biocypher 0.9.2__py3-none-any.whl → 0.12.3__py3-none-any.whl

biocypher/output/in_memory/_pandas.py

@@ -1,6 +1,5 @@
 import pandas as pd
 
-from biocypher._create import BioCypherEdge, BioCypherNode, BioCypherRelAsNode
 from biocypher.output.in_memory._in_memory_kg import _InMemoryKG
 
 
@@ -20,65 +19,8 @@ class PandasKG(_InMemoryKG):
     def add_edges(self, edges):
         self.add_tables(edges)
 
-    def _separate_entity_types(self, entities):
-        """
-        Given mixed iterable of BioCypher objects, separate them into lists by
-        type. Also deduplicates using the `Deduplicator` instance.
-        """
-        lists = {}
-        for entity in entities:
-            if (
-                not isinstance(entity, BioCypherNode)
-                and not isinstance(entity, BioCypherEdge)
-                and not isinstance(entity, BioCypherRelAsNode)
-            ):
-                raise TypeError(
-                    "Expected a BioCypherNode / BioCypherEdge / " f"BioCypherRelAsNode, got {type(entity)}."
-                )
-
-            if isinstance(entity, BioCypherNode):
-                seen = self.deduplicator.node_seen(entity)
-            elif isinstance(entity, BioCypherEdge):
-                seen = self.deduplicator.edge_seen(entity)
-            elif isinstance(entity, BioCypherRelAsNode):
-                seen = self.deduplicator.rel_as_node_seen(entity)
-
-            if seen:
-                continue
-
-            if isinstance(entity, BioCypherRelAsNode):
-                node = entity.get_node()
-                source_edge = entity.get_source_edge()
-                target_edge = entity.get_target_edge()
-
-                _type = node.get_type()
-                if _type not in lists:
-                    lists[_type] = []
-                lists[_type].append(node)
-
-                _source_type = source_edge.get_type()
-                if _source_type not in lists:
-                    lists[_source_type] = []
-                lists[_source_type].append(source_edge)
-
-                _target_type = target_edge.get_type()
-                if _target_type not in lists:
-                    lists[_target_type] = []
-                lists[_target_type].append(target_edge)
-                continue
-
-            _type = entity.get_type()
-            if _type not in lists:
-                lists[_type] = []
-            lists[_type].append(entity)
-
-        return lists
-
     def add_tables(self, entities):
-        """
-        Add Pandas dataframes for each node and edge type in the input.
-        """
-
+        """Add Pandas dataframes for each node and edge type in the input."""
         lists = self._separate_entity_types(entities)
 
         for _type, _entities in lists.items():

biocypher/output/templates/powershell_template.ps1

@@ -0,0 +1,60 @@
+$banner = @"
+# ============================================================================== #
+# ========                   Import Script for Powershell               ======== #
+# ============================================================================== #
+"@
+Write-Host $banner -ForegroundColor Cyan
+Write-Host "[$(Get-Date -Format 'u')] Starting Neo4j import process..." -ForegroundColor Cyan
+
+# ================================ #
+#      Neo4j Binary Settings       #
+# ================================ #
+{neo4j_bin_path}
+Write-Host "[$(Get-Date -Format 'u')] Neo4j bin path set to: $NEO4J_BIN_PATH_WINDOWS"
+
+{neo4j_version_check}
+Write-Host "[$(Get-Date -Format 'u')] Detected Neo4j version: $version"
+
+$major_version = $version.Trim().Split('.')[0]
+$major = [int]$major_version
+
+
+# ================================ #
+#    Neo4j import arguments        #
+# ================================ #
+
+if ( $major -lt 5 )
+{{
+    $args_neo4j=@(
+@'
+{args_neo4j_v4}
+'@
+)
+    Write-Host "[$(Get-Date -Format 'u')] Detected Neo4j v4 - using legacy import command." -ForegroundColor Yellow
+    Write-Host "[$(Get-Date -Format 'u')] Args for Neo4j v4:"
+    $args_neo4j -split ' ' | ForEach-Object {{ Write-Host "`t$_" }}
+}}
+else
+{{
+    $args_neo4j = @(
+@'
+{args_neo4j_v5}
+'@
+)
+    Write-Host "[$(Get-Date -Format 'u')] Detected Neo4j v5 or newer - using modern import command." -ForegroundColor Yellow
+    Write-Host "[$(Get-Date -Format 'u')] Args for Neo4j >= v5:"
+    $args_neo4j -split ' ' | ForEach-Object {{ Write-Host "`t$_" }}
+}}
+
+# ================================ #
+#    Neo4j-admin import call       #
+# ================================ #
+Write-Host "[$(Get-Date -Format 'u')] Running import command..." -ForegroundColor Cyan
+
+Invoke-Expression "$NEO4J_BIN_PATH_WINDOWS $args_neo4j"
+if ($LASTEXITCODE -eq 0) {{
+    Write-Host "[$(Get-Date -Format 'u')] Import completed successfully!" -ForegroundColor Green
+}} else {{
+    Write-Host "[$(Get-Date -Format 'u')] Import failed with exit code $LASTEXITCODE." -ForegroundColor Red
+}}
+Write-Host "[$(Get-Date -Format 'u')] Script finished." -ForegroundColor Cyan

