GENE RECOGNITION BY COMBINATION OF SEVERAL GENE-FINDING PROGRAMS

Motivation: A number of programs have been developed to predict the eu karyotic gene structures in DNA sequences. However gene finding is sti ll a challenging problem. Results: We have explored the effectiveness when the results of several gene-finding programs were re-analyzed and combined. We studied several methods with four programs (FEXH, GenePa rser3, GEN-SCAN and GRAIL2). By HIGHEST-policy combination method or B OUNDARY method, approximate correlation (AC) improved by 3-5% in compa rison with the best single gene-finding program. From another viewpoin t, OR-based combination of the four programs is the most reliable to k now whether a candidate exon overlaps with the real exon or not, altho ugh it is less sensitive than GENSCAN for exon-intron boundaries. Our methods can easily be extended to combine other programs.