Abstract

Author summary

Citation: Swapna G, Dube N, Roth MJ, Montelione GT (2025) Memorization bias impacts modeling of alternative conformational states of solute carrier membrane proteins with methods from deep learning. PLoS Comput Biol 21(10): e1013590. https://doi.org/10.1371/journal.pcbi.1013590

Editor: Alex Peralvarez-Marin, Universitat Autònoma de Barcelona: Universitat Autonoma de Barcelona, SPAIN

Received: May 1, 2025; Accepted: October 6, 2025; Published: October 17, 2025

Copyright: © 2025 Swapna et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Data Availability: All scripts and key data generated in this study are available at https://doi.org/10.5281/zenodo.17386602

Funding: FINANCIAL DISCLOSURE This work was supported financially by National Institutes of Health NIGMS (https://www.nigms.nih.gov/) grants R35 GM141818 (to G.T.M.) and R35 GM122518 (to M.J.R.), and by the Rensselaer Polytechnic Institute (RPI) Bio-computing and Bio-informatics Constellation Chair Fund (to G.T.M). GTM also acknowledges access to the RPI Center for Computational Innovations (CCI) computing infrastructure. Research costs and partial salaries of G.V.T.S. were supported by NIH grants R35 GM141818 and R35 GM122518. Research costs and partial salaries of N.D. were supported by NIH grant R35 GM141818. Research costs and partial salaries of M.J.R. were support by NIH grant R35 GM122518. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Competing interests: I have read the journal’s policy and the authors of this manuscript have the following competing interests: GTM is a founder of Nexomics Biosciences, Inc.

Abbreviations: AF2, AlphaFold2 Multimer; AF3, AlphaFold3; EC, evolutionary covariance; ESM, Evolutionary-Scale Modeling; LDDT, local-distance difference test; MD, molecular dynamics; ML, machine learning; mmCIF, macromolecular Crystallographic Information File; MSA, multiple sequence alignment; PDB, Protein Data Bank; pLDDT, predicted Local-Distance Difference Test, a confidence score predicted from ML; TM, Template Modeling score to assess similarity between two protein structures

Introduction

Proteins adopt multiple conformational states which are essential to their functions. While AlphaFold2/3 (AF2/3) [1], Evolutionary Scale Modeling (ESM) [2], and related machine-learning methods [3,4] can provide accurate structural models of proteins, for systems that adopt multiple conformational states, conventional AF2/3 and ESM calculations often deliver only one of the multiple states observed experimentally [5–13]. Recent advances have been reported using modified AF2 protocols and "enhanced sampling" methods to model multiple conformational states of proteins, including integral membrane proteins [14]. Promising approaches use a conventional AF2 platform with curated input such as (i) state-annotated conformational templates [15,16], (ii) shallow multiple sequence alignments (MSAs) chosen either randomly (AlphaFold-alt) [6,17] or by clustering homologous protein sequences (AF-cluster) [8], (iii) very shallow MSAs and even single protein sequences [9,18] that allow knowledge inherent to the AI to dominate the modeling process, or (iv) using MSAs masked at multiple positions, as implemented in both (SPEACH-AF) [19] and AF-sample2 [12], to bias the prediction toward alternative conformational states. AF2 calculations using network dropouts (AF-sample) can also generate conformational diversity [20–24]. Despite these advances, challenges remain in reliably modeling alternative conformational states that are observed experimentally. In particular, assessments report various enhanced sampling methods to be successful in modeling multiple conformational states for 50% (or less) of experimentally-available alternative conformer pairs [9,11,13]. This observation suggests that at least some cases of successful modeling result from some kind of memorization by the AI, rather than its inherent "learning" of protein structure principles [9,13]. Such memorization can bias the AI-based modeling towards conformational state(s) used in the training process and prevent accurate modeling of alternative conformational states. To the degree that memorization biases the successful prediction of alternative conformational states, more robust methods leveraging the tools of AI-based modeling are required.

The Solute Carrier (SLC) superfamily of integral membrane proteins function to transport a wide array of solutes across the plasma and organelle membranes. The superfamily includes more than 66 SLC protein families (https://www.bioparadigms.org/slc/intro.htm), each including many individual proteins. SLC proteins transport a wide array of molecules, including sugars, amino acids, vitamins, nucleotides, metals, inorganic ions, organic anions, oligopeptides, and drugs [25–28]. Some are orphan transporters with no known substrate. SLC proteins can also function as receptors for viral entry into the cell [29]. They constitute a major portion of all human transporter-related proteins and play key roles in human health and disease [27,28,30].