biocypher/output/write/_batch_writer.py

@@ -162,8 +162,8 @@ class _BatchWriter(_Writer, ABC):
         which need to be overwritten by the child classes.
 
         Each batch writer instance has a fixed representation that needs to be
-        passed at instantiation via the :py:attr:`schema` argument. The instance
-        also expects an ontology adapter via :py:attr:`ontology_adapter` to be
+        passed at instantiation via the `schema` argument. The instance
+        also expects an ontology adapter via `ontology_adapter` to be
         able to convert and extend the hierarchy.
 
         Requires the following methods to be overwritten by database-specific
@@ -289,7 +289,7 @@ class _BatchWriter(_Writer, ABC):
         self._labels_orders = ["Alphabetical", "Ascending", "Descending", "Leaves"]
         if labels_order not in self._labels_orders:
             msg = (
-                f"neo4j's 'labels_order' parameter cannot be '{labels_order}',"
+                f"A batch writer 'labels_order' parameter cannot be '{labels_order}',"
                 "must be one of: {' ,'.join(self._labels_orders)}",
             )
             raise ValueError(msg)
@@ -545,7 +545,7 @@ class _BatchWriter(_Writer, ABC):
                                         f"Must be one of {self._labels_orders}"
                                     )
                                     raise ValueError(msg)
-                        # concatenate with array delimiter
+                        # concatenate with array delimiters
                         all_labels = self._write_array_string(all_labels)
                     else:
                         all_labels = self.translator.name_sentence_to_pascal(label)

biocypher/output/write/_get_writer.py

@@ -9,6 +9,7 @@ from typing import TYPE_CHECKING
 from biocypher._config import config as _config
 from biocypher._logger import logger
 from biocypher.output.write._batch_writer import _BatchWriter
+from biocypher.output.write.graph._airr import _AirrWriter
 from biocypher.output.write.graph._arangodb import _ArangoDBBatchWriter
 from biocypher.output.write.graph._neo4j import _Neo4jBatchWriter
 from biocypher.output.write.graph._networkx import _NetworkXWriter
@@ -50,6 +51,7 @@ DBMS_TO_CLASS = {
     "Tabular": _PandasCSVWriter,
     "networkx": _NetworkXWriter,
     "NetworkX": _NetworkXWriter,
+    "airr": _AirrWriter,
 }
 
 
@@ -93,6 +95,8 @@ def get_writer(
         raise ValueError(msg)
 
     if writer is not None:
+        # FIXME: passing dbms_config as kwargs would ensure that we pass all config by default.
+        # TODO: to do that, config options names need to be aligned first.
         return writer(
             translator=translator,
             deduplicator=deduplicator,
@@ -105,6 +109,7 @@ def get_writer(
             import_call_file_prefix=dbms_config.get("import_call_file_prefix"),
             wipe=dbms_config.get("wipe"),
             strict_mode=strict_mode,
+            labels_order=dbms_config.get("labels_order"),  # batch writer
             skip_bad_relationships=dbms_config.get("skip_bad_relationships"),  # neo4j
             skip_duplicate_nodes=dbms_config.get("skip_duplicate_nodes"),  # neo4j
             db_user=dbms_config.get("user"),  # psql

