In the developing Drosophila VNC, approximately 90 neurons express the LIM-homeodomain regulator Apterous (Ap), and these represent at least six different cell types. Herein, we will focus on three of the Ap neurons: two cells of the Ap cluster—the Tv cells, which express FMRFa, and the Tvb cells, which together with the dAp cells express DopR (Figure 1G). A number of regulators involved in Tv neuron specification have been identified, but to better understand specification of the related Tvb/dAp neurons, we wanted to identify the putative neuropeptide gene expressed by Tvb/dAp neurons. The completion of the Drosophila genome led to the prediction of several additional neuropeptide genes, including the Neuropeptide like precursor protein 1–4 genes (Nplp1–4; Flybase, http://flybase.bio.indiana.edu/). The validity of these predictions has been confirmed by the identification of expressed sequence tags (ESTs) matching these genes (Flybase, http://flybase.bio.indiana.edu/), and by the detection of amidated and secreted peptides in circulation, and/or in brain extracts [15]. Expression of gene products from one of these genes, Nplp1, was found in a set of cells in the VNC reminiscent of the Tvb/dAp neurons [15]. In situ hybridization for Nplp1 verified that these cells indeed correspond to the dAp neurons and to one Ap cluster neuron (Figure S1C–S1E). To further identify this Ap cluster neuron, we raised antibodies against pro-Nplp1 and against one of the processed and amidated peptides, IPNamide, and detected a similar pattern (Figure S1A and S1B). We used markers for specific subsets of Ap neurons, and could identify the Nplp1-expressing cell in the Ap cluster as the Tvb neuron (Figure 1A–1E). In Tvb/dAp neurons, Nplp1 and DopR expression commences in the late embryo (18 h after egg laying [AEL]) and persists at least into the third larval stage (unpublished data). Nplp1 and DopR are thus specifically expressed by the 28 embryonic and larval Tvb/dAp neurons (Figure 1G).

Recent studies have revealed that ap and dimm are important for DopR expression in Tvb/dAp [14]. We analyzed whether these Ap neuron determinants, as well as eya, also affected Nplp1 expression (Figure 2). We found that Nplp1 expression depended on eya, ap, and dimm (Figure 2C–2E), and that eya also regulates DopR (Figure 2H–2I). How is Tv versus Tvb/dAp cell fate then determined? Although both cell types express ap, dimm, and eya, only Tv neurons express dac and have activated the BMP pathway. Could the mere absence of dac and/or BMP activation be sufficient to specify the Tvb/dAp fate? To test this, we analyzed expression of Nplp1 in dac and BMP mutants, but found no evidence of ectopic Nplp1 expression in Tv neurons (see below). Thus, specification of Tvb/dAp neurons likely requires additional factors restricted to this cell type.

The COE family of HLH regulators is highly evolutionary conserved [16], and is represented in Drosophila by a single member, col (Flybase, knot) [17]. COE genes play important roles during nervous system development in Caenorhabditis elegans and vertebrates [18–24], and col is expressed in the developing Drosophila central nervous system (CNS) [17], although no function has yet been assigned to it there. The involvement of members of this gene family in nervous system development in other species, and the embryonic CNS expression of col, prompted us to investigate the possible role of col during Ap neuron specification. col has a dynamic expression pattern in the VNC (below), and we initially focused on its expression in mature Ap neurons, at 18 h AEL, and larval stages. We find that at these stages, col is expressed specifically in Tvb/dAp neurons (Figure 1F), and expression is maintained in these neurons at least into the third larval stage (see below). This raised the possibility that col plays a role in Tvb/dAp cell fate specification. This notion was supported by the complete loss of Nplp1 and DopR expression in col mutants (Figure 2A, 2B, 2F, 2G, and 2I).

Previous studies have addressed the regulatory interactions between several of the Ap neuron determinants [9–12]. However, these had not been addressed in the case of dac, eya, and dimm. As expected from the late onset of dimm expression, we find no evidence of dimm regulation of Dac or Eya (Figure S2M and S2N). Similarly, as expected from the mild effect of dac upon FMRFa, we find that dac does not regulate Dimm (Figure S2L). In contrast, in eya mutants, we find a nearly complete loss of Dimm expression in the Tv, Tvb, and dAp neurons (Figure S2K and S2O).

