Embeddings esm (#93)

* added new implementation * defined data graph model * renamed pyeed class * implemented db connector with respect to neomodel * added working uniprot fetcher with db transaction * refactored requester * 😵‍💫 * added implementation to calculate embeddings
PyEED · Oct 14, 2024 · 50ce1f1 · 50ce1f1
1 parent ee41af2
commit 50ce1f1
Show file tree

Hide file tree

Showing 63 changed files with 3,388 additions and 588 deletions.
diff --git a/README.md b/README.md
@@ -7,7 +7,7 @@
 [![Documentation](https://github.com/PyEED/pyeed/actions/workflows/make_docs.yaml/badge.svg)](https://github.com/PyEED/pyeed/actions/workflows/make_docs.yaml)
 
 ## About 📖
-pyEED is a toolkit enabling object-oriented analysis of protein sequences, instead of working with sequences in a file-oriented fashion. This will enable the user to easily access and manipulate sequence information and to perform analyses on the sequence data.  
+pyeed is a toolkit enabling object-oriented analysis of protein sequences, instead of working with sequences in a file-oriented fashion. This will enable the user to easily access and manipulate sequence information and to perform analyses on the sequence data.  
 This library is currently under development and thus the API is subject to change.
 
 
@@ -20,9 +20,7 @@ pip install git+https://github.com/PyEED/pyeed.git
 
 ## Quick start 🚀
 
-Library is currently refactored, quick start will be updated soon!
-
-## Documentation 📘
-
-Check out the [documentation](https://pyeed.github.io/pyeed/) for in-depth information on how to setup `pyeed`, 
-use the build-in tools, and store sequence data in databases. 
+### Launch Neo4j database via Docker and mount to a local directory
+```bash
+docker run --name pyeed-neo4j -p 7474:7474 -p 7687:7687 -v $PWD/data:/data -v $PWD/logs:/logs -v $PWD/import:/var/lib/neo4j/import -v $PWD/plugins:/plugins -e NEO4J_AUTH=neo4j/test -d neo4j
+```
diff --git a/docs/examples/ids.json b/docs/examples/ids.json
@@ -1,68 +1 @@
-[
-    "WP_211530438",
-    "RUM32465",
-    "NOZ59931",
-    "MCI2415466",
-    "MCD6512403",
-    "MCL4350655",
-    "RLF67685",
-    "RLE93954",
-    "TMJ11138",
-    "WP_248897180",
-    "MBU7022768",
-    "NPA53530",
-    "MCL4451275",
-    "MBP7070042",
-    "NHV96297",
-    "NQE45598",
-    "PLJ76955",
-    "Q6L123",
-    "Q8TZW1",
-    "Q8ZYP7",
-    "Q46CW6",
-    "Q18H49",
-    "C3MJ04",
-    "Q8TV85",
-    "A6UU75",
-    "Q97CT6",
-    "O59488",
-    "WCN31494",
-    "O27429",
-    "Q2FN14",
-    "P0DF56",
-    "A0B742",
-    "Q2NEB3",
-    "Q9HM12",
-    "A5UMW7",
-    "Q9YBK2",
-    "A4G0T1",
-    "Q12WC8",
-    "A2BIZ8",
-    "O30186",
-    "C3NF87",
-    "A6UQS6",
-    "A1RSD7",
-    "A8MD44",
-    "P0CW62",
-    "A6VHQ4",
-    "A9A923",
-    "B6YUL1",
-    "Q5V2S5",
-    "Q4JAL1",
-    "B1YC36",
-    "P0CW63",
-    "Q980S9",
-    "Q3IQF5",
-    "Q9V1P7",
-    "Q8PWS4",
-    "Q5JF22",
-    "Q8TU57",
-    "C5A4B7",
-    "B0R5A8",
-    "P26498",
-    "O67275",
-    "A7I771",
-    "Q976F3",
-    "A3MY01",
-    "Q58605"
-]
+["Q9YBK2", "A6UQS6", "A1RSD7", "Q46CW6", "Q4JAL1", "Q8TU57", "P26498", "Q980S9", "B1YC36", "C3MJ04", "Q9HM12", "A3MY01", "A9A923", "Q5V2S5", "A4G0T1", "Q8TZW1", "Q6L123", "Q2FN14", "Q8PWS4", "Q18H49", "Q8ZYP7", "A8MD44", "P0DF56", "B0R5A8", "B6YUL1", "O30186", "A5UMW7", "Q2NEB3", "A6VHQ4", "Q12WC8", "A7I771", "Q5JF22", "Q8TV85", "O67275", "A2BIZ8", "Q3IQF5", "Q976F3", "P0CW63", "P0CW62", "C5A4B7", "O27429", "C3NF87", "Q97CT6", "Q58605", "Q9V1P7", "A6UU75", "O59488", "A0B742", "RUM32465.1", "NPA53530.1", "RLF67685.1", "MCL4350655.1", "NOZ59931.1", "WP_248897180.1", "MCL4451275.1", "RLE93954.1", "MBU7022768.1", "NHV96297.1", "PLJ76955.1", "WCN31494.1", "WP_211530438.1", "MBP7070042.1", "MCD6512403.1", "MCI2415466.1", "TMJ11138.1", "NQE45598.1"]
diff --git a/docs/model_diagram.json b/docs/model_diagram.json
@@ -0,0 +1,247 @@
+{
+    "style": {
+        "node-color": "#ffffff",
+        "border-color": "#000000",
+        "caption-color": "#000000",
+        "arrow-color": "#000000",
+        "label-background-color": "#ffffff",
+        "directionality": "directed",
+        "arrow-width": 5
+    },
+    "nodes": [
+        {
+            "id": "n0",
+            "position": {
+                "x": 0,
+                "y": 0
+            },
+            "caption": "",
+            "style": {},
+            "labels": [
+                "StrictStructuredNode"
+            ],
+            "properties": {}
+        },
+        {
+            "id": "n1",
+            "position": {
+                "x": 346.4101615137755,
+                "y": 199.99999999999997
+            },
+            "caption": "",
+            "style": {},
+            "labels": [
+                "Organism"
+            ],
+            "properties": {
+                "taxonomy_id": "int - required",
+                "name": "str",
+                "domain": "str",
+                "kingdom": "str",
+                "phylum": "str",
+                "tax_class": "str",
+                "order": "str",
+                "family": "str",
+                "genus": "str",
+                "species": "str"
+            }
+        },
+        {
+            "id": "n2",
+            "position": {
+                "x": 2.4492935982947064e-14,
+                "y": 400.0
+            },
+            "caption": "",
+            "style": {},
+            "labels": [
+                "Site"
+            ],
+            "properties": {
+                "site_id": "id - unique",
+                "name": "str",
+                "positions": "list[int] - required",
+                "annotation": "str - required"
+            }
+        },
+        {
+            "id": "n3",
+            "position": {
+                "x": -346.4101615137754,
+                "y": 200.00000000000014
+            },
+            "caption": "",
+            "style": {},
+            "labels": [
+                "Region"
+            ],
+            "properties": {
+                "region_id": "id - unique",
+                "start": "int - required",
+                "end": "int - required",
+                "annotation": "str - required"
+            }
+        },
+        {
+            "id": "n4",
+            "position": {
+                "x": -346.4101615137755,
+                "y": -199.99999999999991
+            },
+            "caption": "",
+            "style": {},
+            "labels": [
+                "GOAnnotation"
+            ],
+            "properties": {
+                "go_id": "str - required",
+                "term": "str",
+                "definition": "str"
+            }
+        },
+        {
+            "id": "n5",
+            "position": {
+                "x": -7.347880794884119e-14,
+                "y": -400.0
+            },
+            "caption": "",
+            "style": {},
+            "labels": [
+                "Protein"
+            ],
+            "properties": {
+                "accession_id": "str - required",
+                "sequence": "str - required",
+                "name": "str",
+                "seq_length": "int - required",
+                "mol_weight": "float",
+                "ec_number": "str",
+                "nucleotide_id": "str",
+                "locus_tag": "str",
+                "structure_ids": "list[str]",
+                "go_terms": "list[str]",
+                "embedding": "list[float]"
+            }
+        },
+        {
+            "id": "n6",
+            "position": {
+                "x": 346.41016151377534,
+                "y": -200.00000000000017
+            },
+            "caption": "",
+            "style": {},
+            "labels": [
+                "DNA"