biocypher/output/write/graph/_airr.py

@@ -0,0 +1,32 @@
+"""Module to provide the AnnData writer class for BioCypher."""
+
+from biocypher._logger import logger
+from biocypher.output.write._writer import _Writer
+
+
+class _AirrWriter(_Writer):
+    """A minimal placeholder writer class that implements the required methods
+    but performs no actual writing operations, since there is an existing anndata native writer functionality
+    """
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        logger.info("Placeholder writer initialized")
+
+    def _write_node_data(self, nodes) -> bool:
+        """Required implementation that does nothing with nodes."""
+        logger.info("Placeholder: Node data received but not processed")
+        return True
+
+    def _write_edge_data(self, edges) -> bool:
+        """Required implementation that does nothing with edges."""
+        logger.info("Placeholder: Edge data received but not processed")
+        return True
+
+    def _construct_import_call(self) -> str:
+        """Return a placeholder import script."""
+        return "# This is a placeholder import script\nprint('No actual import functionality implemented')"
+
+    def _get_import_script_name(self) -> str:
+        """Return a placeholder script name."""
+        return "placeholder_import.py"

biocypher/output/write/graph/_neo4j.py

@@ -1,6 +1,7 @@
 """Module to provide the Neo4j writer class."""
 
 import os
+import sys
 
 from biocypher._logger import logger
 from biocypher.output.write._batch_writer import _BatchWriter, parse_label
@@ -226,7 +227,7 @@ class _Neo4jBatchWriter(_BatchWriter):
                     self.translator.ontology.mapping.extended_schema.get(  # (seems to not work with 'not')
                         schema_label,
                     ).get("use_id")
-                    == False  # noqa: E712 (seems to not work with 'not')
+                    is False
                 ):
                     skip_id = True
 
@@ -260,12 +261,26 @@ class _Neo4jBatchWriter(_BatchWriter):
 
         Returns
         -------
-            str: The name of the import script (ending in .sh)
+            str: The name of the import script (ending in .sh or .ps1 depending on OS)
 
         """
+        if sys.platform.startswith("win"):
+            return "neo4j-admin-import-call.ps1"
         return "neo4j-admin-import-call.sh"
 
     def _construct_import_call(self) -> str:
+        """Construct the import call script for Neo4j admin import.
+
+        Returns
+        -------
+            str: The import call script.
+
+        """
+        if sys.platform.startswith("win"):
+            return self._construct_import_call_powershell()
+        return self._construct_import_call_bash()
+
+    def _construct_import_call_bash(self) -> str:
         """Function to construct the import call detailing folder and
         individual node and edge headers and data files, as well as
         delimiters and database name. Built after all data has been
@@ -278,9 +293,7 @@ class _Neo4jBatchWriter(_BatchWriter):
         """
         import_call_neo4j_v4 = self._get_import_call("import", "--database=", "--force=")
         import_call_neo4j_v5 = self._get_import_call("database import full", "", "--overwrite-destination=")
-        neo4j_version_check = (
-            f"version=$({self._get_default_import_call_bin_prefix()}neo4j-admin --version | cut -d '.' -f 1)"
-        )
+        neo4j_version_check = f"version=$({self.import_call_bin_prefix}neo4j-admin --version | cut -d '.' -f 1)"
 
         import_script = (
             f"#!/bin/bash\n{neo4j_version_check}\nif [[ $version -ge 5 ]]; "
@@ -288,6 +301,47 @@ class _Neo4jBatchWriter(_BatchWriter):
         )
         return import_script
 
+    def _construct_import_call_powershell(self) -> str:
+        """Construct the import call script for Neo4j admin import (PowerShell).
+
+        Returns
+        -------
+            str: PowerShell script for Neo4j admin import.
+
+        """
+        # Path to the PowerShell template
+        template_path = os.path.join(
+            os.path.dirname(os.path.abspath(__file__)),
+            "..",
+            "..",
+            "templates",
+            "powershell_template.ps1",
+        )
+
+        # Read the template file
+        with open(template_path, encoding="utf-8") as f:
+            template = f.read()
+
+        # Prepare the dynamic components for the template
+        import_call_neo4j_v4 = self._get_import_call_windows("import", "--database=", "--force=")
+        import_call_neo4j_v5 = self._get_import_call_windows("database import full", "", "--overwrite-destination=")
+
+        # Prepare the version check command
+        neo4j_version_check = (
+            f"$version = & powershell -NoProfile -ExecutionPolicy Bypass -File "
+            f'"{self.import_call_bin_prefix}neo4j-admin.ps1" --version'
+        )
+
+        # Fill in the template with the dynamic components
+        import_script = template.format(
+            neo4j_bin_path=f'$NEO4J_BIN_PATH_WINDOWS = "{self.import_call_bin_prefix}neo4j-admin.ps1"',
+            neo4j_version_check=neo4j_version_check,
+            args_neo4j_v4=import_call_neo4j_v4,
+            args_neo4j_v5=import_call_neo4j_v5,
+        )
+
+        return import_script
+
     def _get_import_call(self, import_cmd: str, database_cmd: str, wipe_cmd: str) -> str:
         """Get parametrized import call for Neo4j 4 or 5+.
 
