First_Biospecimen_ID = Sample)
 }

analyses/fusion-summary/01-fusion-summary.nb.html

@@ -1767,14 +1767,14 @@ <h3>Libraries and functions</h3>
 <!-- rnb-source-begin eyJkYXRhIjoibGlicmFyeSh0aWR5dmVyc2UpIn0= -->
 <pre class="r"><code>library(tidyverse)</code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-message-begin eyJkYXRhIjoi4pSA4pSAIEF0dGFjaGluZyBjb3JlIHRpZHl2ZXJzZSBwYWNrYWdlcyDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIAgdGlkeXZlcnNlIDIuMC4wIOKUgOKUgFxu4pyUIGRwbHlyICAgICAxLjEuMSAgICAg4pyUIHJlYWRyICAgICAyLjEuNFxu4pyUIGZvcmNhdHMgICAxLjAuMCAgICAg4pyUIHN0cmluZ3IgICAxLjUuMFxu4pyUIGdncGxvdDIgICAzLjQuMiAgICAg4pyUIHRpYmJsZSAgICAzLjIuMVxu4pyUIGx1YnJpZGF0ZSAxLjkuMiAgICAg4pyUIHRpZHlyICAgICAxLjMuMFxu4pyUIHB1cnJyICAgICAxLjAuMSAgICAgXG7ilIDilIAgQ29uZmxpY3RzIOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgOKUgCB0aWR5dmVyc2VfY29uZmxpY3RzKCkg4pSA4pSAXG7inJYgZHBseXI6OmZpbHRlcigpIG1hc2tzIHN0YXRzOjpmaWx0ZXIoKVxu4pyWIGRwbHlyOjpsYWcoKSAgICBtYXNrcyBzdGF0czo6bGFnKClcbuKEuSBVc2UgdGhlIGNvbmZsaWN0ZWQgcGFja2FnZSAoPGh0dHA6Ly9jb25mbGljdGVkLnItbGliLm9yZy8+KSB0byBmb3JjZSBhbGwgY29uZmxpY3RzIHRvIGJlY29tZSBlcnJvcnNcbiJ9 -->
-<pre><code>── Attaching core tidyverse packages ───────────────────────────────────────────────────────────────────────────── tidyverse 2.0.0 ──
+<!-- rnb-message-begin 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 -->
+<pre><code>── Attaching core tidyverse packages ───────────────────────────────────────── tidyverse 2.0.0 ──
 ✔ dplyr     1.1.1     ✔ readr     2.1.4
 ✔ forcats   1.0.0     ✔ stringr   1.5.0
 ✔ ggplot2   3.4.2     ✔ tibble    3.2.1
 ✔ lubridate 1.9.2     ✔ tidyr     1.3.0
 ✔ purrr     1.0.1     
-── Conflicts ─────────────────────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
+── Conflicts ─────────────────────────────────────────────────────────── tidyverse_conflicts() ──
 ✖ dplyr::filter() masks stats::filter()
 ✖ dplyr::lag()    masks stats::lag()
 ℹ Use the conflicted package (&lt;http://conflicted.r-lib.org/&gt;) to force all conflicts to become errors</code></pre>
@@ -1852,18 +1852,13 @@ <h3>Read in data</h3>
 #&#39; file but have been assayed - we will gather those from the histology file
 hist &lt;- read_tsv(file.path(dataDir, &quot;histologies-base.tsv&quot;))</code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-warning-begin eyJkYXRhIjoiV2FybmluZzogT25lIG9yIG1vcmUgcGFyc2luZyBpc3N1ZXMsIGNhbGwgYHByb2JsZW1zKClgIG9uIHlvdXIgZGF0YSBmcmFtZSBmb3IgZGV0YWlscywgZS5nLjpcbiAgZGF0IDwtIHZyb29tKC4uLilcbiAgcHJvYmxlbXMoZGF0KVxuIn0= -->
-<pre><code>Warning: One or more parsing issues, call `problems()` on your data frame for details, e.g.:
-  dat &lt;- vroom(...)
-  problems(dat)</code></pre>
-<!-- rnb-warning-end -->
-<!-- rnb-message-begin eyJkYXRhIjoiUm93czogNDM3MjkgQ29sdW1uczogNTNcbuKUgOKUgCBDb2x1bW4gc3BlY2lmaWNhdGlvbiDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIBcbkRlbGltaXRlcjogXCJcXHRcIlxuY2hyICgzNCk6IEtpZHNfRmlyc3RfQmlvc3BlY2ltZW5fSUQsIHNhbXBsZV9pZCwgYWxpcXVvdF9pZCwgS2lkc19GaXJzdF9QYXJ0aS4uLlxuZGJsICgxNyk6IGFnZV9hdF9kaWFnbm9zaXNfZGF5cywgT1NfZGF5cywgRUZTX2RheXMsIGFnZV9sYXN0X3VwZGF0ZV9kYXlzLCBuby4uLlxubGdsICAoMik6IGludGVncmF0ZWRfZGlhZ25vc2lzLCBtb2xlY3VsYXJfc3VidHlwZVxuXG7ihLkgVXNlIGBzcGVjKClgIHRvIHJldHJpZXZlIHRoZSBmdWxsIGNvbHVtbiBzcGVjaWZpY2F0aW9uIGZvciB0aGlzIGRhdGEuXG7ihLkgU3BlY2lmeSB0aGUgY29sdW1uIHR5cGVzIG9yIHNldCBgc2hvd19jb2xfdHlwZXMgPSBGQUxTRWAgdG8gcXVpZXQgdGhpcyBtZXNzYWdlLlxuIn0= -->
-<pre><code>Rows: 43729 Columns: 53
-── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────
+<!-- rnb-message-begin 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 -->
+<pre><code>Rows: 47507 Columns: 56
+── Column specification ─────────────────────────────────────────────────────────────────────────
 Delimiter: &quot;\t&quot;
-chr (34): Kids_First_Biospecimen_ID, sample_id, aliquot_id, Kids_First_Parti...
-dbl (17): age_at_diagnosis_days, OS_days, EFS_days, age_last_update_days, no...
-lgl  (2): integrated_diagnosis, molecular_subtype
+chr (37): Kids_First_Participant_ID, Kids_First_Biospecimen_ID, sample_id, a...
+dbl (17): cell_line_passage, OS_days, EFS_days, age_at_diagnosis_days, age_a...
+lgl  (2): molecular_subtype, integrated_diagnosis
 
