opencloning 0.4.8__py3-none-any.whl → 0.5.0.1__py3-none-any.whl

opencloning/app_settings.py

@@ -22,6 +22,11 @@ if os.environ.get('ALLOWED_ORIGINS') is not None:
 
 # External services settings =================================
 NCBI_API_KEY = os.environ.get('NCBI_API_KEY')
+NCBI_MAX_SEQUENCE_LENGTH = (
+    int(os.environ.get('NCBI_MAX_SEQUENCE_LENGTH'))
+    if os.environ.get('NCBI_MAX_SEQUENCE_LENGTH') is not None
+    else 500000
+)
 PLANNOTATE_URL = os.environ['PLANNOTATE_URL'] if 'PLANNOTATE_URL' in os.environ else None
 PLANNOTATE_TIMEOUT = int(os.environ['PLANNOTATE_TIMEOUT']) if 'PLANNOTATE_TIMEOUT' in os.environ else 20
 # Handle trailing slash:
@@ -58,6 +63,7 @@ class Settings(BaseModel):
     BATCH_CLONING: bool
     RECORD_STUBS: bool
     NCBI_API_KEY: str | None
+    NCBI_MAX_SEQUENCE_LENGTH: int
     ALLOWED_ORIGINS: list[str]
     PLANNOTATE_URL: str | None
     PLANNOTATE_TIMEOUT: int
@@ -73,6 +79,7 @@ settings = Settings(
     BATCH_CLONING=BATCH_CLONING,
     RECORD_STUBS=RECORD_STUBS,
     NCBI_API_KEY=NCBI_API_KEY,
+    NCBI_MAX_SEQUENCE_LENGTH=NCBI_MAX_SEQUENCE_LENGTH,
     ALLOWED_ORIGINS=ALLOWED_ORIGINS,
     PLANNOTATE_URL=PLANNOTATE_URL,
     PLANNOTATE_TIMEOUT=PLANNOTATE_TIMEOUT,

opencloning/batch_cloning/pombe/__init__.py

@@ -70,8 +70,8 @@ async def post_batch_cloning(
         try:
             pombe_summary(temp_dir)
             pombe_gather(temp_dir)
-        except Exception:
-            raise HTTPException(status_code=400, detail='Summary failed')
+        except Exception as e:
+            raise HTTPException(status_code=400, detail=f'Summary failed: {e}')
 
         # zip the temp dir and return it
         zip_filename = f'{temp_dir}_archive'

opencloning/batch_cloning/pombe/pombe_clone.py

@@ -1,35 +1,34 @@
 import os
-from opencloning.endpoints.external_import import genome_coordinates, get_from_repository_id_addgene, read_from_file
-from opencloning.endpoints.assembly import pcr, homologous_recombination
-from opencloning.pydantic_models import (
-    GenomeCoordinatesSource,
-    TextFileSequence,
-    AddgeneIdSource,
-    PCRSource,
-    PrimerModel,
-    HomologousRecombinationSource,
-    BaseCloningStrategy,
-    UploadedFileSource,
-)
-
-from opencloning.ncbi_requests import get_annotations_from_query
+from pydna.assembly2 import homologous_recombination_integration, pcr_assembly
+from opencloning.dna_functions import request_from_addgene
+from opencloning.ncbi_requests import get_annotations_from_query, get_genome_region_from_annotation
 import asyncio
-import json
 from Bio import SeqIO
+from pydna.primer import Primer
+from pydna.opencloning_models import CloningStrategy
+from fastapi.datastructures import UploadFile
 from pydna.parsers import parse as pydna_parse
 
