There exist numerous potential benefits to identifying organic materials which can replicate the electronic properties of inorganic systems, particularly rare-earth metals which are costly to obtain and pose environmental risks. Superconductivity and ferroelectricity are two such electronic properties which has recently been identified in metal organic frameworks (MOFs). This motivates a search for functional MOFS within the organic material database (OMDB) developed by the theoretical quantum matter group at NORDITA. The OMDB is the largest database of organic materials, containing over 40000 entries. We will use density functional theory and the Quantum Espresso software package to screen the ~1500 suitable MOFs within the OMDB and identify optimal candidates for replacing known inorganic compounds. We will further train generative neural networks to perform inverse design of novel functional organic compounds using diffusion networks and graph neural networks(GNNs) to predict the band gap of OMDB crystals. This project builds on past steady support for materials development in OMDB by the NAISS. We would also like to emphasize that are usage has steadily increased as our processes have been fine tuned. In the past months we have utilized the entirety of our allocation on Tetralith and our progress has been slowed only by access to more resources. We have also begun to capitalize on the GPU resources within ALVIS as our processes for data analysis and inverse design have progressed. We believe our resource request is in line with the resources that we will reliably utilize in their entirety every month.