Variation in genome architecture and epigenetic modification across the microsporidia phylogeny

Variation in genome architecture and epigenetic modification across the microsporidia phylogeny | 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 Variation in genome architecture and epigenetic modification across the microsporidia phylogeny View ORCID Profile Pascal Angst , View ORCID Profile Dieter Ebert , View ORCID Profile Peter D. Fields doi: https://doi.org/10.1101/2025.01.20.633886 Pascal Angst 1 Department of Environmental Sciences, Zoology, University of Basel , Basel, Switzerland Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Pascal Angst For correspondence: pascal.angst{at}unibas.ch Dieter Ebert 1 Department of Environmental Sciences, Zoology, University of Basel , Basel, Switzerland Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Dieter Ebert Peter D. Fields 1 Department of Environmental Sciences, Zoology, University of Basel , Basel, Switzerland Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Peter D. Fields Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract Microsporidia are a model clade for studying intracellular parasitism, being well-known for their streamlined genomes and their extreme life history. Although microsporidia are highly diverse and ecologically important to a broad range of hosts, previous research on genome architecture has focused primarily on the mammal-infecting genus Encephalitozoon . Here, we expand that work, testing the universality of the patterns observed in Encephalitozoon by investigating and comparing variation in genetic and epigenetic architectures in the high-quality genome assemblies of several major microsporidia clades. Our comparison of nine genomes, including the first genome assemblies of Binucleata daphniae , Gurleya vavrai , and Conglomerata obtusa , and revised, improved assemblies of Glugoides intestinalis and Ordospora colligata , found limited conservation of genetic and epigenetic architecture across all microsporidia, although many genomic characteristics, such as nucleotide composition and repeat content, were shared between genomes of the same or related clades. For example, rRNA genes were hypermethylated in all species, but their position close to chromosome ends was only found in the Encephalitozoon and its sister clade. GC-content varied widely, linked to genome size, phylogenetic position and activity of repeat elements. These findings enhance our insight into genome evolution and, consistent with findings from other systems, suggest epigenetic modification as a regulatory mechanism of gene expression and repeat element activity in microsporidia. Our comparative genome analysis reveals higher variation among microsporidia than previously supposed. Introduction The study of parasite evolution looks at the mechanisms by which parasites adapt to exploit their hosts ( Poulin & Randhawa, 2015 ; Schmid-Hempel, 2021 ). These adaptations include physical structures used to invade or attach to the host, secretory molecules that subvert the host’s immune system or alter its behavior to the parasite’s advantage, and genomic rearrangements that optimize gene transcription and genome replication. Genome evolution particularly has received much recent attention in the field of microsporidia. These fungi-related intracellular parasites exhibit high variation in genome length, possibly related to their life history ( Haag et al., 2020 ), but although comparative studies of microsporidia have provided initial insights into what is arguably the most extreme form of parasitism, including the molecular basis of parasitic adaptations ( Nakjang et al., 2013 ; Wadi & Reinke, 2020 ; Williams et al., 2022 ), the lack of high-quality genomes for most major microsporidia clades in this little understood branch of the tree of life has limited comparative studies of genome architecture to single genera (see e.g., Khalaf et al. (2024) , Mascarenhas dos Santos et al. (2023) ). The available short-read-based genome assemblies have provided inadequate insights into microsporidia genomic architecture, despite hinting at its high diversity. Microsporidia exhibit highly derived genomic features for parasitism, including mitochondrion genome loss and nuclear genome compaction ( Jespersen et al., 2022 ), the latter of which is highly variable among microsporidia clades, with different forms and levels of (non-)coding DNA loss. Extreme examples can be seen in the mammalian parasite genus Enterocytozoon , which lacks most genes involved in glycolysis and is therefore energetically completely dependent on its host (Wiredu Boakye et al., 2017 ), and in the Encephalitozoonidae family, which has reduced inter- and intragenic regions, including repeat content ( Corradi & Slamovits, 2011 ; Mascarenhas dos Santos et al., 2023 ). An opposite phenomenon, genome expansion, is observed secondarily in microsporidia with mixed-mode (horizontal and vertical) transmission, such as Nosema bombycis and Hamiltosporidium tvaerminnensis ( de Albuquerque et al., 2020 ; Parisot et al., 2014 ). This likely occurs because vertical transmission reduces effective population size and thus the efficacy of natural selection to limit genome expansion, e.g., through the proliferation of transposable elements ( Haag et al., 2020 ). While the quality of microsporidian genome assemblies is not as essential when it comes to comparing the length or presence of genetic elements, we do need high-quality assemblies to study the abundance and relative location of these genetic elements across species. Although microsporidia are found in a wide range of host species, including humans and agriculturally important animals, from different environments, most microsporidia seem to occur in aquatic environments with the greatest richness found in Crustacea ( Bojko & Stentiford, 2022 ). Indeed, thanks, perhaps, to the vast abundance of Crustacea and the opportunistic nature of microsporidia ( Weiss & Becnel, 2014 ), Crustacea host microsporidia from all major clades ( Bojko et al., 2022 ). Additionally, because many microcrustaceans such as the model system Daphnia are filter feeders, they accumulate infectious pathogen cells during feeding, which provides the initial contact point and opportunity for microsporidia–host interactions. Daphnia alone are known to be regularly infected by species from at least four of the seven major microsporidia clades, as well as an expanded microsporidium that still has a mitochondrion ( Ebert, 2008 ; Haag et al., 2014 ). In this comparative genomic study, we aim to better understand genomic evolution in microsporidia by elucidating the causes of variation in their genomic features, and the arrangement and epigenetic modifications of their genome. Only recently, and only for a few microsporidia genera, have genomic architecture and methylation patterns been described. For example, a recently-described genomic architecture for three species in the human-infecting genus Encephalitozoon found that each chromosome in the genomes of Encephalitozoon spp., from the ends to the core, consists of 5-mer telomeric repeats, telomere-associated repeat elements (TAREs), hypermethylated ribosomal RNA (rRNA) genes, less methylated subtelomeres, and a hypomethylated chromosome core ( Mascarenhas dos Santos et al., 2023 ). Our aim is to evaluate the generality of this architecture by using high-quality genome resources to examine microsporidia from diverse clades of the phylum. We look at Encephalitozoon intestinalis , its close relative Ordospora colligata , Vairimorpha necatrix also of the Nosematida clade, Glugoides intestinalis of the sister clade Enterocytozoonida, Hamiltosporidium tvaerminnensis of the orphan clade, three microsporidia of the Amblyosporida clade ( Binucleata daphniae , Gurleya vavrai , and Conglomerata obtusa (≡ Larssonia obtusa )), and one expanded microsporidium, Mitosporidium daphniae . We further explore the processes that drive genome rearrangements and epigenetic modifications in these microsporidia. Previous studies have shown a relationship between mode of transmission and repeat content in the microsporidia genome ( de Albuquerque et al., 2020 ; Haag et al., 2020 ), suggesting that, for example, life history contributes to the evolution of genomic architecture. As part of our study on genome organization and (epi)genetic features in these diverse microsporidia, we also contribute here the first high-quality genome assemblies and epigenetic annotations for a number of understudied microsporidia clades. Results Genome assemblies We generated genome assemblies for five microsporidia ( Table 1 ), including first-time assemblies for B. daphniae , G. vavrai , and C. obtusa , as well as enhanced assemblies for O. colligata and G. intestinalis . To expand our taxon sampling, we also included available high-quality genomes of four other microsporidia: E. intestinalis ( Mascarenhas dos Santos et al., 2023 ), H. tvaerminnensis ( Angst et al., 2023 ), M. daphniae (Angst et al., in prep.), and V. necatrix ( Svedberg et al., 2024 ) ( Table 1 ). The overall length of the nine genome assemblies correlated negatively with their GC-content ( F (1,7) = 19.44, P = 0.003, R 2 = 0.74; Figure 1 ), following the trend seen in all (draft) microsporidia reference genome assemblies available in the NCBI database (Figure S1, Table S1). The Amblyosporida, H. tvaerminnensis , and V. necatrix genomes had about 15 % lower GC-content (22 – 29 %) and were about three times longer (10 – 22 Mb) than the smaller E. intestinalis , O. colligata , G. intestinalis , and M. daphniae genomes (34 – 43 % and 3 – 6 Mb). The larger genomes had a higher repeat content (26 – 50 %) and a higher number of protein-coding genes (2,847 – 4,231 bp) than the smaller genomes (12 – 20 % and 1,768 – 2,840 bp), except for G. intestinalis , whose genome consisted of 43 % repeats (Positive correlation between assembly and repeat length: F (1,7) = 36.35, P = 0.001, R 2 = 0.84). The protein-coding genes in larger genomes tended to be shorter on average (952 – 1,081 bp) than in shorter genomes (1,019 – 1,447 bp), except for H. tvaerminnensis (1,391 bp) whose protein-coding genes were closest to the expanded microsporidium M. daphniae (1,447 bp) in average length. Download figure Open in new tab Figure 1: Relationship between genome length, total repeat length, and GC-content in nine microsporidia species. Assembly length (black dots and line) and total length of repeats (gray dots and line) correlated negatively with GC-content. Species names are displayed to the right of the plot at the corresponding GC-content. View this table: View inline View popup Table 1: Assembly information for the analyzed m 151 icrosporidia genomes. BUSCO completeness was calculated using the microsporidia specific microsporidia_odb10 database, which is not specific to expanded microsporidia like M. daphniae . Our improved O. colligata and G. intestinalis genome assemblies were more complete than previous assemblies, containing subtelomeric sequences for most chromosomes (Table S2). Phylogenetic inference confirmed previous rRNA gene phylogenies, placing our eight core microsporidia genomes into four different clades; M. daphniae was placed with the expanded microsporidium Paramicrosporidium saccamoebae ( Figure 2 and S2). Our first high-quality genome assemblies in the Amblyosporida clade were all from the Gurleyidae family. Download figure Open in new tab Figure 2: Maximum likelihood phylogeny of the core and expanded microsporidia with Rozella allomycis as an outgroup. In addition to the species discussed here (highlighted), we selected a representative sample of microsporidia species with available data for phylogenetic inference based on 15 single-copy orthologs. Node labels represent bootstrap values from 1,000 runs, and major microsporidia clades are delineated according to Bojko et al. (2022) . Genome architecture and synteny Our reference and starting point for this comparison of microsporidia genome architecture was the well-described chromosome arrangement of Encephalitozoon ( Mascarenhas dos Santos et al., 2023 ). We first compared E. intestinalis to its close relative O. colligata , finding them to have a similar genome architecture with a 5-mer telomeric repeat (TTAGG) followed by a large and a small rRNA gene each (= rRNA operon), which we found on both ends of six out of the nine contigs and on one end of each of the other three contigs ( Figure 3 , Table S2). The next most closely related species, V. necatrix and G. intestinalis , had the same 5-mer telomeric repeat and a 4-mer telomeric repeat motif (TTAG), respectively. In G. intestinalis , rRNA genes followed the telomeric repeats on both ends of four contigs, on one end of seven contigs, and were absent in two contigs with telomeric repeats, indicating variation in chromosomal arrangement. The V. necatrix genome was more repetitive than its closest relatives, with more repeats between telomeres and rRNA genes, and with variation in their presence and number. In the other major clades containing Amblyosporida and H. tvaerminnensis , the genome architecture differed even more widely. The rRNA operons were not bound to the subtelomeres and occurred in tandem with tail-to-tail orientation. Hamiltosporidium tvaerminnensis had ten rRNA operons at five locations, and G. vavrai had 14 copies at seven locations. Each pair of juxtaposed rRNA operons surrounded specific LINE repeats that were predominantly found there. G. vavrai was also found to contain the previously described telomeric repeat motif of H. tvaerminnensis (TTAGGG; Angst et al. (2023) ). From the less contiguous genome assemblies of B. daphniae and C. obtusa , we could recover no telomeric repeats and only a few to no rRNA genes. Download figure Open in new tab Figure 3: Summary of (epi)genetic features across species. Each row in the maximum likelihood phylogeny corresponds to a species and its associated (epi)genetic features. Node labels represent bootstrap values from 1,000 runs. Overall, we found limited concordance in sequence arrangement (or synteny) across the analyzed microsporidia unless they were closely related ( Figure 4 ). For example, although single-copy BUSCO genes, which are preserved due to their importance for organismal function and survival, occurred in conserved linkages across closely related species, only a few BUSCO linkage groups were shared by all core microsporidia. This was as expected due to the high degree of species divergence. Throughout the phylogeny, we found no centromeric regions based on chromosome-wide GC or repeat content, supporting hypotheses that microsporidian chromosomes might be holocentric, or their centromeres might be epigenetically defined ( Khalaf et al., 2024 ; Mascarenhas dos Santos et al., 2023 ). Download figure Open in new tab Figure 4: Ribbon diagram with maximum likelihood phylogeny showing synteny limited to closely related microsporidia. Contigs, some of which represent complete chromosomes, are represented by horizontal bars and connected by ribbons that connect the location of individual single-copy BUSCO genes across assemblies. Bold-type ribbons represent statistically conserved linkages. Because of its lower assembly contiguity, Conglomerata obtusa was omitted from the analysis. Repeat landscapes Encephalitozoon spp. have few to no repeats except at chromosome ends, which are all highly similar ( Mascarenhas dos Santos et al., 2023 ). However, as seen in Figure 1 , the genomes analyzed here showed high variation in repeat content, suggesting that repeats may play a role in shaping the evolution of microsporidian genomes. Using the Kimura substitution level, which estimates divergence from a repeat consensus sequence, we assessed repeat content and its activity over evolutionary time. High substitution levels indicate high divergence related to activity deep in the evolutionary past, and low substitution levels indicate low divergence and therefore recent activity. The largest genomes showed high repeat content and constant repeat activities throughout their past ( Figure 5 ). The three Amblyosporida species shared similar repeat activity, especially in their early past, indicative of the activity in a common ancestor. DNA and LTR transposons were highly active in all three species, but G. vavrai , and especially B. daphniae , showed higher activity in the recent past. The apparent lack of recent activity in C. obtusa might be an artefact of the low divergence repeats collapsed in this short-read assembly. Recent increases in repeats compared to earlier activity were more pronounced in species with smaller genomes, such as LINEs in G. intestinalis. These observations all indicate that different transposon families could shape the larger genomes. As species with shorter genomes had less activity in their more distant past, repeats may have only recently been expanded or removed in the shorter genomes. Download figure Open in new tab Figure 5: Repeat landscapes of microsporidia. Low