 
 async def main(
-    gene: str, assembly_accession: str, output_dir: str, plasmid: str | dict = '19343', padding: int = 1000
+    gene: str,
+    assembly_accession: str,
+    output_dir: str,
+    plasmid_input: UploadFile | str = '19343',
+    padding: int = 1000,
 ):
     print(f"\033[92mCloning {gene}\033[0m")
     # Parse primers =================================================================================
-    primer_records = list(SeqIO.parse(os.path.join(output_dir, gene, 'primers.fa'), 'fasta'))
-    checking_primers = list(SeqIO.parse(os.path.join(output_dir, 'checking_primers.fa'), 'fasta'))
-    primer_records = primer_records[:3] + checking_primers[1:] + primer_records[3:] + checking_primers[:1]
-    primers = []
-    for primer in primer_records:
-        primers.append(PrimerModel(sequence=str(primer.seq), id=0, name=primer.id))
+    primers = [Primer(p) for p in SeqIO.parse(os.path.join(output_dir, gene, 'primers.fa'), 'fasta')]
+    common_primers = [Primer(p) for p in SeqIO.parse(os.path.join(output_dir, 'checking_primers.fa'), 'fasta')]
+
+    # Get plasmid sequence =================================================================================
+    if isinstance(plasmid_input, UploadFile):
+        file_content = (await plasmid_input.read()).decode()
+
+        plasmid = pydna_parse(file_content)[0]
+    else:
+        plasmid = await request_from_addgene(plasmid_input)
 
     # Get genome region =====================================================================
     annotations = await get_annotations_from_query(gene, assembly_accession)
@@ -40,104 +39,24 @@ async def main(
     if len(annotations) != 1:
         raise ValueError(f'No right annotation found for {gene}')
 
-    annotation = annotations[0]
-
-    gene_range = annotation['genomic_regions'][0]['gene_range']['range'][0]
-    sequence_accession = annotation['genomic_regions'][0]['gene_range']['accession_version']
-    locus_tag = annotation.get('locus_tag', None)
-    gene_id = annotation.get('gene_id', None)
-    start = int(gene_range['begin'])
-    end = int(gene_range['end'])
-    orientation = 1 if gene_range['orientation'] == 'plus' else -1
-
-    source = GenomeCoordinatesSource(
-        id=0,
-        start=start - padding,
-        end=end + padding,
-        strand=orientation,
-        assembly_accession=assembly_accession,
-        sequence_accession=sequence_accession,
-        locus_tag=locus_tag,
-        gene_id=gene_id,
-        output_name=gene,
-    )
-    locus = await genome_coordinates(source)
-
-    cloning_strategy = BaseCloningStrategy(
-        sequences=[],
-        sources=[],
-        primers=[],
-        description=f'Cloning strategy for deleting the gene {gene} using PCR and homologous recombination',
-    )
-    for primer in primers:
-        cloning_strategy.add_primer(primer)
-    locus_seq: TextFileSequence = TextFileSequence.model_validate(locus['sequences'][0])
-    locus_source: GenomeCoordinatesSource = GenomeCoordinatesSource.model_validate(locus['sources'][0])
-    cloning_strategy.add_source_and_sequence(locus_source, locus_seq)
-
-    # Get plasmid sequence =================s================================================================
-    if not isinstance(plasmid, str):
-        if plasmid.filename.endswith('.fa') or plasmid.filename.endswith('.fasta'):
-            resp = await read_from_file(plasmid, None, None, True, None, None, None)
-        else:
-            resp = await read_from_file(plasmid, None, None, None, None, None, None)
-        # Verify that plasmid is circular
-        if not pydna_parse(resp['sequences'][0].file_content)[0].circular:
-            raise ValueError('Plasmid is not circular')
-        plasmid_source: UploadedFileSource = UploadedFileSource.model_validate(resp['sources'][0])
-    else:
-        addgene_source = AddgeneIdSource(
-            id=0,
-            repository_id=plasmid,
-            repository_name='addgene',
-        )
-        resp = await get_from_repository_id_addgene(addgene_source)
-        plasmid_source: AddgeneIdSource = AddgeneIdSource.model_validate(resp['sources'][0])
-
-    plasmid_seq: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][0])
-    cloning_strategy.add_source_and_sequence(plasmid_source, plasmid_seq)
+    locus = await get_genome_region_from_annotation(annotations[0], 1000, 1000)
 
