RESUMO
Marine macro-algae, commonly known as "seaweed," are used in everyday commodity products worldwide for food, feed, and biostimulant for plants and animals and continue to be one of the conspicuous components of world aquaculture production. However, the application of ANN in seaweeds remains limited. Here, we described how to perform ANN-based machine learning modeling and GA-based optimization to enhance seedling production for implications on commercial farming. The critical steps from seaweed seedling explant preparation, selection of independent variables for laboratory culture, formulating experimental design, executing ANN Modelling, and implementing optimization algorithm are described.
Assuntos
Algoritmos , Redes Neurais de Computação , Alga Marinha , Plântula , Alga Marinha/crescimento & desenvolvimento , Plântula/crescimento & desenvolvimento , Regeneração , Aquicultura/métodos , Aprendizado de Máquina , Modelos GenéticosRESUMO
The present study deals with the metabolomic status of Ulva cells undergoing phase transition (vegetative, determination and differentiation) when exposed to different abiotic conditions. The objective was to study whether metabolite changes occurring during the phase transition reveal any commonality among differential abiotic conditions. The phase transition was followed through microscopic observations and 1H NMR characterization at 0 h, 24 h, and 48 h after the incubation of the thallus under abiotic conditions, such as different salinities (20-35 psu), temperatures (20-35 °C), photoperiods (18 : 6, 12 : 12, and 6 : 18 D/N), light intensities (220, 350, and 500 µmol photons m-2 s-1), nitrate (0.05-0.2 g L-1) and phosphate (0.05-0.2 g L-1) concentrations. Microscopic analysis revealed the role of all abiotic conditions except variable salinity and phosphate concentration in phase transition. NMR analysis revealed that glucose increased in the determination phase [7.58 to 9.62 normalized intensity (AU)] and differentiation phase (5.85 to 6.41 AU) from 20 °C to 25 °C temperature. Coniferyl aldehyde increased in vegetative (5.79 to 6.83 AU) and differentiation (6.66 to 7.40 AU) phases from 20 °C to 30 °C temperature. The highest average (22.97) was found in photoperiod (average range = 0-122.91) and the highest SD (24.73) in salinity (SD range = 1.86-57.04) in region 9 (creatinine and cysteine) of the differentiation phase. A total of 30 metabolites were identified under the categories of sugars, amino acids, and aromatic compounds. The present study will aid in understanding the mechanisms underlying cell differentiation during reproduction. The result may serve as an important reference point for future studies, besides helping in controlling seedling preparation for commercial farming as well as the management of rapid green tide formation.