Graph neural network predictions of metal organic framework CO<mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" id="d1e488" altimg="si38.svg"><mml:msub><mml:mrow /><mml:mrow><mml:mn>2</mml:mn></mml:mrow></mml:msub></mml:math> adsorption properties

The increasing CO2 level is a critical concern and suitable materials are needed to capture such gases from the environment. While experimental conventional computational methods useful in finding materials, they usually slow there need expedite processes. We use Atomistic Line Graph Neural Network (ALIGNN) method predict adsorption metal organic frameworks (MOF), which known for their high functional tunability. train ALIGNN models hypothetical MOF (hMOF) database with 137953 MOFs grand canonical Monte Carlo (GCMC) based isotherms. develop accuracy fast pre-screening applications. apply trained model on CoREMOF computationally rank them synthesis. In addition isotherm, we also electronic bandgaps, surface area, void fraction, lowest cavity diameter, pore limiting illustrate strength limitation of graph neural network models. For few candidate carry out GCMC calculations evaluate deep-learning (DL) predictions.