 ℹ Use `spec()` to retrieve the full column specification for this data.
 ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.</code></pre>
@@ -1878,9 +1873,9 @@ <h3>Read in data</h3>
   read_tsv(file.path(dataDir, &quot;fusion-putative-oncogenic.tsv&quot;))
 }</code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-message-begin eyJkYXRhIjoiUm93czogNTUyNjAgQ29sdW1uczogMjJcbuKUgOKUgCBDb2x1bW4gc3BlY2lmaWNhdGlvbiDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIDilIBcbkRlbGltaXRlcjogXCJcXHRcIlxuY2hyICgyMCk6IFNhbXBsZSwgRnVzaW9uTmFtZSwgTGVmdEJyZWFrcG9pbnQsIFJpZ2h0QnJlYWtwb2ludCwgRG9tYWluUmV0YWluZS4uLlxuZGJsICAoMSk6IGNhbGxlci5jb3VudFxubGdsICAoMSk6IHJlY2lwcm9jYWxfZXhpc3RzXG5cbuKEuSBVc2UgYHNwZWMoKWAgdG8gcmV0cmlldmUgdGhlIGZ1bGwgY29sdW1uIHNwZWNpZmljYXRpb24gZm9yIHRoaXMgZGF0YS5cbuKEuSBTcGVjaWZ5IHRoZSBjb2x1bW4gdHlwZXMgb3Igc2V0IGBzaG93X2NvbF90eXBlcyA9IEZBTFNFYCB0byBxdWlldCB0aGlzIG1lc3NhZ2UuXG4ifQ== -->
-<pre><code>Rows: 55260 Columns: 22
-── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────
+<!-- rnb-message-begin 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 -->
+<pre><code>Rows: 81348 Columns: 22
+── Column specification ─────────────────────────────────────────────────────────────────────────
 Delimiter: &quot;\t&quot;
 chr (20): Sample, FusionName, LeftBreakpoint, RightBreakpoint, DomainRetaine...
 dbl  (1): caller.count
@@ -1900,13 +1895,13 @@ <h3>Read in DGD and arrange as fusion filtering df</h3>
 <pre class="r"><code># read in DGD data 
 dgd_fusion &lt;- readr::read_tsv(file.path(dataDir, &quot;fusion-dgd.tsv.gz&quot;))</code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-message-begin 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 -->
-<pre><code>Rows: 278 Columns: 17
-── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────────────────
+<!-- rnb-message-begin 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 -->
+<pre><code>Rows: 533 Columns: 22
+── Column specification ─────────────────────────────────────────────────────────────────────────
 Delimiter: &quot;\t&quot;
-chr (9): Sample, FusionName, Fusion_Type, Gene1A, Gene1B, annots, Gene1A_ann...
-dbl (2): JunctionReadCount, SpanningFragCount
-lgl (6): Gene2A, Gene2B, LeftBreakpoint, RightBreakpoint, Gene2A_anno, Gene2...
+chr (14): Sample, FusionName, Fusion_Type, Gene1A, Gene1B, 5_prime_transcrip...
+dbl  (2): JunctionReadCount, SpanningFragCount
+lgl  (6): Gene2A, Gene2B, LeftBreakpoint, RightBreakpoint, Gene2A_anno, Gene...
 
