Merge pull request #51 from mskcc/dev

Dev
mskcc · Jul 30, 2024 · ab09ea5 · ab09ea5
2 parents d82ec09 + 7f820a8
commit ab09ea5
Show file tree

Hide file tree

Showing 15 changed files with 378 additions and 203 deletions.
diff --git a/modules.json b/modules.json
@@ -6,27 +6,27 @@
             "modules": {
                 "msk": {
                     "neoantigenediting/aligntoiedb": {
-                        "branch": "neoantigen",
-                        "git_sha": "14ae2b3db25701828835e7145cee14dfdaddf180",
+                        "branch": "develop",
+                        "git_sha": "cac9c047e374ee259fb612ba5816e7e6aae6b86f",
                         "installed_by": ["neoantigen_editing"]
                     },
                     "neoantigenediting/computefitness": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "1f65c2ecdc5010549055ff7f4e6b8bccee48d4ae",
                         "installed_by": ["neoantigen_editing"]
                     },
                     "neoantigenutils/formatnetmhcpan": {
-                        "branch": "neoantigen",
-                        "git_sha": "fceccd3f96fec678849bb9bc0c04e53d9965f973",
+                        "branch": "develop",
+                        "git_sha": "c5d1252252e15555abcc82ea537cebeb281a1856",
                         "installed_by": ["netmhcstabandpan"]
                     },
                     "neoantigenutils/generatehlastring": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "33f0bd33095fa15016ee24f4fb4d61e896dbb970",
                         "installed_by": ["netmhcstabandpan"]
                     },
                     "neoantigenutils/generatemutfasta": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "bb7975c796ab9a2d7a45ef733a6a226a0f5ad74a",
                         "installed_by": ["netmhcstabandpan"]
                     },
@@ -36,32 +36,32 @@
                         "installed_by": ["modules"]
                     },
                     "netmhcpan": {
-                        "branch": "neoantigen",
-                        "git_sha": "33f0bd33095fa15016ee24f4fb4d61e896dbb970",
+                        "branch": "develop",
+                        "git_sha": "503abeb67260f060d8228221b07d743aa4180345",
                         "installed_by": ["modules", "netmhcstabandpan"]
                     },
                     "netmhcstabpan": {
-                        "branch": "neoantigen",
-                        "git_sha": "33f0bd33095fa15016ee24f4fb4d61e896dbb970",
+                        "branch": "develop",
+                        "git_sha": "c1a473f8bc08f778269a36ab62d5adf24357225f",
                         "installed_by": ["modules", "netmhcstabandpan"]
                     },
                     "phylowgs/createinput": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "b031249dcf4279606c25e626da2a628756e75e8a",
                         "installed_by": ["phylowgs"]
                     },
                     "phylowgs/multievolve": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "535662d391a3533dea3b11c462c14799227e08b2",
                         "installed_by": ["phylowgs"]
                     },
                     "phylowgs/parsecnvs": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "8471691d7c29bc2f5f4fb92279c94fb2640b6c38",
                         "installed_by": ["phylowgs"]
                     },
                     "phylowgs/writeresults": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "6d27f08bf649e8680ace321d3127dcdf0e210973",
                         "installed_by": ["phylowgs"]
                     }
@@ -70,17 +70,17 @@
             "subworkflows": {
                 "msk": {
                     "neoantigen_editing": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "56a628201401866096d6307b9e8c690c5eb46ac2",
                         "installed_by": ["subworkflows"]
                     },
                     "netmhcstabandpan": {
-                        "branch": "neoantigen",
-                        "git_sha": "1b7ac020798572be26402a72dd9c1a22ce849a63",
+                        "branch": "develop",
+                        "git_sha": "d60211568e3709e9284bc06eef938e361d474d08",
                         "installed_by": ["subworkflows"]
                     },
                     "phylowgs": {
-                        "branch": "neoantigen",
+                        "branch": "develop",
                         "git_sha": "a5d61394af346f21ee2eb7ecfd97ab25bdbd1d0e",
                         "installed_by": ["subworkflows"]
                     }

diff --git a/modules/msk/neoantigenediting/aligntoiedb/meta.yml b/modules/msk/neoantigenediting/aligntoiedb/meta.yml
@@ -1,7 +1,7 @@
 ---
 # yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "neoantigenediting_aligntoiedb"
-description: Align neoantigens to the IEDB resource
+description: Align neoantigens to the IEDB file
 keywords:
   - neoantigenediting
   - neoantigens

diff --git a/modules/msk/neoantigenediting/aligntoiedb/resources/usr/bin/align_neoantigens_to_IEDB.py b/modules/msk/neoantigenediting/aligntoiedb/resources/usr/bin/align_neoantigens_to_IEDB.py
@@ -47,14 +47,20 @@ def load_blosum62_mat():
 * -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4 -4  1
 """
     amino_acids = "ACDEFGHIKLMNPQRSTVWY"
-    blosum62_mat_str_list = [l.split() for l in raw_blosum62_mat_str.strip().split("\n")]
+    blosum62_mat_str_list = [
+        l.split() for l in raw_blosum62_mat_str.strip().split("\n")
+    ]
     blosum_aa_order = [blosum62_mat_str_list[0].index(aa) for aa in amino_acids]
 