With a more complete picture of how previously identified Ap neuron determinants interact genetically, we next addressed whether col acts upstream, downstream, or in parallel to other Ap neuron determinants. We first analyzed the expression of Col in embryos mutant for these other regulators. In general, we found no severe effects on Col expression (Figures S2A–S2I). The one exception was in sqz, in which we found a reproducible increase in the number of Col cells (Figure S2B, S2C, and S2J). This was, however, expected, since sqz affects the composition of Ap cluster cells, with an increase both in the number of Ap cluster cells (specifically in T1) and an increase in Tvb cells at the expense of Tv cells (in T1–T3) [9,10]. In line with this, we also find an increase in Nplp1 cells in sqz mutants (Figure S2B, S2C, and S2J).

Does col act upstream of other Ap neuron determinants instead? To address this, we analyzed the expression of these other regulators in col mutant embryos. This analysis was facilitated by the fact that col² and col³ mutants, which are both genetically strong alleles, are not protein null, thus allowing for detection of Col in col mutants. In addition, Col is expressed by all four Ap cluster neurons at stage 15 (see below). In col mutants (Figure 3), we find that although sqz and Dac are largely unaffected (Figure 3A, 3B, and 3J), ap, Eya, and Dimm are all completely absent from Ap neurons (Figure 3C–3H and 3J). Because ap, eya, and dimm all regulate FMRFa, the loss of these regulators prompted us to look at the expression of FMRFa as well, and as expected, in col mutants, we find a complete loss of FMRFa in the Tv neurons (Figure 3I and 3J). However, FMRFa is still expressed in the SE2 neurons, a feature common to all identified FMRFa regulators except dimm (Figure 3I). These results suggest that Ap cluster neurons are generated in col mutants, but are incompletely specified because they express part of their normal specification code such as dac and sqz, but not other elements of the code such as ap, Eya, Dimm, FMRFa, Nplp1, and DopR.

The severe effect of col upon ap, eya, and dimm within all Ap cluster neurons, and upon FMRFa within the Tv neuron, is at odds with the restricted expression of Col in Tvb/dAp neurons at late embryonic stages. We therefore analyzed whether Col is more widely expressed at earlier embryonic stages, focusing on the Ap cluster neurons. This revealed that although col is restricted to Tvb neurons at stages 17 and 16 (Figure S3K and S3L), we observe expression in all four Ap cluster neurons at stage 15, the stage at which these neurons are first identifiable using ap, Eya, Dac, and sqz as specific markers (Figure S3E).

Is Col expressed even in the progenitor cells generating Ap cluster neurons? Because ap, Eya, Dac, and sqz are not expressed in Ap cluster neurons prior to stage 15, resolving this issue required the identification of the neuroblast lineage generating the Ap cluster. Extensive work during the last two decades has provided a detailed lineage map of most, if not all, of the 30 neuroblasts found in each hemisegment, and has identified regulatory genes expressed by different neuroblasts [25–29]. These studies, together with the extreme lateral positioning of early Ap cluster neurons and their appearance only in thoracic hemisegments, allowed us to use a series of specific markers and determine that the Ap cluster is generated by NB 5–6—a lateral-most neuroblast that has been shown to generate larger lineages in the thoracic segments [28,29] (see Figure S3 and Text S1 for a full description of the mapping of Col expression in NB 5–6). These results, combined with previous detailed studies of NB 5–6 development, allow us to outline a tentative model for the thoracic NB 5–6 lineage, and to place Col expression within this lineage (see below).

Col is expressed by all four newly born Ap cluster neurons and is essential for Ap cluster specification, as evident from the complete loss of ap and Eya expression in col mutants. Col is rapidly down-regulated from three Ap cluster cells and maintained only in Tvb. Is the down-regulation of col important for proper Ap cluster differentiation? To test this, we misexpressed col using the ap^GAL4 driver, which is not expressed until stage 16, thus maintaining col expression in all four Ap cluster neurons at the time when Col is normally down-regulated. This experiment led to frequent activation of Nplp1 in one additional Ap cluster neuron (Figure 4A and 4B), and staining for Dimm reveals that this cell is indeed the Tv neuron (Figure 4C). FMRFa expression is frequently down-regulated in Tv, but we do observe Tv cells that co-express FMRFa and Nplp1 (Figure 4B). The finding that col misexpression in the Ap cluster only leads to one ectopic Nplp1 cell and no ectopic Dimm cells indicates that col cannot induce a peptidergic cell fate, at least not with this late driver. However, because the two unaffected cells already are expressing ap and Eya, we predicted that co-misexpression of dimm, together with col, should trigger Nplp1 expression in all four Ap cluster neurons. This is indeed what we find (Figure 4D and 4E). In summary, down-regulation of col in three Ap cluster neurons is essential for proper Ap cluster specification.

