Domoic acid biosynthesis and genome expansion in Nitzschia navis-varingica

Domoic acid biosynthesis and genome expansion in Nitzschia navis-varingica | 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 Domoic acid biosynthesis and genome expansion in Nitzschia navis-varingica View ORCID Profile Steffaney M. Wood-Rocca , View ORCID Profile Nicholas Allsing , Yasuhiro Ashida , Masaki Mochizuki , Malia L. Moore , Zoltán Füssy , Yuichi Kotaki , Clyde Puilingi , Yukari Maeno , Aodhan W. Beattie , Andrew E. Allen , Mari Yotsu-Yamashita , View ORCID Profile Todd P. Michael , View ORCID Profile Bradley S. Moore doi: https://doi.org/10.1101/2025.04.19.649686 Steffaney M. Wood-Rocca 1 Center for Marine Biotechnology and Biomedicine, Scripps Institution of Oceanography, University of California San Diego , La Jolla, CA 2 Environmental Genomics group, J. Craig Venter Institute , La Jolla, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Steffaney M. Wood-Rocca Nicholas Allsing 3 The Plant Molecular and Cellular Biology Laboratory, Salk Institute for Biological Sciences , La Jolla, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Nicholas Allsing Yasuhiro Ashida 4 Graduate School of Agricultural Science, Tohoku University , Aramaki-Aza-Aoba, Aoba-ku, Sendai, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Masaki Mochizuki 4 Graduate School of Agricultural Science, Tohoku University , Aramaki-Aza-Aoba, Aoba-ku, Sendai, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Malia L. Moore 1 Center for Marine Biotechnology and Biomedicine, Scripps Institution of Oceanography, University of California San Diego , La Jolla, CA 3 The Plant Molecular and Cellular Biology Laboratory, Salk Institute for Biological Sciences , La Jolla, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Zoltán Füssy 2 Environmental Genomics group, J. Craig Venter Institute , La Jolla, CA 8 Integrative Oceanography, Scripps Institution of Oceanography, University of California San Diego , La Jolla, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Yuichi Kotaki 4 Graduate School of Agricultural Science, Tohoku University , Aramaki-Aza-Aoba, Aoba-ku, Sendai, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Clyde Puilingi 5 Faculty of Science and Technology, Solomon Islands National University , Honiara, Solomon Islands 6 School of Science & Technology, Pacific Adventist University , Private Mail Bag, Boroko, NCD, Papua New Guinea Find this author on Google Scholar Find this author on PubMed Search for this author on this site Yukari Maeno 7 Graduate School of Agricultural and Life Sciences, The University of Tokyo , Yayoi, Bunkyo-ku, Tokyo, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Aodhan W. Beattie 1 Center for Marine Biotechnology and Biomedicine, Scripps Institution of Oceanography, University of California San Diego , La Jolla, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Andrew E. Allen 2 Environmental Genomics group, J. Craig Venter Institute , La Jolla, CA 7 Graduate School of Agricultural and Life Sciences, The University of Tokyo , Yayoi, Bunkyo-ku, Tokyo, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Mari Yotsu-Yamashita 4 Graduate School of Agricultural Science, Tohoku University , Aramaki-Aza-Aoba, Aoba-ku, Sendai, Japan Find this author on Google Scholar Find this author on PubMed Search for this author on this site Todd P. Michael 1 Center for Marine Biotechnology and Biomedicine, Scripps Institution of Oceanography, University of California San Diego , La Jolla, CA 3 The Plant Molecular and Cellular Biology Laboratory, Salk Institute for Biological Sciences , La Jolla, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Todd P. Michael Bradley S. Moore 1 Center for Marine Biotechnology and Biomedicine, Scripps Institution of Oceanography, University of California San Diego , La Jolla, CA 9 Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego , La Jolla, CA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Bradley S. Moore For correspondence: bsmoore{at}ucsd.edu Abstract Full Text Info/History Metrics Preview PDF ABSTRACT Production of the neurotoxin domoic acid (DA) by benthic diatom Nitzschia navis-varingica poses considerable health and economic concerns. In this study, we employed whole genome sequencing and transcriptomic analyses of regionally distinct N. navis-varingica strains to unravel the genomic underpinnings of DA biosynthesis. Our analyses revealed sizable genomes—characterized by an abundance of repetitive elements and noncoding DNA—that exceed the size of any other pennate diatoms. Central to our findings is the discovery of an expanded domoic acid biosynthesis ( dab ) gene cluster, spanning over 60 kb and marked by a unique organization that includes core genes interspersed with additional genetic elements. Phylogenetic and syntenic comparisons indicate that transposition events may have driven the expansion and reorganization of this cluster. Biochemical assays validated that the kainoid synthase encoded by dabC catalyzes the formation of isodomoic acid B, thereby establishing a distinct chemotype in contrast to the DA profiles of planktonic diatoms. These results highlight the evolutionary trajectory of DA biosynthesis in diatoms and potential advantages conferred by genome expansion and enzyme diversification in dynamic marine environments. IMPORTANCE Domoic acid (DA) is a potent neurotoxin produced by marine micro- and macroalgae problematic to fisheries and toxic to humans and animals. Our study elucidates the molecular mechanisms underlying DA production in the widespread Western Pacific benthic diatom, Nitzschia navis-varingica . Genomic and biochemical insights add information to our understanding of the evolution of toxin production across diverse phyla and also fill a gap in the knowledge of secondary metabolism in marine diatoms. These findings provide a genetic framework for identifying toxin production and its impacts in the benthos of vulnerable, coastal ecosystems. INTRODUCTION Domoic acid (DA) is a member of the kainoid class of natural neurotoxins, which includes the isomers and derivatives of DA, the namesake kainic acid, and acromelic acid ( 1 , 2 ). Kainoids are non-proteinogenic amino acids characterized by a glutamate-derived pyrrolidine ring and multiple carboxylates ( Fig. 1A ). DA functions as a potent glutamate receptor agonist, leading to neurotoxic effects such as memory loss, disorientation, vomiting, seizures, and in severe cases, coma and death ( 3 – 5 ). The first recorded outbreak of DA poisoning in humans, termed amnesic shellfish poisoning, occurred in 1987 in Prince Edward Island, Canada. This outbreak was attributed to the accumulation of DA in mussels that had consumed the toxin-producing diatom from what is now known as Pseudo-nitzschia multiseries ( 6 , 7 ). Download figure Open in new tab Figure 1. Kainoid production across marine eukaryotes. (A) Simplified eukaryotic tree of life based on Burki et al. with DA and kainic acid producers highlighted within their respective supergroups ( 38 ). (B) Rooted multi-locus phylogenetic analysis of alignments of 18S (SSU) and 23S (LSU) nuclear RNA genes as well as chloroplast genes psbC and rbcL from the Bacillariaceae family. Supplementary Figure S1 shows a complete version of this phylogeny. Stars indicate dab cluster identified from this species. Bold indicates strains highlighted in this study. Download figure Open in new tab Figure S1. Rooted phylogenetic analysis of Bacillariaceae family using concatenated alignments of 18S (SSU) and 23S (LSU) nuclear RNA genes as well as chloroplast genes psbC and rbcL. Digenea simplex genes used as outgroup. Blue clades are included in Fig.1 . Bolded are strains highlighted in this study. Since this deadly initial outbreak, subsequent research has described DA production in a variety of marine eukaryotic algae ( 8 – 11 ). Approximately half of the over 50 described species of harmful algal bloom-forming diatoms in the genus Pseudo-nitzschia have been reported to produce DA ( 12 ). These toxic blooms have caused significant negative economic impact and safety risks to humans and animals through bioaccumulation of DA in the marine food web ( 12 – 14 ). Additionally, red macroalgae of the family Rhodomelaceae—most notably Chondria armata , from which DA was first described—and other pennate diatoms such as Amphora sp., Nitzschia bizertensis , and Nitzschia navis-varingica have also been demonstrated to produce this neurotoxin ( 9 , 12 , 15 ). N. navis-varingica is commonly found in benthic ecosystems in the Western Pacific, where its DA production poses a threat to aquaculture facilities and shellfish harvested from mangrove ecosystems ( 16 , 17 ). DA production in N. navis-varingica is widespread, corresponding with its ability to inhabit diverse ecological niches in conditions ranging from planktonic to benthic and euhaline to brackish systems ( 18 – 20 ). N. navis-varingica strains tend to produce higher ratios of isodomoic acid B to DA, in contrast to Pseudo-nitzschia spp. that primarily produce DA and isodomoic acid A ( 20 , 21 ). Recent studies have demonstrated that geographically distinct populations display a high degree of genetic homogeneity and strains with similar DA profiles are typically monophyletic, underscoring a genetic determinant in toxin production ( 17 , 19 , 22 ). With the expansion of whole genomic sequencing of DA-producing algae, the evolution of DA biosynthesis is being unraveled ( 15 , 23 ). DA biosynthesis genes ( dab ) were first identified in P. multiseries in a biosynthesis gene cluster (BGC) encoding a N -prenyltransferase ( dabA ), hypothetical protein ( dabB ), kainoid synthase ( dabC ), and cytochrome P450 (CYP450, dabD ) ( 23 ). Dab gene clusters have thus far been identified in toxigenic Pseudo-nitzschia spp., including P. multiseries , P. australis , P. seriata , P. cuspidata , and P. multistriata , with their protein sequences displaying high amino acid identity ( 23 – 27 ). DA and kainic acid biosynthesis have also been described in red macroalgae Chondria armata as well as Digenia simplex and Palmaria palmata , respectively ( 15 , 28 , 29 ). Despite the evolutionary distance between diatoms (Bacillariophyta) and red algae (Rhodophyta), the red algal domoic acid biosynthesis genes ( radACD ) display a high degree of gene synteny with both kainic acid biosynthesis genes ( kabAC ) and the DA biosynthesis ( dabABCD) gene clusters of Pseudo-nitzschia species ( 15 ). The unique structure and activity of these enzymes has led to additional research, as they represent a possible horizontal gene transfer event across distant taxa and novel biochemical mechanisms and enzyme structures ( 30 – 33 ). These discoveries highlight the complex evolutionary history of DA biosynthesis and underscore the need for further research. Despite the incredible diversity within Nitzschia , comprising over 170,000 species and intraspecific names, only a handful of non-DA producers have been