     # PCR ================================================================================================
-    pcr_source = PCRSource(id=0, output_name='amplified_marker')
-    resp = await pcr(pcr_source, [plasmid_seq], [primers[0], primers[1]], 15, 0)
+    pcr_products = pcr_assembly(plasmid, primers[0], primers[1], limit=14, mismatches=0)
+    pcr_products[0].name = 'amplified_marker'
+    alleles = homologous_recombination_integration(locus, [pcr_products[0]], 40)
+    pcr_check1 = pcr_assembly(alleles[0], primers[2], common_primers[1], limit=14, mismatches=0)[0]
+    pcr_check1.name = 'check_pcr_left'
+    pcr_check2 = pcr_assembly(alleles[0], primers[3], common_primers[0], limit=14, mismatches=0)[0]
+    pcr_check2.name = 'check_pcr_right'
 
-    pcr_product: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][0])
-    pcr_source: PCRSource = PCRSource.model_validate(resp['sources'][0])
-    cloning_strategy.add_source_and_sequence(pcr_source, pcr_product)
-
-    # Homologous recombination ========================================================================
-    hrec_source = HomologousRecombinationSource(id=0, output_name='deletion_allele')
-    resp = await homologous_recombination(hrec_source, [locus_seq, pcr_product], 50)
-
-    hrec_product: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][0])
-    hrec_source: HomologousRecombinationSource = HomologousRecombinationSource.model_validate(resp['sources'][0])
-    cloning_strategy.add_source_and_sequence(hrec_source, hrec_product)
-
-    # Checking pcr 1 ======================================================================================
-    check_pcr_source_left = PCRSource(id=0, output_name='check_pcr_left')
-    resp = await pcr(check_pcr_source_left, [hrec_product], [primers[2], primers[3]], 15, 0)
-
-    check_pcr_product_left: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][0])
-    check_pcr_source_left: PCRSource = PCRSource.model_validate(resp['sources'][0])
-    cloning_strategy.add_source_and_sequence(check_pcr_source_left, check_pcr_product_left)
-
-    # Checking pcr 2 ======================================================================================
-    check_pcr_source_right = PCRSource(id=0, output_name='check_pcr_right')
-    resp = await pcr(check_pcr_source_right, [hrec_product], [primers[4], primers[5]], 15, 0)
-
-    check_pcr_product_right: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][0])
-    check_pcr_source_right: PCRSource = PCRSource.model_validate(resp['sources'][0])
-    cloning_strategy.add_source_and_sequence(check_pcr_source_right, check_pcr_product_right)
-
-    cloning_strategy.description = (
-        f'Cloning strategy for deleting the gene {gene} using PCR and homologous recombination'
-    )
+    cs = CloningStrategy.from_dseqrecords([pcr_check1, pcr_check2])
 
     if not os.path.exists(os.path.join(output_dir, gene)):
         os.makedirs(os.path.join(output_dir, gene))
 
     with open(os.path.join(output_dir, gene, 'cloning_strategy.json'), 'w') as f:
-        json.dump(cloning_strategy.model_dump(), f, indent=2)
+        f.write(cs.model_dump_json(indent=2))
 
 
 if __name__ == '__main__':

opencloning/batch_cloning/pombe/pombe_summary.py

@@ -1,10 +1,17 @@
-from ...pydantic_models import BaseCloningStrategy, PrimerModel, PCRSource, HomologousRecombinationSource
+from pydna.utils import location_boundaries
+from ...pydantic_models import BaseCloningStrategy
+from opencloning_linkml.datamodel import (
+    Primer as PrimerModel,
+    PCRSource,
+    HomologousRecombinationSource,
+)
 from pydna.parsers import parse as pydna_parse
 import os
 import json
 from pydna import tm
 from Bio.Seq import reverse_complement
 import argparse
+from Bio.SeqFeature import Location
 