Col is expressed prior to ap and Eya in the Ap cluster neurons, and it is essential for ap and Eya expression within these cells. To address whether col is also sufficient to activate ap and Eya, we misexpressed col in all neurons, using the elav-GAL4 driver (Figure 5) [30]. This led to ectopic activation of both ap and Eya (Figure 5A–5E). In addition, we found some activation of Dimm, Nplp1, and DopR expression (Figure 5F–5L and 5O–5Q). Although ectopic activation of ap or Eya alone was found in several regions, co-activation was largely confined to neuroblast row 5—the anterior region of Gsbn expression (Figure 5M and 5N). We typically observe six to ten ap/Eya co-expressing cells in the lateral-most part of row 5 (Figure 5M and 5N). Ectopic activation of ap/Eya, together with Dimm, Nplp1, and DopR, was also confined to lateral-most row 5, i.e., the posterior-most part of gsb^lacZ cells, and further confined to thoracic segments (Figure 5B–5D, 5J, 5L, and 5O–5Q). Ectopic Nplp1/DopR expression is not overlapping with FMRFa, and there is clear evidence of ectopic Dimm expression (Figure 5P and 5Q), indicating that additional peptidergic neurons are being generated. Ectopic generation of ap/Eya double-expressing cells, i.e., ectopic “Ap cluster” neurons, was observed already at stage 13, i.e., prior to when Ap cluster neurons are normally born (unpublished data).

These results show that col can activate ap and Eya in a number of neurons, but can act to generate bona fide Ap cluster neurons only in a highly context-dependent manner: in lateral, thoracic, row 5 neurons. The appearance of six to ten Eya-expressing cells, but only three to five Nplp1/DopR-expressing cells, and no evidence of ectopic FMRFa expression, suggests that the generation of ectopic Ap cluster neurons is biased toward Tvb (Nplp1/DopR expressing) as opposed to Tv (FMRFa expressing) cell fate. In contrast, although col function depends upon these three positional cues, our results indicate that col is able to override the temporal coding within lateral row 5, and activate Nplp1 and DopR in earlier-born neurons.

The loss- and gain-of-function studies place col clearly upstream of ap and eya. Does col act merely to regulate ap and eya in early postmitotic Ap cluster neurons, or does it play additional roles during Ap cluster formation? To further address this issue, we attempted to “cross-rescue” col with ap and eya, by expressing ap and eya in a col mutant background (Figure 6). First, as a positive control, we attempted to rescue col by providing col activity using elav-GAL4/UAS-col. This led to a robust rescue, both of Ap cluster determinants (Eya, ap, and Dimm) and of terminal differentiation genes (Nplp1, DopR, and FMRFa) (Figure 6A–6H, 6L, and 6M). Similar to the col misexpression experiments, we find a clear increase in “Ap cluster” neurons, primarily of the Tvb type, as evident from the finding of six to ten ap/Eya- and three to five Nplp1/DopR-expressing neurons per hemisegment (Figure 6E–6H and 6M). Next, we attempted to “cross-rescue” col mutants with ap and eya, and could indeed find a significant degree of rescue of Ap cluster formation, as evident both from Dimm and FMRFa expression (Figure 6J–6M). In contrast, we found no evidence of rescue of Nplp1 or DopR in these embryos (Figure 6I and 6L). Because we can detect Col in the col² and col³ mutant backgrounds, we could identify a Dimm/Col-expressing cell adjacent to the Tv/FMRFa neuron (Figure 6K and 6N). This indicates that ap/eya can partially rescue Tvb cell fate, but in the absence of col activity, these “Tvb” neurons do not activate Nplp1. In summary, the finding that in col mutants, ap and eya can partially rescue the Tv cell fate, but not Tvb cell fate, suggests additional roles for col in Tvb specification.

Our results indicate that Tvb cell fate is not specified by a linear col→ap/eya→dimm→Nplp1/DopR genetic cascade. To further address this issue, we tested the sufficiency of col, ap, and eya to activate Dimm when misexpressed both alone and in combination. These experiments reveal that although col can trigger some ectopic activation of Dimm, there is little effect upon Dimm when misexpressing ap, eya, or ap/eya (Figure 7A). In contrast, co-misexpression of col with either ap or eya, and in particular, co-misexpression of all three genes, leads to striking ectopic Dimm expression (Figure 7A–7E).

