geney 1.2.32__py2.py3-none-any.whl → 1.2.34__py2.py3-none-any.whl

geney/config_setup.py

@@ -6,7 +6,8 @@ def get_config():
     config_file = os.path.join(os.path.expanduser('~'), '.oncosplice_setup_1_2', 'config.json')
     if Path(config_file).exists():
         config_setup = {k: {k_in: Path(p_in) for k_in, p_in in p.items()} for k, p in json.loads(open(config_file).read()).items()}
-
+        config_setup['hg38']['titer_path'] = Path('/tamir2/nicolaslynn/tools/titer')
+        config_setup['hg38']['yoram_path'] = Path('/tamir2/yoramzar/Projects/Cancer_mut/Utils')
     else:
         print("Database not set up.")
         config_setup = {}

geney/oncosplice.py

@@ -7,7 +7,7 @@ import pandas as pd
 from .splicing_utils import find_transcript_missplicing, develop_aberrant_splicing, Missplicing
 from .seqmat_utils import *
 from .mutation_utils import *
-
+from .tis_utils import find_tis
 
 ### Scoring
 def find_continuous_gaps(sequence):
@@ -416,58 +416,69 @@ def oncosplice(mut_id, splicing_threshold=0.5, protein_coding=True, primary_tran
 
 
 import asyncio
-async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=True, primary_transcript=False, window_length=13, organism='hg38', engine='spliceai'):
+
+
+async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=True, primary_transcript=False,
+                               window_length=13, organism='hg38', engine='spliceai'):
     import sys, os
-    from pathlib import Path
-    needed_path = Path('/tamir2/yoramzar/Projects/Cancer_mut/Utils')
-    needed_file1 = needed_path / 'rest_api_utils.py'
-    needed_file2 = needed_path / 'uniprot_utils.py'
+    needed_file1 = config[organism]['yoram_path'] / 'rest_api_utils.py'
+    needed_file2 = config[organism]['yoram_path'] / 'uniprot_utils.py'
 
-    if sys.platform == 'linux' and (needed_file1.is_file() and os.access(needed_file1, os.X_OK)) and (needed_file2.is_file() and os.access(needed_file2, os.X_OK)):
-        sys.path.append(str(needed_path))
+    if sys.platform == 'linux' and (needed_file1.is_file() and os.access(needed_file1, os.R_OK)) and (
+            needed_file2.is_file() and os.access(needed_file2, os.R_OK)):
+        sys.path.append(str(config[organism]['yoram_path']))
         import uniprot_utils as uput
 
     else:
-        raise SystemError("Oncosplice Prototype can only be run on Power with access to the /tamir2/yoramzar/Projects/Cancer_mut/Utils folder.")
+        raise SystemError(
+            "Oncosplice Prototype can only be run on Power with access to the /tamir2/yoramzar/Projects/Cancer_mut/Utils folder.")
+
+    from .tis_utils import find_tis
 
     # Define async functions
     async def background_request(ensb_id, Uniprot_features=["Topological domain", "Transmembrane", "Domain"]):
         return uput.retrieve_protein_data_features_subset(uput.ensembl_id2uniprot_id(ensb_id), Uniprot_features)
 
+    def inspect_domain(row, modified_vector, conservation_vector):
+        v1, v2 = modified_vector[row.start:row.end], conservation_vector[row.start:row.end]
+        return pd.Series([f'{row.type}|{row.start}|{row.end}|{row.description}', sum(v1 * v2) / sum(v2)],
+                         index=['domain_identifier', 'score'])
 
     gene = Gene(mut_id.split(':')[0], organism=organism)
-    # request_thread = threading.Thread(target=background_request, args=(gene.transcript_ids, domains))
-    # request_thread.start()
-
-    mutation = get_mutation(mut_id, rev=gene.rev)
+    mutations = [get_mutation(mut_id, rev=gene.rev) for mut_id in mut_id.split('|')]
 
     results = []
     for tid, transcript in gene.run_transcripts(protein_coding=protein_coding, primary_transcript=primary_transcript):
         if not transcript.cons_available:
             continue
 
-        if mutation not in transcript:
+        if all(mutation not in transcript for mutation in mutations):
             results.append({'transcript_id': transcript.transcript_id})
             continue
 
-        task1 = asyncio.create_task(background_request(transcript.transcript_id))
+        task1 = asyncio.create_task(background_request(tid))
 
         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)
+        transcript.generate_mature_mrna().generate_protein(inplace=True)
         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."
+        assert len(ref_protein) == len(
+            cons_vector), f"Protein ({len(ref_protein)}) and conservation vector ({len(cons_vector)} must be same length."
 