Kimura substitution levels represent low divergence from the repeat consensus sequence, corresponding to recently expanded sequences, whereas high substitution levels indicate high divergence, indicating earlier activity. Genome assembly lengths are indicated in brackets. Methylation Epigenetic modifications may act to regulate not only gene expression but also repeat element activity and the associated variation in genome architecture. Encephalitozoon has hypermethylated chromosome ends with rRNA genes and hypomethylated chromosome cores with mRNA genes ( Mascarenhas dos Santos et al., 2023 ). Using a genome ontology approach based on hypergeometric tests, we compared these methylation patterns with the genomes for which we have epigenetic information. From our species with available ONT data for methylation analysis, we found that the closest Encephalitozoon relative, G. intestinalis , showed the most similar pattern: hypermethylated rRNA genes at the chromosome ends and hypomethylated mRNA genes at the chromosome cores ( Tables 2 and S3). Unlike Encephalitozoon , however, G. intestinalis had LTRs and hypermethylated LINE repeats. In the other species with available ONT data, H. tvaerminnensis , G. vavrai , and B. daphniae also had hypermethylated rRNA genes and tended to have hypermethylated transposable repeat elements like DNA, LINE, and LTR, even though their genome architectures were very different than Encephalitozoon and G. intestinalis . Non-transposable repeats, like simple repeats and low-complexity regions, were hypomethylated in all species. Coding sequences were hypomethylated in the H. tvaerminnensis genome, like in Encephalitozoon and G. intestinalis , but were hypermethylated in G. vavrai and B. daphniae . Differential methylation of coding sequences and repeat elements could indicate gene expression and repeat activity regulation, respectively. The two repeat elements that expanded most recently (LINEs in G. intestinalis and LTRs in B. daphniae ) were not consistently hyper- or hypomethylated. View this table: View inline View popup Download powerpoint Table 2: Methylation patterns of microsporidia. Overrepresented (= hypermethylated) genomic features have a negative log P- value, whereas underrepresented (= hypomethylated) genomic features have a positive log P- value. Asterisks denote levels of statistical significance obtained from genome ontology, while shading highlights directionality. Specifically, * indicates p < 0.05, ** indicates p < 0.01, and *** indicates p < 0.001. Present and absent protein domains Genome streamlining in microsporidia has resulted in the loss of protein domains that are considered essential in non-parasitic free-living fungi ( Haag et al., 2014 ; Jespersen et al., 2022 ). Using comparative genomics, we identified present and absent metabolic and functional capacities across microsporidia, looking at which functions were retained in all or most species and which were reduced. We began by summarizing the presence and absence of protein domains (Pfam)–characteristic protein families for biological pathways (Table S4). Among the nine microsporidia genomes, the extended microsporidium M. daphniae had, as expected, the most exclusive protein domains (656), even more than the shared protein domains across all nine species (444). These included mitochondrial carrier proteins (PF00153) that are characteristic of the transfer of molecules across mitochondrial membranes ( M. daphniae has a mitochondrion) but that were absent in all mitochondria-free canonical microsporidia ( Figure 6 ). Asparyl protease domains, e.g., PF13650, were among the most abundant protein domains with presence/absence polymorphism among the nine microsporidia ( Figure 6 ). These endopeptidases are known virulence factors of pathogenic fungi ( Mandujano-González et al., 2016 ). Looking at all species used in our phylogeny ( Figure 2 ), we found that the functional glycolysis characteristic Fructose-bisphosphate aldolase class-I family (PF00274) was absent in Enterocytozoon bieneusi (Table S4), consistent with previous findings that glycolysis is reduced in this species that obtains its energy directly from the host (Wiredu Boakye et al., 2017 ). Protein domains like ABC transporter (PF00005), Hsp70 (PF00012), and actin (PF00022) were present in all species (Table S4) and thus appear to be essential for microsporidia. Download figure Open in new tab Figure 6: Variably present protein domains (Pfam) ordered from most to least abundant. Rows list individual protein domains with their Pfam domain description and ID (in parentheses), while columns with a maximum likelihood phylogeny at the top list the nine species. The penultimate column tallies the number of protein domains present, while the last column provides the proportion of species in which they occur. Full data is presented in Table S4. Discussion Microsporidia are intracellular parasites that are enigmatic due to their high degree of specialization. Our goal was to better understand the evolution of their genome by producing several new high-quality genome assemblies that reveal the (epi)genetic architecture across this taxon. We focused mainly on defining which features are general for all microsporidia and which are derived in subclades. GC-content, genome length, chromosomal sequence arrangement, and methylation patterns vary widely among microsporidian clades; however, species that share a more recent common ancestor tend to exhibit less variation in these features, similar to other systems with high-quality genomes available for study. The architecture of microsporidia genomes studied here were only similar to the previously described Encephalitozoon in one close relative and in a species of the next closest major microsporidian clade, proving that Encephalitozoon ’s chromosomal sequence arrangement is not general to all microsporidia, as has been speculated ( Brugère et al., 2000 ). Our other studied species showed very diverse chromosomal arrangements and repeat contents, although the same genetic features tend to be hyper- or hypomethylated in all species. For example, rRNA gene positions are different among all microsporidian clades, but always hypermethylated in all species. Because the new and improved microsporidia genome assemblies presented here are all from species that infect the aquatic crustacean Daphnia, we can see that the variation in genome architecture is not explained by the host: indeed, the host’s role in parasite genome architecture appears to be minor. As models, thus, Daphnia and its microsporidian parasites from across the phylum allow us to extend microsporidia research and improve our understanding of genome evolution in these extreme parasites beyond the mammal-parasite model. Nucleotide composition linked to genome size Nucleotide composition is fundamental to genome architecture, and although GC-content varies widely across all lifeforms, it tends to evolve to lower values in parasites such as the microsporidia. Reduced recombination rates, diminished DNA repair mechanisms, relaxed purifying selection, and increased selection for AT mutations have all been proposed as reasons for reduced GC in parasite genomes ( Videvall, 2018 ). These mechanisms may play a role in the negative correlation observed here between GC-content and repeat content, which is also seen in fungi and other related phyla ( Elliott & Gregory, 2015 ). First, it might be easier for repeat elements to proliferate in species with relaxed purifying selection due to the small effective population size relative to the mode of transmission ( Haag et al., 2020 ). We expect species with a small effective population size to have more and more recent expansions of repeat elements due to vertical transmission compared to species with a higher effective population size and horizontal-only transmission ( de Albuquerque et al., 2020 ). With our sample, it is hard to draw conclusions on demographic effects; however, long genome Amblyosporida and Nosema/Vairimorpha clade species are known for complex life cycles with mixed-mode transmission ( Vávra et al., 2018 ; Xiong et al., 2023 ), and mixed-mode transmission in the large genome microsporidium H. tvaerminnensis has been associated with small effective population sizes ( Haag et al., 2020 ). Contrarily, species with small genomes are only transmitted horizontally. Second, AT mutations might accumulate in proliferating repeat elements, directly and indirectly accelerating the decrease in GC-content. This occurs indirectly if 5mC methylation is used to slow the proliferation of repeat elements because fewer positions are available for this epigenetic modification. In contrast, GC-richer repeats might be more of a methylation target, possibly constraining their proliferation. Although repeat elements were hypermethylated across species, repeat activity was more evenly distributed across time in lower GC species than in higher GC species, where activity occurred mainly in the recent past. This could be because higher GC species have more stringent selection against repeat proliferation, more efficient mechanisms to remove repeats, higher recombination rates, or lower tendency for AT mutation, such that our methodology estimates higher recent repeat activity because of the lower divergence among them. Distribution of rRNA genes The rRNA genes are of special interest in microsporidia genome architecture, mainly because of their unusual location in Encephalitozoon close to each chromosome end, at the subtelomeres ( Mascarenhas dos Santos et al., 2023 ). Contrary to previous findings from a short-read-based draft genome ( Mascarenhas dos Santos et al., 2023 ; Pombert et al., 2015 ), we show that O. colligata shares this structure with its close Encephalitozoon relatives. This highlights the use of high-quality resources to study genome architecture. rRNA genes are also located at some, but not all, of the subtelomeres in a species of the next closely related major clade, G. intestinalis, which also shows small-scale rRNA gene rearrangements ( Refardt & Mouton, 2007 ). Given that transposable elements (TEs) show high and recent activity in G. intestinalis , that rRNA genes and TEs are co-located, and that TEs interact with and benefit from each other ( Garcia et al., 2024 ), we suggest that rRNA genes and TEs may coevolve together in this microsporidium or even across microsporidia, a hypothesis supported also by our finding that rRNA genes and TEs are co-located in H. tvaerminnensis and Amblyosporida microsporidia. Moreover, rRNA genes in these species have yet another outstanding arrangement: rRNA operons occur in tandem with tail-to-tail orientation and few LINE or unknown repeats between them. These rRNA operon pairs are not located close to a chromosome end, however, suggesting that the proximity of rRNA genes to chromosome ends is a derived characteristic found in some species of the Nosematida and Enterozytozoonida clades. Co-occurrence and epigenetic modification of repeat elements The significance of methylation is unclear in microsporidia. Mascarenhas dos Santos et al. (2023) have speculated that methylation at rRNA genes facilitates heterochromatin formation, helping to silence the ribosomal machinery during phases of the life cycle that have low or no access to energy. Indeed, we found rRNA genes to be hypermethylated in all the species studied, regardless of their location. The hypothesis proposed by Mascarenhas dos Santos et al. (2023) could also apply to other genetic loci, such as TEs, which because their activity may be unfavorable, are silenced by epigenetic modifications that facilitate heterochromatin formation. Whereas small microsporidia genomes have low to no repeats, including TEs, and hypomethylated cores, larger genomes might show methylation at repeat loci across the genome to reduce TE activity through heterochromatin formation. Given that rRNA genes and transposable elements co-occur in the studied microsporidia, hypermethylation could help to simultaneously control their activity and spread. At the same time, their co-occurrence might be beneficial to the TEs, which might be more likely to proliferate or less likely to be removed if they occur close to the rRNA genes, which are highly expressed. The microsporidia V. necatrix and Nosema muscidifuracis from the same clade as Encephalitozoon and Ordospora have more randomly distributed rRNA operons (and N. muscidifuracis has many more), while both have much lower whole-genome GC-content than their relatives ( Xiong et al., 2023 ). A telomere-to-telomere assembly of the N. muscidifuracis genome would help pin down rRNA gene location and methylation data for the two species to clarify the role of epigenetic modification in the evolution of microsporidia repeat families. Neither epigenetic, nucleotide, nor sequence composition has indicated the location of centromeres in the species studied here. Hi-C sequencing could help identify centromeres ( Khalaf et al., 2024 ). Conclusion Microsporidia have attracted much attention because of their parasitic life history and because they include some of the smallest known eukaryote genomes. However, their genomes also exhibit drastic variation in size and other features. Here we present high-quality genome assemblies from across the major microsporidia clades, showing covariance in GC-content, chromosomal sequence arrangement, and epigenetic modification. Species with high GC-content have a sequence arrangement similar to Encephailtozoon spp., with hypermethylated subtelomeres and hypomethylated cores. In contrast, low-GC species do not share this pattern, having instead a higher activity of repeat elements, which have lower GC-content than coding sequences, likely because the latter are under purifying selection ( Videvall, 2018 ). Low-GC genomes might arise due to a lowered selection regime that allow transposable repeats to proliferate more easily ( de Albuquerque et al., 2020 ; Videvall, 2018 ). The evolutionary dynamics leading to the discrepancy between relatively strong selection on coding sequences and weak selection outside of them remain unknown. Still, the activity of repeat elements clearly shapes the evolution of genome architecture, and with the recent advent of high-throughput sequencing technologies should thus be included in comparative studies of GC-content where it was previously not. Although the streamlining of genomes has led to a significantly fewer coding sequences across all core microsporidia (Žárský et al., 2023), certain species show extraordinary genome reductions, like the partial absence of glycolysis genes in Enterocytozoon spp. (Wiredu Boakye et al., 2017 ). Here, we provide an overview of the presence and absence of protein domains across microsporidia as a resource for studies focused on the presence/absence polymorphism and functional adaptations to parasitism across the microsporidia clades. Knowing the phylogenetic distribution of protein domains and other genomic features in the microsporidia allows us to dive deeper into the evolution of this extraordinary group of parasites. Features that are conserved by all microsporidia may have contributed to the radiation of this group, with the loss of typical mitochondria being the hallmark example. In contrast, features present only in individual microsporidian clades or species may have been important in evolving adaptations to specific hosts or life histories. Furthermore, correlations between the presence of certain genomic features and life history traits can shed light on the evolutionary drivers of these traits. Thus, the presence or absence of protein domains and other genomic features can be the starting point for in-depth comparative study of the microsporidia and their genomic architecture with these high-quality genomes. As a final step for obtaining telomere-to-telomere assemblies, especially the harder-to-assemble longer genomes, we suggest applying Hi-C sequencing to microsporidia. Methods Samples Using long wide-mouth pipettes, we collected Daphnia pulex infected with C. obtusa from the Tvaerminne archipelago, Finland (59°49’55.4", N 23°15’17.6" E), placed them in RNAlater (Ambion, Glasgow, United Kingdom), and kept them refrigerated until DNA isolation. Daphnia pulex infected with G. vavrai were collected from Aegelsee lake near Frauenfeld, Switzerland (47°33′28.0″ N, 8°51′46.0″ E) and were transported to the laboratory for DNA isolation. Daphnia magna infected with B. daphniae (ID: BE-OM-3), G. intestinalis (KZ-23-1), and O. colligata (GB-LK1-1) were previously collected and kept in the lab as iso-female lines (Angst et al., in prep.; Pombert et al., 2015 ; Refardt et al., 2008 ) until DNA isolation. We obtained high-molecular-weight DNA from Daphnia with parasites using the GenePure DNA Isolation Kit (QIAGEN, Hilden, Germany) as described in Angst et al. (in review) ( https://dx.doi.org/10.17504/protocols.io.5jyl82n96l2w/v1 ; Angst & Fields (2024) ). Illumina paired-end sequencing and either PacBio HiFi (Pacific Biosciences high fidelity) or ONT (Oxford Nanopore Technologies) sequencing was used to obtain the highest quality nucleotide or modification calls, respectively. Illumina libraries were prepared using Kapa PCR-free kits and sequenced by the Quantitative Genomics Facility service platform at the Department of Biosystem Science and Engineering (D-BSSE, ETH) Basel, Switzerland, on an Illumina HiSeq 6000 sequencer. PacBio SMRTbell libraries were prepared and sequenced on a PacBio Revio at the Lausanne Genomics Technologies Facility (GTF, UNIL), Switzerland. We prepared ONT libraries with the SQK-LSK110 ligation kit and sequenced them using a MinION device with a Spot-ON Flow Cell (R9.4.1). Additionally, we downloaded genomic data of E. intestinalis (NCBI database; Assembly name: ASM2439929v1; GenBank assembly accession: GCA_024399295.1; SRA accession: SRR17865590; Bioproject accession: PRJNA594722; Mascarenhas dos Santos et al. 2023 ) H. tvaerminnensis (NCBI database; Assembly name: FIOER33 v3; GenBank assembly accession: GCA_022605425.2; SRA accession: SRR24575619, Bioproject accession: PRJNA778105; Angst et al. 2023 ), M. daphniae (NCBI database; Bioproject accession: PRJNA1199805; Angst et al. (in prep.)), and V. necatrix (NCBI database; Assembly name: ASM3663032v1; GenBank assembly accession: GCF_036630325.1; Bioproject accession: PRJNA909071; Svedberg et al. 2024 ) for analysis. Assembly Glugoides intestinalis and O. colligata Glugoides intestinalis (total/average read length: 79.38 Gb/10.75 Kb) and O. colligata (20.22 Gb/8.84 Kb) were sequenced using PacBio HiFi sequencing to an average sequencing coverage of 55× and 45×, respectively. We used hifiasm v.0.19.8-r603 ( Cheng et al., 2021 ) to assemble the obtained sequencing reads with default parameters for G. intestinalis and with --hom-cov 45 -l1 --n-hap 1 parameters for O. colligata . Additionally, we generated a second hifiasm assembly for both species after excluding host-specific PacBio HiFi reads using SAMtools v.1.7 ( Danecek et al., 2021 ) that were identified by mapping them to the D. magna genome (NCBI database; Assembly name: ASM4014379v1; GenBank assembly accession: GCA_040143795.1; BioProject ID: PRJNA624896; Cornetti et al. 2024 ) using minimap2 v.2.20-r1061 (H. Li, 2018 ). For each species, we aligned the two assemblies using minimap2 and merged them manually. We assessed the quality and completeness of the assemblies using QUAST v.5.0.2 ( Gurevich et al., 2013 ) and BUSCO v.5.5.0 ( Manni et al., 2021 ) with the microsporidia_odb10 database (Creation date: 2020-08-05). All software was used with default parameters unless stated otherwise. Binucleata daphniae and G. vavrai We sequenced B. daphniae (total/N50: 0.72 Gb/7.21 Kb) and G. vavrai (3.96 Gb/3.53 Kb) using ONT sequencing in adaptive mode, depleting for sequences homologous to the D. magna and the D. pulex genome (NCBI database; Assembly name: PA42 4.2; GenBank assembly accession: GCA_911175335.1; BioProject ID: PRJEB46221; Ye et al. 2021 ), respectively. We used bonito v.0.5.3 ( https://github.com/nanoporetech/bonito ) to base-call ONT sequencing reads with the [email protected] model. For the B. daphniae genome assembly, we used MaSuRCA v.4.0.5 ( Zimin et al., 2017 ) with ONT (53×) and Illumina (639×) sequencing reads, excluding host-specific, adaptor, and low-quality sequences using minimap2, bwa-mem2 mem v.2.2.1 ( Vasimuddin et al., 2019 ), SAMtools, and fastp v.0.23.2 ( Chen, 2023 ) with -q 30 and -l 100 parameters. Haplotigs were purged twice from the assembly using the Purge Haplotigs pipeline v.1.1.2 ( Roach et al., 2018 ) with -l 125 -m 220 -h 400 parameters and BEDTools v.2.30.0 ( Quinlan, 2014 ) for generating the read-depth distribution. For the G. vavrai genome assembly, we used nextDenovo v.2.5.0 ( Hu et al., 2024 ) with ONT sequencing reads (98×) and polished the resulting assembly with Illumina sequencing reads (458×) using nextPolish v.1.4.1 ( Hu et al., 2020 ), Medaka v.1.7.2 ( https://github.com/nanoporetech/medaka ) and Pilon v.1.24 ( Walker et al., 2014 ). The Purge Haplotigs pipeline was applied with -l 88 -m 176 -h 300 parameters. Conglomerata obtusa Because we were unable to generate sufficient quality genomic material to conduct long-read sequencing for C. obtusa , we used Illumina sequencing (153×) for this case only. We excluded sequencing reads mapping to the D. pulex host genome and assembled the remaining reads using megahit v.1.2.9 (D. Li et al., 2016 ). We excluded contigs with less than a third of the average coverage, shorter than 500 basepairs, with GC-content above 33, or with coverage over 1× for a Daphnia sample from a parasite-free pond of the same island (NCBI database; SRA accession: SRR26394761, Bioproject ID: PRJNA862292; Angst et al. 2024 ) using seqtk v.1.3 ( https://github.com/lh3/seqtk ) and BBMap v.38.96 ( Bushnell, 2014 ). Genome annotation and phylogenetic inference We annotated de novo genome assemblies as described in Angst et al. (in prep.) using funannotate v.1.8.14 ( Palmer & Stajich, 2022 ) and associated software for gene prediction and functional annotation ( Almagro Armenteros et al., 2019 ; Brůna et al., 2020 ; Cantalapiedra et al., 2021 ; Frith, 2011 ; Haas et al., 2008 ; Huerta-Cepas et al., 2019 ; Jones et al., 2014 ; Käll et al., 2004 ; Korf, 2004 ; Majoros et al., 2004 ; Seppey et al., 2019 ; Stanke et al., 2006 , 2008 ). For phylogenetic inference, we downloaded genomes from a broad range of microsporidia ( Aurrecoechea et al., 2017 ) including the extended microsporidium P. saccamoebae ( Quandt et al., 2017 ) along with Rozella allomycis ( James et al., 2013 ) as an outgroup. We identified single-copy orthologs among the species using proteinortho v.6.3.0 ( Klemm et al., 2023 ), concatenated them, aligned the individual genes as well as the concatenated genes using MAFFT v.7.508 ( Katoh et al., 2002 ; Katoh & Standley, 2013 ), and trimmed the alignments using trimAl v.1.4.rev15 ( Capella-Gutiérrez et al., 2009 ) with the -automated1 flag. We inferred a maximum likelihood species tree from the concatenated sequences using IQ-TREE 2 v.2.2.0 ( Minh et al., 2020 ) and a weighted phylogeny from the individual maximum likelihood gene trees using Weighted ASTRAL v.1.19.3.7 ( Zhang & Mirarab, 2022 ) with - r 16 -s 16 -x 100 -n 0 parameters separately for all species and the nine main study species. Comparative genomics and genome ontology We looked for homology and synteny across genomes using odp v.0.3.3 ( Schultz et al., 2023 ). Specifically, we used the coordinates of the identified BUSCO genes to infer ancestral BUSCO gene linkage groups, test for conserved linkages among genomes, and create the ribbon diagram. To obtain modified base calls from ONT sequencing reads, we used megalodon v.2.5.0 ( https://nanoporetech.github.io/megalodon ) focusing on 5mC modifications for downstream analyses. We tested whether genomic annotations, including mRNA genes, rRNA genes, and different repeat types, were enriched with methylation sites by using the genome ontology peak annotation enrichment in homer v.5.1 ( Heinz et al., 2010 ). This analysis considered sites to be methylated if read depth was above 3× and percent modified reads over 50 %. The inclusion of multiple cell stages in our DNA isolation protocol explains, at least in part, variation in epigenetic modification between sequencing reads. For example, spores might have a different methylation pattern than sporonts, meronts, or other life stages ( Mascarenhas dos Santos et al., 2023 ). For G. intestinalis , we re-used ONT reads from Angst et al. (in prep.) (NCBI database; SRA accession: SRR31799445, Bioproject accession: PRJNA1199805). We identified repeats using RepeatModeler v.2.0.2, including the LTR pipeline ( Flynn et al., 2020 ), and ReapeatMasker v.4.1.2 ( Smit et al., 2013 ), and separately identified rRNA genes using cmscan of the Infernal pipeline v.1.1.2 ( Nawrocki & Eddy, 2013 ). From the ReapeatMasker alignments, we created repeat landscapes using ReapeatMasker utils calcDivergenceFromAlign.pl and createRepeatLandscape.pl. Finally, we summarized PFAM domains to identify the presence and absence of protein domains across all species using the module compare of funannotate, and the tidyverse 2.0.0 ( Wickham et al., 2019 ) R v.4.4.1 ( R Core Team, 2024 ) package for representation and statistics. Data availability Raw data are deposited in the NCBI SRA database, and the assembled genome plus the predicted protein sequences are available in the NCBI GenBank (BioProject ID: PRJNA1199946). Funding This work was supported by the Swiss National Science Foundation (SNSF) (grant numbers 310030_188887 and 310030_219529 to D.E.). Conflicts of interest None declared. Acknowledgments We thank Ju rgen Hottinger, Michelle Krebs, and Urs Stiefel for their help in the laboratory and all members of the Ebert group for providing feedback on the study and the manuscript. Alix Thivolle extracted DNA from D. pulex infected with C. obtusa . Christina Tadiri collected D. pulex infected with G. vavrai . Calculations were performed at sciCORE ( http://scicore.unibas.ch/ ) scientific computing center at the University of Basel. Suzanne Zweizig improved the language of the text. Funder Information Declared Swiss National Science Foundation , 310030_188887 and 310030_219529 Footnotes Added new figure summarizing (epi)genetic features across species. References ↵ Almagro Armenteros , J. J. , Tsirigos , K. D. , Sønderby , C. K. , Petersen , T. N. , Winther , O. , Brunak , S. , von Heijne , G. , & Nielsen , H. ( 2019 ). SignalP 5.0 improves signal peptide predictions using deep neural networks . Nature Biotechnology , 37 ( 4 ), Article 4. doi: 10.1038/s41587-019-0036-z OpenUrl CrossRef ↵ Angst , P. , & Fields , P. D . ( 2024 ). DNA-extraction of Daphnia and symbionts . Protocols.Io . doi: 10.17504/protocols.io.5jyl82n96l2w/v1 OpenUrl CrossRef ↵ Angst , P. , Haag , C. R. , Ben-Ami , F. , Fields , P. D. , & Ebert , D . ( 2024 ). Genome-wide allele frequency changes reveal that dynamic metapopulations evolve differently . Molecular Biology and Evolution , 41 ( 7 ), msae128 . doi: 10.1093/molbev/msae128 OpenUrl CrossRef PubMed ↵ Angst , P. , Pombert , J.-F. , Ebert , D. , & Fields , P. D . ( 2023 ). Near chromosome–level genome assembly of the microsporidium Hamiltosporidium tvaerminnensis . G3 Genes|Genomes|Genetics , jkad185 . doi: 10.1093/g3journal/jkad185 OpenUrl CrossRef Angst , P. , Thivolle , A. , Haden , Z. , Wale , N. , & Ebert , D . (in review). Genomic analysis of the zooplankton-associated pathogenic bacterium Spirobacillus cienkowskii reveals its functional and metabolic capacities . Angst , P. , Thivolle , A. , Krebs , M. , Galimov , Y. , Fields , P. D. , & Ebert , D. (in prep.). Phenotypic and molecular convergent evolution of microsporidia infecting host gut epithelium . ↵ Aurrecoechea , C. , Barreto , A. , Basenko , E. Y. , Brestelli , J. , Brunk , B. P. , Cade , S. , Crouch , K. , Doherty , R. , Falke , D. , Fischer , S. , Gajria , B. , Harb , O. S. , Heiges , M. , Hertz-Fowler , C. , Hu , S. , Iodice , J. , Kissinger , J. C. , Lawrence , C. , Li , W. , … Zheng , J . ( 2017 ). EuPathDB: The eukaryotic pathogen genomics database resource . Nucleic Acids Research , 45 ( Database issue ), D581 – D591 . doi: 10.1093/nar/gkw1105 OpenUrl CrossRef PubMed ↵ Bojko , J. , Reinke , A. W. , Stentiford , G. D. , Williams , B. , Rogers , M. S. J. , & Bass , D . ( 2022 ). Microsporidia: A new taxonomic, evolutionary, and ecological synthesis . Trends in Parasitology , 38 ( 8 ), 642 – 659 . doi: 10.1016/j.pt.2022.05.007 OpenUrl CrossRef ↵ Bojko , J. , & Stentiford , G. D. ( 2022 ). Microsporidian pathogens of aquatic animals . In L. M. Weiss & A. W. Reinke (Eds.), Microsporidia: Current Advances in Biology (pp. 247 – 283 ). Springer International Publishing . doi: 10.1007/978-3-030-93306-7_10 OpenUrl CrossRef ↵ Brugère , J.-F. , Cornillot , E. , Méténier , G. , Bensimon , A. , & Vivarès , C. P . ( 2000 ). Encephalitozoon cuniculi (Microspora) genome: Physical map and evidence for telomere-associated rDNA units on all chromosomes . Nucleic Acids Research , 28 ( 10 ), 2026 – 2033 . OpenUrl CrossRef PubMed Web of Science ↵ Brůna , T. , Lomsadze , A. , & Borodovsky , M . ( 2020 ). GeneMark-EP+: Eukaryotic gene prediction with self-training in the space of genes and proteins . NAR Genomics and Bioinformatics , 2 ( 2 ), lqaa026 . doi: 10.1093/nargab/lqaa026 OpenUrl CrossRef PubMed ↵ Bushnell , B. ( 2014 ). BBMap: A Fast, Accurate, Splice-Aware Aligner (No. LBNL-7065E) . Lawrence Berkeley National Lab. (LBNL) , Berkeley , CA (United States). https://www.osti.gov/biblio/1241166-bbmap-fast-accurate-splice-aware-aligner ↵ Cantalapiedra , C. P. , Hernández-Plaza , A. , Letunic , I. , Bork , P. , & Huerta-Cepas , J . ( 2021 ). eggNOG-mapper v2: Functional annotation, orthology assignments, and domain prediction at the metagenomic scale . Molecular Biology and Evolution , 38 ( 12 ), 5825 – 5829 . doi: 10.1093/molbev/msab293 OpenUrl CrossRef PubMed ↵ Capella-Gutiérrez , S. , Silla-Martínez , J. M. , & Gabaldón , T . ( 2009 ). trimAl: A tool for automated alignment trimming in large-scale phylogenetic analyses . Bioinformatics , 25 ( 15 ), 1972 – 1973 . doi: 10.1093/bioinformatics/btp348 OpenUrl CrossRef PubMed Web of Science ↵ Chen , S . ( 2023 ). Ultrafast one-pass FASTQ data preprocessing, quality control, and deduplication using fastp . iMeta , 2 ( 2 ), e107 . doi: 10.1002/imt2.107 OpenUrl CrossRef ↵ Cheng , H. , Concepcion , G. T. , Feng , X. , Zhang , H. , & Li , H . ( 2021 ). Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm . Nature Methods , 18 ( 2 ), Article 2. doi: 10.1038/s41592-020-01056-5 OpenUrl CrossRef ↵ Cornetti , L. , Fields , P. D. , Du Pasquier , L. , & Ebert , D. ( 2024 ). Long-term balancing selection for pathogen resistance maintains trans-species polymorphisms in a planktonic crustacean . Nature Communications , 15 ( 1 ), 5333 . doi: 10.1038/s41467-024-49726-8 OpenUrl CrossRef ↵ Corradi , N. , & Slamovits , C. H . ( 2011 ). The intriguing nature of microsporidian genomes . Briefings in Functional Genomics , 10 ( 3 ), 115 – 124 . doi: 10.1093/bfgp/elq032 OpenUrl CrossRef PubMed Web of Science ↵ Danecek , P. , Bonfield , J. K. , Liddle , J. , Marshall , J. , Ohan , V. , Pollard , M. O. , Whitwham , A. , Keane , T. , McCarthy , S. A. , Davies , R. M. , & Li , H . ( 2021 ). Twelve years of SAMtools and BCFtools . GigaScience , 10 ( 2 ), giab008 . doi: 10.1093/gigascience/giab008 OpenUrl CrossRef PubMed ↵ de Albuquerque , N. R. M. , Ebert , D. , & Haag , K. L. ( 2020 ). Transposable element abundance correlates with mode of transmission in microsporidian parasites . Mobile DNA , 11 , 19 . doi: 10.1186/s13100-020-00218-8 OpenUrl CrossRef PubMed ↵ Ebert , D . ( 2008 ). Host–parasite coevolution: Insights from the Daphnia –parasite model system . Current Opinion in Microbiology , 11 ( 3 ), 290 – 301 . doi: 10.1016/j.mib.2008.05.012 OpenUrl CrossRef PubMed Web of Science ↵ Elliott , T. A. , & Gregory , T. R . ( 2015 ). What’s in a genome? The C-value enigma and the evolution of eukaryotic genome content . Philosophical Transactions of the Royal Society B: Biological Sciences , 370 ( 1678 ), 20140331 . doi: 10.1098/rstb.2014.0331 OpenUrl CrossRef PubMed ↵ Flynn , J. M. , Hubley , R. , Goubert , C. , Rosen , J. , Clark , A. G. , Feschotte , C. , & Smit , A. F . ( 2020 ). RepeatModeler2 for automated genomic discovery of transposable element families . Proceedings of the National Academy of Sciences , 117 ( 17 ), 9451 – 9457 . doi: 10.1073/pnas.1921046117 OpenUrl Abstract / FREE Full Text ↵ Frith , M. C . ( 2011 ). A new repeat-masking method enables specific detection of homologous sequences . Nucleic Acids Research , 39 ( 4 ), e23 . doi: 10.1093/nar/gkq1212 OpenUrl CrossRef PubMed ↵ Garcia , S. , Kovarik , A. , Maiwald , S. , Mann , L. , Schmidt , N. , Pascual-Díaz , J. P. , Vitales , D. , Weber , B. , & Heitkam , T . ( 2024 ). The dynamic interplay between ribosomal DNA and transposable elements: A perspective from genomics and cytogenetics . Molecular Biology and Evolution , 41 ( 3 ), msae025 . doi: 10.1093/molbev/msae025 OpenUrl CrossRef PubMed ↵ Gurevich , A. , Saveliev , V. , Vyahhi , N. , & Tesler , G . ( 2013 ). QUAST: Quality assessment tool for genome assemblies. Bioinformatics (Oxford , England ) , 29 ( 8 ), 1072 – 1075 . doi: 10.1093/bioinformatics/btt086 OpenUrl CrossRef PubMed Web of Science ↵ Haag , K. L. , James , T. Y. , Pombert , J.-F. , Larsson , R. , Schaer , T. M. M. , Refardt , D. , & Ebert , D . ( 2014 ). Evolution of a morphological novelty occurred before genome compaction in a lineage of extreme parasites . Proceedings of the National Academy of Sciences , 111 ( 43 ), 15480 – 15485 . doi: 10.1073/pnas.1410442111 OpenUrl Abstract / FREE Full Text ↵ Haag , K. L. , Pombert , J.