In yeasts, including the pathogenic Candida, an up-regulation of multidrug transporter genes belonging to either ATP Binding Cassette (ABC) or Major Facilitator Superfamily (MFS) is frequently observed in the cells exposed to the drugs leading to the phenomena of multidrug resistance (MDR) [1]. Among the 28 putative ABC and 95 MFS transporter genes identified in the C. albicans genome, only ABC transporters CaCdr1p and CaCdr2p and MFS transporter CaMdr1p, are found to be the major determinants of azole resistance [2],[3]. The reversal of the functionality of these multidrug efflux pump proteins represents an attractive strategy to combat azole resistance.

The major ABC transporters such as CaCdr1p, CaCdr2p bear similar topology and exist as two homologous halves. These, like any other member of the ABC superfamily have four distinct modules: two transmembrane domains (TMDs) each consisting of six transmembrane segments (TMSs) and two nucleotide binding domains (NBDs) located on the cytosolic side of the membrane. Though similar in topology and promiscuity towards substrate specificity, these ABC multidrug transporters of C. albicans also display selectivity to the range of substrates they can export [4].

The transporters belonging to MFS, consists of membrane proteins from bacteria to higher eukaryotes and these are involved in symport, antiport or uniport of various substrates [5],[6]. One of the 17 families of MFS transporters uses the proton motive force to drive drug transport and has been identified in both prokaryotes and eukaryotes [7]. Crystal structures of MFS proteins such as lactose permease (LacY), glycerol-3-phosphate (GlpT), EmrD and oxalate: formate antiporter (OxlT), suggest high structural resemblance among this family of proteins [8]. These consist of 12 TMS, arranged with a similar predicted topology, strongly supporting a common structural architecture or fold across all the MFS transporters [9]–[12]. The fungal MFS members particularly those involved in drug transport are poorly explored in terms of their structure and function [13]. The multidrug MFS transporter CaMdr1p belongs to DHA1 family which is widely distributed and includes both drug-specific and multidrug efflux pumps [14].

Random and site-directed mutational strategies have been extensively used to understand the structure and function of these MDR efflux proteins. For example, random mutational analysis of an ABC transporter, ScPdr5p of budding yeast identified several amino acid residues that alter its substrate specificity and sensitivity to various inhibitors [15],[16]. Tutulan-Cunita et al. observed that several point mutations led to significant changes in drug specificity of ScPdr5p which are distributed throughout the length of the protein [17]. Site-directed mutagenesis followed by an elegant screen done by Golin's group has revealed interactions between TMS 2 and the NBD which may help to define at least part of the translocation pathway for coupling ATP hydrolysis to drug transport mediated by ScPdr5p. Recently, Schmitt et al. have elucidated the role of H1068 in H-loop of ScPdr5p which couples ATP hydrolysis with drug transport [18].

Site-directed mutational analysis of multidrug ABC multidrug transporter CaCdr1p (a close homologue of ScPdr5p) has revealed insight into its drug binding and efflux properties. These studies have implicated some of the amino acid residues of TMS 5, 6, 11 and 12 as the components of the substrate binding pocket(s) of CaCdr1p [19],[20]. Together, these studies suggest that the drug binding sites in CaCdr1p are scattered throughout the protein and probably more than one residue of different helices are involved in binding and extrusion of drugs. However, there is still insufficient information available to predict where and how exactly the most common antifungals such as azoles bind and how are they extruded by CaCdr1p.

Site-directed mutational strategies rely on conservation of residues in a Multiple Sequence Alignment (MSA). The conservation of a residue is calculated from the amino acid frequency distribution in the corresponding column of a MSA. However, the physicochemical conservation is not necessarily responsible for a protein's structure and function but could reflect a more general function such as membrane localization. Thus conservation alone is not sufficient to distinguish between residues responsible for the protein function and membrane localization. Membrane proteins differ from soluble proteins because of their inter-TM hydrophilic and TM hydrophobic propensities, which have allowed the development of efficient membrane protein TM prediction methods [21] and of membrane protein specific substitution matrices [22].

