Efficient amplicon panels for evaluating hybridization and genetic structure in the Schistosoma haematobium species group

Efficient amplicon panels for evaluating hybridization and genetic structure in the Schistosoma haematobium species group | 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 Efficient amplicon panels for evaluating hybridization and genetic structure in the Schistosoma haematobium species group View ORCID Profile Roy N Platt II , Grace A Arya , Bonnie L Webster , Aidan M Emery , View ORCID Profile Timothy JC Anderson doi: https://doi.org/10.1101/2025.07.18.665602 Roy N Platt II 1 Texas Biomedical Research Institute , San Antonio TX, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Roy N Platt II For correspondence: rplatt{at}txbiomed.org tanderso{at}txbiomed.org Grace A Arya 1 Texas Biomedical Research Institute , San Antonio TX, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site Bonnie L Webster 2 Natural History Museum , London, United Kingdom Find this author on Google Scholar Find this author on PubMed Search for this author on this site Aidan M Emery 2 Natural History Museum , London, United Kingdom Find this author on Google Scholar Find this author on PubMed Search for this author on this site Timothy JC Anderson 1 Texas Biomedical Research Institute , San Antonio TX, United States Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Timothy JC Anderson For correspondence: rplatt{at}txbiomed.org tanderso{at}txbiomed.org Abstract Full Text Info/History Metrics Supplementary material Preview PDF Abstract Genetic markers for detecting hybridization and measuring population genetic parameters must be informative and cost-effective. Most population genetic studies within the Schistosoma haematobium species group rely on either a two-marker system consisting of the mitochondrial, c ytochrome ox idase 1 ( cox 1) and the nuclear internal transcribed s pacer (ITS) markers or, at the other extreme, millions of s ingle n ucleotide v ariants (SNVs) from whole genome/exome sequencing. cox 1 and ITS studies contain minimal population genetic information but whole genome sequencing is cost-prohibitive. We examined ∼38 million previously published, whole genome SNVs genotyped in 162 S. haematobium and S. bovis sampled across Africa. We compared population genetic parameters from 4,000 panels of 10-100,000 randomly sampled SNVs to results from the whole genome dataset to test the resolution of reduced representation sequencing in schistosomes. We found that panels of 500 SNVs captured >99% of the population genetic information contained in the whole genome dataset by using Procrustes transformed principal component analyses and ancestry estimates ( r² = 0.85). Additionally, the costs of genotyping parasites with an amplicon panel is two to three times less than whole genome sequencing. Our results show that moderately-sized amplicon panels targeting random SNVs provide an efficient approach to large scale, field-based schistosome surveillance. Background Many schistosome species are capable of hybridizing under laboratory conditions (1) and the opportunity for hybridization in the field is a particular concern ( 2 , 3 ). Significant efforts have been made to monitor the extent of hybridization in the field, with a strong focus on interbreeding between the livestock parasite, S. bovis, and the human parasite, S. haematobium . The discordance between mitochondrial c ytochrome ox idase subunit I ( cox 1) and nuclear ribosomal internal transcribed s pacer (ITS) genetic markers has been used to identify putative hybrid schistosomes collected from humans in many African countries ( 4 ). Despite the reliance on this system, there are reasons to believe that hybrid parasites cannot be accurately identified using just two markers. A central problem is that hybrid parasites that contain heterozygous alleles at ribosomal ITS loci could reflect F1 hybrids, or be the result of shared ancestral polymorphisms and lineage sorting ( 5 ). Equally well, parasites resulting from historical hybridization events that occurred hundreds or thousands of generations ago may retain heterozygous ITS alleles further complicating hybrid identification. To provide a parallel example, many humans contain low levels of Neanderthal or Denisovan DNA, most of which are present in heterozygous state ( 6 ). These heterozygous archaic human alleles obviously do not indicate that F1 human-Neanderthal hybrids but instead reflect events that occurred ∼50,000 years ago. The presence of discordant mitochondria, represented by the cox 1 gene, can be caused by hybridization, incomplete lineage sorting as well as introgression. Due to their haploid and non-recombining nature, multiple discrete mitochondrial haplotypes can circulate within a population. When populations sub-divide, these haplotypes may be randomly distributed in the daughter lineages. As a result, the phylogenetic history of the mitochondria and alleles in the nuclear genome may differ substantially and give the appearance of gene flow between non-sister taxa ( 7 ). In other cases, mitochondrial discordance can be the direct result of historical gene flow between species which has been well documented in ( 8 ), flycatchers ( 9 ), skuas ( 10 ), chipmunks ( 11 ), Daphnia ( 12 ), and shrews ( 13 ), among other species. As a potential solution, whole genome studies can generate millions of s ingle n ucleotide v ariants (SNVs) and provide higher resolution than cox 1 and ITS markers. Unfortunately, the data is expensive to generate which limits the number of samples that can be examined in a study. To date, only a few hundred field-collected S. haematobium and S . bovis parasites have been examined with genome or exome SNVs compared to the thousands of samples included in cox 1 and ITS studies. These whole genome or exome studies have not yet identified recent hybrids (F1 or F2), but are underpowered for detecting rare contemporary hybridization events ( 14 – 17 ). Hence while the precision of whole genome sequencing is desirable, such studies are cost prohibitive, and difficult to scale. Several techniques have been used to generate large numbers of genome-wide markers in a high-throughput and cost-effective way but each has limitations. Microsatellites can generate dozens of distributed markers with multiplex PCRs and these results have confirmed the reproductive isolation between S. haematobium and S. bovis in Senegal ( 15 ). However, scoring microsatellites is not straightforward and can vary between labs ( 18 ). Reduced representation