bumped requirents and fixed tests

hiyama341 · Oct 24, 2024 · 29e49fe · 29e49fe
1 parent 70b09f5
commit 29e49fe
Show file tree

Hide file tree

Showing 4 changed files with 351 additions and 227 deletions.
diff --git a/requirements.txt b/requirements.txt
@@ -1,9 +1,9 @@
 # This file is needed for READtheDOCS and GitHub actions- all requirements are installed in the setup.py
-pydna==5.2.0 ## TODO There is a new version of pydna 6.0.0 but has induced breaking changes
+pydna>=5.2.0 ## TODO There is a new version of pydna 6.0.0 but has induced breaking changes
 pandas>=1.3.0
 benchlingapi>=2.1.12
 numpy>=1.21.0
-biopython==1.80    # TODO There is a new version of Biopython 1.82 but has induced breaking changes
+biopython>=1.82    # TODO There is a new version of Biopython 1.82 but has induced breaking changes
 python-dotenv>=0.20.0
 openpyxl>=3.0.9
 wheel>=0.37.1

diff --git a/teemi/design/cloning.py b/teemi/design/cloning.py
@@ -76,14 +76,12 @@ def CAS9_cutting(gRNA_record, background_record):
     dw.name = "DW" + "_" + gRNA_record.name + "_" + background_record.name
 
     up_feature = Bio.SeqFeature.SeqFeature(
-        Bio.SeqFeature.FeatureLocation(0, len(up)), type="misc_feature", strand=+1
-    )
+        Bio.SeqFeature.FeatureLocation(0, len(up)), type="misc_feature")
     up_feature.qualifiers["label"] = up.name
     up.features.append(up_feature)
 
     dw_feature = Bio.SeqFeature.SeqFeature(
-        Bio.SeqFeature.FeatureLocation(0, len(dw)), type="misc_feature", strand=+1
-    )
+        Bio.SeqFeature.FeatureLocation(0, len(dw)), type="misc_feature")
     dw_feature.qualifiers["label"] = dw.name
     dw.features.append(dw_feature)
 
@@ -352,7 +350,7 @@ def casembler(
         assembly.name = assembly_names[int_no]
 
         assembly_feat = Bio.SeqFeature.SeqFeature(
-            Bio.SeqFeature.FeatureLocation(0, len(assembly), strand=1),
+            Bio.SeqFeature.FeatureLocation(0, len(assembly)),
             type="misc_feature",
         )
         assembly_feat.qualifiers["name"] = site_names[int_no]
@@ -450,9 +448,7 @@ def seq_to_annotation(
 
     feature = Bio.SeqFeature.SeqFeature(
         Bio.SeqFeature.FeatureLocation(start_location, end_location),
-        type=type_name,
-        strand=strand,
-    )
+        type=type_name)
 
     feature.qualifiers["label"] = seq_record_from.id
     seq_record_onto.features.append(feature)
@@ -532,8 +528,7 @@ def add_feature_annotation_to_seqrecord(
     None
     """
     bio_feature = Bio.SeqFeature.SeqFeature(
-        Bio.SeqFeature.FeatureLocation(0, len(sequence)), type=type_name, strand=strand
-    )
+        Bio.SeqFeature.FeatureLocation(0, len(sequence)), type=type_name)
 
     # label
     sequence.features.append(bio_feature)
@@ -577,83 +572,3 @@ def find_all_occurrences_of_a_sequence(
         return len(matches_watson)
 
