De novo genome Assembly of Rauvolfia Serpentina and comparative paleodemographic analysis of Apocynaceae plants

De novo genome Assembly of Rauvolfia Serpentina and comparative paleodemographic analysis of Apocynaceae plants | 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 De novo genome Assembly of Rauvolfia Serpentina and comparative paleodemographic analysis of Apocynaceae plants Mratunjay Dwivedi , View ORCID Profile Nagarjun Vijay doi: https://doi.org/10.1101/2025.10.27.684745 Mratunjay Dwivedi 1 Computational Evolutionary Genomics Lab, Department of Biological Sciences, IISER Bhopal , Bhauri, Madhya Pradesh, India Find this author on Google Scholar Find this author on PubMed Search for this author on this site Nagarjun Vijay 1 Computational Evolutionary Genomics Lab, Department of Biological Sciences, IISER Bhopal , Bhauri, Madhya Pradesh, India Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Nagarjun Vijay For correspondence: nagarjun{at}iiserb.ac.in Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract Rauvolfia serpentina is a perennial subshrub widely distributed across Asia and the Indian subcontinent. Belonging to the medicinally important Apocynaceae family, it is renowned for its ecological importance and ethnobotanical applications, especially through the biosynthesis of therapeutic indole alkaloids. In this study, we present a de novo genome assembly and annotation for R. serpentina . The assembled genome comprises approximately 184,000 scaffolds with a scaffold N50 of 7.18 Kbp and a high BUSCO completeness score of ∼90% encompassing ∼22,000 annotated genes. We analysed the paleodemographic histories of nine additional Apocynaceae species using Pairwise Sequentially Markovian Coalescent (PSMC) modelling to place these findings in a broader evolutionary context. This comparative analysis revealed a consistent signature of a pronounced bottleneck across the family during the Mid-Pleistocene glaciations, with few notable species showing high adaptive resilience marked by early recovery in effective population size (N e ), while some even showed secondary N e peaks in the warmer interglacial periods. Although marked by complex and fairly distinct demographic trajectories, most species exhibit stabilised N e near the onset of the Holocene. The availability of this high-quality draft genome assembly provides an important resource to advance functional, ecological, and comparative genomics in R. serpentina as well as aid heterologous production of pharmaceutically important biomolecules at an industrial scale, thereby alleviating the pressure on wild populations. Introduction Rauvolfia serpentina (commonly known as Sarpgandha, Chandrika, Serpentine wood, Indian snakeroot , or Devil peppers ) is a perennial, evergreen subshrub belonging to the Apocynaceae family within the order Gentianales . Native to Southeast Asia, the species is now found widely distributed across tropical regions, including parts of Africa, America, Sri Lanka, Nepal, Myanmar, Malaysia, Indonesia, and most notably along the lower Gangetic plains and the sub-Himalayan belt of the Indian subcontinent ( Mukherjee et al., 2019 ) where it has been historically recognised within the traditional systems of medicine, with ancient Ayurvedic texts such as the Sushruta Samhita, Charaka Samhita, Ashtanga Hridaya and Vrindamadhava dating back to around 1000 BCE documenting its medical usage ( Lobay, 2015 ). The pharmacological relevance of R. serpentina is primarily attributed to its diverse repertoire of secondary metabolites, particularly the monoterpene indole alkaloids (MIAs), which include reserpine, reserpiline, rescinnamine, ajmaline, ajmalacine, deserpidine, serpinine, serpentine, serpentinine, rauvolfinine, vomilenine, yohimbine, picrinine, norseredamine, vinorine, and seredamine, among others ( Dey and De, 2010 ) (Pan dey et al., 2016 ). In addition, other important phytochemicals such as stigmasterol ( Dey et al., 2016 ; Dey and Pandey, 2014 ) and rutin ( Dey and De, 2010 ) have also been reported. These compounds have been reported to exhibit a broad spectrum of biological activities, including antimalarial and anticancer effects ( Beljanski and Beljanski, 1986 , 1984 , 1982 ; Wright et al., 1996 ),( Bae et al., 2020 ; Lin et al., 2012 ) with demonstrated therapeutic potential in the treatment of cardiovascular disorders such as hypertension ( Achor et al., 1955 ; Lobay, 2015 ) and arrhythmias ( Brugada et al., 2003 ; Rolf et al., 2003 ; Wolpert et al., 2005 ), as well as in managing anxiety, epilepsy, trauma, and gastrointestinal disturbances ( Meena et al., 2009 ; Poonam, 2013 ). Alongside these well-documented applications, traditional ethnomedicinal uses of R. serpentina also encompass treatment for snakebite, insect stings, psychiatric conditions, including schizophrenia and insomnia, dermatological conditions, respiratory ailments, fever, pneumonia, body pain, scabies, spleen disorders, ocular diseases, and even AIDS and various veterinary diseases ( Dey and De, 2011 , 2010 ; Pandey et al., 2016 ). However, despite its