sequenced ( 34 – 36 ). Genomic studies of benthic diatoms such as N. inconspicua and Seminavis robusta revealed expansion of repetitive elements and unique adaptations to the benthos ( 35 , 37 ). We therefore suspect N. navis-varingica will show a similar structure in line with its benthic adaptations. Moreover, these genomic data are essential for characterizing the evolution of the dab pathway in a novel lineage of algae. To further investigate the evolution of DA biosynthesis and the ecological adaptations of sub/tropical benthic diatoms, herein we sequenced regionally distinct strains of N. navis-varingica for comparative genome and transcriptome analyses and DA biochemical validation. We report here that genome expansion in N. navis-varingica is mirrored in the enlarged organization of the dab BGC that encodes the synthesis of the intermediate isodomoic acid B, in contrast to Pseudo-nitzschia diatoms, thereby suggesting a distinct evolutionary history in these diatom genera. RESULTS Nitzschia navis-varingica molecular taxonomy and genome characteristics N. navis-varingica strains K0620 and K0969 were isolated from a marine shrimp culture pond and coastal waters in northern Vietnam, respectively ( 39 ). Strain PNB19-01 originated from Bootless Bay near Port Moresby, Papua New Guinea, following previous reports of DA and isodomoic acid B production ( 19 ). We investigated their molecular taxonomy within the Bacillariaceae family using a multi-locus phylogeny (18S rRNA, 23S rRNA, psbC , and rbcL ). All three strains formed a well-supported, monophyletic lineage within a clade containing N. linearis , N. dubiformis , and N. traheaformis , remaining distinct from the DA-producing Pseudo-nitzschia clade ( Fig. 1B ). The N. navis-varingica clade is most closely related to Psammodictyon species, indicating that N. navis-varingica belongs to a separate lineage outside the major Nitzschia clades. The Nitzschia genus in this phylogeny is polyphyletic ( Fig. S1 ), as has been previously reported and further evidenced by the clustering of Nitzschia spp. and Psammodictyon . Indeed, Mann et al. (2021) suggest that the two clades harboring N. navis-varingica may merit recognition as new genera, given the lack of clear morphological synapomorphies to unite them under Nitzschia as currently defined ( 34 ). We produced partially phased genome assemblies of K0620 and K0969 and transcripts for PNB19-01 to investigate diversity in dab genes across DA-producing organisms as well as regionally distinct N. navis-varingica isolates. For K0620 and K0969, we used PacBio genomic and IsoSeq transcriptomic sequencing, while for PNB19-01, we used Novogene RNA-seq. PacBio sequencing produced HiFi reads to ∼35× coverage of K0620 with a read N50 of 16,137 bp, and ∼31× coverage of K0969 with a read N50 of 13,179 bp. IsoSeq transcriptomic sequencing resulted in 13,042,775 reads with an N50 of 1,415 bp for K0620 and 11,434,165 reads with an N50 of 1,537 bp for K0969. Analysis of K-mer composition of the HiFi reads reveals distinct homozygous and heterozygous peaks as well as elevated duplication, highlighting the diploid nature of the genome and the pronounced lower coverage heterozygous peak ( Fig. S2 ). Assembling K0620 and K0969 HiFi reads into haploid genomes produced Haplotype 1 and Haplotype 2 assemblies for each, and while both assemblies are available, we use the Haplotype 1 for our analyses due to higher quality ( Table S1 ). Haplotype 1 of K0620 assembled to 879.5 Mbp with an N50 of 303,884 bp and K0969 to 782.8 Mbp with an N50 of 134,724 bp ( Table 1 ). For PNB19-01, Novogene RNA-seq resulted in 12,640,360 reads, 3.79 Gbp, with an N50 of 1,759 bp. Download figure Open in new tab Figure S2. Genome survey analysis of N. navis-varingica K0620. 30 View this table: View inline View popup Download powerpoint Table S1. Genome statistics for assemblies produced for N. navis-varingica K0620 and K0969. View this table: View inline View popup Download powerpoint Table 1. Genome characteristics of select pennate diatoms. See Table S1 for complete statistics for genomes produced in this study. Both genomes are at least 15 times the size of Nitzschia inconspicua str. hildebrandi GAI-293 and up to 25 times the size of other pennate diatoms such as P. delicatissima . Despite the difficulty removing bacterial contamination prior to sequencing, the quality of assemblies was high, as evidenced by conserved Stramenopiles marker genes with 95% and 85% BUSCO completeness for K0620 and K0969, respectively ( Fig. 2A , Table 1 ). Comparison of GC content with sequencing depth supports minimal contamination given that the majority of contigs cluster around the average GC content of approximately 33% ( Fig. S3 ). Indicative of allelic variation retained in the assemblies, BUSCO analysis also identified a duplication of 19% and 31% for K0620 and K0969, respectively. Moreover, IsoSeq mapping statistics indicated that 91.5% and 83% of transcriptomic reads aligned to the K0620 and K0969 assemblies, further supporting the completeness of the gene models. Download figure Open in new tab Figure S3. Mean Depth of IsoSeq and HiFi reads to Hap1 of Nnav620 and Nnav969. Download figure Open in new tab Figure 2. Genome Assembly Quality and Repeat Composition Across Haplotypes. (A) BUSCO completeness assessments highlighting the proportion of complete single-copy (S), duplicated (D), fragmented (F), and missing (M) orthologs in each assembly. (B) Length of different repeat elements within genome assemblies of K0969 and K0620. Categories include long interspersed nuclear elements (LINEs), long terminal repeat (LTR) elements, DNA transposons, rolling-circles, unclassified repeats, and non-repeats. See haplotype genome and repeat statistics in Table S1 . (C) Genomic neighborhood of the dab gene cluster. Arrows represent genes and bars represent repetitive elements. See full length dab -containing contigs in Fig. S3 . The genome size in N. navis-varingica is shaped by the large proportion of non-protein coding regions and repetitive DNA ( Fig 2B ). Both strains only constitute approximately 7% coding sequences, in contrast to approximately 70% repetitive DNA. Despite this, they still contain more predicted proteins than other pennate diatom genomes ( Table 1 ). Of the various classes of repetitive DNA, unclassified repetitive elements make up the largest fraction of the genomes (48-50%), followed by long-terminal repeats (LTR) (8-9%) and rolling-circles (6-8%). A similar makeup has been previously reported in centric diatom genomes ( 43 ). Of the functionally annotated genes, the majority correspond to core metabolic processes ( Fig. S4 ). The prevalence of annotations related to macromolecule transport, such as bicarbonate, nitrate, and magnesium, light harvesting, and stress response possibly reflect adaptations to the environmental fluctuation of pH, light and nutrient availability, and temperature that is common in the sub/tropical benthos ( 44 – 46 ). Given the ability of benthic Nitzschia spp. to produce volatile, halogenated hydrocarbons, like methyl iodide ( 47 – 49 ), we queried the genomes for putative haloperoxidase and halide methyltransferase genes. We observed an interesting colocalization of genes encoding a putative halide methyltransferase with an iodotyrosine deiodinase, the latter of which had homologs in benthic diatom Seminavis robusta and various Alveolates ( Table S2 , Fig. S5 ). The N. navis-varingica iodotyrosine deiodinase may function to detoxify halogenated amino acids, which in turn would result in cellular iodide that would be methylated and removed as volatile methyl iodide ( 49 – 53 ). Download figure Open in new tab Figure S4. Distribution of KEGG, GO, and COG terms in EggNOG mapper functional annotations. 33 View this table: View inline View popup Download powerpoint Table S2. Amino acid sequence for putative iodoperoxidase gene from K0620 hap1 assembly. Top BlastP hits from NR database. Download figure Open in new tab Figure S5. Putative iodotyrosine deiodinase gene containing contig in K0620 hap1. Arrows represent genes and bars represent repetitive elements. Domoic acid biosynthesis gene cluster identification We identified the dab gene cluster in the genomes of N. navis-varingica K0620 and K0969 using BLAST and HMM searches with the existing collection of Pseudo-nitzschia dab genes and C. armata red algal domoic acid ( rad ) genes. Initial searches revealed the co-localization of homologs for dabA , dabB , dabC , and a CYP450 unrelated to canonical dabD genes in both K0620 and K0969 ( Fig. 2 and S5 ). An additional copy of dabC was also identified in K0620 (referred to as dabC2 ) on a separate contig ( Fig S7 ). Notably, we identified a similar set of dabABC and a CYP450 transcripts in N. navis-varingica PNB19-01. Curiously, the CYP450 sequences that displayed the strongest homology with Pseudo-nitzschia dabD sequences were not co-localized with dabABC in K0620 and K0969. Rather, the co-localized CYP450s only exhibited up to 21% amino acid identity with known dabD sequences, a trend also observed in C. armata (15, Fig. S8 ). We thus suspect that the co-clustered CYP450, which is conserved across all three strains, functions as the oxygenase DabD. Additionally, the N. navis-varingica dab cluster contains the dabB gene that encodes a protein of unknown function as first reported in Pseudo-nitzschia diatoms, yet not in DA-producing red algae ( 23 ). Download figure Open in new tab Figure S6. Domoic acid biosynthetic gene cluster containing contigs across both haplotype-resolved assemblies for strains K0620 and K0969. Arrows represent genes and bars represent repetitive elements. Download figure Open in new tab Figure S7. N. navis-varingica hap1 dabC2 contig genomic neighborhood. Arrows represent genes and bars represent repetitive elements. Download figure Open in new tab Fig S8. Heatmap of amino acid percent identity among dabD sequences. The N. navis-varingica dab cluster spans over 60 kb, features a unique gene arrangement, and contains additional genes and repetitive elements ( Fig. 2C ). The expansion of intergenic space and the abundance of repeats at the dab locus mirror the overall genome size and composition. The cluster is flanked by DNA transposons and rolling circle elements, suggesting that transposition events may have contributed to its expansion and rearrangement. Within the cluster, interspersed genes encode proteins with domains such as aldehyde dehydrogenase, major facilitator superfamily, acyl-coenzyme A oxidase, and AMP-binding enzymes. To further determine if these genes were potential segment repeat elements misannotated by RepeatMasker (v4.1.8), the intergenic space between dabA and dabD was BLAST searched against the remainder of the genome assembly ( 54 ). Results showed that portions of the non-coding intergenic space, but not the inserted coding sequences, displayed high (up to 95%) nucleotide similarity throughout the genome ( Fig. S9 ). Download figure Open in new tab Figure S9. Comparative analysis of top 100 BLAST hits for dab cluster segment repeat element in K0620 hap1 and K0969 hap1. Each row represents a contig, horizontal bars show the aligned portion of the segment repeat and indicate nucleotide percent identity (85%+) relative to the reference dab -containing contigs shown on the bottom row. The schematic at the bottom illustrates the portion of the dab cluster between dabA and dabD, with coding sequences represented as arrows. The gene order of the N. navis-varingica dab cluster is rearranged relative to other DA-producing organisms: dabA and dabC are adjacent, followed by a series of interspersed genes, then dabB and the putative dabD . The CoA-binding protein and protein kinase genes that flank a block containing the aldehyde dehydrogenase, major facilitator superfamily member, dabB , dabD , and a nodulin-like gene are similar to the sequences found in other diatom genomes. The putative integration site for the Pseudo-nitzschia dab gene cluster, involving a highly conserved CoA-binding protein (K0620 hap1 g25680) and protein kinase ( K0620 hap1 g25681) gene pair as proposed by He et al., is present in N. navis-varingica in a genomic region separate from the dab cluster ( 24 ). Interestingly, genes containing similar domains are found in the N. navis-varingica dab locus. The protein kinase gene found downstream of the N. navis-varingica dab cluster is more homologous (31% amino acid identity) to the sequence found in putative Pseudo-nitzschia dab insertion site than the CoA-binding gene (19% amino acid identity). Phylogenetic analysis of these sequences shows that these sequences are highly conserved across diatoms ( Fig S10 ). This observation suggests that the putative integration site may be highly conserved across many diatom lineages. The presence of orthologous protein kinase may indicate a possible conserved mechanism of cluster integration across these taxa. Download figure Open in new tab Figure S10. Phylogenetic analysis of (A) protein kinase and (B) CoA-binding protein genes. Nitzschia navis-varingica and Pseudo-nitzschia spp. genes are bolded. Blue branches correspond with diatom sequences. N. navis-varingica compound detection and biochemical validation of isodomoic acid B synthase Analysis of N. navis-varingica culture extracts using liquid chromatography mass spectrometry (LCMS) revealed the presence of DA along with related isomers isodomoic acid A and isodomoic acid B ( Fig. 3 and S11 ). While N. navis-varingica cultures primarily produce DA, isodomoic acid B is present at substantial levels—a pattern that contrasts with DA-producing Pseudo-nitzschia species that predominantly yield DA and isodomoic acid A. Based on these observations, we hypothesized that the kainoid synthase enzyme (DabC) in N. navis-varingica generates isodomoic acid B, a pattern found in isodomoic acid B chemotype seen in C. armata ( 15 ). Download figure Open in new tab Figure S11. Culture extracts and DabC assays compared with synthetic standards. Positive ion mode LC-MS extracted ion chromatogram profiles for anticipated domoic acid and related isomer products ( m/z 312.1±1.0). Download figure Open in new tab Figure 3. Domoic acid biosynthesis pathway in N. navis-varingica proceeds through isodomoic acid B. (A) N. navis-varingica Dab enzymes collectively L-glutamic acid (L-Glu) and geranyl diphosphate (GPP) to isodomoic acid B on route to DA. (B) Extracted ion chromatogram profiles for DA and isodomoic acid B ( m/z 312.1±1.0) from DabC assays and culture extracts. See comparison to synthetic standards in Fig. S7 . (C) Branching of isodomic acid B synthase DabC amino acid sequences visible through unrooted phylogeny of kainoid synthase enzymes. Clade shading indicates isodomoic acid A or B production. To validate this hypothesis, we examined key steps in the DA biosynthesis pathway. Enzyme assays with purified glutamate N -prenyltransferase enzymes (K0620-NnvDabA and PNB19-01-NnvDabA) confirmed the production of N -geranyl-L-glutamic acid ( Fig. 3 , compound 3 , L-NGG) from geranyl diphosphate ( 1 ) and L-glutamate ( 2 , Fig. S12 ). Subsequent assays of the kainoid synthase enzymes K0620-NnvDabC and PNB19-01-NnvDabC revealed that they catalyzed the oxidative cyclization of linear precursor 7’-carboxy-L-NGG ( 4 ), yielding isodomoic acid B ( 5 ) as the product ( Fig. 3B ). These results establish that N. navis-varingica exhibits a distinct chemotype from other DA-producing diatoms in its production of isodomoic acid B. It also underscores the role of the kainoid synthase in driving isomer diversity within the DA biosynthesis pathway. Download figure Open in new tab Figure S12. Positive ion mode LC-MS extracted ion chromatogram profiles for L-NGG ( m/z 280.2 ± 0.1) from synthetic standard and DabA assays. NnvDabC enzymes also cyclize L-NGG ( 3 ) to produce primarily dainic acid A ( Fig. S13 ). NnvDabC from strain K0620 also appears to produce trace amounts of dainic acid B/C, which have been shown to co-elute using our methods ( 15 , 23 ). This is consistent with enzymatic products produced by isodomoic acid B synthase RadC and P. multiseries isodomoic acid A synthase DabC, but a marked discrepancy from KabC, which cannot cyclize the geranyl side chain present dab pathway intermediates ( 14 ). It should also be noted that dainic acid A can sometimes be detected in culture extracts of N. navis-varingica ( Fig. S14 ), as has been previously reported in C. armata ( 29 ). Download figure Open in new tab Figure S13. (A) Dainic acid isomers. (B) Positive ion mode LC-MS extracted ion chromatogram profiles for dainic acid isomers compared with synthetic standards ( m/z 282.2±1.0). Dainic acids B and C have been shown to co-elute using our LCMS methods ( 14 ). Download figure Open in new tab Figure S14. Dainic acid in culture extracts. Negative ion mode LC-MS extracted ion chromatogram profiles for dainic acid isomers compared with synthetic standards ( m/z 280.2±0.1). Dainic acids B and C have been shown to co-elute using our LCMS methods ( 14 ). Gene synteny and phylogenetic analysis of kainoid biosynthesis gene clusters Phylogenetic analysis of individual dab genes largely aligns with previous studies ( 15 , 23 , 28 , 30 ). Isodomoic acid B synthase NnvDabC groups more closely with RadC, rather than with the isodomoic acid A synthases found in more closely related Pseudo-nitzschia species ( Fig. 3C ). All kainoid synthase DabC enzymes nonetheless form a subclade in the broader phylogeny of bacterial and fungal alpha-ketoglutarate dependent Fe(II)-containing dioxygenases as previously observed ( 15 ), highlighting the sources of a likely horizontal gene transfer event ( Fig. S15A ). DabB phylogeny shows that NnvDabB groups separately from Pseudo-nitzschia spp. DabB sequences, and other uncharacterized proteins sequences in the tree are distantly related ( Fig. S16 ). In silico analysis of NnvDabB indicates that it contains N-terminal signal peptide and may act as a type II signal anchor that anchors proteins to the membrane ( 55 , 56 ) Download figure Open in new tab Figure S15. Phylogenetic analysis of (A) kainoid synthase and (B) DabD CYP450 enzymes. Maximum likelihood trees were constructed using Kalign and iTOL (EMBL). Kainoid synthase enzymes form a distinct branch, while N. navis-varingica DabD clusters with other diatom CYP450 sequences. Download figure Open in new tab Figure S16. Unrooted phylogenetic analysis of DabB protein sequences. Broader phylogeny of DabD sequences within CYP450s highlights the uniqueness of N. navis-varingica DabD that groups with other diatom CYP450 sequences but separately from Pseudo-nitzschia spp. DabD, also echoing the possibility of gene duplication and lineage-specific neofunctionalization of CYP450 enzymes as reported in the rad pathway (15, Fig. S15B ). To understand the evolutionary origin of the taxonomically distinct NnvDabD co-localized with the dab cluster, we constructed a phylogenetic tree of all 128 annotated K0620 CYP450 sequences ( Fig. S17 ). While the dabD gene candidate predicted by homology to the characterized Pseudo-nitzschia spp. dabD formed a clade with CYPs of mostly unknown function, the dabD candidate from the BGC groups with CYP450s widely annotated as retinoid hydroxylases. This result indicates a possible origin of the candidate CYP450 DabD in carotenoid biosynthesis, potentially resulting from similarities in structural motifs of the two isoprenoid species. Download figure Open in new tab Figure S17. Nitzschia navis-varingica K0620 Cytochrome P450 phylogenetic tree. CYP function was annotated based on KEGG Orthology(KO). In the larger context of kainoid BGCs, a concatenated phylogeny of N -prenyltransferase (A-type), B proteins (unknown function), kainoid synthase (C-type), and CYP450 (D-type) genes forms a well-supported N. navis-varingica clade distinct from both the Pseudo-nitzschia dab clusters and the red algal (Rhodophyta) domoic/kainic acid pathways ( Fig. 4 ). Notably, gene synteny for dabA and dabC is highly conserved among N. navis-varingica strains, with amino acid identities ranging from 84% to 99%. These findings underscore a unique evolutionary route for isodomoic acid B biosynthesis in N. navis-varingica and highlight the potential for divergent enzymatic adaptations in diatom versus red algal kainoid production. Download figure Open in new tab Figure 4. Syntenic comparisons and phylogenetic analysis of kainoid biosynthesis gene clusters. Phylogram represents unrooted phylogeny of concatenated kainoid biosynthesis genes coupled with visualization of the corresponding biosynthesis gene clusters. Lines represent contiguous stretches of DNA; arrows represent genes and their orientation; shading between genes represents amino acid sequence identity. *Transcripts. DISCUSSION This study describes the DA biosynthesis pathway in pennate, benthic diatom N. navis-varingica . By combining genomic and transcriptomic analysis of regionally distinct strains of N. navis-varingica , we uncovered a novel organization of the dab gene cluster, assembled two high-quality diatom genomes, and clarified the phylogenetic position of N. navis-varingica within Bacillariaceae. Additionally, in vitro biochemical assays with key biosynthesis enzymes validated the DA isomer profile across strains, leading to the discovery of a diatom isodomoic acid B synthase, NnvDabC, which represents a novel enzymatic function within DA-producing diatoms. Gene cluster organization and evolution The dab gene cluster in N. navis-varingica strains uniquely spans over 60 kb, which is roughly ten times larger than dab clusters found in Pseudo-nitzschia spp. and C. armata ( 15 , 23 ). Expansion of BGCs through duplication and recruitment of additional enzymes has often been cited in eukaryotes for the diversification of secondary metabolite production ( 57 – 61 ). To our knowledge, this is the first instance of secondary metabolite BGC expansion in diatoms. The dab cluster expansion is further