aiagents4pharma 1.13.1__py3-none-any.whl → 1.14.1__py3-none-any.whl

aiagents4pharma/talk2biomodels/tools/get_annotation.py

@@ -0,0 +1,304 @@
+#!/usr/bin/env python3
+
+"""
+This module contains the `GetAnnotationTool` for fetching species annotations 
+based on the provided model and species names.
+"""
+import math
+from typing import List, Annotated, Type
+import logging
+from dataclasses import dataclass
+from pydantic import BaseModel, Field
+import basico
+import pandas as pd
+from langgraph.types import Command
+from langgraph.prebuilt import InjectedState
+from langchain_core.tools.base import BaseTool
+from langchain_core.tools.base import InjectedToolCallId
+from langchain_core.messages import ToolMessage
+from .load_biomodel import ModelData, load_biomodel
+from ..api.uniprot import search_uniprot_labels
+from ..api.ols import search_ols_labels
+from ..api.kegg import fetch_kegg_annotations
+
+# Initialize logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+ols_ontology_abbreviations = {'pato', 'chebi', 'sbo', 'fma', 'pr','go'}
+
+def prepare_content_msg(species_not_found: List[str],
+                        species_without_description: List[str]):
+    """
+    Prepare the content message.
+    """
+    content = 'Successfully extracted annotations for the species.'
+    if species_not_found:
+        content += f'''The following species do not exist, and
+                        hence their annotations were not extracted:
+                        {', '.join(species_not_found)}.'''
+    if species_without_description:
+        content += f'''The descriptions for the following species
+                        were not found:
+                        {", ".join(species_without_description)}.'''
+    return content
+
+@dataclass
+class ArgumentData:
+    """
+    Dataclass for storing the argument data.
+    """
+    experiment_name: Annotated[str, "An AI assigned _ separated name of"
+                                    " the experiment based on human query"
+                                    " and the context of the experiment."
+                                    " This must be set before the experiment is run."]
+    list_species_names: List[str] = Field(
+        default=None,
+        description='''List of species names to fetch annotations for.
+                      If not provided, annotations for all
+                      species in the model will be fetched.'''
+    )
+
+class GetAnnotationInput(BaseModel):
+    """
+    Input schema for annotation tool.
+    """
+    arg_data: ArgumentData = Field(description="argument data")
+    sys_bio_model: ModelData = Field(description="model data")
+    tool_call_id: Annotated[str, InjectedToolCallId]
+    state: Annotated[dict, InjectedState]
+
+class GetAnnotationTool(BaseTool):
+    """
+    Tool for fetching species annotations based on the provided model and species names.
+    """
+    name: str = "get_annotation"
+    description: str = '''A tool to extract annotations for a list of species names
+                        based on the provided model. Annotations include
+                        the species name, description, database, ID, link,
+                        and qualifier. The tool can handle multiple species
+                        in a single invoke.'''
+    args_schema: Type[BaseModel] = GetAnnotationInput
+    return_direct: bool = False
+
+    def _run(self,
+             arg_data: ArgumentData,
+             tool_call_id: Annotated[str, InjectedToolCallId],
+             state: Annotated[dict, InjectedState],
+             sys_bio_model: ModelData = None) -> str:
+        """
+        Run the tool.
+        """
+        logger.info("Running the GetAnnotationTool tool for species %s, %s",
+                    arg_data.list_species_names,
+                    arg_data.experiment_name)
+
+        # Prepare the model object
+        sbml_file_path = state['sbml_file_path'][-1] if state['sbml_file_path'] else None
+        model_object = load_biomodel(sys_bio_model, sbml_file_path=sbml_file_path)
+
+        # Extract all the species names from the model
+        df_species = basico.model_info.get_species(model=model_object.copasi_model)
+
+        if df_species is None:
+            # for example this may happen with model 20
+            raise ValueError("Unable to extract species from the model.")
+        # Fetch annotations for the species names
+        arg_data.list_species_names = arg_data.list_species_names or df_species.index.tolist()
+
+        (annotations_df,
+         species_not_found,
+         species_without_description) = self._fetch_annotations(arg_data.list_species_names)
+
+        # Check if annotations are empty
+        # If empty, return a message
+        if annotations_df.empty:
+            logger.warning("The annotations dataframe is empty.")
