openQDC - Open Quantum Data Commons

Installing openQDC

git clone git@github.com:OpenDrugDiscovery/openQDC.git
cd openQDC
# use mamba/conda
mamba env create -n openqdc -f env.yml
pip install -e .

Tests

You can run tests locally with:

pytest

Documentation

You can build the documentation locally with:

mkdocs serve

Downloading Datasets

A command line interface is available to download datasets or see which dataset is available, for more information please run openqdc --help.

# Display the available datasets
openqdc datasets

# Display the help message for the download command
openqdc download --help

# Download the Spice and QMugs dataset
openqdc download Spice QMugs

Overview of Datasets

We provide support for the following publicly available QM Potential Energy Datasets.

Potential Energy

Dataset	# Molecules	# Conformers	Average Conformers per Molecule	Force Labels	Atom Types	QM Level of Theory	Off-Equilibrium Conformations
ANI	57,462	20,000,000	348	No	4	ωB97x:6-31G(d)	Yes
GEOM	450,000	37,000,000	82	No	18	GFN2-xTB	No
Molecule3D	3,899,647	3,899,647	1	No	5	B3LYP/6-31G*	No
NablaDFT	1,000,000	5,000,000	5	No	6	ωB97X-D/def2-SVP
OrbNet Denali	212,905	2,300,000	11	No	16	GFN1-xTB	Yes
PCQM_PM6			1	No		PM6	No
PCQM_B3LYP	85,938,443	85,938,443	1	No		B3LYP/6-31G*	No
QMugs	665,000	2,000,000	3	No	10	GFN2-xTB, ωB97X-D/def2-SVP	No
QM7X	6,950	4,195,237	603	Yes	7	PBE0+MBD	Yes
SN2RXN	39	452709	11,600	Yes	6	DSD-BLYP-D3(BJ)/def2-TZVP
SolvatedPeptides		2,731,180		Yes		revPBE-D3(BJ)/def2-TZVP
Spice	19,238	1,132,808	59	Yes	15	ωB97M-D3(BJ)/def2-TZVPPD	Yes
tmQM	86,665	86,665	1	No		TPSSh-D3BJ/def2-SVP
Transition1X		9,654,813		Yes		ωB97x/6–31 G(d)	Yes
WaterClusters	1	4,464,740		No	2	TTM2.1-F	Yes

Interaction energy

We also provide support for the following publicly available QM Noncovalent Interaction Energy Datasets.

Dataset
DES370K
DES5M
Metcalf
DESS66
DESS66x8
Splinter
X40
L7

CI Status

The CI runs tests and performs code quality checks for the following combinations:

The three major platforms: Windows, OSX and Linux.
The four latest Python versions.

	`main`
Lib build & Testing
Code Sanity (linting and type analysis)
Documentation Build
Pre-Commit

How to cite

All data presented in the OpenQDC are already published in scientific journals, full reference to the respective paper is attached to each dataset class. When citing data obtained from OpenQDC, you should cite both the original paper(s) the data come from and our paper on OpenQDC itself. The reference is:

ADD REF HERE LATER

valence-labs/openQDC