geney 1.2.55__py2.py3-none-any.whl → 1.2.57__py2.py3-none-any.whl

geney/oncosplice.py

@@ -9,7 +9,6 @@ from .seqmat_utils import *
 from .mutation_utils import *
 from .tis_utils import find_tis
 
-### Scoring
 def find_continuous_gaps(sequence):
     """Find continuous gap sequences in an alignment."""
     return [(m.start(), m.end()) for m in re.finditer(r'-+', sequence)]
@@ -121,43 +120,6 @@ def transform_conservation_vector(conservation_vector, window=13, factor=4):
     return exp_factors
 
 
-# def find_modified_positions(sequence_length, deletions, insertions, reach_limit=16):
-#     """
-#     Identify unmodified positions in a sequence given deletions and insertions.
-#
-#     :param sequence_length: Length of the sequence.
-#     :param deletions: Dictionary of deletions.
-#     :param insertions: Dictionary of insertions.
-#     :param reach_limit: Limit for considering the effect of insertions/deletions.
-#     :return: Array indicating unmodified positions.
-#     """
-#     unmodified_positions = np.zeros(sequence_length, dtype=float)
-#
-#     for pos, insertion in insertions.items():
-#         # if pos >= sequence_length:
-#         #     pos = sequence_length - 1
-#         #     add_factor = 1
-#
-#         reach = min(len(insertion) // 2, reach_limit)
-#         front_end, back_end = max(0, pos - reach), min(sequence_length - 1, pos + reach)
-#         len_start, len_end = pos - front_end, back_end - pos
-#         try:
-#             gradient_front = np.linspace(0, 1, len_start, endpoint=False)
-#             gradient_back = np.linspace(0, 1, len_end, endpoint=True)[::-1]
-#             combined_gradient = np.concatenate([gradient_front, np.array([1]), gradient_back])
-#             unmodified_positions[front_end:back_end + 1] = combined_gradient
-#
-#         except ValueError as e:
-#             print(
-#                 f"Error: {e} | Lengths: unmodified_positions_slice={back_end - front_end}.")
-#             unmodified_positions[front_end:back_end] = np.zeros(back_end - front_end)
-#
-#     for pos, deletion in deletions.items():
-#         deletion_length = len(deletion)
-#         unmodified_positions[pos:pos + deletion_length] = 1
-#
-#     return unmodified_positions
-
 def find_modified_positions(sequence_length, deletions, insertions, reach_limit=16):
     """
     Identify unmodified positions in a sequence given deletions and insertions.
@@ -251,12 +213,7 @@ def moving_average_conv(vector, window_size, factor=1):
 
     return np.convolve(vector, np.ones(window_size), mode='same') / window_size
 
-
-
-
-
 def find_splice_site_proximity(pos, transcript):
-
     for i, (ex_start, ex_end) in enumerate(transcript.exons):
         if min(ex_start, ex_end) <= pos <= max(ex_start, ex_end):
             return i + 1, None, abs(pos - ex_start), abs(pos - ex_end)
@@ -323,7 +280,7 @@ def summarize_missplicing_event(pes, pir, es, ne, ir):
 
 # Annotating
 def OncospliceAnnotator(reference_transcript, variant_transcript, mut):
-    affected_exon, affected_intron, distance_from_5, distance_from_3 = find_splice_site_proximity(mut.indices[0],
+    affected_exon, affected_intron, distance_from_5, distance_from_3 = find_splice_site_proximity(np.floor(mut.indices[0]),
                                                                                                   reference_transcript)
 
     report = {}
@@ -361,59 +318,60 @@ def OncospliceAnnotator(reference_transcript, variant_transcript, mut):
     return report
 