sequencing methods ( 19 ), like restriction-site a ssociated D NA seq uencing (RADseq), have shown that S. haematobium hybridizes with S. guineensis ( 20 ), but reproducibility between RADseq studies can be an issue in general ( 21 ). Targeted sequence capture which uses biotinylated probes to hybridize and enrich pre-determined loci have been used to sequence entire exomes in schistosomes ( 17 , 22 – 24 ). The probes themselves are capable of capturing moderately diverged sequences making them particularly useful in capturing homologous loci in related taxa ( 25 ), but the initial cost of developing the probes and cost per reaction can represent a hurdle. Amplicon panels can be generated to target multiple markers simultaneously using a two-step multiplexed PCR reaction ( 26 ). In the first step ancestry-informative markers ( 27 ), drug resistance markers ( 28 ), small indels ( 29 ) or other combinations of variants ( 30 ) can be targeted with locus specific primers. Amplicon panels that target moderate numbers of SNVs have been show to resolve population structure for a range of taxa with dozens to hundreds of markers (for examples see 31, 32, 33) and primer sequences can be shared between labs potentially solving the problem of reproducibility. A clear need exists for a high-throughput cost effective method for genotyping schistosomes that is robust and reproducible. This study was designed to determine how many SNVs are required for accurate assessment of hybridization and population structure in schistosome populations using amplicon panels. To achieve this, we down sampled SNVs from a published dataset ( 14 ) comprising 38 million SNVs in 141 S. haematobium and 21 S. bovis parasites collected across Africa. The genome wide dataset clearly defines three populations: S. bovis , northern S. haematobium and southern S. haematobium . We compare panels of various sizes to determine the minimum number of markers necessary to maintain high accuracy in ancestry estimation for investigating hybridization and population structure in schistosomes. Our findings demonstrate that panels containing several hundred, genome-wide markers can perform as well as whole genome genotyping. Adoption of such panels has the potential to transform molecular surveillance in endemic areas, enabling more accurate detection of hybrids and better informing control strategies, while maintaining scalability and affordability. Methods Down-sampling All sequence data used in this study were obtained from public sources and previously examined in Platt et al . ( 14 ). The SNVs are available as a single file in the variant call format (VCF) at https://doi.org/10.5061/dryad.xgxd254sk . The dataset includes 38,198,427 SNVs genotyped for 162 S. haematobium (n=141) or S. bovis (n=21) parasites. S. haematobium individuals were further subcategorized into two populations that broadly coincide with north (n=82) and south (n=59) Africa based on previous analyses ( 14 ). We applied additional filters to retain autosomal variants at moderate to high frequencies (>5%) using VCFtools v0.1.16 ( 34 ). Then we used PLINK v 2.00a5.12 to prune linked variants in sliding windows of 25 SNVs, shifting the window by 5 SNVs at a time, and removing variants with pairwise linkage disequilibrium, measured as r ²>0.2. We randomly subsampled SNVs from the filtered dataset in 38 bins, ranging in size from 10-100,000 SNVs. This was replicated 100 times by randomly sampling SNVs without replacement and repeating the population genetic analyses (described below). Random SNVs were selected using Python’s v3.11.11 random.sample() function, with the random seed initialized using NumPy’s v2.1.3 randint() function ( 35 ). A VCF file was created for each SNV subset using VCFtools v0.1.16 ( 34 ). Population genetic comparisons using down-sampled datasets We compared the complete dataset, with each down-sampled dataset using several metrics: (i) Principal component analysis (PCA) : This analysis was performed using PLINK v 2.00a5.12 ( 36 ). Each subset PCA was compared to a reference PCA, as generated from all filtered SNVs, using a Procrustes transformation ( 37 ) via the scipy.spatial.procrustes() function v1.15.2 ( 38 ). Disparity ( M² ) is a unitless metric that minimizes the sum of the squared distances between data points (individuals) in the transformed PCAs. Procrustes disparity ( M²) can be converted to similarity (𝑡 0 ) with . In this case it is used to assess differences in population structure as it is ascertained by PCA with all of the SNVs versus a subset. (ii) Fixation index (FST): We calculated the global, weighted, Weir-Cockerham FST for each subsampled set of SNVs. Individuals in the data set were assigned to three possible populations including S. bovis and either northern or southern S. haematobium based on the designations specified in Platt et al . ( 14 ). We measured FST between populations with VCFtools v0.1.16 ( 34 ). (iii) Ancestry estimation : We estimated ancestry for each individual using panels with 10-100,000 SNVs from a randomly chosen set of replicates. We estimated ancestry for each panel and included two populations ( k ) and 1,000 cross-validation replicates with ADMIXTURE v1.3.0 ( 39 ). We selected k =2 because it corresponds with the two species in the dataset; S. haematobium and S. bovis . Next, we compared the non– S. haematobium ancestry proportion ( q ) between the subsampled and full datasets using the linear regression linregress() function from SciPy v1.15.2 ( 38 ). The linear regression was restricted to S. haematobium individuals based on the species assignments provided by Platt et al . ( 14 ). We calculated the slope, intercept, correlation ( r² ), and p-value to assess the strength and significance of the association between the two sets of ancestry estimates. Cost estimates We estimated the costs of genotyping 1,000 parasites with whole genome sequencing, and an amplicon panel with 500 loci. We assumed that each sample started from a single miracidium stored on an FTA card. DNA is extracted from the card and amplified simultaneously using whole genome amplification ( 23 ). We targeted 20x coverage for whole genome samples based on a 400.3 Mb ( 40 ) genome (8.0 Gb / parasite) and 100x coverage per sample per locus for amplicon panels (7.5 Mb / parasite). Costs for reagents were taken directly from manufacturer websites and do not include unpublished discounts. When reaction sizes were not divisible by 100 samples, we included costs for partial kits. Reproducibility Analyses were conducted on compute