@@ -331,3 +385,35 @@ class _Neo4jBatchWriter(_BatchWriter):
             import_call += f'--relationships="{header_path},{parts_path}" '
 
         return import_call
+
+    def _get_import_call_windows(self, import_cmd: str, database_cmd: str, wipe_cmd: str) -> str:
+        """Get parametrized import call for Neo4j 4 or 5+ (Windows).
+
+        Args:
+        ----
+            import_cmd (str): The import command to use.
+            database_cmd (str): The database command to use.
+            wipe_cmd (str): The wipe command to use.
+
+        Returns:
+        -------
+            str: The import call for Windows.
+
+        """
+        import_call = []
+        import_call.append(f"{import_cmd} ")
+        import_call.append(f"{database_cmd}{self.db_name} ")
+        import_call.append(f'--delimiter="{self.escaped_delim}" ')
+        import_call.append(f'--array-delimiter="{self.escaped_adelim}" ')
+        import_call.append(f'--quote="{self.quote}" ' if self.quote == "'" else f"--quote='{self.quote}' ")
+        import_call.append(f"{wipe_cmd}true " if self.wipe else "")
+        import_call.append("--skip-bad-relationships=true " if self.skip_bad_relationships else "")
+        import_call.append("--skip-duplicate-nodes=true " if self.skip_duplicate_nodes else "")
+        import_call.extend(
+            f'--nodes="{header_path},{parts_path}" ' for header_path, parts_path in self.import_call_nodes
+        )
+        import_call.extend(
+            f'--relationships="{header_path},{parts_path}" ' for header_path, parts_path in self.import_call_edges
+        )
+
+        return "".join(import_call)

biocypher/output/write/relational/_postgresql.py

@@ -6,7 +6,8 @@ from biocypher.output.write._batch_writer import _BatchWriter
 
 
 class _PostgreSQLBatchWriter(_BatchWriter):
-    """
+    """Write node and edge representations for PostgreSQL.
+
     Class for writing node and edge representations to disk using the
     format specified by PostgreSQL for the use of "COPY FROM...". Each batch
     writer instance has a fixed representation that needs to be passed
@@ -39,12 +40,13 @@ class _PostgreSQLBatchWriter(_BatchWriter):
         self._copy_from_csv_commands = set()
         super().__init__(*args, **kwargs)
 
-    def _get_default_import_call_bin_prefix(self):
-        """
-        Method to provide the default string for the import call bin prefix.
+    def _get_default_import_call_bin_prefix(self) -> str:
+        """Provide the default string for the import call bin prefix.
 
-        Returns:
+        Returns
+        -------
             str: The default location for the psql command
+
         """
         return ""
 
@@ -56,33 +58,36 @@ class _PostgreSQLBatchWriter(_BatchWriter):
             return "VARCHAR"
 
     def _quote_string(self, value: str) -> str:
-        """
-        Quote a string.
-        """
-
+        """Quote a string."""
         return f"{self.quote}{value}{self.quote}"
 
     def _write_array_string(self, string_list) -> str:
-        """
-        Abstract method to output.write the string representation of an array into a .csv file
-        as required by the postgresql COPY command, with '{','}' brackets and ',' separation.
+        """Write the string representation of an array into a .csv file.
+
+        Abstract method to output.write the string representation of an array
+        into a .csv file as required by the postgresql COPY command, with
+        '{','}' brackets and ',' separation.
 
         Args:
+        ----
             string_list (list): list of ontology strings
 
         Returns:
+        -------
             str: The string representation of an array for postgres COPY
+
         """
         string = ",".join(string_list)
         string = f'"{{{string}}}"'
         return string
 
     def _get_import_script_name(self) -> str:
-        """
-        Returns the name of the psql import script
+        """Return the name of the psql import script.
 