 
-# def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_required=False, primary_transcript=False, window_length=13, organism='hg38', engine='spliceai', domains=None):
-#     gene = Gene(mut_id.split(':')[0], organism=organism)
-#     reference_gene_proteins = {tid: transcript.generate_pre_mrna().generate_mature_mrna().generate_protein() for tid, transcript in gene.run_transcripts(protein_coding=True)}
-#     mutations = [get_mutation(m, rev=gene.rev) for m in mut_id.split('|')]
-#
-#     results = []
-#     for tid, transcript in gene.run_transcripts(protein_coding=protein_coding, primary_transcript=primary_transcript):
-#         if cons_required and not transcript.cons_available:
-#             continue
-#
-#         if all(mutation not in transcript for mutation in mutations):
-#             # results.append({'transcript_id': transcript.transcript_id})
-#             continue
-#
-#         transcript.generate_pre_mrna()
-#         transcript.cons_vector = transform_conservation_vector(transcript.cons_vector, window=window_length)
-#         transcript.generate_mature_mrna().generate_protein(inplace=True, domains=domains)
-#         ref_protein, cons_vector = transcript.protein, transcript.cons_vector
-#         reference_transcript = copy.deepcopy(transcript)
-#
-#         assert len(ref_protein) == len(cons_vector), f"Protein ({len(ref_protein)}) and conservation vector ({len(cons_vector)}) must be same length. {ref_protein}, \n>{cons_vector}\n>{transcript.cons_seq}"
-#
-#         missplicing = Missplicing(find_transcript_missplicing(transcript, mutations, engine=engine, threshold=splicing_threshold), threshold=splicing_threshold)
-#         for mutation in mutations:
-#             transcript.pre_mrna += mutation
-#
-#         for i, new_boundaries in enumerate(develop_aberrant_splicing(transcript, missplicing.aberrant_splicing)):
-#             transcript.acceptors = new_boundaries['acceptors']
-#             transcript.donors = new_boundaries['donors']
-#             transcript.generate_mature_mrna().generate_protein()
-#
-#             alignment = get_logical_alignment(reference_transcript.protein, transcript.protein)
-#             deleted, inserted = find_indels_with_mismatches_as_deletions(alignment.seqA, alignment.seqB)
-#             modified_positions = find_modified_positions(len(ref_protein), deleted, inserted)
-#             temp_cons = np.convolve(cons_vector * modified_positions, np.ones(window_length)) / window_length
-#             affected_cons_scores = max(temp_cons)
-#             percentile = (
-#                         sorted(cons_vector).index(next(x for x in sorted(cons_vector) if x >= affected_cons_scores)) / len(
-#                     cons_vector))
-#
-#             report = OncospliceAnnotator(reference_transcript, transcript, mutation)
-#             report['mut_id'] = mut_id
-#             report['oncosplice_score'] = affected_cons_scores
-#             report['percentile'] = percentile
-#             report['isoform_id'] = i
-#             report['isoform_prevalence'] = new_boundaries['path_weight']
-#             report['full_missplicing'] = missplicing.aberrant_splicing
-#             report['missplicing'] = max(missplicing)
-#             report['reference_resemblance'] = reference_gene_proteins.get(transcript.protein, None)
-#             results.append(report)
-#
-#     report = pd.DataFrame(results)
-#     return report
+def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, cons_required=False, primary_transcript=False, window_length=13, organism='hg38', engine='spliceai', domains=None):
+    gene = Gene(mut_id.split(':')[0], organism=organism)
+    reference_gene_proteins = {tid: transcript.generate_pre_mrna().generate_mature_mrna().generate_protein() for tid, transcript in gene.run_transcripts(protein_coding=True)}
+    mutations = [get_mutation(m, rev=gene.rev) for m in mut_id.split('|')]
+
+    results = []
+    for tid, transcript in gene.run_transcripts(protein_coding=protein_coding, primary_transcript=primary_transcript):
+        if cons_required and not transcript.cons_available:
+            continue
+
+        if all(mutation not in transcript for mutation in mutations):
+            continue
+
+        transcript.generate_pre_mrna()
+        transcript.cons_vector = transform_conservation_vector(transcript.cons_vector, window=window_length)
+        transcript.generate_mature_mrna().generate_protein(inplace=True, domains=domains)
+        ref_protein, cons_vector = transcript.protein, transcript.cons_vector
+        reference_transcript = copy.deepcopy(transcript)
+
+        assert len(ref_protein) == len(cons_vector), f"Protein ({len(ref_protein)}) and conservation vector ({len(cons_vector)}) must be same length. {ref_protein}, \n>{cons_vector}\n>{transcript.cons_seq}"
+
+        missplicing = Missplicing(find_transcript_missplicing(transcript, mutations, engine=engine, threshold=splicing_threshold), threshold=splicing_threshold)
+        for mutation in mutations:
+            transcript.pre_mrna += mutation
+
+        for i, new_boundaries in enumerate(develop_aberrant_splicing(transcript, missplicing.aberrant_splicing)):
+            transcript.acceptors = new_boundaries['acceptors']
+            transcript.donors = new_boundaries['donors']
+            transcript.generate_mature_mrna().generate_protein()
+
+            alignment = get_logical_alignment(reference_transcript.protein, transcript.protein)
+            deleted, inserted = find_indels_with_mismatches_as_deletions(alignment.seqA, alignment.seqB)
+            modified_positions = find_modified_positions(len(ref_protein), deleted, inserted)
+            temp_cons = np.convolve(cons_vector * modified_positions, np.ones(window_length)) / window_length
+            affected_cons_scores = max(temp_cons)
+            percentile = (
+                        sorted(cons_vector).index(next(x for x in sorted(cons_vector) if x >= affected_cons_scores)) / len(
+                    cons_vector))
+
+            report = OncospliceAnnotator(reference_transcript, transcript, mutation)
+            report['mut_id'] = mut_id
+            report['oncosplice_score'] = affected_cons_scores
+            report['percentile'] = percentile
+            report['isoform_id'] = i
+            report['isoform_prevalence'] = new_boundaries['path_weight']
+            report['full_missplicing'] = missplicing.aberrant_splicing
+            report['missplicing'] = max(missplicing)
+            report['reference_resemblance'] = reference_gene_proteins.get(transcript.protein, None)
+            results.append(report)
+
+    if len(results) == 0:
+        return None
+
+    return pd.DataFrame(results)
 