nodes with 192 cores and 1 TB of memory at the Texas Biomedical Research Institute’s high-performance computing cluster. We managed all software environments with Conda v24.11.3 and open source repositories at CondaForge MiniForge and BioConda. All code necessary to reproduce the analyses are stored in a Jupyter Lab v4.3.5 notebooks and environmental recipe files at GitHub ( https://github.com/nealplatt/schisto_aim_panel ) and permanently archived on Zenodo at ( https://doi.org/10.5281/zenodo.15236800 ). Results The Platt et al . ( 14 ) dataset contained 162 S. haematobium and S. bovis samples genotyped at 38,198,427 SNVs. We removed 7,860,528 variants from the mitochondrial genome and sex chromosomes and another 24,364,917 that were at low frequency (38 million SNVs from the Platt et al . ( 14 ) dataset were reduced to 381,501 moderate-to-high frequency, unlinked, autosomal variants. We randomly down sampled the variants into datasets with 10-100,000 SNVs and replicated each SNV size category 100 times to understand how many SNVs are needed to replicate the results from the full, genome-wide dataset. In total we generated 3,700 random combinations of SNVs. For each set of SNV replicates we compared a PCA to one generated from the genome-wide SNVs in the filtered dataset ( Table 1 ). Similarity between the Procrustes transformed PCAs is correlated with the number of markers examined ( Figure 1 ); with 10 markers similarity between the PCAs was low (mean 0.755; range = 0.422-0.886). By 500 SNVs mean similarity between all replicated and whole genome datasets was high ( t o ≥0.99) with an interquartile range 0.999; Figure 2 ). Download figure Open in new tab Figure 1. Similarity between randomly sampled SNV panels and a whole genome dataset. (A). Procrustes similarity ( t 0 ) between panels of random SNVs and the whole genome dataset were calculated across >100 replicate PCAs for panels ranging in size from 10-1,000 SNVs. SNV datasets >1,000 SNVs aren’t shown but show t 0 <0.999 in all replicates. Red lines indicate mean values, box plots cover the interquartile range from 25%-75% of values. Whiskers indicate the full range of values. All t 0 values are shown with grey markers. The source data shown in this figure is available in the supplemental materials. Download figure Open in new tab Figure 2. P rincipal c omponent a nalyses (PCA) converge with increase numbers of SNVs PCAs were generated from all filtered variants (n = 381,501 SNVs; red markers) and randomly selected variants (blue markers). Procrustes transformations were used to measure similarity ( t 0 ) between PCAs generated from all and a random subset of variants. We examined SNVs panels containing 10 - 100,00. Results are shown for (A) 10, (B) 20, (C) 50, (D) 100 (E) 200, (F) 300, (G) 400, (H) 500, (I) 1,000, (J) 2,000, (K) 10,000, and (L) 100,000 SNVs at which point the similarity between the panel and full data sets are effectively identical. The source data shown in this figure is available in the supplemental materials. View this table: View inline View popup Download powerpoint Table 1. Procrustes similarity (t0) measured between SNV panels and the whole genome dataset across multiple replicates. We examined changes in ancestry assignment ( q ) using Admixture and assuming 2 populations ( k ). Specifically, we compared S. bovis introgression in S. haematobium parasites by comparing q from SNV panels and the whole genome dataset ( Figure 3 ). S. bovis ancestry estimates from whole genome data and 10 random SNVs was weakly and negatively correlated ( Table 2 , Figure 3 ). In this case, the ancestry component that is highest in S. bovis is also highest in southern S. haematobium . This result demonstrates the difficulty in ancestry assignment with underpowered datasets. Whole genome and panel estimates were highly correlated with 400 ( r 2 =0.77) to 500 ( r 2 =0.86) SNVs. The panel of 500 SNVs underestimated the amount of introgressed S. bovis ancestry by (mean) 0.4% but some samples were affected by as much as - 10.3% to 5%. Interestingly the mean bias is comparable in the 400 SNV panel (-0.6%) but the range of bias is smaller from -7.5% to 6%. This is likely an artifact of randomly selecting SNVs and would decrease with the number of markers. Once 1,000 SNVs were sampled all correlations were greater than 0.9 and the bias range is less than 8%. Download figure Open in new tab Figure 3 Comparing ancestry estimates SNV panels and whole genome data. (A). S. bovis introgressed alleles are present in many S. haematobium individuals. We compared the percent minor parent ancestry ( q ) from SNV panels to estimates made from whole genome data. The two are positively correlated once 50 SNVs are sampled though the strength of the correlation continues to increase. The scatter plots only show S. haematobium individuals. These results show that the panels of SNVs can accurately replicate a set of whole genome SNVs with a few hundred to thousand markers. The source data shown in this figure is available in the supplemental materials. View this table: View inline View popup Download powerpoint Table 2. Correlation among S. haematobium and S. bovis ancestry estimates from SNV panels and a whole genome dataset. We measured the global, weighted, Weir-Cockerham FST for each replicate. Overall, the mean FST values were relatively robust to changes in panel size ( Figure 4 ). For example, FST from all SNVs was 0.429 and the mean FST with 10 SNVs was 0.407 measured across 100 replicates. However, the variance in FST decreases with an increase in panel size. FST ranged from 0.182-0.649 with 10 SNVs to 0.393-0.468 with 500 SNVs (mean FST = 0.427) and the interquartile range (IQR) was reduced by 6.3-fold from 0.133 to 0.021 between these two datasets. Download figure Open in new tab Figure 4. Fixation index (FST) versus panel size. The global, weighted Weir-Cockerham FST was measured between northern S. haematobium , southern S. haematobium , and S. bovis with panels ranging from 10-100,000 SNVs. The red line indicates FST measured with all autosomal, unlinked, common (minor allele frequency >0.05) SNVs in the whole genome dataset (n SNVs = 381,501). Yellow boxes represent mean values for each panel size. Individual FST values are shown with black dots. Mean Fst is relatively consistent regardless of panel size, but the variation among replicates is inversely correlated the number of makers. The source data shown in this figure is available in the supplemental materials. Supplemental Tables 1 and 2 provide estimated costs to genotype 