supported by an additional copy of dabC outside of the cluster, the co-localization of dab genes with repetitive elements, and interspersion of additional genes. Based on the genomic arrangement and gene synteny conservation among both N. navis-varingica strains and across diverse taxa, we hypothesize that core kainoid biosynthesis genes dabA and dabC form a single module within the cluster. The presence of flanking DNA transposons also supports the current proposal of DA evolution in which horizontal gene transfer contributed to the acquisition of this module. This observation is consistent with reports that diatoms may have acquired up to 5% of their genes through horizontal gene transfer ( 62 ). The downstream presence of dabB and dabD represent an additional module that was likely recruited through neofunctionalization and intra-genomic reorganization to confer the production of DA. The repetitive segment between dabA and dabD , displaying over 90% nucleotide identity in approximately 100 other places in the genome, further supports this hypothesis. Notably, protein of unknown function dabB is consistently found in diatom dab clusters but is absent in the red alga C. armata , suggesting a lineage-specific recruitment event that may contribute to differences in DA biosynthesis between these groups. Phylogenetic analysis of hypothetically assigned NnvDabD suggests its recruitment via neofunctionalization of native biochemistry, as was found in C. armata ( 15 ). The conservation of a protein kinase downstream of the dabBD module—identified as a potential dab cluster integration site in P. cuspidata —suggests that this region may favor DA biosynthesis insertion and regulation ( 24 ). Phylogenetic analysis shows that the protein kinase is orthologous to sequences found in P. multiseries and P. multistriata , indicating that this locus may favor dab cluster insertion or facilitate genomic rearrangements involving the putative neofunctionalized CYP450. However, the CoA-binding gene present at the dab locus is not orthologous to sequences found in Pseudo-nitzschia ; instead, the orthologous CoA-binding and protein kinase gene pair exists outside of the cluster in N. navis-varingica . This implies that their co-localization with the dab cluster may be coincidental, rather than representing a conserved regulatory or integration hotspot. This regulatory context is particularly relevant when considering the evolution of the cluster toward DA production, which implies that DA confers ecological advantages, such as in response to pH or grazer stress ( 23 , 26 , 63 – 67 ). For example, the regulation of putative CYP450 DabD modulates the addition of the carboxylic acid moiety crucial for DA’s toxicity, supporting its potential role in deterring grazers ( 31 ). Indeed, the N. navis-varingica K0620 strain sequenced in this study was shown to deter grazing by the mixotrophic dinoflagellate Karlodinium armiger ( 68 ). Additionally, DA production may be linked to pH tolerance given that N. navis-varingica is found in shallow, brackish environments with elevated pH; whereas, DA production in Pseudo-nitzschia is linked with elevated pCO2 ( 23 , 67 , 69 , 70 ). Further investigation of the regulatory network modulating DA production in response to environmental stress should be done by comparing gene expression patterns in N. navis-varingica and DA-producing Pseudo-nitzschia species. Mechanistic insights and enzymatic functions Our work also sheds light on the evolution of the gene cluster towards DA production through functional diversification of kainoid synthase enzymes. Our biochemically supported phylogenetic analysis shows that isodomoic acid B synthase NnvDabC1 groups functionally with RadC, with both enzymes converting L-NGG ( 3 ) and cNGG ( 4 ) to DA-like molecules dainic acid A and isodomoic acid B ( 5 ), respectively. DA-producer C. armata RadC behaves similarly, whereas kainic acid-producing D. simplex KabC does not ( 15 , 28 ). P. multiseries DabC was demonstrated to act as an isodomoic acid A synthase, whereas we have shown that N. navis-varingica DabC functions an isodomoic acid B synthase, demonstrating a distinct evolutionary trajectory between these genera. The function of NnvDabC1, presence of additional genes at the dab locus, dabC paralogs outside of the dab cluster, and low homology of putative CYP450 NnvDabD, raises important biosynthesis questions about the order of operations in the pathway as well as the elusive final step—namely, the conversion of isodomoic acid A or B to DA. Conversion of isodomoic acid B to DA not only requires 1,3-olefin migration, but also an additional and separate trans to cis isomerization of the second olefin. Sequence analysis reveals that CYP450 NnvDabD exhibits significantly lower homology to other DabD enzymes in other dab and rad clusters, suggesting it may catalyze a distinct reaction. Consequently, rather than performing the precedented carboxylation of L-NGG ( 3 ), the pathway may proceed through the formation of dainic acid intermediates. This possibility is strengthened by the presence of dainic acids in culture extracts. The discovery of additional oxidative enzymes—beyond the core alpha-ketoglutarate dependent Fe(II)-containing dioxygenase C protein and CYP450 D proteins—such as genes encoding acyl-CoA oxidase and aldehyde dehydrogenase within the dab locus may imply involvement in double bond isomerization. For example, these additional enzymes could induce oxidative rearrangement of the double bond to be shifted out of conjugation with the carboxylate, or work in concert with core oxidative enzymes in the dab cluster ( 71 – 73 ). Alternatively, though less precedented, activation of isodomoic acids by AMP-binding protein could allow for double bond isomerization by dehydrogenase enzyme, in a manner similar to bacillaene biosynthesis and other double bond isomerization biosynthesis strategies present polyketide systems ( 74 – 76 ). Although further work is required to fully elucidate the order and function of these steps, these potential mechanisms align with rare biosynthesis strategies in which oxidative enzyme-catalyzed saturation of unactivated double bonds results in olefin migration ( 72 , 77 , 78 ). However, the presence of dabC paralogs outside of the dab cluster implies that other genes outside of the dab locus may be involved in this pathway, as well. Ecological and evolutionary implications of genome expansion Our study also found that N. navis-varingic a strains have exceptionally large genomes relative to other pennate and benthic diatoms. The over 750 Mbp genomes are more than fifteen times the size of closely related N. inconspicua str. hildibrandii, but only six times the size of fellow benthic diatom Seminavis robusta ( 35 , 37 ). Similar to the observations of centric diatom Thalassiosira (with genomes up to 1.5 Gbp) and across eukaryotes, genome expansion in N. navis-varingica appears to be due to the expansion of noncoding DNA ( 43 , 79 , 80 ). This result is intriguing because Bergmann’s rule predicts smaller cells, and therefore genome sizes, at warmer temperatures, which are typical of sub/tropical benthic environments ( 81 – 83 ). Our findings add to emerging evidence that diatoms may defy this ecological principle, potentially contributing more to global primary production under the threat of rising ocean temperatures ( 84 – 86 ). In this instance, the size of N. navis-varingica genome may correlate with increased genetic diversity and adaptations to fluctuating salinity, pH, light, and nutrient availability, which in turn could lead to greater cell abundance—a trend in support of the latter hypothesis and observed in polar diatom communities ( 43 ). Moreover, DA-producing species of Pseudo-nitzschia have augmented genomes with increased repetitive elements, relative to non-DA producing species ( 24 , 25 ). Genomes of non-DA producing strains of N. navis-varingica may reveal a similar trend of differential DNA content. Taxonomic and phylogenomic considerations Following the first outbreak of DA poisoning by the diatom formerly known as Nitzschia f. pungens (now, Pseudo-nitzschia multiseries ), the genus Pseudo-nitzschia was delineated from Nitzschia partly through taxonomic research driven by DA production ( 6 , 7 ). Our work extends this re-evaluation to N. navis-varingica , another DA-producer within the Bacilliaracae family, which has been documented as widespread throughout the Western Pacific and harbor significant intraspecific diversity ( 22 , 34 ). Our analysis of multiple conserved genetic markers of the speciose Nitzschia genus and Bacillariaceae family reveals that N. navis-varingica strains clade with a subset of Nitzschia spp. and Psammodictyon spp. commonly found in the benthos of the western sub/tropical Pacific. Given its phylogenetic position outside the primary Nitzschia clades, the reported absence of unifying synapomorphy, and presence of DA-producing species, this “cryptic” clade is a strong candidate for taxonomic revision ( 34 , 87 ). Further phylogenomic investigations are recommended to resolve these taxonomic ambiguities and elucidate the origins of DA production within the Bacillariaceae. Conclusion In summary, our study provides new insights into the evolution and organization of the DA biosynthesis pathway by identification of a novel dab cluster in N. navis-varingica . The unique genome-wide expansion reflects the expansion and modular reorganization of the dab gene cluster. The discovery of the genetic basis of DA production in N. navis-varingica and biochemical verification of the Dab pathway suggest that DA production may offer ecological advantages in the subtropical benthic habitat. Future research should explore N. navis-varingica dab gene expression patterns and taxonomic relationships among DA-producing diatoms to better understand the ecological and evolutionary implications of DA production. MATERIALS AND METHODS Diatom culturing and harvesting Nitzschia navis-varingica strains K0620 and K0969 were obtained from the Norwegian Culture Collection of Algae (NORCCA, https://norcca.scrol.net/ , 39). Strains were maintained in natural seawater F/2 media (Guillard, 1983), 16°C, and under a 12:12 photoperiod. Strain K0969 was incidentally co-cultured with a Pseudobodo sp. (Bicoecea), present from the culture collection. Attempts to isolate strain K0969 without the contaminant were unsuccessful. PNB19-01 ( 19 ) was cultured in 30 mL of F/2 medium in 50 mL tissue culture flask (Greiner bio-one, Tokyo, Japan), and by incubating them at 25°C under an irradiance level of 80 μmol photons m −2 s −1 , with a 12:12 h light:dark cycle. The medium was prepared using seawater diluted with distilled water to a salinity of ca. 28. For scale-up culturing, K0620 and K0969 were first treated with antibiotics. They were then grown at 4 L scale at 20°C until exponential growth phase, approximately 1 week. To maintain exponential phase, 2 L of cell culture was harvested by centrifugation at 7,000 xg for 20 minutes every 4-5 days. The remainder of the culture was replenished with 2 L F media. This was repeated until sufficient biomass was collected. DNA and RNA extraction For strains K0620 and K0960, high molecular weight (HMW) DNA was extracted from 0.1 g biomass using Illustra Nucleon Phytopure Genomic DNA Extraction Kit (Cytiva). Manufacturer’s instructions were followed with the following exception: the chloroform extraction and DNA precipitation steps were repeated 5 times in order to increase the quality of DNA. Extracted DNA was size selected using the BluePippin system with a High Pass Plus 15 kb cassette (Sage Science Cat# BPLUS03) and HMW fragment lengths verified using the 4150 TapeStation (Agilent Cat# G2992AA) with a Genomic DNA Screentape (Agilent Cat# 5067-5365). RNA was extracted from 0.1 g of biomass using the Direct-zol RNA Purification Kit (Zymo) following the manufacturer instructions. RNA was quantified and quality assessed using a Qubit RNA BR Assay Kit (Invitrogen Cat# Q33231) and TapeStation RNA ScreenTape (Agilent Cat# 5067-5576). For strain PNB19-01, the 29 days culture (15 mL) was harvested at 3.3 h after switching the lighting to light from dark by centrifugation in 50 mL conical tube at 670g for 1 min at 25°C. After removal of the supernatant, TRI reagent (Sigma, cat#T9424, 1 mL) and 0.1 mL of Zirconia Ball YTZ-0.05 mm (Nikkato corporation, Japan) were added to the cells, then the cells were disrupted using MS-100 (TOMY, Japan), 3,000 rpm for 1 min. The suspension was moved into a micro tube (1.5 mL) and chloroform (0.2 mL) was added, then kept for 5 min at room temperature (RT). The mixture was centrifuged for 15 min at 20,600g at 4°C. The supernatant was moved to a new microtube, then isopropanol (0.5 mL) was added and kept for 5 min at room temperature (RT). After centrifugation for 15 min at 20,600g at 4°C, the supernatant was removed, then 75 % EtOH (1 mL) was added to the precipitation, then centrifuged again for 6 min at 5,000g at 4°C. After removal of the supernatant, the precipitation was dissolved with RNase free water (15 µL), and mixed with DNase I 10 x buffer (1.5 µL) and DNase I (RNase free, Nippon gene, 0.5 µL) using vortex, then kept at 37°C for 10 min. After reaction, TRI reagent (0.5 mL) and chloroform (0.1 mL) were added to the reactant and kept 5 min at RT, then centrifuged for 15 min at 20,600g at 4°C. The supernatant was moved to a new microtube, then isopropanol (0.25 mL) was added. After keeping at RT for 5 min, the mixture was centrifuged for 15 min at 20,600g at 4°C. The supernatant was removed, then 75%EtOH (0.5 mL) was added, then centrifuged 6 min at 5,000g at 4°C. The obtained total RNA was dissolved with 50 µL of RNase free water, then quantified as total 1.38 µg using Quantus Fluorometer (Promega). Library preparation and sequencing Strains K0620 and K0969 were sequenced on a Pacific Biosciences (PacBio) Revio to produce PacBio HiFi reads, intended for nuclear genome assembly, and IsoSeq reads were used to map transcriptomic data to the assembled genome. SMRTbell libraries were prepared from the HMW DNA preps of each strain using the HiFi SMRTbell prep kit 3.0 (PacBio Cat# 102-182-700) according to the manufacturer’s instructions, including the recommended DNA shearing step for eukaryotes. Iso-Seq Kinnex libraries were prepared from total RNA using the Kinnex Full-Length RNA kit (PacBio Cat# 103-238-700) with the Iso-Seq Express 2.0 Kit for cDNA synthesis (PacBio Cat# 103-071-500), according to the manufacturer’s instructions which include a polyA-selection. The K0620 and K0969 SMRTbell libraries were barcoded and multiplexed on a single 25M SMRT cell (Cat# 102-202-200), and the K0620 and K0969 Kinnex libraries barcoded and multiplexed on a single SMRT cell along with several other libraries. Both runs used the v13.0.0.205983 Revio chemistry bundle and a 30-hour movie time. For strain PNB19-01, cDNA libraries were sequenced by Novogene using NovaSeq X Plus (Illumina) (3Gb, PE150, 20 M PE read). Genome and transcriptome assembly, size estimation, and annotation The PacBio genomic HiFi reads from the N. navis-varingica K0620 and K0969 samples were assembled into partially phased contigs using HiFiasm v0.19.8. The assembled contigs were then screened and filtered for contamination utilizing v0.5.0 of NCBI’s Foreign Contamination Screening – GX (FCS-GX) workflow. The filtered assemblies were then assessed for contiguity and completeness with assembly-stats v1.0.1 and the stramenopiles_odb10 BUSCO v5.4.3 database. Concurrently, a k-mer approach was taken to predict genome size, heterozygosity, and repeat content of the N. navis-varingica samples using the HiFi reads, GenomeScope 2.0, and meryl v1.3. For sample K0969, lower HiFi read coverage required setting the initial kmercov estimate to 10 for GenomeScope 2.0. Transcripts were identified from the PacBio IsoSeq reads of N. navis-varingica K0620 and K0969 using isoseq v4.2.0. The reads were segmented with skera v1.3.0 before primer removal and read demultiplexing via lima v2.12.0. After segmentation and demultiplexing, poly(A) tails and concatemers were removed with the “isoseq refine --require-polya” command. The three IsoSeq runs were then clustered for each sample by running “isoseq cluster2 --singletons” and subsequently mapped to the associated genome assembly with pbmm2 v1.16.0. Genome annotation was conducted using a combination of BRAKER v2.1.6, GALBA v1.0.1, and TSEBRA v1.1.2.5. BRAKER was used to predict genes based on the IsoSeq transcript mapping and protein annotation sequences from 8 related Bacillariophyceae species: Phaeodactylum tricornutum CCAP 1055/1, Fragilariopsis cylindrus CCMP1102, Fistulifera solaris, Nitzschia inconspicua, Mayamaea pseudoterrestris, Pseudo-nitzschia multistriata, Seminavis robusta, and Cylindrotheca closterium with the GenBank accessions: GCA_000150955.2, GCA_001750085.1, GCA_002217885.1, GCA_019154785.2, GCA_027923505.1, GCA_900660405.1, GCA_903772945.1, and GCA_933822405.4, respectively. These protein sequences were additionally used in the GALBA annotation workflow to predict protein coding gene structures. After BRAKER and GALBA, the results were input into TSEBRA to select the highest-confidence transcripts. Functional annotations of gene models were generated by annotation against common protein domain databases Pfam v35.0, PANTHER v15.0, TIGRFAM v15.0, KEGG v30-01-2023, and EggNOG v5 using a combination of tools (diamond v2.0.15, eggNOG-mapper v2.1.10, Interproscan v5.57-90.0, kofamscan v1.3.0 ( 88 – 93 ). Lineage Probability Index (LPI) was calculated from top 100 diamond blastp hits by dividing the sum of probabilities of each taxonomic term by the normalization factor corresponding to its taxonomic level in the lineage and choosing the term with the highest index ( 94 ). For each assembly, RepeatModeler v2.0.6 with default parameters was used to prepare a custom repeat library which was used as input for RepeatMasker v4.1.8 with the “-xsmall -nolow -norna -no_is -q” parameters. For PNB19-01, de novo assembled data was used for BLAST search and other bioinformatics analysis using GENEYX-MAC (Nihon Server, Tokyo). Annotation of domoic acid biosynthesis gene clusters and phylogenetic analysis Dab gene amino acid sequences from P. multiseries , P. multistriata , P. australis , and C. armata were used to build a Hidden Markov Model (HMMER v3.3.2) query for each individual gene in the cluster using hmmsearch (part of HMMER) or BlastP ( 95 – 97 ). The peptide sequences from assemblies were queried to identify candidates and verified by sequence alignment. Single gene phylogenies were built using Kalign (EMBL-EBI), top BLAST hits for the N. navis-varingica sequences, representative UniRef50 sequences, in addition to those listed in previously published phylogenies ( 15 , 98 ). Concatenated phylogenies of Bacillariaceae marker genes ( Fig. 1 ) and kainoid biosynthesis genes ( Fig. 4 ) were built using SPLACE to align and concatenate genes of interest ( 99 ). Maximum-likelihood trees were built using IQ-TREE and visualized in iTOL ( 90 , 91 ). Visualization of genomic data was performed using RStudio (v2024.12.1.563), including packages taxize, gggenes and ggplot2 ( 100 – 103 ). Clinker was used for kainoid gene cluster comparison ( 104 ). Subsequent figure refinement (color adjustments and figure compilation) was performed in Affinity Designer ( https://affinity.serif.com/en-us/designer/ ). Heterologous protein expression and purification For strain PNB19-01, dabA and dabC clones were obtained using reverse transcriptase polymerase chain reaction (RT-PCR). They were then cloned into a pet28 vector and expressed as described below. See all expressed genes in Table S3 . In RT-PCR obtained clone of dabA , single nucleotide change from 296-A (RNA-seq) to G was detected. This 296-G clone was expressed. View this table: View inline View popup Download powerpoint Table S3. Nucleotide sequences of genes expressed in vitro . Putative chloroplast signal peptide was identified on K0620-dabA using HECTAR (v1.3) and SignalP (Eukarya, v6.0) ( 55 , 56 ). Therefore, K0620 dabA was ordered with a 26 amino acid truncation and expressed as such. Both dabA and dabC genes were codon optimized for E. coli expression, domesticated for SapI and BsaI cut sites, and designed with N-terminal His-6 affinity tag in pET-28a(+) vectors and ordered from Twist Bioscience. See all expressed nucleotide sequences in Table S3 . Both DabA and DabC were expressed and purified as previously ( 15 , 23 ) using conventional methods. Constructs were transformed into chemically competent E. coli BL21(DE3) cells and plated on kanamycin (50 mg/mL) plates. Overnight cultures of transformed BL21(DE3) E. coli were used to inoculate expression cultures, which were grown at 37°C in 500 mL TB broth supplemented with 4% glycerol to an OD-600 of ∼0.6. Cultures were chilled on ice and induced with 1 mM of isopropylthio-beta-galactoside (IPTG). Flasks were shaken at 18°C overnight (∼18 hours). Cells were harvested by centrifugation (8,000 x g, 15 mins) and frozen at -80°C until future purification. Frozen pellets were defrosted on ice and at 4°C overnight, resuspended in 5 mL lysis buffer (10 mM HEPES, 100 mM NaCl, 25 mM Imidazole, 0.2 mM DTT, 2.5 mM EDTA, 20% glycerol, pH 7.5) per 5 mg pellet amended with 1 mg/mL lysozyme. Cells were lysed by sonication using a Qsonica tip at 50% amplitude for 15s on, 45s off, 7 min total working time. DNase I in 5 mM MgCl2 was added halfway through sonication to a final concentration of 5 ug/mL. Lysate was centrifuged at 40,000xg for 30 minutes at 4°C to remove cellular debris. Supernatant filtered through Whatman filter before purification. Purification was performed using immobilized metal-affinity chromatography purification (IMAC) of His6-tagged proteins using a HisTrap FF column (Cytiva) on a AKTA pure™ 25 L1 (Cytiva) fast protein liquid chromatography (FPLC) system and a BioLogic DuoFlow system (Bio-Rad). FPLC data was analyzed with UNICORN version 7 software. Clarified lysate was loaded at 2 mL/min onto a 5 mL HisTrap FF column (Cytiva) pre-equilibrated with lysis buffer. The column was washed with 10 column volumes of 8% elution buffer (10 mM HEPES, 100 mM NaCl, 500 mM imidazole, 20% glycerol, pH 7.5) and then eluted with a linear 8–100% gradient over 15 column volumes in 4 mL fractions. Fractions were analyzed by SDS-PAGE. Fractions containing the target protein were pooled, desalted, and buffer-exchanged using PD-10 columns (Sephadex G-25 M, Cytiva) that were pre-equilibrated with storage buffer (50 mM HEPES, 250 mM NaCl, pH 8, 10% glycerol). Storage buffer for DabA was amended to final concentration of 5 mM MgCl2. Buffer exchanged protein was concentrated using Amicon Ultra-15 centrifugal filters, aliquoted, and flash frozen in liquid nitrogen. Aliquots were stored at -80 until further analysis. All protein quantification was calculated using denatured protein UV absorbance at 280 nm and the protein’s extinction coefficient, at multiple dilutions with Milli-Q water. Preparation of substrates and standards and enzymatic activity assays DA standard was purchased from the National Research Council of Canada ( 105 ). Kainic acid standard was purchased from Chem-Impex. Preparation of all non-commercial substrates were used as prepared for previous studies ( 15 , 23 , 28 , 31 ). All substrates and enzymatic assay products were verified using retention time and mass via LCMS. DabA enzyme assays to demonstrate N-prenyltransferase function were performed as previously described ( 15 , 23 , 30 ), with a few modifications. Reaction mixture was prepared in a final volume of 100 μL in 100 mM HEPES (pH 8.0), 100 mM KCl, 10% glycerol buffer with 5 mM MgCl2, 1 mM geranyl diphosphate (GPP), and 20 mM of L-glutamate. Reactions were allowed to incubate at room temperature (∼22 °C) for 6 hours and were then quenched with 100 L of ice-cold methanol. Quenched reactions were centrifuged, filtered, and injected (10 uL) onto LC-HRMS. Enzyme assays to demonstrate kainoid synthase activity for K0620-DabC and PNB19-01-DabC were performed as previously described ( 15 , 23 ) with few modifications. A reaction mixture was prepared in a final volume of 100 μL containing 100 mM HEPES (pH 8.0), 100 mM KCl, 10% glycerol, 1 mM L-ascorbate, 6.25 mM 2-oxoglutaric acid, 25 μM to 1 mM of either 7’-COOH-L-NGG or L-NGG, 50 μM DabC, and 50 μM FeSO₄·7H₂O, and incubated at 25°C overnight (15 h). The reaction was quenched by adding 100 μL of methanol, followed by centrifugation. The supernatant was purified via filtration with a nylon 0.22 µm pore CA membrane (Costar Spin-X) or purified using a reversed-phase resin (Cosmosil 140C-OPN) prior to liquid chromatography mass spectrometry (LCMS) analysis. Metabolite extraction from N. navis-varingica Solid phase extraction was performed using Agilent Bond Elut PPL cartridges (200 mg, 3 mL), in a manner similar to analysis for dissolved organic matter analysis ( 106 ). During exponential phase of strains K0620 and K0969, 50 mL of cell culture was acidified to pH 2 with concentrated HCl. The PPL cartridges were washed and activated using LCMS grade methanol and LCMS grade water (pH 2), respectively. Acidified samples were loaded onto the cartridge under vacuum in a drip-wise manner. After sample loading, cartridges were washed with acidified LCMS grade water (pH 2) to remove salts. Cartridges were dried under nitrogen gas and eluted with 2 mL of LCMS grade methanol. Samples were dried down in a Speedvac and resuspended in 100 µL of 80% aqueous methanol (LCMS grade) with 0.1% formic acid (LCMS grade). Samples were stored at -80°C until LCMS analysis. PNB19-01 cell extract (the one-month culture, 8 mL) cells (approximately 10 mg) were collected by 1,500 × g 3 min centrifugation, then extracted with 50% MeOH 100 µL by sonication 10 sec. After centrifugation (20,600 × g 30 sec), the supernatant was collected. The half of the supernatant (approximately 50 µL) was used after removal of the solvent using vacuum centrifugation at room temperature (finally from 5 mg cell extract). Liquid chromatography mass spectrometry LCMS measurements were conducted in a similar manner as previously described ( 11 ). Samples were injected onto an Agilent single quadrupole UPLC-MS iQ using the Single Quadrupole Analytical LCMS. Compounds were separated by reversed-phase chromatography on a Phenomenex Kinetex 5 mm C18 100 Å 150 x 4.6 mm LC column with water + 0.1% formic acid (solvent A) and acetonitrile + 0.1% formic acid (solvent B) as eluents. The following gradient was applied at a flow rate of 0.75 mL/min: hold at 5% B for 1 minute, 5% to 35% B over 30 min, 35 to 100% B over 1 minute, hold at 100% B for 1.5 min, 100% to 5% B over 2.5 min, hold at 5% B for 2 min. Higher resolution mass spectrometry was necessary for detection of biosynthetic intermediates in culture extracts. High resolution LCMS measurements were conducted using an Agilent Technologies 1200 Series system with diode array detector coupled to an Agilent Technologies 6530 accurate-mass Q-TOF LCMS. Identical chromatographic methods were applied and run in negative ionization mode. ACKNOWLEDGMENTS This work was supported by the National Oceanic and Atmospheric Administration (NA19NOS4780181 to B.S.M. and A.E.A.), JSPS KAKENHI (JP23H02146 and JP23K26839 to M.Y.Y.), Tang Genomics Fund (T.P.M.), and graduate student fellowships from UC San Diego (S.M.W.-R., A.B.) and the National Science Foundation (NSF) (GRFP #2021321499 to M.L.M.). REFERENCES 1. ↵ Parsons AF . 1996 . Recent developments in kainoid amino acid chemistry . Tetrahedron 52 : 4149 – 4174 . OpenUrl CrossRef 2. ↵ Maeno Y , Terada R , Kotaki Y , Cho Y , Konoki K , Yotsu-Yamashita M . 2019 . Possible Biosynthetic Products and Metabolites of Kainic Acid from the Red Alga Digenea simplex and Their Biological Activity . J Nat Prod 82 : 1627 – 1633 . OpenUrl CrossRef 3. ↵ Cendes F , Andermann F , Carpenter S , Zatorre RJ , Cashman NR . 1995 . Temporal lobe epilepsy caused by domoic acid intoxication: Evidence for glutamate receptor–mediated excitotoxicity in humans . Ann Neurol 37 : 123 – 126 . OpenUrl CrossRef PubMed Web of Science 4. ↵ Hampson DR , Manalo JL . 1998 . The activation of glutamate receptors by kainic acid and domoic acid . Nat Toxins 6 : 153 – 158 . OpenUrl CrossRef PubMed 5. ↵ Tian Z , Clark BLM , Menard F . 2019 . Kainic Acid-Based Agonists of Glutamate Receptors: SAR Analysis and Guidelines for Analog Design . ACS Chem Neurosci 10 : 4190 – 4198 . OpenUrl CrossRef PubMed 6. ↵ Hasle GR . 1994 . Pseudo-nitzschia as a Genus Distinct from Nitzschia (Bacillariophyceae) . J Phycol 30 : 1036 – 1039 . OpenUrl CrossRef 7. ↵ Bates SS , Bird CJ , Freitas ASW de , Foxall R , Gilgan M , Hanic LA , Johnson GR , McCulloch AW , Odense P , Pocklington R , Quilliam MA , Sim PG , Smith JC , Rao DVS , Todd ECD , Walter JA , Wright JLC . 1989 . Pennate Diatom Nitzschia pungens as the Primary Source of Domoic Acid, a Toxin in Shellfish from Eastern Prince Edward Island, Canada . Can J Fish Aquat Sci 46 : 1203 – 1215 . OpenUrl CrossRef 8. ↵ Wright JLC , Boyd RK , Freitas ASW de , Falk M , Foxall RA , Jamieson WD , Laycock MV , McCulloch AW , McInnes AG , Odense P , Pathak VP , Quilliam MA , Ragan MA , Sim PG , Thibault P , Walter JA , Gilgan M , Richard DJA , Dewar D. 1989 . Identification of domoic acid, a neuroexcitatory amino acid, in toxic mussels from eastern Prince Edward Island . Can J Chem 67 : 481 – 490 . OpenUrl CrossRef Web of Science 9. ↵ Daigo K . 1959 . Studies on the constituents of Chondria armata . II. Isolation of an anthelmintical constituent. J Pharm Soc Japan 353 – 356 . 10. Impellizzeri G , Mangiafico S , Oriente G , Piattelli M , Sciuto S , Fattorusso E , Magno S , Santacroce C , Sica D . 1975 . Amino acids and low-molecular-weight carbohydrates of some marine red algae . Phytochemistry 14 : 1549 – 1557 . OpenUrl CrossRef 11. ↵ Laycock MV , de Freitas ASW , Wright JLC . 1989 . Glutamate agonists from marine algae . J Appl Phycol 1 : 113 – 122 . OpenUrl CrossRef 12. ↵ Bates SS , Hubbard KA , Lundholm N , Montresor M , Leaw CP . 2018 . Pseudo-nitzschia , Nitzschia , and domoic acid: New research since 2011 . Harmful Algae 79 : 3 – 43 . OpenUrl CrossRef PubMed 13. Trainer VL , Bates SS , Lundholm N , Thessen AE , Cochlan WP , Adams NG , Trick CG . 2012 . Pseudo-nitzschia physiological ecology, phylogeny, toxicity, monitoring and impacts on ecosystem health . Harmful Algae 14 : 271 – 300 . OpenUrl CrossRef Web of Science 14. ↵ Anderson DM , Fensin E , Gobler CJ , Hoeglund AE , Hubbard KA , Kulis DM , Landsberg JH , Lefebvre KA , Provoost P , Richlen ML , Smith JL , Solow AR , Trainer VL . 2021 . Marine harmful algal blooms (HABs) in the United States: History, current status and future trends . Harmful Algae 102 : 101975 . OpenUrl CrossRef PubMed 15. ↵ Steele TS , Brunson JK , Maeno Y , Terada R , Allen AE , Yotsu-Yamashita M , Chekan JR , Moore BS . 2022 . Domoic acid biosynthesis in the red alga Chondria armata suggests a complex evolutionary history for toxin production . Proc Natl Acad Sci 119 . 16. ↵ Lundholm N , Jvind Moestrup Ø . 2000 . Morphology of the Marine Diatom Nitzschia navis-varingica , Sp. Nov. (Bacillariophyceae), Another Producer of the Neurotoxin Domoic Acid . J Phycol 36 : 1162 – 1174 . OpenUrl CrossRef 17. ↵ Tan SN , Teng ST , Lim HC , Kotaki Y , Bates SS , Leaw CP , Lim PT . 2016 . Diatom Nitzschia navis-varingica (Bacillariophyceae) and its domoic acid production from the mangrove environments of Malaysia . Harmful Algae 60 : 139 – 149 . OpenUrl CrossRef PubMed 18. ↵ Ayaz F , Eker-Develi E , Sahin M . 2018 . First report of Nitzschia navis-varingica in the Mediterranean Sea and growth stimulatory effects of Nitzschia navis-varingica , Chrysochromulina alifera and Heterocapsa pygmaea on different mammalian cell types . Mol Biol Rep 45 : 571 – 579 . OpenUrl CrossRef PubMed 19. ↵ Puilingi CG , Tan SN , Maeno Y , Leaw CP , Lim PT , Yotsu-Yamashita M , Terada R , Kotaki Y . 2022 . First record of the diatom Nitzschia navis-varingica (Bacillariophyceae) producing amnesic shellfish poisoning-toxins from Papua New Guinea . Toxicon 216 : 65 – 72 . OpenUrl CrossRef 20. ↵ Romero MLJ , Kotaki Y , Lundholm N , Thoha H , Ogawa H , Relox JR , Terada R , Takeda S , Takata Y , Haraguchi K , Endo T , Lim P-T , Kodama M , Fukuyo Y . 2011 . Unique amnesic shellfish toxin composition found in the South East Asian diatom Nitzschia navis-varingica . Harmful Algae 10 : 456 – 462 . OpenUrl CrossRef 21. ↵ Kotaki Y , Furio EF , Satake M , Lundholm N , Katayama T , Koike K , Fulgueras VP , Bajarias FFA , Takata Y , Kobayashi K , Sato S , Fukuyo Y , Kodama M . 2005 . Production of isodomoic acids A and B as major toxin components of a pennate diatom Nitzschia navis-varingica . Toxicon 46 : 946 – 953 . OpenUrl CrossRef PubMed 22. ↵ Tan SN , Kotaki Y , Teng ST , Lim HC , Gao C , Lundholm N , Wolf M , Gu H , Lim PT , Leaw CP . 