 chromosomes = {
     'NC_003424.3': 'I',
@@ -17,11 +24,11 @@ chromosomes = {
 def find_primer_aligned_sequence(pcr_sources: list[PCRSource], primer: PrimerModel) -> str:
     for source in pcr_sources:
         if source.input[0].sequence == primer.id:
-            loc = source.input[0].right_location
-            return str(primer.sequence[loc.start : loc.end])
+            loc = Location.fromstring(source.input[0].right_location)
+            return loc.extract(primer.sequence)
         if source.input[-1].sequence == primer.id:
-            loc = source.input[-1].left_location
-            return str(reverse_complement(primer.sequence)[loc.start : loc.end])
+            loc = Location.fromstring(source.input[-1].left_location)
+            return loc.extract(reverse_complement(primer.sequence))
     raise ValueError(f"Primer {primer.id} not found in any PCR source")
 
 
@@ -33,13 +40,18 @@ def process_folder(working_dir: str):
     # We do this to have action to .end and .start
     pcr_sources = [PCRSource.model_validate(s.model_dump()) for s in pcr_sources]
     locus_source = next(s for s in strategy.sources if s.type == 'GenomeCoordinatesSource')
+    locus_location = Location.fromstring(locus_source.coordinates)
     hrec_source = next(s for s in strategy.sources if s.type == 'HomologousRecombinationSource')
     # We do this to have action to .end and .start
     hrec_source: HomologousRecombinationSource = HomologousRecombinationSource.model_validate(hrec_source.model_dump())
 
-    chromosome = chromosomes[locus_source.sequence_accession]
-    insertion_start = locus_source.start + hrec_source.input[0].right_location.end
-    insertion_end = locus_source.start + hrec_source.input[-1].left_location.start
+    chromosome = chromosomes[locus_source.repository_id]
+    insertion_start = (
+        locus_location.start + location_boundaries(Location.fromstring(hrec_source.input[0].right_location))[1]
+    )
+    insertion_end = (
+        locus_location.start + location_boundaries(Location.fromstring(hrec_source.input[-1].left_location))[0]
+    )
 
     # Write out the sequences in genbank format and extract some relevant info
     sequences = [pydna_parse(sequence.file_content)[0] for sequence in strategy.sequences]

opencloning/batch_cloning/ziqiang_et_al2024/__init__.py

@@ -6,10 +6,10 @@ from typing import Annotated
 from fastapi import Body, Query, HTTPException
 
 from ...get_router import get_router
-from ...pydantic_models import (
-    BaseCloningStrategy,
-    PrimerModel,
+from ...pydantic_models import BaseCloningStrategy
+from opencloning_linkml.datamodel import (
     TextFileSequence,
+    Primer as PrimerModel,
     PCRSource,
     RestrictionAndLigationSource,
     GatewaySource,
@@ -96,7 +96,7 @@ async def ziqiang_et_al2024_post(
         else:
             name = f'end_ps{i}_start_ps{i + 1}'
 
-        pcr_source = PCRSource(id=0, output_name=name)
+        pcr_source = PCRSource(id=0, input=[], output_name=name)
         fwd_primer = next(p for p in cloning_strategy.primers if p.id == fwd_primer_id)
         rvs_primer = next(p for p in cloning_strategy.primers if p.id == rvs_primer_id)
 
@@ -112,18 +112,18 @@ async def ziqiang_et_al2024_post(
 
     # Make all input of a Golden gate assembly
     golden_gate_source = RestrictionAndLigationSource(
-        id=0, output_name='golden_gate_assembly', restriction_enzymes=['BsaI']
+        id=0, input=[], output_name='golden_gate_assembly', restriction_enzymes=['BsaI']
     )
 
