A draft genome assembly of the agricultural pest Leucoptera coffeella and analysis of its dsRNA processing machinery is a key step towards RNAi-based biopesticides in Lepidoptera

A draft genome assembly of the agricultural pest Leucoptera coffeella and analysis of its dsRNA processing machinery is a key step towards RNAi-based biopesticides in Lepidoptera | 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 A draft genome assembly of the agricultural pest Leucoptera coffeella and analysis of its dsRNA processing machinery is a key step towards RNAi-based biopesticides in Lepidoptera View ORCID Profile Jay K. Goldberg , Leonardo A. Vidal , Erick S.L. Queiroz , Eliza F.M.B Nascimento , Marcos J.A. Viana , Wellington R. Clarindo , Andrea Q. Maranhao , Natália F. Martins , Érika V.S. Albuquerque doi: https://doi.org/10.1101/2025.07.28.667214 Jay K. Goldberg 1 School of Life Sciences, Arizona State University , Tempe, AZ, USA 85287 2 Department of Crop Genetics, John Innes Centre , Norwich, Norfolk, UK NR41UD Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Jay K. Goldberg For correspondence: erika.albuquerque{at}embrapa.br jay.goldberg{at}jic.ac.uk jay.goldberg{at}asu.edu Leonardo A. Vidal 3 Brasil Embrapa Recursos Genéticos e Biotecnologia , Brasília, DF 70770-917, Brasil Find this author on Google Scholar Find this author on PubMed Search for this author on this site Erick S.L. Queiroz 4 Departamento de Biologia Molecular, Universidade de Brasília , Brasília, DF 70910-900, Brasil Find this author on Google Scholar Find this author on PubMed Search for this author on this site Eliza F.M.B Nascimento 3 Brasil Embrapa Recursos Genéticos e Biotecnologia , Brasília, DF 70770-917, Brasil Find this author on Google Scholar Find this author on PubMed Search for this author on this site Marcos J.A. Viana 5 Embrapa Agroindústria Tropical , Rua Dra Sara Mesquita 2270, Planalto do Pici, Fortaleza, CE 60511-110 Find this author on Google Scholar Find this author on PubMed Search for this author on this site Wellington R. Clarindo 6 Departamento de Biologia Geral, Universidade Federal de Viçosa , Viçosa-MG, Brasil, 36570-900, Brasil Find this author on Google Scholar Find this author on PubMed Search for this author on this site Andrea Q. Maranhao 3 Brasil Embrapa Recursos Genéticos e Biotecnologia , Brasília, DF 70770-917, Brasil Find this author on Google Scholar Find this author on PubMed Search for this author on this site Natália F. Martins 5 Embrapa Agroindústria Tropical , Rua Dra Sara Mesquita 2270, Planalto do Pici, Fortaleza, CE 60511-110 Find this author on Google Scholar Find this author on PubMed Search for this author on this site Érika V.S. Albuquerque 3 Brasil Embrapa Recursos Genéticos e Biotecnologia , Brasília, DF 70770-917, Brasil Find this author on Google Scholar Find this author on PubMed Search for this author on this site For correspondence: erika.albuquerque{at}embrapa.br jay.goldberg{at}jic.ac.uk jay.goldberg{at}asu.edu Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract The Coffee Leaf Miner (Lepidoptera: Lyonetiidae: Leucoptera coffeella ) is a specialist herbivore and major global pest of coffee plants. Current pest control strategies primarily rely on chemical pesticides, leading to human and environmental constraints. Additionally, the emergence of insecticide-resistant populations underscores the urgent need for more specific and efficient pest management strategies. The development of novel techniques for controlling this insect pest requires rigorous interrogation of its physiology and interactions with host plants at a molecular/genetic level. To enable future research in this vein, we sequenced and assembled a draft L. coffeella genome using PacBio highly accurate long-reads (HiFi). Our assembly is comprised of 1615 contigs showing fragmentation, yet the majority of gene content is represented (BUSCO complete = 91.7%). We annotated 17467 protein-coding genes within our assembly, seven of which are core components of the small interfering RNA machinery. The expression of these genes was further confirmed via qPCR. This analysis – and the underlying genomic data – highlights potential targets for RNAi-based biopesticide development and will serve as the foundation for important future research aimed at protecting global coffee production from one of its most destructive pests. Introduction Lepidopteran insects, which include butterflies and moths, are estimated to represent more than 70% of agricultural pests. Current control practices rely on the application of chemical pesticides to the detriment of off-target species and, in some cases, human health ( Pathak et al. 2022 ), causing global biodiversity losses ( Raven and Wagner 2021 ) and triggering insecticide