Accuracy on multiple sequence alignments (MSA) is of great significance for such important biological applications as evolution and phylogenetic analysis, homology and domain structure prediction. In such analyses, alignment accuracy is crucial. In this paper, we investigate a combined scoring function capable of obtaining a good approximation to the biological quality of the alignment. The algorithm uses the information obtained by the different quality scores in order to improve the accuracy. The results show that the combined score is able to evaluate alignments better than the isolated scores.This work was supported by the Ministry of Education and Science of Spain under contract TIN2011-28689-C02-02, TIN2010-12011-E and Consolider CSD2007-00050. MO is funded by the CUR of DIUE of GENCAT. CN is funded by the Plan Nacional BFU2008-00419 and the 7th Framework Programme of the European Commission through the LEISHDRUG project (no. 223414) and The Quantomics project (KBBE-2A-222664).