update priors

data/script/download_hci_priors.sh

@@ -86,15 +86,15 @@ tabix -p vcf priors_hg19.vcf.gz
 
 
 ## crossmap to lift from GRCh37 to GRCh38
-CrossMap.py vcf $data/genomes/hg19ToHg38.fixed.over.chain.gz priors_hg19.vcf.gz $grch38 priors.vcf
+CrossMap vcf $data/genomes/hg19ToHg38.fixed.over.chain.gz priors_hg19.vcf.gz $grch38 priors.vcf
 rm priors_hg19.vcf.gz
 rm priors_hg19.vcf.gz.tbi
 
 
 python3 $dbconverter -g MLH1 -e exon1 >> priors.vcf
 
 ##### STILL MISSING:
-python3 $dbconverter -g MSH2 -e exon1 >> priors.vcf
+python3 $dbconverter -g MSH2 -e exon1 > priors_msh2.vcf
 python3 $dbconverter -g MSH6 -e exon1 >> priors.vcf
 
 $ngsbits/VcfSort -in priors.vcf -out priors.vcf

tools/priors_crawler.py

@@ -69,11 +69,13 @@ def extract_ref_alt(variant_container_text):
 
 def parse_html(url):
     try:
-        resp = requests.get(url)
+        resp = requests.get(url, verify=False)
+        resp.raise_for_status()
         html_text = resp.text
         return lxml.html.fromstring(html_text)
     except: #(HTTPError, RemoteDisconnected) as e
-        functions.eprint("Got an error for url: " + url + "... retrying")
+        functions.eprint(resp.text)
+        functions.eprint("Got a http " + str(resp.status_code) + " error for url: " + url + "... retrying")
         return None
 
 
@@ -88,7 +90,7 @@ def retry_parse_html(url):
 
 
 
-base_url = "http://priors.hci.utah.edu/PRIORS/BRCA/"
+base_url = "https://priors.hci.utah.edu/PRIORS/BRCA/"
 exon_url = urljoin(base_url, ("viewer.php?gene=%s&exon=%s" % (gene, first_exon)))
 
 
@@ -123,6 +125,7 @@ def retry_parse_html(url):
     ]
     functions.write_vcf_header(info_headers, reference_genome="hg19")
 
+functions.eprint("YOYO")
 
 all_exon_urls = []
 
@@ -135,7 +138,6 @@ def retry_parse_html(url):
             all_exon_urls.append(new_exon_url)
 
 
-
 for exon_url in all_exon_urls:
     functions.eprint(exon_url)
     doc = retry_parse_html(exon_url)