resistance in important crop pests ( Barathi et al. 2024 ; Willow and Smagghe 2025 ). The Coffee Leaf Miner (CLM; Lepidoptera: Lyonetiidae: Leucoptera coffeella ; Figure 1 ) is a great hazardous pest to one of the most traded crops in the world. This monophagous lepidoptera is currently a cosmopolitan pest present in all coffee producing countries, causing 87% losses on both Coffea arabica and Coffea canephora plantations ( Picanço Filho et al. 2024 ). Leaf damage is caused by larval feeding behavior, which consists of burrowing mines into the mesophyll ( Figure 1 ), leading to necrosis and consequently reducing photosynthesis, accelerating senescence, and causing defoliation that weaken plant growth and reduce yield ( Dantas et al., 2021 ). CLM reproduction is favored by high temperatures and dry climatic conditions, leading to worsening infestations that are further exacerbated by anthropogenic climate change. ( Leite et al. 2020 ). Download figure Open in new tab Figure 1. Symptoms and developmental stages of L. coffeella in coffee plants. The pictures show: (A) Coffee plant ( C. arabica ) heavily infested by the CLM, showing chlorosis and defoliation; (B) Leaf damage caused by larval feeding, with characteristic necrotic mines along the leaf blade; (C) Larva L2 isolated from leaf tissue after removal from mine; (D) Pupa within its silk protective structure adhered to the abaxial leaf surface; (E) Adult moth of L. coffeella , showing characteristic moth morphology and microlepidoptera size. Scale bars = 1 mm. RNA interference (RNAi) and post-transcriptional gene silencing continue to offer promising solutions for developing alternative, species-specific biopesticides ( Ortolá and Daròs 2024 ). RNAi-based technologies, which are centered around the application of double-stranded RNA (dsRNA) constructs to silence genes in target species ( Niu et al. 2024 ), include low-risk biopesticides that reduce pest loads on crops while avoiding unwanted environmental consequences ( Willow and Smagghe 2025 ). RNAi constructs can be directly engineered into host plants themselves or delivered by non-transgenic spray-induced methods that may avoid the regulatory complications surrounding genetic modification ( Chen et al. 2025 ). In order to design effective RNAi-based pesticides, we must enhance our fundamental understanding of these mechanisms in insect species of interest. To enable molecular biological studies of CLM and the development of targeted RNAi-based pest control solutions, we sequenced and assembled a draft genome for L. coffeella . Due to the small size of this insect, we used a pooled-sample of multiple individuals that we sequenced with PacBio highly accurate long-reads (HiFi). To improve the knowledge about the RNAi machinery genes in Lepidopteran pests, we identified in our assembly multiple genes that are involved with exogenous dsRNA processing pathway and validated their active expression along the development stages. Additionally, BUSCO categories allow the search of species-specific biopesticide targets. Our analysis, and the underlying genomic and transcriptomic datasets, will serve as a firm foundation for future research – fundamental and applied – on CLM and its interactions with host plants. Materials and Methods Sample collection, preparation, and sequencing Genomic DNA (gDNA) was obtained from a pool of individuals at the pupa stage ( Figure 1 ), collected from C. arabica leaves collected from Embrapa Cerrados – Planaltina – D.F., Brazil. A modified protocol of the EZNA insect DNA kit (Omega BioTek, Cat. No.: D0926-02) was used for the extractions, as described in ( Nascimento et al. 2022 ). DNA quantity and quality were analyzed using NanoDrop, Qubit, agarose gel electrophoresis, and Femto Pulse. High molecular weight gDNA was stored at 4 °C until sequencing began. Genomic sequencing was carried out by Precision Genomics (Gangseo-gu, Seoul, SK) The samples were prepared using a PacBio HiFi Express Prep kit and sequenced using the Sequel II platform. Total RNA was extracted from CLM at different developmental stages: three larval instars (L2, L3, and L4), pupae, male and female adults. Extracted RNA was cleaned with a ReliaPrep RNA Tissue Miniprep System kit (Promega, Cat. No.: PRZ6111), applying the modified protocol described in ( Nascimento et al. 2022 ). After extraction, the concentration and quality of the RNA were evaluated using NanoDrop, Qubit, and Bioanalyzer, and the sample was stored immediately at -80 °C until sequencing using Illumina technology Novaseq 6000. Genome size estimate via flow cytometry Adult insects (male and female) were collected from two populations in Brazil (Viçosa-MG and Barreiras-BA) and dissected in commercial saline solution. Nuclear