Development

.gitignore

@@ -129,4 +129,7 @@ docs/.vitepress/dist
 docs/.vitepress/dist/*
 docs/.vitepress/cache
 docs/.vitepress/cache/*
-node_modules
+node_modules
+
+#grafana
+grafana_data/

Dockerfile

@@ -2,6 +2,7 @@ FROM continuumio/miniconda3 AS cheminf-python-ms
 
 ENV PYTHON_VERSION=3.10
 ENV RDKIT_VERSION=2023.03.1
+ENV OPENBABEL_VERSION=v3.1
 
 ARG RELEASE_VERSION
 ENV RELEASE_VERSION=${RELEASE_VERSION}
@@ -12,8 +13,9 @@ RUN apt-get update && \
     apt-get update -y && \
     apt-get install -y openjdk-11-jre
 
-RUN conda install -c conda-forge python>=$PYTHON_VERSION
+RUN conda install -c conda-forge python>=PYTHON_VERSION
 RUN conda install -c conda-forge rdkit>=RDKIT_VERSION
+RUN conda install -c conda-forge openbabel>=OPENBABEL_VERSION
 
 RUN python3 -m pip install -U pip
 

README.md

@@ -13,7 +13,7 @@
 [![framework](https://img.shields.io/badge/Framework-FastAPI-blue?style)](https://fastapi.tiangolo.com/)
 [![FastAPI Documentation](https://img.shields.io/badge/docs-fastapi-blue)](https://api.naturalproducts.net/v1/docs#/)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7747862.svg)](https://doi.org/10.5281/zenodo.7747862)
-## Overview of Cheminformatics Python Microservices
+## Overview of Cheminformatics Python Microservice
 
 This set of essential and valuable microservices is designed to be accessed via API calls to support cheminformatics. Generally, it is designed to work with SMILES-based inputs and could be used to translate between different machine-readable representations, get Natural Product (NP) likeliness scores, visualize chemical structures, and generate descriptors. In addition, the microservices also host an instance of [STOUT](https://github.com/Kohulan/Smiles-TO-iUpac-Translator) and another instance of [DECIMER](https://github.com/Kohulan/DECIMER-Image_Transformer) (two deep learning models for IUPAC name generation and optical chemical structure recognition, respectively).
 

app/__init__.py

@@ -9,4 +9,4 @@
 please raise a issue on our Github repository.
 """
 
-__version__ = "0.8.0"
+__version__ = "0.10.0"

app/main.py

@@ -2,10 +2,11 @@
 from fastapi.responses import RedirectResponse
 from fastapi_versioning import VersionedFastAPI
 
-# from .config import settings
-from .routers import chem, converters, decimer
+from .routers import chem, converters, depict, ocsr
 from fastapi.middleware.cors import CORSMiddleware
 
+from prometheus_fastapi_instrumentator import Instrumentator
+
 app = FastAPI(
     title="Cheminf Micro Services",
     description="This set of essential and valuable microservices is designed to be accessed via API calls to support cheminformatics. Generally, it is designed to work with SMILES-based inputs and could be used to translate between different machine-readable representations, get Natural Product (NP) likeliness scores, visualize chemical structures, and generate descriptors. In addition, the microservices also host an instance of STOUT and another instance of DECIMER (two deep learning models for IUPAC name generation and optical chemical structure recognition, respectively).",
@@ -33,7 +34,8 @@
 
 app.include_router(chem.router)
 app.include_router(converters.router)
-app.include_router(decimer.router)
+app.include_router(depict.router)
+app.include_router(ocsr.router)
 
 app = VersionedFastAPI(
     app,
@@ -52,7 +54,11 @@
     },
 )
 
+Instrumentator().instrument(app).expose(app)
+
 
 @app.get("/", include_in_schema=False)
 async def root():
-    return RedirectResponse(url="https://steinbeck-lab.github.io/cheminformatics-python-microservice")
+    return RedirectResponse(
+        url="https://steinbeck-lab.github.io/cheminformatics-python-microservice"
+    )

app/modules/alldescriptors.py

@@ -1,10 +1,10 @@
 from rdkit.Chem import Descriptors, QED, Lipinski, rdMolDescriptors, rdmolops
-from app.modules.rdkitmodules import (
+from app.modules.toolkits.rdkitmodules import (
     checkRo5Violations,
     checkSMILES,
     getTanimotoSimilarityRDKit,
 )
-from app.modules.cdkmodules import (
+from app.modules.toolkits.cdkmodules import (
     getCDKSDG,
     JClass,
     cdk_base,