 
 import asyncio

geney/pangolin_utils.py

@@ -46,10 +46,12 @@ def pang_one_hot_encode(seq):
 
 
 
-def pangolin_predict_probs(true_seq, models):
+def pangolin_predict_probs(true_seq, models, just_ss=False):
     # print(f"Running pangolin on: {true_seq}")
-    model_nums = [0, 2, 4, 6]
-    model_nums = [0, 1, 2, 3, 4, 5, 6]
+    if just_ss:
+        model_nums = [0, 2, 4, 6]
+    else:
+        model_nums = [0, 1, 2, 3, 4, 5, 6, 7]
     INDEX_MAP = {0: 1, 1: 2, 2: 4, 3: 5, 4: 7, 5: 8, 6: 10, 7: 11}
 
     seq = true_seq

geney/spliceai_utils.py

@@ -12,8 +12,8 @@ if tf.config.list_physical_devices('GPU'):
 else:
     print("Running on CPU.")
 
-# tf.config.threading.set_intra_op_parallelism_threads(1)
-# tf.config.threading.set_inter_op_parallelism_threads(1)
+tf.config.threading.set_intra_op_parallelism_threads(1)
+tf.config.threading.set_inter_op_parallelism_threads(1)
 
 sai_paths = ('models/spliceai{}.h5'.format(x) for x in range(1, 6))
 sai_models = [load_model(resource_filename('spliceai', x)) for x in sai_paths]

geney/splicing_utils.py

@@ -145,7 +145,7 @@ def find_ss_changes(ref_dct, mut_dct, known_splice_sites, threshold=0.5):
     return discovered_pos, deleted_pos
 
 
-def find_transcript_missplicing(transcript, mutations, context=5000, window=2500, threshold=0.5, engine='spliceai'):
+def find_transcript_missplicing(transcript, mutations, context=5000, window=2500, threshold=0.5, engine='spliceai', just_ss=False):
     from functools import reduce
     ref = transcript.pre_mrna
     var = reduce(lambda acc, mutation: acc + mutation, mutations, ref)
@@ -182,8 +182,8 @@ def find_transcript_missplicing(transcript, mutations, context=5000, window=2500
 
     elif engine == 'pangolin':
         from .pangolin_utils import pangolin_predict_probs, pang_models
-        ref_seq_donor_probs, ref_seq_acceptor_probs = pangolin_predict_probs(ref_seq, models=pang_models)
-        mut_seq_donor_probs, mut_seq_acceptor_probs = pangolin_predict_probs(var_seq, models=pang_models)
+        ref_seq_donor_probs, ref_seq_acceptor_probs = pangolin_predict_probs(ref_seq, models=pang_models, just_ss=just_ss)
+        mut_seq_donor_probs, mut_seq_acceptor_probs = pangolin_predict_probs(var_seq, models=pang_models, just_ss=just_ss)
 
     else:
         raise ValueError(f"{engine} not implemented")

geney/tis_utils.py

@@ -28,26 +28,13 @@ def find_tis(ref_seq, mut_seq, left_context=100, right_context=102):
                                                                                                 right_context=right_context,
                                                                                                 padding='$')
 