Does col play a role even at the final step of Tvb differentiation, i.e., in the activation of Nplp1? We attempted to address the possible late role of col by misexpressing it alone and together with other Ap neuron determinants, and then assay its potency in activating Nplp1. Importantly, if there is a simple linear col→ap/eya→dimmNplp1/DopR genetic cascade at work, the effect of triple co-misexpression of ap/eya/dimm should not be enhanced by addition of col to this code. However, we find a striking enhancement of ectopic Nplp1 expression when adding col to this code (Figure 7F–7J). One particular double co-misexpression combination, col/ap, was more potent than others in activating both Dimm and Nplp1 (Figure 7E and 7J). A likely explanation for this effect is that co-misexpression of col/ap activates significant ectopic eya expression (unpublished data).

To further address the late role of col, we generated a transgenic RNA-interference (RNAi) line (UAS-col-dsRNA) and attempted to suppress col gene activity by crossing this line to ap^GAL4. Because ap^GAL4 also drives expression in the developing wing disc, we first analyzed the efficiency of this novel tool in suppressing col gene activity in this tissue. This phenocopied the effects of col mutants on wing development [31], with a clear L3–L4 wing vein fusion (unpublished data), indicating that this RNAi transgene specifically blocks col gene activity. However, upon analyzing late larval (third instar) CNSs, we found no effect upon Col expression in Tvb neurons, and as expected, no effect upon Nplp1 expression (unpublished data). Recent studies reveal that RNAi can be efficiently enhanced by overexpression of components of the RNAi pathway, in particular of the Dicer-2 (Dcr-2) gene (G. Dietzl and B. Dickson, personal communication). We therefore co-expressed Dcr-2 with col dsRNA (UAS-Dcr-2/+; ap^GAL4/UAS-col-dsRNA), and found a clear effect not only upon Col, but importantly, also upon Nplp1 expression. We found no obvious effect in the first instar larvae (unpublished data), but in third instar larvae, Col expression is specifically and completely lost from all Tvb/dAp cells (Figures 8A, 8B, and 8E). This leads to a complete loss of Nplp1 in 44% of Tvb/dAp cells (Figure 8C–8E), and strongly reduced expression in the remaining expressing cells (Figure 8B). Strikingly, this strong effect upon Nplp1 is not an indirect effect of down-regulation of ap, Eya, or Dimm (Figure 8A–8E). As anticipated, col RNAi has no effect upon FMRFa expression in the third instar larvae (n = 5 VNC; unpublished data).

Together, the finding that col can act potently with ap and eya to activate Dimm, that col can act potently with ap, eya, and dimm to activate Nplp1, and that postmitotic RNAi of col strongly affects Nplp1 expression without affecting ap, Eya, or Dimm, does not fit with a simple linear cascade model for Tvb specification. Rather, it strongly suggests that col is acting at several levels during Tvb specification and differentiation.

Previous studies have identified several regulators acting to specify Tv fate and to control FMRFa expression. Although co-misexpression of parts of this code had been previously tested, all possible combinations had not. Similar to the combinatorial activation of Nplp1 and DopR, we find that whereas co-misexpression of ap/sqz, ap/dac, or ap/dimm has limited effect upon FMRFa expression (Figure 9) [9,10,12], triple co-misexpression of these regulators, and in particular of ap/dimm/dac, leads to a dramatic ectopic activation of FMRFa (Figure 9G–9K and 9M).

The identification of two partly overlapping and highly potent combinatorial codes allowed us to ask an important question: Does combinatorial misexpression of these regulators merely lead to a general confusion with a mixed neuronal identity, or are these codes truly instructive and specific? To address this issue, we analyzed the expression of Nplp1 and FMRFa in the various misexpression backgrounds. Not surprisingly, when common and partial components of these codes are misexpressed, such as ap/dimm (common to both Tv and Tvb/dAp neurons), we find ectopic activation of both Nplp1 and FMRFa in different subsets of cells (Figure 9B, 9H, and 9M). However, as a third, and cell-type specific, regulator is added, not only does the amount of ectopic, terminal differentiation gene expression increase dramatically, but we find less evidence of cross-activation of the inappropriate downstream gene (Figure 9C–9F and 9I–9M). This surprising finding reveals that combinatorial misexpression may act in a highly specific and instructive manner, and that these combinatorial codes may be viewed as potent binary switches for cell fate specification. In addition, for both codes, ectopic activation of FMRFa and Nplp1 is observed in neurons throughout the VNC and brain, and traverses many developmental boundaries, such as anteroposterior, dorsoventral, and mediolateral boundaries.