Despite being classified as a single superfamily, the various SLC fold families do not share a single common fold classification and are not all phylogenetically related. For example, the two most common SLC fold families, the major facilitator superfamily (MFS) fold, which constitute the largest class of SLC proteins, and the LeuT fold, another important class of SLCs, are topologically and structurally distinct [27]. However, despite these differences, many SLC transporters have a characteristic structural architecture with pseudo two-fold symmetry, where the two halves of the protein structure are related by a two-fold symmetry axis in the plane of the membrane bilayer [27,31]. These halves have a similar fold but non-identical conformations, enabling the protein to adopt multiple conformational states essential for its function. MFS-fold SLC proteins have a "6 + 6" topology comprised of two "inverted pseudo-repeat" 6-helical bundles with antiparallel orientations related by a pseudosymmetry axis, while the strikingly similar but topologically distinct LeuT-fold membrane proteins feature two 5-helical bundles with "inverted pseudo-repeat" sequences that form structures related to one another by a pseudosymmetry axis [27]. Some (but not all) other SLC proteins also have folds with internal structural pseudosymmetry [27].

SLC proteins populate different conformational states during the transport process, including "outward-open", with a surface cavity directed one way, intermediate states (i.e., occluded, with no surface cavity), and "inward-open" with a surface cavity directed to the opposite side of the membrane [26,27]. These "inward-open" and "outward-open" conformational states are sometimes called "inward-facing" and "outward-facing" states in the literature. Crystal structures have been solved for inward-open, occluded, and outward-open states of several MFS and LeuT SLC proteins; for a few SLC proteins both inward and outward-open states have been determined by X-ray crystallography or cryoEM [32–36]. This conformational "flipping" confers an "airlock" or "revolving door" function, which underlies their mechanisms of symporter or antiporter solute transport [26,27,31]. The switch between outward- and inward-open states results from swapping of the conformations of the N-terminal and C-terminal symmetry-related sub-structures, in which the N-terminal helical bundle switches to adopt the conformation of the C-terminal helical bundle, while simultaneously the C-terminal helical bundle switches into the original conformation of the N-terminal helical bundle. These dynamic structural and biophysical properties confer to SLC proteins their functions as gates for symporter and antiporter transport of biochemically-important solutes and biomolecules [27,28].

Computational methods significantly impact our understanding of SLC protein structure-function relationships and can guide experimental design. However, as they are medium-sized integral membrane proteins, molecular dynamics simulations are quite challenging, requiring powerful computing resources, accurate potential energy functions, and appropriate simulation of membrane-mimicking environments. The evolving AI-based enhanced sampling methods outlined above can sometimes provide models of multiple conformational states of SLC proteins, but they are not always successful [6–12]. These observations suggest the need for more robust methods for modeling the multiple conformational states of this important class of membrane protein transporters.

Importantly, multiple conformational state modeling of proteins can be guided by evolutionary covariance (EC) analysis of functionally-preserved direct contacts, which can provide information about contacts present in the two (or more) states adopted by the protein structure [37–43]. Of special significance for SLC proteins is their unique pseudo-symmetrical transport mechanisms, which provides the basis for an elegant method of modeling the inward-open (or outward-open) conformations of some SLC proteins from knowledge of their outward (or inward) open conformations by swapping the pseudo-symmetric structures of the N- and C-terminal halves, and then using the resulting virtual structure as a template to model the alternative conformational state [31,44–50]. Although it is logical to combine the two concepts of validation with EC-based contact information and swapping of pseudo-symmetric structures, it has not yet been implemented as a general strategy for modeling SLC proteins.

Here we describe a simple and robust approach for modeling alternative conformational states of pseudo-symmetric SLC proteins using a combined ESM – template-based-modeling process inspired by the methods of Forrest and others [31,44–50]. In this approach, templates for alternative conformational states are generated from a reordered, or "flipped virtual sequence", using ESMFold [2], and template-based modeling is then performed using either AF2/3 [1,51] or, where training bias impacts the AF2 structure prediction, with the template-based modeling software MODELLER [52]. First, an ESM-AF approach was used to model the inward-/ outward-open forms of two SLC proteins, human ZnT8 (SLC30A8, a Zn transporter) and Escherichia coli D-galactonate:proton symporter (SLC17, a MFS superfamily transporter) for which experimental structures of both outward- and inward-open states are available, and the resulting models of alternative conformations were validated against EC-based contact maps and by comparison against atomic coordinates determined by cryoEM or X-ray crystallography. For two additional SLC proteins, Zea mays CMP-sialic acid transporter 1 (SLC35A1) and Saccharomyces cerevisiae GDP-mannose sugar transporter 1 (SLC35D subfamily), only the outward-open forms are available as experimental structures. In these cases, AF modeling was found to be biased towards these states and the alternative inward-open forms were modeled with an ESM-MODELLER process. Models were then validated by comparison against EC-based contact maps. For SLC35F2, although neither inward nor outward-open experimental structures are available, the outward-open state is strongly preferred when using conventional AF2. However, the inward-open conformational state could be modeled using either the ESM– AF2 or ESM – MODELLER processes. Both the inward- and outward-open structures were validated against EC-based contact maps. For other SLC proteins where experimental structures are available for only one conformational state, significant bias towards one state or the other was also observed using AF2 or AF3. In these cases, the ESM-MODELLER approach was successful in modeling both inward and outward-open states, which were validated by comparisons against EC-based contact maps.

