wip: integrated enzyme choices for all workflows now

web_app/callbacks/workflow_3.py

@@ -27,6 +27,8 @@
 import logging
 import sys
 import io
+from Bio.Restriction import * 
+from Bio import Restriction
 
 
 # Create a StringIO object to capture logs in memory
@@ -131,7 +133,9 @@ def register_workflow_3_callbacks(app):
         State('backbone-overhang-f', 'value'),
         State('backbone-overhang-r', 'value'),
         State('cys4-sequence', 'value'),
-        State('editing_context_3', 'value')
+        State('editing_context_3', 'value'),
+        State('restriction-enzymes_3', 'value')
+
 
         ]
     )
@@ -141,7 +145,7 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
                     number_of_sgRNAs_per_group, only_stop_codons, chosen_polymerase, melting_temperature,
                     primer_concentration, flanking_region_number,
                     restriction_overhang_f, restriction_overhang_r, backbone_overhang_f, backbone_overhang_r, cys4_sequence, 
-                    editing_context):
+                    editing_context, restriction_enzymes):
 
         if n_clicks is None:
             raise PreventUpdate
@@ -215,10 +219,15 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
                 logger.info(f"sgRNA list prepared: {len(sgRNA_list)} sequences")
 
                 sgRNA_handle_cys4_sites = [Dseqrecord(sgRNA_handle_input, name='sgRNA_handle_cys4')] * len(sgRNA_list)
-                golden_gate = GoldenGateCloning(sgRNA_list, sgRNA_handle_cys4_sites, target_tm=input_tm,
-                                                restriction_overhang_f=restriction_overhang_f, restriction_overhang_r=restriction_overhang_r,
-                                                backbone_overhang_f=backbone_overhang_f, backbone_overhang_r=backbone_overhang_r,
-                                                cys4=cys4_sequence, tm_function=primer_tm_neb,
+                golden_gate = GoldenGateCloning(sgRNA_list, 
+                                                sgRNA_handle_cys4_sites, 
+                                                target_tm=input_tm,
+                                                restriction_overhang_f=restriction_overhang_f, 
+                                                restriction_overhang_r=restriction_overhang_r,
+                                                backbone_overhang_f=backbone_overhang_f, 
+                                                backbone_overhang_r=backbone_overhang_r,
+                                                cys4=cys4_sequence, 
+                                                tm_function=primer_tm_neb,
                                                 polymerase=chosen_polymerase)
                 logger.info("Golden Gate Cloning setup completed.")
 
@@ -242,8 +251,11 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
 
                 digest_amplicons = digest_amplicons_w_BsaI(list_of_amplicons)
                 logger.info(f"Amplicons digested: {len(digest_amplicons)} fragments")
+                # Cut plasmid
+                restriction_enzymes = restriction_enzymes.split(',')
+                enzymes_for_repair_template_integration = [getattr(Restriction, str(enzyme)) for enzyme in restriction_enzymes]
 
-                linear_plasmid, _ = sorted(clean_plasmid.cut(NcoI, NheI), key=lambda x: len(x), reverse=True)
+                linear_plasmid = sorted(clean_plasmid.cut(enzymes_for_repair_template_integration), key=lambda x: len(x), reverse=True)[0]
                 logger.info("Plasmid linearized.")
 
                 for amplicon in digest_amplicons:

web_app/callbacks/workflow_4.py

@@ -12,6 +12,8 @@
 from Bio.Restriction import NcoI
 from pydna.dseqrecord import Dseqrecord
 from teemi.design.fetch_sequences import read_genbank_files
+from Bio.Restriction import * 
+from Bio import Restriction
 
 from dash import dcc, html, dash_table, exceptions
 from dash.dependencies import Input, Output, State
@@ -95,12 +97,14 @@ def register_workflow_4_callbacks(app):
             State('off-target-upper_4', 'value'),
             State('cas-type_4', 'value'),
             State('number-of-sgRNAs-per-group_4', 'value'),
-            State('extension-to-promoter-region_4', 'value')
+            State('extension-to-promoter-region_4', 'value'),
+            State('restriction-enzymes_4', 'value')
+
         ]
     )
     def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vector_filename, genes_to_KO, 
                      up_homology, dw_homology, gc_upper, gc_lower, off_target_seed, off_target_upper, cas_type, 
-                     number_of_sgRNAs_per_group, extension_to_promoter_region):
+                     number_of_sgRNAs_per_group, extension_to_promoter_region, restriction_enzymes):
         if n_clicks is None:
             raise PreventUpdate
 
@@ -155,7 +159,10 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
                 logging.debug(f"List of ssDNAs: {list_of_ssDNAs}")
 
                 logging.info("Cutting plasmid")
-                linearized_plasmid = sorted(clean_plasmid.cut(NcoI), key=lambda x: len(x), reverse=True)[0]
+                restriction_enzymes = restriction_enzymes.split(',')
+                enzymes_for_repair_template_integration = [getattr(Restriction, str(enzyme)) for enzyme in restriction_enzymes]
+
+                linearized_plasmid = sorted(clean_plasmid.cut(enzymes_for_repair_template_integration), key=lambda x: len(x), reverse=True)[0]
                 logging.debug(f"Linearized plasmid: {linearized_plasmid}")
 
                 logging.info("Assembling plasmid")

web_app/callbacks/workflow_5.py

@@ -15,7 +15,8 @@
 import dash_bootstrap_components as dbc
 
 from dash.exceptions import PreventUpdate
-from Bio.Restriction import NcoI
+from Bio.Restriction import * 
+from Bio import Restriction
 
 
 # Local module imports
@@ -101,13 +102,17 @@ def register_workflow_5_callbacks(app):
             State('flanking-region-number_5', 'value'), 
             State('repair_templates_length_5', 'value'), 
             State('overlap_for_gibson_length_5', 'value'), 
+            State('restriction-enzymes_5', 'value'),
+            State('restriction-enzymes_5-2', 'value')
+
+
         ]
     )
     def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vector_filename, genes_to_KO, 
                                                       up_homology, dw_homology, gc_upper, gc_lower, off_target_seed, off_target_upper, cas_type, 
                                                       number_of_sgRNAs_per_group, in_frame_deletion, chosen_polymerase, melting_temperature, 
                                                       primer_concentration, flanking_region_number, 
-                                                      repair_templates_length, overlap_for_gibson_length):
+                                                      repair_templates_length, overlap_for_gibson_length, restriction_enzymes, restriction_enzymes_2):
         if n_clicks is None:
             raise PreventUpdate
 
@@ -165,7 +170,9 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
                                     downstream_ovh=dw_homology)
 
                 # cut plasmid
-                linearized_plasmid = sorted(clean_plasmid.cut(NcoI), key=lambda x: len(x), reverse=True)[0]
+                restriction_enzymes = restriction_enzymes.split(',')
+                enzymes_for_repair_template_integration = [getattr(Restriction, str(enzyme)) for enzyme in restriction_enzymes]
+                linearized_plasmid = sorted(clean_plasmid.cut(enzymes_for_repair_template_integration), key=lambda x: len(x), reverse=True)[0]
                 #print(linearized_plasmid)
 
                 sgRNA_vectors = assemble_plasmids_by_ssDNA_bridging(list_of_ssDNAs,linearized_plasmid)
@@ -196,7 +203,9 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
                     logging.info(f"Repair templates data: {repair_templates_data}")
 
                     # Digest the plasmids
-                    processed_records = [Dseqrecord(record, circular=True).cut(StuI)[0] for record in sgRNA_vectors]
+                    restriction_enzymes_2 = restriction_enzymes_2.split(',')
+                    enzymes_for_repair_template_integration_2 = [getattr(Restriction, str(enzyme)) for enzyme in restriction_enzymes_2]
+                    processed_records = [Dseqrecord(record, circular=True).cut(enzymes_for_repair_template_integration_2)[0] for record in sgRNA_vectors]
                     logging.info(f"processed_records: {processed_records}")
 
                     # Rename them appropriately
@@ -250,7 +259,7 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
 
                     workflow_df = determine_workflow_order_for_plasmids(sgRNA_vectors, 
                                                                             assembled_contigs,
-                                                                            ["StuI",], [ "NcoI"])
+                                                                            restriction_enzymes_2, restriction_enzymes)
 
                     plasmid_metadata_df = pd.merge(plasmid_metadata_df, workflow_df, on='plasmid_name', how='inner') 
 

web_app/callbacks/workflow_6.py

@@ -109,7 +109,7 @@ def register_workflow_6_callbacks(app):
     def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vector_filename, genes_to_KO, 
                                                       forward_protospacer_overhang, reverse_protospacer_overhang, gc_upper, gc_lower, off_target_seed, off_target_upper, cas_type, 
                                                       number_of_sgRNAs_per_group, in_frame_deletion, chosen_polymerase, melting_temperature, 
-                                                      primer_concentration, flanking_region_number, enzyme_for_repair_template_integration, 
+                                                      primer_concentration, flanking_region_number, restriction_enzymes_2, 
                                                       repair_templates_length, overlap_for_gibson_length, backbone_fwd_overhang, backbone_rev_overhang):
         if n_clicks is None:
             raise PreventUpdate
@@ -209,7 +209,8 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
                                                                         primer_tm_kwargs={'conc':primer_concentration, 'prodcode':chosen_polymerase} , 
                                                                         repair_length=repair_templates_length)
                     # Convert the lists to a list of enzyme object
-                    enzymes_for_repair_template_integration = [getattr(Restriction, str(enzyme)) for enzyme in enzymes_for_repair_template_integration]
+                    restriction_enzymes_2 = restriction_enzymes_2.split(',')
+                    enzymes_for_repair_template_integration = [getattr(Restriction, str(enzyme)) for enzyme in restriction_enzymes_2]
 
                     logging.info("Digesting plasmids with enzyme_for_repair_template_integration.")
                     processed_records = [sorted(Dseqrecord(record, circular=True).cut(enzymes_for_repair_template_integration), key=lambda x: len(x), reverse=True)[0] for record in assembled_cas3_plasmids]
@@ -250,7 +251,7 @@ def run_workflow(n_clicks, genome_content, vector_content, genome_filename, vect
 
                     workflow_df = determine_workflow_order_for_plasmids(assembled_cas3_plasmids, 
                                                                         assembled_contigs,
-                                                                        [enzyme_for_repair_template_integration], ["NcoI", "BstBI"]) 
+                                                                        restriction_enzymes_2, ["NcoI", "BstBI"]) 
 
                     plasmid_metadata_df = pd.merge(plasmid_metadata_df, workflow_df, on='plasmid_name', how='inner')