From 63d58634f328d07e1515233f8e1dca914fb5dbf6 Mon Sep 17 00:00:00 2001
From: WeichenZhou <arthurzhou10@gmail.com>
Date: Fri, 27 Nov 2020 17:43:02 -0500
Subject: [PATCH 1/4] 2020.1127.patch1

2020.1127.patch1
---
 PALMER.v1.7.cpp => PALMER.v1.7.1.cpp | 0
 scp/3_read_masker.cpp                | 5 +++++
 2 files changed, 5 insertions(+)
 rename PALMER.v1.7.cpp => PALMER.v1.7.1.cpp (100%)

diff --git a/PALMER.v1.7.cpp b/PALMER.v1.7.1.cpp
similarity index 100%
rename from PALMER.v1.7.cpp
rename to PALMER.v1.7.1.cpp
diff --git a/scp/3_read_masker.cpp b/scp/3_read_masker.cpp
index a807dd2..d01658e 100644
--- a/scp/3_read_masker.cpp
+++ b/scp/3_read_masker.cpp
@@ -236,6 +236,11 @@ int ReadMasker(string WD_dir){
                                     seq[k+x]='N';
                                 }
                             }
+                            else if((bit-number)<start&&bit>end){
+                                for(int x=start-bit+number;x!=end-bit+number+1;++x){
+                                    seq[k+x]='N';
+                                }
+                            }
                             k=k+number;
                         }
                         else if(cig=='D'||cig=='N') {bit=bit+number;

From 4eaa7ef3b9e79af137841629e4c9b7e9fcbe387d Mon Sep 17 00:00:00 2001
From: WeichenZhou <arthurzhou10@gmail.com>
Date: Sat, 28 Nov 2020 01:49:51 -0500
Subject: [PATCH 2/4] 2020.1128.v1.7.2.patch.

Upgrade for HIFI reads. Happy Thanksgiving!
---
 scp/6_TSD_seq.cpp |  4 ++--
 scp/7_FP_ex.cpp   | 32 +++++++++++++++++++++++---------
 scp/8_calling.cpp |  5 +++++
 3 files changed, 30 insertions(+), 11 deletions(-)

diff --git a/scp/6_TSD_seq.cpp b/scp/6_TSD_seq.cpp
index 787a415..9cd7d98 100644
--- a/scp/6_TSD_seq.cpp
+++ b/scp/6_TSD_seq.cpp
@@ -310,8 +310,8 @@ int tsd_module(string WD_dir, string t, int tsd_index){
             if(je2>loc[i][6]) je2=loc[i][6];
             
             int l1,l2;
-            l1=je1-js1+1;
-            l2=je2-js2+1;
+            l1=je1-js1+1+0.5*BIN_5;
+            l2=je2-js2+1+0.5*BIN_5;
             char *right_j;
             right_j=new char[l2];
             char *left_j;
diff --git a/scp/7_FP_ex.cpp b/scp/7_FP_ex.cpp
index 622c2f5..0a32e68 100644
--- a/scp/7_FP_ex.cpp
+++ b/scp/7_FP_ex.cpp
@@ -367,12 +367,13 @@ int fp_ex(string WD_dir, string fasta, string chr, string t, int tsd_index){
                        */
                     int fix_5;
                     //fix_5=1+loc_tsd[w][4]-BIN_5+J_BIN;
-                    if(BIN_5>=(info[i][3].length()-J_BIN_mer)) fix_5=1+loc_tsd[w][4]-BIN_5;
-                    else if (BIN_5<(info[i][3].length()-J_BIN_mer)) fix_5=1+loc_tsd[w][4]-BIN_5+info[i][3].length()-J_BIN_mer-BIN_5;
+                    if(BIN_5>=(info[i][3].length()-J_BIN_mer)) fix_5=0;
+                    else if (BIN_5<(info[i][3].length()-J_BIN_mer)) fix_5=info[i][3].length()-J_BIN_mer-BIN_5-1;
+                    
                     
                     int fix_3;
-                    if(BIN_3>=info[i][4].length()) fix_3=1+loc_tsd[w][5]-BIN_3;
-                    else if(BIN_3<info[i][4].length()) fix_3=1+loc_tsd[w][5]-BIN_3+info[i][4].length()-BIN_3;
+                    if(BIN_3>=info[i][4].length()) fix_3=0;
+                    else if(BIN_3<info[i][4].length()) fix_3=info[i][4].length()-BIN_3-1;
                     
                     string fasta5_str="";
                     string fasta3_str="";
@@ -382,7 +383,12 @@ int fp_ex(string WD_dir, string fasta, string chr, string t, int tsd_index){
                         string fa_s5,fa_s3;
                         fa_3.clear();
                         fa_5.clear();
-                        for(int n=loc_tsd[w][1]-1-(J_BIN*3)/2+1+fix_5;n!=(loc_tsd[w][1]+fix_5)&&n<=info[i][3].length();++n){
+                        int patch_n=loc_tsd[w][1]-1-(J_BIN*3)/2+fix_5;
+                        if(patch_n<0) {
+                            //cout<<"patch_n="<<patch_n<<endl;
+                            patch_n=0;
+                        }
+                        for(int n=patch_n;n!=(loc_tsd[w][1]+fix_5)&&n<=info[i][3].length();++n){
                             if(seq5[n]!='A'&&seq5[n]!='T'&&seq5[n]!='G'&&seq5[n]!='C'){
                                 fasta5_str=fasta5_str+"N";
                             }
@@ -420,7 +426,12 @@ int fp_ex(string WD_dir, string fasta, string chr, string t, int tsd_index){
                         string fa_s5,fa_s3;
                         fa_3.clear();
                         fa_5.clear();
-                        for(int n=loc_tsd[w][2]-1-(J_BIN*3)/2+fix_3;n!=(loc_tsd[w][2]+fix_3-1)&&n<=info[i][4].length();++n){
+                        int patch_n_2=loc_tsd[w][2]-1-(J_BIN*3)/2+fix_3-1;
+                        if(patch_n_2<0) {
+                            //cout<<"patch_n_2="<<patch_n_2<<endl;
+                            patch_n_2=0;
+                        }
+                        for(int n=patch_n_2;n!=(loc_tsd[w][2]+fix_3-1)&&n<=info[i][4].length();++n){
                             if(seq3[n]!='A'&&seq3[n]!='T'&&seq3[n]!='G'&&seq3[n]!='C'){
                                 fasta3_str=fasta3_str+"N";
                             }
@@ -453,9 +464,12 @@ int fp_ex(string WD_dir, string fasta, string chr, string t, int tsd_index){
                     }
                     //file22<<endl;
                     //file222<<endl;
+                    int fasta5_str_len=int(fasta5_str.length()*60/75);
+                    int fasta3_str_len=int(fasta3_str.length()*60/75);
+                    string fasta5_str_length=to_string(fasta5_str_len);
+                    string fasta3_str_length=to_string(fasta3_str_len);
                     
-                    
-                    string sys_3_blast = "bash -c \"blastn -evalue 0.05 -task blastn -query <(echo -e \\\">"+name_tag_1+"\\\\n"+(fasta5_str)+"\\\") -subject "+ref_junc_file+" -dust no -outfmt \\\"7 std\\\" |grep -v \\\"#\\\" | awk '{if(\\\$3>=80&&\\\$4>=60&&(\\\$10-\\\$9)>0) print \\\"1\\\"}' |wc -l \"";
+                    string sys_3_blast = "bash -c \"blastn -evalue 0.05 -task blastn -query <(echo -e \\\">"+name_tag_1+"\\\\n"+(fasta5_str)+"\\\") -subject "+ref_junc_file+" -dust no -outfmt \\\"7 std\\\" |grep -v \\\"#\\\" | awk '{if(\\\$3>=80&&\\\$4>="+fasta5_str_length+"&&(\\\$10-\\\$9)>0) print \\\"1\\\"}' |wc -l \"";
                     //> "+WD_dir+"read_result_junc_fake.txt";
                     //cout<<sys_3_blast<<endl;
                     
@@ -477,7 +491,7 @@ int fp_ex(string WD_dir, string fasta, string chr, string t, int tsd_index){
                     //loc_tsd_fp[w][0]=pp_3_int;
                     loc_tsd_fp[w][0]=accumulate(pp_3_int.begin(),pp_3_int.end(),loc_tsd_fp[w][0]);
                     