1,000 samples with whole genome SNVs or a 500-locus amplicon panel. Sequencing an amplicon panel costs ∼$29.43 per sample compared $77.21 for whole genome sequencing. Of these costs, $9.34 goes towards isolating, purifying, and whole genome amplifying DNA from miracidia stored on FTA cards wich is used in both methods. Consumables like pipette tips, tubes, etc. count for an additional $2.16-$4.40 per sample. Library preparation for whole genome sequencing requires additional steps leading to higher consumable costs. Sequencing costs are higher for whole genome sequencing since each sample needs approximately three orders of magnitude more reads to achieve acceptable coverage for genotyping; 7.5Mb per amplicon sample vs 8.0 Gb per whole genome sample. Alternatively generating an initial pool of 100 uM primers for 500 loci represents a substantial upfront cost (∼$5,400) that offsets some of these savings when using amplicon panel. Pooled primers are sufficient for thousands of reactions so are ideal for large studies with multiple individuals. Discussion Population genetics can be used to guide the management and elimination of schistosomes ( 41 ). Unfortunately, the most common tools used for studying schistosome population genetics and hybridization - cox 1/ITS or whole genome sequencing - represent the extremes in costs, throughput, and precision. A two-marker system provides little information concerning ancestry in schistosomes. Further, in-silico work has shown that 7-293 species diagnostic markers are needed to differentiate between contemporary hybrids from parental species. However, differentiating advanced backcrosses can require thousands of markers ( 42 , 43 ). In this study, we used in-silico tests to examine the performance of random SNV panels relative to whole genome data. The results show that panels comprising hundreds of SNVs contain comparable information to hundreds of thousands of markers ( Figure 1 , Table 1 ). This is similar to results from human studies that show 500 -1,000 random SNVs can effectively replicate whole genome results ( 44 ). Generating sequencing libraries from hundreds of loci can be done in a multiplex PCR reaction. Target loci can be randomly selected from available variants, and primers pools that minimize mispriming and optimize PCR reaction conditions can be generated with tools like PrimerJinn ( 45 ), BatchPrimer3 ( 46 ), or SADDLE ( 47 ). After the target loci have been amplified a second PCR reaction is used to index the library and complete the Illumina sequencing adapters. This method has been used to genotype thousands of individuals at hundreds of loci in other taxa ( 26 ). Random SNVs vs Ancestry Informative Markers Other studies have used tools like PCA loadings or FST to extract a minimal set of a ncestry informative m arkers (AIMs) to distinguish between species or populations ( 33 , 48 – 50 ). These panels may contain as few as a dozen markers ( 51 ). For studies where the central goal is to evaluate levels of hybridization between S. haematobium and S. bovis , such AIM panels may be useful. Modeling work has shown that identifying F1 hybrids requires at least 5 species diagnostic markers ( 52 ). If markers are not diagnostic, as many as 12 loci are needed to identify an F1 hybrid only if there are moderate allele frequency differences between the parental populations ( 53 ). That number climbs dramatically when trying to differentiate between advanced backcrossed from pure-parental classes. For example, after 6 generations of backcrossing, 191 diagnostic markers are required to achieve 95% confidence (α = .05) and 293 markers are needed for 99% (α = .01) confidence in the classification ( 42 ). There are 275,657 SNVs that differentiate S. haematobium and S. bovis (Supplemental Table 2 in 14): a subset of these could be used to generate an AIM panel. However, while AIM panels maximize the amount of information regarding ancestry or population assignment, they are biased when quantifying population genetic parameters. Hence, a small panel of AIMs would be useful to explore levels of introgression between S. haematobium and S. bovis , but the same panel would be extremely biased for studying population differentiation between locations, or determining relatedness of parasites, and may miss signals of hybridization or introgression from other species ( 20 , 54 – 56 ). Further, our results show that small panels of SNVs may lack precision in estimating parameters like FST ( Figure 4 ). Both random and AIM panels may be useful for different research questions, and optimal panels for both can be designed based on genome-wide marker data from Platt et al . ( 14 ). However, randomly selected marker panels are more generally useful. Cost-efficiency vs Diagnostic Power The accuracy of hybrid identification or population parameter estimation is directly linked to the number of markers used, but additional markers increase costs. We estimated the costs to examine 1,000 parasitesusing a 500-locus amplicon panel and whole genome sequencing. The results show that amplicon panels are two to three times more affordable than whole genome sequencing while providing comparable resolution. Further technical modification can decrease the prices even further. For example, cost-saving techniques like library miniaturization ( 57 ) and automation can substantially reduce the price of reaction sizes and the necessary reagents. Other reduced representation methods likely provide similar benefits. For example, Landeryou et al . identified S. haematobium and S. guineensis hybrids by genotyping RADseq loci ( 20 ). The costs of RADseq are comparable to amplicon panels given the reduced number of reads needed to achieve reasonable coverage. However, amplicon panels require less technical expertise than RADseq, so they can be widely adopted. Laboratories that routinely conduct cox 1/ITS genotyping can transition to using amplicon panels. In addition to being cost-effective, amplicon panels require fewer computational resources for data analyses. For example, whole genome SNV datasets with millions of markers require access to a computing cluster. Our lab uses a computing cluster with 12 nodes; each with 192 processors and 1-1.5 Tb of memory. In that case, genotyping 218 samples still took several weeks. By comparison, smaller amplicon datasets could be analyzed on a reasonably powered personal computer in a matter of hours. Limitations and Future Perspectives While reduced representation sequencing seems to be a viable option for schistosomes it is worth