extraction and isolation were processed in a BD Accuri™ C6 Flow Cytometer (Accuri, Belgium) and the flow cytometry histograms were analyzed considering G0/G1 fluorescent peaks with coefficient of variation below 5 percent for nuclear 2C value measurement. Mean nuclear 2C values were converted to Mbp, considering that 1C pg is equivalent to 978 Mbp ( Praça-Fontes et al. 2011 ). Genome assembly and annotation CCS output (ie: HiFi reads; N reads = 1712831; N50 = 14954) were found to have a highly inflated number of low-coverage contigs (Figure S1) which could be due to genetic heterogeneity or the presence of contamination. To identify contaminant reads, we first produced a metagenomic assembly of our data using metaMDBG ( Benoit et al., 2024 ). We then used the blobtoolkit pipeline ( Challis et al., 2020 ), which calls on minimap2 ( Li 2018 ) and blastn ( Camacho et al., 2009 ), to identify contaminant contigs and filter our PacBio HiFi reads to remove contigs identified as anything other than Lepidoptera (N = 63334). Kmer analysis of both raw and filtered reads was conducted using jellyfish ( Marcais and Kingsford 2012 ) and GenomeScope2.0 ( Ranallo-Benavidez et al. 2020 ). Filtered reads (N = 1649497) were then assembled using hifiasm 2.4.0 ( Cheng et al. 2021 ). We assessed the completeness of this assembly using BUSCO v5.4.7 within the lepidoptera_odb10 dataset and determined that our genome was heavily duplicated due to the presence of alternative haplotigs resulting from our pooled sample of multiple insects. To remove duplicated regions, we ran the purge_dups algorithm v1.2.6 ( Guan et al. 2020 ) five times with the -e option removed to include both duplications at the ends and interiors of contigs. Genome statistics were obtained from Bandage v0.8.1 ( Wick et al. 2015 ) after each round of purge_dups. Our purged assembly was then error corrected with Inspector v1.3.1 ( Chen et al. 2021 ). Structural annotation was performed using Helixer v0.3.4 using the pre-trained invertebrate model (Stiehler et al. 2020; Holst et al., 2023 ). The completeness of our annotation was determined using BUSCO v.5.4.7 ( Seppey et al. 2019 ) in protein mode and by aligning RNA-seq reads (preprint) of multiple life stages (larvae, pupae, and adults) to our genome using STAR v2.7 ( Dobin et al. 2013 ) on the default settings. Functional annotation of our gene models was done using the eggnog-mapper (v2) web portal (eggnog-mapper.embl.de; Cantalapiedra et al. 2021 ). Repetitive element content of our genome was assessed using RepeatMasker ( Tarailo-Graovac and Chen 2009 ). qPCR and structural modeling of RNAi machinery Gene models that eggnog-mapper identified as RNAi pathway components in L. coffeella data were submitted to structural predictions using InterproScan and AlphaFold3 to confirm both gene annotations and structural-functional conservation ( Blum et al. 2021 ; Abramson et al. 2024 ). Primers for quantitative real-time PCR (RT-qPCR) reactions (Table S1) were synthesized by Sigma® ( Rpl10, Rpl18, Sid1, C3pO ) or Exxtend® ( Ago1, Ago2, Dcr1, Dcr2 , and R2d2 ) and used in amplification reactions performed in a QuantStudio 3® system (Applied Biosystems, Waltham, Massachusetts, USA). Amplification data were analyzed using LinRegPCR, removing potential biases from the sample data ( Ramakers et al. 2003 ). Fold Change (FC) of the relative gene expression was quantified using the 2 −ΔΔCT method ( Livak and Schmittgen, 2001 ). The ΔC T values of pupa samples were compared with larva/male/female samples from three biological experiments. Statistical significance was calculated with two-way ANOVA, followed by Tukey’s post-hoc test (p-value < 0.01). Results and Discussion Genome assembly and annotation Blobtools analysis of our preliminary meta-genomic assembly identified only a handful of contigs (N = 21) belonging to phyla other than Arthopoda (Figure S2). Of those identified as Arthropoda, 600 were found to correspond to classes other than Lepidoptera (Figures S2&3). Removing all non-Lepidoptera reads did not meaningfully reduce the low-coverage kmers in our dataset (Figure S4, suggesting that they were the result of pooling multiple genetically heterogeneous individuals. Assembling only the Lepidoptera-identified reads with hifiasm produced an assembly that was free of contamination (Figure S5) yet highly duplicated (>90% of odb10_lepidoptera BUSCOs; Figure 2 ). Five iterations of purge_dups were able to reduce the duplicated BUSCO rate to 10.5% ( Figures 3 , S6), consistent with previous studies that found it suitable for reducing spurious duplication in pooled-sample assemblies ( Goldberg et al. 2024 ). Download figure Open in new tab Figure 2. Results of BUSCO analysis for the raw assembly produced by hifiasm (top bar), the final assembly after 5x rounds of purge_dups and polishing with Inspector (middle bar), and the structural annotation produced by helixer (bottom row). Download figure Open in new tab Figure 3. AlphaFold3-predicted structures of key RNAi proteins: LcDCR1 (pink), LcDCR2 (magenta), LcAGO1 (yellow), LcAGO2 (orange), LcSID1 (ocher), LcC3PO (light green), LcR2D2 (dark green), and dsRNA (multicolored), all modeled from the L. coffeella genome. Our final assembly remained highly fragmented by the standards of modern long-read sequencing standards (number of contigs = 1615; largest contig = 6.3Mb; total size = 370.6Mb; Tables 1 , S2) and slightly smaller than our kmer estimate (399.7Mb; Figure S4); however, it is important to note that our estimate is likely inflated by the presence of multiple haplotypes in our dataset and the true genome size much smaller than our total assembly size. Indeed, the size of our genome assembly is larger than our flow cytometry measurement (294.6225 Mbp; mean nuclear value = 2C = 0.603pg) consistent with the presence of haplotypic duplication. Both our flow cytometry measurement and the size of our assembly are well within the range expected based on other lepidopteran genomes (e.g. Manduca sexta = 470Mb, Gershman et al 2021; Plutella xylostella = 323Mb, Boyes et al. 2023; Pieris rapae = 246Mb, Shen et al. 2016) View this table: View inline View popup Download powerpoint Table 1. Statistics describing our final (purged & polished) assembly Inspector found that our assembly was error-prone (N small-scale errors = 2.03M; 5482 per Mb; Table S1), which is typical of pooled-sample assemblies ( Goldberg et al. 2024 ), yet the polishing algorithm was able to significantly reduce this (N small-scale errors = 190k; 512 per Mb). Despite these errors, BUSCO analysis found that most gene content was still represented (BUSCO complete = 91.6%; Table 1 ). This was further supported by high mapping rates for our six RNA-seq samples (Mean mapping rate = 86%; Table S3). RepeatMasker found that 46.44% of our assembly was composed of repetitive elements (Table S4), predominantly retroelements (20.91% of total length) and unclassified elements (18.14% of total length); however, our aggressive purging of duplicate haplotigs is likely to have collapsed repetitive regions of the genome, thus the real repeat content of the L. coffeella genome may be higher. Helixer was able to annotate 17467 genes in our assembly, with 91.2% of protein BUSCOs complete; 13725 of these genes were able to be functionally annotated. This speaks to the ability of helixer to identify lepidopteran genes, and is likely due to the over-representation of holometabola (especially lepidopteran and dipteran) genomes within its training corpus (details regarding Helixer training data sets can be found at https://uni-duesseldorf.sciebo.de/s/lQTB7HYISW71Wi0 ). Identification and analysis of RNAi machinery Eggnog-mapper revealed several putative gene sequences associated with small RNA processing and transport pathways in the CLM genome: Double-Stranded RNA-Specific Endoribonuclease ( Dcr ), Argonaute RISC Component 1 ( Arg ), Systemic RNAi-deficient-1, RNAi regulator-component 3 promoter of RISC ( C3po ), dsRNA-binding protein R2D2 ( R2d2 ). We performed homology-based molecular modeling of selected RNAi core protein candidates to establish a robust framework for validating genomic predictions by elucidating conserved structural and functional features. By transforming sequence-based genomic data into testable structural hypotheses, our results showed that the predicted proteins LcDCR1, LcDCR2, LcAGO1, LcAGO2, SID1, C3PO and R2D2 retain not only sequence homology but also their expected conformational function ( Davis-Vogel et al. 2018 ; Arraes et al. 2020; Figures 4 and S8). Although RNAi is a conserved mechanism in eukaryotes, variations in gene duplication, deletion, and expression across insect species affect its efficiency ( Cooper et al. 2019 ). RNAi efficacy is influenced more by the expression levels of key enzymes—such as Dicer, Argonaute, and RISC components—than by the sheer number of core genes. The reported high variability in RNAi responses among insects suggests that analyzing the expression of RNAi-related genes could enhance our understanding of interspecies differences in RNAi efficiency and help identify key factors influencing silencing success ( Koo et al. 2024 ). The expression patterns of larvae, male and female compared to the pupal stage are depicted in Figure S7. Our qPCR results show that even candidate genes coding for closely related proteins (i.e. DCR2 and AGO2) presented different melting temperature of the amplicon and expression profiles, suggesting that the mined sequences