Methods

Results

The challenge we encountered arises from the fact that conventional AF modeling protocols generally provided only one of the multiple conformations of SLC proteins, particularly when only one of these states was available as an experimental structure at the time of training. Even enhanced sampling methods successfully generate alternative conformational states for only some multistate proteins [6,8–13]. These observations motivate the need for robust and consistent methods for modeling alternative conformational states (outward-open vs inward-open) of SLC proteins, at the very least for use as reference states for assessing the evolving deep learning methods for generating alternative conformational states of proteins.

Discussion

We were very surprised to observe significant weaknesses of various published protocols using AF2 or AF3 for modeling alternative conformations of pseudo-symmetric SLC transporters. However, where conventional AF2/3 modeling (or even AF2 modeling with enhanced sampling) provides only one (either inward- or outward-open) conformational state; the alternative state can be modeled by the template-based ESM-AF (or ESM-MODELLER) protocol. The ESM-AF protocol is inspired by a more traditional approach using comparative modeling of the pseudo-symmetric halves of SLC transporters [31,44–50]. This traditional approach requires an accurate sequence alignment between the two symmetric halves of SLC protein to generate a structural template for the alternative state, which can be quite difficult to generate. In the ESM-AF (or ESM-MODELLER) approach, we use ESMfold to generate from a virtual flipped sequence a virtual protein structure, which is then used as a structure modeling template. Memorization bias does not significantly impact this process. This allowed us to reliably model alternative conformational states of several SLC transporters that were difficult to model using the traditional approach. Importantly, the resulting multi-state models are validated by comparison with sequence-based evolutionary co-variance data (ECs) that encode information about contacts present in the various conformational states adopted by the protein.

The ESM-AF2 approach is simple to implement and runs fast using publicly-available servers. Currently, the DeepMind AF3 server does not support template-based modeling, but ESM-AF3 can be run using locally-installed instances of AF3. However, despite the successful examples demonstrated in this study, the ESM-AF protocol for modeling alternative conformational states of pseudo-symmetric SLC proteins has some limitations. In particular, where structures of only one of the alternative states was available in the PDB at the time of training, a significant bias towards this state was observed when AF2/3 were used either directly or as part of the ESM-AF modeling process. Although this bias is overcome using the ESM-MODELLER protocol, it is somewhat disappointing to have to sometimes resort to older template-based modeling methods in place of AI-based methods like AF2/3. Another shortcoming is that neither protocol can be applied directly to homodimeric pseudo-symmetric SLC proteins, such as YiiP or EmrE [27,63]. Coordinates of SLC proteins with large loops and other structural decorations require manual editing to eliminate these loops/ decorations prior to applying the protocol. In addition, the validation of alternative state conformations by contact predictions relies on the quality of these contact predictions, and may not work well for SLC sequence families for which only shallow MSAs are available.

While we have focused our analysis on the outward and inward conformational states of SLC transporters, intermediate "occluded" states have also been captured in X-ray crystal and cryoEM structures. Although the ESM-AF2/MODELLER protocols sometimes also generate such occluded states, these states were not explored in this study. Ultimately, it would be desirable to develop methods which can generate complete conformational landscapes beyond the three major "inward-open", "occluded", "outward-open" states [12,64].

Symmetry in some integral membrane proteins such as SLC35F2 is easy to identify. Protein secondary structure and AF2 predictions indicate 10 helices connected by short loops. Chopping the sequence at the exact center of the loop between symmetric halves and swapping the coordinates of the two halves orients the helices with inverted conformation that overlays with the EC contact maps. The flipped sequence when used as input into ESMfold provides a flipped conformer which can be used as a template for further predictions as described in the Methods section. For SLC proteins that have a long loop between their symmetric halves, chopping the sequence in the exact center fails to provide a flipped sequence that can be used to successfully generate a proper flipped conformer. In these cases, the long loop was replaced by an 8 to 12 residue polyglycine linker, and the split was made at the center of this linker. The resulting flipped sequence was sufficient for ESMfold to predict the flipped conformer. The contact maps generated for the flipped conformers are always compared with the EC-contact map. In cases where the match is not reflecting the contacts of the flipped state accurately, a few trials were made in the elimination of residues of the loop regions. It may also be possible to identify correct symmetry using repeat definitions identified by symmetry analyses available in the Encompass database [65].

In this study, alternative conformational states of SLC proteins were validated against contact predictions based on evolutionary co-variance (ECs). ECs are an interpretation of experimental protein sequence data, and hence this validation is effectively against experimental data. However, this validation is not as robust as validation against protein-specific experimental data such as X-ray crystallography, NMR, or cryoEM data.

The ability of AF2 to model protein structures not included in its training has been demonstrated in various CASP blind assessments [66,67]. Conventional AF2 was also reported to be successful in accurate modeling of protein structures determined by NMR methods which were not included in its training data, and for which no structures of homologous proteins were available at the time of training [68]. However, for proteins adopting multiple conformational states, AI training carried out with data that includes only one state can bias the inference and limit its ability to model the alternative state. Memorization can also result from homologous protein structures connected with the target protein through the MSA [9].

Recently Porter and co-workers have demonstrated that, at least for fold-flipping proteins which have significant structural differences between conformational states, AF2 modeling with enhanced sampling is often biased toward the conformational state reported in the PDB and potentially used in the AF2 training, and often is not able to predict conformational states not represented in the AF2 training data. Combining >280,000 models from several implementations of AF2 and AF3, only a 35% success rate was achieved in modeling alternative states of fold switchers for which one state was available for AF training [9,69]. In a related study of cryptic sites in proteins, Lazou et al. were able to use AF2 to generate both open and closed conformations for only 6 of 16 proteins studied [13], attributing this low success rate to bias due to training memorization. Bryant and Noé also have explored this question by training a structure prediction network, Cfold, on a conformational split of the PDB that excludes alternative conformations for protein structure pairs solved in two conformational states. While > 50% of experimentally-known nonredundant alternative protein conformations evaluated were predicted with high accuracy (TM-score > 0.8), for the remaining pairs Cfold failed to correctly model the alternative conformational state that was not included in the training data [11] and was biased toward the conformational state used in training. These results indicate that while in some cases, the network has learned enough to model alternative conformational states not included in the training data [70], in other cases success may in fact rely on some kind of memorization; i.e., both factors can be at play. ESMfold is generally less sensitive to this memorization bias [10]. Consistent with these observations, we also observed a bias toward previously reported conformational states when modeling with either AF2/3 or with the ESM-AF protocol outlined here. This bias was not suppressed by using single-sequences or very shallow MSAs (8–16 sequences) in the AF2/3 modeling. Nor was it overcome in the cases tested using enhanced sampling with AFSample [21] or AFSample2 [12]. For these SLC proteins, this bias is overcome using the ESM-MODELLER protocol. However, where no memorization bias is involved, the ESM-AF protocol is preferable as template-guided AF2 has more accurate properties than conventional template-based modeling methods.

While previous studies have demonstrated that training memorization bias impacts AF2 modeling of alternative states of "fold flip" proteins that have significant structural differences between the states [9], the Cfold study cited above, using a structure prediction network trained on a split version of the PDB excluding alternative conformational states of multistate proteins [11] demonstrated less impact of memorization and high success rates in modeling distinct conformational states with smaller structural differences. The SLC proteins studied here have very similar overall structures and contact maps for the two states, yet the bias from conformational states available for the training process still strongly impacts the reliability of alternative conformational modeling by AF2/3. These observations suggest that it may be possible to use a retrained AF network that excludes homologous structures from training data to suppress memorization bias and improve inference for modeling alternative conformational states of proteins.

Conclusions

In this work we document bias in modeling multiple conformational states of SLC proteins that challenges the view that modeling of the multiple conformational states of this important class of integral membrane proteins is a largely solved problem. We describe, validate, and compare hybrid ESM-AF2, ESM-AF3, and ESM-MODELLER protocols for modeling alternative conformational states of pseudo-symmetric SLC proteins. This approach overcomes one shortcoming of conventional AF2/3 structure calculations which generally provide only one of the multiple conformational states observed experimentally. We observed that while AF2/3 generally does an excellent job of modeling one of the conformational states, there is a significant bias of AF towards conformational states available in the PDB at the time of its training. This bias can be overcome using the ESM-AF or ESM-MODELLER protocols. In this approach, the resulting multi-state models are validated by comparison with sequence-based EC data that encode information about contacts present in the various conformational states adopted by the protein. The method is simple to use, rapid to run, and can be implemented using public domain servers. Overall, the current study validates the ESM-AF/MODELLER protocol for modeling conformational heterogeneity of pseudo-symmetric SLC transporters, one of the most extensive class of transporters in the human proteome.

Supporting information

Acknowledgments

We thank Dr. Alberto Perez and Jokent Gaza for running inference using several structural templates with their locally-installed instance of AlphaFold3, and Dr. Davide Sala for providing scripts for running AF-alt. We also thank T.B. Acton, T. Benavides, A. De Falco, A. Gaur, R. Greene-Cramer, Y.J. Huang, T.A. Ramelot, B. Shurina, L. Spaman, and R. Tejero for helpful discussions and comments on the manuscript, and S. Collen for computer system administration support.