We have identified a multistep process for specifying the Tv and Tvb cell fates. What would be the purpose of this type of sequential combinatorial coding? In other model systems with higher genetic resolution, such as Escherichia coli and yeast, extensive genetic analysis has revealed that this type of sequential gene regulation is quite common [32,33], and a recent study in C. elegans suggests it may also function during neuronal specification [34]. These regulatory nodes, also known as feedforward loops (FFL), have been shown to ensure fidelity in gene regulation [35,36]. For instance, in a simple FFL in which gene A regulates gene B, and A/B then co-operate to regulate C, activation of C depends upon prolonged A expression such that A/B will have time to activate C. If A is only active in a short burst, B may be activated, but C is not, because A/B never co-express for a sufficiently prolonged period of time. The role of col during Ap cluster specification provides an excellent example of a FFL used during neuronal cell fate specification. col is expressed in all four Ap cluster cells and plays an early role in activating ap and Eya, but is only maintained in Tvb, where it plays a later role in activating first dimm, then Nplp1. Maintained expression of col in all four Ap cluster neurons, by driving col expression from ap^GAL4, leads to activation of the Tvb program also in the Tv neuron. Thus, a burst of col expression has a different informational value than persistent col expression—general Ap cluster specification versus Tvb specification.

Misexpression of each of the two identified combinatorial codes leads to striking ectopic activation of the Nplp1 and FMRFa genes, and we are surprised by two particular aspects of these findings. First, the global potency of these codes—co-misexpression triggers ectopic FMRFa of Nplp1 in a number of neurons, located in many different anteroposterior, dorsoventral, and mediolateral positions. Thus, it would appear that early regulators mainly act to ensure proper combinatorial coding in each neuron, and play a minor role in restricting cell fate by limiting the cell's competence—once the proper code is in place, the cell fate specification program will be carried out irrespective of the history of the cell. Second, the striking binary effect of these codes is noteworthy—the change of one single player in a code completely alters target gene choice. For instance, misexpression of ap/dimm/dac leads almost exclusively to strong FMRFa activation, but simply replacing dac with col leads to almost exclusively Nplp1 activation. Thus, it appears that more complete codes not only have great potency, but also have great specificity.

Col shows a very dynamic expression pattern in the VNC—exemplified in NB 5–6 by the expression in the neuroblast, in two GMCs, in all four Ap cluster neurons, and finally only in Tvb. This poses three obvious questions: what activates col in the neuroblast, what shuts it down in three of the Ap cluster neurons, and finally, what maintains col in Tvb? As for the activation of col in the late 5–6 neuroblast, row 5 neuroblast determinants, thoracic determinants, and late temporal determinants are obvious candidates. Indeed, our current work has identified input from a number of such upstream regulators (D. Karlsson, M. Baumgardt, and S. Thor, unpublished data). It is less clear why col expression is lost from three Ap cluster cells and maintained in Tvb. It is possible that the initial expression in all four Ap cluster cells merely reflects residual expression, as an effect of the activation by earlier determinants acting in the neuroblast. But why is col then maintained in Tvb, and similarly, what maintains eya and ap in all four Ap cluster cells? One simple solution would be autoregulation of each gene. But surprisingly, there is no evidence of autoregulation of col (this study) or ap [6,9] (eya has not been addressed). In addition, we find no clear evidence of cross-regulation between col, ap, or eya, at least not during embryonic stages. Thus, it seems likely that other mechanisms, either unidentified regulators or, perhaps, epigenetic mechanisms, act to ensure the continual expression of these regulators during larval (and perhaps adult) life.

