Refactor sequence alignment #63 (#70)

* okay import fixed and fixed proteinRecord Test * working on fixing the fetcher not working but fixed al lot of wrong refences * okay fixeed protein record and test * API update * ruff is happy now with the test * API update * all work with simple test * API update * fix circular import * API update * move `ProteinRecord` into functions * move `ProteinRecord` into functions * added test to detect circular imports * API update * enabled tests upon PR * API update * use `psycopg2-binary` to prevent missing bins * API update * API update * API update * tests for alignment * API update * fix circular import * remove literals * API update --------- Co-authored-by: Niklas Abraham <[email protected]> Co-authored-by: sdRDM Bot <[email protected]> Co-authored-by: Jan Range <[email protected]> Co-authored-by: Max Häußler <[email protected]> Co-authored-by: max <[email protected]>
PyEED · May 8, 2024 · fd8c319 · fd8c319
1 parent 8390fb4
commit fd8c319
Show file tree

Hide file tree

Showing 20 changed files with 92 additions and 72 deletions.
diff --git a/pyeed/align/hmm.py b/pyeed/align/hmm.py
@@ -1,13 +1,16 @@
+from __future__ import annotations
+
 import os
-from typing import List, Union
+from typing import List, Union, TYPE_CHECKING
 
 import pyhmmer
 from pydantic import BaseModel, Field
 
-# TODO import sequence record
-from pyeed.core.abstractsequence import AbstractSequence
-from pyeed.core.alignment import Alignment
-from pyeed.core.sequence import Sequence
+from pyeed.core.abstractannotation import AbstractAnnotation
+
+if TYPE_CHECKING:
+    from pyeed.core.alignment import Alignment
+    from pyeed.core.sequence import Sequence
 
 # TODO FIX ENTIRE THING
 
@@ -54,7 +57,7 @@ def build_model(self) -> pyhmmer.easel.MSA:
 
     def search(
         self,
-        sequence: Union[AbstractSequence, List[AbstractSequence]],
+        sequence: Union["AbstractSequence", List["AbstractSequence"]],
         **pipeline_kwargs,
     ):
 
@@ -103,7 +106,7 @@ def from_file(cls, path: str):
         return cls(model=model, name=model.name)
 
     def _prepare_sequences(
-        self, sequences: Union[AbstractSequence, List[AbstractSequence]]
+        self, sequences: Union["AbstractSequence", List["AbstractSequence"]]
     ):
         if not isinstance(sequences, list):
             sequences = [sequences]

diff --git a/pyeed/core/abstractannotation.py b/pyeed/core/abstractannotation.py
@@ -51,7 +51,7 @@ class AbstractAnnotation(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/alignmentdata.py b/pyeed/core/alignmentdata.py
@@ -51,7 +51,7 @@ class AlignmentData(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/blastdata.py b/pyeed/core/blastdata.py
@@ -90,7 +90,7 @@ class BlastData(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/clustalomegadata.py b/pyeed/core/clustalomegadata.py
@@ -32,7 +32,7 @@ class ClustalOmegaData(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/cluster.py b/pyeed/core/cluster.py
@@ -49,7 +49,7 @@ class Cluster(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/dnarecord.py b/pyeed/core/dnarecord.py
@@ -62,7 +62,7 @@ class DNARecord(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/organism.py b/pyeed/core/organism.py
@@ -108,7 +108,7 @@ class Organism(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/pairwisealignment.py b/pyeed/core/pairwisealignment.py
@@ -60,7 +60,7 @@ class PairwiseAlignment(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/proteinrecord.py b/pyeed/core/proteinrecord.py
@@ -16,13 +16,10 @@
 from sdRDM.tools.utils import elem2dict
 
 from pyeed.container.abstract_container import Blastp
-from pyeed.core.dnarecord import DNARecord
-from pyeed.core.region import Region
-from pyeed.core.sequencerecord import SequenceRecord
-from pyeed.core.site import Site
-from pyeed.fetch.blast import Blast, BlastProgram, NCBIDataBase
+from pyeed.fetch.blast import BlastProgram, NCBIDataBase
 from pyeed.fetch.proteinfetcher import ProteinFetcher
 
+from .dnarecord import DNARecord
 from .region import Region
 from .sequencerecord import SequenceRecord
 from .site import Site
@@ -106,7 +103,7 @@ class ProteinRecord(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)
@@ -283,6 +280,7 @@ def from_sequence(
             AssertionError: If the specified database is not supported.
         """
 
+        from pyeed.fetch.blast import BlastProgram
         from pyeed.fetch.proteinfetcher import ProteinFetcher
 
         nest_asyncio.apply()
@@ -436,20 +434,3 @@ def from_ncbi(self):
     def from_accessions(self):
         raise DeprecationWarning("This method is deprecated. Use `get_ids` instead.")
 
-
-if __name__ == "__main__":
-
-    mat_accessions = [
-        "MBP1912539.1",
-        "SEV92896.1",
-        "MBO8174569.1",
-        "WP_042680787.1",
-        "NPA47376.1",
-        "WP_167889085.1",
-        "WP_048165429.1",
-        "ACS90033.1",
-    ]
-
-    mats = ProteinRecord.get_ids(mat_accessions)
-
-    print(mats)
diff --git a/pyeed/core/region.py b/pyeed/core/region.py
@@ -38,7 +38,7 @@ class Region(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/sequence.py b/pyeed/core/sequence.py
@@ -38,7 +38,7 @@ class Sequence(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/sequencerecord.py b/pyeed/core/sequencerecord.py
@@ -62,7 +62,7 @@ class SequenceRecord(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _object_terms: Set[str] = PrivateAttr(default={"http://edamontology.org/data_0849"})

diff --git a/pyeed/core/site.py b/pyeed/core/site.py
@@ -35,7 +35,7 @@ class Site(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/core/standardnumbering.py b/pyeed/core/standardnumbering.py
@@ -47,7 +47,7 @@ class StandardNumbering(
 