well-established pharmacological significance and extensive biochemical profiling, R. serpentina remains relatively under-investigated at the genomic level. Adequate genomic data could not only provide insight into its evolutionary lineage but also help reveal the molecular pathways underlying its biosynthetic capabilities. In this study, we perform high-coverage whole-genome sequencing of R. serpentina and report its first de novo genome assembly and annotation. Our study will not only expand the genomic repertoire of the medicinally valuable Apocynaceae family but also serve as a foundational resource for future molecular and biotechnological research, potentially expanding its therapeutic applications and aiding in the development of effective in vitro conservation and genetic improvement strategies for its sustainable utilisation and long-term preservation ( Gantait et al., 2017 ). Methods Sample Collection and DNA Sequencing Fresh leaves of R. serpentina were harvested from a shrub located within the premises of the Indian Institute of Science Education and Research, Bhopal (GPS coordinates: 23°17′18.8196″N, 77°16′29.946″E; altitude: 520 meters above sea level). Genomic DNA was isolated using the Qiagen DNeasy Kit. The quality and integrity of the extracted DNA were evaluated through 1× agarose gel electrophoresis, Nanodrop spectrophotometry, and Qubit fluorometry. Short-read sequencing libraries (150 bp) were prepared using the Kapa HyperPrep Kit with an average insert size of 250 ± 50 bp. Approximately 83 Gbp of paired-end sequencing data was generated using the Illumina NovaSeq 6000 platform. The raw sequencing data quality was assessed using FASTQC version 2.3.0 ( Andrews et al., 2015 ), and the results were aggregated and visualised using MULTIQC version 1.22.2 ( Ewels et al., 2016 ). To estimate the genome size, a k-mer-based approach was employed using Jellyfish version 1.1.12 ( Marçais and Kingsford, 2011 ), followed by modelling with GenomeScope version 1.0.0 ( Vurture et al., 2017 ) using a k-mer length of 21. Genome Assembly The genome of R. serpentina was assembled using Platanus version 1.2.4 ( Kajitani et al., 2014 ), optimised for highly heterozygous plant genomes. Assembly parameters included an initial k-mer size of 35, a bubble crush threshold of 0.2 for resolving ambiguous paths, a minimum k-mer coverage of 10, and a k-mer extension step size of 10. The same pipeline was used for scaffold formation and gap filling to get the final genome assembly (see Fig. 1 ). Download figure Open in new tab Fig. 1. Snailplot summarising assembly metrics and gene completeness for the Rauvolfia serpentina genome. (A) R. serpentina is an important medicinal plant of the Apocynaceae family. (B) The dark grey area depicts the distribution of scaffold lengths, with the plot radius scaled to the longest scaffold assembled (139 kbp). Orange and pale orange segments indicate the N50 and N90 scaffold lengths, respectively. The pale grey spiral represents the cumulative scaffold count plotted on a logarithmic scale. The outer ring, shaded in blue and pale blue, illustrates the distribution of GC, AT, and ambiguous (N) base percentages. The green pie chart in the upper right corner shows the proportion of BUSCO genes identified as complete or missing. Then, the quality of the assembled genome was comprehensively evaluated, and multiple metrics were employed to assess assembly continuity, completeness, and repeat content. QUAST version 5.2.2 ( Mikheenko et al., 2018 ) was used to compute standard assembly statistics representing genome continuity, including N50, N75, longest contig length, and the number of ambiguous bases (N’s) per 100 Kbp (see Supplementary Table S1 ). The completeness of the assembly was assessed using BUSCO version 5.8.2 ( Simão et al., 2015 ), which quantifies the presence of conserved single-copy orthologous genes. Analyses were conducted using both the eudicotyledons_odb10 (see Supplementary Table S2 ) and embryophyta_odb10 (see Supplementary Table S3 ) lineage datasets, alongside comparisons to previously published genomes within the family Apocynaceae . In addition to these structural metrics, the assembly quality in repetitive, low-complexity genomic regions was also evaluated through the LAI (LTR Assembly Index) score, calculated using the LAI module of LTR-retriever version 2.9. The repeats were further visualised using Repeat Landscape ( Ou and Jiang, 2018 ) (see Supplementary Table S4 ). Genome Annotation Structural gene annotation was performed using MAKER-P version 3.01.04 ( Campbell et al., 2014 ) with MPI for parallel processing. Repeat libraries were generated using LTR-retriever version 2.9.0 ( Ou and Jiang, 2018 ) and used to mask repetitive elements within the genome. For the initial round of de novo gene prediction, the coding sequence (CDS) dataset of Rauvolfia tetraphylla ( Lezin et al., 2024 ) and a concatenated multi-fasta of protein sequences of Rauvolfia tetraphylla and Arabidopsis thaliana were used as homology evidence. For further rounds of annotation, the results from