 
-# def UPandDW(strain, isite_name, path_to_gRNA_table="../data/raw/gRNAtable.csv"):
-#     """Finds upstream and downstream sequences based on genome and site name.
-
-#     Parameters
-#     ----------
-#     strain : str
-#         name of the strain eg. CENPK113-7d
-#         (you should specify path to the chromosome)
-
-#     isite_name : str
-#         a string of the site chomosomal site you want to retrieve
-
-#     Returns
-#     -------
-#     UP_sites : list
-#         list of pydna.dseqrecord or pydna.amplicon.Amplicon
-
-#     DW_sites : list
-#         list of pydna.dseqrecord or pydna.amplicon.Amplicon
-
-#     """
-
-#     # load lookup table
-#     gRNAtable = pd.read_csv(path_to_gRNA_table, index_col="name")
-
-#     chromosome_no = gRNAtable.loc[isite_name, "chromosome"]
-
-#     # load chromosome
-#     PathToChromosomeSeq = (
-#         "../data/raw/" + strain + "/" + str(chromosome_no).zfill(2) + ".fa"
-#     )
-#     ChromosomeSeq = Bio.SeqIO.read(PathToChromosomeSeq, "fasta").seq
-
-#     # define homology region location with respect to gRNA sequence
-#     # f_hom is the length of the UP homology
-#     # e_hom is the length of the DW homology
-#     # f_dist is distance from end of UP homology to the first base in isite_sequence
-#     # e_dist is distance from end of the isite_sequence to DW homology
-#     f_dist = gRNAtable.loc[isite_name, "f_dist"]
-#     e_dist = gRNAtable.loc[isite_name, "e_dist"]
-#     f_hom = gRNAtable.loc[isite_name, "f_hom"]
-#     e_hom = gRNAtable.loc[isite_name, "e_hom"]
-
-#     isite_sequence = gRNAtable.loc[isite_name, "sequence"]
-#     isite_sequence = Bio.Seq.Seq(isite_sequence)
-
-#     # Determine gRNA sequence strand
-#     gRNA_strand = 1
-#     if ChromosomeSeq.find(isite_sequence) == -1:
-#         print("not on +1")
-#         gRNA_strand = -1
-#         isite_sequence = isite_sequence.reverse_complement()
-#         if ChromosomeSeq.find(isite_sequence) == -1:
-#             print("not on -1")
-#             print("CAN'T FIND THE CUT SITE IN YOUR SEQUENCE")
-
-#     # Locate UP and DW
-#     StartIndex = ChromosomeSeq.find(isite_sequence)
-#     EndIndex = StartIndex
-
-#     UPseq = ChromosomeSeq[StartIndex + f_dist - f_hom : StartIndex + f_dist]
-#     DWseq = ChromosomeSeq[EndIndex + e_dist : EndIndex + e_dist + e_hom]
-
-#     UPrec = Bio.SeqRecord.SeqRecord(UPseq, name=isite_name + "UP")
-#     DWrec = Bio.SeqRecord.SeqRecord(DWseq, name=isite_name + "DW")
-
-#     # Annotate
-#     UP_feature = Bio.SeqFeature.SeqFeature(
-#         Bio.SeqFeature.FeatureLocation(0, len(UPseq)), type="misc_feature", strand=+1
-#     )
-#     UP_feature.qualifiers["label"] = UPrec.name
-#     UPrec.features.append(UP_feature)
-
-#     DW_feature = Bio.SeqFeature.SeqFeature(
-#         Bio.SeqFeature.FeatureLocation(0, len(DWseq)), type="misc_feature", strand=+1
-#     )
-#     DW_feature.qualifiers["label"] = DWrec.name
-#     DWrec.features.append(DW_feature)
-
-#     return ([UPrec], [DWrec])
diff --git a/tests/test_cloning.py b/tests/test_cloning.py
@@ -134,9 +134,12 @@ def test_seq_to_annotation():
     # The actual test
     seq_to_annotation(test_sequence, test_plasmid, 'AMPLICON2')
 
-    assert test_plasmid.features[-1].type == 'AMPLICON2'
-    assert test_plasmid.features[-1].location.start.position == 0
-    assert test_plasmid.features[-1].location.end.position == 100
+    ## Assertions to verify the annotation
+    assert test_plasmid.features[-1].type == 'AMPLICON2', "Feature type should be 'AMPLICON2'"
+
+    # Access the start and end positions correctly
+    assert int(test_plasmid.features[-1].location.start) == 0, "Feature start position should be 0"
+    assert int(test_plasmid.features[-1].location.end) == 100, "Feature end position should be 100"
 
 
 def test_casembler():
@@ -205,11 +208,12 @@ def test_crispr_db_break_location():
 
 def test_add_feature_annotation_to_seqrecord(): 
     test_plasmid = SeqIO.read('../teemi/tests/files_for_testing/MIA-HA-1.gb', 'gb')
-    add_feature_annotation_to_seqrecord(test_plasmid,label=f'This a test', strand = 1)
+    add_feature_annotation_to_seqrecord(test_plasmid,label=f'This a test')
 
     assert test_plasmid.features[0].qualifiers['label'] == 'This a test'
-    assert test_plasmid.features[-1].location.start.position == 0
-    assert test_plasmid.features[-1].location.end.position == len(test_plasmid)
+    # Directly use the ExactPosition as an integer
+    assert int(test_plasmid.features[-1].location.start) == 0
+    assert int(test_plasmid.features[-1].location.end) == len(test_plasmid)