Ever since Charles Darwin employed domestication as a model for natural evolution [1], crop domestication has been extensively studied by evolutionary biologists [2–7]. Part of the power of domestication as a model for evolution is that the crop ancestors are extant and cross-compatible with crop species, allowing genetic dissection of the inheritance of domestication traits. Domestication also allows us to discern the impact of selection on genetic architecture through comparison of pre- and post-domestication populations. Since the genetic architecture of the ancestral species influences the possible outcomes when selection is applied to move a population to a new optimum, such comparisons can reveal how genetic architecture can both facilitate and constrain domestication [8].

Maize and teosinte offer an excellent system for genetic analysis of domestication. Both phylogenetic and archaeological evidence revealed that maize was domesticated from Balsas teosinte (Z. mays ssp. parviglumis) by a single domestication event in southern Mexico about 9,000 years ago [9, 10]. As outcrossing species, teosinte and maize conform to many of the assumptions underlying standard population genetic models, empowering the application of diverse evolutionary analyses [11]. Maize has undergone dramatic morphological change from its wild ancestor teosinte during domestication. A typical teosinte plant has multiple long lateral branches, each tipped with a tassel, whereas a typical maize plant has one or two short branches, each tipped with a single ear. A teosinte plant produces many two-ranked ears, each with only a few fruitcase-enveloped kernels, easily shattering into single-seed units at maturity. In contrast, a maize plant produces only one or two multiple-ranked ears, each with hundreds of naked grains, remaining intact on the cob at maturity. Finally, maize has a large number of genomic and genetic resources available (https://maizegdb.org/), including high-quality genomes of inbred lines [12–15], high-density genotypic data [16], and diverse mapping populations [17, 18].

In this paper, we report a comprehensive comparison of genetic architecture in 18 domestication traits for matched populations of a maize landrace and teosinte. Our overarching goal is to better define genetic architecture in maize and teosinte and ask how it changed as a result of domestication. From our analyses, we observed that genetic architecture has been reshaped during domestication with a substantial reduction in the number of segregating QTL affecting domestication traits. We observed that regions of the genome that are strongly divergent between teosinte and maize (high F_ST) explain less variation in maize than teosinte. We also observed that genomic regions of high recombination explain a disproportionately large proportion of heritable variance both before and after domestication. Finally, we observed that only 25% of the additive variance in both teosinte and maize can be ascribed to specific QTL. Overall, our work suggests that trait evolution during maize domestication is largely attributable to very large numbers of QTL of very small effects.

Our results showed that the maize landrace population has far fewer QTL for domestication traits as compared to our teosinte population. Previous reports suggest that most domesticated crops have experienced a “domestication bottleneck” which reduced their nucleotide diversity relative to their wild ancestors [24]. For maize, there has been on average a reduction in nucleotide diversity of 30% as compared to teosinte and this reduction becomes much more severe (>65%) for genes under selection [25, 26]. Given that the domestication bottleneck and/or selection would cause the loss or fixation of many functional alleles at QTL, it was expected to find a reduced number of QTL in our maize landrace relative to teosinte.

Our observation of more and therefore novel QTL in teosinte compared to maize implies that teosinte should possess many useful alleles absent in maize. This represents an opportunity for breeding, as crop wild relatives have been extremely valuable resource to identify allelic variation by genome-wide association studies (GWAS) or quantitative trait locus (QTL) mapping approaches, and these alleles, if favorable, can be introduced into a domesticated background by marker-assisted selection [27, 28]. For maize-teosinte, a BC₂S₃ RIL (recombinant inbred line) population [29] and TeoNAM (teosinte nested association mapping) population [17] have been developed to comprehensively map QTL from teosinte. Using this BC₂S₃ population, a recent study demonstrated that fine-mapping QTL for maize leaf angle and then transferring the favorable teosinte allele into modern hybrids can enhance high-density maize grain yield [30]. Therefore, the favorable alleles of QTL that we detected in our teosinte population could be introduced into maize cultivars in the future.

Our observation that large effect alleles in both teosinte and maize landrace are rare fits expectations under mutation-selection balance [11]. Rare alleles of large effect would be rapidly removed if detrimental or driven to fixation if beneficial due to strong selection, and thus not be observed at middling frequencies. In contrast, alleles of very small effect experience weaker selection such that they move more slowly to fixation and can exhibit middling frequencies [31, 32]. Height in humans is an example from the literature of a trait apparently under mutation-selection balance, showing an inverse relationship between effect size and allele frequency [33]. Such an inverse relationship is also observed from a QTL study of inflorescence traits in maize, in which the number of large-effect QTL is very few and caused by low-frequency SNPs [34]. In our study, one example of a rare allele of large effect is the QTL for GW in teosinte (T/A, S4_184126058, P = 6.38E-50), where the MAF is 0.012 among the progeny and the minor allele comes from a single one of our 49 teosinte parents (PC_N57_ID2) (Fig 3A). Overall, the negative correlation between effect size and MAF in our data suggest an important role for mutation-selection balance in teosinte and maize.