2025 . Intraspecific genetic diversity with unrestricted gene flow in the domoic acid-producing diatom Nitzschia navis - varingica (Bacillariophyceae) from the Western Pacific . Harmful Algae 141 : 102769 . OpenUrl CrossRef PubMed 23. ↵ Brunson JK , McKinnie SMK , Chekan JR , McCrow JP , Miles ZD , Bertrand EM , Bielinski VA , Luhavaya H , Oborník M , Smith GJ , Hutchins DA , Allen AE , Moore BS . 2018 . Biosynthesis of the neurotoxin domoic acid in a bloom-forming diatom . Science 361 : 1356 – 1358 . OpenUrl Abstract / FREE Full Text 24. ↵ He Z , Xu Q , Chen Y , Liu S , Song H , Wang H , Leaw CP , Chen N . 2024 . Acquisition and evolution of the neurotoxin domoic acid biosynthesis gene cluster in Pseudo-nitzschia species . Commun Biol 7 : 1 – 12 . OpenUrl CrossRef PubMed 25. ↵ Mager S , Manfellotto F , Ruggiero A , Di Tuccio V , Cerino F , Accoroni S , Nishimura T , Mikhno M , Fattorini N , Turk Dermastia T , Arapov J , Skejic S , Rhodes L , Smith K , Longo A , Manzari C , Campbell L , Pesole G , Sanges R , Raffini F , Ruggiero MV , Russo MT , Montresor M , Ferrante MI . 2025 . Genomic diversity in time and space in the toxic diatom Pseudo-nitzschia multistriata . Harmful Algae 142 : 102791 . OpenUrl CrossRef PubMed 26. ↵ Harðardóttir S , Wohlrab S , Hjort DM , Krock B , Nielsen TG , John U , Lundholm N . 2019 . Transcriptomic responses to grazing reveal the metabolic pathway leading to the biosynthesis of domoic acid and highlight different defense strategies in diatoms . BMC Mol Biol 20 : 7 . OpenUrl PubMed 27. ↵ Brunson JK , Thukral M , Ryan JP , Anderson CR , Kolody BC , James CC , Chavez FP , Leaw CP , Rabines AJ , Venepally P , Fussy Z , Zheng H , Kudela RM , Smith GJ , Moore BS , Allen AE . 2024 . Molecular forecasting of domoic acid during a pervasive toxic diatom bloom . Proc Natl Acad Sci 121 : e2319177121 . OpenUrl CrossRef PubMed 28. ↵ Chekan JR , McKinnie SMK , Moore ML , Poplawski SG , Michael TP , Moore BS . 2019 . Scalable Biosynthesis of the Seaweed Neurochemical, Kainic Acid . Angew Chem Int Ed Engl 58 : 8454 – 8457 . OpenUrl CrossRef 29. ↵ Maeno Y , Kotaki Y , Terada R , Cho Y , Konoki K , Yotsu-Yamashita M . 2018 . Six domoic acid related compounds from the red alga, Chondria armata , and domoic acid biosynthesis by the diatom, Pseudo-nitzschia multiseries . Sci Rep 8 : 356 . OpenUrl CrossRef PubMed 30. ↵ Chekan JR , McKinnie SMK , Noel JP , Moore BS . 2020 . Algal neurotoxin biosynthesis repurposes the terpene cyclase structural fold into an N-prenyltransferase . Proc Natl Acad Sci 117 : 12799 – 12805 . OpenUrl Abstract / FREE Full Text 31. ↵ Maeno Y , Kotaki Y , Terada R , Hidaka M , Cho Y , Konoki K , Yotsu-Yamashita M . 2021 . Preparation of domoic acid analogues using a bioconversion system, and their toxicity in mice . Org Biomol Chem 19 : 7894 – 7902 . OpenUrl CrossRef PubMed 32. Chang W , Yang Z-J , Tu Y-H , Chien T-C . 2019 . Reaction Mechanism of a Nonheme Iron Enzyme Catalyzed Oxidative Cyclization via C–C Bond Formation . Org Lett 21 : 228 – 232 . OpenUrl CrossRef PubMed 33. ↵ Hopiavuori AR , McKinnie SMK . 2023 . Algal Kainoid Synthases Exhibit Substrate-Dependent Hydroxylation and Cyclization Activities . ACS Chem Biol 18 : 2457 – 2463 . OpenUrl CrossRef PubMed 34. ↵ Mann DG , Trobajo R , Sato S , Li C , Witkowski A , Rimet F , Ashworth MP , Hollands RM , Theriot EC . 2021 . Ripe for reassessment: A synthesis of available molecular data for the speciose diatom family Bacillariaceae . Mol Phylogenet Evol 158 : 106985 . OpenUrl CrossRef PubMed 35. ↵ Oliver A , Podell S , Pinowska A , Traller JC , Smith SR , McClure R , Beliaev AS , Bohutskyi P , Hill EA , Rabines A , Zheng H , Allen LZ , Kuo A , Grigoriev IV , Allen AE , Hazlebeck DA , Allen EE . 2021 . Diploid genomic architecture of Nitzschia inconspicua , an elite biomass production diatom . Sci Rep 11 . 36. ↵ Chen J , Huang Y , Shu Y , Hu X , Wu D , Jiang H , Wang K , Liu W , Fu W . 2022 . Recent Progress on Systems and Synthetic Biology of Diatoms for Improving Algal Productivity . Front Bioeng Biotechnol 10 . 37. ↵ Osuna-Cruz CM , Bilcke G , Vancaester E , De Decker S , Bones AM , Winge P , Poulsen N , Bulankova P , Verhelst B , Audoor S , Belisova D , Pargana A , Russo M , Stock F , Cirri E , Brembu T , Pohnert G , Piganeau G , Ferrante MI , Mock T , Sterck L , Sabbe K , De Veylder L , Vyverman W , Vandepoele K . 2020 . The Seminavis robusta genome provides insights into the evolutionary adaptations of benthic diatoms. 1 . Nat Commun 11 : 3320 . OpenUrl CrossRef PubMed 38. ↵ Burki F , Roger AJ , Brown MW , Simpson AGB . 2020 . The New Tree of Eukaryotes . Trends Ecol Evol 35 : 43 – 55 . OpenUrl CrossRef PubMed 39. ↵ The Norwegian Culture Collection of Algae | NORCCA . https://norcca.scrol.net/ . Retrieved 15 April 2025. 40. Russo MT , Vitale L , Entrambasaguas L , Anestis K , Fattorini N , Romano F , Minucci C , De Luca P , Biffali E , Vyverman W , Sanges R , Montresor M , Ferrante MI . 2018 . MRP3 is a sex determining gene in the diatom Pseudo-nitzschia multistriata . Nat Commun 9 : 5050 . OpenUrl CrossRef PubMed 41. Mock T , Otillar RP , Strauss J , McMullan M , Paajanen P , Schmutz J , Salamov A , Sanges R , Toseland A , Ward BJ , Allen AE , Dupont CL , Frickenhaus S , Maumus F , Veluchamy A , Wu T , Barry KW , Falciatore A , Ferrante MI , Fortunato AE , Glöckner G , Gruber A , Hipkin R , Janech MG , Kroth PG , Leese F , Lindquist EA , Lyon BR , Martin J , Mayer C , Parker M , Quesneville H , Raymond JA , Uhlig C , Valas RE , Valentin KU , Worden AZ , Armbrust EV , Clark MD , Bowler C , Green BR , Moulton V , van Oosterhout C , Grigoriev IV . 2017 . Evolutionary genomics of the cold-adapted diatom Fragilariopsis cylindrus . 7638. Nature 541 : 536 – 540 . OpenUrl CrossRef PubMed 42. Tanaka T , Maeda Y , Veluchamy A , Tanaka M , Abida H , Maréchal E , Bowler C , Muto M , Sunaga Y , Tanaka M , Yoshino T , Taniguchi T , Fukuda Y , Nemoto M , Matsumoto M , Wong PS , Aburatani S , Fujibuchi W . 2015 . Oil Accumulation by the Oleaginous Diatom Fistulifera solaris as Revealed by the Genome and Transcriptome . Plant Cell 27 : 162 – 176 . OpenUrl Abstract / FREE Full Text 43. ↵ Roberts WR , Siepielski AM , Alverson AJ . 2024 . Diatom abundance in the polar oceans is predicted by genome size . PLOS Biol 22 : e3002733 . OpenUrl CrossRef PubMed 44. ↵ Tanaka K , Choo P-S . 2000 . Influences of Nutrient Outwelling from the Mangrove Swamp on the Distribution of Phytoplankton in the Matang Mangrove Estuary, Malaysia . J Oceanogr 56 : 69 – 78 . OpenUrl CrossRef 45. Pandey PK , Pathak R , Yumnam R , Mallik SK . 2024 . Benthic Microbial Community in the Aquatic Environment , p. 16 . In Handbook of Aquatic Microbiology , 1st ed. CRC Press, Boca Raton . 46. ↵ Manokaran S , Joydas TV , Khan A . 2022 . Chapter 6 - Physico-chemical factors regulating marine benthos structure and function , p. 209–250. In Godson , PS , Vincent , SGT , Krishnakumar , S (eds.), Ecology and Biodiversity of Benthos . Elsevier . 47. ↵ Vanelslander B , Paul C , Grueneberg J , Prince EK , Gillard J , Sabbe K , Pohnert G , Vyverman W . 2012 . Daily bursts of biogenic cyanogen bromide (BrCN) control biofilm formation around a marine benthic diatom . Proc Natl Acad Sci 109 : 2412 – 2417 . OpenUrl Abstract / FREE Full Text 48. Moore RM , Webb M , Tokarczyk R , Wever R . 1996 . Bromoperoxidase and iodoperoxidase enzymes and production of halogenated methanes in marine diatom cultures . J Geophys Res Oceans 101 : 20899 – 20908 . OpenUrl CrossRef 49. ↵ Hill VL , Manley SL . 2009 . Release of reactive bromine and iodine from diatoms and its possible role in halogen transfer in polar and tropical oceans . Limnol Oceanogr 54 : 812 – 822 . OpenUrl CrossRef 50. Hernández Javier L , Benzekri H , Gut M , Claros MG , van Bergeijk S , Cañavate JP , Manchado M . 2018 . Characterization of Iodine-Related Molecular Processes in the Marine Microalga Tisochrysis lutea (Haptophyta) . Front Mar Sci 5 . 51. Hughes C , Malin G , Nightingale PD , Liss PS . 2006 . The effect of light stress on the release of volatile iodocarbons by three species of marine microalgae . Limnol Oceanogr 51 : 2849 – 2854 . OpenUrl CrossRef 52. Paul C , Pohnert G . 2011 . Production and role of volatile halogenated compounds from marine algae . Nat Prod Rep 28 : 186 – 195 . OpenUrl CrossRef PubMed 53. ↵ de laCuesta JL , Manley SL . 2009 . Iodine assimilation by marine diatoms and other phytoplankton in nitrate-replete conditions . Limnol Oceanogr 54 : 1653 – 1664 . OpenUrl CrossRef 54. ↵ Smit A , Hubley R , Green P . 2013 -2015 . RepeatMasker Open - 4 . 0 . http://www.repeatmasker.org OpenUrl 55. ↵ Gschloessl B , Guermeur Y , Cock JM . 2008 . HECTAR: A method to predict subcellular targeting in heterokonts . BMC Bioinformatics 9 : 393 . OpenUrl CrossRef PubMed 56. ↵ Teufel F , Almagro Armenteros JJ , Johansen AR , Gíslason MH , Pihl SI , Tsirigos KD , Winther O , Brunak S , von Heijne G , Nielsen H . 2022 . SignalP 6.0 predicts all five types of signal peptides using protein language models . Nat Biotechnol 40 : 1023 – 1025 . OpenUrl CrossRef PubMed 57. ↵ Rokas A , Mead ME , Steenwyk JL , Raja HA , Oberlies NH . 2020 . Biosynthetic gene clusters and the evolution of fungal chemodiversity . Nat Prod Rep 37 : 868 – 878 . OpenUrl CrossRef PubMed 58. Li Q , Ramasamy S , Singh P , Hagel JM , Dunemann SM , Chen X , Chen R , Yu L , Tucker JE , Facchini PJ , Yeaman S . 2020 . Gene clustering and copy number variation in alkaloid metabolic pathways of opium poppy . Nat Commun 11 : 1190 . OpenUrl CrossRef PubMed 59. Qi X , Bakht S , Qin B , Leggett M , Hemmings A , Mellon F , Eagles J , Werck-Reichhart D , Schaller H , Lesot A , Melton R , Osbourn A . 2006 . A different function for a member of an ancient and highly conserved cytochrome P450 family: From essential sterols to plant defense . Proc Natl Acad Sci 103 : 18848 – 18853 . OpenUrl Abstract / FREE Full Text 60. Bai Y , Cao T , Dautermann O , Buschbeck P , Cantrell MB , Chen Y , Lein CD , Shi X , Ware MA , Yang F , Zhang H , Zhang L , Peers G , Li X , Lohr M . 2022 . Green diatom mutants reveal an intricate biosynthetic pathway of fucoxanthin . Proc Natl Acad Sci 119 : e2203708119 . OpenUrl CrossRef PubMed 61. ↵ Cullen A , D’Agostino PM , Mazmouz R , Pickford R , Wood S , Neilan BA . 2018 . Insertions within the Saxitoxin Biosynthetic Gene Cluster Result in Differential Toxin Profiles . ACS Chem Biol 13 : 3107 – 3114 . OpenUrl CrossRef PubMed 62. ↵ Vancaester E , Depuydt T , Osuna-Cruz CM , Vandepoele K . 2020 . Comprehensive and Functional Analysis of Horizontal Gene Transfer Events in Diatoms . Mol Biol Evol 37 : 3243 – 3257 . OpenUrl CrossRef PubMed 63. ↵ Selander E , Kubanek J , Hamberg M , Andersson MX , Cervin G , Pavia H . 2015 . Predator lipids induce paralytic shellfish toxins in bloom-forming algae . Proc Natl Acad Sci 112 : 6395 – 6400 . OpenUrl Abstract / FREE Full Text 64. Lundholm N , Krock B , John U , Skov J , Cheng J , Pančić M , Wohlrab S , Rigby K , Nielsen TG , Selander E , Harðardóttir S . 