-F. , Sun , Y. , de Albuquerque , N. R. M. , Batliner , B. , Fields , P. , Lopes , T. F. , & Ebert , D. ( 2020 ). Microsporidia with vertical transmission were likely shaped by nonadaptive processes . Genome Biology and Evolution , 12 ( 1 ), 3599 – 3614 . doi: 10.1093/gbe/evz270 OpenUrl CrossRef PubMed ↵ Haas , B. J. , Salzberg , S. L. , Zhu , W. , Pertea , M. , Allen , J. E. , Orvis , J. , White , O. , Buell , C. R. , & Wortman , J. R . ( 2008 ). Automated eukaryotic gene structure annotation using EVidenceModeler and the program to assemble spliced alignments . Genome Biology , 9 ( 1 ), R7 . doi: 10.1186/gb-2008-9-1-r7 OpenUrl CrossRef PubMed ↵ Heinz , S. , Benner , C. , Spann , N. , Bertolino , E. , Lin , Y. C. , Laslo , P. , Cheng , J. X. , Murre , C. , Singh , H. , & Glass , C. K . ( 2010 ). Simple combinations of lineage-determining transcription factors prime cis -regulatory elements required for macrophage and B cell identities . Molecular Cell , 38 ( 4 ), 576 – 589 . doi: 10.1016/j.molcel.2010.05.004 OpenUrl CrossRef PubMed Web of Science ↵ Hu , J. , Fan , J. , Sun , Z. , & Liu , S . ( 2020 ). NextPolish: A fast and efficient genome polishing tool for long-read assembly . Bioinformatics , 36 ( 7 ), 2253 – 2255 . doi: 10.1093/bioinformatics/btz891 OpenUrl CrossRef ↵ Hu , J. , Wang , Z. , Sun , Z. , Hu , B. , Ayoola , A. O. , Liang , F. , Li , J. , Sandoval , J. R. , Cooper , D. N. , Ye , K. , Ruan , J. , Xiao , C.-L. , Wang , D. , Wu , D.-D. , & Wang , S . ( 2024 ). NextDenovo: An efficient error correction and accurate assembly tool for noisy long reads . Genome Biology , 25 ( 1 ), 107 . doi: 10.1186/s13059-024-03252-4 OpenUrl CrossRef PubMed ↵ Huerta-Cepas , J. , Szklarczyk , D. , Heller , D. , Hernández-Plaza , A. , Forslund , S. K. , Cook , H. , Mende , D. R. , Letunic , I. , Rattei , T. , Jensen , L. J. , von Mering , C. , & Bork , P. ( 2019 ). eggNOG 5.0: A hierarchical, functionally and phylogenetically annotated orthology resource based on 5090 organisms and 2502 viruses . Nucleic Acids Research , 47 ( D1 ), D309 – D314 . doi: 10.1093/nar/gky1085 OpenUrl CrossRef PubMed ↵ James , T. Y. , Pelin , A. , Bonen , L. , Ahrendt , S. , Sain , D. , Corradi , N. , & Stajich , J. E . ( 2013 ). Shared signatures of parasitism and phylogenomics unite Cryptomycota and microsporidia . Current Biology: CB , 23 ( 16 ), 1548 – 1553 . doi: 10.1016/j.cub.2013.06.057 OpenUrl CrossRef PubMed ↵ Jespersen , N. , Monrroy , L. , & Barandun , J. ( 2022 ). Impact of genome reduction in microsporidia . In L. M. Weiss & A. W. Reinke (Eds.), Microsporidia: Current Advances in Biology (pp. 1 – 42 ). Springer International Publishing . doi: 10.1007/978-3-030-93306-7_1 OpenUrl CrossRef ↵ Jones , P. , Binns , D. , Chang , H.-Y. , Fraser , M. , Li , W. , McAnulla , C. , McWilliam , H. , Maslen , J. , Mitchell , A. , Nuka , G. , Pesseat , S. , Quinn , A. F. , Sangrador-Vegas , A. , Scheremetjew , M. , Yong , S.-Y. , Lopez , R. , & Hunter , S . ( 2014 ). InterProScan 5: Genome-scale protein function classification . Bioinformatics , 30 ( 9 ), 1236 – 1240 . doi: 10.1093/bioinformatics/btu031 OpenUrl CrossRef PubMed Web of Science ↵ Käll , L. , Krogh , A. , & Sonnhammer , E. L. L . ( 2004 ). A combined transmembrane topology and signal peptide prediction method . Journal of Molecular Biology , 338 ( 5 ), 1027 – 1036 . doi: 10.1016/j.jmb.2004.03.016 OpenUrl CrossRef PubMed Web of Science ↵ Katoh , K. , Misawa , K. , Kuma , K. , & Miyata , T . ( 2002 ). MAFFT: A novel method for rapid multiple sequence alignment based on fast Fourier transform . Nucleic Acids Research , 30 ( 14 ), 3059 – 3066 . doi: 10.1093/nar/gkf436 OpenUrl CrossRef PubMed Web of Science ↵ Katoh , K. , & Standley , D. M . ( 2013 ). MAFFT Multiple Sequence Alignment Software Version 7: Improvements in Performance and Usability . Molecular Biology and Evolution , 30 ( 4 ), 772 – 780 . doi: 10.1093/molbev/mst010 OpenUrl CrossRef PubMed Web of Science ↵ Khalaf , A. , Francis , O. , & Blaxter , M. L . ( 2024 ). Genome evolution in intracellular parasites: Microsporidia and Apicomplexa. Journal of Eukaryotic Microbiology , e 13033 . doi: 10.1111/jeu.13033 OpenUrl CrossRef ↵ Klemm , P. , Stadler , P. F. , & Lechner , M . ( 2023 ). Proteinortho6: Pseudo-reciprocal best alignment heuristic for graph-based detection of (co-)orthologs . Frontiers in Bioinformatics , 3 . doi: 10.3389/fbinf.2023.1322477 OpenUrl CrossRef ↵ Korf , I . ( 2004 ). Gene finding in novel genomes . BMC Bioinformatics , 5 ( 1 ), 59 . doi: 10.1186/1471-2105-5-59 OpenUrl CrossRef PubMed ↵ Li , D. , Luo , R. , Liu , C.-M. , Leung , C.-M. , Ting , H.-F. , Sadakane , K. , Yamashita , H. , & Lam , T.-W . ( 2016 ). MEGAHIT v1.0: A fast and scalable metagenome assembler driven by advanced methodologies and community practices . Methods , 102 , 3 – 11 . doi: 10.1016/j.ymeth.2016.02.020 OpenUrl CrossRef PubMed ↵ Li , H . ( 2018 ). Minimap2: Pairwise alignment for nucleotide sequences . Bioinformatics , 34 ( 18 ), 3094 – 3100 . doi: 10.1093/bioinformatics/bty191 OpenUrl CrossRef PubMed ↵ Majoros , W. H. , Pertea , M. , & Salzberg , S. L . ( 2004 ). TigrScan and GlimmerHMM: Two open source ab initio eukaryotic gene-finders . Bioinformatics , 20 ( 16 ), 2878 – 2879 . doi: 10.1093/bioinformatics/bth315 OpenUrl CrossRef PubMed Web of Science ↵ Mandujano-González , V. , Villa-Tanaca , L. , Anducho-Reyes , M. A. , & Mercado-Flores , Y . ( 2016 ). Secreted fungal aspartic proteases: A review . Revista Iberoamericana de Micología , 33 ( 2 ), 76 – 82 . doi: 10.1016/j.riam.2015.10.003 OpenUrl CrossRef PubMed ↵ Manni , M. , Berkeley , M. R. , Seppey , M. , Simão , F. A. , & Zdobnov , E. M . ( 2021 ). BUSCO update: Novel and streamlined workflows along with broader and deeper phylogenetic coverage for scoring of eukaryotic, prokaryotic, and viral genomes . Molecular Biology and Evolution , 38 ( 10 ), 4647 – 4654 . doi: 10.1093/molbev/msab199 OpenUrl CrossRef PubMed ↵ Mascarenhas dos Santos , A. C. , Julian , A. T. , Liang , P. , Juárez , O. , & Pombert , J.-F. ( 2023 ). Telomere-to-Telomere genome assemblies of human-infecting Encephalitozoon species . BMC Genomics , 24 ( 1 ), 237 . doi: 10.1186/s12864-023-09331-3 OpenUrl CrossRef PubMed ↵ Minh , B. Q. , Schmidt , H. A. , Chernomor , O. , Schrempf , D. , Woodhams , M. D. , von Haeseler , A. , & Lanfear , R. ( 2020 ). IQ-TREE 2: New Models and Efficient Methods for Phylogenetic Inference in the Genomic Era . Molecular Biology and Evolution , 37 ( 5 ), 1530 – 1534 . doi: 10.1093/molbev/msaa015 OpenUrl CrossRef PubMed ↵ Nakjang , S. , Williams , T. A. , Heinz , E. , Watson , A. K. , Foster , P. G. , Sendra , K. M. , Heaps , S. E. , Hirt , R. P. , & Embley , T. M . ( 2013 ). Reduction and expansion in microsporidian genome evolution: New insights from comparative genomics . Genome Biology and Evolution , 5 ( 12 ), 2285 – 2303 . doi: 10.1093/gbe/evt184 OpenUrl CrossRef PubMed ↵ Nawrocki , E. P. , & Eddy , S. R . ( 2013 ). Infernal 1.1: 100-fold faster RNA homology searches . Bioinformatics , 29 ( 22 ), 2933 – 2935 . doi: 10.1093/bioinformatics/btt509 OpenUrl CrossRef PubMed Web of Science ↵ Palmer , J. , & Stajich , J. ( 2022 ). nextgenusfs/funannotate: Funannotate (Version 1.8.11) [Computer software] . Zenodo . https://zenodo.org/record/2604804 ↵ Parisot , N. , Pelin , A. , Gasc , C. , Polonais , V. , Belkorchia , A. , Panek , J. , El Alaoui , H. , Biron , D. G. , Brasset , E. , Vaury , C. , Peyret , P. , Corradi , N. , Peyretaillade , É. , & Lerat , E . ( 2014 ). Microsporidian genomes harbor a diverse array of transposable elements that demonstrate an ancestry of horizontal exchange with metazoans . Genome Biology and Evolution , 6 ( 9 ), 2289 – 2300 . doi: 10.1093/gbe/evu178 OpenUrl CrossRef PubMed ↵ Pombert , J.