mgnify-pipelines-toolkit 1.2.3__py3-none-any.whl → 1.2.4__py3-none-any.whl

mgnify_pipelines_toolkit/analysis/amplicon/permute_primers.py

@@ -0,0 +1,87 @@
+import argparse
+from itertools import product
+from pathlib import Path
+
+from Bio import SeqIO
+
+
+def parse_args():
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument(
+        "-i",
+        "--input_primers",
+        required=True,
+        type=str,
+        help="Input primers to generate permutations for due to IUPAC ambiguous codes",
+    )
+    parser.add_argument("-p", "--prefix", required=True, type=str, help="Output prefix")
+
+    args = parser.parse_args()
+
+    input_path = args.input_primers
+    prefix = args.prefix
+
+    return input_path, prefix
+
+
+def permute_seq(seq):
+
+    ambiguous_bases_dict = {
+        "R": ["A", "G"],
+        "Y": ["C", "T"],
+        "S": ["G", "C"],
+        "W": ["A", "T"],
+        "K": ["G", "T"],
+        "M": ["A", "C"],
+        "B": ["C", "G", "T"],
+        "D": ["A", "G", "T"],
+        "H": ["A", "C", "T"],
+        "V": ["A", "C", "G"],
+        "N": ["A", "C", "T", "G"],
+    }
+
+    seq_template = []
+
+    for base in seq:
+        if base in ["A", "C", "T", "G"]:
+            seq_template.append(base)
+        else:
+            seq_template.append(ambiguous_bases_dict[base])
+
+    seq_permutations = []
+    for combo in product(*seq_template):
+        seq_permutations.append("".join(combo))
+
+    return seq_permutations
+
+
+def make_primer_permutations(primers_dict, prefix):
+
+    with open(f"{prefix}_permuted_primers.fasta", "w") as fw:
+        for primer_name, seq in primers_dict.items():
+
+            primer_seq = seq.seq
+            fw.write(f">{primer_name}\n{primer_seq}\n")
+
+            if primer_name == "F_auto" or primer_name[-1] == "F":
+                strand = "F"
+            elif primer_name == "R_auto" or primer_name[-1] == "R":
+                strand = "R"
+
+            seq_permutations = permute_seq(primer_seq)
+
+            for counter, permuted_seq in enumerate(seq_permutations, 1):
+                variant_name = f"{primer_name}_variant_{counter}_{strand}"
+                fw.write(f">{variant_name}\n{permuted_seq}\n")
+
+
+def main():
+
+    input_path, prefix = parse_args()
+    primers_dict = SeqIO.to_dict(SeqIO.parse(Path(input_path), "fasta"))
+    make_primer_permutations(primers_dict, prefix)
+
+
+if __name__ == "__main__":
+    main()

mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py

@@ -97,6 +97,8 @@ def main():
     fwd_primers_fw = open("./fwd_primers.fasta", "w")
     rev_primers_fw = open("./rev_primers.fasta", "w")
 
+    matched_primers_list = []
+
     with open(input, "r") as fr:
         for line in fr:
             line = line.strip()
@@ -108,6 +110,10 @@ def main():
             beg = float(line_lst[5])
             end = float(line_lst[6])
 
+            cleaned_primer_name = "_".join(primer_name.split("_")[0:-3])
+            if cleaned_primer_name in matched_primers_list:
+                continue
+
             if rfam == "RF00177":
                 gene = "16S"
                 model = REGIONS_16S_BACTERIA
@@ -118,7 +124,7 @@ def main():
                 gene = "18S"
                 model = REGIONS_18S
             else:  # For cases when it's a std primer but for some reason hasn't matched the model
-                if primer_name == "F_auto" or primer_name == "R_auto":
+                if cleaned_primer_name == "F_auto" or cleaned_primer_name == "R_auto":
                     continue
                 gene = "Unknown"
                 amp_region = "Unknown"
@@ -130,27 +136,32 @@ def main():
 
             strand = ""
 
-            if primer_name == "F_auto" or primer_name[-1] == "F":
+            if primer_name[-1] == "F":
                 strand = STRAND_FWD
-            elif primer_name == "R_auto" or primer_name[-1] == "R":
+            elif primer_name[-1] == "R":
                 strand = STRAND_REV
+            else:
+                print(f"Not sure what strand this is, exiting: {primer_name}")
 
             if model:
                 amp_region = get_amp_region(beg, end, strand, model)
-            primer_seq = str(fasta_dict[primer_name].seq)
+
+            primer_seq = str(fasta_dict[cleaned_primer_name].seq)
 
             res_dict["Gene"].append(gene)
             res_dict["VariableRegion"].append(amp_region)
-            res_dict["PrimerName"].append(primer_name)
+            res_dict["PrimerName"].append(cleaned_primer_name)
             res_dict["PrimerStrand"].append(strand)
             res_dict["PrimerSeq"].append(primer_seq)
 
             if strand == STRAND_FWD:
-                fwd_primers_fw.write(f">{primer_name}\n{primer_seq}\n")
+                fwd_primers_fw.write(f">{cleaned_primer_name}\n{primer_seq}\n")
             elif strand == STRAND_REV:
                 if single_end:
                     primer_seq = Seq(primer_seq).reverse_complement()
-                rev_primers_fw.write(f">{primer_name}\n{primer_seq}\n")
+                rev_primers_fw.write(f">{cleaned_primer_name}\n{primer_seq}\n")
+
+            matched_primers_list.append(cleaned_primer_name)
 
     res_df = pd.DataFrame.from_dict(res_dict)
     res_df.to_csv(f"./{sample}_primer_validation.tsv", sep="\t", index=False)