+            return prepare_content_msg(species_not_found, species_without_description)
+
+        # Process annotations
+        annotations_df = self._process_annotations(annotations_df)
+
+        # Prepare the simulated data
+        dic_annotations_data = {
+            'name': arg_data.experiment_name,
+            'source': sys_bio_model.biomodel_id if sys_bio_model.biomodel_id else 'upload',
+            'tool_call_id': tool_call_id,
+            'data': annotations_df.to_dict()
+        }
+
+        # Update the state with the annotations data
+        dic_updated_state_for_model = {}
+        for key, value in {
+            "model_id": [sys_bio_model.biomodel_id],
+            "sbml_file_path": [sbml_file_path],
+            "dic_annotations_data": [dic_annotations_data]
+        }.items():
+            if value:
+                dic_updated_state_for_model[key] = value
+
+        return Command(
+            update=dic_updated_state_for_model | {
+                "messages": [
+                    ToolMessage(
+                        content=prepare_content_msg(species_not_found,
+                                                    species_without_description),
+                        artifact=True,
+                        tool_call_id=tool_call_id
+                    )
+                ]
+            }
+        )
+
+    def _fetch_annotations(self, list_species_names: List[str]) -> tuple:
+        """
+        Fetch annotations for the given species names from the model.
+        In this method, we fetch the MIRIAM annotations for the species names.
+        If the annotation is not found, we add the species to the list of
+        species not found. If the annotation is found, we extract the descriptions
+        from the annotation and add them to the data list.
+
+        Args:
+            list_species_names (List[str]): List of species names to fetch annotations for.
+
+        Returns:
+            tuple: A tuple containing the annotations dataframe, species not found list,
+                   and description not found list.
+        """
+        species_not_found = []
+        description_not_found = []
+        data = []
+
+        # Loop through the species names
+        for species in list_species_names:
+            # Get the MIRIAM annotation for the species
+            annotation = basico.get_miriam_annotation(name=species)
+            # If the annotation is not found, add the species to the list
+            if annotation is None:
+                species_not_found.append(species)
+                continue
+
+            # Extract the descriptions from the annotation
+            descriptions = annotation.get("descriptions", [])
+
+            if descriptions == []:
+                description_not_found.append(species)
+                continue
+
+            # Loop through the descriptions and add them to the data list
+            for desc in descriptions:
+                data.append({
+                    "Species Name": species,
+                    "Link": desc["id"],
+                    "Qualifier": desc["qualifier"]
+                })
+
+        # Create a dataframe from the data list
+        annotations_df = pd.DataFrame(data)
+
+        # Return the annotations dataframe and the species not found list
+        return annotations_df, species_not_found, description_not_found
+
+    def _process_annotations(self, annotations_df: pd.DataFrame) -> pd.DataFrame:
+        """
+        Process annotations dataframe to add additional information.
+        In this method, we add a new column for the ID, a new column for the database,
+        and a new column for the description. We then reorder the columns and process
+        the link to format it correctly.
+
+        Args:
+            annotations_df (pd.DataFrame): Annotations dataframe to process.
+
+        Returns:
+            pd.DataFrame: Processed annotations dataframe
+        """
+        logger.info("Processing annotations.")
+        # Add a new column for the ID
+        # Get the ID from the link key
+        annotations_df['Id'] = annotations_df['Link'].str.split('/').str[-1]
+
+        # Add a new column for the database
+        # Get the database from the link key
+        annotations_df['Database'] = annotations_df['Link'].str.split('/').str[-2]
+
+        # Fetch descriptions for the IDs based on the database type
+        # by qyerying the respective APIs
+        identifiers = annotations_df[['Id', 'Database']].to_dict(orient='records')
+        descriptions = self._fetch_descriptions(identifiers)
+
+        # Add a new column for the description
+        # Get the description from the descriptions dictionary
+        # based on the ID. If the description is not found, use '-'
+        annotations_df['Description'] = annotations_df['Id'].apply(lambda x:
+                                                                   descriptions.get(x, '-'))
+        # annotations_df.index = annotations_df.index + 1
+
+        # Reorder the columns
+        annotations_df = annotations_df[
+            ["Species Name", "Description", "Database", "Id", "Link", "Qualifier"]
+        ]
+
+        # Process the link to format it correctly
+        annotations_df["Link"] = annotations_df["Link"].apply(self._process_link)
+
+        # Return the processed annotations dataframe
+        return annotations_df
+
+    def _process_link(self, link: str) -> str:
+        """
+        Process link to format it correctly.
+        """
+        for ols_ontology_abbreviation in ols_ontology_abbreviations:
+            if ols_ontology_abbreviation +'/' in link:
+                link = link.replace(f"{ols_ontology_abbreviation}/", "")
+        if "kegg.compound" in link:
+            link = link.replace("kegg.compound/", "kegg.compound:")
+        return link
+
+    def _fetch_descriptions(self, data: List[dict[str, str]]) -> dict[str, str]:
+        """
+        Fetch protein names or labels based on the database type.
+        """
+        logger.info("Fetching descriptions for the IDs.")
+        results = {}
+        grouped_data = {}
+
+        # In the following loop, we create a dictionary with database as the key
+        # and a list of identifiers as the value. If either the database or the
+        # identifier is NaN, we set it to None.