previous annotation rounds progressively serve as the training set for gene prediction tools, SNAP version 2.46.1 ( Korf, 2004 ) and AUGUSTUS version 3.3.3 ( Stanke et al., 2008 ), implemented in BUSCO version 5.8.2 ( Simão et al., 2015 ). Annotation was iteratively refined across four rounds until convergence was achieved, as indicated by stabilisation of the Annotation Edit Distance (AED) values (see Supplementary Table S5 ). Organelle Genome Assembly and Annotation The raw sequencing read data were used to assemble the chloroplast genome using the NOVOPlasty version 4.3.5 ( Dierckxsens et al., 2017 ) program. The pbsA gene sequence of R. serpentina (Gene ID: 54600169) was used as a seed sequence. The assembler uses the seed sequence to find reads that cover this sequence and initiates overlapped sequence assembly. The assembled chloroplast genome consisted of one contig (see Fig. 2A ). The full length of the assembled chloroplast genome was 155.3 Kbp. It was then annotated using GeSeq and visualised using OGDRAW implemented in CHLOROBOX ( Greiner et al., 2019 ). For mitochondrial genome assembly, the nad7 gene sequence of Trachelospermum jasminoides (Gene ID: 88599469) was used as a seed, and the T. jasminoides mitochondrial genome (Accession ID: OR333986.1 ) was used as a reference. The total assembled mitochondrial sequence was 627.3 Kbp (see Fig. 2B ). Download figure Open in new tab Fig. 2. Chloroplast and mitochondrial genome maps of Rauvolfia serpentina . (A) Circular representation of the R. serpentina chloroplast genome. The inner circle highlights the major structural regions: the Large Single Copy (LSC), Small Single Copy (SSC), and the Inverted Repeats (IRA and IRB). The outermost ring shows gene positions and functional annotations, with gene classes colour-coded according to functional categories indicated in the legend (lower left). (B) Circular map of the R. serpentina mitochondrial genome. Genes transcribed on the positive strand are placed on the outer circle, while those on the negative strand appear on the inner circle. Genes containing introns are marked with an asterisk (*). Functional categories are colour-coded, and the transcription direction is clockwise (outer) or counterclockwise (inner). The innermost dark grey plot indicates the GC content across the mitochondrial genome. Phylogenetic analysis and genome comparison For phylogenetic analysis, 22 complete chloroplast genomes from the Apocynaceae family were downloaded from NCBI, followed by alignment using MAFFT v7.525 ( Katoh et al., 2002 ; Katoh and Standley, 2013 ). The phylogenetic tree was generated using maximum likelihood (ML) implemented in RaxML ( Stamatakis, 2014 ). Phylogenetic robustness was evaluated using 1000 bootstrap replicates, and the resulting tree was visualised in Figtree ( Rambaut, 2016 , 2009 ). Additionally, the comparison of the borders of large single copy (LSC), small single copy (SSC), and inverted repeat regions (IR) in the chloroplast genome was performed with Cynanchum wilfordii, Catharanthus roseus, R. serpentina, Asclepias syriaca and Rhazya stricta using IR scope ( Amiryousefi et al., 2018 ). Demographic history inference Published plant genome assemblies of species belonging to the Apocynaceae family, particularly Apocynum pictum, Apocynum venetum, Asclepias incarnata, A. syriaca, C. roseus, C. wilfordii, Echites panduratus, Marsdenia floribunda, and Pachypodium lamerei , were downloaded from NCBI. The genomes and corresponding short-read data were downloaded from public repositories and mapped to the corresponding genomes using the minimap2 read mapper ( Li, 2018 ). PSMC analysis ( Li and Durbin, 2011 ) was performed on the majority of these species with default parameters, i.e., -t5 –r5 –p “4 + 25*2 + 4 + 6” while C. wilfordii and A. venetum were analysed with -p “10 + 18*2 + 6”. These parameter settings of PSMC were found to result in more than 10 recombination events in each atomic interval after 20 iterations, thereby enhancing the resolution and reliability of inferred historical effective population sizes. A uniform mutation rate estimate of 2.5e-09 per site per year previously established for Populus trichocarpa in an earlier study ( Bai et al., 2018 ) was used for all the species. Species-specific per-generation mutation rates were obtained using corresponding generation times curated through a literature search (see Supplementary Table S6 ). Results Genome Assembly and Annotation The de novo assembly of R. serpentina yielded a draft genome of length 408.6 Mb, distributed across 184,278 scaffolds, which was a little less than the genome size of 513.7 Mb estimated using GenomeScope (see Supplementary Fig. 1 ), through k -mer frequency analysis of the raw reads. Assembly contiguity was assessed using standard metrics. The N50 scaffold length was 7.18 Kbp, and the L50 value was 11,573, while the longest scaffold assembled was 139 Kbp. Evaluation of repeat content using LTR-retriever yielded a LTR Assembly Index (LAI) score of 1.2, suggesting the assembly captured low-complexity repetitive regions, albeit