noting a few limitations. First, while the median difference between S. bovis ancestry estimates from genome sequence data and an amplicon panel of 500 markers is less than 1%, individual estimates may differ by -10.3% to 5%. This variance could affect hybrid classification with software that uses allele frequencies ( 43 ). Future work could incorporate lab generated hybrids as a positive control to precisely quantify this uncertainty. Second, the SNVs in this study are circulating in the S. haematobium and S. bovis populations at moderate frequencies. Introgression from an unsampled species, like S. guineensis ( 20 ), may not be readily apparent in this case. They could even be missed if the introgressed variants are at low frequencies (<5%) and were filtered out from the Platt et al . ( 14 ) SNV set. This issue will be resolved as the population genomic data for S. curassoni, intercalatum , guineensis , mattheei and margrebowiei become available and panels can be re- designed and updated to have the broadest applicability within the S. haematobium group. Conclusion Large scale, genome studies are able to resolve population genetic structure with high precision but are difficult to scale adequately to detect rare hybridization events. By contrast, genotyping parasites with only two markers, as is the standard in many schistosome studies, can be applied to thousands of individuals, but can produce ambiguous results. Here we show that sequencing a moderate number of random SNVs can efficiently capture the majority of the population genetic data contained within a parasite genome. Further, the costs of sequencing such panels are considerably less than whole genome sequencing allowing examination of hundreds or thousands of individuals. We conclude that amplicon panels provide an effective compromise strategy, allowing cost-effective, robust characterization of large numbers of samples, and providing accurate measures of both population structure and hybrid ancestry. Acknowledgements We thank Sandy Smith and John Heaner for providing computational support at Texas Biomedical Research Institute’s High-Performance Computing Cluster. Jenna M. Hulke provided valuable insights regarding data analysis and experimental design. This research was funded by the National Institute of Allergy and Infectious Diseases (NIAD R01 AI166049-01). Funder Information Declared National Institute of Allergy and Infectious Diseases , AI166049-01 References 1. Taylor MG . Hybridisation experiments on five species of African schistosomes . Journal of helminthology . 1970 ; 44 ( 3 ): 253 – 314 . Epub 1970/01/01. doi: 10.1017/s0022149x00021969 . PubMed PMID: 5505355 . OpenUrl CrossRef PubMed 2. ↵ King KC , Stelkens RB , Webster JP , Smith DF , Brockhurst MA. Hybridization in Parasites: Consequences for Adaptive Evolution, Pathogenesis, and Public Health in a Changing World . PLoS pathogens . 2015 ; 11 ( 9 ): e1005098 . Epub 2015/09/04. doi: 10.1371/journal.ppat.1005098 . PubMed PMID: 26336070 ; PMCID: PMC4559376 . OpenUrl CrossRef PubMed 3. ↵ Stothard JR , Kayuni SA , Al-Harbi MH , Musaya J , Webster BL . Future schistosome hybridizations: Will all Schistosoma haematobium hybrids please stand-up! PLoS Negl Trop Dis . 2020 ; 14 ( 7 ): e0008201 . Epub 2020/07/03. doi: 10.1371/journal.pntd.0008201 . PubMed PMID: 32614820 ; PMCID: PMC7332241 . OpenUrl CrossRef PubMed 4. ↵ Agniwo P , Savassi B , Boissier J , Dolo M , Ibikounlé M , Dabo A . Mapping of schistosome hybrids of the haematobium group in West and Central Africa . Journal of helminthology . 2024 ; 98 : e53 . Epub 2024/09/18. doi: 10.1017/s0022149x24000257 . PubMed PMID: 39291545 . OpenUrl CrossRef PubMed 5. ↵ Fleming JF , Valero-Gracia A , Struck TH . Identifying and addressing methodological incongruence in phylogenomics: A review . Evolutionary applications . 2023 ; 16 ( 6 ): 1087 – 104 . Epub 2023/06/26. doi: 10.1111/eva.13565 . PubMed PMID: 37360032 ; PMCID: PMC10286231 . OpenUrl CrossRef PubMed 6. ↵ Sankararaman S , Mallick S , Dannemann M , Prüfer K , Kelso J , Pääbo S , Patterson N , Reich D . The genomic landscape of Neanderthal ancestry in present-day humans . Nature . 2014 ; 507 (7492): 354 -7. Epub 2014/01/31. doi: 10.1038/nature12961 . PubMed PMID: 24476815 ; PMCID: PMC4072735 . OpenUrl CrossRef PubMed Web of Science 7. ↵ Ballard JW , Whitlock MC . The incomplete natural history of mitochondria . Molecular ecology . 2004 ; 13 ( 4 ): 729 – 44 . Epub 2004/03/12. doi: 10.1046/j.1365-294x.2003.02063.x . PubMed PMID: 15012752 . OpenUrl CrossRef PubMed Web of Science 8. ↵ Toews DP , Brelsford A . The biogeography of mitochondrial and nuclear discordance in animals . Molecular ecology . 2012 ; 21 ( 16 ): 3907 – 30 . Epub 2012/06/29. doi: 10.1111/j.1365-294X.2012.05664.x . PubMed PMID: 22738314 . OpenUrl CrossRef PubMed Web of Science 9. ↵ Andersen MJ , McCullough JM , Gyllenhaal EF , Mapel XM , Haryoko T , Jønsson KA , Joseph L . Complex histories of gene flow and a mitochondrial capture event in a nonsister pair of birds . Molecular ecology . 2021 ; 30 ( 9 ): 2087 – 103 . Epub 2021/02/23. doi: 10.1111/mec.15856 . PubMed PMID: 33615597 ; PMCID: PMC8252742 . OpenUrl CrossRef PubMed 10. ↵ Mikkelsen EK , Weir JT . Phylogenomics Reveals that Mitochondrial Capture and Nuclear Introgression Characterize Skua Species Proposed to be of Hybrid Origin . Systematic biology . 2023 ; 72 ( 1 ): 78 – 91 . Epub 2022/12/23. doi: 10.1093/sysbio/syac078 . PubMed PMID: 36546866 . OpenUrl CrossRef PubMed 11. ↵ Good JM , Hird S , Reid N , Demboski JR , Steppan SJ , Martin-Nims TR , Sullivan J . Ancient hybridization and mitochondrial capture between two species of chipmunks . Molecular ecology . 2008 ; 17 ( 5 ): 1313 – 27 . Epub 2008/02/28. doi: 10.1111/j.1365-294X.2007.03640.x . PubMed PMID: 18302691 . OpenUrl CrossRef PubMed Web of Science 12. ↵ Marková S , Dufresne F , Manca M , Kotlík P . Mitochondrial capture misleads about ecological speciation in the Daphnia pulex complex . PLoS One . 2013 ; 8 ( 7 ): e69497 . Epub 2013/07/23. doi: 10.1371/journal.pone.0069497 . PubMed PMID: 23869244 ; PMCID: PMC3711805 . OpenUrl CrossRef PubMed 13. ↵ Kunerth HD , Tapisso JT , Valente R , Mathias MDL , Alves PC , Searle JB , Vega R , Paupério J . Characterising Mitochondrial Capture in an Iberian Shrew . Genes . 2022 ; 13 ( 12 ). Epub 2022/12/24. doi: 10.3390/genes13122228 . PubMed PMID: 36553495 ; PMCID: PMC9777731 . OpenUrl CrossRef PubMed 14. ↵ Platt II RN , Enabulele EE , Adeyemi E , Agbugui MO , Ajakaye OG , Amaechi EC , Ejikeugwu CP , Igbeneghu C , Njom VS , Dlamini P , Arya GA , Diaz R , Rabone M , Allan F , Webster B , Emery A , Rollinson D , Anderson TJC . Genomic data reveal a north-south split and introgression history of blood fluke populations across Africa . Nat Commun . 