References

1. 1. Jumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596(7873):583–9. pmid:34265844
   • View Article
   • PubMed/NCBI
   • Google Scholar
2. 2. Lin Z, Akin H, Rao R, Hie B, Zhu Z, Lu W, et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. 2023;379(6637):1123–30. pmid:36927031
   • View Article
   • PubMed/NCBI
   • Google Scholar
3. 3. Baek M, DiMaio F, Anishchenko I, Dauparas J, Ovchinnikov S, Lee GR, et al. Accurate prediction of protein structures and interactions using a three-track neural network. Science. 2021;373(6557):871–6. pmid:34282049
   • View Article
   • PubMed/NCBI
   • Google Scholar
4. 4. Ahdritz G, Bouatta N, Floristean C, Kadyan S, Xia Q, Gerecke W, et al. OpenFold: retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. Nat Methods. 2024;21(8):1514–24. pmid:38744917
   • View Article
   • PubMed/NCBI
   • Google Scholar
5. 5. Huang YJ, Zhang N, Bersch B, Fidelis K, Inouye M, Ishida Y, et al. Assessment of prediction methods for protein structures determined by NMR in CASP14: Impact of AlphaFold2. Proteins. 2021;89(12):1959–76. pmid:34559429
   • View Article
   • PubMed/NCBI
   • Google Scholar
6. 6. Del Alamo D, Sala D, Mchaourab HS, Meiler J. Sampling alternative conformational states of transporters and receptors with AlphaFold2. Elife. 2022;11:e75751. pmid:35238773
   • View Article
   • PubMed/NCBI
   • Google Scholar
7. 7. Saldaño T, Escobedo N, Marchetti J, Zea DJ, Mac Donagh J, Velez Rueda AJ, et al. Impact of protein conformational diversity on AlphaFold predictions. Bioinformatics. 2022;38(10):2742–8. pmid:35561203
   • View Article
   • PubMed/NCBI
   • Google Scholar
8. 8. Wayment-Steele HK, Ojoawo A, Otten R, Apitz JM, Pitsawong W, Hömberger M, et al. Predicting multiple conformations via sequence clustering and AlphaFold2. Nature. 2024;625(7996):832–9. pmid:37956700
   • View Article
   • PubMed/NCBI
   • Google Scholar
9. 9. Chakravarty D, Schafer JW, Chen EA, Thole JF, Ronish LA, Lee M, et al. AlphaFold predictions of fold-switched conformations are driven by structure memorization. Nat Commun. 2024;15(1):7296. pmid:39181864
   • View Article
   • PubMed/NCBI
   • Google Scholar
10. 10. Xie T, Huang J. Can protein structure prediction methods capture alternative conformations of membrane transporters? J Chem Inf Model. 2024;64(8):3524–36. pmid:38564295
    • View Article
    • PubMed/NCBI
    • Google Scholar
11. 11. Bryant P, Noé F. Structure prediction of alternative protein conformations. Nat Commun. 2024;15(1):7328. pmid:39187507
    • View Article
    • PubMed/NCBI
    • Google Scholar
12. 12. Kalakoti Y, Wallner B. AFsample2: predicting multiple conformations and ensembles with AlphaFold2. bioRxiv. 2024.
    • View Article
    • Google Scholar
13. 13. Lazou M, Khan O, Nguyen T, Padhorny D, Kozakov D, Joseph-McCarthy D, et al. Predicting multiple conformations of ligand binding sites in proteins suggests that AlphaFold2 may remember too much. Proc Natl Acad Sci U S A. 2024;121(48):e2412719121. pmid:39565312
    • View Article
    • PubMed/NCBI
    • Google Scholar
14. 14. Sala D, Engelberger F, Mchaourab HS, Meiler J. Modeling conformational states of proteins with AlphaFold. Curr Opin Struct Biol. 2023;81:102645. pmid:37392556
    • View Article
    • PubMed/NCBI
    • Google Scholar
15. 15. Heo L, Feig M. Multi-state modeling of G-protein coupled receptors at experimental accuracy. Proteins. 2022;90(11):1873–85. pmid:35510704
    • View Article
    • PubMed/NCBI
    • Google Scholar
16. 16. Faezov B, Dunbrack RL Jr. AlphaFold2 models of the active form of all 437 catalytically competent human protein kinase domains. bioRxiv. 2023. pmid:37547017
    • View Article
    • PubMed/NCBI
    • Google Scholar
17. 17. Sala D, Hildebrand PW, Meiler J. Biasing AlphaFold2 to predict GPCRs and kinases with user-defined functional or structural properties. Front Mol Biosci. 2023;10:1121962. pmid:36876042
    • View Article
    • PubMed/NCBI
    • Google Scholar
18. 18. Porter LL, Chakravarty D, Schafer JW, Chen EA. ColabFold predicts alternative protein structures from single sequences, coevolution unnecessary for AF-cluster. bioRxiv. 2023. pmid:38076792
    • View Article
    • PubMed/NCBI
    • Google Scholar