While mutation-selection may be the principal force operating on QTL, we observed some hints that balancing selection may be present as well. In contrast to the expectation that large effect alleles are rare under mutation-selection balance, allele frequencies are expected to be more intermediate if balancing selection is operating [11]. An example of possible balancing selection in our data is the largest effect QTL for DTA in teosinte on chromosome 3 near ZmMADS69 with an MAF of 0.48 (Fig 4A). Flowering time is a trait for which selection pressure may vary from year to year due to annual variation in rainfall and temperature [35]. In this situation, allelic fitness will oscillate from year to year, preventing segregating functional alleles at the locus from either being lost or fixed. However, we note that stabilizing selection on a phenotype which has recently shifted its optimum can also explain high frequency large effect alleles without invoking balancing selection [36].

For seed dormancy in teosinte, we expected to observe evidence for balancing selection in the form of functional alleles maintained at a high frequency since adaptation should favor a mix of phenotypes with seeds that germinate over a broad temporal range. Seed dormancy desynchronizes germination such that not all seed germinates the following season when environmental conditions for plant growth may be unsuitable in some years. Thus, selection should favor allelic diversity in wild species such that at least some seeds will be programed for delayed germination until future growth seasons [37]. Contrary to this expectation, we observed all six QTL detected for seed dormancy do not exceed a MAF of 0.03 which better fits a mutation-selection balance mechanism. In domesticated cultivars, it is desirable to have uniform germination to ensure synchronous maturity and therefore efficient harvesting by farmers [38, 39]. Accordingly, there is no seed dormancy in maize, and seeds, once planted, germinate readily.

Although large-effect QTL are rare, we observed the largest allele effects in maize (Fig 2). This reflects the differences in demography and selective forces acting on maize compared to teosinte. Teosinte traits are under selection because of their genetic correlations with fitness. Human selection in maize includes some similar fitness components (such as viability and fecundity), but the genetic correlations among maize traits are generally lower than among teosinte traits [8], and humans also select strongly for ear and kernel type, for example, possibly at the expense of natural fitness traits [40, 41]. Therefore, selection coefficients on fitness-related traits in maize are likely to be lower than in teosinte, reducing the effectiveness of selection on fixing or purging large-effect alleles. In combination with reduced selection, maize populations are managed by humans, who tend to plant seed from relatively few female parents [42], leading to greater genetic drift; but also migration is likely much more important in maize landraces than in teosinte because of active seed exchange among Mexican farmers [43, 44]. Recent migration could introduce novel alleles that were already fixed in other maize landraces, resulting in their segregation in the study population.

Another possibility is that the effective population size of our maize landrace is smaller than that of our teosinte population, so that selection would be more effective in teosinte. According to the Watterson estimator θ = 4N_eμ, where N_e is the effective population size and μ is the per-generation mutation rate of the population [45], we calculated θ_T for the teosinte population and θ_M for the maize population using the common set of 4.2 million SNPs. The results show the mean Watterson’s θ in maize is 89.8% smaller than in teosinte (θ_M = 3.89E-04; θ_T = 4.33E-04). If we use the estimates of mutation rate in maize, which is around 3×10⁻⁸ per site per generation [46, 47], then N_e in our maize landrace is smaller than N_e in our teosinte population, thus selection would be less effective in maize landrace and cannot bring large effect alleles into loss or fixation.

We observed more dominance in maize landrace than teosinte as shown by an increase in D/A ratio (Fig 5), suggesting that the additive genetic variants were depleted at a faster rate than the dominance genetic variants during domestication. This is consistent with the observation of Yang et al. [8] that selection during domestication depleted the additive variance relative to the dominance variance. Population genetic theory has shown that traits that were subject to directional selection have significantly higher dominance estimates than traits that are not subject to strong selection [48, 49]. This theory aligns with our observation that maize landrace, which has been subject to strong selection, has an excess of dominant variants relative to teosinte for domestication traits.

Genomic scans can help to identify candidate genes for follow-up analyses. Our stepwise regression approach detected several strong candidate genes in both teosinte and maize landrace. (1) We detected a major effect QTL on chromosome 3 for flowering time in teosinte near ZmMADS69, which is under balancing selection. Several recent studies using maize-teosinte mapping populations have mapped a flowering time QTL containing this gene [17, 50, 51]. Another recent study further fine-mapped ZmMADS69, which functions as a flowering activator through the ZmRap2.7-ZCN8 regulatory network and contributes to both long-day and short-day adaptation [52]. Notably, these studies investigated ZmMADS69 in maize-teosinte crosses and they did not identify the causative site affecting flowering time. Therefore, our results could be useful for future investigation to discover novel alleles in teosinte alone, and determine the functional variant of ZmMADS69. (2) We also detected a major effect QTL on chromosome 4 for seed weight in teosinte. For this QTL, a candidate gene TPP4 is near the QTL peak. TPP4 is a fully redundant paralogue of RAMOSA3 (RA3) and loss of both RA3 and TPP4 in maize leads to reduced meristem determinacy and more inflorescence branching [53]. (3) Finally, we detected two rough sheath genes as candidate QTL of plant height: rough sheath1 in landrace and rough sheath2 in teosinte. Both genes have been reported to affect plant architecture including plant height [20, 21]. It may be worth exploring natural variation in these genes and how domestication has acted on them.