     # Make them
     input_sequences = [next(s for s in cloning_strategy.sequences if s.id == p) for p in pcr_product_ids]
-    resp = await restriction_and_ligation(golden_gate_source, input_sequences, False, False)
+    resp = await restriction_and_ligation(golden_gate_source, input_sequences, False)
     golden_gate_product: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][0])
     golden_gate_source: RestrictionAndLigationSource = RestrictionAndLigationSource.model_validate(resp['sources'][0])
     cloning_strategy.add_source_and_sequence(golden_gate_source, golden_gate_product)
 
     bp_target = next(s for s in cloning_strategy.sequences if s.id == 6)
-    gateway_source = GatewaySource(id=0, output_name='entry_clone', reaction_type='BP', greedy=False)
+    gateway_source = GatewaySource(id=0, input=[], output_name='entry_clone', reaction_type='BP', greedy=False)
     resp = await gateway(gateway_source, [golden_gate_product, bp_target], circular_only=True, only_multi_site=True)
     gateway_product: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][0])
     gateway_source: GatewaySource = GatewaySource.model_validate(resp['sources'][0])
@@ -141,7 +141,7 @@ async def ziqiang_et_al2024_post(
     all_input_ids = [s.sequence for s in all_inputs]
     sequences_to_clone = [s for s in cloning_strategy.sequences if s.id not in all_input_ids]
 
-    gateway_source = GatewaySource(id=0, output_name='expression_clone', reaction_type='LR', greedy=False)
+    gateway_source = GatewaySource(id=0, input=[], output_name='expression_clone', reaction_type='LR', greedy=False)
     resp = await gateway(gateway_source, sequences_to_clone, circular_only=True, only_multi_site=True)
     index_of_product = next(i for i, s in enumerate(resp['sequences']) if '/label="Cas9"' in s.file_content)
     expression_clone: TextFileSequence = TextFileSequence.model_validate(resp['sequences'][index_of_product])

opencloning/batch_cloning/ziqiang_et_al2024/ziqiang_et_al2024.json

@@ -81,7 +81,6 @@
       "database_id": null,
       "input": [],
       "repository_id": "71287",
-      "repository_name": "addgene",
       "sequence_file_url": "https://media.addgene.org/snapgene-media/v2.0.0/sequences/352460/6c8b0369-e549-4517-95da-8d07146ca49d/addgene-plasmid-71287-sequence-352460.gbk",
       "addgene_sequence_type": "addgene-full"
     },
@@ -92,7 +91,6 @@
       "database_id": null,
       "input": [],
       "repository_id": "71287",
-      "repository_name": "addgene",
       "sequence_file_url": "https://media.addgene.org/snapgene-media/v2.0.0/sequences/352460/6c8b0369-e549-4517-95da-8d07146ca49d/addgene-plasmid-71287-sequence-352460.gbk",
       "addgene_sequence_type": "addgene-full"
     },
@@ -103,7 +101,6 @@
       "database_id": null,
       "input": [],
       "repository_id": "213912",
-      "repository_name": "addgene",
       "sequence_file_url": "https://media.addgene.org/snapgene-media/v2.0.0/sequences/437264/8bd82b44-a1c3-4f81-8936-ebcc16d171e9/addgene-plasmid-213912-sequence-437264.gbk",
       "addgene_sequence_type": "addgene-full"
     },
@@ -114,7 +111,6 @@
       "database_id": null,
       "input": [],
       "repository_id": "213913",
-      "repository_name": "addgene",
       "sequence_file_url": "https://media.addgene.org/snapgene-media/v2.0.0/sequences/437263/af62d64e-1f22-4dce-aafa-7935d1665700/addgene-plasmid-213913-sequence-437263.gbk",
       "addgene_sequence_type": "addgene-full"
     },
@@ -125,7 +121,6 @@
       "database_id": null,
       "input": [],
       "repository_id": "133748",
-      "repository_name": "addgene",
       "sequence_file_url": "https://media.addgene.org/snapgene-media/v2.0.0/sequences/271264/c0ae5f43-46e6-4175-a0c1-9a00cbb92034/addgene-plasmid-133748-sequence-271264.gbk",
       "addgene_sequence_type": "addgene-full"
     },
@@ -135,8 +130,7 @@
       "output_name": "pDONR_P2r-P3",
       "database_id": null,
       "input": [],
-      "repository_id": "gateway_cloning_vectors/pDONR_P2r-P3",
-      "repository_name": "snapgene"
+      "repository_id": "gateway_cloning_vectors/pDONR_P2r-P3"
     },
     {
       "id": 7,
@@ -207,7 +201,6 @@
       "database_id": null,
       "input": [],
       "repository_id": "63143",
-      "repository_name": "addgene",
       "sequence_file_url": "https://media.addgene.org/snapgene-media/v2.0.0/sequences/223326/8c81fe9a-fb57-40bc-93d6-e17d83502061/addgene-plasmid-63143-sequence-223326.gbk",
       "addgene_sequence_type": "addgene-full"
     }
@@ -258,7 +251,7 @@
   ],
   "description": "",
   "files": null,
-  "schema_version": "0.4.3",
+  "schema_version": "0.4.9",
   "backend_version": null,
   "frontend_version": null
 }

