From fbc430ac1fbe91ba4b779aed2ad843b2db8940a1 Mon Sep 17 00:00:00 2001
From: Shixiang Wang <wangshx@shanghaitech.edu.cn>
Date: Mon, 7 Mar 2022 19:26:41 +0800
Subject: [PATCH] avoid invalid region extraction #396 related

---
 DESCRIPTION           |  2 +-
 NEWS.md               |  4 ++++
 R/generate_matrices.R | 12 ++++++------
 3 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index a2108204..09d3122d 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: sigminer
 Title: Extract, Analyze and Visualize Mutational Signatures for
     Genomic Variations
-Version: 2.1.2
+Version: 2.1.3
 Authors@R: 
     c(person(given = "Shixiang",
              family = "Wang",
diff --git a/NEWS.md b/NEWS.md
index 1bd24955..a1ca105b 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,3 +1,7 @@
+# sigminer 2.1.3
+
+- Fixed error in extracting invalid regions (#396, thanks to @KirsieMin).
+
 # sigminer 2.1.2
 
 - Enhanced the `read_copynumber_seqz()` to include minor copy number. (Thanks to yancey)
diff --git a/R/generate_matrices.R b/R/generate_matrices.R
index 9b1ed982..bfc98852 100644
--- a/R/generate_matrices.R
+++ b/R/generate_matrices.R
@@ -21,14 +21,14 @@ generate_matrix_SBS <- function(query, ref_genome, genome_build = "hg19", add_tr
   ss <- BSgenome::getSeq(
     x = ref_genome,
     names = extract.tbl$Chromosome,
-    start = extract.tbl$Start - 2,
+    start = pmax(extract.tbl$Start - 2, 1L),
     end = extract.tbl$End + 2,
     as.character = TRUE
   )
 
   send_info("Extracting +/- 20bp around mutated bases for background C>T estimation.")
   updwn <- BSgenome::getSeq(
-    x = ref_genome, names = extract.tbl$Chromosome, start = extract.tbl$upstream,
+    x = ref_genome, names = extract.tbl$Chromosome, start = pmax(extract.tbl$upstream, 1L),
     end = extract.tbl$downstream, as.character = FALSE
   )
   updwn.alphFreq <- data.table::as.data.table(BSgenome::alphabetFrequency(x = updwn))[, c("A", "T", "G", "C")] # Nucleotide frequency
@@ -346,8 +346,8 @@ generate_matrix_DBS <- function(query, ref_genome, genome_build = "hg19", add_tr
     BSgenome::getSeq(
       x = ref_genome,
       names = Chromosome,
-      start = Start_Position - 1,
-      end = Start_Position - 1
+      start = pmax(Start_Position - 1, 1L),
+      end = pmax(Start_Position - 1, 1L)
     )
   )]
   query[, downstream := as.character(
@@ -534,8 +534,8 @@ generate_matrix_INDEL <- function(query, ref_genome, genome_build = "hg19", add_
     BSgenome::getSeq(
       x = ref_genome,
       names = Chromosome,
-      start = Start_Position - 50,
-      end = Start_Position - 1
+      start = pmax(Start_Position - 50, 1L),
+      end = pmax(Start_Position - 1, 1L)
     )
   )]