In this paper the biosorption of metal ions Cu2+, Cd2+ and Zn2+ in single-component system by Sargassum filipendula pre-treated with 0.5 M CaCl2 was studied. The experiments were carried out in a batch reactor at different fixed pH (3.0, 4.0, 5.0 and 6.0) and 30oC. All the equilibrium data obtained were described using two pH-dependent isotherm models, based on the Langmuir isotherm. Artificial neural networks was also used to represent the pH effect on the biosorption equilibrium. The input of the networks were the equilibrium concentration of the metal in the fluid phase and the pH. As output the concentration of the metallic specie in the biosorbent was used. The results showed that the modeling using artificial neural networks technique represented the equilibrium data much better than the conventional modeling by the pH-dependent isotherm models.