were distinct enough to be assigned to L. coffeella as LcDcr1, LcDcr2, LcAgo1 and LcAgo2 . There are several fascinating findings within our analysis of dsRNA processing in L. coffeella . Firstly, R2D2 – a dsRNA-binding protein which forms a complex with Dicer to process dsRNA into siRNA thereby initiating RNAi through the loading of siRNA duplexes onto ARG proteins ( Hameed et al. 2024 ). R2d2 has not been detected in several lepidopteran transcriptomes, suggesting a possible loss or reduced function of this gene in the order. In Bombyx mori , the R2D2 homolog is expressed at very low levels ( Swevers et al. 2011 ). Interestingly, our study revealed LcR2d2 has a higher expression in males compared to larva, pupa and female. Although R2D2’s role in the RNAi pathway is well established, its involvement in male-specific traits or processes remains largely uncharacterized. There is currently no information about the implication of R2D2 in male-specific development or reproduction. Second, LcSid1 – a transmembrane protein involved in double-stranded RNA uptake (Saakre et al., 2023), exhibited an overexpression peak in adult males, with mean fold change values significantly higher than those observed in immature stages and females. Conversely, expression analyses in Ostrinia nubilalis showed that R2d2 transcripts were present across all developmental stages, with expression levels significantly lower in males than in females ( Cooper et al. 2021 ). Also, in contrast to L. coffeella, Sid-1 expression in Nilaparvata lugens was lower in males compared to females ( Zha et al. 2011 ). Altogether, these results suggest that RNAi pathways may be involved in sex-specific regulatory dynamics that warrant further investigation, especially when determining possible targets for novel biopesticides. Concluding Remarks In light of rapid environmental changes and biodiversity loss, especially within the highly diverse tropics, the need to protect agriculture with novel pest management solutions has never been greater. RNAi-based biopesticides are a promising solution but require a substantial amount of research into the biology of target species to develop. By generating a draft genome assembly with PacBio long-reads, we have taken a crucial first step towards the goal of protecting coffee production from its most damaging pest, the CLM. Furthermore, we characterized the structures and expression of key RNAi pathway genes within our genome and confirmed the presence of RNAi machinery within L. coffeella . This establishes targeted biopesticides as a solution worthy of continued research and development. Notably, the serendipitous discovery of sex-biased expression in these genes points to previously undiscovered roles for RNAi in lepidopteran biology. As such, our study – and the underlying data – will serve as a valuable resource for future research, both fundamental and applied. Data Availability The genome assembly and raw HiFi reads underlying this article are available at NCBI with the BioProject ID PRJNA832598. RNA-seq data are available from the Redape database (doi:10.48432/HTKLJ4). Author Contributions Conceptualization— J.K.G., N.F.M., E.V.S.A.; Data curation—J.K.G., N.F.M., M.J.A.V., E.V.S.A.; Formal Analysis— J.K.G., L.A.V., N.F.M., M.J.A.V.; Funding acquisition—J.K.G., E.V.S.A; Investigation— E.F.M.B.N., L.A.V.; Software— J.K.G., N.F.M., M.J.A.V.; Project administration—E.V.S.A.; Validation— J.K.G., N.F.M. L.A.V.; Visualization— J.K.G., N.F.M., L.A.V., E.S.L.Q.; Resources— E.V.S.A.; Supervision — N.F.M., W.R.C., E.V.S.A.; Writing—original draft— J.K.G., N.F.M., W.R.C., E.V.S.A.; Writing—review and editing— J.K.G., N.F.M., W.R.C., A.Q.M., E.V.S.A. Acknowledgements We thank Adriano Veiga from Embrapa for the accession to the field infested plants; Genomix Data, for contracting sequencing facilities. We also thank the University of Arizona HPC team for maintaining computational resources and Professor Judith Bronstein for providing access to JKG. Funding This work was funded by grants and fellowships from the CONCAFE consortium (Project funding and Fellowships to E.F.M.B.N., E.S.L.Q.) and CNPq (L.A.V.). Funder Information Declared CONCAFE Consortium CNPq Literature Cited ↵ Abramson , J. , Adler , J. , Dunger , J. , Evans , R. , Green , T. , Pritzel , A. , Ronneberger , O. , Willmore , L. , Ballard , A.J. , Bambrick , J. , Bodenstein , S.W. , Evans , D.A. , Hung , C.