From 5e7483d2dcc2bdb6022fa58caa44a30803f6e87c Mon Sep 17 00:00:00 2001
From: Marek Schwarz <schwarz.marek@outlook.com>
Date: Tue, 26 Nov 2019 12:43:19 +0100
Subject: [PATCH] update readme, blast regex and version

---
 readme.md                                    |  3 ++-
 rna_blast_analyze/BR_core/parse_accession.py | 11 +++--------
 rna_blast_analyze/VERSION                    |  2 +-
 3 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/readme.md b/readme.md
index 6983adf..da316c2 100644
--- a/readme.md
+++ b/readme.md
@@ -67,7 +67,8 @@ conda install -c conda-forge -c bioconda -c schwarz.marek rboanalyzer
   # or
   pip3 install --upgrade pip --user
   ```
-- ncbi-blast+ >= 2.6, < 2.8.1 [link](http://ftp.ncbi.nih.gov/blast/executables/blast+/2.7.1/)
+- ncbi-blast+ >= 2.8.1 [link](http://ftp.ncbi.nih.gov/blast/executables/blast+/2.9.0/)
+  (The pipeline can use blast from version 2.6.0, however this version is not compatible with blast dbv5)
 - locarna >= 1.9.2, <2 [link](https://github.com/s-will/LocARNA/releases/tag/v1.9.2.2)
 - infernal >= 1.1, <2 [link](http://eddylab.org/infernal/)
 - clustalo >= 1.2.4, <2 [link](http://www.clustal.org/omega/)
diff --git a/rna_blast_analyze/BR_core/parse_accession.py b/rna_blast_analyze/BR_core/parse_accession.py
index d4e819b..d5aa3a8 100644
--- a/rna_blast_analyze/BR_core/parse_accession.py
+++ b/rna_blast_analyze/BR_core/parse_accession.py
@@ -73,26 +73,21 @@
 
 old = [r'ZP_[0-9]{8}\.[0-9]+', r'NS_[0-9]{6}\.[0-9]+']
 
-pdb = ["[0-9A-Z]{4}[_|][0-9A-Z]{1,2}",]
+# accommodate up to 4 characters chain id (https://www.wwpdb.org/deposition/preparing-pdbx-mmcif-files)
+pdb_on_steroids = [r"(gi\|\d+\|)?(?(1))((?<=\|pdb\|)[0-9A-Z]{4}[_|][0-9A-Za-z]{1,4}|^[0-9A-Z]{4}[_|][0-9A-Za-z]{1,4})"]
 
 exceptions = [
     '1KPD',  # although it has chain, in the NCBI nt database it is listed without chain
     r'GPS_[0-9]{9}\.[0-9]+',  # from refseq
 ]
 
-known_acc_formats = genbank_nucl + genbank_wgs + refseq_re + genbank_mga + genbank_prot + pdb + genbank_wgs_scafolds + exceptions + old
+known_acc_formats = genbank_nucl + genbank_wgs + refseq_re + genbank_mga + genbank_prot + genbank_wgs_scafolds + exceptions + old + pdb_on_steroids
 accession_regex = '|'.join(known_acc_formats)
 compiled_accession_regex = re.compile(accession_regex)
 
 
 if __name__ == '__main__':
 
-    _javascript_xml_re = '(' + accession_regex + ')(?=\|?</Hit_id>)'
-    _javascript_txt_re = '^>(' + accession_regex
-
-    print(_javascript_xml_re.__repr__())
-    print(_javascript_txt_re.__repr__())
-
     import sys
     import gzip
     import re
diff --git a/rna_blast_analyze/VERSION b/rna_blast_analyze/VERSION
index 1a3c67c..446ba66 100644
--- a/rna_blast_analyze/VERSION
+++ b/rna_blast_analyze/VERSION
@@ -1 +1 @@
-0.1.4a2
\ No newline at end of file
+0.1.4
\ No newline at end of file