app/modules/classyfire.py

@@ -2,7 +2,13 @@
 import json
 
 
-async def classify(smiles):
+async def classify(smiles: str):
+    """
+    This fucntion takes a smiles string and returns a json response
+    from classyfire API.
+    Args (str): SMILES string.
+    Returns (json): classyfire results.
+    """
     if any(char.isspace() for char in smiles):
         smiles = smiles.replace(" ", "+")
     url = "http://classyfire.wishartlab.com/queries/?format=json"
@@ -16,6 +22,12 @@ async def classify(smiles):
 
 
 async def result(id):
+    """
+    This fucntion takes a ID and returns a json response
+    from classyfire API.
+    Args : ID.
+    Returns (json): classyfire results.
+    """
     url = "http://classyfire.wishartlab.com/queries/" + str(id) + "?format=json"
 
     headers = {"Content-Type": "application/json"}

app/modules/coconutdescriptors.py

@@ -1,5 +1,9 @@
-from app.modules.rdkitmodules import getRDKitDescriptors, checkSMILES
-from app.modules.cdkmodules import getSugarInfo, getMurkoFramework, getCDKDescriptors
+from app.modules.toolkits.rdkitmodules import getRDKitDescriptors, checkSMILES
+from app.modules.toolkits.cdkmodules import (
+    getSugarInfo,
+    getMurkoFramework,
+    getCDKDescriptors,
+)
 from app.modules.alldescriptors import getCDKRDKitcombinedDescriptors
 from app.modules.npscorer import getNPScore
 

app/modules/coconutpreprocess.py

@@ -1,6 +1,6 @@
 from rdkit import Chem
-import app.modules.rdkitmodules as rdkitmodules
-import app.modules.cdkmodules as cdkmodules
+import app.modules.toolkits.rdkitmodules as rdkitmodules
+import app.modules.toolkits.cdkmodules as cdkmodules
 from app.modules.coconutdescriptors import getCOCONUTDescriptors
 
 

app/modules/depict.py → app/modules/depiction.py

@@ -2,7 +2,7 @@
 from rdkit import Chem
 from rdkit.Chem import rdDepictor
 from rdkit.Chem.Draw import rdMolDraw2D
-from app.modules.cdkmodules import getCDKSDG, getCIPAnnotation
+from app.modules.toolkits.cdkmodules import getCDKSDG, getCIPAnnotation
 from jpype import JClass
 
 

app/modules/cdkmodules.py → app/modules/toolkits/cdkmodules.py

@@ -401,6 +401,46 @@ def getCXSMILES(smiles: str):
     return str(CXSMILES)
 
 
+def getCanonSMILES(smiles: str):
+    """This function takes the user input SMILES and creates a
+    Canonical SMILES string with 2D atom coordinates
+    Args:
+            smiles (string): SMILES string given by the user.
+    Returns:
+            smiles (string): Canonical SMILES string.
+
+    """
+    moleculeSDG = getCDKSDG(smiles)
+    SmiFlavor = JClass(cdk_base + ".smiles.SmiFlavor")
+    SmilesGenerator = JClass(cdk_base + ".smiles.SmilesGenerator")(SmiFlavor.Absolute)
+    CanonicalSMILES = SmilesGenerator.create(moleculeSDG)
+    return str(CanonicalSMILES)
+
+
+def getInChI(smiles: str, InChIKey=False):
+    """This function takes the user input SMILES and creates a
+    InChI string
+    Args:
+            smiles (string): SMILES string given by the user.
+    Returns:
+            smiles (string): InChI/InChIKey string.
+
+    """
+    moleculeSDG = getCDKSDG(smiles)
+    InChIGeneratorFactory = JClass(cdk_base + ".inchi.InChIGeneratorFactory")
+    InChI = (
+        InChIGeneratorFactory.getInstance().getInChIGenerator(moleculeSDG).getInchi()
+    )
+    if InChIKey:
+        InChIKey = (
+            InChIGeneratorFactory.getInstance()
+            .getInChIGenerator(moleculeSDG)
+            .getInchiKey()
+        )
+        return InChIKey
+    return InChI
+
+
 async def getCDKHOSECodes(smiles: str, noOfSpheres: int, ringsize: bool):
     """This function takes the user input SMILES and returns a mol
        block as a string with Structure Diagram Layout.

app/modules/toolkits/openbabelmodules.py

@@ -0,0 +1,81 @@
+from openbabel import openbabel as ob
+from openbabel import pybel
+
+
+def getOBCanonicalSMILES(smiles: str):
+    """This function takes an input as a SMILES string and
+    returns a Canonical SMILES.
+    Args (str): SMILES string.
+    Returns (str): Canonical SMILES string.
+    """
+    if any(char.isspace() for char in smiles):
+        smiles = smiles.replace(" ", "+")
+
+    # Create an Open Babel molecule object
+    mol = ob.OBMol()
+
+    conv = ob.OBConversion()
+    conv.SetInAndOutFormats("smi", "can")
+    conv.ReadString(mol, smiles)
+
+    canSMILES = conv.WriteString(mol)
+    canSMILES = canSMILES.strip()  # Remove leading/trailing whitespace
+    return canSMILES
+
+
+def getOBInChI(smiles: str, InChIKey: bool = False):
+    """This function takes an input as a SMILES string and
+    returns a InChI
+    Args (str): SMILES string.
+    Returns (str): InChI string.
+    """
+    if any(char.isspace() for char in smiles):
+        smiles = smiles.replace(" ", "+")
+
+    # Create an Open Babel molecule object
+    mol = ob.OBMol()
+
+    # Create OBConversion
+    conv = ob.OBConversion()
+    conv.SetInAndOutFormats("smi", "inchi")
+    conv.ReadString(mol, smiles)
+
+    inchi = conv.WriteString(mol)
+    inchi = inchi.strip()  # Remove leading/trailing whitespace
+    if InChIKey:
+        conv.SetOptions("K", conv.OUTOPTIONS)
+        inchikey_ = conv.WriteString(mol).rstrip()
+        return inchikey_
+    return inchi
+
+
+def getOBMol(smiles: str, threeD: bool = False):
+    """This function takes an input as a SMILES string and
+    returns a 2D/3D mol block.
+    Args (str): SMILES string.
+    Returns (str): Mol block (2D/3D).
+    """
+    if any(char.isspace() for char in smiles):
+        smiles = smiles.replace(" ", "+")
+
+    if threeD:
+        mol = pybel.readstring("smi", smiles)
+        mol.addh()
+        mol.make3D()
+        mol.removeh()
+        return mol.write("mol")
+
+    # Create an Open Babel molecule object
+    mol = ob.OBMol()
+
+    conv = ob.OBConversion()
+    conv.SetInAndOutFormats("smi", "mol")
+    conv.ReadString(mol, smiles)
+
+    # Generate 2D coordinates
+    obBuilder = ob.OBBuilder()
+    obBuilder.Build(mol)
+
+    mol_block = conv.WriteString(mol)
+    mol_block = mol_block.strip()  # Remove leading/trailing whitespace
+    return mol_block

app/modules/rdkitmodules.py → app/modules/toolkits/rdkitmodules.py

@@ -1,7 +1,7 @@
 from chembl_structure_pipeline import standardizer
 from rdkit import Chem, DataStructs
 from rdkit.Chem import AllChem, Descriptors, QED, Lipinski, rdMolDescriptors, rdmolops
-from app.modules.cdkmodules import getCDKSDGMol
+from app.modules.toolkits.cdkmodules import getCDKSDGMol
 from hosegen import HoseGenerator
 
 
@@ -194,3 +194,38 @@ def has_stereochemistry(smiles: str):
             return True
 
     return False
+
+
+def get2Dmol(smiles: str):
+    """This function takes an input as a SMILES string and
+    returns a 2D mol block.
+    Args (str): SMILES string.
+    Returns (str): 2D Mol block.
+    """
+    if any(char.isspace() for char in smiles):
+        smiles = smiles.replace(" ", "+")
+    mol = Chem.MolFromSmiles(smiles)
+
+    if mol:
+        AllChem.Compute2DCoords(mol)
+        molfile = Chem.MolToMolBlock(mol)
+        return molfile
+    else:
+        return "Error reading SMILES string, check again."
+
+
+def getRDKitCXSMILES(smiles: str):
+    """This function takes an input as a SMILES string and
+    returns a CXSMILES with coordinates.
+    Args (str): SMILES string.
+    Returns (str): CXSMILES with coordinates.
+    """
+    if any(char.isspace() for char in smiles):
+        smiles = smiles.replace(" ", "+")
+    mol = Chem.MolFromSmiles(smiles)
+
+    if mol:
+        AllChem.Compute2DCoords(mol)
+        return Chem.MolToCXSmiles(mol)
+    else:
+        return "Error reading SMILES string, check again."