opencloning/bug_fixing/backend_v0_3.py

@@ -4,10 +4,12 @@ See info in README.md
 
 from ..pydantic_models import (
     BaseCloningStrategy as CloningStrategy,
+)
+from pydna.opencloning_models import SequenceLocationStr
+from opencloning_linkml.datamodel import (
     AssemblySource,
     TextFileSequence,
-    PrimerModel,
-    SequenceLocationStr,
+    Primer as PrimerModel,
 )
 from .._version import __version__
 import json
@@ -50,9 +52,15 @@ def fix_backend_v0_3(input_data: dict) -> CloningStrategy | None:
                 primers = [PrimerModel.model_validate(p) for p in data['primers'] if p['id'] in primer_ids]
                 input_seqs = [primers[0], input_seqs[0], primers[1]]
 
-            assembly_plan = assembly_source.get_assembly_plan(input_seqs)
-            for join in assembly_plan:
-                if len(join[2]) != len(join[3]):
+            assembly_fragments = [a for a in assembly_source.input if a.type == 'AssemblyFragment']
+
+            for prev_f, next_f in zip(assembly_fragments, assembly_fragments[1:] + assembly_fragments[:1]):
+                left = prev_f.right_location
+                right = next_f.left_location
+                if (left is not None and right is not None) and (
+                    len(SequenceLocationStr(left).to_biopython_location())
+                    != len(SequenceLocationStr(right).to_biopython_location())
+                ):
                     problematic_source_ids.add(source['id'])
                     break
 

opencloning/catalogs/__init__.py

@@ -0,0 +1,36 @@
+import os
+import yaml
+
+
+def get_seva_catalog():
+    seva_catalog_path = os.path.join(os.path.dirname(__file__), 'seva.tsv')
+    seva_catalog = dict()
+    with open(seva_catalog_path, 'r') as f:
+        for line in f:
+            name, genbank_link = line.strip().split('\t')
+            seva_catalog[name] = genbank_link
+    return seva_catalog
+
+
+def get_snapgene_catalog():
+    snapgene_catalog_path = os.path.join(os.path.dirname(__file__), 'snapgene.yaml')
+    with open(snapgene_catalog_path, 'r') as f:
+        return yaml.safe_load(f)
+
+
+def get_openDNA_collections_catalog():
+    catalog_path = os.path.join(os.path.dirname(__file__), 'openDNA_collections.yaml')
+    with open(catalog_path, 'r') as f:
+        return yaml.safe_load(f)
+
+
+def get_iGEM2024_catalog():
+    catalog_path = os.path.join(os.path.dirname(__file__), 'igem2024.yaml')
+    with open(catalog_path, 'r') as f:
+        return yaml.safe_load(f)
+
+
+seva_catalog = get_seva_catalog()
+snapgene_catalog = get_snapgene_catalog()
+openDNA_collections_catalog = get_openDNA_collections_catalog()
+iGEM2024_catalog = get_iGEM2024_catalog()