{mgnify_pipelines_toolkit-1.2.3.dist-info → mgnify_pipelines_toolkit-1.2.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mgnify_pipelines_toolkit
-Version: 1.2.3
+Version: 1.2.4
 Summary: Collection of scripts and tools for MGnify pipelines
 Author-email: MGnify team <metagenomics-help@ebi.ac.uk>
 License: Apache Software License 2.0

{mgnify_pipelines_toolkit-1.2.3.dist-info → mgnify_pipelines_toolkit-1.2.4.dist-info}/RECORD

@@ -3,7 +3,8 @@ mgnify_pipelines_toolkit/analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeR
 mgnify_pipelines_toolkit/analysis/amplicon/classify_var_regions.py,sha256=nUvboLz08RyqRE8Thfh8NRlmgJk0kVdXcSvgmAfKip0,20649
 mgnify_pipelines_toolkit/analysis/amplicon/make_asv_count_table.py,sha256=ohguvrMSg7GuiiZ5aHj1DvCnfThKFUG4s13LUSMM0mo,8892
 mgnify_pipelines_toolkit/analysis/amplicon/mapseq_to_asv_table.py,sha256=BLqhflblUegCvuQic16PrFXfIXlFWmGkmWJyl4wJoLQ,5040
-mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=aJiKzp2uLdVeobCOF2ySkofXPN5NMaQ7esc4oGDx_h4,4841
+mgnify_pipelines_toolkit/analysis/amplicon/permute_primers.py,sha256=1aGOJX9tC7M1rnd0U2PeJ681sUo02wxk7_ycJqeVt6s,2216
+mgnify_pipelines_toolkit/analysis/amplicon/primer_val_classification.py,sha256=I9JfkM_o6Wp4VINOMO6ff9mHqghdJw1kDIfiF37JtLo,5185
 mgnify_pipelines_toolkit/analysis/amplicon/remove_ambiguous_reads.py,sha256=Wu4tRtuRkgd3hoeuwPl_E5ghxIW7e_1vrcvFGWv_U4A,3173
 mgnify_pipelines_toolkit/analysis/amplicon/rev_comp_se_primers.py,sha256=yLpzkRJXAeXRUNgz60zopEwHcdprM2UDjquE-GkrFys,1722
 mgnify_pipelines_toolkit/analysis/amplicon/study_summary_generator.py,sha256=epVClL10QcllL8yu7YGjx0rXNVHL2GxHi-Ek0MOjsjo,13859
@@ -42,9 +43,9 @@ mgnify_pipelines_toolkit/schemas/schemas.py,sha256=pyDZvCuWbwccQF0D7c5BN1vv36wQd
 mgnify_pipelines_toolkit/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 mgnify_pipelines_toolkit/utils/fasta_to_delimited.py,sha256=lgYIR1S4crURY7C7nFtgE6QMV4u4zCNsUrVkcRnsEEo,3996
 mgnify_pipelines_toolkit/utils/get_mpt_version.py,sha256=aS9bWrC9CP7tpxoEVg6eEYt18-pmjG7fJl5Mchz4YOU,798
-mgnify_pipelines_toolkit-1.2.3.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-mgnify_pipelines_toolkit-1.2.3.dist-info/METADATA,sha256=CJCRbR2EbaS2qjpqqjRJHQ7jDjg7jZc9SLDbkZMjwcc,5775
-mgnify_pipelines_toolkit-1.2.3.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mgnify_pipelines_toolkit-1.2.3.dist-info/entry_points.txt,sha256=d7r4_VUS1hWNMnTJOy8u2kTRSFcy-sDN5NLRUXz-IhU,3041
-mgnify_pipelines_toolkit-1.2.3.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
-mgnify_pipelines_toolkit-1.2.3.dist-info/RECORD,,
+mgnify_pipelines_toolkit-1.2.4.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+mgnify_pipelines_toolkit-1.2.4.dist-info/METADATA,sha256=UXCHFcEcjuPMZvUgtzITSY_iIG-j_nfGVBMGCWjBjjA,5775
+mgnify_pipelines_toolkit-1.2.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mgnify_pipelines_toolkit-1.2.4.dist-info/entry_points.txt,sha256=sHDxlHizt_iZPtkNp0EDuohDGvC4O12B57JtpUmHwYk,3123
+mgnify_pipelines_toolkit-1.2.4.dist-info/top_level.txt,sha256=xA_wC7C01V3VwuDnqwRM2QYeJJ45WtvF6LVav4tYxuE,25
+mgnify_pipelines_toolkit-1.2.4.dist-info/RECORD,,

{mgnify_pipelines_toolkit-1.2.3.dist-info → mgnify_pipelines_toolkit-1.2.4.dist-info}/entry_points.txt

@@ -23,6 +23,7 @@ make_asv_count_table = mgnify_pipelines_toolkit.analysis.amplicon.make_asv_count
 mapseq2biom = mgnify_pipelines_toolkit.analysis.shared.mapseq2biom:main
 mapseq_to_asv_table = mgnify_pipelines_toolkit.analysis.amplicon.mapseq_to_asv_table:main
 markergene_study_summary = mgnify_pipelines_toolkit.analysis.shared.markergene_study_summary:main
+permute_primers = mgnify_pipelines_toolkit.analysis.amplicon.permute_primers:main
 primer_val_classification = mgnify_pipelines_toolkit.analysis.amplicon.primer_val_classification:main
 process_dbcan_cazys = mgnify_pipelines_toolkit.analysis.assembly.process_dbcan_result_cazys:main
 process_dbcan_clusters = mgnify_pipelines_toolkit.analysis.assembly.process_dbcan_result_clusters:main