BEGIN:VCALENDAR VERSION:2.0 PRODID:-//jEvents 2.0 for Joomla//EN CALSCALE:GREGORIAN METHOD:PUBLISH BEGIN:VEVENT UID:af3ef2862f0e9a220f767316d77bc146 CATEGORIES:Physical Chemistry Seminar CREATED:20210226T181233 SUMMARY:Dr. Arghya Dutta, Max Planck Institute for Polymer Research DESCRIPTION:
Data-Driven Search for Drug-Membrane Per meability Equations
Drug effica cy depends on its capacity to permeate across the cell membrane. This capac ity is quantified by the drug–membrane permeability coefficient. In this ta lk, I will present results from our recent work where we considered the pre diction of passive permeability coefficient via equations that depend on ac idity in addition to the widely recognized hydrophobicity. To discover easi ly interpretable equations that explain the data well, we used sure-indepen dence screening and sparsifyingoperator (SISSO), an artificial-intelligence technique that combines symbolic regression with compressed sensing. Our s tudy is based on a large in silico dataset of 0.4 million small molecules e xtracted from coarse-grained simulations. I will then rationalize the equat ion suggested by SISSO via an analysis of the inhomogeneous solubility–diff usion model in several asymptotic acidity regimes. Together, SISSO and anal ytically derived asymptotes establish and validate an accurate, broadly app licable, and interpretable equation for passive permeability.
Hosted by Professor Zheng Shi
For Webex meetin
g information, please contact Loretta Lupo @
Data-Driven Search for Drug-Membrane Permeability Equations
Drug efficacy depends on its capacity to permeate across t he cell membrane. This capacity is quantified by the drug–membrane permeabi lity coefficient. In this talk, I will present results from our recent work where we considered the prediction of passive permeability coefficient via equations that depend on acidity in addition to the widely recognized hydr ophobicity. To discover easily interpretable equations that explain the dat a well, we used sure-independence screening and sparsifyingoperator (SISSO) , an artificial-intelligence technique that combines symbolic regression wi th compressed sensing. Our study is based on a large in silico dataset of 0 .4 million small molecules extracted from coarse-grained simulations. I wil l then rationalize the equation suggested by SISSO via an analysis of the i nhomogeneous solubility–diffusion model in several asymptotic acidity regim es. Together, SISSO and analytically derived asymptotes establish and valid ate an accurate, broadly applicable, and interpretable equation for passive permeability.
Hosted by Professor Zheng Shi
& nbsp;
For Webex meeting information, please contact Loretta Lupo @&nb
sp;