The quantification of residue conservation has evolved over the last few years to the use of information theoretic measures [23]. Relative entropy is a distance measure commonly applied to multiple alignments by comparing the observed frequency distribution with a background distribution. In the present study, we have developed and employed a new method using information theory to rationalize mutation strategies and also applied it to a MFS multidrug transporter CaMdr1p [24]. Relative Entropy (RE) or the Kullback-Liebler divergence is an information theoretic measure of the difference between two probability distributions and has been increasingly applied in bioinformatics to identify functional residues [24],[25]. The use of RE with background frequencies [26] can improve the prediction of a protein's functional residues [27]–[32] as well as detect residues that determine the functional subtype of proteins [28]. Though the basic Kullback-Liebler equation has not changed, its intelligent application in our method calculates Relative Entropy (RE_M) relative to its context within the membrane. The RE_M scoring scheme has been improved by treating TM and inter-TM regions of MFS proteins separately which has drastically increased the credibility over the existing methods [23]. In this manuscript, we have compared traditional treatment of conservation, and standard RE, with our improved method. We validated our predictions by replacing the predicted highest RE_M positions of CaMdr1p with alanine by site-directed mutagenesis. We show that most of these residues when replaced with alanine showed decreased resistance to drugs which was corroborated by abrogated efflux of drugs. Additionally, we could further confirm the functional relevance of each of these high RE_M residues by predicting their location in deduced 3D model of CaMdr1p and their role in maintaining apparent inter-helical interactions. With this approach, our method enabled us to accurately predict MFS-wide function-specific residues, validated by using CaMdr1p.

The multidrug MFS transporter CaMdr1p harbors a conserved antiporter ‘motif C’ within TMS 5. Our recent study has revealed that the conserved and critical residues of this motif and of TMS 5 are bunched together on the same face of its helical wheel projection and are critical in drug efflux [35]. However, the structure and function aspects of this major multidrug transporter remain poorly understood. To address some of these questions, in this study, we have rationalized conventional mutational strategy and applied computational approach to predict functionally critical residues of CaMdr1p.

The sequence set described in this manuscript represents a comprehensive non-redundant coverage of annotated MFS sequences from SWISSPROT. Many methods have been developed to improve the MSA of membrane protein families for accurate predictions of residues critical for structure and function [36]. Membrane proteins have fold signals which are easily mapped to the primary sequence as TM and inter-TM stretches. Considering the differences in physico-chemical properties of these two regions, membrane protein specific substitution matrices have been developed [22]. However, we argued that a conservation score on the basis of identity or physico-chemical similarity still remains inadequate as the background frequencies of their immediate environmental milieu are radically different with respect to hydrophilic and hydrophobic propensities. This is also apparent from the conservation scores of the MSA wherein a large proportion of the conserved columns correspond to hydrophobic TM regions. Notably, two CaMdr1p residues (F216 and L217) with high conservation but low RE_M were taken as controls, when replaced with alanine showed no change in the phenotype (data not shown). One of the most basic fold specific signals is the hydrophobic core in globular proteins, and the TM region in membrane proteins. Unlike globular proteins, the hydrophobic TM region is continuous in the membrane protein's primary structure, and indeed this still remains one of the preferred methods to identify membrane proteins, and map their TM regions. While it is intuitive that the synchronous stretch of hydrophobic residues is responsible for membrane localization, the application of a scoring method that can distinguish these residues from family-wide alignment columns associated with other functions has not yet been deployed. In essence, we require a method that can objectively separate the TM signals from other signals. To overcome these limitations, we improved existing method(s) of information theory wherein RE_M was calculated on the basis of MSA of MFS proteins, keeping in mind the differences in the environmental milieus. We thus treated TM and inter-TM regions by different background probabilities for calculation of RE_M. These RE_M scores helped us to predict those sites which have amino acid distributions very different from the respective background distribution thereby statistically predicted to be functionally critical. Not all the residues predicted using RE_M, are present in every protein in the family. In CaMdr1p, 16 residues were identical with the most frequently occurring residue in the thirty highest scored alignment columns, and were mutated to directly validate the prediction (Fig. 2B). Our results of drug susceptibility assays revealed that almost all of these matched residues with high RE_M when replaced with alanine displayed sensitivity to the tested drugs and showed abrogated drug transport (Fig. 3). Interestingly, when we mutated residues which had high conservation values but lower RE_M values (negative control); none showed alterations in drug susceptibilities and thus did not retain the functionally critical stringency as was evident from residues with higher RE_M. For example, analysis of a few conserved columns of the MSA, such as F216, L217 and L171 having RE_M values between 0.57-0.44 revealed that their replacement with alanine did not affect the function of CaMdr1p (data not shown). This strengthens the fact that our method takes into account the conservation along with the background frequency and thus lists out residues which affect the function. Also, to check the efficiency of the method, another negative control used was to mutate residues which are having low conservation and low RE_M values but lie in the vicinity of one of the 16 selected high RE_M residues. For example, when C225 which is closer to the critical G219 and D235, was mutated to C225A, the functioning of the protein was not affected (data not shown). Similarly, for critical G256, when residues A248, A253 and V254 which are within its vicinity were mutated as A248G, A253G and V254A, the mutant variants continued to behave as WT-CaMDR1-GFP [35].