with limited resolution in long terminal repeat (LTR) regions. The relative abundance of repeat classes was further visualised using Repeat Landscape (see Supplementary Fig. 2 ). Assessment and comparison of genome completeness with other Apocynaceae genomes was performed using BUSCO v5.8.2, using both eudicotyledons_odb10 and embryophyta_odb10 datasets, reporting a comparable and complete genome with 89.9% and 90.6% complete gene sets present, respectively, in the datasets (see Fig. 3 ). Gene annotation predicted around 21,983 genes with an average length of 3636.31. These results collectively indicate a reasonably complete draft genome, suitable for downstream comparative analyses. Download figure Open in new tab Fig. 3. Assembly quality comparison of the Apocynaceae family using BUSCO. Assembly quality comparison of the Apocynaceae family using the Eudicotyledons_odb10 (left) and Embryophyta_odb10 (right) dataset. Comparison of genome completeness based on BUSCO scores of Apocynaceae genome assemblies. R. serpentina showed relatively complete assembly compared to other species. Phylogenetic analysis and genome comparison The evolutionary placement of R. serpentina was determined using the chloroplast genomes of 22 other species of the Apocynaceae family to generate the phylogenetic tree. The presented chloroplast assembly was found to cluster with other species in the Rauvolfia family in the generated phylogenetic tree (see Supplementary Fig. 3 ). The LSC, SSC, and IR areas of R. serpentina relative to other Apocynaceae chloroplast genomes were visualised to evaluate differences in size and junction (see Supplementary Fig. 4 ). Demographic Analysis PSMC plots estimated highly variable N e curves from ∼10 million years ago to 10 KYA (based on scaling parameters) (see Fig. 4 ). All the species exhibit at least one cycle of demographic expansion followed by contraction. The curves show strong increases in N e at ∼5 Ma, with N e peaks in the mid-Pleistocene period, following an immediate decline and stabilisation at ∼50 KYA. Other than these limited occurrences of similarity, we observed a complex demographic history in Apocynaceae species with lineages following varying trends of expansion and contraction through time. Download figure Open in new tab Fig. 4. Comparative demographic histories of Apocynaceae plants, PSMC-inferred Ne trajectories for ten Apocynaceae species are shown with bootstrap support. Rectangles at the top indicate time intervals corresponding to major predicted glaciation events. R. serpentina displays a notably stabilised Ne trajectory compared to the other species. While most species exhibit a general decline in effective population size during the Mid-Pleistocene glaciations and the onset of the last glacial period, a few—such as Asclepias syriaca, Cynanchum wilfordii , and Marsdenia floribunda —demonstrate signs of recovery from these bottlenecks, suggesting higher adaptive capacity marked by early Ne stabilisation. In contrast, the remaining species show limited or no such recovery in effective population size. In Asia, C. wilfordii and A. venetum have N e curves with unimodal and bimodal peaks, respectively, coinciding around ∼2Ma, while R. serpentina shows a distinct peak at ∼200 KYA, followed by a gradual decline and a secondary peak near ∼30 KYA after which N e continues to decline till ∼10 KYA. A. pictum depicts a single peak of N e at around ∼4Ma, following a sustained decline till ∼150 KYA, followed by an immediate stabilization of N e . Among plants endemic to Madagascar, C. roseus shows an intense unimodal peak at around 900 KYA. P. lamerei shows notable fluctuations in N e over time, with distinct peaks observed during both the Pliocene and Pleistocene glacial periods. M. floribunda shows bimodal peaks in N e with a major peak lying in the early Pleistocene period at around ∼2Ma, followed by contraction and partial recovery at the MIS5 stage. In regions of Central America and Canada, all species peak in N e at around ∼1Ma. A. incarnata curve depicts population expansion starting at ∼2Ma with effective population size peaking at ∼1Ma, followed by a sharp decline in N e a few thousand years later. E. panduratus , on the other hand, shows bimodal peaks with increasing amplitudes at ∼1Ma and 250 KYA. In contrast, A. syriaca exhibits bimodal peaks; however, compared to the other two, the overall distribution of effective population size throughout history is undramatic and remains stabilised, especially in the earlier time intervals from around ∼500 KYA. Overall, all the lineages show a decline in effective population size in the recent time intervals. From approximately 50 KYA, the lineages show relative stabilisation with a slight downward trend. All species exhibit high variance in N e among bootstrap replicates at recent times compared to the rest of the curve. Such patterns are expected, as in recent time intervals, fewer recombination events are created with very recent coalescent histories. Discussion In this paper, we report a de novo genome assembly for Sarpgandha, R. serpentina . As the first genome assembly of a Rauvolfia species native to India, this study fills a significant gap in the genomic resources available for the Apocynaceae family and was paleodemographically analysed in conjunction with nine other species to help understand the historical population dynamics of Apocynaceae and the climatic and ecological events that have shaped their evolutionary trajectories. The demographic histories inferred from the Pairwise Sequentially Markovian Coalescent (PSMC) model revealed a general declining trend in effective population size across the Apocynaceae family from ∼300,000 to ∼900,000 years ago. Such a decline is most likely attributable to the intense climatic oscillations associated with the Mid-Pleistocene Transition (MPT), during which the duration of glacial cycles increased from ∼41,000 to ∼100,000 years. These climatic changes led to longer and more severe glacial–interglacial cycles, which resulted in extended periods of cold and dry conditions ( Clark et al., 2006 ; Pisias and Moore, 1981 ; Schuman, 2025 ; van der Hammen, 1974 ; Verbitsky et al., 2018 ). Thereby, this concurrent decline in N e likely reflects a shared historical bottleneck rather than an independent, species-specific demographic occurrence. Nevertheless, species-specific traits such as dispersal ability, physiological plasticity, and biotic and abiotic interactions can modulate the response to such environmental challenges, enhancing ecological adaptation and resilience to fluctuations in temperature and precipitation. As a result, some species varied from the usual trend, depicting complex trajectories. A. syriaca, C. wilfordii , and M. floribunda displayed relatively stable Ne trajectories throughout much of the mid to late Pleistocene period, particularly during interglacial periods, from Marine Isotope Stages (MIS) 11 to 5, while E. panduratus, P. lamerei , and A. venetum demonstrated signs of recovery in Ne following earlier periods of decline, suggesting that interglacial intervals—characterised by warmer climates, receding ice sheets, and elevated atmospheric CO□ levels facilitated demographic expansion in some lineages. In the case of R. serpentina , the demographic trajectory remained relatively stable from approximately 400 KYA until a more recent decline, which may be attributed to habitat loss and anthropogenic pressures. However, it is important to recognise that PSMC is sensitive to unaccounted substructure and sex-fluid populations; hence, peaks in N e estimates may also be a result of historical subpopulation structure, as lineage subdivision can lead to a decrease in frequency of coalescent events, which can inflate N e ( Hilgers et al., 2025 ; Mather et al., 2020 ; Nadachowska-Brzyska et al., 2016 ). Therefore, sampling multiple individuals across various geographic and ecological gradients within each species can render more confidence in the demographic inferences. In addition, the amplitude of N e estimates is influenced by generation time, which can vary among populations due to environmental factors such as soil properties, humidity, temperature, and precipitation. However, this limitation is largely mitigated by interpreting demographic trajectories based on their overall shape and relative trends rather than absolute amplitudes. Overall, this study provides a comprehensive comparative perspective on the demographic history of important Apocynaceae species. As more genomes from this family become available, similar coalescent-based approaches can be used to infer the ecological and evolutionary processes driving interspecific and intraspecific trends in population history with greater precision. To preliminarily evaluate the utility of this genome assembly for studying monoterpene indole alkaloid (MIA) biosynthesis, several publicly available genes and transcript sequences independently isolated and involved in the biosynthetic pathways of key compounds such as ajmaline and vinorine were queried against the assembled genome. Full-length matches were successfully recovered for several enzyme-coding transcripts, including ajmaline N-methyltransferase (Accession ID: KC708445 ) , vinorine synthase (Accession ID: AJ556780.2 ), vinorine hydroxylase (Accession ID: KY926696.1 ), and strictosidine-O-β-D-glucosidase (Accession ID: AJ302044.1 ). Thus, this genome assembly can be potentially leveraged for targeted identification and characterisation of genes involved in MIA biosynthesis, helping to engineer heterologous production systems for industrial-scale synthesis of pharmacologically important indole alkaloids, thereby reducing reliance on wild plant harvesting and alleviating anthropogenic pressures. It can also prove instrumental in facilitating genetic improvement strategies to introduce resistance traits against major pathogenic threats such as Cercospora rauvolfiae and Alternaria tenuis , or in potentially modulating the yield and flowering of the plant, to further promote the conservation and sustainable utilisation of R. serpentina . Ethical Statements This article does not