-        Returns:
+        Returns
+        -------
             str: The name of the import script (ending in .sh)
+
         """
         return f"{self.db_name}-import-call.sh"
 
@@ -91,14 +96,17 @@ class _PostgreSQLBatchWriter(_BatchWriter):
         string = string.lower()
         return string
 
-    def _write_node_headers(self):
-        """
+    def _write_node_headers(self) -> bool:
+        """Write node header files for PostgreSQL.
+
         Writes single CSV file for a graph entity that is represented
         as a node as per the definition in the `schema_config.yaml`,
         containing only the header for this type of node.
 
-        Returns:
+        Returns
+        -------
             bool: The return value. True for success, False otherwise.
+
         """
         # load headers from data parse
         if not self.node_property_dict:
@@ -158,7 +166,7 @@ class _PostgreSQLBatchWriter(_BatchWriter):
                         )
 
                     self._copy_from_csv_commands.add(
-                        f"\\copy {pascal_label} FROM '{parts_path}' DELIMITER E'{self.delim}' CSV;"
+                        f"\\copy {pascal_label} FROM '{parts_path}' DELIMITER E'{self.delim}' CSV;",
                     )
 
             # add file path to import statement
@@ -175,13 +183,14 @@ class _PostgreSQLBatchWriter(_BatchWriter):
         return True
 
     def _write_edge_headers(self):
-        """
-        Writes single CSV file for a graph entity that is represented
+        """Writes single CSV file for a graph entity that is represented
         as an edge as per the definition in the `schema_config.yaml`,
         containing only the header for this type of edge.
 
-        Returns:
+        Returns
+        -------
             bool: The return value. True for success, False otherwise.
+
         """
         # load headers from data parse
         if not self.edge_property_dict:
@@ -221,7 +230,7 @@ class _PostgreSQLBatchWriter(_BatchWriter):
                     raise ValueError(
                         "Column name '_ID' is reserved for internal use, "
                         "denoting the relationship ID. Please choose a "
-                        "different name for your column."
+                        "different name for your column.",
                     )
 
                 columns.append(f"{col_name} {col_type}")
@@ -255,7 +264,7 @@ class _PostgreSQLBatchWriter(_BatchWriter):
                         )
 
                     self._copy_from_csv_commands.add(
-                        f"\\copy {pascal_label} FROM '{parts_path}' DELIMITER E'{self.delim}' CSV;"
+                        f"\\copy {pascal_label} FROM '{parts_path}' DELIMITER E'{self.delim}' CSV;",
                     )
 
             # add file path to import statement
@@ -272,14 +281,15 @@ class _PostgreSQLBatchWriter(_BatchWriter):
         return True
 
     def _construct_import_call(self) -> str:
-        """
-        Function to construct the import call detailing folder and
+        """Function to construct the import call detailing folder and
         individual node and edge headers and data files, as well as
         delimiters and database name. Built after all data has been
         processed to ensure that nodes are called before any edges.
 
-        Returns:
+        Returns
+        -------
             str: a bash command for postgresql import
+
         """
         import_call = ""
 

{biocypher-0.9.2.dist-info → biocypher-0.12.3.dist-info}/METADATA

@@ -1,43 +1,47 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: biocypher
-Version: 0.9.2
+Version: 0.12.3
 Summary: A unifying framework for biomedical research knowledge graphs
-Home-page: https://github.com/biocypher/biocypher
-License: MIT
-Author: Sebastian Lobentanzer
-Author-email: sebastian.lobentanzer@gmail.com
-Requires-Python: >=3.10,<4.0
+Project-URL: Homepage, https://biocypher.org
+Project-URL: Documentation, https://biocypher.org
+Project-URL: Repository, https://github.com/biocypher/biocypher
+Project-URL: Issues, https://github.com/biocypher/biocypher/issues
+Project-URL: Bug Tracker, https://github.com/biocypher/biocypher/issues
+Author-email: Sebastian Lobentanzer <sebastian.lobentanzer@gmail.com>, Denes Turei <turei.denes@gmail.com>
+License: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
+Keywords: bioinformatics,biomedical-data,graph-database,knowledge-graph
 Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Natural Language :: English
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Requires-Dist: PyYAML (>=5.0)
+Requires-Python: >=3.10
 Requires-Dist: appdirs
-Requires-Dist: more_itertools
-Requires-Dist: neo4j-utils (==0.0.7)
-Requires-Dist: networkx (>=3.0,<4.0)
-Requires-Dist: pandas (>=2.0.1,<3.0.0)
-Requires-Dist: pooch (>=1.7.0,<2.0.0)
-Requires-Dist: rdflib (>=6.2.0,<7.0.0)
-Requires-Dist: tqdm (>=4.65.0,<5.0.0)
-Requires-Dist: treelib (==1.6.4)
-Project-URL: Bug Tracker, https://github.com/biocypher/biocypher/issues
-Project-URL: Repository, https://github.com/biocypher/biocypher
+Requires-Dist: more-itertools
+Requires-Dist: networkx>=3.0
+Requires-Dist: pandas>=2.0.1
+Requires-Dist: pooch>=1.7.0
+Requires-Dist: pyyaml>=5.0
+Requires-Dist: rdflib>=6.2.0
+Requires-Dist: toml>=0.10.2
+Requires-Dist: tqdm>=4.65.0
+Requires-Dist: treelib==1.6.4
+Provides-Extra: neo4j
+Requires-Dist: neo4j>=5.0; extra == 'neo4j'
+Provides-Extra: scirpy
+Requires-Dist: scirpy>=0.22.0; extra == 'scirpy'
 Description-Content-Type: text/markdown
 