2018 . Induction of domoic acid production in diatoms— Types of grazers and diatoms are important . Harmful Algae 79 : 64 – 73 . OpenUrl CrossRef PubMed 65. Cochlan WP , Bill BD , Cailipan AB , Trainer VL . 2023 . Domoic acid production by Pseudo-nitzschia australis : Re-evaluating the role of macronutrient limitation on toxigenicity . Harmful Algae 125 : 102431 . OpenUrl CrossRef PubMed 66. Lema KA , Latimier M , Nézan É , Fauchot J , Le Gac M . 2017 . Inter and intra-specific growth and domoic acid production in relation to nutrient ratios and concentrations in Pseudo-nitzschia : phosphate an important factor . Harmful Algae 64 : 11 – 19 . OpenUrl CrossRef PubMed 67. ↵ Kelly KJ , Mansour A , Liang C , Kim AM , Mancini LA , Bertin MJ , Jenkins BD , Hutchins DA , Fu F-X . 2023 . Simulated upwelling and marine heatwave events promote similar growth rates but differential domoic acid toxicity in Pseudo-nitzschia australis . Harmful Algae 127 : 102467 . OpenUrl CrossRef PubMed 68. ↵ Berge T , Hansen PJ , Moestrup Ø . 2008 . Prey size spectrum and bioenergetics of the mixotrophic dinoflagellate Karlodinium armiger . Aquat Microb Ecol 50 : 289 – 299 . OpenUrl CrossRef 69. ↵ Lundholm N , Hansen PJ , Kotaki Y . 2004 . Effect of pH on growth and domoic acid production by potentially toxic diatoms of the genera Pseudo-nitzschia and Nitzschia . Mar Ecol Prog Ser 273 : 1 – 15 . OpenUrl CrossRef Web of Science 70. ↵ Tatters AO , Fu F-X , Hutchins DA . 2012 . High CO2 and Silicate Limitation Synergistically Increase the Toxicity of Pseudo-nitzschia fraudulenta . PLoS ONE 7 : 1 – 7 . OpenUrl CrossRef PubMed 71. ↵ Zhang J-M , Liu X , Wei Q , Ma C , Li D , Zou Y . 2022 . Berberine bridge enzyme-like oxidase-catalysed double bond isomerization acts as the pathway switch in cytochalasin synthesis. 1 . Nat Commun 13 : 225 . OpenUrl CrossRef PubMed 72. ↵ Nett RS , Dho Y , Low Y-Y , Sattely ES . 2021 . A metabolic regulon reveals early and late acting enzymes in neuroactive Lycopodium alkaloid biosynthesis . Proc Natl Acad Sci 118 . 73. ↵ Davison J , al Fahad A , Cai M , Song Z , Yehia SY , Lazarus CM , Bailey AM , Simpson TJ , Cox RJ . 2012 . Genetic, molecular, and biochemical basis of fungal tropolone biosynthesis . Proc Natl Acad Sci 109 : 7642 – 7647 . OpenUrl Abstract / FREE Full Text 74. ↵ Helfrich EJN , Piel J . 2016 . Biosynthesis of polyketides by trans-AT polyketide synthases . Nat Prod Rep 33 : 231 – 316 . OpenUrl CrossRef PubMed 75. Lohr F , Jenniches I , Frizler M , J. Meehan M , Sylvester M , Schmitz A , Gütschow M , C. Dorrestein P , M. König G , F. Schäberle T . 2013 . α,β → β,γ double bond migration in corallopyronin A biosynthesis . Chem Sci 4 : 4175 – 4180 . OpenUrl CrossRef 76. ↵ Kusebauch B , Busch B , Scherlach K , Roth M , Hertweck C . 2010 . Functionally Distinct Modules Operate Two Consecutive α,β→β,γ Double-Bond Shifts in the Rhizoxin Polyketide Assembly Line . Angew Chem Int Ed 49 : 1460 – 1464 . OpenUrl CrossRef PubMed Web of Science 77. ↵ Keller Y , Bouvier F , d’Harlingue A , Camara B . 1998 . Metabolic compartmentation of plastid prenyllipid biosynthesis--evidence for the involvement of a multifunctional geranylgeranyl reductase . Eur J Biochem 251 : 413 – 417 . OpenUrl CrossRef PubMed Web of Science 78. ↵ Gomez Maqueo Chew A , Frigaard N-U , Bryant DA . 2008 . Identification of the bchP Gene, Encoding Geranylgeranyl Reductase in Chlorobaculum tepidum . J Bacteriol 190 : 747 – 749 . OpenUrl Abstract / FREE Full Text 79. ↵ Kidwell MG . 2002 . Transposable elements and the evolution of genome size in eukaryotes . Genetica 115 : 49 – 63 . OpenUrl CrossRef PubMed Web of Science 80. ↵ Wicker T , Gundlach H , Spannagl M , Uauy C , Borrill P , Ramírez-González RH , De Oliveira R , Mayer KFX , Paux E , Choulet F , International Wheat Genome Sequencing Consortium . 2018 . Impact of transposable elements on genome structure and evolution in bread wheat . Genome Biol 19 : 103 . OpenUrl CrossRef PubMed 81. ↵ Bergmann C . 1847 . Über die Verhältnisse der Wärmeökonomie der Thiere zu ihrer Grösse [About the relationship of the thermal economy of animals to their body size.] , 3rd ed. Vandenhoeck und Ruprecht . 1 : 595 – 708 . OpenUrl 82. Sommer U , Peter KH , Genitsaris S , Moustaka-Gouni M . 2017 . Do marine phytoplankton follow Bergmann’s rule sensu lato? Biol Rev 92 : 1011 – 1026 . OpenUrl CrossRef 83. ↵ Barton AD , Pershing AJ , Litchman E , Record NR , Edwards KF , Finkel ZV , Kiørboe T , Ward BA . 2013 . The biogeography of marine plankton traits . Ecol Lett 16 : 522 – 534 . OpenUrl CrossRef PubMed 84. ↵ Hattich GSI , Jokinen S , Sildever S , Gareis M , Heikkinen J , Junghardt N , Segovia M , Machado M , Sjöqvist C . 2024 . Temperature optima of a natural diatom population increases as global warming proceeds . Nat Clim Change 14 : 518 – 525 . OpenUrl CrossRef 85. Xu D , Zheng G , Brennan G , Wang Z , Jiang T , Sun K , Fan X , Bowler C , Zhang X , Zhang Y , Wang W , Wang Y , Li Y , Wu H , Li Y , Fu F-X , Hutchins DA , Tan Z , Ye N . 2023 . Plastic responses lead to increased neurotoxin production in the diatom Pseudo-nitzschia under ocean warming and acidification . 4. ISME J 17 : 525 – 536 . OpenUrl 86. ↵ Adams GL , Pichler DE , Cox EJ , O’Gorman EJ , Seeney A , Woodward G , Reuman DC . 2013 . Diatoms can be an important exception to temperature–size rules at species and community levels of organization . Glob Change Biol 19 : 3540 – 3552 . OpenUrl CrossRef 87. ↵ Grunow A . 1862 . Die österreichischen Diatomaceen nebst Anschluss einiger neuen Arten von andern Lokalitäten und einer kritischen Uebersicht der bisher bekannten Gattungen und Arten. Erste Folge. Familie Nitzschieae . Verhandlungen Kais Zool Ges Wien 12 : 315 . OpenUrl 88. ↵ Rho M , Tang H , Ye Y . 2010 . FragGeneScan: predicting genes in short and error-prone reads . Nucleic Acids Res 38 : e191 . OpenUrl CrossRef PubMed 89. Aramaki T , Blanc-Mathieu R , Endo H , Ohkubo K , Kanehisa M , Goto S , Ogata H . 2020 . KofamKOALA: KEGG Ortholog assignment based on profile HMM and adaptive score threshold . Bioinforma Oxf Engl 36 : 2251 – 2252 . OpenUrl 90. ↵ Buchfink B , Xie C , Huson DH . 2015 . Fast and sensitive protein alignment using DIAMOND . Nat Methods 12 : 59 – 60 . OpenUrl CrossRef PubMed 91. ↵ Cantalapiedra CP , 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 . Mol Biol Evol 38 : 5825 – 5829 . OpenUrl CrossRef PubMed 92. Huerta-Cepas J , Szklarczyk D , Heller D , Hernández-Plaza A , Forslund SK , Cook H , Mende DR , Letunic I , Rattei T , Jensen LJ , 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 Res 47 : D309 – D314 . OpenUrl CrossRef PubMed 93. ↵ Jones P , Binns D , Chang H-Y , Fraser M , Li W , McAnulla C , McWilliam H , Maslen J , Mitchell A , Nuka G , Pesseat S , Quinn AF , Sangrador-Vegas A , Scheremetjew M , Yong S- Y , Lopez R , Hunter S . 2014 . InterProScan 5: genome-scale protein function classification . Bioinforma Oxf Engl 30 : 1236 – 1240 . OpenUrl 94. ↵ Delaye L , Vargas C , Latorre A , Moya A . 2020 . Inferring Horizontal Gene Transfer with DarkHorse , Phylomizer, and ETE Toolkits. Methods Mol Biol Clifton NJ 2075 : 355 – 369 . OpenUrl 95. ↵ Eddy SR . 2011 . Accelerated Profile HMM Searches . PLOS Comput Biol 7 : e1002195 . OpenUrl CrossRef PubMed 96. Boratyn GM , Schäffer AA , Agarwala R , Altschul SF , Lipman DJ , Madden TL . 2012 . Domain enhanced lookup time accelerated BLAST . Biol Direct 7 : 12 . OpenUrl CrossRef PubMed 97. ↵ Camacho C , Coulouris G , Avagyan V , Ma N , Papadopoulos J , Bealer K , Madden TL . 2009 . BLAST+: architecture and applications . BMC Bioinformatics 10 : 421 . OpenUrl CrossRef PubMed 98. ↵ Kalign <EMBL-EBI. https://www.ebi.ac.uk/jdispatcher/msa/kalign?stype=protein . Retrieved 28 March 2025. 99. ↵ Oliveira RRM , Vasconcelos S , Oliveira G . 2022 . SPLACE: A tool to automatically SPLit, Align, and ConcatenatE genes for phylogenomic inference of several organisms . Front Bioinforma 2 . 100. ↵ Wickham H. 2016 . ggplot2: Elegant Graphics for Data Analysis . Springer-Verlag New York . 101. Wilkins D , Kurtz Z . 2023 . gggenes: Draw Gene Arrow Maps in “ggplot2” (0.5.1) . 102. Chamberlain S , Szoecs E , Foster Z , Arendsee Z , Boettiger C , Ram K , Bartomeus I , Baumgartner J , O’Donnell J , Oksanen J , Tzovaras BG , Marchand P , Tran V , Salmon M , Li G , Grenié M , rOpenSci . 2025 . taxize: Taxonomic Information from Around the Web (v0.10.0) . 103. ↵ RStudio Team . 2020 . RStudio: Integrated Development for R. RStudio, PBC ., Boston, MA . 104. ↵ Gilchrist CLM , Chooi Y-H . 2021 . clinker & clustermap.js: automatic generation of gene cluster comparison figures . Bioinformatics 37 : 2473 – 2475 . OpenUrl CrossRef PubMed 105. ↵ Canada NRC . 2015 . CRM-DA-h | National Research Council Canada . https://nrc.canada.ca/en/certifications-evaluations-standards/certified-reference-materials/list/48 . Retrieved 3 April 2025. 106. ↵ Thukral M , Koester I , Petras D , Torres RR , Aron A , Gentry E , Siwe-Noundou X , Dorrington R , McPhail K , Hartmann A , Aluwihare L . 2022 . Protocol for PPL Solid Phase Extraction for Dissolved Organic Matter (DOM) Sample Preparation for LC-MS/MS . https://www.protocols.io/view/protocol-for-ppl-solid-phase-extraction-for-dissol-b4×8qxrw . View the discussion thread. Back to top Previous Next Posted April 24, 2025. Download PDF 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 Domoic acid biosynthesis and genome expansion in Nitzschia navis-varingica 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 Domoic acid biosynthesis and genome expansion in Nitzschia navis-varingica Steffaney M. Wood-Rocca , Nicholas Allsing , Yasuhiro Ashida , Masaki Mochizuki , Malia L. Moore , Zoltán Füssy , Yuichi Kotaki , Clyde Puilingi , Yukari Maeno , Aodhan W. Beattie , Andrew E. Allen , Mari Yotsu-Yamashita , Todd P. Michael , Bradley S. Moore bioRxiv 2025.04.19.649686; doi: https://doi.org/10.1101/2025.04.19.649686 Share This Article: Copy Citation Tools Domoic acid biosynthesis and genome expansion in Nitzschia navis-varingica Steffaney M. Wood-Rocca , Nicholas Allsing , Yasuhiro Ashida , Masaki Mochizuki , Malia L. Moore , Zoltán Füssy , Yuichi Kotaki , Clyde Puilingi , Yukari Maeno , Aodhan W. Beattie , Andrew E. Allen , Mari Yotsu-Yamashita , Todd P. Michael , Bradley S. Moore bioRxiv 2025.04.19.649686; doi: https://doi.org/10.1101/2025.04.19.649686 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 Genomics Subject Areas All Articles Animal Behavior and Cognition (7635) Biochemistry (17690) Bioengineering (13892) Bioinformatics (41936) Biophysics (21451) Cancer Biology (18588) Cell Biology (25499) Clinical Trials (138) Developmental Biology (13378) Ecology (19899) Epidemiology (2067) Evolutionary Biology (24320) Genetics (15609) Genomics (22506) Immunology (17736) Microbiology (40394) Molecular Biology (17181) Neuroscience (88603) Paleontology (666) Pathology (2832) Pharmacology and Toxicology (4824) Physiology (7641) Plant Biology (15152) Scientific Communication and Education (2045) Synthetic Biology (4294) Systems Biology (9825) Zoology (2271)