contain any studies with human or animal participants. CRediT authorship contribution statement Mratunjay Dwivedi : Conceptualisation, Methodology, Writing -original draft, Formal analysis, Data curation, Investigation, Validation, Visualisation. Nagarjun Vijay : Funding acquisition, Conceptualisation, Supervision, Project administration, Resources, Writing - original draft, Writing - review & editing. Data availability All the genome sequencing data generated as part of this project are made available through BioProject: PRJEB77109 under the experiments ERX12715045, ERX12715046, ERX12715047, and ERX12715048 on European Nucleotide Archive (ENA). The genome assembly is submitted to ENA under accession ERZ28493929. Acknowledgements We thank the Ministry of Human Resource Development for the fellowship to MD. The computational analyses were performed on the Har Gobind Khorana Computational Biology cluster established and maintained by combining funds from IISER Bhopal under Grant # INST/BIO/2017/019, IYBA 2018 from the Department of Biotechnology (Grant no. BT/11/IYBA/2018/03) and ECRA (Grant no. ECR/2017/001430) from Science and Engineering Research Board (all Government of India). Funds for genome sequencing were from IISER Bhopal under Grant # INST/BIO/2017/019. Funder Information Declared Department of Biotechnology, https://ror.org/03tjsyq23 , BT/11/IYBA/2018/03 Science and Engineering Research Board, https://ror.org/03ffdsr55 , ECR/2017/001430 References ↵ Achor , R.W.P. , Hanson , N.O. , Gifford , R.W. , 1955 . Hypertension treated with rauwolfia serpentina (whole root) and with reserpine: Controlled study disclosing occasional severe depression . J Am Med Assoc 159 . doi: 10.1001/jama.1955.02960260011004 OpenUrl CrossRef PubMed Web of Science ↵ Amiryousefi , A. , Hyvönen , J. , Poczai , P. , 2018 . IRscope: an online program to visualize the junction sites of chloroplast genomes . Bioinformatics 34 . doi: 10.1093/bioinformatics/bty220 OpenUrl CrossRef PubMed ↵ Andrews , S. , Krueger , F. , Seconds-Pichon , A. , Biggins , F. , Wingett , S. , 2015 . FastQC. A quality control tool for high throughput sequence data. Babraham Bioinformatics [WWW Document] . Babraham Institute . ↵ Bae , H. , Song , G. , Lim , W. , 2020 . Stigmasterol causes ovarian cancer cell apoptosis by inducing endoplasmic reticulum and mitochondrial dysfunction . Pharmaceutics 12 . doi: 10.3390/pharmaceutics12060488 OpenUrl CrossRef ↵ Bai , W.N. , Yan , P.C. , Zhang , B.W. , Woeste , K.E. , Lin , K. , Zhang , D.Y. , 2018 . Demographically idiosyncratic responses to climate change and rapid Pleistocene diversification of the walnut genus Juglans (Juglandaceae) revealed by whole-genome sequences . New Phytologist 217 . doi: 10.1111/nph.14917 OpenUrl CrossRef ↵ Beljanski , M. , Beljanski , M.S. , 1986 . Three Alkaloids as Selective Destroyers of Cancer Cells in Mice . Oncology 43 . doi: 10.1159/000226363 OpenUrl CrossRef PubMed Web of Science ↵ Beljanski , M. , Beljanski , M.S. , 1984 . Three alkaloids as selective destroyers of the proliferative capacity of cancer cells . IRCS Med Sci 12 . ↵ Beljanski , M. , Beljanski , M.S. , 1982 . Selective inhibition of in vitro synthesis of cancer DNA by alkaloids of β-carboline class . Exp Cell Biol 50 . doi: 10.1159/000163131 OpenUrl CrossRef PubMed Web of Science ↵ Brugada , J. , Brugada , P. , Brugada , R. , 2003 . The ajmaline challenge in Brugada syndrome: A useful tool or misleading information? Eur Heart J . doi: 10.1016/S0195-668X(03)00232-X OpenUrl CrossRef PubMed Web of Science ↵ Campbell , M.S. , Law , M.Y. , Holt , C. , Stein , J.C. , Moghe , G.D. , Hufnagel , D.E. , Lei , J. , Achawanantakun , R. , Jiao , D. , Lawrence , C.J. , Ware , D. , Shiu , S.H. , Childs , K.L. , Sun , Y. , Jiang , N. , Yandell , M. , 2014 . MAKER-P: A Tool kit for the rapid creation, management, and quality control of plant genome annotations . Plant Physiol 164 . doi: 10.1104/pp.113.230144 OpenUrl Abstract / FREE Full Text ↵ Clark , P.U. , Archer , D. , Pollard , D. , Blum , J.D. , Rial , J.A. , Brovkin , V. , Mix , A.C. , Pisias , N.G. , Roy , M. , 2006 . The middle Pleistocene transition: characteristics, mechanisms, and implications for long-term changes in atmospheric pCO2 . Quat Sci Rev 25 . doi: 10.1016/j.quascirev.2006.07.008 OpenUrl CrossRef GeoRef PubMed Web of Science ↵ Dey , A. , De , J.N. , 2011 . Ethnobotanical aspects of rauvolfia serpentina (L). Benth. ex Kurz. in India, Nepal and Bangladesh . Journal of Medicinal Plants Research . ↵ Dey , A. , De , J.N. , 2010 . Rauvolfia serpentina (L). benth. ex kurz.