VTechWorks staff will be away for the winter holidays starting Tuesday, December 24, 2024, through Wednesday, January 1, 2025, and will not be replying to requests during this time. Thank you for your patience, and happy holidays!

University Libraries

Permanent URI for this community

https://hdl.handle.net/10919/5540

Browse

Browsing University Libraries by Author "Achenie, Luke E. K."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Infusing theory into deep learning for interpretable reactivity prediction
    Wang, Shih-Han; Pillai, Hemanth Somarajan; Wang, Siwen; Achenie, Luke E. K.; Xin, Hongliang (Nature Research, 2021)
    Despite recent advances of data acquisition and algorithms development, machine learning (ML) faces tremendous challenges to being adopted in practical catalyst design, largely due to its limited generalizability and poor explainability. Herein, we develop a theory-infused neural network (TinNet) approach that integrates deep learning algorithms with the wellestablished d-band theory of chemisorption for reactivity prediction of transition-metal surfaces. With simple adsorbates (e.g., *OH, *O, and *N) at active site ensembles as representative descriptor species, we demonstrate that the TinNet is on par with purely data-driven ML methods in prediction performance while being inherently interpretable. Incorporation of scientific knowledge of physical interactions into learning from data sheds further light on the nature of chemical bonding and opens up new avenues for ML discovery of novel motifs with desired catalytic properties.
  • Thumbnail Image
    A passive diffusion model of fluorescein derivatives in an in vitro human brain microvascular endothelial cell (HBMEC) monolayer
    Simmons, Jamelle M.; Lee, Yong Woo; Achenie, Luke E. K. (JVE, 2018-09-29)
    Eukaryotic cells have a protective plasma membrane, which restricts the free movement of molecules from the external environment to the internal environment. This study aims to computationally model the transport of fluorescein derivatives across the monolayer of human brain microvascular endothelial cells (HBMEC). The determination of plausible effective diffusion constants (𝐷eff) will allow models to be built that could be useful beyond in vitro experimentation. Fluorescein-5-isothiocyanate (FITC) modeling produced a 𝐷effrange of 1E-20 to 5E-20 cm²/s at a 1 μm cell monolayer thickness and a 𝐷eff constant near 5E-29 cm²/s at a 5 μm cell monolayer thickness. Both fluorescein and sodium fluorescein (NaFl) modeling at the 1 and 5 μm thicknesses did not produce simulations that closely resembled the HBMEC in vitro model. Overall, it is possible that the fluorescent intensity noted with fluorescein and NaFl may be better explained by a mechanism other than passive diffusion. Simulations of FITC diffusion produced a narrow range of 𝐷eff constants that closely matched the in vitro HBMEC fluorescent intensity.