We used a Diversity Fixed Foundation Set comprising 48 inbred lines of Brassica juncea and representing all the adaption zones of the crop for association mapping. Extensive phenotypic variations were observed for all the grain yield components and root traits under both irrigated and restricted moisture conditions. The genotypes differed in their responses to moisture stress. Trait averages declined numerically under restricted moisture conditions when compared to a standard irrigation schedule. Canonical analysis demonstrated the importance of primary branches and seed size as the traits of significance for drought susceptibility index. Microsatellite markers (158), representing all the 18 chromosomes, were used to assess the population structure, linkage disequilibrium (LD) in the association panel and marker–trait associations (MTA's). A comparison of four association models [general linear model/GLM(Q-matrix/Q), mixed linear model: MLM(Q+kinship matrix/K), GLM (principal components/PC) and MLM(PC + K)] showed that GLM(PC) and MLM(PC + K), incorporating principal components and kinship matrix, were the best models. Maximum proportions of significant results were observed in the models GLM(PC) and MLM(PC + K). MLM was preferred as there were fewer false positives than GLM. Thirteen significant associations were detected between the molecular markers and agronomic traits. Of these, seven were identified under normal moisture conditions, and six under restricted moisture conditions. Marker–trait associations included four markers associated with grain yield, three with seed size, two with secondary branches and one marker each with plant height, root diameter and root length. A single marker SB1822-1, was repeatedly detected for seed size and grain yield, and was localized at 17.5 cM (centiMorgans) on chromosome B3. Marker SB3872-3 revealed a significant effect under normal moisture conditions on seed size (R2% = 15.16) at 60.9 cM on chromosome B5 during the first year. Among the favorable alleles, SB1822-1 had the average positive phenotypic effect for seed size and grain yield. Marker cnu316-3 had maximum positive phenotypic effects on grain yield.