+        for entry in data:
+            identifier = entry.get('Id')
+            database = entry.get('Database')
+            # Check if database is NaN
+            if isinstance(database, float):
+                if math.isnan(database):
+                    database = None
+                    results[identifier or "unknown"] = "-"
+            else:
+                database = database.lower()
+                grouped_data.setdefault(database, []).append(identifier)
+
+        # In the following loop, we fetch the descriptions for the identifiers
+        # based on the database type.
+        # Constants
+
+        for database, identifiers in grouped_data.items():
+            if database == 'uniprot':
+                results.update(search_uniprot_labels(identifiers))
+            elif database in ols_ontology_abbreviations:
+                annotations = search_ols_labels([
+                        {"Id": id_, "Database": database}
+                        for id_ in identifiers
+                    ])
+                for identifier in identifiers:
+                    results[identifier] = annotations.get(database, {}).get(identifier, "-")
+            elif database == 'kegg.compound':
+                data = [{"Id": identifier, "Database": "kegg.compound"}
+                        for identifier in identifiers]
+                annotations = fetch_kegg_annotations(data)
+                for identifier in identifiers:
+                    results[identifier] = annotations.get(database, {}).get(identifier, "-")
+            else:
+                for identifier in identifiers:
+                    results[identifier] = "-"
+        return results

aiagents4pharma/talk2biomodels/tools/load_arguments.py

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+
+"""
+A utility module for defining the dataclasses
+for the arguments to set up initial settings
+before the experiment is run.
+"""
+
+import logging
+from dataclasses import dataclass
+from typing import Union, List, Optional, Annotated
+from pydantic import Field
+import basico
+
+# Initialize logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+@dataclass
+class TimeData:
+    """
+    Dataclass for storing the time data.
+    """
+    duration: Union[int, float] = Field(
+        description="Duration of the simulation",
+        default=100)
+    interval: Union[int, float] = Field(
+        description="The interval is the time step or"
+        " the step size of the simulation. It is unrelated"
+        " to the step size of species concentration and parameter values.",
+        default=100)
+
+@dataclass
+class SpeciesInitialData:
+    """
+    Dataclass for storing the species initial data.
+    """
+    species_name: List[str] = Field(
+        description="List of species whose initial concentration is to be set."
+        " This does not include species that reoccur or the species whose"
+        " concentration is to be determined/observed at the end of the experiment."
+        " Do not hallucinate the species name.",
+        default=[])
+    species_concentration: List[Union[int, float]] = Field(
+        description="List of initial concentrations of species."
+        " This does not include species that reoccur or the species whose"
+        " concentration is to be determined/observed at the end of the experiment."
+        " Do not hallucinate the species concentration.",
+        default=[])
+
+@dataclass
+class TimeSpeciesNameConcentration:
+    """
+    Dataclass for storing the time,
+    species name, and concentration data.
+    """
+    time: Union[int, float] = Field(description="time point where the event occurs")
+    species_name: str = Field(description="species name")
+    species_concentration: Union[int, float] = Field(
+        description="species concentration at the time point")
+
+@dataclass
+class ReocurringData:
+    """
+    Dataclass for species that reoccur. In other words,
+    the concentration of the species resets to a certain
+    value after a certain time interval.
+    """
+    data: List[TimeSpeciesNameConcentration] = Field(
+        description="List of time, name, and concentration data"
+                    " of species or parameters that reoccur",
+                    default=[])
+
+@dataclass
+class ArgumentData:
+    """
+    Dataclass for storing the argument data.
+    """
+    experiment_name: Annotated[str, "An AI assigned _ separated name of"
+                                    " the experiment based on human query"
+                                    " and the context of the experiment."
+                                    " This must be set before the experiment is run."]
+    time_data: Optional[TimeData] = Field(
+        description="time data",
+        default=None)
+    species_to_be_analyzed_before_experiment: Optional[SpeciesInitialData] = Field(
+        description="Data of species whose initial concentration"
+        " is to be set before the experiment. This does not include"
+        " species that reoccur or the species whose concentration"
+        " is to be determined at the end of the experiment.",
+        default=None)
+    reocurring_data: Optional[ReocurringData] = Field(
+        description="List of concentration and time data of species that"
+        " reoccur. For example, a species whose concentration resets"
+        " to a certain value after a certain time interval.",
+        default=None)
+
+def add_rec_events(model_object, reocurring_data):
+    """
+    Add reocurring events to the model.
+
+    Args:
+        model_object: The model object.
+        reocurring_data: The reocurring data.
+
+    Returns:
+        None
+    """
+    for row in reocurring_data.data:
+        tp, sn, sc = row.time, row.species_name, row.species_concentration
+        basico.add_event(f'{sn}_{tp}',
+                            f'Time > {tp}',
+                            [[sn, str(sc)]],
+                            model=model_object.copasi_model)