Establishing of chemometric technique for enzyme activities quantification based on FT-IR spectroscopy and artificial neural networks

• Grant number: 14/06447-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2014
• End date: June 30, 2015
• Field of knowledge: Engineering - Chemical Engineering
• Principal Investigator: Eutimio Gustavo Fernández Núñez
• Grantee: Augusto Cesar Barchi
• Host Institution: Faculdade de Ciências e Letras (FCL-ASSIS). Universidade Estadual Paulista (UNESP). Campus de Assis. Assis , SP, Brazil

Abstract

The analytical techniques for enzyme activity quantification from aqueous extracts derived to solid state fermentations are usually performed following protocols consisting of multiple steps, as a consequence they are time consuming, and highly likely to get inaccurate results when inexperienced analysts perform these analytical procedures. This project aims to establish a chemometric method to quantify the amylolytic and proteolytic enzyme activities simultaneously from FT-IR spectra of diluted enzyme extracts from solid state fermentation processes using filamentous fungus Rhizopus oligosporus. The correlation method of choice will be supervised artificial neural network (multilayer perceptron) with backpropagation learning rule. A set of over 100 samples, comprising extracts obtained from four agricultural residues fermented individually and combinations of two ternary mixtures of these substrates will be used to train, validate and test the artificial neural network. For this purpose, it will determine proteolytic and amylolytic activities of extracts by classical methods while the FT-IR spectral analysis of diluted samples will be also performed. The calibrated artificial neural network will reduce time and costs of enzymatic determinations and in parallel increase results precision.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

FERNANDEZ NUNEZ, EUTIMIO GUSTAVO; BARCHI, AUGUSTO CESAR; ITO, SHURI; ESCARAMBONI, BRUNA; HERCULANO, RONDINELLI DONIZETTI; MALACRIDA MAYER, CASSIA ROBERTA; NETO, PEDRO DE OLIVA. Artificial intelligence approach for high level production of amylase using Rhizopus microsporus var. oligosporus and different agro-industrial wastes. JOURNAL OF CHEMICAL TECHNOLOGY AND BIOTECHNOLOGY, v. 92, n. 3, p. 684-692, MAR 2017. (14/06447-0)

ITO, SHURI; BARCHI, AUGUSTO CESAR; ESCARAMBONI, BRUNA; DE OLIVA NETO, PEDRO; HERCULANO, RONDINELLI DONIZETTI; BORGES, FELIPE AZEVEDO; ROMEIRO MIRANDA, MATHEUS CARLOS; FERNANDEZ NUNEZ, EUTIMIO GUSTAVO. UV/Vis spectroscopy combined with chemometrics for monitoring solid-state fermentation with Rhizopus microsporus var. oligosporus. JOURNAL OF CHEMICAL TECHNOLOGY AND BIOTECHNOLOGY, v. 92, n. 10, p. 2563-2572, OCT 2017. (14/06447-0)

BARCHI, AUGUSTO CESAR; ITO, SHURI; ESCARAMBONI, BRUNA; DE OLIVA NETO, PEDRO; HERCULANO, RONDINELLI DONIZETTI; ROMEIRO MIRANDA, MATHEUS CARLOS; PASSALIA, FELIPE JOSE; ROCHA, JOSE CELSO; FERNANDEZ NUNEZ, EUTIMIO GUSTAVO. Artificial intelligence approach based on near-infrared spectral data for monitoring of solid-state fermentation. Process Biochemistry, v. 51, n. 10, p. 1338-1347, OCT 2016. (14/06447-0)