Merge pull request #834 from uclahs-cds/czhu-add-fuzz-test-log

Add fuzz test log
uclahs-cds · Dec 23, 2023 · 18e8cda · 18e8cda
2 parents e7a4096 + eea7e6d
commit 18e8cda
Show file tree

Hide file tree

Showing 10 changed files with 31 additions and 34 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -10,7 +10,7 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
 
 ## [Unreleased]
 
-## [1.2.2] - 2023-10-23
+## [1.2.2] - 2023-12-22
 
 ### Fixed:
 

diff --git a/docs/files/fuzz_test_history.tsv b/docs/files/fuzz_test_history.tsv
@@ -26,3 +26,6 @@ v1.2.0	aca093e	2023-09-21	comprehensive	184432	1	0	0:00:00.348405	1.459285447300
 v1.2.0	8bb50b1	2023-10-03	snv	298799	0	0	0:00:00.148556	0.3663789187817885	0:00:56.622936	118.54456105047444
 v1.2.0	8bb50b1	2023-10-03	indel	295046	0	0	0:00:00.200385	0.41735107691824685	0:00:42.615877	100.6975160415037
 v1.2.0	8bb50b1	2023-10-03	comprehensive	562642	0	0	0:00:00.360436	1.536579515902589	0:00:41.751076	182.56285717474975
+v1.2.1	e7a4096	2023-11-28	snv	277035	0	0	0:00:00.138178	0.36248703508333757	0:00:56.331649	118.07408019871977
+v1.2.1	e7a4096	2023-11-28	indel	275106	0	0	0:00:00.196090	0.41617068589153344	0:00:41.637490	99.04928608751558
+v1.2.1	e7a4096	2023-11-28	comprehensive	522929	0	0	0:00:00.378236	15.50100807513127	0:00:41.256473	179.70483365195142
diff --git a/moPepGen/aa/AminoAcidSeqRecord.py b/moPepGen/aa/AminoAcidSeqRecord.py
@@ -412,8 +412,8 @@ def update_peptides(peptide):
 
 class AminoAcidSeqRecordWithCoordinates(AminoAcidSeqRecord):
     """ Amino acid sequence record with coordinates """
-    def __init__(self, seq:Seq, locations:List[MatchedLocation],
-            *args, orf:FeatureLocation=None, **kwargs ):
+    def __init__(self, seq:Seq, *args,
+            locations:List[MatchedLocation]=None, orf:FeatureLocation=None, **kwargs ):
         """ Constract a DNASeqRecordWithCoordinates object.
 
         Args:
@@ -423,7 +423,7 @@ def __init__(self, seq:Seq, locations:List[MatchedLocation],
             orf (FeatureLocation): The open reading frame start and end.
         """
         super().__init__(seq=seq, *args, **kwargs)
-        self.locations = locations
+        self.locations = locations or []
         # query index
         self.orf = orf
 

diff --git a/moPepGen/dna/DNASeqRecord.py b/moPepGen/dna/DNASeqRecord.py
@@ -277,8 +277,8 @@ class DNASeqRecordWithCoordinates(DNASeqRecord):
             sequence is aligned tp.
         orf (FeatureLocation): The open reading frame start and end.
     """
-    def __init__(self, seq:Seq, locations:List[MatchedLocation],
-            *args, orf:FeatureLocation=None, selenocysteine:List[FeatureLocation]=None,
+    def __init__(self, seq:Seq, *args, locations:List[MatchedLocation]=None,
+            orf:FeatureLocation=None, selenocysteine:List[FeatureLocation]=None,
             **kwargs,):
         """ Constract a DNASeqRecordWithCoordinates object.
 
@@ -289,7 +289,7 @@ def __init__(self, seq:Seq, locations:List[MatchedLocation],
             orf (FeatureLocation): The open reading frame start and end.
         """
         super().__init__(seq=seq, *args, **kwargs)
-        self.locations = locations
+        self.locations = locations or []
         # query index
         self.orf = orf
         self.selenocysteine = selenocysteine or []

diff --git a/moPepGen/fake.py b/moPepGen/fake.py
@@ -551,10 +551,9 @@ def fake_transcript_model(n_exons:int, is_coding:bool, is_selenoprotein:bool,
         attributes['tag'].append('mrna_end_NF')
     for i in range(n_exons):
         exon_len = random.randint(min_exon_size, max_exon_size)
-        loc = FeatureLocation(start=offset, end=offset + exon_len, seqname=chrom)
+        loc = FeatureLocation(start=offset, end=offset + exon_len, seqname=chrom, strand=strand)
         exon = GTFSeqFeature(
-            location=loc, strand=strand, type='exon', id=tx_id,
-            attributes=attributes, chrom=chrom
+            location=loc, type='exon', id=tx_id, attributes=attributes, chrom=chrom
         )
         exon_set.append(exon)
         if is_coding:
@@ -586,10 +585,9 @@ def fake_transcript_model(n_exons:int, is_coding:bool, is_selenoprotein:bool,
             else:
                 cds_end = offset + exon_len
 
-            loc = FeatureLocation(start=cds_start, end=cds_end, seqname=chrom)
+            loc = FeatureLocation(start=cds_start, end=cds_end, seqname=chrom, strand=strand)
             cds = GTFSeqFeature(
-                location=loc, strand=strand, type='CDS', id=tx_id,
-                attributes=attributes, chrom=chrom
+                location=loc, type='CDS', id=tx_id, attributes=attributes, chrom=chrom
             )
             cds_set.append(cds)
 
@@ -661,12 +659,12 @@ def fake_transcript_model(n_exons:int, is_coding:bool, is_selenoprotein:bool,
 
             if strand == 1:
                 sec_pos = sec_pos_cds - k + cds.location.start
-                loc = FeatureLocation(sec_pos, sec_pos + 3)
+                loc = FeatureLocation(sec_pos, sec_pos + 3, strand=strand)
             else:
                 sec_pos = cds.location.end - (sec_pos_cds - k)
-                loc = FeatureLocation(sec_pos - 3, sec_pos)
+                loc = FeatureLocation(sec_pos - 3, sec_pos, strand=strand)
             sec = GTFSeqFeature(
-                location=loc, strand=strand, type='selenocysteine', id=tx_id,
+                location=loc, type='selenocysteine', id=tx_id,
                 attributes=attributes, chrom=chrom
             )
             sec_set.append(sec)
@@ -677,11 +675,10 @@ def fake_transcript_model(n_exons:int, is_coding:bool, is_selenoprotein:bool,
         if cds_set[0].location.start != exon_set[0].location.start:
             loc = FeatureLocation(
                 start=exon_set[0].location.start, end=cds_set[0].location.start,
-                seqname=chrom
+                seqname=chrom, strand=strand
             )
             utr = GTFSeqFeature(
-                location=loc, strand=strand, type='UTR', id=tx_id,
-                attributes=attributes, chrom=chrom
+                location=loc, type='UTR', id=tx_id, attributes=attributes, chrom=chrom
             )
             utr_set.append(utr)
             if strand == 1:
@@ -692,11 +689,10 @@ def fake_transcript_model(n_exons:int, is_coding:bool, is_selenoprotein:bool,
         if cds_set[-1].location.end != exon_set[-1].location.end:
             loc = FeatureLocation(
                 start=cds_set[-1].location.end, end=exon_set[-1].location.end,
-                seqname=chrom
+                seqname=chrom, strand=strand
             )
             utr = GTFSeqFeature(
-                location=loc, strand=strand, type='UTR', id=tx_id,
-                attributes=attributes, chrom=chrom
+                location=loc, type='UTR', id=tx_id, attributes=attributes, chrom=chrom
             )
             utr_set.append(utr)
             if strand == 1:
@@ -705,12 +701,11 @@ def fake_transcript_model(n_exons:int, is_coding:bool, is_selenoprotein:bool,
                 five_utr_set.append(utr)
 
     loc = FeatureLocation(
-        start=exon_set[0].location.start,
-        end=exon_set[-1].location.end,
-        seqname=chrom
+        start=exon_set[0].location.start, end=exon_set[-1].location.end,
+        seqname=chrom, strand=strand
     )
     transcript = GTFSeqFeature(
-        location=loc, strand=strand, type='transcript', id=tx_id,
+        location=loc, type='transcript', id=tx_id,
         attributes=attributes, chrom=chrom
     )
 
