Polymeric
membrane design is a multidimensional process involving
selection of membrane materials and optimization of fabrication conditions
from an infinite candidate space. It is impossible to explore the
entire space by trial-and-error experimentation. Here, we present
a membrane design strategy utilizing machine learning-based Bayesian
optimization to precisely identify the optimal combinations of unexplored
monomers and their fabrication conditions from an infinite space.
We developed ML models to accurately predict water permeability and
salt rejection from membrane monomer types (represented by the Morgan
fingerprint) and fabrication conditions. We applied Bayesian optimization
on the built ML model to inversely identify sets of monomer/fabrication
condition combinations with the potential to break the upper bound
for water/salt selectivity and permeability. We fabricated eight membranes
under the identified combinations and found that they exceeded the
present upper bound. Our findings demonstrate that ML-based Bayesian
optimization represents a paradigm shift for next-generation separation
membrane design.
A single Brachionus rotifer can consume thousands of algae cells per hour causing an algae pond to crash within days of infection. Thus, there is a great need to reduce rotifers in order for algal biofuel production to become reality. Copper can selectively inhibit rotifers in algae ponds, thereby protecting the algae crop. Differential toxicity tests were conducted to compare the copper sensitivity of a model rotifer—B. calyciflorus and an alga, C. kessleri. The rotifer LC50 was <0.1 ppm while the alga was not affected up to 5 ppm Cu(II). The low pH of the rotifer stomach may make it more sensitive to copper. However, when these cultures were combined, a copper concentration of 1.5 ppm was needed to inhibit the rotifer as the alga bound the copper, decreasing its bioavailability. Copper (X ppm) had no effect on downstream fatty acid methyl ester extraction.
Although algae-biofuels have many advantages including high areal productivity, algae can be preyed upon by amoebas, protozoans, ciliates, and rotifers, particularly in open pond systems. Thus, these higher organisms need to be controlled. In this study, Chlorella kessleri was used as the algal culture and Brachionus calyciflorus as the source of predation. The effect of sodium hypochlorite (bleach) was tested with the goal of totally inhibiting the rotifer while causing minor inhibition to the alga. The 24-hr LC(50) for B. calyciflorus in spring water was 0.198 mg Cl/L while the 24-hr LC(50) for C. kessleri was 0.321 mg Cl/L. However, chlorine dissipates rapidly as the algae serves as reductant. Results showed a chlorine dosage between 0.45 to 0.6 mg Cl/L and a dosing interval of two hours created the necessary chlorine concentrations to inhibit predation while letting the algae grow; thus giving algae farmers a tool to prevent pond crashes.
The
first step to develop a quantitative structure–activity
relationship (QSAR) model is to identify a set of chemicals with known
activities/properties, which can be either collected from the published
studies or measured experimentally. A key challenge in this process
is how to determine which chemicals are used to train a QSAR model,
and, of those chemicals, which should be prioritized in experimental
trials to ensure that the obtained models have large applicability
domains (ADs). In this study, we employ uncertainty-based active learning
(AC) to address this challenge. We use the Gaussian process (GP) to
develop QSAR models for three public datasets, Koc, solubility, and k
•OH, each with a number of chemicals
represented by molecular descriptors, in which the GP can offer prediction
uncertainty (by means of standard deviation) for the model’s
prediction. The training chemicals of each dataset are selected in
two different ways: (1) random splitting (RS) and (2) uncertainty-based
AC. Uncertainty-based AC iteratively identifies chemicals with the
highest uncertainty and selects them for model training. We demonstrate
that the chemicals selected by AC are more diverse than those selected
by RS and that AC-based QSAR models have better generalizability than
those derived from RS. We then use these two types of models to predict
the properties of chemicals in the REACH dataset (>300,000 chemicals)
and assess their ADs using five different AD determination methods.
We demonstrate that the AD of AC-based QSAR models for all AD methods
is significantly larger than those of RS-based models (up to 24 times
larger). This study provides a novel method to enlarge the AD of QSAR
models, which can guide model development and improve the property
prediction reliability for more REACH dataset chemicals while minimizing
the development cost and time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.