-        missplicing = Missplicing(find_transcript_missplicing(transcript, mutation, engine=engine), threshold=splicing_threshold)
-        transcript.pre_mrna += mutation
-        result1 = await task1
-        print(result1)
+        missplicing = Missplicing(find_transcript_missplicing(transcript, mutations, engine=engine),
+                                  threshold=splicing_threshold)
+        for mutation in mutations:
+            transcript.pre_mrna += mutation
+
+        domains_df = await task1
         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()
+            transcript.generate_mature_mrna()
+            transcript.TIS = find_tis(ref_seq=reference_transcript, mut_seq=transcript)
+            transcript.generate_protein()
 
             alignment = get_logical_alignment(reference_transcript.protein, transcript.protein)
             deleted, inserted = find_indels_with_mismatches_as_deletions(alignment.seqA, alignment.seqB)
@@ -475,8 +486,11 @@ async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=Tr
             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))
+                    sorted(cons_vector).index(next(x for x in sorted(cons_vector) if x >= affected_cons_scores)) / len(
+                cons_vector))
+
+            out = domains_df.apply(lambda row: inspect_domain(row, va, vb), axis=1)
+            domains_affected = '+'.join([f'{a}:{b}' for a, b in list(zip(out.domain_identifier, out.score))])
 
             report = OncospliceAnnotator(reference_transcript, transcript, mutation)
             report['mut_id'] = mut_id
@@ -486,13 +500,13 @@ async def oncosplice_prototype(mut_id, splicing_threshold=0.5, protein_coding=Tr
             report['isoform_prevalence'] = new_boundaries['path_weight']
             report['full_missplicing'] = missplicing.aberrant_splicing
             report['missplicing'] = max(missplicing)
+            report['domains_affected'] = domains_affected
             # report['reference_resemblance'] = reference_gene_proteins.get(variant_isoform.protein, None)
-            results.append(report)
+            results.append(pd.Series(report))
 
-    report = pd.DataFrame(results)
+    report = pd.concat(results, axis=1).T
     return report
 
 
-
 if __name__ == '__main__':
     pass

geney/seqmat_utils.py

@@ -203,7 +203,7 @@ class SeqMat:
             return SeqMat('ATG')
 
     def translate(self, tis_index):
-        from Bio import Seq
+        from Bio.Seq import Seq
         return Seq(self.orf_seqmat(tis_index).seq).translate()
 
 