 ℹ Use `spec()` to retrieve the full column specification for this data.
 ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.</code></pre>
@@ -2209,10 +2204,10 @@ <h4>Perform selection for LGG and HGG fusions</h4>
 # Check they don&#39;t retain the kinase domain. They do not, so leave out.
 table(three_prime_kinase_outframe$DomainRetainedGene1B)</code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-output-begin eyJkYXRhIjoiXG4gTm8gWWVzIFxuIDIyIDE0OCBcbiJ9 -->
+<!-- rnb-output-begin eyJkYXRhIjoiXG4gTm8gWWVzIFxuIDM1IDE5NyBcbiJ9 -->
 <pre><code>
  No Yes 
- 22 148 </code></pre>
+ 35 197 </code></pre>
 <!-- rnb-output-end -->
 <!-- rnb-chunk-end -->
 <!-- rnb-text-begin -->
@@ -2252,11 +2247,12 @@ <h4>Perform selection for LGG and HGG fusions</h4>
   select(Sample, FusionName = five_prime_kinase) %&gt;%
   distinct()</code></pre>
 <!-- rnb-source-end -->
-<!-- rnb-warning-begin eyJkYXRhIjoiV2FybmluZyBpbiBsZWZ0X2pvaW4oLiwgYWxsRnVzZUxHR0hHRywgYnkgPSBjKFwiU2FtcGxlXCIsIFwiRnVzaW9uTmFtZVwiKSk6IERldGVjdGVkIGFuIHVuZXhwZWN0ZWQgbWFueS10by1tYW55IHJlbGF0aW9uc2hpcCBiZXR3ZWVuIGB4YCBhbmQgYHlgLlxu4oS5IFJvdyA0IG9mIGB4YCBtYXRjaGVzIG11bHRpcGxlIHJvd3MgaW4gYHlgLlxu4oS5IFJvdyAxIG9mIGB5YCBtYXRjaGVzIG11bHRpcGxlIHJvd3MgaW4gYHhgLlxu4oS5IElmIGEgbWFueS10by1tYW55IHJlbGF0aW9uc2hpcCBpcyBleHBlY3RlZCwgc2V0IGByZWxhdGlvbnNoaXAgPSBcIm1hbnktdG8tbWFueVwiYCB0byBzaWxlbmNlIHRoaXMgd2FybmluZy5cbiJ9 -->
+<!-- rnb-warning-begin eyJkYXRhIjoiV2FybmluZyBpbiBsZWZ0X2pvaW4oLiwgYWxsRnVzZUxHR0hHRywgYnkgPSBjKFwiU2FtcGxlXCIsIFwiRnVzaW9uTmFtZVwiKSk6IERldGVjdGVkIGFuIHVuZXhwZWN0ZWQgbWFueS10by1tYW55IHJlbGF0aW9uc2hpcCBiZXR3ZWVuIGB4YCBhbmQgYHlgLlxu4oS5IFJvdyA0IG9mIGB4YCBtYXRjaGVzIG11bHRpcGxlIHJvd3MgaW4gYHlgLlxu4oS5IFJvdyAxIG9mIGB5YCBtYXRjaGVzIG11bHRpcGxlIHJvd3MgaW4gYHhgLlxu4oS5IElmIGEgbWFueS10by1tYW55IHJlbGF0aW9uc2hpcCBpcyBleHBlY3RlZCwgc2V0IGByZWxhdGlvbnNoaXAgPSBcIm1hbnktdG8tbWFueVwiYCB0byBzaWxlbmNlXG4gIHRoaXMgd2FybmluZy5cbiJ9 -->
 <pre><code>Warning in left_join(., allFuseLGGHGG, by = c(&quot;Sample&quot;, &quot;FusionName&quot;)): Detected an unexpected many-to-many relationship between `x` and `y`.
 ℹ Row 4 of `x` matches multiple rows in `y`.
 ℹ Row 1 of `y` matches multiple rows in `x`.
-ℹ If a many-to-many relationship is expected, set `relationship = &quot;many-to-many&quot;` to silence this warning.</code></pre>
+ℹ If a many-to-many relationship is expected, set `relationship = &quot;many-to-many&quot;` to silence
+  this warning.</code></pre>
 <!-- rnb-warning-end -->
 <!-- rnb-chunk-end -->
 <!-- rnb-text-begin -->

analyses/fusion-summary/README.md

@@ -2,14 +2,14 @@
 
 This module generates summary files for fusions of interest present in biospecimens taken from:
 
-  1. Ependymoma tumors
+1. Ependymoma tumors
 2. Embryonal tumors not from ATRT or MB
 3. CNS Ewing Sarcomas
 4. LGG/HGG tumors
 
 To generate the tables run:
 
-  ```
+```
 bash run-new-analysis.sh
 ```