-C. , O’Neill , M. , Reiman , D. , Tunyasuvunakool , K. , Wu , Z. , Žemgulytė , A. , Arvaniti , E. , Beattie , C. , Bertolli , O. , Bridgland , A. , Cherepanov , A. , Congreve , M. , Cowen-Rivers , A.I. , Cowie , A. , Figurnov , M. , Fuchs , F.B. , Gladman , H. , Jain , R. , Khan , Y.A. , Low , C.M.R. , Perlin , K. , Potapenko , A. , Savy , P. , Singh , S. , Stecula , A. , Thillaisundaram , A. , Tong , C. , Yakneen , S. , Zhong , E.D. , Zielinski , M. , Žídek , A. , Bapst , V. , Kohli , P. , Jaderberg , M. , Hassabis , D. , Jumper , J.M. , 2024 . Accurate structure prediction of biomolecular interactions with AlphaFold 3 . Nature 630 , 493 – 500 . doi: 10.1038/s41586-024-07487-w OpenUrl CrossRef PubMed Arraes , F.B.M. , Martins-de-Sa , D. , Noriega Vasquez , D.D. , Melo , B.P. , Faheem , M. , de Macedo , L.L.P. , Morgante , C.V. , Barbosa , J.A.R.G. , Togawa , R.C. , Moreira , V.J.V. , Danchin , E.G.J. , Grossi-de-Sa , M.F. , 2021 . Dissecting protein domain variability in the core RNA interference machinery of five insect orders . RNA Biology 18 , 1653 – 1681 . doi: 10.1080/15476286.2020.1861816 OpenUrl CrossRef ↵ Barathi , S. , Sabapathi , N. , Kandasamy , S. , Lee , J. , 2024 . Present status of insecticide impacts and eco-friendly approaches for remediation-a review . Environmental Research 240 , 117432 . doi: 10.1016/j.envres.2023.117432 OpenUrl CrossRef ↵ Benoit , G. , Raguideau , S. , James , R. , Phillippy , A.M. , Chikhi , R. , Quince , C. , 2024 . High-quality metagenome assembly from long accurate reads with metaMDBG . Nat Biotechnol 42 , 1378 – 1383 . doi: 10.1038/s41587-023-01983-6 OpenUrl CrossRef ↵ Blum , M. , Chang , H.-Y. , Chuguransky , S. , Grego , T. , Kandasaamy , S. , Mitchell , A. , Nuka , G. , Paysan-Lafosse , T. , Qureshi , M. , Raj , S. , Richardson , L. , Salazar , G.A. , Williams , L. , Bork , P. , Bridge , A. , Gough , J. , Haft , D.H. , Letunic , I. , Marchler-Bauer , A. , Mi , H. , Natale , D.A. , Necci , M. , Orengo , C.A. , Pandurangan , A.P. , Rivoire , C. , Sigrist , C.J.A. , Sillitoe , I. , Thanki , N. , Thomas , P.D. , Tosatto , S.C.E. , Wu , C.H. , Bateman , A. , Finn , R.D. , 2021 . The InterPro protein families and domains database: 20 years on . Nucleic Acids Research 49 , D344 – D354 . doi: 10.1093/nar/gkaa977 OpenUrl CrossRef PubMed ↵ Camacho , C. , Coulouris , G. , Avagyan , V. , Ma , N. , Papadopoulos , J. , Bealer , K. , Madden , T.L. , 2009 . BLAST+: architecture and applications . BMC Bioinformatics 10 , 1 – 9 . doi: 10.1186/1471-2105-10-421 OpenUrl CrossRef PubMed ↵ Cantalapiedra , C.P. , Hernández-Plaza , A. , Letunic , I. , Bork , P. , Huerta-Cepas , J. , 2021 . eggNOG-mapper v2: Functional Annotation, Orthology Assignments, and Domain Prediction at the Metagenomic Scale . Molecular Biology and Evolution 38 , 5825 – 5829 . doi: 10.1093/molbev/msab293 OpenUrl CrossRef PubMed ↵ Challis , R. , Richards , E. , Rajan , J. , Cochrane , G. , Blaxter , M. , 2020 . BlobToolKit – Interactive Quality Assessment of Genome Assemblies . G3 Genes|Genomes|Genetics 10 , 1361 – 1374 . doi: 10.1534/g3.119.400908 OpenUrl Abstract / FREE Full Text ↵ Chen , P. , Lan , Y. , Ding , S. , Du , R. , Hu , X. , Zhang , H. , Yu , H. , Xu , L. , Li , C. , Lin , F. , Du , L. , Umida , I. , Ray , R. , Liu , T. , Liang , Y. , Niu , D. , Liu , H. , Zhou , T. , Zhao , H. , 2025 . RNA interference-based dsRNA application confers prolonged protection against rice blast and viral diseases, offering a scalable solution for enhanced crop disease management . Journal of Integrative Plant Biology 67 , 1633 – 1648 . doi: 10.1111/jipb.13896 OpenUrl CrossRef PubMed ↵ Chen , Y. , Zhang , Y. , Wang , A.Y. , Gao , M. , Chong , Z. , 2021 . Accurate long-read de novo assembly evaluation with Inspector . Genome Biol 22 , 1 – 21 . doi: 10.1186/s13059-021-02527-4 OpenUrl CrossRef PubMed ↵ Cheng , H. , Concepcion , G.T. , Feng , X. , Zhang , H. , Li , H. , 2021 . Haplotype-resolved de novo assembly using phased assembly graphs with hifiasm . Nat Methods 18 , 170 – 175 . doi: 10.1038/s41592-020-01056-5 OpenUrl CrossRef ↵ Cooper , A.M. , Silver , K. , Zhang , J. , Park , Y. , Zhu , K.Y. , 2019 . Molecular mechanisms influencing efficiency of RNA interference in insects . Pest Manag Sci 75 , 18 – 28 . doi: 10.1002/ps.5126 OpenUrl CrossRef PubMed ↵ Cooper , A.M.W. , Song , H. , Shi , X. , Yu , Z. , Lorenzen , M. , Silver , K. , Zhang , J. , Zhu , K.Y. , 2021 . Characterization, expression patterns, and transcriptional responses of three core RNA interference pathway genes from Ostrinia nubilalis . Journal of Insect Physiology 129 , 104181 . doi: 10.1016/j.jinsphys.2020.104181 OpenUrl CrossRef PubMed ↵ Dantas , T.E.T. , de-Souza , E.D. , Destro , I.R. , Hammes , G. , Rodriguez , C.M.T. , Soares , S.R. , 2021 . How the combination of Circular Economy and Industry 4.0 can contribute towards achieving the Sustainable Development Goals . Sustainable Production and Consumption 26 , 213 – 227 . doi: 10.1016/j.spc.2020.10.005 OpenUrl CrossRef ↵ Davis-Vogel , C. , Allen , B.V. , Hemert , J.L.V. , Sethi , A. , Nelson , M.E. , Sashital , D.G. , 2018 . Identification and comparison of key RNA interference machinery from western corn rootworm, fall armyworm, and southern green stink bug . PLOS ONE 13 , e0203160 . doi: 10.1371/journal.pone.0203160 OpenUrl CrossRef PubMed ↵ Dobin , A. , Davis , C.A. , Schlesinger , F. , Drenkow , J. , Zaleski , C. , Jha , S. , Batut , P. , Chaisson , M. , Gingeras , T.R. , 2013 . STAR: ultrafast universal RNA-seq aligner . Bioinformatics 29 , 15 – 21 . doi: 10.1093/bioinformatics/bts635 OpenUrl CrossRef PubMed Web of Science ↵ Goldberg , J.K. , Allan , C.W. , Copetti , D. , Matzkin , L.M. , Bronstein , J. , 2024 . A pooled-sample draft genome assembly provides insights into host plant-specific transcriptional responses of a Solanaceae-specializing pest, Tupiocoris notatus (Hemiptera: Miridae) . Ecology and Evolution 14 , e10979 . doi: 10.1002/ece3.10979 OpenUrl CrossRef ↵ Guan , D. , McCarthy , S.A. , Wood , J. , Howe , K. , Wang , Y. , Durbin , R. , 2020 . Identifying and removing haplotypic duplication in primary genome assemblies . Bioinformatics 36 , 2896 – 2898 . doi: 10.1093/bioinformatics/btaa025 OpenUrl CrossRef PubMed ↵ Holst , F. , Bolger , A. , Günther , C. , Maß , J. , Triesch , S. , Kindel , F. , Kiel , N. , Saadat , N. , Ebenhöh , O. , Usadel , B. , Schwacke , R. , Bolger , M. , Weber , A.P.M. , Denton , A.K. , 2023 . Helixer– de novo Prediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model (preprint) . Bioinformatics . doi: 10.1101/2023.02.06.527280 OpenUrl CrossRef ↵ Koo , J. , Zhu , G.-H. , Palli , S.R. , 2024 . CRISPR-Cas9 mediated dsRNase knockout improves RNAi efficiency in the fall armyworm . Pesticide Biochemistry and Physiology 200 , 105839 . doi: 10.1016/j.pestbp.2024.105839 OpenUrl CrossRef PubMed ↵ Leite , S.A. , Guedes , R.N.C. , Santos , M.P. dos , Costa , D.R. da , Moreira , A.A. , Matsumoto , S.N. , Lemos , O.L. , Castellani , M.A. , 2020 . Profile of Coffee Crops and Management of the Neotropical Coffee Leaf Miner, Leucoptera coffeella . Sustainability 12 , 8011 . doi: 10.3390/su12198011 OpenUrl CrossRef ↵ Li , H. , 2018 . Minimap2: pairwise alignment for nucleotide sequences . Bioinformatics 34 , 3094 – 3100 . doi: 10.1093/bioinformatics/bty191 OpenUrl CrossRef PubMed ↵ Livak , K.J. , Schmittgen , T.D. , 2001 . Analysis of relative gene expression data using real-time quantitative PCR and the 2(-Delta Delta C(T)) Method . Methods 25 , 402 – 408 . doi: 10.1006/meth.2001.1262 OpenUrl CrossRef PubMed Web of Science ↵ Marcais , G. , Kingsford , C. , 2012 . Jellyfish: A fast k-mer counter . ↵ Nascimento , E.F. de M.B. do , Lucena-Leandro , V. dos S. , Torres , C.R. , Vidal , L.A. , Junqueira , C.I.C.V.F. , Almeida , J.D. de , Albuquerque , É.V.A.S. , 2022 . Optimization of insect genomic DNA and total RNA extraction protocols for high fidelity gene sequencing . ↵ Niu , J. , Chen , R. , Wang , J.-J. , 2024 . RNA interference in insects: the link between antiviral defense and pest control . Insect Science 31 , 2 – 12 . doi: 10.1111/1744-7917.13208 OpenUrl CrossRef PubMed ↵ Ortolá , B. , Daròs , J.-A. , 2024 . RNA Interference in Insects: From a Natural Mechanism of Gene Expression Regulation to a Biotechnological Crop Protection Promise . Biology 13 , 137 . doi: 10.3390/biology13030137 OpenUrl CrossRef PubMed ↵ Pathak , V.M. , Verma , V.K. , Rawat , B.S. , Kaur , B. , Babu , N. , Sharma , A. , Dewali , S. , Yadav , M. , Kumari , R. , Singh , S. , Mohapatra , A. , Pandey , V. , Rana , N. , Cunill , J.M. , 2022 . Current status of pesticide effects on environment, human health and it’s eco-friendly management as bioremediation: A comprehensive review . Front Microbiol 13 , 962619 . doi: 10.3389/fmicb.2022.962619 OpenUrl CrossRef ↵ Picanço Filho , M.C. , Lima , E. , Carmo , D. das G. do , Pallini , A. , Walerius , A.H. , da Silva , R.S. , Sant’Ana , L.C. da S. , Lopes , P.H.Q. , Picanço , M.C. , 2024 . Economic Injury Levels and Economic Thresholds for Leucoptera coffeella as a Function of Insecticide Application Technology in Organic and Conventional Coffee (Coffea arabica), Farms . Plants 13 , 585 . doi: 10.3390/plants13050585 OpenUrl CrossRef PubMed ↵ Praça-Fontes , M.M. , Carvalho , C.R. , Clarindo , W.R. , 2011 . C-value reassessment of plant standards: an image cytometry approach . Plant Cell Rep 30 , 2303 – 2312 . doi: 10.1007/s00299-011-1135-6 OpenUrl CrossRef PubMed ↵ Ramakers , C. , Ruijter , J.M. , Deprez , R.H.L. , Moorman , A.F.M. , 2003 . Assumption-free analysis of quantitative real-time polymerase chain reaction (PCR) data . Neurosci Lett 339 , 62 – 66 . doi: 10.1016/s0304-3940(02)01423-4 OpenUrl CrossRef PubMed Web of Science ↵ Ranallo-Benavidez , T.R. , Jaron , K.S. , Schatz , M.C. , 2020 . GenomeScope 2.0 and Smudgeplot for reference-free profiling of polyploid