We observed that a large proportion (~75%) of the additive heritability is missing in the sense that it cannot be ascribed to the detected QTL. This is true for both our teosinte and maize landrace populations across ten domestication traits (Fig 6). Missing heritability has been widely investigated in human studies and a well-characterized example is height [54]. The heritability of height has been estimated to be ~0.8 by twin studies, while the ~50 detected variants (QTL) first associated with height explained only ~5% of the phenotypic variance [55]. Subsequent larger studies identified 180 height genes that accounted for only 10% of the phenotypic variation [56] and 697 genes that explained only 20% of the heritable variation [57]. There are three main hypotheses regarding missing heritability [58, 59]: (1) missing heritability is largely due to rare variants of large effect, (2) the majority of missing heritability is attributable to common variants of very small effect, and (3) heritability estimates from classic twin studies are biased upward so there actually is no missing heritability.

For our study, large effect but rare variants should be detected because only 49 or 40 parents contributed to the 4,455 or 4,398 progeny. By our design, variants of large effect that are rare in nature become relatively common in our mapping population. Despite this design, we detected relatively few rare QTL of large effect and all QTL together explain only about 25% of the additive variance. Thus, we can exclude the hypothesis that rare alleles of large effect explain an appreciable fraction of the missing heritability. Similarly, we used a robust design and common-garden protocol to estimate trait heritabilities [8], thus it seems unlikely that our heritabilities are biased upward. Moreover, our heritability estimates and QTL detection were performed on precisely the same populations. Thus, our data argue strongly that most heritable variation in both teosinte and landrace is controlled by a mix of rare and common alleles of very small effect sizes below the threshold for detection as individual QTL–that is the infinitesimal model [60, 61].

Our variance component analysis shows that SNPs in regions of high recombination explain most heritable variance in both teosinte and maize landrace, suggesting recombination facilitates the maintenance of additive variation in our populations. It has been proposed that there is an interaction between natural selection and the recombination rate, known as the Hill-Robertson effect, such that there is a reduction in the effectiveness of natural selection in regions of low recombination [62, 63]. With low recombination, selection on one locus will drag variants at linked loci to fixation thereby reducing variation in the region [64]. A well-characterized example is reduced codon bias in regions of low recombination in Drosophila, which supports that natural selection is less effective against slightly disadvantageous mutations in regions lacking recombination [65]. Our observation of greater additive variance being associated with SNPs in regions of high recombination can be explained by the Hill-Robertson effect although this effect may be confounded with the Bulmer effect [11], as we observed the lower recombination regions have a bit more LD (S4 Table).

We also show that SNPs in regions of high divergence (high F_ST) between maize and teosinte explain more variance in teosinte than maize landrace, suggesting variants in these regions were either removed or brought to fixation during domestication, congruent with the results of Xue et al. [66]. A common feature of crop genomes is regions of reduced nucleotide diversity in the crop relative to its wild progenitor [5, 25, 28]. One example is a selective sweep of ~60–90 kb 5’ to the maize domestication gene tb1 that has an extended region of low nucleotide diversity [67, 68]. Another example is a large region on chromosome 10 in maize that was the target of strong selection during domestication, producing a 1.1 Mb segment with >15 genes that lost essentially all genetic diversity [69]. Such regions of high diversity in teosinte and low diversity in maize result in higher nucleotide divergence between maize and teosinte (S3 Fig). Thus, the observation that SNPs in regions of high divergence explain more genetic variance in teosinte accords with the expectation that many variants should have been either removed or fixed during and after domestication bottleneck.

The genetic dissection of crop domestication has been a focus of agronomists and evolutionary biologists ever since the rediscovery of Mendel’s law of inheritance. In this enterprise, diverse approaches have been utilized including classic Mendelian genetics, phylogenetics, population genetics, genomic scans for selection, analysis of differential gene expression, QTL mapping, association mapping, and cloning/charactering major genes controlling domestication traits [4, 5, 7]. In this paper, we take a novel approach of comparing the genetics architecture of 18 domestication traits in maize and its ancestor teosinte using matched populations. From our analyses, we infer that there has been a substantial depletion of quantitative genetic variants in maize relative to teosinte in terms of the numbers of segregating QTL for domestication traits. At the same time, the degree of dominance of segregating QTL has increased in maize, likely a consequence of selective removal of additive variants. We observed that regions of the genome that are strongly differentiated between teosinte and maize (high F_ST) explain less quantitative variation in maize than teosinte, suggesting that, in these regions, allelic variants were brought to (or near) fixation during domestication. Finally, we observed that about 75% of the additive variance in both teosinte and maize is missing in the sense that it cannot be ascribed to detectable QTL and only 25% of variance maps to specific QTL. This latter result suggests that morphological evolution during domestication is largely attributable to very large numbers of QTL of very small effect.