+            ],
+            "properties": {
+                "accession_id": "str - required",
+                "sequence": "str - required",
+                "name": "str",
+                "seq_length": "int - required",
+                "go_terms": "list[str]",
+                "embedding": "list[float]",
+                "gc_content": "float"
+            }
+        }
+    ],
+    "relationships": [
+        {
+            "id": "e0",
+            "type": "ORIGINATES_FROM",
+            "style": {},
+            "properties": {},
+            "fromId": "n5",
+            "toId": "n1"
+        },
+        {
+            "id": "e1",
+            "type": "ORIGINATES_FROM",
+            "style": {},
+            "properties": {},
+            "fromId": "n6",
+            "toId": "n1"
+        },
+        {
+            "id": "e2",
+            "type": "ASSOCIATED_WITH",
+            "style": {},
+            "properties": {},
+            "fromId": "n4",
+            "toId": "n5"
+        },
+        {
+            "id": "e3",
+            "type": "ASSOCIATED_WITH",
+            "style": {},
+            "properties": {},
+            "fromId": "n4",
+            "toId": "n6"
+        },
+        {
+            "id": "e4",
+            "type": "ORIGINATES_FROM",
+            "style": {},
+            "properties": {},
+            "fromId": "n5",
+            "toId": "n1"
+        },
+        {
+            "id": "e5",
+            "type": "HAS_SITE",
+            "style": {},
+            "properties": {},
+            "fromId": "n5",
+            "toId": "n2"
+        },
+        {
+            "id": "e6",
+            "type": "HAS_REGION",
+            "style": {},
+            "properties": {},
+            "fromId": "n5",
+            "toId": "n3"
+        },
+        {
+            "id": "e7",
+            "type": "ASSOCIATED_WITH",
+            "style": {},
+            "properties": {},
+            "fromId": "n5",
+            "toId": "n4"
+        },
+        {
+            "id": "e8",
+            "type": "ORIGINATES_FROM",
+            "style": {},
+            "properties": {},
+            "fromId": "n6",
+            "toId": "n1"
+        },
+        {
+            "id": "e9",
+            "type": "HAS_SITE",
+            "style": {},
+            "properties": {},
+            "fromId": "n6",
+            "toId": "n2"
+        },
+        {
+            "id": "e10",
+            "type": "HAS_REGION",
+            "style": {},
+            "properties": {},
+            "fromId": "n6",
+            "toId": "n3"
+        },
+        {
+            "id": "e11",
+            "type": "ASSOCIATED_WITH",
+            "style": {},
+            "properties": {},
+            "fromId": "n6",
+            "toId": "n4"
+        }
+    ]
+}
diff --git a/pyeed/__init__.py b/pyeed/__init__.py
@@ -1,21 +1 @@
-import os
-
-from .core.abstractannotation import AbstractAnnotation
-from .core.alignmentresult import AlignmentResult
-from .core.annotation import Annotation
-from .core.blastdata import BlastData
-from .core.clustalomegaresult import ClustalOmegaResult
-from .core.cluster import Cluster
-from .core.dnarecord import DNARecord
-from .core.numberedsequence import NumberedSequence
-from .core.ontology import Ontology
-from .core.organism import Organism
-from .core.pairwisealignmentresult import PairwiseAlignmentResult
-from .core.proteinrecord import ProteinRecord
-from .core.region import Region
-from .core.regionset import RegionSet
-from .core.sequence import Sequence
-from .core.sequencerecord import SequenceRecord
-from .core.sequencetype import SequenceType
-from .core.site import Site
-from .core.standardnumbering import StandardNumbering
+from pyeed.pyeed import Pyeed
diff --git a/pyeed/fetch/__init__.py → pyeed/adapter/__init__.py b/pyeed/fetch/__init__.py → pyeed/adapter/__init__.py