 # BioCypher
 
 |     |     |     |     |
 | --- | --- | --- | --- |
-| __License__ | [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) | __Python__ | [![Python](https://img.shields.io/pypi/pyversions/biocypher)](https://www.python.org) |
+| __License__ | [![License: Apache 2.0](https://img.shields.io/badge/license-Apache%202-blue)](https://opensource.org/license/apache-2-0) | __Python__ | [![Python](https://img.shields.io/pypi/pyversions/biocypher)](https://www.python.org) |
 | __Package__ | [![PyPI version](https://img.shields.io/pypi/v/biocypher)](https://pypi.org/project/biocypher/) [![Downloads](https://static.pepy.tech/badge/biocypher)](https://pepy.tech/project/biocypher) [![DOI](https://zenodo.org/badge/405143648.svg)](https://zenodo.org/doi/10.5281/zenodo.10158203) | __Build status__ | [![CI](https://github.com/biocypher/biocypher/actions/workflows/tests_and_code_quality.yaml/badge.svg)](https://github.com/biocypher/biocypher/actions/workflows/tests_and_code_quality.yaml) [![Docs build](https://github.com/biocypher/biocypher/actions/workflows/docs.yaml/badge.svg)](https://github.com/biocypher/biocypher/actions/workflows/docs.yaml) |
 | __Tests__ | [![Coverage](https://raw.githubusercontent.com/biocypher/biocypher/coverage/coverage.svg)](https://github.com/biocypher/biocypher/actions/workflows/tests_and_code_quality.yaml) | __Docker__ | [![Latest image](https://img.shields.io/docker/v/biocypher/base)](https://hub.docker.com/repository/docker/biocypher/base/general) [![Image size](https://img.shields.io/docker/image-size/biocypher/base/latest)](https://hub.docker.com/repository/docker/biocypher/base/general) |
 | __Development__ | [![pyOpenSci](https://tinyurl.com/y22nb8up)](https://github.com/pyOpenSci/software-review/issues/110) [![Project Status: Active – The project has reached a stable, usable state and is being actively developed.](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active) [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit) [![Code style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://black.readthedocs.io/en/stable/) | __Contributions__ | [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) [![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg)](CONTRIBUTING.md) [![Powered by the