2025 ; 16 ( 1 ): 3508 . Epub 2025/04/14. doi: 10.1038/s41467-025-58543-6 . PubMed PMID: 40223094 ; PMCID: PMC11994774 . OpenUrl CrossRef PubMed 15. ↵ Boon NAM , Mbow M , Paredis L , Moris P , Sy I , Maes T , Webster BL , Sacko M , Volckaert FAM , Polman K , Huyse T . No barrier breakdown between human and cattle schistosome species in the Senegal River Basin in the face of hybridisation . International journal for parasitology . 2019 ; 49 ( 13-14 ): 1039 – 48 . Epub 2019/11/18. doi: 10.1016/j.ijpara.2019.08.004 . PubMed PMID: 31734338 . OpenUrl CrossRef PubMed 16. Rey O , Toulza E , Chaparro C , Allienne JF , Kincaid-Smith J , Mathieu-Begné E , Allan F , Rollinson D , Webster BL , Boissier J . Diverging patterns of introgression from Schistosoma bovis across S. haematobium African lineages . PLoS pathogens . 2021 ; 17 ( 2 ): e1009313 . Epub 2021/02/06. doi: 10.1371/journal.ppat.1009313 . PubMed PMID: 33544762 ; PMCID: PMC7891765 . OpenUrl CrossRef PubMed 17. ↵ Platt RN , McDew-White M , Le Clec’h W , Chevalier FD , Allan F , Emery AM , Garba A , Hamidou AA , Ame SM , Webster JP , Rollinson D , Webster BL , Anderson TJC. Ancient Hybridization and Adaptive Introgression of an Invadolysin Gene in Schistosome Parasites . Molecular biology and evolution . 2019 ; 36 (10): 2127 - 42 . Epub 2019/06/30. doi: 10.1093/molbev/msz154 . PubMed PMID: 31251352 ; PMCID: PMC6759076 . OpenUrl CrossRef PubMed 18. ↵ Pasqualotto AC , Denning DW , Anderson MJ. A cautionary tale: Lack of consistency in allele sizes between two laboratories for a published multilocus microsatellite typing system . Journal of clinical microbiology . 2007 ; 45 ( 2 ): 522 – 8 . Epub 2006/12/15. doi: 10.1128/jcm.02136-06 . PubMed PMID: 17166958 ; PMCID: PMC1829014 . OpenUrl Abstract / FREE Full Text 19. ↵ Good JM . Reduced representation methods for subgenomic enrichment and next- generation sequencing. Methods in molecular biology (Clifton , NJ ). 2011 ; 772 : 85 – 103 . Epub 2011/11/09. doi: 10.1007/978-1-61779-228-1_5 . PubMed PMID: 22065433 . OpenUrl CrossRef PubMed Web of Science 20. ↵ Landeryou T , Rabone M , Allan F , Maddren R , Rollinson D , Webster BL , Tchuem- Tchuenté LA , Anderson RM , Emery AM . Genome-wide insights into adaptive hybridisation across the Schistosoma haematobium group in West and Central Africa . PLoS Negl Trop Dis . 2022 ; 16 ( 1 ): e0010088 . Epub 2022/02/01. doi: 10.1371/journal.pntd.0010088 . PubMed PMID: 35100291 ; PMCID: PMC8803156 . OpenUrl CrossRef PubMed 21. ↵ Mastretta-Yanes A , Arrigo N , Alvarez N , Jorgensen TH , Piñero D , Emerson BC . Restriction site-associated DNA sequencing, genotyping error estimation and de novo assembly optimization for population genetic inference . Molecular ecology resources . 2015 ; 15 ( 1 ): 28 – 41 . Epub 2014/06/12. doi: 10.1111/1755-0998.12291 . PubMed PMID: 24916682 . OpenUrl CrossRef PubMed 22. ↵ Platt RN , 2nd , Le Clec’h W , Chevalier FD , McDew-White M , LoVerde PT , Ramiro de Assis R , Oliveira G , Kinung’hi S , Djirmay AG , Steinauer ML , Gouvras A , Rabone M , Allan F , Webster BL , Webster JP , Emery AM , Rollinson D , Anderson TJC. Genomic analysis of a parasite invasion: Colonization of the Americas by the blood fluke Schistosoma mansoni. Molecular ecology . 2022 ; 31 ( 8 ): 2242 – 63 . Epub 2022/02/14. doi: 10.1111/mec.16395 . PubMed PMID: 35152493 . OpenUrl CrossRef PubMed 23. ↵ Le Clec’h W , Chevalier FD , McDew-White M , Allan F , Webster BL , Gouvras AN , Kinunghi S , Tchuem Tchuenté LA , Garba A , Mohammed KA , Ame SM , Webster JP , Rollinson D , Emery AM , Anderson TJC . Whole genome amplification and exome sequencing of archived schistosome miracidia . Parasitology . 2018 ; 145 ( 13 ): 1739 – 47 . Epub 2018/05/29. doi: 10.1017/s0031182018000811 . PubMed PMID: 29806576 ; PMCID: PMC6193844 . OpenUrl CrossRef PubMed 24. ↵ Jutzeler KS , Platt RN , Diaz R , Morales M , Clec’h WL , Chevalier FD , Anderson TJC . Abundant genetic variation is retained in many laboratory schistosome populations2024 : 2024 .10.21.619418. doi: 10.1101/2024.10.21.619418%JbioRxiv . OpenUrl CrossRef 25. ↵ Bi K , Vanderpool D , Singhal S , Linderoth T , Moritz C , Good JM . Transcriptome-based exon capture enables highly cost-effective comparative genomic data collection at moderate evolutionary scales . BMC genomics . 2012 ; 13 : 403 . Epub 2012/08/21. doi: 10.1186/1471-2164-13-403 . PubMed PMID: 22900609 ; PMCID: PMC3472323 . OpenUrl CrossRef PubMed 26. ↵ Campbell NR , Harmon SA , Narum SR . Genotyping-in-Thousands by sequencing (GT- seq): A cost effective SNP genotyping method based on custom amplicon sequencing . Molecular ecology resources . 2015 ; 15 ( 4 ): 855 – 67 . Epub 2014/12/06. doi: 10.1111/1755-0998.12357 . PubMed PMID: 25476721 . OpenUrl CrossRef PubMed 27. ↵ Galanter JM , Fernandez-Lopez JC , Gignoux CR , Barnholtz-Sloan J , Fernandez- Rozadilla C , Via M , Hidalgo-Miranda A , Contreras AV , Figueroa LU , Raska P , Jimenez-Sanchez G , Zolezzi IS , Torres M , Ponte CR , Ruiz Y , Salas A , Nguyen E , Eng C , Borjas L , Zabala W , Barreto G , González FR , Ibarra A , Taboada P , Porras L , Moreno F , Bigham A , Gutierrez G , Brutsaert T , León-Velarde F , Moore LG , Vargas E , Cruz M , Escobedo J , Rodriguez-Santana J , Rodriguez-Cintrón W , Chapela R , Ford JG , Bustamante C , Seminara D , Shriver M , Ziv E , Burchard EG , Haile R , Parra E , Carracedo A . Development of a panel of genome-wide ancestry informative markers to study admixture throughout the Americas . PLoS genetics . 2012 ; 8 ( 3 ): e1002554 . Epub 2012/03/14. doi: 10.1371/journal.pgen.1002554 . PubMed PMID: 22412386 ; PMCID: PMC3297575 the Future." 23andme is a Mountain View, CA, company that provides direct-to-consumer genetic products. CB is also on the SAB of Ancestry.com, a company in Provo, UT, that provides direct-to-consumer genetic products. Neither company played a part in the research described here or has a financial stake in the results. The remaining authors have declared that no competing interests exist. OpenUrl CrossRef PubMed Web of Science 28. ↵ Rovira-Vallbona E , Kattenberg JH , Hong NV , Guetens P , Imamura H , Monsieurs P , Chiheb D , Erhart A , Phuc BQ , Xa NX , Rosanas-Urgell A . Molecular surveillance of Plasmodium falciparum drug-resistance markers in Vietnam using multiplex amplicon sequencing (2000- 2016) . Sci Rep . 