Revise SNPclip sort order, use user supplied input format;Fix LDpair …

…multiallelic query for second SNP input
CBIIT · May 24, 2022 · 28ef9ab · 28ef9ab
1 parent e47e2fe
commit 28ef9ab
Show file tree

Hide file tree

Showing 6 changed files with 9 additions and 6 deletions.
diff --git a/LDlink/LDcommon.py b/LDlink/LDcommon.py
@@ -218,7 +218,7 @@ def getRecomb(db, filename, chromosome, begin, end, genome_build):
             }) + '\n')
     return recomb_results_sanitized
 
-def parse_vcf(vcf,snp_coords):
+def parse_vcf(vcf,snp_coords,ifsorted):
     delimiter = "#"
     snp_lists = str('**'.join(vcf)).split(delimiter)
     snp_dict = {}
@@ -258,7 +258,9 @@ def parse_vcf(vcf,snp_coords):
             snp_rs_dict[s_key] = snp_dict[snp_coord[2]]
     del snp_dict
 
-    sorted_snp_rs = OrderedDict(sorted(snp_rs_dict.items(),key=customsort))
+    sorted_snp_rs = snp_rs_dict
+    if ifsorted:
+        sorted_snp_rs = OrderedDict(sorted(snp_rs_dict.items(),key=customsort))
 
     return sorted_snp_rs," ".join(missing_rs)
 

diff --git a/LDlink/LDhap.py b/LDlink/LDhap.py
@@ -240,7 +240,7 @@ def set_alleles(a1, a2):
         hap2.append([])
 
     # parse vcf
-    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords)
+    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords,True)
    # throw error if no data is returned from 1000G
     if len(missing_snp.split()) == len(snp_pos):
         output["error"] = "Input variant list does not contain any valid RS numbers or coordinates. " + str(output["warning"] if "warning" in output else "")

diff --git a/LDlink/LDmatrix.py b/LDlink/LDmatrix.py
@@ -280,7 +280,7 @@ def set_alleles(a1, a2):
     for i in range(len(index) - 1):
         hap2.append([])
 
-    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords)
+    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords,True)
 
     # all lists does not contain data which is returned from 1000G
     if len(missing_snp.split()) == len(snp_pos):

diff --git a/LDlink/LDmatrix_plot_sub.py b/LDlink/LDmatrix_plot_sub.py
@@ -189,7 +189,7 @@ def set_alleles(a1, a2):
     for i in range(len(index) - 1):
         hap2.append([])
 
-    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords)
+    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords,True)
 
     rsnum_lst = []
     allele_lst = []

diff --git a/LDlink/SNPclip.py b/LDlink/SNPclip.py
@@ -305,7 +305,7 @@ def calc_r2(var1, var2):
         if head[i] in pop_ids:
             pop_index.append(i)
 
-    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords)
+    snp_dict,missing_snp = parse_vcf(vcf[h+1:],snp_coords,False)
 
    # throw error if no data is returned from 1000G
     if len(missing_snp.split()) == len(snp_pos):

diff --git a/LDlink/news-5.3.3.html b/LDlink/news-5.3.3.html
@@ -1,5 +1,6 @@
 <p><b>LDlink 5.3.3 Release (05/24/2022)</b></p>
 <ul>
+    <li>Revise SNPclip sort order, use user supplied input format; 
     <li>Fix LDpair multiallelic query for second SNP input</li>
 </ul>
 <br>