Bioregistry](https://img.shields.io/static/v1?label=Powered%20by&message=Bioregistry&color=BA274A&style=flat&logo=image/png;base64,iVBORw0KGgoAAAANSUhEUgAAACgAAAAoCAYAAACM/rhtAAAACXBIWXMAAAEnAAABJwGNvPDMAAAAGXRFWHRTb2Z0d2FyZQB3d3cuaW5rc2NhcGUub3Jnm+48GgAACi9JREFUWIWtmXl41MUZxz/z291sstmQO9mQG0ISwHBtOOSwgpUQhApWgUfEowKigKI81actypaqFbWPVkGFFKU0Vgs+YgvhEAoqEUESrnDlEEhCbkLYJtlkk9399Y/N/rKbzQXt96+Zed+Z9/t7Z+adeecnuA1s5yFVSGrLOAf2qTiEEYlUZKIAfYdKE7KoBLkQSc4XgkPfXxz/owmT41ZtiVtR3j94eqxQq5aDeASIvkVb12RBtt0mb5xZsvfa/5XgnqTMcI3Eq7IQjwM+7jJJo8YvNhK/qDBUOl8A7JZWWqqu01Jeg6Pd1nW4NuBjjax6eWrRruv/M8EDqTMflmXeB0Jcbb6RIRhmTCJ0ymgC0wYjadTd9nW0tWMu+In63NNU7c3FWtvgJpXrZVlakVGU8/ltEcwzGjU3miI/ABa72vwTB5K45AEi7x2PUEl9fZsHZLuDmgPHuLJpJ82lle6iTSH6mpXp+fnt/Sa4yzhbp22yfwFkgnMaBy17kPhFmQh1997qLxztNkq35XB505fINtf0iz1WvfTQ7Pxdlj4Jdnjuny5yvpEhjHh7FQOGD/YyZi4owS86HJ+QQMDpJaBf3jUXlHD21+8q0y4LDppV/vfNO7+jzV3Pa6SOac0E8I8fSPonpm7JAVR+eRhzwU/Ofj+e49tpT/HdtGXcyLvQJ8HAtCTGfmJCF2dwfpTMz4NszX/uqqdyr+xPyVwoEK+C03PGrDX4GkJ7NBJ+txH/hCgAit7cRlNxOY62dmzmZgwzJvZJUh2gI/xnRmoOHsfe3AqQ/kho0qXs+pLzLh3FgwdT54YKxLsAQq0mbf1zHuTsltZejemHJSrlgGGDPGTXc09zdM5qTi59jZbKOg+Zb1QYI95+XokEQogPDifPDnPJFQ8uCkl8FyGmACQtn4dhxp3KINX7jnHi0ZeJnT8dla8Plbu+48zzfyJ08kh8ggIACB4zlIAhsURm3EnML6eB6Fzep1a+SUt5DS2VddTs+4GQccPRhgV1kowIQRaChhMXAPxkIev/Vl+8R/HgnqTMmI4gjH/iQOIXZSqdzQUlXDB9RPyi+1DrdVx67WMursvCkDERXYxB0ROSIOKecURMG+tBzkXAhbYbZk6teNPLkwmPzUIX71wuMiw+MHx2nEJQrWIFHSdE4pIHlFDisLZxYe1HhIwfTtLK+RSu30rVnlxGvrOapOcW9DsW3vH6CgKS4zxIXlz3Fw8dSaMmcfEcV9XHYbc/DSCZMEkgFoJzY0TeO17pVL7jANbaBoauWUJlTi4VOw+T9sazBKYl0ZB/qV/kALThQRi3vOJB0lpzw0vPMONOtOHOqRcyi7bzkEqanJo3HogBMGROUrziaGundGsOsQsyUPn6UPx2NvELZxIybhinn3uLyx9uVwaW7XbqjxdQmr2X0uy93Dh+Dtlu9zCu9vdj1PsvEWwcii7OwJAXFnoRFCoVhoxJrmr0gOQWo9qBfaorXodOHq0o1x8roN3cSMyC6ZT942uQBIlL53Jl804sV6oY9/fXAGg4WcjFdZuxlFV7GNPFRzFs7VKCRiV7ejJrTa/eDr1rFKXZOQCocEyTgHQAyUdD4B2d4cF8pohg4zC0YUFU7z5C9Jy7sVvbKPtsH6GT0tCGBtFwspBTz/zRixyApbSKk8te5+aZ4l4JdUVQWpIScmQhjGocUjJCRhcTieSjURQTF89FtttpuVaLpaya8Knp1B3OQ5Zlag/nU//9cmScS6EnONrauWjazIQv3kCoVD3quUPS+uAXHU7z1SpATpEQchSA78AwD0WVnxa1XkdjURlCJRGQHMfN/EuEjk9jyr4NRN47Hltjc58Gm0sraTjZ/w3l5BLuKkZJdFzT1f5+3Sq3NZjRDNAjaX1orb2BX2wEmkA9fvGGbvW7Q+OlUu+2wlIqdx+h3dzkJVPrda5iQJ93p+DRqcQ/PhsAw8xJ6AfHdkhuIVvoEribLl/jxKOv4Gi34T8omgnb1yOk7sdTA01AiK3J6yoGgP+gaPwHOdOP6LlTlXb3mNYXAlI8da9/e0pJBZovV2BrakYzQK/I3bg0SsiiCqClqs/0wAPB6UOVo6k3+CdEETwm1aPtP+dLlLJPSKAHOYDWCoVLlYTkKAKcCU4vO7IrhErFsLVLPXZ+V0haDcN+v8xjB9strdQfPavUA0ckefRxWNuwVNS6rBRKQB44r+Lmc5f7TRAgaFQyYzb9Dv/4gd18ASQ8/gsC0zwJNJVcw97aeWmOcDtaAW6eLXZLBchTC8EhWXbW6o+cInhMipetuu9OUvTWNnwNodzx+krlvAQIGjmECV+spyH/Ak3F5QDok+OoPXicip2