2023 ; 13 ( 1 ): 13948 . Epub 2023/08/26. doi: 10.1038/s41598-023-40935-7 . PubMed PMID: 37626131 ; PMCID: PMC10457381 . OpenUrl CrossRef PubMed 29. ↵ Huang Y , Liu C , Xiao C , Chen X , Yi S , Huang D . Development of a new 32-plex InDels panel for forensic purpose . Forensic science international Genetics . 2020 ; 44 : 102171 . Epub 2019/10/16. doi: 10.1016/j.fsigen.2019.102171 . PubMed PMID: 31614309 . OpenUrl CrossRef PubMed 30. ↵ Aranda-Díaz A , Neubauer Vickers E , Murie K , Palmer B , Hathaway N , Gerlovina I , Boene S , García-Ulloa M , Cisteró P , Katairo T , Semakuba FD , Nsengimaana B , Gwarinda H , García-Fernández C , Louie W , Esayas E , Da Silva C , Datta D , Kiyaga S , Wiringilimaana I , Feleke SM , Bennett A , Smith JL , Gadisa E , Parr JB , Conrad MD , Raman J , Tukwasibwe S , Ssewanyana I , Rovira-Vallbona E , Tato CM , Briggs J , Mayor A , Greenhouse B . Sensitive and modular amplicon sequencing of Plasmodium falciparum diversity and resistance for research and public health . Sci Rep . 2025 ; 15 ( 1 ): 10737 . Epub 2025/03/29. doi: 10.1038/s41598-025-94716-5 . PubMed PMID: 40155691 ; PMCID: PMC11953298 . OpenUrl CrossRef PubMed 31. Khan A , Krishna SM , Ramakrishnan U , Das R . Recapitulating whole genome based population genetic structure for Indian wild tigers through an ancestry informative marker panel . Heredity . 2022 ; 128 ( 2 ): 88 – 96 . Epub 2021/12/04. doi: 10.1038/s41437-021-00477-y . PubMed PMID: 34857925 ; PMCID: PMC8813985 . OpenUrl CrossRef PubMed 32. Qin P , Li Z , Jin W , Lu D , Lou H , Shen J , Jin L , Shi Y , Xu S . A panel of ancestry informative markers to estimate and correct potential effects of population stratification in Han Chinese . European journal of human genetics : EJHG . 2014 ; 22 ( 2 ): 248 – 53 . Epub 2013/05/30. doi: 10.1038/ejhg.2013.111 . PubMed PMID: 23714748 ; PMCID: PMC3895631 . OpenUrl CrossRef PubMed 33. ↵ Das R , Roy R , Venkatesh N . Using Ancestry Informative Markers (AIMs) to Detect Fine Structures Within Gorilla Populations . Front Genet . 2019 ; 10 : 43 . Epub 2019/02/26. doi: 10.3389/fgene.2019.00043 . PubMed PMID: 30800141 ; PMCID: PMC6375890 . OpenUrl CrossRef PubMed 34. ↵ Danecek P , Auton A , Abecasis G , Albers CA , Banks E , DePristo MA , Handsaker RE , Lunter G , Marth GT , Sherry ST , McVean G , Durbin R . The variant call format and VCFtools . Bioinformatics . 2011 ; 27 ( 15 ): 2156 – 8 . Epub 2011/06/10. doi: 10.1093/bioinformatics/btr330 . PubMed PMID: 21653522 ; PMCID: PMC3137218 . OpenUrl CrossRef PubMed Web of Science 35. ↵ Harris CR , Millman KJ , van der Walt SJ , Gommers R , Virtanen P , Cournapeau D , Wieser E , Taylor J , Berg S , Smith NJ , Kern R , Picus M , Hoyer S , van Kerkwijk MH , Brett M , Haldane A , Del Río JF , Wiebe M , Peterson P , Gérard-Marchant P , Sheppard K , Reddy T , Weckesser W , Abbasi H , Gohlke C , Oliphant TE . Array programming with NumPy . Nature . 2020 ; 585 (7825): 357 – 62 . Epub 2020/09/18. doi: 10.1038/s41586-020-2649-2 . PubMed PMID: 32939066 ; PMCID: PMC7759461 . OpenUrl CrossRef PubMed 36. ↵ Purcell S , Neale B , Todd-Brown K , Thomas L , Ferreira MA , Bender D , Maller J , Sklar P , de Bakker PI , Daly MJ , Sham PC . PLINK: a tool set for whole-genome association and population-based linkage analyses . American journal of human genetics . 2007 ; 81 ( 3 ): 559 – 75 . Epub 2007/08/19. doi: 10.1086/519795 . PubMed PMID: 17701901 ; PMCID: PMC1950838 . OpenUrl CrossRef PubMed 37. ↵ Hurley JR , Cattell RBJBs . The Procrustes program: Producing direct rotation to test a hypothesized factor structur e1962; 7 ( 2 ): 258 . 38. ↵ Virtanen P , Gommers R , Oliphant TE , Haberland M , Reddy T , Cournapeau D , Burovski E , Peterson P , Weckesser W , Bright J , van der Walt SJ , Brett M , Wilson J , Millman KJ , Mayorov N , Nelson ARJ , Jones E , Kern R , Larson E , Carey CJ , Polat İ , Feng Y , Moore EW , VanderPlas J , Laxalde D , Perktold J , Cimrman R , Henriksen I , Quintero EA , Harris CR , Archibald AM , Ribeiro AH , Pedregosa F , van Mulbregt P. SciPy 1.0: fundamental algorithms for scientific computing in Python . Nature methods . 2020 ; 17 ( 3 ): 261 – 72 . Epub 2020/02/06. doi: 10.1038/s41592-019-0686-2 . PubMed PMID: 32015543 ; PMCID: PMC7056644 author list, but not for authors in the SciPy 1.0 Contributor group beyond that. These affiliations may have since changed. R.G. was employed by Quansight LLC. T.E.O., E.J. and R.K. were employed by Enthought, Inc. T.E.O. and I.H. were employed by Anaconda Inc. N.M. was employed by WayRay LLC. E.W.M. was employed by Bruker Biospin Corp. F.P. and P.v.M. were employed by Google LLC. OpenUrl CrossRef PubMed 39. ↵ Alexander DH , Novembre J , Lange K . Fast model-based estimation of ancestry in unrelated individuals . Genome Res . 2009 ; 19 ( 9 ): 1655 – 64 . Epub 2009/08/04. doi: 10.1101/gr.094052.109 . PubMed PMID: 19648217 ; PMCID: PMC2752134 . OpenUrl Abstract / FREE Full Text 40. ↵ Stroehlein AJ , Korhonen PK , Lee VV , Ralph SA , Mentink-Kane M , You H , McManus DP , Tchuenté LT , Stothard JR , Kaur P , Dudchenko O , Aiden EL , Yang B , Yang H , Emery AM , Webster BL , Brindley PJ , Rollinson D , Chang BCH , Gasser RB , Young ND . Chromosome-level genome of Schistosoma haematobium underpins genome-wide explorations of molecular variation . PLoS pathogens . 2022 ; 18 ( 2 ): e1010288 . Epub 2022/02/16. doi: 10.1371/journal.ppat.1010288 . PubMed PMID: 35167626 ; PMCID: PMC8846543 . OpenUrl CrossRef PubMed 41. ↵ Lund AJ , Wade KJ , Nikolakis ZL , Ivey KN , Perry BW , Pike HNC , Paull SH , Liu Y , Castoe TA , Pollock DD , Carlton EJ . Integrating genomic and epidemiologic data to accelerate progress toward schistosomiasis elimination . eLife . 2022 ; 11 . Epub 2022/08/31. doi: 10.7554/eLife.79320 . PubMed PMID: 36040013 ; PMCID: PMC9427098 . OpenUrl CrossRef PubMed 42. ↵ Silva JPD , Caetano AR . Determining minimum numbers of di-allelic diagnostic markers required to identify introgressions in diploid cross-species hybrid individuals from different types of inter- and backcross populations . Genetics and molecular biology . 2020 ; 43 ( 3 ): e20190324 . Epub 2020/09/02. doi: 10.1590/1678-4685-gmb-2019-0324 . PubMed PMID: 32870232 ; PMCID: PMC7445936 . OpenUrl CrossRef PubMed 43. ↵ Anderson EC . Bayesian inference of species hybrids using multilocus dominant genetic markers. Philosophical transactions of the Royal Society of London Series B , Biological sciences . 2008 ; 363 (1505): 2841 -50. Epub 2008/05/30. doi: 10.1098/rstb.2008.0043 . PubMed PMID: 18508754 ; PMCID: PMC2606736 . OpenUrl CrossRef PubMed 44. ↵ Pardo-Seco J , Martinón-Torres F , Salas A . Evaluating the accuracy of AIM panels at quantifying genome ancestry . BMC genomics . 