opencloning 0.4.7__tar.gz → 0.5__tar.gz

{opencloning-0.4.7 → opencloning-0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opencloning
-Version: 0.4.7
+Version: 0.5
 Summary: Backend of OpenCloning, a web application to generate molecular cloning strategies in json format, and share them with others.
 License: MIT
 License-File: LICENSE
@@ -17,14 +17,13 @@ Requires-Dist: beautifulsoup4 (>=4.11.1,<5.0.0)
 Requires-Dist: biopython (>=1.85,<2.0)
 Requires-Dist: fastapi
 Requires-Dist: httpx (>=0.28.1,<0.29.0)
-Requires-Dist: opencloning-linkml (==0.4.4)
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: packaging (>=25.0,<26.0)
 Requires-Dist: pairwise-alignments-to-msa (>=0.1.1,<0.2.0)
 Requires-Dist: pandas (>=2.2.3,<3.0.0)
-Requires-Dist: primer3-py (==2.2.0)
+Requires-Dist: primer3-py (>=2.3,<3.0)
 Requires-Dist: pydantic (>=2.7.1,<3.0.0)
-Requires-Dist: pydna (==5.5.2)
+Requires-Dist: pydna (>=5.5.5,<6.0.0)
 Requires-Dist: python-multipart
 Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
 Requires-Dist: regex (>=2024.11.6,<2025.0.0)
@@ -47,9 +46,9 @@ Read [main project readme](https://github.com/manulera/OpenCloning) first.
 
 This API provides a series of entry points. The API documentation can be accessed [here](https://api.opencloning.org/docs). You can use the documentation page to try some request directly on the browser. Otherwise, the API is open for you to make requests from a python script or command line at: [https://api.opencloning.org/](https://api.opencloning.org/).
 
-## Scripting
+## Scripting with pydna
 
-The API functions can also be used to write python scripts to automate cloning. See the [scripting examples](examples/scripting) for more information.
+You can write python scripts to automate cloning using the python library [pydna](https://github.com/pydna-group/pydna), which is now integrated with the OpenCloning data model. See [the documentation](https://github.com/pydna-group/pydna/blob/master/docs/notebooks/history.ipynb) for how to get started.
 
 ## Migrating between model versions and fixing model bugs
 
@@ -117,7 +116,7 @@ docker run -d --name backendcontainer -p 8000:8000 manulera/opencloningbackend
 
 ```
 
-If you don't want to download the repository and build the image, you can fetch the latest image from dockerhub (same image that is used in [https://api.opencloning.org/](https://api.opencloning.org/))
+If you don't want to download the repository and build the image, you can fetch the latest image from dockerhub.
 
 ```bash
 docker pull manulera/opencloningbackend
@@ -167,7 +166,7 @@ pytest -v -ks
 ### Ping a particular library version from github:
 
 ```
-poetry add git+https://github.com/BjornFJohansson/pydna#4fd760d075f77cceeb27969e017e04b42f6d0aa3
+poetry add git+https://github.com/pydna-group/pydna#4fd760d075f77cceeb27969e017e04b42f6d0aa3
 ```
 
 When installing the last version, sometimes poetry may not be able to access the latest version
@@ -188,3 +187,14 @@ RECORD_STUBS=1 uvicorn opencloning.main:app --reload --reload-exclude='.venv'
 
 This will record the stubs (requests and responses) in the `stubs` folder.
 
+
+### Catalogs
+
+Catalogs are used to map ids to urls for several plasmid collections. They are stored in the `src/opencloning/catalogs` folder.
+
+To update the catalogs, run the following command:
+
+```bash
+poetry run python scripts/update_catalogs.py
+```
+

{opencloning-0.4.7 → opencloning-0.5}/README.md

@@ -13,9 +13,9 @@ Read [main project readme](https://github.com/manulera/OpenCloning) first.
 
 This API provides a series of entry points. The API documentation can be accessed [here](https://api.opencloning.org/docs). You can use the documentation page to try some request directly on the browser. Otherwise, the API is open for you to make requests from a python script or command line at: [https://api.opencloning.org/](https://api.opencloning.org/).
 
-## Scripting
+## Scripting with pydna
 
-The API functions can also be used to write python scripts to automate cloning. See the [scripting examples](examples/scripting) for more information.
+You can write python scripts to automate cloning using the python library [pydna](https://github.com/pydna-group/pydna), which is now integrated with the OpenCloning data model. See [the documentation](https://github.com/pydna-group/pydna/blob/master/docs/notebooks/history.ipynb) for how to get started.
 
 ## Migrating between model versions and fixing model bugs
 
@@ -83,7 +83,7 @@ docker run -d --name backendcontainer -p 8000:8000 manulera/opencloningbackend
 
 ```
 
-If you don't want to download the repository and build the image, you can fetch the latest image from dockerhub (same image that is used in [https://api.opencloning.org/](https://api.opencloning.org/))
+If you don't want to download the repository and build the image, you can fetch the latest image from dockerhub.
 
