Comparative analyses of response surface methodology and artificial neural network on medium optimization for Tetraselmis sp. FTC209 grown under mixotrophic condition

Abstract

Mixotrophic metabolism was evaluated as an option to augment the growth and lipid production of marine microalga Tetraselmis sp. FTC 209. In this study, a five-level three-factor central composite design (CCD) was implemented in order to enrich the W-30 algal growth medium. Response surface methodology (RSM) was employed to model the effect of three medium variables, that is, glucose (organic C source), NaNO3 (primary N source), and yeast extract (supplementary N, amino acids, and vitamins) on biomass concentration, X(max), and lipid yield, P(max)/X(max). RSM capability was also weighed against an artificial neural network (ANN) approach for predicting a composition that would result in maximum lipid productivity, Pr(lipid). A quadratic regression from RSM and a Levenberg-Marquardt trained ANN network composed of 10 hidden neurons eventually produced comparable results, albeit ANN formulation was observed to yield higher values of response outputs. Finalized glucose (24.05 g/L), NaNO3 (4.70 g/L), and yeast extract (0.93 g/L) concentration, affected an increase of X(max) to 12.38 g/L and lipid a accumulation of 195.77 mg/g dcw. This contributed to a lipid productivity of 173.11 mg/L per day in the course of two-week cultivation.

Figure 1

Surface response plots of (a, b, c) biomass concentration, (d, e, f) intracellular lipid, and (g, h, i) overall lipid productivity as modeled via RSM.

Figure 2

Parity plots correlating the observed and predicted values of the ANN models with respect to different testing dataset.

Figure 3

Finalized neural network architecture (3-10-1) trained via Levenberg-Marquardt algorithm for the estimation of lipid productivity.

Figure 4

Response surfaces with regard to lipid productivity showing the interactions between (a) yeast extract with glucose, (b) NaNO₃ with glucose, and (c) NaNO₃ with yeast extract as modeled via neural network.

Figure 5

The level of importance of effective medium constituents on lipid productivity.

Figure 6

Photomicrographs of 1000x (1) phase contrast, (2) fluorescence of Nile red stained microalga viewed under excitation filter of 355–425 nm and emission filter of 470 nm, and (3) alternatively, excitation filter of 515–560 nm and emission filter of 590 nm of the 2-week old cultures. Red color, chlorophyll autofluorescence; yellow-gold fluorescence (excitation: 355–425 nm) or bright yellow fluorescence (excitation: 515–560 nm), lipid bodies. Samples were cultivated using (a) Walne's photoautotrophic medium, (b) W-30 + 30 g/L glucose, and (c) ANN-based optimized medium.