Search for: All records

Metal-organic frameworks (MOFs) exhibit great promise for CO₂capture. However, finding the best performing materials poses computational and experimental grand challenges in view of the vast chemical space of potential building blocks. Here, we introduce GHP-MOFassemble, a generative artificial intelligence (AI), high performance framework for the rational and accelerated design of MOFs with high CO₂adsorption capacity and synthesizable linkers. GHP-MOFassemble generates novel linkers, assembled with one of three pre-selected metal nodes (Cu paddlewheel, Zn paddlewheel, Zn tetramer) into MOFs in a primitive cubic topology. GHP-MOFassemble screens and validates AI-generated MOFs for uniqueness, synthesizability, structural validity, uses molecular dynamics simulations to study their stability and chemical consistency, and crystal graph neural networks and Grand Canonical Monte Carlo simulations to quantify their CO₂adsorption capacities. We present the top six AI-generated MOFs with CO₂capacities greater than 2m mol g⁻¹, i.e., higher than 96.9% of structures in the hypothetical MOF dataset.

We introduce an end-to-end computational framework that allows for hyperparameter optimization using theDeepHyperlibrary, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models includingCGCNN,PhysNet,SchNet,MPNN,MPNN-transformer, andTorchMD-NET. We employ these AI models along with the benchmarkQM9,hMOF, andMD17datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab.

Chloride homeostasis is regulated in all cellular compartments. CLC-type channels selectively transport Cl⁻across biological membranes. It is proposed that side-chains of pore-lining residues determine Cl⁻selectivity in CLC-type channels, but their spatial orientation and contributions to selectivity are not conserved. This suggests a possible role for mainchain amides in selectivity. We use nonsense suppression to insert α-hydroxy acids at pore-lining positions in two CLC-type channels, CLC-0 and bCLC-k, thus exchanging peptide-bond amides with ester-bond oxygens which are incapable of hydrogen-bonding. Backbone substitutions functionally degrade inter-anion discrimination in a site-specific manner. The presence of a pore-occupying glutamate side chain modulates these effects. Molecular dynamics simulations show backbone amides determine ion energetics within the bCLC-k pore and how insertion of an α-hydroxy acid alters selectivity. We propose that backbone-ion interactions are determinants of Cl⁻specificity in CLC channels in a mechanism reminiscent of that described for K⁺channels.