     _repo: Optional[str] = PrivateAttr(default="https://github.com/PyEED/pyeed")
     _commit: Optional[str] = PrivateAttr(
-        default="6a0708b0501e7ce4e280bbea2af990b0d473371d"
+        default="6c9e70ca7a0928f3e16ace15c2fd2e16a2b6c0d7"
     )
 
     _raw_xml_data: Dict = PrivateAttr(default_factory=dict)

diff --git a/pyeed/fetch/ncbiproteinmapper.py b/pyeed/fetch/ncbiproteinmapper.py
@@ -45,7 +45,7 @@ def map(self, responses: List[str]) -> List[ProteinRecord]:
 
         protein_infos = []
         for record in seq_records:
-            protein_info = ProteinRecord(id=record.id, sequence=str(record.seq))
+            protein_info = ProteinRecord(source_id=record.id, sequence=str(record.seq))
 
             protein_info.organism = Organism(**self.map_organism(record))
 

diff --git a/pyeed/fetch/requester.py b/pyeed/fetch/requester.py
@@ -135,13 +135,17 @@ def make_batches(self):
         """
 
         batches = []
+        print(self.ids)
+        print(self.batch_size)
         for i in range(0, len(self.ids), self.batch_size):
             batch = self.ids[i : i + self.batch_size]
+            print(batch)
             if len(batch) > 1:
                 batch_string = ",".join(batch)
             else:
                 batch_string = str(batch[0])
             batches.append(batch_string)
 
+        print(batches)
         self.ids = batches
         return batches
diff --git a/tests/unit/alignment_tests/test_clustalo.py b/tests/unit/alignment_tests/test_clustalo.py
@@ -0,0 +1,32 @@
+
+# Generated by CodiumAI
+from pyeed.align.clustalo import ClustalOmega
+from pytest_mock import mocker
+
+
+import pytest
+
+class TestClustalOmega:
+
+    # ClustalOmega aligns multiple sequences and returns the alignment result.
+    def test_align_multiple_sequences(self):
+        # Arrange
+        sequences = ["ATCG", "GCTA", "TTAA"]
+        clustal_omega = ClustalOmega()
+
+        # Act
+        alignment = clustal_omega.align(sequences)
+
+        # Assert
+        assert isinstance(alignment, MultipleSeqAlignment)
+        assert len(alignment) == len(sequences)
+
+    # ClustalOmega fails to get the image from Docker Hub.
+    def test_fail_to_get_image_from_docker_hub(self):
+        # Arrange
+        clustal_omega = ClustalOmega()
+        clustal_omega._client.images.get.side_effect = docker.errors.ImageNotFound
+
+        # Act and Assert
+        with pytest.raises(Exception):
+            clustal_omega.run_container(command="", data=[])
diff --git a/tests/unit/alignment_tests/test_hmm.py b/tests/unit/alignment_tests/test_hmm.py
@@ -0,0 +1,21 @@
+
+# Generated by CodiumAI
+from pyeed.core.alignment import Alignment
+from pyeed.align.hmm import HMM
+
+
+import pytest
+
+class TestHMM:
+
+    # HMM can be initialized with a name and an Alignment object
+    def test_initialized_with_name_and_alignment(self):
+        alignment = Alignment()
+        alignment.add_to_input_sequences(source_id="seq1", sequence="ATCG")
+        alignment.add_to_input_sequences(source_id="seq2", sequence="GCTA")
+
+        hmm = HMM(name="test_hmm", alignment=alignment)
+
+        assert hmm.name == "test_hmm"
+        assert hmm.alignment == alignment
+        assert hmm.model is None
diff --git a/tests/unit/network_tests/test_newtork_graph_build.py b/tests/unit/network_tests/test_newtork_graph_build.py
@@ -1,8 +1,11 @@
+import json
+
+import pytest
+
 from pyeed.core import ProteinRecord
 from pyeed.network import SequenceNetwork
 
 
-
 class TestNetworkGraphBuild:
 
     def test_general_build_networkx(self):
@@ -24,33 +27,10 @@ def test_general_build_networkx(self):
             sequences=mats,
             weight="identity",
             dimensions=2,
-        )
-
-        assert network.network is not None
-
-
-    def test_cytoscope(self):
-        mat_accessions = [
-            "MBP1912539.1",
-            "SEV92896.1",
-            "MBO8174569.1",
-            "WP_042680787.1",
-        ]
-        mats = ProteinRecord.get_ids(mat_accessions)
-        # Create a network
-        network = SequenceNetwork(
-            sequences=mats,
-            weight="identity",
-            dimensions=2,
-        )
-        threshhold = 0.85
-        # now create a cytoscape graph
-        # careful if at this point cytoscope is not installed and running in background test will fail
-        network.create_cytoscape_graph(collection="tests", title="test_cytoscape", threshold=threshhold)
-        # check if the hidden edeges are above the threshold
-        assert [item[1] for item in list(network._get_edges_visibilities().items())].count(False) == 4
+        )    
+
+    def test_graph_build(self):
 
-    def test_cytoscape_degree(self):
         mat_accessions = [
             "MBP1912539.1",
             "SEV92896.1",
@@ -95,4 +75,3 @@ def test_cytoscape_nodes_size(self):
         network.set_nodes_size(column_name="degree_with_threshold_{}".format(threshhold), min_size=20, max_size=100)
         network.color_nodes(column_name='species')
 
-