To further elucidate the role of predicted residues in the functionality of CaMdr1p, a homology model based on the available crystal structures of lac permease, glycerol-3-phophate and oxalate: formate transporter was deduced [9]-[11]. The RE_M method predicts the relative importance of a residue purely from sequence analysis and is independent of the protein's structure. However, the role a residue plays in the protein's function is not readily apparent from its sequence. We exploited the protein's 3D model as a guide to reason why a residue is functionally critical. The deduced 3D model suggested that similar to other MFS structures, the 12 TM helices of the CaMdr1p span the membrane in such a way that they form the channel pore particularly aligned by residues of TMS 2, 4, 5, 7, 8, 10 and 11. From the deduced homology model of CaMdr1p, a symmetric contact map was generated to highlight the inter-helical interactions of the protein (Fig. 5B). Based on the predictions from the distance map, we could show that many high RE_M residues are indeed a part of inter-helical interactions (Fig. 6B). It is apparent that more than one residue pair is predicted to be involved in maintaining the interactions between helices (Fig. 6A).

Our aim in developing this method was to identify residues with high specificity which would play a critical role across this entire MFS protein family. Although signals associated with antiporter motifs have been identified using this method, a finer granularity in function such as substrate specificity determining residues is not expected, as these signals would not be family-wide. Since the enlisted residues with high RE_M values which are functionally critical for CaMdr1p are expected to be family-wide function-specific and thus critical for the entire MFS protein data set, we validated their relevance from the earlier published work. It is known that Motif A of the MFS transporters span an eight residue long loop between TMS 2 and 3 and is suggested to be involved in maintaining a β-turn linking the adjacent TM helices [14]. In the present study, G183 and R184 in the loop between TMS 2 and TMS 3 of CaMdr1p were picked up as family-wide function-specific residues thus corroborating that these residues are a part of Motif A (GxLaDrxGrkxxl) which holds importance throughout the MFS transporters. The hypothesized rocking motion in MFS presumably requires conformational changes in the TMS and the β–turns. In this, the transporter inter-converts between C_i (inward facing) and C_o (outward facing) states for translocation of substrates. In glycerol-3-phosphate of E. coli, it was seen that D88 was involved in inter-conversion between these C_i and C_o states of the protein [10]. Interestingly, D88 corresponds to E178 of CaMdr1p which also lies in Motif A which upon mutation to alanine turns out to be critical for drug susceptibility and efflux (Table 1).

Motif B (lxxxRxxqGxgaa) of all MFS has a role in energy coupling which spans the N-terminal half of TMS 4 [7]. CaMdr1p contact map reveals that residues in Motif B interface with residues ¹⁶⁵GxxxG¹⁶⁹ on TMS 2. Motifs rich in glycine and proline residues promote formation of special backbone conformation including kinks in TMS, tight interactions between TMS and very flexible β-turns. In human VAchT, Motif B and the adjacent sequences contain a total of nine notch signatures. A notch allows two helical TMS to approach each other unusually closely because small side chains are located at the interface. R124 of PcaK of Pseudomonas putida which is equivalent to high RE_M R215 of CaMdr1p of C. albicans is shown to be critical for helix packing [37]. Interestingly, G111 of LacY of E.coli which also occupies a position in the same alignment column is also critical and earlier shown to be a residue at a kink.