     blosum62_mat = np.zeros((len(amino_acids), len(amino_acids)))
     for i, bl_ind in enumerate(blosum_aa_order):
-        blosum62_mat[i] = np.array([int(x) for x in blosum62_mat_str_list[bl_ind + 1][1:]])[blosum_aa_order]
+        blosum62_mat[i] = np.array(
+            [int(x) for x in blosum62_mat_str_list[bl_ind + 1][1:]]
+        )[blosum_aa_order]
     blosum62 = {
-        (aaA, aaB): blosum62_mat[i, j] for i, aaA in enumerate(amino_acids) for j, aaB in enumerate(amino_acids)
+        (aaA, aaB): blosum62_mat[i, j]
+        for i, aaA in enumerate(amino_acids)
+        for j, aaB in enumerate(amino_acids)
     }
     return blosum62
 
@@ -226,7 +232,9 @@ def load_epitopes(iedbfasta):
         pjson = json.load(f)
     patient = pjson["patient"]
     neoantigens = pjson["neoantigens"]
-    peptides = set([("_".join(neo["id"].split("_")[:-1]), neo["sequence"]) for neo in neoantigens])
+    peptides = set(
+        [("_".join(neo["id"].split("_")[:-1]), neo["sequence"]) for neo in neoantigens]
+    )
     pepseq2pepid = defaultdict(set)
     for pep_id, pep_seq in peptides:
         pepseq2pepid[pep_seq].add(pep_id)
@@ -251,5 +259,7 @@ def load_epitopes(iedbfasta):
             "Alignment_score",
         ]
     else:
-        aln_data = pd.DataFrame(columns=["Peptide_ID", "Peptide", "Epitope_ID", "Alignment_score"])
+        aln_data = pd.DataFrame(
+            columns=["Peptide_ID", "Peptide", "Epitope_ID", "Alignment_score"]
+        )
     aln_data.to_csv("iedb_alignments_" + patient + ".txt", sep="\t", index=False)
diff --git a/modules/msk/neoantigenediting/computefitness/resources/usr/bin/EpitopeDistance.py b/modules/msk/neoantigenediting/computefitness/resources/usr/bin/EpitopeDistance.py
@@ -11,7 +11,6 @@
 import os
 
 
-# %
 class EpitopeDistance(object):
     """Base class for epitope crossreactivity.
 
@@ -39,7 +38,9 @@ class EpitopeDistance(object):
 
     def __init__(
         self,
-        model_file=os.path.join(os.path.dirname(__file__), "distance_data", "epitope_distance_model_parameters.json"),
+        model_file=os.path.join(
+            os.path.dirname(__file__), "distance_data", "epitope_distance_model_parameters.json"
+        ),
         amino_acids="ACDEFGHIKLMNPQRSTVWY",
     ):
         """Initialize class and compute M_ab."""
@@ -75,5 +76,11 @@ def epitope_dist(self, epiA, epiB):
         """
 
         return sum(
-            [self.d_i[i] * self.M_ab[self.amino_acid_dict[epiA[i]], self.amino_acid_dict[epiB[i]]] for i in range(9)]
+            [
+                self.d_i[i]
+                * self.M_ab[
+                    self.amino_acid_dict[epiA[i]], self.amino_acid_dict[epiB[i]]
+                ]
+                for i in range(9)
+            ]
         )
diff --git a/modules/msk/neoantigenediting/computefitness/resources/usr/bin/compute_fitness.py b/modules/msk/neoantigenediting/computefitness/resources/usr/bin/compute_fitness.py
@@ -60,7 +60,9 @@ def fill_up_clone_neoantigens(tree, mut2neo):
     while len(nodes) > 0:
         node = nodes[0]
         nodes = nodes[1:]
-        node["neoantigens"] = [neo["id"] for mid in node["all_mutations"] for neo in mut2neo[mid]]
+        node["neoantigens"] = [
+            neo["id"] for mid in node["all_mutations"] for neo in mut2neo[mid]
+        ]
         node["neoantigen_load"] = len(node["neoantigens"])
         node["NA_Mut"] = sum([len(mut2neo[mid]) > 0 for mid in node["all_mutations"]])
         if "children" in node:
@@ -157,7 +159,9 @@ def compute_effective_sample_size(sample_json):
         for clone_muts, X in zip(clone_muts_list, freqs):
             for mid in clone_muts:
                 mut_freqs[mid].append(X)
-    avev = np.mean([np.var(mut_freqs[mid]) if mut_freqs[mid] else 0 for mid in mut_freqs])
+    avev = np.mean(
+        [np.var(mut_freqs[mid]) if mut_freqs[mid] else 0 for mid in mut_freqs]
+    )
     n = 1 / avev
     return n
 

