%load_ext autoreload
%autoreload 2

from dotenv import load_dotenv

load_dotenv()

True

Working with Projects

This notebook shows you how to work with Projects in Deeporigin

from deeporigin import projects
from deeporigin.platform import DeepOriginClient
from deeporigin.drug_discovery import LigandSet, BRD_DATA_DIR, Protein, PocketFinder, Ligand

# optional
client = DeepOriginClient()

/home/runner/work/do-dd-client/do-dd-client/.venv/lib/python3.11/site-packages/jwt/api_jwt.py:147: InsecureKeyLengthWarning: The HMAC key is 6 bytes long, which is below the minimum recommended length of 32 bytes for SHA256. See RFC 7518 Section 3.2.
  return self._jws.encode(

Creating a Project

Projects can be created using:

projects.create("python-client-test-project-kfsresf")

'09DEFAULTPROJECT00'

By default, creating a project also loads it, and sets it as the current project.

Viewing current project

To view the currently loaded project, use:

projects.current()

('09DEFAULTPROJECT00', 'python-client-test-project-kfsresf')

List projects

To list available projects, use:

projects.list(limit=10)

	id	name	description
0	09DEFAULTPROJECT00	python-client-test-project-kfsresf	None

Load a project

To load a project, use:

projects.load("python-client-test-project-kfsresf") 
projects.current()

('09DEFAULTPROJECT00', 'python-client-test-project-kfsresf')

Proteins and Ligands in a Project

If a project is loaded, sync methods on Protein, Ligand, and LigandSet assign that entity to that project:

protein = Protein.from_file(BRD_DATA_DIR / "brd.pdb")
protein.sync()

ligands = LigandSet.from_dir(BRD_DATA_DIR)
ligands.sync()

We can view the proteins in this project using:

projects.proteins()

	id	name	file_path	pdb_id
0	brd	brd	testing/brd.pdb	None

Note that the Protein is now assigned a project_id:

protein.project_id

'09DEFAULTPROJECT00'

Similarly, we can view the ligands in the project using:

df = projects.ligands()
df

	id	name	smiles
0	brd-2	cmpd 2 (methyl)	CN(C)C(=O)c1cccc(-c2cn(C)c(=O)c3[nH]ccc23)c1
1	brd-3	cmpd 3 (Allyl)	C=CCn1cc(-c2cccc(C(=O)N(C)C)c2)c2cc[nH]c2c1=O
2	brd-4	cmpd 4 (Crotyl)	C/C=C/Cn1cc(-c2cccc(C(=O)N(C)C)c2)c2cc[nH]c2c1=O
3	brd-5	cmpd 5 (1-Butenyl)	C=CCCn1cc(-c2cccc(C(=O)N(C)C)c2)c2cc[nH]c2c1=O
4	brd-6	cmpd 6 (ethyl)	CCn1cc(-c2cccc(C(=O)N(C)C)c2)c2cc[nH]c2c1=O
5	brd-7	cmpd 7 (n-propyl)	CCCn1cc(-c2cccc(C(=O)N(C)C)c2)c2cc[nH]c2c1=O
6	brd-8	cmpd 8 (n-Butyl)	CCCCn1cc(-c2cccc(C(=O)N(C)C)c2)c2cc[nH]c2c1=O
7	brd-9	cmpd 9 (methoxyethyl)	COCCn1cc(-c2cccc(C(=O)N(C)C)c2)c2cc[nH]c2c1=O

We can download those ligands to disk using:

ligands = LigandSet.from_ids(list(df["id"]))
ligands

LigandSet with 8 ligands

8 unique SMILES NOT PROTONATED 2D

Properties: initial_smiles

Use .to_dataframe() to convert to a dataframe, .show_df() to view dataframewith structures, or .show() for 3D visualization, .prepare() to prepare ligands for docking

ligands[0].project_id

'09DEFAULTPROJECT00'