Residues from Motif C (gxxxGPxxGGxl) which is exclusive to 12-TMS family are also picked up by our calculations [7]. G150 of LacY of E.coli which is equivalent to high RE_M G256 of CaMdr1p is function-specific for LacY protein [38]. A stretch of conserved residues ²⁹⁶Pespr³⁰⁰, previously unidentified, at the end of TMS 6 were also predicted with high RE_M. We have mutated equivalent residues P296A, E297A and T298A of CaMdr1p that overlap with the consensus residues in the stretch and found that cells expressing these mutated variants displayed increased sensitivity to drugs. However, the functional significance of these residues is yet to be established.

There are a few exceptions which emerged from our method. For example, our method did not pick up any residue of Motif D2. This could be an artifact of the method used for alignments in earlier studies. In this study we have employed a membrane protein specific alignment method whereas earlier reports have used standard multiple alignments substitution matrices with smaller data sets. However, when we repeated the alignment using MUSCLE [39] and with the standard substitution matrix (Blosum 62) [40] on the complete data set the motif still did not appear (data not shown). Motif D2 is assumed to have a structural significance as it holds a major kink within TMS 1 but mutations in this motif do not alter the backbone conformation. As an example of the possibly insignificant role of the motif, in human VAchT, the mutation of L49G in this motif completely eliminates propensity for a kink or notch and abolishes activity while normally a glycine itself is expected to be present at this position and is supposed to be involved in maintaining a major kink in this motif [41].

Out of the 16 residues that were mutated, T160A, L211A, W273A and R274A did not lead to any phenotypic changes. It is known that for some of the positions in alignment, the most frequent amino acid does not match with the residue of CaMdr1p at that site. One reason for this could be that some of the functionally important residues co-evolve i.e., these residues may mutate, with compensatory mutation occurring elsewhere in the protein to regain function [42]. T160 where the most frequent residue is a serine at that position may be one such case. Another reason may be that the alignment used in this study involved prediction of TMS with the possibility of errors in demarcating the edges of TM helices. Residues from columns lining the edges of the helices may be wrongly assigned to TM and inter-TM regions. This probably explains the lack of any effect of mutation on residues T160 of TMS 2 and L211 of TMS 4 which lie at the edge of the respective TMS. Other exceptions to our predictions are the mutation of W273 and R274 which though highly conserved and probably a part of the new motif but do not abrogate function upon mutation. Although a few tryptophans in an ABC transporter MRP1, have been shown to be involved in substrate binding and transport [43], generally, in a membrane protein tryptophan residues located on the surface of the molecule are mainly positioned to form hydrogen bonds with the lipid head groups while their hydrophobic rings are immersed in the lipid part of the bilayer [44]. We predict that W273 and R274 may be associated with membrane helix orientation and this function may not be perturbed by mutating them individually through alanine scanning. Alternatively, the tryptophan-arginine residues could be functionally critical in tandem and compensate each other for the loss of either one of them.

Of note, in our predictions, substrate specific residues with high RE_M are not picked up which predominantly occur in C-terminal of MFS proteins. It should be mentioned that since our alignment considers the entire MFS, residues responsible for substrate specificity would only be selectively conserved within a subfamily and would not have sufficiently strong signals to be visible in this present family-wide study. For this, the same method may be applied to a data set classified on the basis of substrate selectivity to identify residues critical to the functioning of that subfamily.

There are a number of conservation methods known but none has yet achieved both biological and statistical rigor. We have used RE_M to separate conserved residues from the background function of TM localization. The interpretations support the well-known fact that MFS has a conserved N-terminal half which has residues important for maintenance of a specific fold for this class of proteins while C-terminal half has a more specific role in substrate binding and recognition [7]. Taken together, our study provides an insight into the molecular details of MFS transporters in general and CaMdr1p in particular. Our method of scaled RE_M calculations improves its performance over other information theoretic methods. Additionally, this study also provides a method for rational mutational analysis not only for MFS proteins but can be applied to any class of membrane proteins and thus makes it possible to predict and locate family-wide functionally relevant residues.