-        # 3. If condition 2 is not met, we perform a TIS reaquisition. If condition 2 is met, then we return the reference TIS to be used in the mutated sequence
     if context_conserved:
-        return tis_coords[0]
-
-    # 4. Reaquisition of TIS follows:
-    #### The logic:
-    #  a. We need to find all possible start codon candidates as relative indices
-    #  b. We need to find what proteins each alternative start codon would create
-    #  c. We need to make sure we are only looking at a region around a mutation
-    #  d. We need the titer score rank relative to all titer score reference ranks and relative to the reference score
+        return [(tis_coords[0], 1, 'canonical')]
 
     sc_table = pd.read_pickle(config['titer_path'] / 'titer_tis_scores.pickle')
-    # target_transcript = sc_table[sc_table.transcript_id == ref_id]
-    # if len(target_transcript) == 0:
-    ### reaquire TIS score for ref
-    # pass
-
     ref_seq_tis_context = ref_seq.asymmetric_subseq(tis_coords[0], left_context=left_context,
                                                     right_context=right_context, padding='$')
-    # target_ref_titer_score = target_transcript.tis_score
+
     ref_titer_score = retrieve_titer_score(ref_seq_tis_context)
     ref_titer_rank = percentileofscore(sc_table['tis_score'], ref_titer_score)
     ref_protein = ref_seq.translate(tis_coords[0])
@@ -56,7 +43,8 @@ def find_tis(ref_seq, mut_seq, left_context=100, right_context=102):
     candidate_positions = np.array(
         [p.align(ref_protein, mut_seq.translate(mut_seq.seqmat[1, i])).score if candidate_positions[i] == True else 0
          for i in range(len(ref_seq.seq))])
-    candidate_positions = candidate_positions > sorted(candidate_positions)[-5]
+
+    candidate_positions = candidate_positions > sorted(candidate_positions)[-5] # implement correct logic
     candidate_positions = np.array([retrieve_titer_score(
         mut_seq.asymmetric_subseq(tis_coords[0], left_context=left_context, right_context=right_context,
                                   padding='$')) if candidate_positions[i] > 0 else False for i in
@@ -66,7 +54,7 @@ def find_tis(ref_seq, mut_seq, left_context=100, right_context=102):
          in range(len(ref_seq.seq))])
     best_position = np.where(candidate_positions == min(candidate_positions))[0][0]
     out = mut_seq.seqmat[1, best_position]
-    return out
+    return out  #output: [(genomic_coord1, probability, filter_tag), (genomic_coord2, probability, filter_tag)]
 
 
 def seq_matrix(seq_list):

{geney-1.2.55.dist-info → geney-1.2.57.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.55
+Version: 1.2.57
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn

{geney-1.2.55.dist-info → geney-1.2.57.dist-info}/RECORD

@@ -6,21 +6,21 @@ 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=-_b0ZSxWa-bSYDoVMt605lJlx8-rXf0WsKsFrMoF6Vg,23707
-geney/pangolin_utils.py,sha256=NJEdY43L_2lielY1hZOjlak0baHqXTa1ITrvx8Tkg5o,2878
+geney/oncosplice.py,sha256=eWgY2Lcj894UBFnIVhbxiVz5oqASHg-Ot1wFbjlJbI8,21857
+geney/pangolin_utils.py,sha256=HvXfdLhHWTDXNmYtc8K3p64iTvDtsBq6-Jml5tpg7JI,2930
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
 geney/seqmat_utils.py,sha256=2cRXT_Ox4IdzCM8x3H2HexxFZzjo5WHs0HZiUQv8fBM,18347
-geney/spliceai_utils.py,sha256=gIGPC8u3J15A7EQrk2Elho5PbF9MmUUNopGGH-eEV8s,1873
-geney/splicing_utils.py,sha256=t0vE5KTAdYOYJLa9wjaSJ1jqiHhsDxZs64OxrgR-Sqc,16811
+geney/spliceai_utils.py,sha256=21_TaiLW3faRuPegMgsVvIf1G1a03penZSiydQ-hOTA,1869
+geney/splicing_utils.py,sha256=34xdarFpTHsHZkhi7VrHby9DaIBZ2xCLqPMrTmasEgE,16860
 geney/survival_utils.py,sha256=KnAzEviMuXh6SnVXId9PgsFLSbgkduTvYoIthxN7FPA,6886
 geney/tcga_utils.py,sha256=D_BNHm-D_K408dlcJm3hzH2c6QNFjQsKvUcOPiQRk7g,17612
-geney/tis_utils.py,sha256=vA2ci4gNfwwQZlCjPpO5ehvL2NRVeM7lHI_VyfT-_10,8049
+geney/tis_utils.py,sha256=2makfGfVlDFVIbxzXE85AY9jmAjcNmxyIAxjvkRA5LY,7396
 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-1.2.55.dist-info/METADATA,sha256=bMKlTktE8jhYNpbxWMnp6Z168gk4NafThjukv45vYI4,948
-geney-1.2.55.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.2.55.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.55.dist-info/RECORD,,
+geney-1.2.57.dist-info/METADATA,sha256=UFirGNGhFN_aJnqSO8WHagJCmEfKoHdfRZojLfKymsE,948
+geney-1.2.57.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.2.57.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.57.dist-info/RECORD,,