-                    string sys_3_blast_2 = "bash -c \"blastn -evalue 0.05 -task blastn -query <(echo -e \\\">"+name_tag_2+"\\\\n"+(fasta3_str)+"\\\") -subject "+ref_junc_file+" -dust no -outfmt \\\"7 std\\\" |grep -v \\\"#\\\" | awk '{if(\\\$3>=80&&\\\$4>=60&&(\\\$10-\\\$9)>0) print \\\"1\\\"}' |wc -l \"";
+                    string sys_3_blast_2 = "bash -c \"blastn -evalue 0.05 -task blastn -query <(echo -e \\\">"+name_tag_2+"\\\\n"+(fasta3_str)+"\\\") -subject "+ref_junc_file+" -dust no -outfmt \\\"7 std\\\" |grep -v \\\"#\\\" | awk '{if(\\\$3>=80&&\\\$4>="+fasta3_str_length+"&&(\\\$10-\\\$9)>0) print \\\"1\\\"}' |wc -l \"";
                     //> "+WD_dir+"read_result_junc_fake.txt";
                     //cout<<sys_3_blast_2<<endl;
                     
diff --git a/scp/8_calling.cpp b/scp/8_calling.cpp
index a850cc4..b271457 100644
--- a/scp/8_calling.cpp
+++ b/scp/8_calling.cpp
@@ -1088,6 +1088,11 @@ int calling(string WD_dir, string t, int tsd_index){
                 
                 //cout<<"p="<<p<<endl;
                 if(p==0){
+                    
+                    file2<<"cluster"<<i<<"_"<<info[i][1]<<"_"<<start1+S<<"_"<<start2-S<<"_"<<end1+S<<"_"<<end2-S<<'\t'<<info[i][1]<<'\t'<<start1+S<<'\t'<<start2-S<<'\t'<<end1+S<<'\t'<<end2-S<<'\t'<<L1_s1+L<<'\t'<<L1_s2-L<<'\t'<<L1_e1+L<<'\t'<<L1_e2-L<<'\t'<<"0"<<'\t'<<number_all<<'\t'<<(number_all-number)<<'\t'<<orien[i]<<'\t'<<"-"<<'\t'<<"0"<<'\t'<<"0"<<'\t'<<"0"<<'\t'<<loc_TP[i][0]<<'\t'<<int((L1_s_TP1+L1_s_TP2)/2)<<'\t'<<int((L1_e_TP1+L1_e_TP2)/2)<<endl;
+                    file4<<"cluster"<<i<<"_"<<info[i][1]<<"_"<<start1+S<<"_"<<start2-S<<"_"<<end1+S<<"_"<<end2-S<<'\t'<<seq_index_a<<'\t'<<"N"<<'\t'<<"N"<<'\t'<<"N"<<'\t'<<"N"<<'\t'<<info_line[i][2]<<endl;
+                    
+                    
                     for(int j=0;j!=line_tsd;++j) {delete [] name_tsd[j];}
                     delete [] name_tsd;
                     

From 6f5be4c2e9eaf3ef99832552003b2cae7aa51559 Mon Sep 17 00:00:00 2001
From: "Weichen (Arthur) Zhou" <arthurzhou10@gmail.com>
Date: Sat, 28 Nov 2020 01:53:41 -0500
Subject: [PATCH 3/4] Update README.md

---
 README.md | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index ef48a3b..0ed2fe7 100644
--- a/README.md
+++ b/README.md
@@ -127,16 +127,22 @@ Nucleic Acids Research, 2019, gkz1173, `https://doi.org/10.1093/nar/gkz1173`
 * arthurz@med.umich.edu
 
 ## Logs
+**Ver1.7.2** Nov.28th.2020! Happy Thanksgiving!!
+
+* Improved HIFI reads calling!!
+* A couple of major bugs fixed!!
+* Improved Running time!!
+
 **Ver1.7** Nov.11th.2020! Happy Singles Day & happy shopping!!
 
-* Enable HERV-K calling!!
-* Enable specific region calling!!
-* Enable cram file calling!!
+* Enabled HERV-K calling!!
+* Enabled specific region calling!!
+* Enabled cram file calling!!
 * Minor bugs fixed.
 
 **Ver1.6.2.Enhanced** Sep.27th.2020 by Jixing Guan
 
-* Optimize PALMER and make samtools as build-in lib
+* Optimized PALMER and make samtools as build-in lib
 
 **Ver1.6.2** May.19th.2020
 

From 4d1ba379358bd3c35ad4f4a278379b1cfe5e5c6d Mon Sep 17 00:00:00 2001
From: "Weichen (Arthur) Zhou" <arthurzhou10@gmail.com>
Date: Sat, 28 Nov 2020 01:54:53 -0500
Subject: [PATCH 4/4] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 0ed2fe7..c4caa38 100644
--- a/README.md
+++ b/README.md
@@ -131,7 +131,7 @@ Nucleic Acids Research, 2019, gkz1173, `https://doi.org/10.1093/nar/gkz1173`
 
 * Improved HIFI reads calling!!
 * A couple of major bugs fixed!!
-* Improved Running time!!
+* Improved running time!!
 
 **Ver1.7** Nov.11th.2020! Happy Singles Day & happy shopping!!