HiJiWTuH6rQx6eh7BxlT0STH4xUbSUl6Df/xAIqaO9bBVn3taKUuy/ZAwYZImpvx4FYjVRgQzOec9r1vK0TmrldMiIDkO45ZXegxLLrRW13P0/heQHQ4CUhIYvfElNIHOtWaztNJ4qZQBqfFKLg3OMz135rNY624ClB0tHJcomTA5ZMGnANbaBmoOHPMy5hvZebNuLCoj71frXIN0i9pDJzj24IsIlUTCo7NI3/KyQg5ArfMleEyKBzmA6r1HO8eV+dSEySEB2G3yRpwZP1c2f+n1GjB07RIlcwNoKi7j3G839EhQF2cg6fmHmbznPRKevJ/GorIedV1wtLVzJesrV9WqQtoIHRfWjreSjwGar1ZRui3Ho7PfwHBGb3jRg6S1roGeoIuNJGBIPKV/zSF31irOrn4HXAu9B1zduhtLecelQxZZ9xTtrgC342Df8IwQyaYqBMKEWo0xaw1BI4d4DNJSWcfF32fRWnuD5NWPEDZ5lIe8NDuHq1v+ha2xGdkho4szYJg1hbj501EH6OgJ5oIS8hf/oWPm5HqNrE51vdt4nC/7k+9bIIT8GYA2Ipixn5jwjQrrZsju0XT5GubTRfiEBqFPisUvOrzPPi0VdeQ9YcJ63bWmxbzphTk7XHKvA/DrlJkfAU+Bcy2N+fA3vZK0WVoxny4idOKIfn+IO7lTz7zRObWCjdMv7VnhruOV9dws9F8u4CsAS1k1J54wYS4o6arWaaS8hvLP998yuZtnisl7wuROLkdjsKzqqtfL45FjB8gzwZnIJy6dS8Jjs3p8ausvHG3tXN26mytZO5W8Rcjsbg1Qze/X45ELHY9I7wHLXG26+CgSl8zFkDGh3zdkF2S7nep9PzhzmnK3FEGwUWOwrJr6zTdeL529EnRhf3LmfCHEBkBZiNrwIAwZkwi9a5Qzh9D6dNvXYW3jZkEJ9UdOOYPwdY/gXgdiufuGuC2C4Hy3kWXrOhmeBLQeA6jV6GLC8Y0KR613Hn+2phZaK69jqah1P/hdsCKLLIfGtnbG+f3eyfHtEHTh38mzom2SY4WQWQjE9tnBE+XIZKuQNrqCcH9wSwRdMGGSJiTnpatwTJOFMIKcgvPVX/kNIcM1gSgC8iTZfii3aEL+7fyG+C+6O8izl1GE5gAAAABJRU5ErkJggg==)](https://github.com/biopragmatics/bioregistry) |
@@ -62,7 +66,7 @@ the docs [here](https://biocypher.org).
            margin-left: auto;
            margin-right: auto;
            width: 70%;"
-    src="docs/graphical_abstract.png"
+    src="docs/assets/img/graphical-abstract-biocypher.png"
     alt="Graphical Abstract">
 </img>
 
@@ -77,9 +81,10 @@ Board](https://github.com/orgs/biocypher/projects/3/views/2).
 
 ## ⚙️ Installation / Usage
 
-Install the package from PyPI using `pip install biocypher`. More comprehensive
+Install the package from PyPI using `pip install biocypher`. For Neo4j online mode
+support, install with `pip install biocypher[neo4j]`. More comprehensive
 installation and configuration instructions can be found
-[here](https://biocypher.org/installation.html).
+[here](https://biocypher.org/BioCypher/installation/).
 
 Exemplary usage of BioCypher to build a graph database is shown in our tutorial
 and the various pipelines we have created. You can find these on the [Components
@@ -112,4 +117,3 @@ as a preprint at https://arxiv.org/abs/2212.13543.
 This project has received funding from the European Union’s Horizon 2020
 research and innovation programme under grant agreement No 965193 for DECIDER
 and No 116030 for TransQST.
-