19. 19. Stein RA, Mchaourab HS. SPEACH_AF: Sampling protein ensembles and conformational heterogeneity with Alphafold2. PLoS Comput Biol. 2022;18(8):e1010483. pmid:35994486
    • View Article
    • PubMed/NCBI
    • Google Scholar
20. 20. Johansson-Åkhe I, Wallner B. Improving peptide-protein docking with AlphaFold-Multimer using forced sampling. Front Bioinform. 2022;2:959160. pmid:36304330
    • View Article
    • PubMed/NCBI
    • Google Scholar
21. 21. Wallner B. AFsample: improving multimer prediction with AlphaFold using massive sampling. Bioinformatics. 2023;39(9):btad573. pmid:37713472
    • View Article
    • PubMed/NCBI
    • Google Scholar
22. 22. Wallner B. Improved multimer prediction using massive sampling with AlphaFold in CASP15. Proteins. 2023;91(12):1734–46. pmid:37548092
    • View Article
    • PubMed/NCBI
    • Google Scholar
23. 23. Huang YJ, Ramelot TA, Spaman LE, Kobayashi N, Montelione GT. Hidden structural states of proteins revealed by conformer selection with AlphaFold-NMR. bioRxiv. 2025. pmid:38979209
    • View Article
    • PubMed/NCBI
    • Google Scholar
24. 24. Benavides TL, Montelione GT. Integrative modeling of protein-polypeptide complexes by Bayesian model selection using AlphaFold and NMR Chemical Shift Perturbation Data. bioRxiv. 2024. pmid:39345459
    • View Article
    • PubMed/NCBI
    • Google Scholar
25. 25. Hediger MA, Clémençon B, Burrier RE, Bruford EA. The ABCs of membrane transporters in health and disease (SLC series): introduction. Mol Aspects Med. 2013;34(2–3):95–107. pmid:23506860
    • View Article
    • PubMed/NCBI
    • Google Scholar
26. 26. Colas C, Ung PM-U, Schlessinger A. SLC transporters: structure, function, and drug discovery. Medchemcomm. 2016;7(6):1069–81. pmid:27672436
    • View Article
    • PubMed/NCBI
    • Google Scholar
27. 27. Bai X, Moraes TF, Reithmeier RAF. Structural biology of solute carrier (SLC) membrane transport proteins. Mol Membr Biol. 2017;34(1–2):1–32. pmid:29651895
    • View Article
    • PubMed/NCBI
    • Google Scholar
28. 28. Pizzagalli MD, Bensimon A, Superti-Furga G. A guide to plasma membrane solute carrier proteins. FEBS J. 2021;288(9):2784–835. pmid:32810346
    • View Article
    • PubMed/NCBI
    • Google Scholar
29. 29. Sarangi A, Bupp K, Roth MJ. Identification of a retroviral receptor used by an envelope protein derived by peptide library screening. Proc Natl Acad Sci U S A. 2007;104(26):11032–7. pmid:17581869
    • View Article
    • PubMed/NCBI
    • Google Scholar
30. 30. Fredriksson R, Nordström KJV, Stephansson O, Hägglund MGA, Schiöth HB. The solute carrier (SLC) complement of the human genome: phylogenetic classification reveals four major families. FEBS Lett. 2008;582(27):3811–6. pmid:18948099
    • View Article
    • PubMed/NCBI
    • Google Scholar
31. 31. Forrest LR. Structural biology. (Pseudo-)symmetrical transport. Science. 2013;339(6118):399–401. pmid:23349276
    • View Article
    • PubMed/NCBI
    • Google Scholar
32. 32. Leano JB, Batarni S, Eriksen J, Juge N, Pak JE, Kimura-Someya T, et al. Structures suggest a mechanism for energy coupling by a family of organic anion transporters. PLoS Biol. 2019;17(5):e3000260. pmid:31083648
    • View Article
    • PubMed/NCBI
    • Google Scholar
33. 33. Xue J, Xie T, Zeng W, Jiang Y, Bai X-C. Cryo-EM structures of human ZnT8 in both outward- and inward-facing conformations. Elife. 2020;9:e58823. pmid:32723473
    • View Article
    • PubMed/NCBI
    • Google Scholar
34. 34. Wang N, Jiang X, Zhang S, Zhu A, Yuan Y, Xu H, et al. Structural basis of human monocarboxylate transporter 1 inhibition by anti-cancer drug candidates. Cell. 2021;184(2):370–383.e13. pmid:33333023
    • View Article
    • PubMed/NCBI
    • Google Scholar
35. 35. Killer M, Wald J, Pieprzyk J, Marlovits TC, Löw C. Structural snapshots of human PepT1 and PepT2 reveal mechanistic insights into substrate and drug transport across epithelial membranes. Sci Adv. 2021;7(45):eabk3259. pmid:34730990
    • View Article
    • PubMed/NCBI
    • Google Scholar
36. 36. Lu Y, Zuo P, Chen H, Shan H, Wang W, Dai Z, et al. Structural insights into the conformational changes of BTR1/SLC4A11 in complex with PIP2. Nat Commun. 2023;14(1):6157. pmid:37788993
    • View Article