-F. , Haag , K. L. , Beidas , S. , Ebert , D. , & Keeling , P. J . ( 2015 ). The Ordospora colligata Genome: Evolution of Extreme Reduction in Microsporidia and Host-To-Parasite Horizontal Gene Transfer . mBio , 6 ( 1 ), e02400 – 14 . doi: 10.1128/mBio.02400-14 OpenUrl CrossRef PubMed ↵ Poulin , R. , & Randhawa , H. S . ( 2015 ). Evolution of parasitism along convergent lines: From ecology to genomics . Parasitology , 142 ( Suppl 1 ), S6 – S15 . doi: 10.1017/S0031182013001674 OpenUrl CrossRef PubMed ↵ Quandt , C. A. , Beaudet , D. , Corsaro , D. , Walochnik , J. , Michel , R. , Corradi , N. , & James , T. Y . ( 2017 ). The genome of an intranuclear parasite, Paramicrosporidium saccamoebae , reveals alternative adaptations to obligate intracellular parasitism . eLife , 6 , e29594 . doi: 10.7554/eLife.29594 OpenUrl CrossRef PubMed ↵ Quinlan , A. R . ( 2014 ). BEDTools: The Swiss-army tool for genome feature analysis . Current Protocols in Bioinformatics , 47 , 11.12.1-11.12.34. doi: 10.1002/0471250953.bi1112s47 OpenUrl CrossRef PubMed ↵ R Core Team . ( 2024 ). R: The R Project for Statistical Computing [Computer software] . R Foundation for Statistical Computing . https://www.r-project.org/ ↵ Refardt , D. , Decaestecker , E. , Johnson , P. T. J. , & Vávra , J . ( 2008 ). Morphology, Molecular Phylogeny, and Ecology of Binucleata daphniae n. G., n. Sp. (Fungi: Microsporidia), a Parasite of Daphnia magna Straus, 1820 (Crustacea: Branchiopoda) . Journal of Eukaryotic Microbiology , 55 ( 5 ), 393 – 408 . doi: 10.1111/j.1550-7408.2008.00341.x OpenUrl CrossRef PubMed ↵ Refardt , D. , & Mouton , L . ( 2007 ). Reverse Arrangement of rRNA Subunits in the Microsporidium Glugoides intestinalis . Journal of Eukaryotic Microbiology , 54 ( 1 ), 83 – 85 . doi: 10.1111/j.1550-7408.2006.00149.x OpenUrl CrossRef PubMed ↵ Roach , M. J. , Schmidt , S. A. , & Borneman , A. R . ( 2018 ). Purge Haplotigs: Allelic contig reassignment for third-gen diploid genome assemblies . BMC Bioinformatics , 19 ( 1 ), 460 . doi: 10.1186/s12859-018-2485-7 OpenUrl CrossRef PubMed ↵ Schmid-Hempel , P . ( 2021 ). Evolutionary Parasitology: The Integrated Study of Infections, Immunology, Ecology, and Genetics (Second Edition, Second Edition) . Oxford University Press . ↵ Schultz , D. T. , Haddock , S. H. D. , Bredeson , J. V. , Green , R. E. , Simakov , O. , & Rokhsar , D. S . ( 2023 ). Ancient gene linkages support ctenophores as sister to other animals . Nature , 618 ( 7963 ), 110 – 117 . doi: 10.1038/s41586-023-05936-6 OpenUrl CrossRef PubMed ↵ Seppey , M. , Manni , M. , & Zdobnov , E. M. ( 2019 ). BUSCO: Assessing Genome Assembly and Annotation Completeness . In M. Kollmar (Ed.), Gene Prediction: Methods and Protocols (pp. 227 – 245 ). Springer . doi: 10.1007/978-1-4939-9173-0_14 OpenUrl CrossRef PubMed ↵ Smit , A. , Hubley , R. , & Green , P. ( 2013 ). RepeatMasker Open-4.0 [Computer software] . http://www.repeatmasker.org ↵ Stanke , M. , Diekhans , M. , Baertsch , R. , & Haussler , D . ( 2008 ). Using native and syntenically mapped cDNA alignments to improve de novo gene finding . Bioinformatics , 24 ( 5 ), 637 – 644 . doi: 10.1093/bioinformatics/btn013 OpenUrl CrossRef PubMed Web of Science ↵ Stanke , M. , Schöffmann , O. , Morgenstern , B. , & Waack , S . ( 2006 ). Gene prediction in eukaryotes with a generalized hidden Markov model that uses hints from external sources . BMC Bioinformatics , 7 ( 1 ), 62 . doi: 10.1186/1471-2105-7-62 OpenUrl CrossRef PubMed ↵ Svedberg , D. , Winiger , R. R. , Berg , A. , Sharma , H. , Tellgren-Roth , C. , Debrunner-Vossbrinck , B. A. , Vossbrinck , C. R. , & Barandun , J . ( 2024 ). Functional annotation of a divergent genome using sequence and structure-based similarity . BMC Genomics , 25 ( 1 ), 6 . doi: 10.1186/s12864-023-09924-y OpenUrl CrossRef PubMed ↵ Vasimuddin , Md ., Misra , S. , Li , H. , & Aluru , S . ( 2019 ). Efficient Architecture-Aware Acceleration of BWA-MEM for Multicore Systems . 2019 IEEE International Parallel and Distributed Processing Symposium (IPDPS) , 314 – 324 . doi: 10.1109/IPDPS.2019.00041 OpenUrl CrossRef ↵ Vávra , J. , Fiala , I. , Krylová , P. , Petrusek , A. , & Hyliš , M . ( 2018 ). Molecular and structural assessment of microsporidia infecting daphnids: The “obtusa-like” microsporidia, a branch of the monophyletic Agglomeratidae clade, with the establishment of a new genus Conglomerata . Journal of Invertebrate Pathology , 159 , 95 – 104 . doi: 10.1016/j.jip.2018.10.003 OpenUrl CrossRef PubMed ↵ Videvall , E . ( 2018 ). Plasmodium parasites of birds have the most AT-rich genes of eukaryotes . Microbial Genomics , 4 ( 2 ), e000150 . doi: 10.1099/mgen.0.000150 OpenUrl CrossRef ↵ Wadi , L. , & Reinke , A. W . ( 2020 ). Evolution of microsporidia: An extremely successful group of eukaryotic intracellular parasites . PLOS Pathogens , 16 ( 2 ), e1008276 . doi: 10.1371/journal.ppat.1008276 OpenUrl CrossRef PubMed ↵ Walker , B. J. , Abeel , T. , Shea , T. , Priest , M. , Abouelliel , A. , Sakthikumar , S. , Cuomo , C. A. , Zeng , Q. , Wortman , J. , Young , S. K. , & Earl , A. M . ( 2014 ). Pilon: An integrated tool for comprehensive microbial variant detection and genome assembly improvement . PLOS ONE , 9 ( 11 ), e112963 . doi: 10.1371/journal.pone.0112963 OpenUrl CrossRef PubMed ↵ Weiss , L. M. , & Becnel , J. J . ( 2014 ). Microsporidia: Pathogens of opportunity . Wiley . doi: 10.1002/9781118395264 OpenUrl CrossRef ↵ Wickham , H. , Averick , M. , Bryan , J. , Chang , W. , McGowan , L. D. , François , R. , Grolemund , G. , Hayes , A. , Henry , L. , Hester , J. , Kuhn , M. , Pedersen , T. L. , Miller , E. , Bache , S. M. , Müller , K. , Ooms , J. , Robinson , D. , Seidel , D. P. , Spinu , V. , … Yutani , H . ( 2019 ). Welcome to the tidyverse . Journal of Open Source Software , 4 ( 43 ), 1686 . doi: 10.21105/joss.01686 OpenUrl CrossRef PubMed ↵ Williams , B. A. P. , Williams , T. A. , & Trew , J. ( 2022 ). Comparative genomics of microsporidia . In L. M. Weiss & A. W. Reinke (Eds.), Microsporidia: Current Advances in Biology (pp. 43 – 69 ). Springer International Publishing . doi: 10.1007/978-3-030-93306-7_2 OpenUrl CrossRef ↵ Wiredu Boakye , D. , Jaroenlak , P. , Prachumwat , A. , Williams , T. A. , Bateman , K. S. , Itsathitphaisarn , O. , Sritunyalucksana , K. , Paszkiewicz , K. H. , Moore , K. A. , Stentiford , G. D. , & Williams , B. A. P. ( 2017 ). Decay of the glycolytic pathway and adaptation to intranuclear parasitism within Enterocytozoonidae microsporidia . Environmental Microbiology , 19 ( 5 ), 2077 – 2089 . doi: 10.1111/1462-2920.13734 OpenUrl CrossRef ↵ Xiong , X. , Geden , C. J. , Bergstralh , D. T. , White , R. L. , Werren , J. H. , & Wang , X . ( 2023 ). New insights into the genome and transmission of the microsporidian pathogen Nosema muscidifuracis . Frontiers in Microbiology , 14 . doi: 10.3389/fmicb.2023.1152586 OpenUrl CrossRef PubMed ↵ Ye , Z. , Jiang , X. , Pfrender , M. E. , & Lynch , M . ( 2021 ). Genome-wide allele-specific expression in obligately asexual Daphnia pulex and the implications for the genetic basis of asexuality . Genome Biology and Evolution , 13 ( 11 ), evab243 . doi: 10.1093/gbe/evab243 OpenUrl CrossRef PubMed Žárský , V. , Karnkowska , A. , Boscaro , V. , Trznadel , M. , Whelan , T. A. , Hiltunen-Thorén , M. , Onut-Brännström , I. , Abbott , C. L. , Fast , N. M. , Burki , F. , & Keeling , P. J. ( 2023 ). Contrasting outcomes of genome reduction in mikrocytids and microsporidians . BMC Biology , 21 ( 1 ), 137 . doi: 10.1186/s12915-023-01635-w OpenUrl CrossRef ↵ Zhang , C. , & Mirarab , S . ( 2022 ). Weighting by gene tree uncertainty improves accuracy of quartet-based species trees . Molecular Biology and Evolution , 39 ( 12 ), msac215 . doi: 10.1093/molbev/msac215 OpenUrl CrossRef PubMed ↵ Zimin , A. V. , Puiu , D. , Luo , M.-C. , Zhu , T. , Koren , S. , Marçais , G. , Yorke , J. A. , Dvořák , J. , & Salzberg , S. L . ( 2017 ). Hybrid assembly of the large and highly repetitive genome of Aegilops tauschii , a progenitor of bread wheat, with the MaSuRCA mega-reads algorithm . Genome Research , 27 ( 5 ), 787 – 792 . doi: 10.1101/gr.213405.116 OpenUrl Abstract / FREE Full Text View the discussion thread. Back to top Previous Next Posted June 06, 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 Variation in genome architecture and epigenetic modification across the microsporidia phylogeny 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 Variation in genome architecture and epigenetic modification across the microsporidia phylogeny Pascal Angst , Dieter Ebert , Peter D. Fields bioRxiv 2025.01.20.633886; doi: https://doi.org/10.1101/2025.01.20.633886 Share This Article: Copy Citation Tools Variation in genome architecture and epigenetic modification across the microsporidia phylogeny Pascal Angst , Dieter Ebert , Peter D. Fields bioRxiv 2025.01.20.633886; doi: https://doi.org/10.1101/2025.01.20.633886 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 (7622) Biochemistry (17648) Bioengineering (13871) Bioinformatics (41880) Biophysics (21423) Cancer Biology (18558) Cell Biology (25460) Clinical Trials (138) Developmental Biology (13364) Ecology (19866) Epidemiology (2067) Evolutionary Biology (24290) Genetics (15589) Genomics (22475) Immunology (17711) Microbiology (40327) Molecular Biology (17145) Neuroscience (88473) Paleontology (666) Pathology (2827) Pharmacology and Toxicology (4816) Physiology (7635) Plant Biology (15114) Scientific Communication and Education (2044) Synthetic Biology (4286) Systems Biology (9815) Zoology (2268)