-A review . Asian J Plant Sci . doi: 10.3923/ajps.2010.285.298 OpenUrl CrossRef ↵ Dey , A. , Mukherjee , S. , De , A. , Pandey , D.K. , 2016 . A Stigmasterol Containing n-hexane Fraction of Rauvolfia serpentina Methanolic Extract Shows Tissue-Specific Variation of Biocidal and Antioxidant Activities . J Herbs Spices Med Plants 22 . doi: 10.1080/10496475.2015.1042617 OpenUrl CrossRef ↵ Dey , A. , Pandey , D.K. , 2014 . HPTLC detection of altitudinal variation of the potential antivenin stigmasterol in different populations of the tropical ethnic antidote Rauvolfia serpentina . Asian Pac J Trop Med 7 . doi: 10.1016/S1995-7645(14)60287-X OpenUrl CrossRef ↵ Dierckxsens , N. , Mardulyn , P. , Smits , G. , 2017 . NOVOPlasty: De novo assembly of organelle genomes from whole genome data . Nucleic Acids Res 45 . doi: 10.1093/nar/gkw955 OpenUrl CrossRef PubMed ↵ Ewels , P. , Magnusson , M. , Lundin , S. , Käller , M. , 2016 . MultiQC: Summarize analysis results for multiple tools and samples in a single report . Bioinformatics 32 . doi: 10.1093/bioinformatics/btw354 OpenUrl CrossRef PubMed ↵ Gantait , S.S. , Dutta , K. , Majumder , J. , 2017 . In vitro regeneration and conservation of an endangered medicinal plant sarpagandha (Rauvolfia serpentina L .). Journal of Horticultural Sciences 12 . doi: 10.24154/jhs.v12i1.74 OpenUrl CrossRef ↵ Greiner , S. , Lehwark , P. , Bock , R. , 2019 . OrganellarGenomeDRAW (OGDRAW) version 1.3.1: Expanded toolkit for the graphical visualization of organellar genomes . Nucleic Acids Res 47 . doi: 10.1093/nar/gkz238 OpenUrl CrossRef ↵ Hilgers , L. , Liu , S. , Jensen , A. , Brown , T. , Cousins , T. , Schweiger , R. , Guschanski , K. , Hiller , M. , 2025 . Avoidable false PSMC population size peaks occur across numerous studies . Current Biology 35 , 927 - 930 .e3. doi: 10.1016/j.cub.2024.09.028 OpenUrl CrossRef PubMed ↵ Kajitani , R. , Toshimoto , K. , Noguchi , H. , Toyoda , A. , Ogura , Y. , Okuno , M. , Yabana , M. , Harada , M. , Nagayasu , E. , Maruyama , H. , Kohara , Y. , Fujiyama , A. , Hayashi , T. , Itoh , T. , 2014 . Efficient de novo assembly of highly heterozygous genomes from whole-genome shotgun short reads . Genome Res 24 . doi: 10.1101/gr.170720.113 OpenUrl Abstract / FREE Full Text ↵ Katoh , K. , Misawa , K. , Kuma , K.I. , Miyata , T. , 2002 . MAFFT: A novel method for rapid multiple sequence alignment based on fast Fourier transform . Nucleic Acids Res 30 . doi: 10.1093/nar/gkf436 OpenUrl CrossRef PubMed Web of Science ↵ Katoh , K. , Standley , D.M. , 2013 . MAFFT multiple sequence alignment software version 7: Improvements in performance and usability . Mol Biol Evol 30 . doi: 10.1093/molbev/mst010 OpenUrl CrossRef PubMed Web of Science ↵ Korf , I. , 2004 . Gene finding in novel genomes . BMC Bioinformatics 5 . doi: 10.1186/1471-2105-5-59 OpenUrl CrossRef PubMed ↵ Lezin , E. , Carqueijeiro , I. , Cuello , C. , Durand , M. , Jansen , H.J. , Vergès , V. , Birer Williams , C. , Oudin , A. , Dugé de Bernonville , T. , Petrignet , J. , Celton , N. , St-Pierre , B. , Papon , N. , Sun , C. , Dirks , R.P. , O’Connor , S.E. , Jensen , M.K. , Besseau , S. , Courdavault , V. , 2024 . A chromosome-scale genome assembly of Rauvolfia tetraphylla facilitates identification of the complete ajmaline biosynthetic pathway . Plant Commun . doi: 10.1016/j.xplc.2023.100784 OpenUrl CrossRef PubMed ↵ Li , H. , 2018 . Minimap2: Pairwise alignment for nucleotide sequences . Bioinformatics 34 . doi: 10.1093/bioinformatics/bty191 OpenUrl CrossRef PubMed ↵ Li , H. , Durbin , R. , 2011 . Inference of human population history from individual whole-genome sequences . Nature 475 . doi: 10.1038/nature10231 OpenUrl CrossRef PubMed Web of Science ↵ Lin , J.P. , Yang , J.S. , Lin , J.J. , Lai , K.C. , Lu , H.F. , Ma , C.Y. , Sai-Chuen Wu , R. , Wu , K.C. , Chueh , F.S. , Gibson Wood , W. , Chung , J.G. , 2012 . Rutin inhibits human leukemia tumor growth in a murine xenograft model in vivo . Environ Toxicol 27 . doi: 10.1002/tox.20662 OpenUrl CrossRef PubMed ↵ Lobay , D. , 2015 . Rauwolfia in the treatment of hypertension . Integrative Medicine (Boulder) . ↵ Marçais , G. , Kingsford , C. , 2011 . A fast, lock-free approach for efficient parallel counting of occurrences of k-mers . Bioinformatics 27 . doi: 10.1093/bioinformatics/btr011 OpenUrl CrossRef PubMed Web of Science ↵ Mather , N. , Traves , S.M. , Ho , S.Y.W. , 2020 . A practical introduction to sequentially Markovian coalescent methods for estimating demographic history from genomic data . Ecol Evol . doi: 10.1002/ece3.5888 OpenUrl CrossRef ↵ Meena , A.K. , Bansal , P. , Kumar , S. , 2009 . Plants-herbal wealth as a potential source of ayurvedic drugs . Distribution 4 . ↵ Mikheenko , A. , Prjibelski , A. , Saveliev , V. , Antipov , D. , Gurevich , A. , 2018 . Versatile genome assembly evaluation with QUAST-LG , in: Bioinformatics . doi: 10.1093/bioinformatics/bty266 OpenUrl CrossRef PubMed ↵ Mukherjee , E. , Gantait , S. , Kundu , S. , Sarkar , S. , Bhattacharyya , S. , 2019 . Biotechnological interventions on the genus Rauvolfia: recent trends and imminent prospects . Appl Microbiol Biotechnol . doi: 10.1007/s00253-019-10035-6 OpenUrl CrossRef ↵ Nadachowska-Brzyska , K. , Burri , R. , Smeds , L. , Ellegren , H. , 2016 . PSMC analysis of effective population sizes in molecular ecology and its application to black-and-white Ficedula flycatchers . Mol Ecol 25 . doi: 10.1111/mec.13540 OpenUrl CrossRef PubMed ↵ Ou , S. , Jiang , N. , 2018 . LTR_retriever: A highly accurate and sensitive program for identification of long terminal repeat retrotransposons . Plant