@@ -761,7 +756,6 @@ def fake_genomic_annotation(n_genes:int, chrom:str, min_exons:int, max_exons:int
         loc = FeatureLocation(start=gene_start, end=gene_end, seqname=chrom)
         gene_model = GeneAnnotationModel(
             location=loc, chrom=chrom, transcripts=[tx_id], type='gene',
-            strand=strand,
             attributes=copy.deepcopy(tx_model.transcript.attributes)
         )
         anno.genes[gene_id] = gene_model

diff --git a/moPepGen/util/brute_force.py b/moPepGen/util/brute_force.py
@@ -937,7 +937,7 @@ def call_peptides_main(self, variants:seqvar.VariantRecordPool,
 
         sec_positions = [] if is_circ_rna else \
             self.get_sec_positions(variant_coordinates)
-        variant_effects = self.check_variant_effect(seq, variant_coordinates)
+        variant_effects = self.check_variant_effect(str(seq), variant_coordinates)
         stop_lost, stop_gain, silent_mutation = variant_effects
 
         if not (is_coding and is_mrna_end_nf):

diff --git a/test/files/annotation_gene.idx b/test/files/annotation_gene.idx
@@ -1,7 +1,7 @@
 ##source=GENCODE
 ##python=3.8.17
 ##moPepGen=1.2.0
-##biopython=1.81
+##biopython=1.82
 ENSG00000128408.9	0	174	ENST00000614167.2,ENST00000614168.2
 ENSG00000244486.9	12491	12694	ENST00000622235.5
 ENSG00000099949.21	24586	24955	ENST00000642151.1

diff --git a/test/files/annotation_tx.idx b/test/files/annotation_tx.idx
@@ -1,7 +1,7 @@
 ##source=GENCODE
 ##python=3.8.17
 ##moPepGen=1.2.0
-##biopython=1.81
+##biopython=1.82
 ENST00000614167.2	174	7260	True
 ENST00000614168.2	7260	12491	True
 ENST00000622235.5	12694	24586	True

diff --git a/test/unit/__init__.py b/test/unit/__init__.py
@@ -115,7 +115,7 @@ def create_three_frame_tvg(nodes:Dict[int,list], seq:str, graph_id:str='') -> Ty
     """
     node_list:Dict[int,svgraph.TVGNode] = {}
     raw_seq = Seq(seq)
-    seq = dna.DNASeqRecordWithCoordinates(raw_seq, [])
+    seq = dna.DNASeqRecordWithCoordinates(raw_seq, locations=[])
     graph = svgraph.ThreeFrameTVG(seq, _id=graph_id)
     graph.cleavage_params = params.CleavageParams()
     for edge in copy.copy(graph.root.out_edges):
@@ -220,7 +220,7 @@ def create_three_frame_tvg(nodes:Dict[int,list], seq:str, graph_id:str='') -> Ty
             )
             seq_locations.append(seq_location)
 
-        seq = dna.DNASeqRecordWithCoordinates(_seq, seq_locations)
+        seq = dna.DNASeqRecordWithCoordinates(_seq, locations=seq_locations)
         node = svgraph.TVGNode(seq, variants,
             reading_frame_index=orf_idx, subgraph_id=graph.id)
         node_list[key] = node

diff --git a/test/unit/test_cvg.py b/test/unit/test_cvg.py
@@ -27,7 +27,7 @@ def test_init_three_frames(self):
         circ_record = create_circ_model('ENST0001', [(0,8),(10,18)], 'CIRCXXX')
         seq = Seq('AATTGGCCCCGGTTAA')
         locations = []
-        seq = dna.DNASeqRecordWithCoordinates(seq, locations)
+        seq = dna.DNASeqRecordWithCoordinates(seq, locations=locations)
         graph = svgraph.ThreeFrameCVG(seq, 'ENST0001', circ_record=circ_record)
         graph.init_three_frames()
         for root in graph.reading_frames:
@@ -40,7 +40,7 @@ def test_extend_loop(self):
         circ_record = create_circ_model('ENST0001', [(0,8),(10,18)], 'CIRCXXX')
         seq = Seq('AATTGGCCCCGGTTAA')
         locations = []
-        seq = dna.DNASeqRecordWithCoordinates(seq, locations)
+        seq = dna.DNASeqRecordWithCoordinates(seq, locations=locations)
         graph = svgraph.ThreeFrameCVG(seq, 'ENST0001', circ_record=circ_record)
         graph.init_three_frames()
         graph.extend_loop()