diff --git a/modules/msk/neoantigenutils/formatnetmhcpan/main.nf b/modules/msk/neoantigenutils/formatnetmhcpan/main.nf
@@ -36,10 +36,10 @@ process NEOANTIGENUTILS_FORMATNETMHCPAN {
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def netmhcOutputType = meta.typeMut ? "MUT": "WT"
+    def netmhcOutputFrom = meta.fromStab ? "STAB": "PAN"
     """
-
-        touch ${prefix}.MUT.tsv
-        touch ${prefix}.WT.tsv
+        touch ${prefix}.${netmhcOutputType}.${netmhcOutputFrom}.tsv
         cat <<-END_VERSIONS > versions.yml
         "${task.process}":
             formatNetmhcpanOutput: \$(echo \$(format_netmhcpan_output.py -v))

diff --git a/modules/msk/neoantigenutils/formatnetmhcpan/resources/usr/bin/format_netmhcpan_output.py b/modules/msk/neoantigenutils/formatnetmhcpan/resources/usr/bin/format_netmhcpan_output.py
@@ -71,21 +71,27 @@ def netMHCpan_out_reformat(netMHCpanoutput, mut, stab, prefix):
 
 def parse_args():
     parser = argparse.ArgumentParser(description="Process input files and parameters")
-    parser.add_argument("--netMHCpan_output", required=True, help="Path to netMHC output")
+    parser.add_argument(
+        "--netMHCpan_output", required=True, help="Path to netMHC output"
+    )
     parser.add_argument("--type_MUT", action="store_true", help="Output is a MUT type")
     parser.add_argument(
         "--from_STAB",
         action="store_true",
         help="Output is from netmhcstab",
     )
     parser.add_argument("--id", required=True, help="Prefix to label the output")
-    parser.add_argument("-v", "--version", action="version", version="%(prog)s {}".format(VERSION))
+    parser.add_argument(
+        "-v", "--version", action="version", version="%(prog)s {}".format(VERSION)
+    )
 
     return parser.parse_args()
 
 
 def main(args):
-    netMHCpan_out_reformat(args.netMHCpan_output, args.type_MUT, args.from_STAB, args.id)
+    netMHCpan_out_reformat(
+        args.netMHCpan_output, args.type_MUT, args.from_STAB, args.id
+    )
 
 
 if __name__ == "__main__":

diff --git a/modules/msk/neoantigenutils/formatnetmhcpan/tests/main.nf.test.snap b/modules/msk/neoantigenutils/formatnetmhcpan/tests/main.nf.test.snap
@@ -30,11 +30,7 @@
                 ]
             }
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-13T12:57:40.919561"
+        "timestamp": "2024-07-30T13:46:27.878268"
     },
     "neoantigenutils_formatnetmhcpan - output(MUT,netmhcpan) - tsv - stub": {
         "content": [
@@ -46,10 +42,7 @@
                             "typeMut": true,
                             "fromStab": false
                         },
-                        [
-                            "test.MUT.tsv:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "test.WT.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
-                        ]
+                        "test.MUT.PAN.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "1": [
@@ -62,22 +55,15 @@
                             "typeMut": true,
                             "fromStab": false
                         },
-                        [
-                            "test.MUT.tsv:md5,d41d8cd98f00b204e9800998ecf8427e",
-                            "test.WT.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
-                        ]
+                        "test.MUT.PAN.tsv:md5,d41d8cd98f00b204e9800998ecf8427e"
                     ]
                 ],
                 "versions": [
                     "versions.yml:md5,2c02f5f3103ee1532c27f7f3b873a578"
                 ]
             }
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-13T12:58:01.264912"
+        "timestamp": "2024-07-30T13:47:05.72509"
     },
     "neoantigenutils_formatnetmhcpan - output(WT,netmhcpan) - tsv": {
         "content": [
@@ -110,11 +96,7 @@
                 ]
             }
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-13T12:57:46.381516"
+        "timestamp": "2024-07-30T13:46:37.183992"
     },
     "neoantigenutils_formatnetmhcpan - output(MUT,netmhcpanstab) - tsv": {
         "content": [
@@ -147,11 +129,7 @@
                 ]
             }
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-13T12:57:51.691253"
+        "timestamp": "2024-07-30T13:46:47.110076"
     },
     "neoantigenutils_formatnetmhcpan - output(WT,netmhcpanstab) - tsv": {
         "content": [
@@ -184,10 +162,6 @@
                 ]
             }
         ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "24.04.2"
-        },
-        "timestamp": "2024-06-13T12:57:56.882818"
+        "timestamp": "2024-07-30T13:46:56.841519"
     }
 }