2014 ; 15 ( 1 ): 543 . Epub 2014/07/02. doi: 10.1186/1471-2164-15-543 . PubMed PMID: 24981136 ; PMCID: PMC4101176 . OpenUrl CrossRef PubMed 45. ↵ Limberis JD , Metcalfe JZ . primerJinn: a tool for rationally designing multiplex PCR primer sets for amplicon sequencing and performing in silico PCR . BMC bioinformatics . 2023 ; 24 ( 1 ): 468 . Epub 2023/12/12. doi: 10.1186/s12859-023-05609-1 . PubMed PMID: 38082220 ; PMCID: PMC10714587 . OpenUrl CrossRef PubMed 46. ↵ Global incidence, prevalence, years lived with disability (YLDs), disability-adjusted life- years (DALYs), and healthy life expectancy (HALE) for 371 diseases and injuries in 204 countries and territories and 811 subnational locations, 1990-2021: a systematic analysis for the Global Burden of Disease Study 2021 . Lancet (London, England). 2024 ; 403 ( 10440 ): 2133 – 61 . Epub 2024/04/21. doi: 10.1016/s0140-6736(24)00757-8 . PubMed PMID: 38642570 ; PMCID: PMC11122111 . OpenUrl CrossRef PubMed 47. ↵ Xie NG , Wang MX , Song P , Mao S , Wang Y , Yang Y , Luo J , Ren S , Zhang DY . Designing highly multiplex PCR primer sets with Simulated Annealing Design using Dimer Likelihood Estimation (SADDLE) . Nat Commun . 2022 ; 13 ( 1 ): 1881 . Epub 2022/04/13. doi: 10.1038/s41467-022-29500-4 . PubMed PMID: 35410464 ; PMCID: PMC9001684 this manuscript, N.G.X., M.X.W., and D.Y.Z. are the inventors, patent applicant is Rice University. This patent has been exclusively licensed to Nuprobe Global. N.G.X., M.X.W., and P.S. declare a competing interest in the form of consulting for Nuprobe USA. D.Y.Z. declares a competing interest in the form of consulting for and significant equity ownership in Nuprobe Global, Torus Biosystems, and Pana Bio. The remaining authors declare no competing interests. OpenUrl CrossRef PubMed 48. ↵ Halder I , Shriver M , Thomas M , Fernandez JR , Frudakis T . A panel of ancestry informative markers for estimating individual biogeographical ancestry and admixture from four continents: utility and applications . Human mutation . 2008 ; 29 ( 5 ): 648 – 58 . Epub 2008/02/21. doi: 10.1002/humu.20695 . PubMed PMID: 18286470 . OpenUrl CrossRef PubMed Web of Science 49. Yahya P , Sulong S , Harun A , Wangkumhang P , Wilantho A , Ngamphiw C , Tongsima S , Zilfalil BA . Ancestry-informative marker (AIM) SNP panel for the Malay population . International journal of legal medicine . 2020 ; 134 ( 1 ): 123 – 34 . Epub 2019/11/25. doi: 10.1007/s00414-019-02184-0 . PubMed PMID: 31760471 . OpenUrl CrossRef PubMed 50. ↵ Wilkinson S , Wiener P , Archibald AL , Law A , Schnabel RD , McKay SD , Taylor JF , Ogden R . Evaluation of approaches for identifying population informative markers from high density SNP chips . BMC genetics . 2011 ; 12 : 45 . Epub 2011/05/17. doi: 10.1186/1471-2156-12-45 . PubMed PMID: 21569514 ; PMCID: PMC3118130 . OpenUrl CrossRef PubMed 51. ↵ Barbosa FB , Cagnin NF , Simioni M , Farias AA , Torres FR , Molck MC , Araujo TK , Gil- Da-Silva-Lopes VL , Donadi EA , Simões AL . Ancestry Informative Marker Panel to Estimate Population Stratification Using Genome-wide Human Array . Annals of human genetics . 2017 ; 81 ( 6 ): 225 – 33 . Epub 2017/09/13. doi: 10.1111/ahg.12208 . PubMed PMID: 28895130 . OpenUrl CrossRef PubMed 52. ↵ Boecklen WJ , Howard DJ . GENETIC ANALYSIS OF HYBRID ZONES: NUMBERS OF MARKERS AND POWER OF RESOLUTION1997;78(8):2611-6 . doi: 10.1890/0012-9658(1997)078[2611:GAOHZN]2.0.CO;2 . OpenUrl CrossRef 53. ↵ Vähä JP , Primmer CR . Efficiency of model-based Bayesian methods for detecting hybrid individuals under different hybridization scenarios and with different numbers of loci . Molecular ecology . 2006 ; 15 ( 1 ): 63 – 72 . Epub 2005/12/22. doi: 10.1111/j.1365-294X.2005.02773.x . PubMed PMID: 16367830 . OpenUrl CrossRef PubMed Web of Science 54. ↵ Tricou T , Tannier E , de Vienne DM . Ghost Lineages Highly Influence the Interpretation of Introgression Tests . Systematic biology . 2022 ; 71 ( 5 ): 1147 – 58 . Epub 2022/02/17. doi: 10.1093/sysbio/syac011 . PubMed PMID: 35169846 ; PMCID: PMC9366450 . OpenUrl CrossRef PubMed 55. Tricou T , Tannier E , de Vienne DM . Ghost lineages can invalidate or even reverse findings regarding gene flow . PLoS Biol . 2022 ; 20 ( 9 ): e3001776 . Epub 2022/09/15. doi: 10.1371/journal.pbio.3001776 . PubMed PMID: 36103518 ; PMCID: PMC9473628 . OpenUrl CrossRef PubMed 56. ↵ Berger DJ , Léger E , Sankaranarayanan G , Sène M , Diouf ND , Rabone M , Emery A , Allan F , Cotton JA , Berriman M , Webster JP . Genomic evidence of contemporary hybridization between Schistosoma species . PLoS pathogens . 2022 ; 18 ( 8 ): e1010706 . Epub 2022/08/09. doi: 10.1371/journal.ppat.1010706 . PubMed PMID: 35939508 ; PMCID: PMC9387932 . OpenUrl CrossRef PubMed 57. ↵ Stewart CM , Gibson MJ , Parsa J-Y , Li JH. A comparison between low-cost library preparation kits for low coverage sequencing 2024:2024.01.30.578044. doi: 10.1101/2024.01.30.578044%JbioRxiv . OpenUrl CrossRef View the discussion thread. Back to top Previous Next Posted July 23, 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 Efficient amplicon panels for evaluating hybridization and genetic structure in the Schistosoma haematobium species group 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 Efficient amplicon panels for evaluating hybridization and genetic structure in the Schistosoma haematobium species group Roy N Platt II , Grace A Arya , Bonnie L Webster , Aidan M Emery , Timothy JC Anderson bioRxiv 2025.07.18.665602; doi: https://doi.org/10.1101/2025.07.18.665602 Share This Article: Copy Citation Tools Efficient amplicon panels for evaluating hybridization and genetic structure in the Schistosoma haematobium species group Roy N Platt II , Grace A Arya , Bonnie L Webster , Aidan M Emery , Timothy JC Anderson bioRxiv 2025.07.18.665602; doi: https://doi.org/10.1101/2025.07.18.665602 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 (7629) Biochemistry (17660) Bioengineering (13881) Bioinformatics (41911) Biophysics (21436) Cancer Biology (18578) Cell Biology (25482) Clinical Trials (138) Developmental Biology (13371) Ecology (19887) Epidemiology (2067) Evolutionary Biology (24302) Genetics (15599) Genomics (22482) Immunology (17728) Microbiology (40363) Molecular Biology (17163) Neuroscience (88536) Paleontology (666) Pathology (2830) Pharmacology and Toxicology (4821) Physiology (7637) Plant Biology (15129) Scientific Communication and Education (2045) Synthetic Biology (4290) Systems Biology (9817) Zoology (2269)