Data: 17 de outubro de 2025     

Horário: 15h   

Palestrante: Prof. Carlos D. Garcia (Clemson University)

Local: Anfiteatro “Prof. Milan Trsic” – Instituto de Química de São Carlos, Edifício Q1 – 2º andar.

Resumo: “The application of deep eutectic solvents (DES) in the pharmaceutical, agricultural, and food industries represents one of the fastest growing fields of green chemistry, as these mixtures can potentially replace traditional organic solvents. These advances are, however, limited by the development of new DES which is today, almost exclusively empirically driven and often derivative from known mixtures. To overcome this limitation, we have developed a series of machine learning approaches, that are able to recognize the patterns in strings that lead to the formation of DES. The simplest approach was adapted from language learning, allowing the use of relatively small datasets and relatively low computational resources and opening the door to the development of multiple novel solvents containing pharmaceuticals. This model has been recently expanded (to an extreme gradient boosting model, eutXG) that is capable of predicting not only the formation but also the melting point (MP) of DES with an average accuracy of 98%. Summarizing these results, this presentation will not only cover the basic concepts behind these models but also provide several examples of their application to address analytical problems. More information about the group as well as the list of contributors to this presentation can be found in our web site: scienceweb.clemson.edu/uacl/.”