Physiol 176 . doi: 10.1104/pp.17.01310 OpenUrl Abstract / FREE Full Text Pandey , D.K. , Radha Dey , A. , 2016 . A validated and densitometric HPTLC method for the simultaneous quantification of reserpine and ajmalicine in Rauvolfia serpentina and Rauvolfia tetraphylla . Revista Brasileira de Farmacognosia 26 . doi: 10.1016/j.bjp.2016.04.002 OpenUrl CrossRef ↵ Pisias , N.G. , Moore , T.C. , 1981 . The evolution of Pleistocene climate: A time series approach . Earth Planet Sci Lett 52 . doi: 10.1016/0012-821X(81)90197-7 OpenUrl CrossRef GeoRef Web of Science ↵ Poonam , P. , 2013 . Physiological, Biochemical and Modern Biotechnological Approach to Improvement of Rauwolfia serpentina . IOSR J Pharm Biol Sci 6 . doi: 10.9790/3008-0627378 OpenUrl CrossRef ↵ Rambaut , A. , 2016 . FigTree – Tree Figure Drawing Tool, version 1.4.3 . Molecular evolution, phylogenetics and epidemiology . ↵ Rambaut , A. , 2009 . FigTree, a graphical viewer of phylogenetic trees . Institute of Evolutionary Biology University of Edinburgh . ↵ Rolf , S. , Bruns , H.J. , Wichter , T. , Kirchhof , P. , Ribbing , M. , Wasmer , K. , Paul , M. , Breithardt , G. , Haverkamp , W. , Eckardt , L. , 2003 . The ajmaline challenge in Brugada syndrome: Diagnostic impact, safety, and recommended protocol . Eur Heart J 24 . doi: 10.1016/S0195-668X(03)00195-7 OpenUrl CrossRef PubMed Web of Science ↵ Schuman , M.C. , 2025 . eLife Assessment: Species biology and demographic history determines species vulnerability to climate change in tropical island endemic birds . doi: 10.7554/eLife.106369.1.sa3 OpenUrl CrossRef ↵ Simão , F.A. , Waterhouse , R.M. , Ioannidis , P. , Kriventseva , E. V. , Zdobnov , E.M. , 2015 . BUSCO: Assessing genome assembly and annotation completeness with single-copy orthologs . Bioinformatics 31 . doi: 10.1093/bioinformatics/btv351 OpenUrl CrossRef PubMed ↵ Stamatakis , A. , 2014 . RAxML version 8: A tool for phylogenetic analysis and post-analysis of large phylogenies . Bioinformatics 30 . doi: 10.1093/bioinformatics/btu033 OpenUrl CrossRef PubMed Web of Science ↵ Stanke , M. , Diekhans , M. , Baertsch , R. , Haussler , D. , 2008 . Using native and syntenically mapped cDNA alignments to improve de novo gene finding . Bioinformatics 24 . doi: 10.1093/bioinformatics/btn013 OpenUrl CrossRef PubMed Web of Science ↵ van der Hammen , T. , 1974 . The Pleistocene Changes of Vegetation and Climate in Tropical South America . J Biogeogr 1 . doi: 10.2307/3038066 OpenUrl CrossRef GeoRef ↵ Verbitsky , M.Y. , Crucifix , M. , Volobuev , D.M. , 2018 . A theory of Pleistocene glacial rhythmicity . Earth System Dynamics 9 . doi: 10.5194/esd-9-1025-2018 OpenUrl CrossRef ↵ Vurture , G.W. , Sedlazeck , F.J. , Nattestad , M. , Underwood , C.J. , Fang , H. , Gurtowski , J. , Schatz , M.C. , 2017 . GenomeScope: Fast reference-free genome profiling from short reads , in: Bioinformatics . doi: 10.1093/bioinformatics/btx153 OpenUrl CrossRef PubMed ↵ Wolpert , C. , Echternach , C. , Veltmann , C. , Antzelevitch , C. , Thomas , G.P. , Spehl , S. , Streitner , F. , Kuschyk , J. , Schimpf , R. , Haase , K.K. , Borggrefe , M. , 2005 . Intravenous drug challenge using flecainide and ajmaline in patients with Brugada syndrome . Heart Rhythm 2 . doi: 10.1016/j.hrthm.2004.11.025 OpenUrl CrossRef PubMed Web of Science ↵ Wright , C.W. , Phillipson , J.D. , Awe , S.O. , Kirby , G.C. , Warhurst , D.C. , Quetin-Leclercq , J. , Angenot , L. , 1996 . Antimalarial activity of cryptolepine and some other anhydronium bases . Phytotherapy Research 10 . doi: 10.1002/(SICI)1099-1573(199606)10:43.0.CO;2-N OpenUrl CrossRef View the discussion thread. Back to top Previous Next Posted October 27, 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 De novo genome Assembly of Rauvolfia Serpentina and comparative paleodemographic analysis of Apocynaceae plants 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 De novo genome Assembly of Rauvolfia Serpentina and comparative paleodemographic analysis of Apocynaceae plants Mratunjay Dwivedi , Nagarjun Vijay bioRxiv 2025.10.27.684745; doi: https://doi.org/10.1101/2025.10.27.684745 Share This Article: Copy Citation Tools De novo genome Assembly of Rauvolfia Serpentina and comparative paleodemographic analysis of Apocynaceae plants Mratunjay Dwivedi , Nagarjun Vijay bioRxiv 2025.10.27.684745; doi: https://doi.org/10.1101/2025.10.27.684745 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Evolutionary Biology Subject Areas All Articles Animal Behavior and Cognition (7617) Biochemistry (17633) Bioengineering (13856) Bioinformatics (41841) Biophysics (21399) Cancer Biology (18529) Cell Biology (25422) Clinical Trials (138) Developmental Biology (13352) Ecology (19860) Epidemiology (2067) Evolutionary Biology (24281) Genetics (15582) Genomics (22461) Immunology (17700) Microbiology (40295) Molecular Biology (17140) Neuroscience (88413) Paleontology (666) Pathology (2823) Pharmacology and Toxicology (4813) Physiology (7632) Plant Biology (15107) Scientific Communication and Education (2042) Synthetic Biology (4284) Systems Biology (9808) Zoology (2267)