Candida antarctica as catalyst for polycaprolactone synthesis: effect of temperature and solvents

Data augmentation and machine learning techniques for control strategy development in bio-polymerization process

Machine learning has been increasingly used in biochemistry. However, in organic chemistry and other experiment-based fields, data collected from real experiments are inadequate and the current coronavirus disease (COVID-19) pandemic has made the situation even worse. Such limited data resources may result in the low performance of modeling and affect the proper development of a control strategy. This paper proposes a feasible machine learning solution to the problem of small sample size in the bio-polymerization process. To avoid overfitting, the variational auto-encoder and generative adversarial network algorithms are used for data augmentation. The random forest and artificial neural network algorithms are implemented in the modeling process. The results prove that data augmentation techniques effectively improve the performance of the regression model. Several machine learning models were compared and the experimental results show that the random forest model with data augmentation by the generative adversarial network technique achieved the best performance in predicting the molecular weight on the training set (with an R² of 0.94) and on the test set (with an R² of 0.74), and the coefficient of determination of this model was 0.74.

Sustainable synthesis and precise characterisation of bio-based star polycaprolactone synthesised with a metal catalyst and with lipase

Development of a sustainable route for the synthesis of star-shaped poly(ε-caprolactone) using renewable feedstocks in clean solvents (scCO₂ and bulk) with the catalysts Sn(Oct)₂ or the enzyme Novozym 435.

Ultrasound assisted lipase catalyzed synthesis of poly-6-hydroxyhexanoate

Ultrasonic irradiation greatly improved the Candida antarctica lipase B mediated ring opening polymerization of ε-caprolactone to poly-6-hydroxyhexanoate in the ionic liquid 1-ethyl-3-methylimidazolium tetraflouroborate. Compared to the conventional nonsonicated reaction, sonication improved the monomer conversion by 63% and afforded a polymer product of a narrower molecular weight distribution and a higher degree of crystallinity. Under sonication, the polydispersity index of the product was ~1.44 compared to a value of ~2.55 for the product of the conventional reaction. With sonication, nearly 75% of the monomer was converted to product, but the conversion was only ~16% for the reaction carried out conventionally. Compared to conventional operation, sonication enhanced the rate of polymer propagation by >2-fold and the turnover number of the lipase by >3-fold.