IH 25DEC2023 pulled in upstream.

ijhoskins · Dec 25, 2023 · c3e5c50 · c3e5c50
2 parents 0847607 + aa7eeb7
commit c3e5c50
Show file tree

Hide file tree

Showing 6 changed files with 19 additions and 8 deletions.
diff --git a/CHANGES.txt b/CHANGES.txt
@@ -48,3 +48,7 @@ Release Summary:
 	Ensure HGVS annotations use uppercase bases to ensure compatibility with MAVEdb.
 
 	Fixed run_mave_hgvs_annot.py script to require target BED and fix bug in deletion-insertion MAVE-HGVS string.
+
+1.1.4-dev, December 25, 2023
+	Fixed bug in HGVS annotations for out-of-frame duplications > 1 nt.
+
diff --git a/README.md b/README.md
@@ -74,7 +74,7 @@ The 'sim' workflow outputs paired FASTQs, a realigned BAM file, and a truth VCF
 
 ### Run 'call'
 
-Support exists for calling SNPs/SNVs, MNPs/MNVs, insertions, and deletions. Complex InDels are not supported (e.g. delete a codon, insert a nt).
+Support exists for calling SNPs/SNVs, MNPs/MNVs, insertions, and deletions. Multi-codon changes and complex InDels are not supported (e.g. delete a codon, insert a nt).
 
 Run 'call' on the simulated data by specifying an Ensembl transcript/gene ID and the directory containing curated reference files.
 ```
@@ -112,6 +112,15 @@ To run unit tests, execute the following from the satmut\_utils repository:
 
 ```nose2 -q```
 
+## Accessory scripts
+
+Two command-line interfaces are provided to enable pre-processing of reads prior to  satmut_utils 'sim':
+
+1. satmut\_trim
+2. satmut\_align
+
+satmut\_trim is a wrapper around cutadapt, and satmut\_align a wrapper around bowtie2.  satmut\_align should be used to generate the BAM file accepted by 'sim'. If reads have been aligned with some other method, there is no guarantee 'sim' will complete without error, as alignment tags output by bowtie2 are required for 'sim' (MD, NM).
+
 ## Citation
 
 If you use satmut\_utils, please cite the following paper:

diff --git a/docs/satmut_utils_manual.md b/docs/satmut_utils_manual.md
@@ -201,7 +201,7 @@ It is recommended that a new output directory is created for each job. Default i
 ```OUTPUT_DIR="/tmp/satmut_utils_test"```
 
 Additionally, the user can set a directory for temporary files by setting an environment variable $SCRATCH. If this variable is not set, temporary files are written to /tmp.
-```export SCRATCH="/tmp/satmut_temp"```
+```export SCRATCH="$(mktemp -d -t satmut_temp)"```
 
 ### 'sim' code examples
 

diff --git a/setup.cfg b/setup.cfg
@@ -1,6 +1,6 @@
 [metadata]
 name = satmut_utils
-version = 1.1.3-dev
+version = 1.1.4-dev
 author = Ian Hoskins
 author_email = [email protected]
 description = Tools for variant simulation and variant calling in paired end, targeted sequencing saturation mutagenesis experiments

diff --git a/src/analysis/coordinate_mapper.py b/src/analysis/coordinate_mapper.py
@@ -137,9 +137,6 @@ class MapperBase(object):
     J_GENE_SEG_ID = "J_gene_segment"
     C_GENE_SEG_ID = "C_gene_segment"
 
-    # Omit transcripts on non-NC contigs
-    CONTIGS_TO_OMIT = re.compile("|".join(["NT", "NW"]))
-
     FEATURES_TO_OMIT = [R_RNA_ID, T_RNA_ID, MI_RNA_ID, SN_RNA_ID, SNO_RNA_ID, NC_RNA_ID, LNC_RNA_ID, TELO_RNA_ID,
                         DLOOP_ID, VAULT_RNA_ID, ANTIS_RNA_ID, Y_RNA, RNASE_MRP_RNA_ID, RNASE_P_RNA_ID, SRP_RNA_ID,
                         PROMOTER_ID, ENHANCER_ID, REPEAT_ID, REGION_ID, SEQ_FEAT_ID, MATCH_ID, CDNA_MATCH_ID,
@@ -640,6 +637,7 @@ def _annotate_snp_hgvs(self, trx_id, location, pos, ref, alt, cds_start_offset,
         elif location == self.CDS_ID:
             hgvs_nt = "%s:c.%i%s>%s" % (trx_id, start_index + 1, ref, alt)
             hgvs_tx = "%s:r.%i%s>%s" % (trx_id, start_index + 1, su.dna_to_rna(ref), su.dna_to_rna(alt))
+
             if ref_aa == alt_aa:
                 hgvs_pro = "p.%s%i=" % (AA_MAP[ref_aa], aa_pos)
             else:
@@ -997,7 +995,7 @@ def _annotate_dup_hgvs(self, trx_id, location, pos, alt_len, cds_start_offset, c
                 else:
                     # Frameshift dup
                     ref_aa, aa_pos = self._get_fs_first_alt_aa(alt_aas, cds_stop_offset, start_index, ref_codon_dict)
-                    hgvs_pro = "p.%s%ifs" % (AA_MAP[translate(ref_aa)], aa_pos)
+                    hgvs_pro = "p.%s%ifs" % (AA_MAP[ref_aa], aa_pos)
         else:
             raise NotImplementedError
 

diff --git a/src/satmut_utils/satmut_utils.py b/src/satmut_utils/satmut_utils.py
@@ -23,7 +23,7 @@
 __author__ = "Ian Hoskins"
 __credits__ = ["Ian Hoskins"]
 __license__ = "GPLv3"
-__version__ = "1.1.3-dev"
+__version__ = "1.1.4-dev"
 __maintainer__ = "Ian Hoskins"
 __email__ = "[email protected]"
 __status__ = "Development"