The following stocks were used: ap^md544 (referred to as ap^GAL4), ap^P44, ap^rK568 (referred to as ap^lacZ), sqz^DF, sqz^GAL4, sqz^ie, UAS-sqz, UAS-ap, wit^A12, wit^B11, UAS-myc-EGFP–farnesylation (referred to as UAS-mEGFP^F) [9]; dimm^p1, dimm^rev4, UAS-dimm [11]; elav-GAL4, [30]; dac³, dac⁴ [37]; UAS-dac [38]; eya^Cli-IID [39]; Df(2L)eya10 (referred to as eya¹⁰), P{UAS-eya.B.II} (referred to as UAS-eya) [40]; UAS-nls-myc-EGFP (referred to as UAS-nmEGFP) [41]; ladybird fragment K driving lacZ (referred to as lb-lacZ) [42]; col¹, col², col³ [43]; UAS-col [31]; P{lacZ-un4}hkb⁵⁹⁵³ (referred to as hkb^lacZ) [44]; gsb⁰¹¹⁵⁵ (referred to as gsb^lacZ) [45]; and wg⁷⁵⁸ (referred to as wg^GAL4) provided by K. Basler. Mutants were kept over CyO, Act-GFP, or TM3, Ser, Act-GFP balancer chromosomes. w¹¹¹⁸ was often used as wild type.

A 497–base pair (bp) fragment of the col cDNA (position 1,584–2,080 of GenBank sequence NM 080074) was amplified by PCR, sequenced, and then inserted as an inverted repeat into the pWIZ vector [46]. Transgenes, denoted UAS-col-dsRNA, were generated by standard methods. Six different UAS-col-dsRNA transgenic lines were driven by ap^GAL4, and showed varying degrees of col wing effects (L3–L4 wing vein fusion). Two strong lines were used for CNS analysis. To enhance the col RNAi effect, a UAS-Dcr-2 transgene (on the X chromosome) was used (a gift from G. Dietzl and B. Dickson).

Full-length col (in pET17b, provided by M. Crozatier and A. Vincent) and C-terminal part of dimm (amino acid residues 210–390 in pGEX-4T) were expressed in bacteria, and antibodies were raised in rabbits and guinea pigs (AgriSera, Vännäs, Sweden). Antibodies to IPNamide and proNplp1 were raised in hens against the peptide sequences NVGTLARDFQLPIPNamide and FLGRVLPPTRATASTHRSRL, respectively (AgriSera). Antibodies to proFMRFa were raised in rabbits against the C-terminal peptide sequence GAQATTTQDGSVEQDQFFGQ (Covance, Princeton, New Jersey, United States). Peptide antibodies were affinity purified, and all polyclonal sera were pre-absorbed against pools of early embryos. Other antibodies used were: guinea pig α-Deadpan (1:1,000) (provided by J. Skeath), rat monoclonal α-Gsbn (1:10) (provided by R. Holmgren), mouse monoclonal antibody (mAb) α-Col (1:250) (provided by M. Crozatier and A. Vincent), mAb α-ELAV (1:10), mAb α-Repo (1:10), mAb α-c-Myc mAb 9E10 (1:30), concentrated mAb α-β-gal mAb 40–1a (1:20), mAb α-Dac dac2–3 (1:25), mAb α-Eya 10H6 (1:250) (all from Developmental Studies Hybridoma Bank, Iowa City, Iowa, United States), rabbit α-β-gal (1:5,000; ICN-Cappel, Aurora, Ohio, United States), rabbit α-GFP (1:500; Molecular Probes, Eugene, Oregon, United States), and rabbit α-phospho-histone H3-Ser10 (pH 3) (1:2,500; Upstate/Millepore, Billerica, Massachusetts, United States). Immunolabeling was carried out as previously described [10].

Zeiss LSM 5 Confocal microscope was used to collect data for all fluorescent images (Zeiss, Oberkochen, Germany); confocal stacks were merged using LSM 5 software or Adobe Photoshop (Adobe Systems, San Jose, California, United States). Where immunolabeling was compared for levels of expression, wild-type and mutant tissue was stained and analyzed on the same slide. Bright-field images were collected on a Nikon E400 microscope with a SPOT-RT digital camera (Nikon, Tokyo, Japan). Statistical analysis was performed using Microsoft Excel (Redmond, Washington, United States). Where appropriate, images were false colored to facilitate for color-blind readers.

The FlyBase (http://flybase.bio.indiana.edu/search) accession numbers for the genes and gene products discussed in this paper are Ap (CG8376), col (Flybase knot) (CG10197), dac (CG4952), dimm (CG8667), DopR (CG9652), eya (CG9554), FMRFa, (CG2346), Gbb (CG5562), Nplp1 (CG3441), PHM (CG3832), sqz (CG5557), and Wit (CG10776).

The GenBank (http://www.ncbi.nlm.nih.gov/Genbank) accession number for the col cDNA from which a 497-bp fragment was taken is NM 080074.