Search for: All records

A new biomanufacturing platform combining intracellular metabolic engineering of the oleaginous yeastYarrowia lipolyticaand extracellular bioreaction engineering provides efficient bioconversion of plant oils/animal fats into high‐value products. However, predicting the hydrodynamics and mass transfer parameters is difficult due to the high agitation and sparging required to create dispersed oil droplets in an aqueous medium for efficient yeast fermentation. In the current study, commercial computational fluid dynamic (CFD) solver Ansys CFX coupled with the MUSIG model first predicts two‐phase system (oil/water and air/water) mixing dynamics and their particle size distributions. Then, a three‐phase model (oil, air, and water) utilizing dispersed air bubbles and a polydispersed oil phase was implemented to explore fermenter mixing, gas dispersion efficiency, and volumetric mass transfer coefficient estimations (k_La). The study analyzed the effect of the impeller type, agitation speed, and power input on the tank's flow field and revealed that upward‐pumping pitched blade impellers (PBI) in the top two positions (compared to Rushton‐type) provided advantageous oil phase homogeneity and similar estimatedk_Lavalues with reduced power. These results show good agreement with the experimental mixing andk_Ladata.

 

Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence.