The evolutionary history of plastid outer envelope proteins – a structure-sequence comparison

The evolutionary history of plastid outer envelope proteins – a structure-sequence comparison | bioRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-M677548'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search New Results The evolutionary history of plastid outer envelope proteins – a structure-sequence comparison View ORCID Profile Deren Büyüktaş , Jonas A. Mehl , View ORCID Profile Timo Engelsdorf , View ORCID Profile Lars M. Voll , View ORCID Profile Hans-Henning Kunz , View ORCID Profile Serena Schwenkert , View ORCID Profile Sophie de Vries doi: https://doi.org/10.1101/2025.06.18.660430 Deren Büyüktaş 1 Department of Applied Bioinformatics, Institute of Microbiology and Genetics, University of Goettingen , Goldschmidtstraße 1, 37077 Goettingen, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Deren Büyüktaş Jonas A. Mehl 1 Department of Applied Bioinformatics, Institute of Microbiology and Genetics, University of Goettingen , Goldschmidtstraße 1, 37077 Goettingen, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site Timo Engelsdorf 2 Philipps-Universität Marburg, Department Biology, Molecular Plant Physiology , Karl-von-Frisch-Strasse 8, D-35043 Marburg, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Timo Engelsdorf Lars M. Voll 2 Philipps-Universität Marburg, Department Biology, Molecular Plant Physiology , Karl-von-Frisch-Strasse 8, D-35043 Marburg, Germany 3 Center for Synthetic Microbiology (SYNMIKRO), Philipps-Universität Marburg , Karl-von-Frisch-Strasse 14, D-35043 Marburg, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Lars M. Voll Hans-Henning Kunz 4 Plant Biochemistry, Biology, LMU Munich , Großhadernerstr. 2-4, 82152 Planegg- Martinsried, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Hans-Henning Kunz For correspondence: sophie.devries{at}uni-goettingen.de serena.schwenkert{at}lmu.de kunz{at}lmu.de Serena Schwenkert 5 Plant Molecular Biology, LMU Munich , Großhaderner Str. 2-4, 82152 Planegg-Martinsried, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Serena Schwenkert For correspondence: sophie.devries{at}uni-goettingen.de serena.schwenkert{at}lmu.de kunz{at}lmu.de Sophie de Vries 1 Department of Applied Bioinformatics, Institute of Microbiology and Genetics, University of Goettingen , Goldschmidtstraße 1, 37077 Goettingen, Germany Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Sophie de Vries For correspondence: sophie.devries{at}uni-goettingen.de serena.schwenkert{at}lmu.de kunz{at}lmu.de Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract Plant metabolism heavily relies on chloroplasts, derived from once free-living organisms. However, how two distinct organisms merged into one remains currently only partially understood. Protein-mediated metabolite exchange across the double-membrane chloroplast envelope is essential for plant cell function. Here, we investigate the evolutionary origins of outer envelope proteins (OEPs) involved in these transport processes. The mosaic nature of the nuclear genome and the deep evolutionary distance since plastid acquisition are major challenges. To address them, we combine sequence-based analyses with emerging structure-based tools, which together enable more sensitive evolutionary comparisons than traditional methods alone. To uncover distinct evolutionary trajectories, we focused on five OEP families: four β-barrel proteins involved in metabolite transport and JASSY, the first published OPDA transporter. We found that the β-barrel proteins were recruited in a stepwise manner and structural homologs of some OEPs point to early recruitment via endosymbiotic gene transfer (EGT). Notably, OEP40 shows a recent structural rearrangement, lacking clear structural homologs in plants other than Arabidopsis, yet retaining sequence conservation across all major land-plant lineages. The JASSY-like family is found across plastid-bearing species, while true JASSY orthologs emerged in embryophytes likely via a stable recruitment of the characteristic lipid-binding domain. Overall, our findings highlight the dynamic nature of the chloroplast outer envelope and show how new functions evolved through structural reshaping and novel domain recruitment. Structure-based approaches thus powerfully complement sequence data, offering more in-depth insight into the evolution of plastid transport systems. Introduction Chloroplasts are vital for plant cells. They produce the carbon building blocks for almost all aspects of plant physiology. All plastids can be traced to a single endosymbiotic event between a heterotrophic, eukaryotic host and a photoautotrophic cyanobacterium. Successful establishment of this relationship was accompanied by massive EGT from the cyanobacterial genome to the nucleus (Timmis et al., 2004). In addition, horizontal gene transfer (HGT) from other prokaryotic sources into the endosymbiont genome and from there to the host is observed (Dagan et al. 2013, Ku et al. 2015 , Ponce-Toledo et al. 2019 ). This complicates tracing the evolutionary origin of genes relevant for chloroplast function. The genetic exchange between the two partners resulted in a mosaic metabolism, which made the two organisms interdependent ( Fernie et al. 2024 ) e.g., chloroplast function relies on nutrients from the cytosol in turn plastids provide fixed carbon and special metabolites. To ensure flawless interaction, plastid outer and inner envelope (OE and IE) membranes harbor a variety of integral proteins assigned to metabolite, ion, and protein transport ( Kunz et al. 2024 , John et al. 2025 ) Weber et al. 2005 , Bölter 2018 ). The abundance of β-barrel proteins in the OE may be especially informative to understand how the cyanobacterial outer membrane was reorganized to allow permanent maintenance of the endosymbiont. In contrast to mitochondria, which mainly rely on the voltage-dependent anion channel (VDAC) as metabolite channel, OEPs appear to have diversified to a greater extent in the course of evolution ( Barth et al. 2022 , Schwenkert et al. 2023 ). Despite decades of research, a detailed understanding of the evolutionary recruitments of molecular mechanisms that allowed and shaped the emergence of the plastid remains scarce ( Barth et al. 2022 ). This information must be engraved in the sequence and structure of key proteins. However, strong evolutionary divergence since the emergence of plastids hampers the investigation of its evolutionary history based on sequence data alone. Homology searches using basic local alignment search tools (BLAST) poorly detect ancient relationships where AA sequence similarity has decayed below 30% ( Rost, 1999 ), often referred to as homologs from the “twilight zone”. Novel approaches capitalize on the fact that, constrained by their biological function, protein structures are ≤10-times more conserved than sequence (Illegård et al. 2009, Ruperti et al. 2023 ). The emerging abundance of predicted protein structures and the success of structure-based method in homology search and sequence alignment ( Chen et al. 2025 ) has renewed the interest of researchers in using the structural information of proteins to directly improve phylogenetic inference ( Moi et al. 2023 , Baltzis et al. 2025 , Bou Dagher et al. 2025 ). Yet, structural phylogenetics has not been applied towards understanding the evolution of plant cells. We reason that integration of structural and sequence analyses can overcome the low sequence conservation of OEPs and gain new insights into the evolution of the chloroplast OE as well as the origin and recruitment of key proteins necessary for the processes of organellar integration. Results and discussion The evolutionary history of OEP protein sequences To test our hypothesis and identify potential pitfalls in structure-based evolutionary analyses, we carried out a comparative proof-of-concept study employing traditional sequence-based phylogenetics and structural analysis in the phylogeny of the green lineage and cyanobacteria. As candidates we selected five OEP families (four β-barrel proteins and one with mixed structure) with specific functions in metabolite transport ( Figure 1a ): (i) OEP21, the structure of which was recently solved, is selective for triose phosphates and regulated by ATP, likely preventing the loss of metabolites during oxidative stress (Günsel et al. 2023), (ii) OEP24 and (iii) OEP37 exhibit broader substrate specificity, functioning as general solute channels that can partially substitute for VDAC in yeast systems ( Röhl et al. 1999 , Götze et al. 2006), (iv) OEP40, a candidate transporter for glucose and phosphorylated derivatives, which contributes to major carbohydrate metabolism and the regulation of flowering under cold stress (Harsmann et al. 2016) and (v) JASSY, which has a mixed alpha helical and β-sheets structure, and was recently characterized to shuttle 12-oxo phytodienoic acid (OPDA) ( Guan et al. 2019 , Schwenkert et al. 2023 ). Download figure Open in new tab Figure 1: Model of key outer envelope proteins. (a) Predicted structures of proteins whose evolutionary histories were traced in this study. (b) Using primary amino acid sequence information, homologs (blue dot) and orthologs (purple dot) of JASSY, OEP21, OEP24, OEPE37, and OEP40 were detected across major chloroplastidal lineages (cyanobacteria as outgroup) using phylogenetic analysis; a white dot means that no homolog was detected. Additionally, protein structural data were used to detect structural homologs/analogs considering only hits with some structural confidence (pLDDT≥70; with the exception for OEP40; here only 5 hits were recovered and all were considered, indicated by *); to distinguish true (likely homologous) and false (likely analogous) positive hits we applied an e-value cutoff of ≤10 (orange dot). If a plant lineage only had hits with e-values >10 we annotated this with yellow dots. Absence of a structural homolog/analog among proteins with structural confidence (pLDDT≥70) is indicated by a light yellow dot (for OEP40 all hits were considered, indicated by *); a white dot indicates that no hits could be determined (Nd) because no structural data were available for the respective clade. (c) Taxonomic distribution of structural hits with a pLDDT≥70 with archaea in green, bacteria in orange and eukaryotes in purple. To identify sequence homologs of five OE channels from Arabidopsis, we employed two approaches, BLASTp and Homology detection & structure prediction by HMM-HMM comparison (HHPred). While BLASTp uses sequence-based comparison, HHPred aims to identify homologs using sequence, domain, and in some cases structural comparison ( Söding et al. 2005 ). HHPred identified hits with probabilities ≥70% across diverse phyla for all OEPs investigated, yet e-values were mostly high (Figure S1, Supplementary Table S1a-i). At JASSY1/2 had several well-supported hits to bacteria or tracheophytes, however no hits to cyanobacteria were recorded. At OEP21A/B had one hit with an e-value ≤ 10 −7 to Pisum sativum OEP21. All other candidates retrieved only hits with insufficient support (e-values > 0.09). To understand whether any of the OEPs can be traced to lineages other than land plants, we further conducted BLASTp searches against the entire non-redundant protein sequence (nr) database, which is more comprehensive compared to the one used in the HHPred approach. Here, we employed strategies to filter for (i) all sequences outside of Viridiplantae, (ii) rhodophytes, (iii) glaucophytes, (iv) cyanobacteria and (v) bacteria. Apart from OEP21A, which recovered possible distant homologs in the rhodophyte genus Galdieria (e-value ≥ 0.002 and identity <27%), none of the β-barrel proteins recovered hits in any of the categories (Supplementary Table S2a). In accordance with the HHPred approach, BLASTp also recovered one bacterial hit for JASSY, but all cyanobacterial hits had e-values ≥10 −5 and were only recovered when specifically querying cyanobacteria (Supplementary Table S2a). However, these potential cyanobacterial sequence hits all represent START (StAR-related lipid-transfer)/RHO_alpha_C/PITP/Bet_v1/CoxG/CalC (SRPBCC) family proteins. Indeed, all cyanobacterial hits only showed similarity to the SRPBCC region of JASSY1. This suggests that they (i) could be distant homologs to JASSY from the phylogenetic twilight zone and may be better recovered using a structural approach or (ii) may not be true homologs but rather share an ubiquitously present START domain. Apart from JASSY, which had few hits to rhodophytes and a bacterial hit, none of the other candidates seem to identify obvious sequence homologs outside of land plants. To scrutinize the appearance and sequence evolution of these OEPs, we next conducted phylogenetic analyses based on the results from BLASTp against our in-house Chloroplastida database ( Figure 1 , 2 , S2, S3, S4, S5, Supplementary Table S2b-f). This analysis indicates that At OEP21A/B do not have homologous sequences beyond chlorophyte algae. Moreover, homologs to At OEP24A/B, At OEP37 and At OEP40 appear limited to streptophytes ( Figure 1b ). Clear orthologs for At OEP21, At OEP37 and At OEP40 exist in all embryophytes, suggesting their existence since the last common ancestor (LCA) of land plants. In contrast, OEP24 only shows clear orthology in gymno- and angiosperms, suggesting an appearance in the LCA of seed plants ( Figure 1b ). Taken together, our data point to an origin of the gene families in the LCAs of Chloroplastida (homologs to OEP21) or Streptophyta (homologs to OEP24, 37 and 40) and the origin of the respective subfamilies in the LCAs of land plants (OEP21, 37 and 40) and seed plants (OEP24). Download figure Open in new tab Figure 2: Maximum likelihood phylogeny of JASSY homologs. The phylogeny was computed based on a global primary sequence alignment using a G-INS-I approach in MAFFT. The dot matrix on the right labels which domains are predicted to be present in the protein homologs. 100 non-parametric (Felsenstein) bootstrap pseudoreplicates were computed. Due to its unique structure and available knowledge on the evolution of jasmonate biosynthesis, we focused on JASSY1/2 in more detail ( Figure 1a , Figure 2 ). Using BLASTp, we obtained one bacterial hit for JASSY that met our e-value threshold of <10 −7 (Supplementary Table S2a). This hit clustered within the JASSY-like clade (bootstrap support 100) but has none of the domains recovered for JASSY-like proteins ( Figure 2 ). This suggests that it (i) may have a different function or (ii) is a sequencing artefact. Independent of this, our phylogenetic inference points to the LCA of angiosperms having possessed a single JASSY gene, while the gene family expanded significantly in the LCA of Brassicaceae with 12 members. This is consistent with the observation that At jassy1 loss-of-function mutants are neither completely JA deficient nor male sterile ( Guan et al. 2019 ). Moreover, we observe lineage-specific expansion of the JASSY family in diverse branches of the green lineage ( Figure 2 ). The At JASSY1 domain composition of a STAR, DUF220, Polyketide cyclases and PaST domain is only observed for homologs from land plants ( Figure 2 ). Brassicaceae JASSY paralogs contain only the DUF220 domain, lacking evidence of the other domains. In contrast, JASSY homologs in streptophyte algae rarely possess the DUF220, but retain representative sequences for the other three domains. No streptophyte algal homolog contains a set of all four domains. This suggests stepwise domain recruitment in the JASSY family and concomitant domain loss after duplication. Stepwise domain recruitment has been previously observed in a large-scale domain acquisition analyses across Chloroplastida and was suggested to be a mechanism to contribute to functional novelty in streptophyte stress response ( Dhabalia Ashok et al. 2024 ). How this relates to JASSY function is so far unclear, but we note that K. nitens , for which the presence of OPDA was reported ( Chini et al. 2023 , Schmidt et al. 2024 ) possess distantly homologous sequences that encode DUF220 or STAR domains ( Figure 2 ). Overall, these sequence-based phylogenetic data point to a complex evolutionary history behind the origin of the chloroplast OE channels of land plants with a stepwise appearance of OEPs. Whether structurally similar cyanobacterial proteins were lost and replaced by newly appearing ones or whether sequences degraded so much that we simply cannot trace their origin back to cyanobacteria, remains unclear. Implementation of structural data suggest distinct evolutionary trajectories of β-barrel OEPs after stepwise recruitment To gain a deeper understanding of the evolutionary trajectory of the OE, we employed structure similarity searches using the AFDB50 database with AlphaFold2 predictions on the selected OEPs. While β-barrel structures can be hard to predict, these challenges appear to have been overcome since AlphaFold2 ( Topitsch et al. 2024 ). Overall, our analysis revealed that most β-barrel OEPs display a broad phylogenetic distribution based on their structure, using a predicted local distance difference test (pLDDT) cutoff ≥70 to only retain structures with confidence in their prediction ( Figure 1c , Supplementary Table S3c-h). Consistent with the tree-of-life wide distribution of β-barrel structures, we found conservation across diverse bacterial, archaeal and eukaryotic sequences outside the green lineage ( Figure 1c ). Noteworthy, the four β-barrel OEP families did not retrieve the same taxonomic coverage or the same hits (supplementary table S3, average overlap between hits across all five OEP families: 11.3±19.3%; supplementary table S4). Thus, it appears for OEPs it is possible to distinguishing different β-barrel structures. The only exception to the broad distribution of structurally similar sequences was At OEP40, which had only five structural hits. One of these had a pLDDT of 71, others were below this threshold (Supplementary Table S3h). This particular gene was annotated as a neuronal cell adhesion molecule-like protein and e-value was high (0.0062), indicating that the proteins are unlikely related. Because At OEP40 exhibits structural differences from At OEP21, 24, and 37 (Figur1a), we hypothesize that it may serve a distinct function. Additionally, we do not recover hits to (i) any of the other OEPs from Arabidopsis or (ii) an overlapping hit spectrum across eu- and prokaryotes with other OEPs on sequence and structure level (Supplementary Table S2a, S2f, S3h, S4). This further supports the lack of sequence or structural similarity with any of the other three OEPs or possible bacterial structure homologs. Altogether, our finding suggests that OEP40 may (i) have significantly diverged in structure and sequence or (ii) originated de novo in the last land plant common ancestor. Given that we observe sequence similarity among land plants, the absence of structural similarity to streptophytes (only two significant putative structural homologs with low pLDDT) suggests low structural conservation and rapid structural turnover ( Figure 1b,c , Figure S5). Coherently, we observe low sequence similarity in the C-terminal region of OEP40 across land plants resulting in an unstructured C-terminal region ( Figure 1a , S6). This points to neofunctionalization within land plants, driven by structural divergence. The function of OEP40 may thus have varying functions across land plant diversity. This makes At OEP40 an excellent candidate to study substrate specificity and potential evolutionary changes in this regard. Among OEP21A/B, 24A/B, and 37, OEP24A and B demonstrated predicted structural conservation (e-value ≤10 −5 ) not only within Chloroplastida but also with rhodophytes, and members from haptophytes and SAR group (Stramenopiles/Alveolates/Rhizaria) that harbor plastids via secondary endosymbiosis (Supplementary Table S3e). This result differs from the sequence-based searches (Supplementary Table S2a) and leaves us with two possibilities: we observe (i) an example of low sequence and high structural conservation or (ii) convergent folding. Haptophyte and SAR species with significant structural hits retain plastids of red algal origin ( Sibbald and Archibald 2020 ), which may support a deep homologous ancestry and acquisition early on via EGT. Indeed, for OEP24 hits, putative functions associated with the identified hits are primarily related to porins found in organellar membranes. OEP37 has significant structural hits from all domains of life (e-value ≤10 −5 , Supplemtary Table S3g). Additionally, we found a significant structural homolog from Crysophytes (e-value ≤10 −5 ) for OEP37. Crysophytes also have a red-algal origin of their plastid ( Sibbald and Archibald 2020 ) and indeed structural hits similar to OEP37 from rhodophytes that barely missed the e-value cutoff exist. These similarities to protein structures in rhodophytes is not apparent for OEP21A/B. This is inconsistent with the low-quality hits retrieved for OEP21A from Galdieria via BLASTp; indicating that these BLASTp-derived hits are not deep homologs from the so-called twilight zone. Given that the three OEP families (OEP21, 24, and 37) (i) do not recover the same taxonomic scope of structural homologs/analogs and (ii) recovered hits with distinct descriptions among the best-fitting structural models, we reason that they have distinct evolutionary histories. The analyses of these four β-barrel OEP families suggests that OEPs next to the stepwise recruitment during the evolution of the chloroplast OE, also underwent different degrees of sequence- and structural turnover. While not recovered using sequence analyses only, structural data suggest that OEP24 may be acquisitions from early EGT event. While all of the four β-barrel OEP are annotated as solute channels, their distinct functions are still largely unclear. Nevertheless, the fact that they follow different evolutionary paths, implicates that they may fulfil different functions in the chloroplast OE and that function can also shift during evolution. JASSY originated from latent genetic potential in the LCA of land plants JASSY proteins exhibit unique structural configurations among OEPs: They unite β-sheets and α-helices, distinguishing them from β-barrel OEPs. Among all five OEP families, JASSY showed the broadest taxonomic distribution in the sequence-based analyses ( Figure 1b , Supplementary Table S2a,b,c). JASSY1/2 encode a StAR/START domain, which is typical for lipid transporters, but also other lipid binding proteins, likely causing the broad taxonomic scope. Both HHPred and Alphafold results support this assumption. This is coherent with a recent comparison between sequence and structural methods showing that Foldseek-based structural searches tend to identify a high number of non-homologous sequences ( Mutti et al. 2024 ). Highly conserved domain sets may be a reason for that. To scrutinize the evolutionary history of JASSY1 and JASSY2, we worked with the structural models of Alphafold2 and computed phylogenies based on structure-based alignments ( Figure 3 ). We recovered three distinct clades with broader streptophyte representation, one clade containing homologs to JASSY and the other two clades containing homologs to At PPP1 and a polyketide cyclase, supporting that several initial hits were attracted due to common domains. Cyanobacterial sequences did not cluster with the JASSY homologs, suggesting that the BLASTp hits discussed above are not distant homologs from the twilight zone, but rather other lipid-binding proteins. Bacterial hits that cluster with the chlorophytes in both phylogenetic approaches likely signify a HGT from eukaryotes to bacteria. Consistent with the BLASTp results we identified significant structural hits from rhodophytes that fell into the JASSY-like clade ( Figure 3a ) Here, too, we found homologous hits from haptophytes and ochrophytes, suggesting that JASSY-like homologs were already present prior to the split of Rhodophyta and Chlorophyta. Moreover, we identified structural hits from Lokiarcheota opening the possibility for an ancient origin. The chlorophyte and streptophyte representation of the JASSY- and JASSY-like containing clade was highly similar to that in the sequence-based phylogeny adding confidence to protein-structure based approaches, even though these approaches are still in development ( Garg and Hochberg 2024 ). In our report, the structural phylogenies were successful in aiding to understand uncertainties and provide further evolutionary insight by combining the use of structure as a baseline for sequence alignments and only sequence-based approaches. Download figure Open in new tab Figure 3: Composite phylogenetic analysis of JASSY homologs based on primary sequence and structural protein data. Maximum likelihood phylogenies of structure and sequence (a) JASSY1 and (b) JASSY2 combining information derived from amino acid distance matrices and 3Di (for details see M&M). Structural information is based on AlphaFold database search. 1000 ultrafast bootstrap pseudoreplicates were computed. White arrows indicate homologs from rhodophytes and species with a secondary endosymbiosis event. The only characterized member of the JASSY family is Arabidopsis thaliana JASSY1 facilitating OPDA export from chloroplasts ( Guan et al. 2019 ). But when did this function of JASSY evolve? Our domain analysis across JASSY homologs suggests that the JASSY1 domain setup was first recruited in the LCA of land plants, while JASSY-like sequences predate this occurrence ( Figure 2 ). The similarity to other StAR/START and DUF220-containing proteins in structural or domain-based analyses supports an ancient origin of the domains followed by lineage-specific domain duplications and distributions across the genomes. Yet, despite the absence of the StAR/START domain our structural phylogeny supported a cluster of JASSY-like proteins from chlorophytes and streptophytes. Among the structurally similar hits, hits to putative transporters of non-polar substrates have been annotated in other bacteria and eukaryotes within the AFDB50 database. To our knowledge, screens across the green lineage have detected neither OPDA nor dn-OPDA in chlorophytes ( Chini et al. 2023 , Schmidt et al. 2024 ) and distribution of them in streptophyte algae was scattered ( Schmidt et al. 2024 ). Further, the overlap between the algal sequences we included in our analyses and the species analyzed for OPDA and dn-OPDA production is small. More metabolomic screenings of chlorophyte and streptophyte algae with JASSY homologs and functional characterization of these deep homologs are needed. Without these, an inference of the functional necessity of any of the four domains that bona fide JASSY proteins encode remain obscure. Regarding the evolutionary history of the JASSY-like family, we hypothesize that JASSY emerged from a novel domain assembly. It is likely that the progenitor of JASSY was a transporter for long-chain, non-polar substances that was co-opted in the green lineage to become an OPDA transporter in land plants. Conclusion OEPs are key elements for chloroplast function. However, tracing their evolutionary history is challenging: For one, the cyanobacterial progenitor of plastids was a genetic chimera shaped by genes acquired through HGT. This complicates efforts to definitively trace genes to their cyanobacterial ancestry, even when that is their true origin ( Ku et al., 2015 ). Second, OEPs may have been co-opted from host-derived proteins. Here, we combined structure-based phylogenetic approaches with traditional phylogenetic analyses to understand the evolutionary history of five OEP families. All OEPs, except OEP40, have clear structural similarities to sequences found across the tree of life. However, except for JASSY, none of this is reflected on the sequence level. The OEPs analyzed here likely resulted (i) from neofunctionalization of pre-existing protein families after ancient duplication events or domain reshuffling, the latter being likely the case for JASSY and/or (ii) ancient EGTs—a possibility for OEP24 family. The presence of structurally similar sequences across diverse life forms, coupled with the difficulty in tracing most OEPs’ sequence-level origins, highlights the intricate evolutionary pathways these proteins have traversed. It also emphasizes the power of combined structure and sequence-level analyses in unraveling the evolutionary history of these crucial chloroplast proteins. Our analyses only scratch the surface of the evolutionary space and structure of OEPs or other plastid transporter proteins. Yet, it is clear from our data that OEPs did not originate all at the same time: Some have been recruited later than others, were co-opted or may have replaced existing bacterial versions due to structural similarities. We now know that the evolution of the OE protein make-up is dynamic, although the driving forces of these dynamics remain obscure. Going forward, we need to integrate structural and sequence-based approaches with biochemical and physiological data to study these evolutionary dynamics that gave rise to today’s chloroplast. Material and Methods Sequence homology analyses We used the A. thaliana protein sequences from JASSY1 and 2, OEP21A, B, OEP24A, B, OEP37, and OEP40 to query our database of land plants and streptophyte and chlorophyte algae (Organisms included: ( Anthoceros agrestis Oxford and Bonn (Li et al ., 2020), Anthoceros punctatus (Li et al ., 2020), Amborella trichopoda (Amborella Genome Project et al ., 2013), A. thaliana (Lamesch et al ., 2011), A. lyrata (Hu et al ., 2011), Azolla filiculoides (Li et al ., 2018), Bathycoccus prasinos (Moreau et al ., 2012), Brassica oleracea (Liu et al ., 2014), Brassica rapa (Goodstein et al ., 2011), Brachypodium distachyon (Vogel et al ., 2010), Capsella grandiflora (Slotte et al ., 2013), Carica papaya (Ming et al ., 2008), Ceratopteris richardii (Marchant et al ., 2022), Chara braunii (Nishiyama et al ., 2018), Chlorokybus melkonianii ((Wang et al ., 2020); for naming, see ( Irisarri et al ., 2021 )), Chlamydomonas reinhardtii (Merchant et al ., 2007), Coccomyxa subellipsoidea (Blanc et al ., 2012), Gnetum montanum (Wan et al ., 2018), Gossypium hirsutum (Li et al ., 2015), Isoetes taiwaniensis (Wickell et al ., 2021), Klebsormidium nitens (Hori et al ., 2014), Marchantia polymorpha (Bowman et al ., 2017), Mesostigma viride (Wang et al ., 2020), Micromonas pusilla (Worden et al ., 2009), Micromonas sp. (Worden et al ., 2009), Nicotiana tabacum ( Sierro et al ., 2014 ), Oryza sativa (Ouyang et al ., 2006), Picea abies (Nystedt et al ., 2013), Physcomitrium patens (Lang et al ., 2018), Salvinia cucullata (Li et al ., 2018), Selaginella moellendorffii (Banks et al ., 2011) Solanum lycopersicum (Sato et al ., 2012), Sphagnum fallax (Healey et al ., 2023), Theobroma cacao (Argout et al ., 2011), Triticum aestivum (The International Wheat Genome Sequencing Consortium et al ., 2018), Mesotaenium endlicherianum V1 (Cheng et al ., 2019), Ostreococcus lucimarinus (Palenik et al ., 2007), Penium margaritaceum (Jiao et al ., 2020), Spirogloea muscicola (Cheng et al ., 2019), Ulva mutabilis (De Clerck et al ., 2018), Volvox carteri (Prochnik et al ., 2010)) using BLASTp. We filtered the output according to e-value and only retained hits with an e-value of ≥10. Additionally, we queried the NCBI nr database with the following restrictions (i) excluding Viridiplantae, (ii) excluding Viridiplantae and bacteria, (iii) Cyanobacteria, (iv) Rhodophyta and (v) Glaucophyta. We used protein sequences of JASSY1 and 2, OEP21A, B, OEP24A, B, OEP37, and OEP40 as an input in HHPred (Zimmermann et al. 2018, Gabler et al. 2020). The search was made across the default database PDB_mmCIF70_16_Aug for each protein separately. No specific proteomes were selected. We used the default parameters in the search except E-value cutoff, which changed to 0.05 and the number of max target hits increased to 10000. After downloading the results, we created a table with organism names and the probabilities for the hits. Then these tables were used to plot histograms in figure S1. To check if cyanobacteria hits are present or not, we used a script to find phylum of each species ( https://github.com/derenbuyuktas/Find_Phylum ). Phylogenetic reconstruction based on sequence similarity approaches We fused the output of the BLASTp analyses and aligned all sequences belonging to the same family (in total five families: JASSY, OEP21, OEP24, OEP37, and OEP40) using mafft with a G-INS-I approach ( Katoh and Standley 2013 ). We checked the quality of the alignment and proceeded to calculating a ML phylogeny. For phylogenetic reconstruction of the BLASTp results, we used IQ-TREE with 100 bootstraps per phylogeny (Nguyen et al. 2014). Models were selected using modelfinder implemented in IQ-TREE ( Kalyaanamoorthy et al. 2017 ). Sequence-based phylogenies were visualized with iTOL ( Letunic and Bork 2021 ) and annotated manually for taxonomy. Structural predictions We used Foldseek ( van Kempen et al. 2024 ) to identify structurally similar proteins using the Alphafold database (AFDB50, Jumper et al. 2021, Varadi et al. 2024, accessed 29 October 2024). As query we used the protein sequences of A. thaliana for JASSY1 and 2, OEP21A, B, OEP24A, B, OEP37, and OEP40. For those were several models existed we used the one with the highest quality (UniProt golden star or if not applicable the highest sequence similarity across most of the protein to the variations that existed for the Arabidopsis proteins in the database). We next selected a cutoff of pLDDT≥70 to include high-confidence structural models, while allowing disordered side-chains. In downstream analyses we further applied an e-value cutoff of 10 to distinguish likely homologous structural hits from analogous structural hits. Taxonomic identification of hits was done by recovering the TaxID for the genus a particular hit corresponded to. Domain predictions Domains were predicted using Interpro and CD batch search using the Arabidopsis thaliana protein sequences as query. Both tools gave the similar results. Significant domains were only reported for JASSY1 and 2. OEP21A/B, 24A/B, and OEP37 had domains named after them, spanning the whole protein, e.g. OEP21A and 21B encode the domain OEP21. Such domains were not visualized. OEP40 included the OS08G0510800 PROTEIN, which was not identified using CD search. Phylogenetic reconstruction based on structural alignments We, here, follow a novel approach for structural phylogenetics of JASSY1 and 2 first presented in Puente-Lelievre et. al (2024), which utilizes the 3Di alphabet introduced by Foldseek to capture tertiary interactions between neighboring residues as information for phylogenetic reconstruction in addition to standard amino acid alignments using a partition scheme in a maximum likelihood framework for a detailed discussion see Puente Lelievre et. al (2024) and Garg & Hochberg (2024) . To infer the structural phylogeny for JASSY1 and 2, we used the the list of possible homologs of JASSY1 and 2 derived from the search in the Alphafold database, we selected hits with an e-value ≥10. The putative homologs were aligned with the structural aligner FoldMason (Gilchchrist et al. 2024) to get both the amino acid and 3Di alignments. The alignments were then trimmed using ClipKIT -m gappy ( Steenwyk et al. 2020 ) in the case of amino acid alignments and trimAl ( Capella-Gutiérrez et al. 2009 ) -gappyout in the case of 3Di alignments, where trimAl performs more extensive trimming in order to confine the 3Di analysis to the protein cores. Trees were constructed using IQ-TREE 2.4.0 and using Modelfinder to find the best fit substitution model and 1000 Ultrafast bootstraps ( Hoang et al. 2018 ). For the combined amino acid and 3Di analysis, both alignments were concatenated and run with an edge-proportional partition scheme ( Chernomor et al. 2016 ), where the custom substitution matrix by Garg and Hochberg (2024) is specified for the 3Di alignment. Acknowledgement We thank Johannes Söding (MPI for Multidisciplinary Sciences, Göttingen) for constructive feedback regarding the setup for structural analyses. SdV is grateful to the German Research Foundation (DFG) for funding (Cymbiomics, VR139/2-1; 515101361). SS received funding from the DFG (CRC TR175, project B06). Funder Information Declared Deutsche Forschungsgemeinschaft, https://ror.org/018mejw64 , 515101361 , CRC TR175 References 1. Amborella Genome Project , Albert VA , et al. ( 2013 ) The Amborella genome and the evolution of flowering plants . Science 342 ( 6165 ): 1241089 . doi: 10.1126/science.1241089 OpenUrl Abstract / FREE Full Text 2. Argout X , et al. ( 2011 ) The genome of Theobroma cacao . Nature genetics 43 ( 2 ): 101 – 108 . doi: 10.1038/ng.736 OpenUrl CrossRef PubMed 3. Banks JA , et al. ( 2011 ) The Selaginella genome identifies genetic changes associated with the evolution of vascular plants . Science 332 ( 6032 ): 960 – 963 . doi: 10.1126/science.1203810 OpenUrl Abstract / FREE Full Text 4. ↵ Baltzis A , Santus L , Langer BE , Magis C , de Vienne DM , Gascuel O , Mansouri L , Notredame C ( 2025 ) multistrap: boosting phylogenetic analyses with structural information . Nat Commun . 16 : 293 . doi: 10.1038/s41467-024-55264-0 OpenUrl CrossRef PubMed 5. ↵ Barth MA , Soll J , Akbaş S. ( 2022 ). Prokaryotic and eukaryotic traits support the biological role of the chloroplast outer envelope . Biochim Biophys Acta Mol Cell Res . 1869 ( 5 ): 119224 OpenUrl 6. Blanc G , et al. ( 2012 ) The genome of the polar eukaryotic microalga Coccomyxa subellipsoidea reveals traits of cold adaptation . Genome Biol 13 ( 5 ): R39 . doi: 10.1186/gb-2012-13-5-r39 OpenUrl CrossRef PubMed 7. ↵ Bölter B. ( 2018 ) En route into chloroplasts: preproteins’ way home . Photosynth Res . 138 : 263 – 275 . doi: 10.1007/s11120-018-0542-8 OpenUrl CrossRef PubMed 8. ↵ Bou Dagher L , Madern D , Malbos P , Brochier-Armanet C ( 2025 ). Faithful Interpretation of Protein Structures through Weighted Persistent Homology Improves Evolutionary Distance Estimation . Mol Biol Evol . 42 : msae271 OpenUrl CrossRef PubMed 9. Bowman JL , et al. ( 2017 ) Insights into land plant evolution garnered from the Marchantia polymorpha genome . Cell 171 ( 2 ): 287 - 304.e215 . doi: 10.1016/j.cell.2017.09.030 OpenUrl CrossRef PubMed 10. ↵ Capella-Gutiérrez , S. , Silla-Martínez , J.M. , and Gabaldón , T. ( 2009 ). trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses . Bioinformatics 25 , 1972 – 1973 . OpenUrl CrossRef PubMed Web of Science 11. Cheng S , et al. ( 2019 ) Genomes of subaerial Zygnematophyceae provide insights into land plant evolution . Cell 179 ( 5 ): 1057 - 1067.e1014 . doi: 10.1016/j.cell.2019.10.019 OpenUrl CrossRef PubMed 12. ↵ Chen Z , Zhang X , Yu W , Luo Q ( 2025 ) A comprehensive benchmarking study of protein structure alignment tools based on downstream task performance . BioRxiv doi: 10.1101/2025.03.11.642719 OpenUrl Abstract / FREE Full Text 13. ↵ Chernomor , O. , von Haeseler , A. , and Minh , B.Q. ( 2016 ). Terrace Aware Data Structure for Phylogenomic Inference from Supermatrices . Syst Biol 65 , 997 – 1008 . doi: 10.1093/sysbio/syw037 . OpenUrl CrossRef PubMed 14. ↵ Chini , A. , Monte , I. , Zamarreno , A.M. , Garcia-Mina , J.M. , and Solano , R. ( 2023 ). Evolution of the jasmonate ligands and their biosynthetic pathways . New Phytol 238 , 2236 – 2246 . doi: 10.1111/nph.18891 . OpenUrl CrossRef PubMed 15. De Clerck O , et al. ( 2018 ) Insights into the evolution of multicellularity from the sea lettuce genome . Curr Biol 28 ( 18 ): 2921 - 2933.e2925 . doi: 10.1016/j.cub.2018.08.015 OpenUrl CrossRef PubMed 16. ↵ Dhabalia Ashok A , de Vries S , Darienko T , Irisarri I , de Vries J. ( 2024 ) Evolutionary assembly of the plant terrestrialization toolkit from protein domains . Proc Roy Soc B 291 : 20240985 doi.org/ 10.1098/rspb.2024.0985 OpenUrl CrossRef PubMed 17. ↵ Fernie AR , de Vries S , de Vries J. ( 2024 ) Evolution of plant metabolism: the state-of-the-art . Philos Trans R Soc Lond B Biol Sci . 379 : 20230347 . doi: 10.1098/rstb.2023.0347 OpenUrl CrossRef PubMed 18. ↵ Garg , S.G. , and Hochberg , G.K.A. ( 2024 ). A general substitution matrix for structural phylogenetics . bioRxiv . doi: 10.1101/2024.09.19.613819 . OpenUrl Abstract / FREE Full Text 19. Gilchrist , C.L.M. , Mirdita , M. , and Steinegger , M. ( 2024 ). Multiple protein structure alignment at scale with FoldMason . bioRxiv . doi: 10.1101/2024.08.01.606130 . OpenUrl Abstract / FREE Full Text 20. Goetze TA , Philippar K , Ilkavets I , Soll J , Wagner R. ( 2006 ) OEP37 is a new member of the chloroplast outer membrane ion channels . J Biol Chem . 281 : 17989 – 17998 . doi: 10.1074/jbc.M600700200 OpenUrl Abstract / FREE Full Text 21. Goodstein DM , et al. ( 2011 ) Phytozome: a comparative platform for green plant genomics . Nucleic Acids Res 40 ( D1 ): D1178 - D1186 . doi: 10.1093/nar/gkr944 OpenUrl CrossRef PubMed Web of Science 22. ↵ Guan L , Denkert N , Eisa A , Lehmann M , Sjuts I , Weiberg A , Soll J , Meinecke M , Schwenkert S. ( 2019 ). JASSY, a chloroplast outer membrane protein required for jasmonate biosynthesis . Proc Natl Acad Sci USA . 116 : 10568 – 10575 . doi: 10.1073/pnas.1900482116 OpenUrl Abstract / FREE Full Text 23. Günsel U , Klöpfer K , Häusler E. et al. ( 2032 ) Structural basis of metabolite transport by the chloroplast outer envelope channel OEP21 . Nat Struct Mol Biol . 30 : 761 – 769 doi: 10.1038/s41594-023-00984-y OpenUrl CrossRef 24. Harsman A , Schock A , Hemmis B , Wahl V , Jeshen I , Bartsch P , Schlereth A , Pertl-Obermeyer H , Goetze TA , Soll J , Philippar K , Wagner R. ( 2016 ) OEP40, a Regulated Glucose-permeable β-Barrel Solute Channel in the Chloroplast Outer Envelope Membrane . J Biol Chem . 291 : 17848 – 17860 . doi: 10.1074/jbc.M115.712398 OpenUrl Abstract / FREE Full Text 25. Healey AL , et al. ( 2023 ) Newly identified sex chromosomes in the Sphagnum (peat moss) genome alter carbon sequestration and ecosystem dynamics . Nat Plants 9 ( 2 ): 238 – 254 . doi: 10.1038/s41477-022-01333-5 OpenUrl CrossRef PubMed 26. ↵ Hoang , D.T. , Chernomor , O. , Von Haeseler , A. , Minh , B.Q. , and Vinh , L.S. ( 2018 ). UFBoot2: improving the ultrafast bootstrap approximation . Molecular biology and evolution 35 , 518 – 522 . OpenUrl CrossRef PubMed 27. Hori K , et al. ( 2014 ) Klebsormidium flaccidum genome reveals primary factors for plant terrestrial adaptation . Nat Commun 5 ( 1 ): 3978 . doi: 10.1038/ncomms4978 OpenUrl CrossRef PubMed 28. Hu TT , et al. ( 2011 ) The Arabidopsis lyrata genome sequence and the basis of rapid genome size change . Nature genetics 43 ( 5 ): 476 – 481 . doi: 10.1038/ng.807 OpenUrl CrossRef PubMed Web of Science 29. Illergård K , Ardell DH , Elofsson A. ( 2009 ) Structure is three to ten times more conserved than sequence--a study of structural response in protein cores . Proteins . 77 : 499 – 508 . doi: 10.1002/prot.22458 OpenUrl CrossRef PubMed Web of Science 30. ↵ Irisarri I , Darienko T , Pröschold T , Fürst-Jansen JMR , Jamy M , de Vries J ( 2021 ) Unexpected cryptic species among streptophyte algae most distant to land plants . Proceedings of the Royal Society B: Biological Sciences 288 ( 1963 ): 20212168 . doi: 10.1098/rspb.2021.2168 OpenUrl CrossRef PubMed 31. Jiao C , et al. ( 2020 ) The Penium margaritaceum genome: Hallmarks of the origins of land plants . Cell 181 ( 5 ): 1097 – 1111 . doi: 10.1016/j.cell.2020.04.019 OpenUrl CrossRef PubMed 32. ↵ John A , Keller I , Ebel KW , Neuhaus HE . ( 2025 ). Two critical membranes: how does the chloroplast envelope affect plant acclimation properties? J Exp Bot . 76 : 214 – 227 . doi: 10.1093/jxb/erae436 OpenUrl CrossRef PubMed 33. ↵ Kalyaanamoorthy , S. , Minh , B.Q. , Wong , T.K. , Von Haeseler , A. , and Jermiin , L.S. ( 2017 ). ModelFinder: fast model selection for accurate phylogenetic estimates . Nature Methods 14 , 587 – 589 . OpenUrl CrossRef PubMed 34. ↵ Katoh , K. , and Standley , D.M. ( 2013 ). MAFFT multiple sequence alignment software version 7:improvements in performance and usability . Molecular Biology and Evolution 30 , 772 – 780 . OpenUrl CrossRef PubMed Web of Science 35. ↵ Ku , C. , Nelson-Sathi , S. , Roettger , M. , Garg , S. , Hazkani-Covo , E. , and Martin , W.F. ( 2015 ). Endosymbiotic gene transfer from prokaryotic pangenomes: Inherited chimerism in eukaryotes . Proc Natl Acad Sci U S A 112 , 10139 – 10146 . doi: 10.1073/pnas.1421385112 . OpenUrl Abstract / FREE Full Text 36. ↵ Kunz H-H , Armbruster U , Mühlbauer S , de Vries J , Davis GA . ( 2024 ) Chloroplast ion homeostasis – what do we know and where should we go? 243 : 543 – 559 . New Phytol . doi: 10.1111/nph.19661 OpenUrl CrossRef PubMed 37. Lamesch P , et al. ( 2011 ) The Arabidopsis Information Resource (TAIR): improved gene annotation and new tools . Nucleic Acids Res 40 ( D1 ): D1202 - D1210 . doi: 10.1093/nar/gkr1090 OpenUrl CrossRef PubMed Web of Science 38. Lang D , et al. ( 2018 ) The Physcomitrella patens chromosome-scale assembly reveals moss genome structure and evolution . Plant J 93 ( 3 ): 515 – 533 . doi: 10.1111/tpj.13801 OpenUrl CrossRef PubMed 39. ↵ Letunic , I. , and Bork , P. ( 2021 ). Interactive Tree Of Life (iTOL) v5: an online tool for phylogenetic tree display and annotation . Nucleic acids research 49 , W293 – W296 . OpenUrl CrossRef PubMed 40. Li F-W , et al. ( 2018 ) Fern genomes elucidate land plant evolution and cyanobacterial symbioses . Nat Plants 4 ( 7 ): 460 – 472 . doi: 10.1038/s41477-018-0188-8 OpenUrl CrossRef PubMed 41. Li F-W , et al. ( 2020 ) Anthoceros genomes illuminate the origin of land plants and the unique biology of hornworts . Nat Plants 6 ( 3 ): 259 – 272 . doi: 10.1038/s41477-020-0618-2 OpenUrl CrossRef PubMed 42. Li F , et al. ( 2015 ) Genome sequence of cultivated Upland cotton (Gossypium hirsutum TM-1) provides insights into genome evolution . Nature Biotechnol 33 ( 5 ): 524 – 530 . doi: 10.1038/nbt.3208 OpenUrl CrossRef PubMed 43. Liu S , et al. ( 2014 ) The Brassica oleracea genome reveals the asymmetrical evolution of polyploid genomes . Nat Commun 5 ( 1 ): 3930 . doi: 10.1038/ncomms4930 OpenUrl CrossRef PubMed 44. Marchant DB , et al. ( 2022 ) Dynamic genome evolution in a model fern . Nat Plants 8 ( 9 ): 1038 – 1051 . doi: 10.1038/s41477-022-01226-7 OpenUrl CrossRef PubMed 45. Merchant SS , et al. ( 2007 ) The Chlamydomonas genome reveals the evolution of key animal and plant functions . Science 318 ( 5848 ): 245 – 250 . doi: 10.1126/science.1143609 OpenUrl Abstract / FREE Full Text 46. Ming R , et al. ( 2008 ) The draft genome of the transgenic tropical fruit tree papaya (Carica papaya Linnaeus) . Nature 452 ( 7190 ): 991 – 996 . doi: 10.1038/nature06856 OpenUrl CrossRef PubMed Web of Science 47. ↵ Moi D , Bernard C , Steinegger M , Nevers Y , Langleib M , Dessimoz C ( 2023 ) Structural phylogenetics unravels the evolutionary diversification of communication systems in gram-positive bacteria and their viruses . BioRxiv doi: 10.1101/2023.09.19.558401 OpenUrl Abstract / FREE Full Text 48. Moreau H , et al. ( 2012 ) Gene functionalities and genome structure in Bathycoccus prasinos reflect cellular specializations at the base of the green lineage . Genome Biol 13 ( 8 ): R74 . doi: 10.1186/gb-2012-13-8-r74 OpenUrl CrossRef PubMed 49. ↵ Mutti , G. , Ocaña-Pallarès , E. , and Gabaldón , T. ( 2024 ). Newly developed structure-based methods do not outperform standard sequence-based methods for large-scale phylogenomics . bioRxiv . doi: 10.1101/2024.08.02.606352 . OpenUrl Abstract / FREE Full Text 50. Nguyen , L.-T. , Schmidt , H.A. , Von Haeseler , A. , and Minh , B.Q. ( 2015 ). IQ-TREE: a fast and effective stochastic algorithm for estimating maximum-likelihood phylogenies . Molecular Biology and Evolution 32 , 268 – 274 . OpenUrl CrossRef PubMed 51. Nishiyama T , et al. ( 2018 ) The Chara genome: Secondary complexity and implications for plant terrestrialization . Cell 174 ( 2 ): 448 – 464 . doi: 10.1016/j.cell.2018.06.033 OpenUrl CrossRef PubMed 52. Nystedt B , et al. ( 2013 ) The Norway spruce genome sequence and conifer genome evolution . Nature 497 ( 7451 ): 579 – 584 . doi: 10.1038/nature12211 OpenUrl CrossRef PubMed Web of Science 53. Ouyang S , et al. ( 2006 ) The TIGR rice genome annotation resource: improvements and new features . Nucleic Acids Res 35 (uppl_1):D883-D887. doi: 10.1093/nar/gkl976 OpenUrl CrossRef PubMed Web of Science 54. Palenik B , et al. ( 2007 ) The tiny eukaryote Ostreococcus provides genomic insights into the paradox of plankton speciation . PNAS 104 ( 18 ): 7705 – 7710 . doi: 10.1073/pnas.0611046104 OpenUrl Abstract / FREE Full Text 55. ↵ Ponce-Toledo RI , López-García P , Moreira D. ( 2019 ) Horizontal and endosymbiotic gene transfer in early plastid evolution . New Phytol . 224 : 618 – 624 . doi: 10.1111/nph.15965 OpenUrl CrossRef PubMed 56. Prochnik SE , et al. ( 2010 ) Genomic analysis of organismal complexity in the multicellular green alga Volvox carteri . Science 329 ( 5988 ): 223 – 226 . doi: 10.1126/science.1188800 OpenUrl Abstract / FREE Full Text 57. Puente-Lelievre C , Malik AJ , Douglas J , Ascher D , Baker M , Allison J , Poole A , Lundin D , Fullmer M , Bouckert R , Kim H , Steinegger M , Matzke N ( 2024 ) Tertiary-interaction characters enable fast, model-based structural phylogenetics beyond the twilight zone . BioRxiv . doi: 10.1101/2023.12.12.571181 OpenUrl Abstract / FREE Full Text 58. ↵ Röhl T , Motzkus M , Soll J. ( 1999 ) The outer envelope protein OEP24 from pea chloroplasts can functionally replace the mitochondrial VDAC in yeast . FEBS Letters . 460 : 491 – 494 . doi: 10.1016/S0014-5793(99)01399-XCita OpenUrl CrossRef PubMed Web of Science 59. ↵ Rost B. ( 1999 ) Twilight zone of protein sequence alignments . Prot Engineer . 12 : 85 – 94 doi: 10.1093/protein/12.2.85 OpenUrl CrossRef PubMed Web of Science 60. ↵ Ruperti F , Papadopoulos N , Musser JM , Mirdita, Steinegger M , Arendt D. ( 2023 ) Cross-phyla protein annotation by structural prediction and alignment . Genome Biol 2023 . 24 : 113 . doi: 10.1186/s13059-023-02942-9 OpenUrl CrossRef PubMed 61. Sato S , et al. ( 2012 ) The tomato genome sequence provides insights into fleshy fruit evolution . Nature 485 ( 7400 ): 635 – 641 . doi: 10.1038/nature11119 OpenUrl CrossRef PubMed Web of Science 62. ↵ Schmidt , V. , Skokan , R. , Depaepe , T. , Kurtovic , K. , Haluska , S. , Vosolsobe , S. , Vaculikova , R. , Pil , A. , Dobrev , P.I. , Motyka , V. , et al. ( 2024 ). Phytohormone profiling in an evolutionary framework . Nat Commun 15 , 3875 . doi: 10.1038/s41467-024-47753-z . OpenUrl CrossRef PubMed 63. ↵ Schwenkert S , Leister D , Lo WT . ( 2023 ). Hidden keyholders – exploring metabolite transport across the outer chloroplast membrane . J Mito Plast Endosymbio . 1 : 2247168 . doi: 10.1080/28347056.2023.2247168 OpenUrl CrossRef 64. ↵ Sibbald SJ , Archibald JM ( 2020 ) Genomic insights into plastid evolution . Genome Biol Evol . 12 : 978 – 990 . doi: 10.1093/gbe/evaa096 . OpenUrl CrossRef 65. ↵ Sierro N , Battey JN , Ouadi S , Bakaher N , Bovet L , Willig A , Goepfert S , Peitsch MC , Ivanov NV ( 2014 ) The tobacco genome sequence and its comparison with those of tomato and potato . Nat Commun 5 : 3833 . doi: 10.1038/ncomms4833 OpenUrl CrossRef PubMed 66. Slotte T , et al. ( 2013 ) The Capsella rubella genome and the genomic consequences of rapid mating system evolution . Nature genetics 45 ( 7 ): 831 – 835 . doi: 10.1038/ng.2669 OpenUrl CrossRef PubMed 67. ↵ Söding J , Biergert A , Lupas AN . ( 2005 ) The HHpred interactive server for protein homology detection and structure prediction . Nucleic Acid Res . 33 : W244 – 8 . doi: 10.1093/nar/gki408 . OpenUrl CrossRef PubMed Web of Science 68. ↵ Steenwyk , J.L. , Buida , T.J. , 3rd . , Li , Y. , Shen , X.X. , and Rokas , A. ( 2020 ). ClipKIT: A multiple sequence alignment trimming software for accurate phylogenomic inference . PLoS Biol 18 , e3001007 . doi: 10.1371/journal.pbio.3001007 . OpenUrl CrossRef PubMed 69. The International Wheat Genome Sequencing Consortium , Appels R , et al. ( 2018 ) Shifting the limits in wheat research and breeding using a fully annotated reference genome . Science 361 ( 6403 ): eaar7191 . doi : doi: 10.1126/science.aar7191 OpenUrl Abstract / FREE Full Text 70. ↵ Topitsch , A. , Schwede , T. , and Pereira , J. ( 2024 ). Outer membrane beta-barrel structure prediction through the lens of AlphaFold2 . Proteins 92 , 3 – 14 . doi: 10.1002/prot.26552 . OpenUrl CrossRef PubMed 71. ↵ van Kempen M , Kim SS , Tumescheit C , Mirdita M , Lee J , Gilchrist CLM , Söding J , Steinegger M. ( 2024 ) Fast and accurate protein structure search with Foldseek . Nat Biotech . 42 : 243 – 246 . doi: 10.1038/s41587-023-01773-0 OpenUrl CrossRef PubMed 72. Vogel JP , et al. ( 2010 ) Genome sequencing and analysis of the model grass Brachypodium distachyon . Nature 463 ( 7282 ): 763 – 768 . doi: 10.1038/nature08747 OpenUrl CrossRef PubMed Web of Science 73. Wan T , et al. ( 2018 ) A genome for gnetophytes and early evolution of seed plants . Nat Plants 4 ( 2 ): 82 – 89 . doi: 10.1038/s41477-017-0097-2 OpenUrl CrossRef PubMed 74. Wang S , et al. ( 2020 ) Genomes of early-diverging streptophyte algae shed light on plant terrestrialization . Nat Plants 6 ( 2 ): 95 – 106 . doi: 10.1038/s41477-019-0560-3 OpenUrl CrossRef PubMed 75. ↵ Weber APM , Schwacke R , Flügge U-I. ( 2005 ) Solute transporters of the plastid envelope membrane . Annu Rev Plant Biol . 56 : 133 – 64 . doi: 10.1146/annurev.arplant.56.032604.144228 OpenUrl CrossRef PubMed 76. Wickell D , et al. ( 2021 ) Underwater CAM photosynthesis elucidated by Isoetes genome . Nat Commun 12 ( 1 ): 6348 . doi: 10.1038/s41467-021-26644-7 OpenUrl CrossRef PubMed 77. Worden AZ , et al. ( 2009 ) Green evolution and dynamic adaptations revealed by genomes of the marine picoeukaryotes Micromonas . Science 324 ( 5924 ): 268 – 272 . doi: 10.1126/science.1167222 OpenUrl Abstract / FREE Full Text View the discussion thread. Back to top Previous Next Posted June 24, 2025. Download PDF Supplementary Material Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following The evolutionary history of plastid outer envelope proteins – a structure-sequence comparison Message Subject (Your Name) has forwarded a page to you from bioRxiv Message Body (Your Name) thought you would like to see this page from the bioRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share The evolutionary history of plastid outer envelope proteins – a structure-sequence comparison Deren Büyüktaş , Jonas A. Mehl , Timo Engelsdorf , Lars M. Voll , Hans-Henning Kunz , Serena Schwenkert , Sophie de Vries bioRxiv 2025.06.18.660430; doi: https://doi.org/10.1101/2025.06.18.660430 Share This Article: Copy Citation Tools The evolutionary history of plastid outer envelope proteins – a structure-sequence comparison Deren Büyüktaş , Jonas A. Mehl , Timo Engelsdorf , Lars M. Voll , Hans-Henning Kunz , Serena Schwenkert , Sophie de Vries bioRxiv 2025.06.18.660430; doi: https://doi.org/10.1101/2025.06.18.660430 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Evolutionary Biology Subject Areas All Articles Animal Behavior and Cognition (7618) Biochemistry (17635) Bioengineering (13859) Bioinformatics (41846) Biophysics (21401) Cancer Biology (18534) Cell Biology (25422) Clinical Trials (138) Developmental Biology (13352) Ecology (19860) Epidemiology (2067) Evolutionary Biology (24285) Genetics (15582) Genomics (22463) Immunology (17700) Microbiology (40298) Molecular Biology (17141) Neuroscience (88424) Paleontology (666) Pathology (2825) Pharmacology and Toxicology (4813) Physiology (7633) Plant Biology (15107) Scientific Communication and Education (2042) Synthetic Biology (4284) Systems Biology (9808) Zoology (2267)