Molecular marker analysis of the approach to homozygosity by selfing in diploid alfalfa

Although inbreeding is used extensively in alfalfa breeding and genetics, the actual approach to homozygosity during inbreeding is unknown and may differ from that predicted by the inbreeding coefficient (F) because of the need to select for vigor and fertility when inbreeding. Observed and expected values of heterozygosity were compared by means of 40 co-dominant RFLP loci for two inbred series each consisting of four independent lines derived by selfing two diploid alfalfa genotypes. Selling was continued with selection for fertility until self-sterility was reached at the S-2, S-3, or S-4 generation. Additional S-1 progenies were also evaluated to identify the heterozygous RFLP loci. The observed percentage heterozygosity, calculated as the percentage of the 40 RFLP loci still heterozygous in each plant, declined less than expected based on the inbreeding coefficient in each inbred series. The lowest observed percentage heterozygosity was 30% in one inbred series and 40% in the other inbred series despite expectations as low as 6%. Tests of genotype and allele ratios indicated that the deviations may be due to selection favoring heterozygotes. Our results show that inbreeding in diploid alfalfa proceeds more slowly than expected, based on F, and that inbreeding depression may limit the level of homozygosity obtainable.