genomes . Nat Commun 11 , 1432 . doi: 10.1038/s41467-020-14998-3 OpenUrl CrossRef PubMed ↵ Raven , P.H. , Wagner , D.L. , 2021 . Agricultural intensification and climate change are rapidly decreasing insect biodiversity . Proc Natl Acad Sci U S A 118 , e2002548117 . doi: 10.1073/pnas.2002548117 OpenUrl Abstract / FREE Full Text Saakre , M. , Jaiswal , S. , Rathinam , M. , Raman , K.V. , Tilgam , J. , Paul , K. , Sreevathsa , R. , Pattanayak , D. , 2024 . Host-Delivered RNA Interference for Durable Pest Resistance in Plants: Advanced Methods, Challenges, and Applications . Mol Biotechnol 66 , 1786 – 1805 . doi: 10.1007/s12033-023-00833-9 OpenUrl CrossRef PubMed ↵ Hameed , M. , Ren , Y. , Tuda , M. , Basit , A. , Urooj , N. , 2024 . Role of Argonaute proteins in RNAi pathway in Plutella xylostella: A review . Gene 903 , 148195 . doi: 10.1016/j.gene.2024.148195 OpenUrl CrossRef PubMed ↵ Kollmar , M. Seppey , M. , Manni , M. , Zdobnov , E.M. , 2019 . BUSCO: Assessing Genome Assembly and Annotation Completeness , in: Kollmar , M. (Ed.), Gene Prediction: Methods and Protocols, Methods in Molecular Biology . Springer , New York, NY , pp. 227 – 245 . doi: 10.1007/978-1-4939-9173-0_14 OpenUrl CrossRef PubMed Stiehler , F. , Steinborn , M. , Scholz , S. , Dey , D. , Weber , A.P.M. , Denton , A.K. , 2021 . Helixer: cross-species gene annotation of large eukaryotic genomes using deep learning . Bioinformatics 36 , 5291 – 5298 . doi: 10.1093/bioinformatics/btaa1044 OpenUrl CrossRef PubMed ↵ Swevers , L. , Liu , J. , Huvenne , H. , Smagghe , G. , 2011 . Search for Limiting Factors in the RNAi Pathway in Silkmoth Tissues and the Bm5 Cell Line: The RNA-Binding Proteins R2D2 and Translin . PLOS ONE 6 , e20250 . doi: 10.1371/journal.pone.0020250 OpenUrl CrossRef PubMed ↵ Tarailo-Graovac , M. , Chen , N. , 2009 . Using RepeatMasker to Identify Repetitive Elements in Genomic Sequences . Current Protocols in Bioinformatics 25 , 4.10.1-4.10.14. doi: 10.1002/0471250953.bi0410s25 OpenUrl CrossRef PubMed ↵ Wick , R.R. , Schultz , M.B. , Zobel , J. , Holt , K.E. , 2015 . Bandage: interactive visualization of de novo genome assemblies . Bioinformatics 31 , 3350 – 3352 . doi: 10.1093/bioinformatics/btv383 OpenUrl CrossRef PubMed ↵ Willow , J. , Smagghe , G. , 2025 . RNAi applications toward environmentally sustainable food security . Current Opinion in Environmental Science & Health 45 , 100612 . doi: 10.1016/j.coesh.2025.100612 OpenUrl CrossRef ↵ Zha , W. , Peng , X. , Chen , R. , Du , B. , Zhu , L. , He , G. , 2011 . Knockdown of Midgut Genes by dsRNA-Transgenic Plant-Mediated RNA Interference in the Hemipteran Insect Nilaparvata lugens . PLOS ONE 6 , e20504 . doi: 10.1371/journal.pone.0020504 OpenUrl CrossRef PubMed View the discussion thread. Back to top Previous Next Posted July 31, 2025. Download PDF Supplementary Material Email Thank you for your interest in spreading the word about bioRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following A draft genome assembly of the agricultural pest Leucoptera coffeella and analysis of its dsRNA processing machinery is a key step towards RNAi-based biopesticides in Lepidoptera 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 A draft genome assembly of the agricultural pest Leucoptera coffeella and analysis of its dsRNA processing machinery is a key step towards RNAi-based biopesticides in Lepidoptera Jay K. Goldberg , Leonardo A. Vidal , Erick S.L. Queiroz , Eliza F.M.B Nascimento , Marcos J.A. Viana , Wellington R. Clarindo , Andrea Q. Maranhao , Natália F. Martins , Érika V.S. Albuquerque bioRxiv 2025.07.28.667214; doi: https://doi.org/10.1101/2025.07.28.667214 Share This Article: Copy Citation Tools A draft genome assembly of the agricultural pest Leucoptera coffeella and analysis of its dsRNA processing machinery is a key step towards RNAi-based biopesticides in Lepidoptera Jay K. Goldberg , Leonardo A. Vidal , Erick S.L. Queiroz , Eliza F.M.B Nascimento , Marcos J.A. Viana , Wellington R. Clarindo , Andrea Q. Maranhao , Natália F. Martins , Érika V.S. Albuquerque bioRxiv 2025.07.28.667214; doi: https://doi.org/10.1101/2025.07.28.667214 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 (17697) Bioengineering (13895) Bioinformatics (41953) Biophysics (21456) Cancer Biology (18595) Cell Biology (25521) Clinical Trials (138) Developmental Biology (13381) Ecology (19903) Epidemiology (2067) Evolutionary Biology (24323) Genetics (15612) Genomics (22511) Immunology (17738) Microbiology (40401) Molecular Biology (17184) Neuroscience (88623) Paleontology (667) Pathology (2833) Pharmacology and Toxicology (4825) Physiology (7644) Plant Biology (15158) Scientific Communication and Education (2046) Synthetic Biology (4296) Systems Biology (9825) Zoology (2271)