Evolutionary analysis of alpha and beta hemoglobin genes by REH theory under the assumption of the equiprobability of genetic events

Abstract

It is shown how REH theory in conjunction with mRNA or gene sequence data can be used to obtain estimates of the fixation intensity, the number of varions, and the total mutations fixed between homologous pairs of nucleic acids. These estimates are more accurate than those that can be derived from amino acid sequence data. The method is illustrated for alpha and beta hemoglobin genes and these improved estimates are compared with those made from the amino acid sequences for which those genes code. Significant differences are found between the estimates made by these two methods. For the beta hemoglobin gene sequences examined here, the fixation intensity is somewhat less than the protein data had suggested, and the number of varions is considerably greater. Depending on the gene sequences examined, between 62 and 83% of the codons appear able to fix mutations during the divergences considered. This reflects the constraints of natural selection on acceptable mutations. The total number of base replacements separating the genes for human, mouse, and rabbit beta hemoglobin varies from 61 to 105 depending on the pair examined. Rabbit alpha and beta hemoglobin are separated by at least 290 fixed mutations. For such distantly related sequences estimates made from protein and mRNA data differ less, reflecting the higher quality of information from the many observed changes in primary structure. The effects of nonrandom gene structure on these evolutionary estimates and the fact that various genetic events are not equiprobable are discussed.