 ```bash
 docker pull manulera/opencloningbackend
@@ -133,7 +133,7 @@ pytest -v -ks
 ### Ping a particular library version from github:
 
 ```
-poetry add git+https://github.com/BjornFJohansson/pydna#4fd760d075f77cceeb27969e017e04b42f6d0aa3
+poetry add git+https://github.com/pydna-group/pydna#4fd760d075f77cceeb27969e017e04b42f6d0aa3
 ```
 
 When installing the last version, sometimes poetry may not be able to access the latest version
@@ -153,3 +153,14 @@ RECORD_STUBS=1 uvicorn opencloning.main:app --reload --reload-exclude='.venv'
 ```
 
 This will record the stubs (requests and responses) in the `stubs` folder.
+
+
+### Catalogs
+
+Catalogs are used to map ids to urls for several plasmid collections. They are stored in the `src/opencloning/catalogs` folder.
+
+To update the catalogs, run the following command:
+
+```bash
+poetry run python scripts/update_catalogs.py
+```

{opencloning-0.4.7 → opencloning-0.5}/pyproject.toml

@@ -8,7 +8,7 @@ authors = ["Manuel Lera-Ramirez <manulera14@gmail.com>"]
 description = "Backend of OpenCloning, a web application to generate molecular cloning strategies in json format, and share them with others."
 license = "MIT"
 name = "opencloning"
-version = "0.4.7"
+version = "0.5"
 package-mode = true
 readme = "README.md"
 repository = "https://github.com/manulera/OpenCloning_backend"
@@ -20,17 +20,16 @@ httpx = "^0.28.1"
 python = "^3.11"
 python-multipart = "*"
 uvicorn = "*"
-pydna = "5.5.2"
 regex = "^2024.11.6"
 pydantic = "^2.7.1"
 pandas = "^2.2.3"
 openpyxl = "^3.1.5"
 pyyaml = "^6.0.2"
-opencloning-linkml = "0.4.4"
-primer3-py = "2.2.0"
+primer3-py = "^2.3"
 biopython = "^1.85"
 packaging = "^25.0"
 pairwise-alignments-to-msa = "^0.1.1"
+pydna = "^5.5.5"
 
 [tool.poetry.group.dev.dependencies]
 autopep8 = "^2.0.4"

{opencloning-0.4.7 → opencloning-0.5}/src/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-0.4.7 → opencloning-0.5}/src/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-0.5/src/opencloning/batch_cloning/pombe/pombe_clone.py

@@ -0,0 +1,102 @@
+import os
+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
+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_input: UploadFile | str = '19343',
+    padding: int = 1000,
+):
+    print(f"\033[92mCloning {gene}\033[0m")
+    # Parse primers =================================================================================
+    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)
+    if len(annotations) == 0:
+        raise ValueError(f'No annotations found for {gene}')
+
+    annotations = [a for a in annotations if gene.upper() in a['locus_tag'].upper()]
+    if len(annotations) != 1:
+        raise ValueError(f'No right annotation found for {gene}')
+
+    locus = await get_genome_region_from_annotation(annotations[0], 1000, 1000)
+
+    # PCR ================================================================================================
+    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'
+
+    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:
+        f.write(cs.model_dump_json(indent=2))
+
+
+if __name__ == '__main__':
+    import argparse
+
+    parser = argparse.ArgumentParser(description='List of genes to delete from S. pombe')
+    parser.add_argument(
+        '--genes', type=str, required=True, help='Path to a file containing a list of genes, one per line'
+    )
+    args = parser.parse_args()
+
+    parser.add_argument(
+        '--assembly_accession',
+        type=str,
+        default='GCF_000002945.2',
+        help='Assembly accession for S. pombe genome (default: GCF_000002945.2)',
+    )
+
+    parser.add_argument(
+        '--output_dir',
+        type=str,
+        default='batch_cloning_output',
+        help='Directory to save the output files (default: batch_cloning_output)',
+    )
+
+    parser.add_argument(
+        '--plasmid',
+        type=str,
+        default='19343',
+        help='Addgene ID for the plasmid (default: 19343)',
+    )
+
+    args = parser.parse_args()
+    assembly_accession = args.assembly_accession
+
+    with open(args.genes, 'r') as f:
+        genes = [line.strip() for line in f if line.strip()]
+
+    if not os.path.exists(args.output_dir):
+        os.makedirs(args.output_dir)
+
+    for gene in genes:
+        asyncio.run(main(gene, assembly_accession, args.output_dir, args.plasmid))

{opencloning-0.4.7 → opencloning-0.5}/src/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-0.4.7 → opencloning-0.5}/src/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-0.4.7 → opencloning-0.5}/src/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-0.4.7 → opencloning-0.5}/src/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-0.5/src/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()