geney 1.3.43__py2.py3-none-any.whl → 1.3.45__py2.py3-none-any.whl

geney/SeqMats.py

@@ -311,8 +311,8 @@ class SeqMat:
         ### NEEDS some work to make sure that mutations can continue being added without issue...
 
         # Ensure strand compatibility
-        if not self._is_same_strand(mut):
-            raise ValueError("Mutation and sequence are not on the same strand.")
+        # if not self._is_same_strand(mut):
+        #     raise ValueError("Mutation and sequence are not on the same strand.")
 
         # something to make sure the mutation is contained as one deletion, insertion, or snp or indel
         ref_seqmat = self.seqmat.copy()
@@ -351,6 +351,9 @@ class SeqMat:
         return SeqMat(ref_seqmat)
 
     def orf_seqmat(self, tis_index):
+        if tis_index not in self.indices:
+            return SeqMat.from_seq({'seq': ''})
+
         temp = self.seqmat[:, self._rel_index(tis_index):]
         temp = temp[:, temp[0, :] != 5]
         temp = SeqMat(temp)  # .drop_indices()
@@ -362,6 +365,7 @@ class SeqMat:
         else:
             stop_index = len(raw_seq)
         end_index = stop_index
+        assert end_index % 3 == 0, f"{end_index} is not a multiple of 3"
         return SeqMat(temp.seqmat[:, :end_index])
 
     def translate(self, tis_index):

geney/oncosplice.py

@@ -305,13 +305,18 @@ def OncospliceAnnotator(reference_transcript, variant_transcript, mut, ref_attri
 
 
 def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_required=False, primary_transcript=False,
-               window_length=13, organism='hg38', splicing_engine=None, splicing_db=None, verbose=False):
+               window_length=13, organism='hg38', splicing_engine=None, splicing_db=None, verbose=False,
+               tis_engine=None, tis_db=None):
+
     gene = Gene.from_file(mut_id.split(':')[0], organism=organism)
     reference_gene_proteins = {
         transcript.generate_pre_mrna().generate_mature_mrna().generate_protein().protein: transcript.transcript_id for
         transcript in gene if transcript.transcript_biotype == 'protein_coding'}
 
     mutations = [MutSeqMat.from_mutid(m) for m in mut_id.split('|')]
+    if gene.rev:
+        mutations = [m.reverse_complement(inplace=True) for m in mutations[::-1]]
+
     results = []
     for reference_transcript in tqdm(gene, desc=f'Processing {mut_id}...'):
         if (cons_required and not reference_transcript.cons_available) or (
@@ -325,6 +330,7 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
         center = np.mean([m.indices[0] for m in current_mutations]) // 1
 
         mutated_transcript = reference_transcript.clone()
+
         for mutation in current_mutations:
             mutated_transcript.mutate(mutation, inplace=True)
 
@@ -361,6 +367,18 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
             mutated_transcript.donors = new_boundaries['donors']
             mutated_transcript.generate_mature_mrna().generate_protein()
 
+            ### Experimental
+            # mutated_transcript.generate_mature_mrna()
+            # if tis_engine is None:
+            #     tis_candidates = [(mutated_transcript.tis, 1)]
+            # else:
+            #     from tis_utils import tis_predictor
+            #     tis_candidates = tis_predictor(mutated_transcript.mature_mrna)
+            #
+            # for tis_candidate, tis_score in tis_candidates:
+            #     mutated_transcript.generate_protein(tis_candidate)
+            ######
+
             alignment = get_logical_alignment(reference_transcript.protein, mutated_transcript.protein)
             deleted, inserted = find_indels_with_mismatches_as_deletions(alignment.seqA, alignment.seqB)
             modified_positions = find_modified_positions(len(reference_transcript.protein), deleted, inserted)
@@ -375,6 +393,9 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_require
             report = OncospliceAnnotator(reference_transcript, mutated_transcript, current_mutations[0])
             report['mut_id'] = mut_id
             report['splicing_engine'] = splicing_engine if splicing_engine is not None else 'None'
+            # report['tis_engine'] = tis_engine if tis_engine is not None else 'None'
+            # report['tis_pos'] = tis_candidate
+            # report['tis_score'] = tis_score
             report['oncosplice_score'] = affected_cons_scores
             report['percentile'] = percentile
             report['isoform_id'] = short_hash_of_list(mutated_transcript.exons)

geney/splicing_utils.py

@@ -324,7 +324,7 @@ def find_transcript_missplicing(mut_id, transcript=None, threshold=0.5, engine='
 
 def find_transcript_missplicing_seqs(ref_seq, var_seq, donors, acceptors, threshold=0.5, engine='spliceai'):
     if ref_seq.seq == var_seq.seq:
-        return {'missed_acceptors': {}, 'missed_donors': {}, 'discovered_acceptors': {}, 'discovered_donors': {}}
+        return Missplicing({'missed_acceptors': {}, 'missed_donors': {}, 'discovered_acceptors': {}, 'discovered_donors': {}})
 
     ref_seq_acceptor_probs, ref_seq_donor_probs = run_splicing_engine(ref_seq.seq, engine)
     mut_seq_acceptor_probs, mut_seq_donor_probs = run_splicing_engine(var_seq.seq, engine)

geney/tis_utils.py

@@ -9,7 +9,16 @@ from geney import config
 p = PairwiseAligner()
 
 
-def find_tis(ref_seq, mut_seq, left_context=100, right_context=102):
+def find_tis(reference_mrna, mutated_mrna, ref_tis_pos, left_context=100, right_context=102):
+    '''
+        mature_mrna: row 0 --> encoded nucleotides
+                     row 1 --> genomic indices
+                     row 2 --> super positions (incase of insertions or deletions
+                                row1+row2 = conhesive & monotonic genomic indices
+                     row 3 --> binary mutated position or not
+        mature_mrna.seq
+        mature_mrna.indices
+    '''
     tis_coords = ref_seq.mature_mrna.asymmetric_indices(ref_seq.TIS, left_context=0, right_context=3)
     ref_seq, mut_seq = ref_seq.mature_mrna, mut_seq.mature_mrna
 

{geney-1.3.43.dist-info → geney-1.3.45.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.3.43
+Version: 1.3.45
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.3.43.dist-info → geney-1.3.45.dist-info}/RECORD

@@ -1,6 +1,6 @@
 geney/Fasta_segment.py,sha256=99HxNGNh_MfdVW6hhtlb1vOn7eSmT7oFoEfHDFMxG8w,11275
 geney/Gene.py,sha256=nMWJjoQaiVFm2iRjoiq7ghZqnXtW0tJDcq2S0AyOIvY,6883
-geney/SeqMats.py,sha256=aLpqd7RJSEU07jdPXpbtZPeb2D9BxrZuW6BTkcXpNE4,18819
+geney/SeqMats.py,sha256=hQcEYTcFm06g4dGJf25Lvo_xCHsj0-GGhP-O2fPrBlE,18987
 geney/Transcript.py,sha256=CpfxYkuCwFILozrtLuiWnlr1mRnMKn4o84HVJislgYs,14499
 geney/__init__.py,sha256=eBdDl42N6UhcYeZDjOnv199Z88fI5_8Y6xW8447OKXM,755
 geney/_mutation_utils.py,sha256=dHssUsnii_mf-wuRoMmF13UlD7k3ml_VwQMItTYnXpU,1132
@@ -11,21 +11,21 @@ geney/graphic_utils.py,sha256=oMsBpB9YeEn96gGpKh4MmtagJffWZbk-xPrIwHvkFhA,11016
 geney/gtex_utils.py,sha256=asL2lHyU5KsbWpV096vkf1Ka7hSo_RRfZqw7p5nERmE,1919
 geney/immune_utils.py,sha256=ZRni5ttrhpYBnmNr0d0ZatIbNPYs4nmQuoUO00SpsS4,5271
 geney/mutation_utils.py,sha256=C_kv2MB_L8LlhX3W2ooXjJ3uDoJ8zX1WeDtZKoBZJkI,1547
-geney/oncosplice.py,sha256=6s0aW6vXtD-z7yToFBcFCS5M_npoQe4tgdf4g5TuR2o,23465
+geney/oncosplice.py,sha256=q1W8k4nvRzQPH7LZsefTky6Nw2Kmx-DDXZ_UCty0Wog,24299
 geney/pangolin_utils.py,sha256=i5j5vEMCWOTIa1mRP2377BAhlUFZjHBzTQBips4lA_4,2934
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=wzb3PX5it5bpIFQvcxyzlxfhoJTbHHbsjg0rzh05iVs,19753
 geney/spliceai_utils.py,sha256=PFIhTK8Ihrj-cv5tgRN0UFPYEmC4uxtqXSP9bBLnZRM,3077
-geney/splicing_utils.py,sha256=TQsRhEegW4SW6t7dghHQ5vGgn9WdioTcai6EzPPcdKM,38485
+geney/splicing_utils.py,sha256=WflxRPfc4DzeHuYOZqjpa-YD1nuZzs7h_WCsv-LX87A,38498
 geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
 geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
-geney/tis_utils.py,sha256=2makfGfVlDFVIbxzXE85AY9jmAjcNmxyIAxjvkRA5LY,7396
+geney/tis_utils.py,sha256=la0CZroaKe5RgAyFd4Bf_DqQncklWgAY2823xVst98o,7813
 geney/utils.py,sha256=EsKvBM-Nz2a3_4ZAhF4Dxd4PwT7_6YYKpxEN4LLgg10,2174
 geney/translation_initiation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 geney/translation_initiation/tis_utils.py,sha256=AF3siFjuQH-Rs44EV-80zHdbxRMvN4woLFSHroWIETc,4448
 geney/translation_initiation/resources/kozak_pssm.json,sha256=pcd0Olziutq-6H3mFWDCD9cujQ_AlZO-iiOvBl82hqE,1165
 geney/translation_initiation/resources/tis_regressor_model.joblib,sha256=IXb4DUDhJ5rBDKcqMk9zE3ECTZZcdj7Jixz3KpoZ7OA,2592025
-geney-1.3.43.dist-info/METADATA,sha256=kqekeyuXWKLb40n_ShUhUqBqqZAyIob5vEDY8dgiSxI,990
-geney-1.3.43.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
-geney-1.3.43.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.3.43.dist-info/RECORD,,
+geney-1.3.45.dist-info/METADATA,sha256=5YI3G03swzoNav06ijsq6XG8aLMzWlSCEZnY7Y4b3MM,990
+geney-1.3.45.dist-info/WHEEL,sha256=AHX6tWk3qWuce7vKLrj7lnulVHEdWoltgauo8bgCXgU,109
+geney-1.3.45.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.3.45.dist-info/RECORD,,