    • PubMed/NCBI
    • Google Scholar
37. 37. Hopf TA, Colwell LJ, Sheridan R, Rost B, Sander C, Marks DS. Three-dimensional structures of membrane proteins from genomic sequencing. Cell. 2012;149(7):1607–21. pmid:22579045
    • View Article
    • PubMed/NCBI
    • Google Scholar
38. 38. Morcos F, Jana B, Hwa T, Onuchic JN. Coevolutionary signals across protein lineages help capture multiple protein conformations. Proc Natl Acad Sci U S A. 2013;110(51):20533–8. pmid:24297889
    • View Article
    • PubMed/NCBI
    • Google Scholar
39. 39. Sutto L, Marsili S, Valencia A, Gervasio FL. From residue coevolution to protein conformational ensembles and functional dynamics. Proc Natl Acad Sci U S A. 2015;112(44):13567–72. pmid:26487681
    • View Article
    • PubMed/NCBI
    • Google Scholar
40. 40. Toth-Petroczy A, Palmedo P, Ingraham J, Hopf TA, Berger B, Sander C, et al. Structured states of disordered proteins from genomic sequences. Cell. 2016;167(1):158–170.e12. pmid:27662088
    • View Article
    • PubMed/NCBI
    • Google Scholar
41. 41. Zheng S, Sham L-T, Rubino FA, Brock KP, Robins WP, Mekalanos JJ, et al. Structure and mutagenic analysis of the lipid II flippase MurJ from Escherichia coli. Proc Natl Acad Sci U S A. 2018;115(26):6709–14. pmid:29891673
    • View Article
    • PubMed/NCBI
    • Google Scholar
42. 42. Huang YJ, Brock KP, Ishida Y, Swapna GVT, Inouye M, Marks DS, et al. Combining evolutionary covariance and NMR data for protein structure determination. Methods Enzymol. 2019;614:363–92. pmid:30611430
    • View Article
    • PubMed/NCBI
    • Google Scholar
43. 43. Schafer JW, Porter LL. Evolutionary selection of proteins with two folds. Nat Commun. 2023;14(1):5478. pmid:37673981
    • View Article
    • PubMed/NCBI
    • Google Scholar
44. 44. Crisman TJ, Qu S, Kanner BI, Forrest LR. Inward-facing conformation of glutamate transporters as revealed by their inverted-topology structural repeats. Proc Natl Acad Sci U S A. 2009;106(49):20752–7. pmid:19926849
    • View Article
    • PubMed/NCBI
    • Google Scholar
45. 45. Radestock S, Forrest LR. The alternating-access mechanism of MFS transporters arises from inverted-topology repeats. J Mol Biol. 2011;407(5):698–715. pmid:21315728
    • View Article
    • PubMed/NCBI
    • Google Scholar
46. 46. Schushan M, Rimon A, Haliloglu T, Forrest LR, Padan E, Ben-Tal N. A model-structure of a periplasm-facing state of the NhaA antiporter suggests the molecular underpinnings of pH-induced conformational changes. J Biol Chem. 2012;287(22):18249–61. pmid:22431724
    • View Article
    • PubMed/NCBI
    • Google Scholar
47. 47. Liao J, Li H, Zeng W, Sauer DB, Belmares R, Jiang Y. Structural insight into the ion-exchange mechanism of the sodium/calcium exchanger. Science. 2012;335(6069):686–90. pmid:22323814
    • View Article
    • PubMed/NCBI
    • Google Scholar
48. 48. Kowalczyk L, Ratera M, Paladino A, Bartoccioni P, Errasti-Murugarren E, Valencia E, et al. Molecular basis of substrate-induced permeation by an amino acid antiporter. Proc Natl Acad Sci U S A. 2011;108(10):3935–40. pmid:21368142
    • View Article
    • PubMed/NCBI
    • Google Scholar
49. 49. Mancusso R, Gregorio GG, Liu Q, Wang D-N. Structure and mechanism of a bacterial sodium-dependent dicarboxylate transporter. Nature. 2012;491(7425):622–6. pmid:23086149
    • View Article
    • PubMed/NCBI
    • Google Scholar
50. 50. Kim J, Tan YZ, Wicht KJ, Erramilli SK, Dhingra SK, Okombo J, et al. Structure and drug resistance of the Plasmodium falciparum transporter PfCRT. Nature. 2019;576(7786):315–20. pmid:31776516
    • View Article
    • PubMed/NCBI
    • Google Scholar
51. 51. Abramson J, Adler J, Dunger J, Evans R, Green T, Pritzel A, et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature. 2024;630(8016):493–500. pmid:38718835
    • View Article
    • PubMed/NCBI
    • Google Scholar
52. 52. Webb B, Sali A. Comparative Protein Structure Modeling Using MODELLER. Curr Protoc Bioinformatics. 2016;54:5.6.1–5.6.37. pmid:27322406
    • View Article
    • PubMed/NCBI
    • Google Scholar
53. 53. He B, Mortuza SM, Wang Y, Shen H-B, Zhang Y. NeBcon: protein contact map prediction using neural network training coupled with naïve Bayes classifiers. Bioinformatics. 2017;33(15):2296–306. pmid:28369334
    • View Article
    • PubMed/NCBI
    • Google Scholar
54. 54. Vehlow C, Stehr H, Winkelmann M, Duarte JM, Petzold L, Dinse J, et al. CMView: interactive contact map visualization and analysis. Bioinformatics. 2011;27(11):1573–4. pmid:21471016
    • View Article
    • PubMed/NCBI
    • Google Scholar
55. 55. Mirdita M, Schütze K, Moriwaki Y, Heo L, Ovchinnikov S, Steinegger M. ColabFold: making protein folding accessible to all. Nat Methods. 2022;19(6):679–82. pmid:35637307
    • View Article
    • PubMed/NCBI
    • Google Scholar
56. 56. Sali A, Blundell TL. Comparative protein modelling by satisfaction of spatial restraints. J Mol Biol. 1993;234(3):779–815. pmid:8254673
    • View Article
    • PubMed/NCBI
    • Google Scholar
57. 57. Zemla A, Zhou CE, Slezak T, Kuczmarski T, Rama D, Torres C, et al. AS2TS system for protein structure modeling and analysis. Nucleic Acids Res. 2005;33:W111–5. pmid:15980437
    • View Article
    • PubMed/NCBI
    • Google Scholar
58. 58. Nji E, Gulati A, Qureshi AA, Coincon M, Drew D. Structural basis for the delivery of activated sialic acid into Golgi for sialyation. Nat Struct Mol Biol. 2019;26(6):415–23. pmid:31133698
    • View Article
    • PubMed/NCBI
    • Google Scholar
59. 59. Parker JL, Newstead S. Structural basis of nucleotide sugar transport across the Golgi membrane. Nature. 2017;551(7681):521–4. pmid:29143814
    • View Article
    • PubMed/NCBI
    • Google Scholar
60. 60. Waterhouse A, Bertoni M, Bienert S, Studer G, Tauriello G, Gumienny R, et al. SWISS-MODEL: homology modelling of protein structures and complexes. Nucleic Acids Res. 2018;46(W1):W296–303. pmid:29788355
    • View Article
    • PubMed/NCBI
    • Google Scholar
61. 61. Johnson LS, Eddy SR, Portugaly E. Hidden Markov model speed heuristic and iterative HMM search procedure. BMC Bioinformatics. 2010;11:431. pmid:20718988
    • View Article
    • PubMed/NCBI
    • Google Scholar
62. 62. Hauser M, Steinegger M, Söding J. MMseqs software suite for fast and deep clustering and searching of large protein sequence sets. Bioinformatics. 2016;32(9):1323–30. pmid:26743509
    • View Article
    • PubMed/NCBI
    • Google Scholar
63. 63. Fleishman SJ, Harrington SE, Enosh A, Halperin D, Tate CG, Ben-Tal N. Quasi-symmetry in the cryo-EM structure of EmrE provides the key to modeling its transmembrane domain. J Mol Biol. 2006;364(1):54–67. pmid:17005200
    • View Article
    • PubMed/NCBI
    • Google Scholar
64. 64. Lewis S, Hempel T, Jiménez-Luna J, Gastegger M, Xie Y, Foong AYK, et al. Scalable emulation of protein equilibrium ensembles with generative deep learning. Science. 2025;389(6761):eadv9817. pmid:40638710
    • View Article
    • PubMed/NCBI
    • Google Scholar
65. 65. Aleksandrova AA, Sarti E, Forrest LR. EncoMPASS: An encyclopedia of membrane proteins analyzed by structure and symmetry. Structure. 2024;32(4):492–504.e4. pmid:38367624
    • View Article
    • PubMed/NCBI
    • Google Scholar
66. 66. Kryshtafovych A, Schwede T, Topf M, Fidelis K, Moult J. Critical assessment of methods of protein structure prediction (CASP)-Round XIV. Proteins. 2021;89(12):1607–17. pmid:34533838
    • View Article
    • PubMed/NCBI
    • Google Scholar
67. 67. Kryshtafovych A, Schwede T, Topf M, Fidelis K, Moult J. Critical assessment of methods of protein structure prediction (CASP)-Round XV. Proteins. 2023;91(12):1539–49. pmid:37920879
    • View Article
    • PubMed/NCBI
    • Google Scholar
68. 68. Li EH, Spaman LE, Tejero R, Janet Huang Y, Ramelot TA, Fraga KJ, et al. Blind assessment of monomeric AlphaFold2 protein structure models with experimental NMR data. J Magn Reson. 2023;352:107481. pmid:37257257
    • View Article
    • PubMed/NCBI
    • Google Scholar
69. 69. Chakravarty D, Lee M, Porter LL. Proteins with alternative folds reveal blind spots in AlphaFold-based protein structure prediction. Curr Opin Struct Biol. 2025;90:102973. pmid:39756261
    • View Article
    • PubMed/NCBI
    • Google Scholar
70. 70. Roney JP, Ovchinnikov S. State-of-the-art estimation of protein model accuracy using AlphaFold. Phys Rev Lett. 2022;129(23):238101. pmid:36563190
    • View Article
    • PubMed/NCBI
    • Google Scholar