geney/tis_utils.py

@@ -0,0 +1,175 @@
+import numpy as np
+import pandas as pd
+import os
+from scipy.stats import percentileofscore
+import shelve
+from Bio.Align import PairwiseAligner
+from geney import config
+
+p = PairwiseAligner()
+
+
+def find_tis(ref_seq, mut_seq, left_context=100, right_context=102):
+    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
+
+    # 1. Is the start codon (the indices) conserved in the mut sequence?
+    assert all(a in ref_seq.seqmat[1, :] for a in
+               tis_coords), f"Start codon indices specified not found in the reference sequence."
+    tis_conserved = all(a in mut_seq.seqmat[1, :] for a in tis_coords)
+
+    # 2. If condition 1 is passed, is the context around that start codon the same in both the reference and the mutated?
+    context_conserved = False
+    if tis_conserved:
+        context_conserved = ref_seq.asymmetric_subseq(tis_coords[0], left_context=left_context,
+                                                      right_context=right_context,
+                                                      padding='$') == mut_seq.asymmetric_subseq(tis_coords[0],
+                                                                                                left_context=left_context,
+                                                                                                right_context=right_context,
+                                                                                                padding='$')
+
+        # 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
+
+    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='$')
+    # target_ref_titer_score = target_transcript.tis_score
+    ref_titer_score = retrieve_titer_score(ref_seq_tis_context)
+    ref_titer_rank = percentileofscore(sc_table['tis_score'], ref_titer_score)
+    ref_protein = ref_seq.translate(tis_coords[0])
+
+    candidate_positions = np.array([mut_seq.seq[i:i + 3] in TITER_acceptable_TISs for i in range(len(mut_seq.seq))])
+    candidate_positions = np.array(
+        [p.align(ref_protein, mut_seq.translate(mut_seq.seqmat[1, i])).score if candidate_positions[i] == True else 0
+         for i in range(len(ref_seq.seq))])
+    candidate_positions = candidate_positions > sorted(candidate_positions)[-5]
+    candidate_positions = np.array([retrieve_titer_score(
+        mut_seq.asymmetric_subseq(tis_coords[0], left_context=left_context, right_context=right_context,
+                                  padding='$')) if candidate_positions[i] > 0 else False for i in
+                                    range(len(ref_seq.seq))])
+    candidate_positions = np.array(
+        [percentileofscore(sc_table.tis_score, candidate_positions[i]) if candidate_positions[i] != False else 100 for i
+         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
+
+
+def seq_matrix(seq_list):
+    tensor = np.zeros((len(seq_list), 203, 8))
+    for i in range(len(seq_list)):
+        seq = seq_list[i]
+        j = 0
+        for s in seq:
+            if s == 'A' and (j < 100 or j > 102):
+                tensor[i][j] = [1, 0, 0, 0, 0, 0, 0, 0]
+            if s == 'T' and (j < 100 or j > 102):
+                tensor[i][j] = [0, 1, 0, 0, 0, 0, 0, 0]
+            if s == 'C' and (j < 100 or j > 102):
+                tensor[i][j] = [0, 0, 1, 0, 0, 0, 0, 0]
+            if s == 'G' and (j < 100 or j > 102):
+                tensor[i][j] = [0, 0, 0, 1, 0, 0, 0, 0]
+            if s == '$':
+                tensor[i][j] = [0, 0, 0, 0, 0, 0, 0, 0]
+            if s == 'A' and (j >= 100 and j <= 102):
+                tensor[i][j] = [0, 0, 0, 0, 1, 0, 0, 0]
+            if s == 'T' and (j >= 100 and j <= 102):
+                tensor[i][j] = [0, 0, 0, 0, 0, 1, 0, 0]
+            if s == 'C' and (j >= 100 and j <= 102):
+                tensor[i][j] = [0, 0, 0, 0, 0, 0, 1, 0]
+            if s == 'G' and (j >= 100 and j <= 102):
+                tensor[i][j] = [0, 0, 0, 0, 0, 0, 0, 1]
+            j += 1
+    return tensor
+
+
+def build_titer_model(TITER_path=config['titer_setup']):
+    print('Building TITER model...')
+    from tensorflow.keras.constraints import MaxNorm
+    from tensorflow.keras.layers import Conv1D, MaxPool1D, LSTM, Dropout, Flatten, Dense, Activation
+    from tensorflow.keras import Sequential, Input
+
+    model = Sequential()
+    model.add(Input(shape=(203, 8)))
+    model.add(Conv1D(filters=128,
+                     kernel_size=3,
+                     padding='valid',
+                     kernel_constraint=MaxNorm(3),
+                     activation='relu'))
+    model.add(MaxPool1D(3))
+    model.add(Dropout(rate=0.21370950078747658))
+    model.add(LSTM(units=256,
+                   return_sequences=True))
+    model.add(Dropout(rate=0.7238091317104384))
+    model.add(Flatten())
+    model.add(Dense(1))
+    model.add(Activation('sigmoid'))
+
+    model.compile(loss='binary_crossentropy',
+                  optimizer='nadam',
+                  metrics=['accuracy'])
+
+    models = []
+
+    # Load weights into multiple instances of the model
+    for i in range(32):
+        model_copy = Sequential(model.layers)  # Create a new model instance with the same architecture
+        weights_path = os.path.join(TITER_path, f"bestmodel_{i}.hdf5")
+
+        if os.path.exists(weights_path):
+            model_copy.load_weights(weights_path)  # Load weights into the new model instance
+            models.append(model_copy)
+            print(f"Loaded model {i} with weights from {weights_path}")
+        else:
+            print(f"Warning: Weights file {weights_path} not found")
+
+    return models
+
+
+def calculate_titer_score(candidate_seq, titer_model=None):  # , prior):
+    if titer_model is None:
+        titer_model = TITER_MODEL
+    processed_seq = seq_matrix([candidate_seq])  # Wrap in list to keep dimensions consistent
+    # prior = np.array([prior]).reshape(1, 1)
+    analyzed_score = np.zeros((1, 1))
+
+    # Iterate through the models (assuming 32 models) and calculate the score
+    for i in range(32):
+        y_pred = titer_model[i].predict(processed_seq, verbose=0)
+        analyzed_score += y_pred  # * prior
+    print(analyzed_score)
+    return analyzed_score[0][0]
+
+
+def retrieve_titer_score(sequence, filename='sequences_shelve.db'):
+    # Open the shelf (acts like a dictionary, stored in a file)
+    with shelve.open(filename) as db:
+        # Check if sequence is already in the shelf
+        if sequence in db:
+            return db[sequence]
+        else:
+            # If not, run the function, store the result, and return it
+            value = calculate_titer_score(sequence, TITER_MODEL)
+            db[sequence] = value
+            return value
+
+
+TITER_acceptable_TISs = ['ATG', 'CTG', 'ACG', 'TTG', 'GTG']
+codon_tis_prior = {'ATG': 3.5287101354987644, 'CTG': 1.746859242328512, 'ACG': 1.3535552403706805,
+                   'TTG': 1.1364995562364615, 'GTG': 1.218573747658257}
+stop_codons = ['TAA', 'TAG', 'TGA']
+TITER_MODEL = build_titer_model()

geney/translation_initiation/tis_utils.py

@@ -120,3 +120,5 @@ def get_end_codon(seq, start_position):
 
 def calculate_titer_score(seq, pos):
     return 0
+
+

{geney-1.2.32.dist-info → geney-1.2.34.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: geney
-Version: 1.2.32
+Version: 1.2.34
 Summary: A Python package for gene expression modeling.
 Home-page: https://github.com/nicolaslynn/geney
 Author: Nicolas Lynn
@@ -13,7 +13,7 @@ Classifier: License :: Free for non-commercial use
 Classifier: Operating System :: POSIX :: Linux
 Classifier: Operating System :: MacOS
 Classifier: Programming Language :: Python :: 3.9
-Requires-Python: >3.9
+Requires-Python: ==3.10
 Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: networkx

{geney-1.2.32.dist-info → geney-1.2.34.dist-info}/RECORD

@@ -1,25 +1,26 @@
 geney/Fasta_segment.py,sha256=0zCdzPUbDeM9Rz642woH5Q94pwI46O0fE3H8w0XWebc,11255
 geney/__init__.py,sha256=eBdDl42N6UhcYeZDjOnv199Z88fI5_8Y6xW8447OKXM,755
-geney/config_setup.py,sha256=VA6mhVGMRadwlpEx4m1wrssmDM8qpfKT21MAijIwjyQ,428
+geney/config_setup.py,sha256=klm_k7Ca_703DpeGBcGoDqz1XwHQhNXENPKjj_xfSQw,608
 geney/data_setup.py,sha256=2RHmuvcGUQbEglXQEZr0C2QPDTQYRZOEm0EcmyfQJgU,12229
 geney/graphic_utils.py,sha256=tjm6IDQ1BdfSeuPYzjlqAUHFQoDYH9jXTzJjKFS4Hh4,11078
 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=7wf0_-Gkc_G9HhUXjORHk3buZ66JzVzSFVQ4EZOtUAE,21787
+geney/oncosplice.py,sha256=QETLNIzc3T1CYausLD3W_jCSJveDkg2F6WnIMagVLT0,22536
 geney/pangolin_utils.py,sha256=ETTGpuaQgdZ1v8H0NP8sbTEfGWu0VXUFUS7wsURsTc4,2991
 geney/power_utils.py,sha256=MehZFUdkJ2EFUot709yPEDxSkXmH5XevMebX2HD768A,7330
-geney/seqmat_utils.py,sha256=TDWhE5oVTGJceaO6YmE7I_BEWRxWLT74_3rkmY1M0Fs,18368
+geney/seqmat_utils.py,sha256=YV5DFLbfjXLIswPGvqK1-eEfwn9TUby0b2kewdGAKws,18372
 geney/spliceai_utils.py,sha256=gIGPC8u3J15A7EQrk2Elho5PbF9MmUUNopGGH-eEV8s,1873
 geney/splicing_utils.py,sha256=q47EdcsHrp4aLIPVWvkGBJSzS3l3DKiD9DNDsPpZdHk,16075
 geney/survival_utils.py,sha256=2CAkC2LsspicHIdrqsiPnjgvpr5KHDUfLFFqnRbPJqs,5762
 geney/tcga_utils.py,sha256=vXSMf1OxoF_AdE_rMguy_BoYaart_E1t4FFMx2DS1Ak,15585
+geney/tis_utils.py,sha256=GlzyO_QvMFt5tM4kewQ1L2l1KAYrCixgw8ny_WsGsYQ,8040
 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=iXrWVijyPe-f8I9rEVGdxNnXBrOGPoKFjmvaOEnQYNE,4446
+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-1.2.32.dist-info/METADATA,sha256=aHeSBHWq3b1li4G_CI2ClUEHJc5SfWHowqKrkZbQPGk,948
-geney-1.2.32.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
-geney-1.2.32.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
-geney-1.2.32.dist-info/RECORD,,
+geney-1.2.34.dist-info/METADATA,sha256=LfYqiCiEw25eyzdGGYy2OrJ7rGC05l1lnaF8eupWrTE,950
+geney-1.2.34.dist-info/WHEEL,sha256=fS9sRbCBHs7VFcwJLnLXN1MZRR0_TVTxvXKzOnaSFs8,110
+geney-1.2.34.dist-info/top_level.txt,sha256=O-FuNUMb5fn9dhZ-dYCgF0aZtfi1EslMstnzhc5IIVo,6
+geney-1.2.34.dist-info/RECORD,,