The central challenge the team confronted is a notorious one in human genetics. PKD1 shares extensive stretches of near-identical sequence with six pseudogenes located elsewhere on chromosome 16, remnants of duplicated DNA that have lost their protein-coding function. Any sequencing approach that reads the genome indiscriminately risks aligning true PKD1 reads to the wrong location or, worse, mistaking pseudogene sequence for genuine gene sequence, producing false calls that could mislead clinical decisions. To sidestep this interference, the researchers employed long-range PCR, a technique that selectively amplifies the functional PKD1 gene in large fragments before sequencing, effectively isolating the target from its deceptive copies.

Oxford Nanopore Technology has attracted growing interest in clinical genomics because of its accessibility. A MinION device is roughly the size of a large USB stick, requires comparatively modest capital investment, and can be run in laboratories far from major sequencing centers. The trade-off has always been accuracy: nanopore reads carry higher error rates than the short-read Illumina platforms that dominate clinical laboratories, because each DNA strand threads through a protein pore and is read base by base as electrical current fluctuations. Raw errors, however, are largely random rather than systematic, which means that reading the same molecule many times and applying sophisticated computational correction can drive the consensus error rate down to levels suitable for variant calling. The catch is that this correction demands careful bioinformatic optimization, and until now no validated, end-to-end pipeline existed specifically for PKD1 on the nanopore platform.

The Chilean team built their solution as a nine-stage bioinformatic pipeline, with each stage dedicated to a distinct computational task in the journey from raw electrical signal to final variant call. The stages encompass the standard architecture of modern long-read analysis: quality assessment of the raw data, basecalling that converts current measurements into DNA sequence, demultiplexing to sort reads by sample, adapter trimming and filtering to remove artifacts, alignment of reads to the human reference genome, post-alignment processing, variant calling, and annotation that interprets each variant’s likely biological consequence. Crucially, rather than adopting tools by default, the authors performed a systematic, criteria-based selection at every stage, comparing candidate programs against explicit performance benchmarks to choose the configuration best suited to the error profile of nanopore data derived from long-range PCR amplicons.

This structured development approach is what distinguishes the work from ad hoc bioinformatics. Nanopore pipelines are notoriously sensitive to parameter choices: the settings that work for whole-genome sequencing of bacteria may fail badly when applied to a single amplified human gene, where coverage is deep, read lengths are constrained by the PCR fragment size, and homopolymer stretches, runs of identical bases that nanopore sequencers historically struggled to measure, can distort indel calls. By evaluating tools stage by stage against defined criteria, the team produced a reproducible framework whose behavior can be understood and audited, an essential property for any pipeline intended for clinical use. The pipeline was also designed with computational efficiency in mind, so that it can run on modest hardware rather than demanding a high-performance computing cluster, although the authors acknowledged the Patagn supercomputer team for supporting their development work.

Validation proceeded in two independent cohorts with distinct purposes. The first consisted of eight samples in which PKD1 variants had already been confirmed by Sanger sequencing, the decades-old method that reads DNA through chain-termination chemistry and remains the reference standard in many clinical laboratories. The optimized nanopore pipeline achieved complete concordance with Sanger across all eight samples, correctly recovering every previously known variant without introducing false positives. This head-to-head agreement is the critical benchmark for any platform aspiring to clinical deployment, because it demonstrates that the computational corrections have neutralized the platform’s raw error rate to the point where the two technologies deliver identical answers on real patient material.

The second cohort provided the true test of diagnostic utility: 26 ADPKD patients who had never received a molecular diagnosis. When the pipeline was applied to their sequenced samples, it identified pathogenic or likely pathogenic PKD1 variants in 69 percent of cases, a detection rate consistent with the known genetics of ADPKD, in which PKD1 accounts for the large majority of cases with an identifiable cause and roughly a tenth of patients carry variants in PKD2 or other genes instead. Among the prioritized findings were six variants never before reported, expanding the catalog of known disease-causing mutations in the gene. To confirm these new calls, the researchers sent 18 prioritized variants for independent Sanger verification, and 17 were confirmed, a validation rate that underscores both the sensitivity of the pipeline and the value of orthogonal confirmation for novel discoveries.

The implications reach well beyond a single gene. ADPKD is one of the most common inherited kidney diseases worldwide, and targeted therapies now exist that can slow disease progression, making early molecular diagnosis clinically meaningful rather than merely informative. Yet in many countries, including Chile where this study was conducted, patients may wait years for genetic testing or never receive it, because sending samples to commercial laboratories abroad is costly and short-read sequencing of PKD1 requires careful strategies to handle the pseudogene problem. A pipeline that runs on a benchtop nanopore device, uses long-range PCR to guarantee specificity, and delivers Sanger-concordant results changes the calculus for public health systems, allowing regional hospitals and university laboratories to perform the analysis in-house at low infrastructure cost.

The work also offers a template for tackling other clinically important genes haunted by pseudogenes or other architectural complexities. Many disease genes share this burden, and the authors argue that their structured, criteria-based development approach, demonstrated diagnostic performance, and computational optimization make the framework applicable to genomic research and clinical settings requiring high-sensitivity analysis of large, complex genes. Because the pipeline is described as reproducible and its development logic is documented stage by stage, other groups can adapt it rather than rebuilding the analysis from scratch, accelerating the spread of long-read diagnostics into low-resource environments.

The study, conducted under ethical approval from the Research Ethics Committee of the Health Service of Valdivia and with informed consent from all participants recruited across Chilean health centers, was supported by Chile’s National Agency for Research and Development through FONDECYT Regular projects and by Innovation Fund for Competitiveness grants from the Regional Government of Los Ros. The authors credit collaboration among the Nephrology Laboratory of Universidad Austral de Chile, the Valdivia Base Hospital, the Centro de Investigacin Clnica Avanzada, and nephrologists across the country who connected patients with the research. As nanopore sequencing matures from a promising technology into a validated clinical tool, this pipeline stands as evidence that careful bioinformatics, not expensive hardware, can be the decisive factor in bringing precision diagnosis to patients who have historically been left waiting.

Subject of Research: Development and clinical validation of an Oxford Nanopore bioinformatic pipeline for detecting PKD1 variants in autosomal dominant polycystic kidney disease

Article Title: An optimized nanopore-based bioinformatic pipeline for PKD1 variant detection: development and validation with clinical samples

Article References: Millar, D., Gajardo, M., Poblete, B., Ubilla, R., Izquierdo, M., Medina, A., Lehmann, P., Flores, C., Krall, P., & Maturana, J. (2026). An optimized nanopore-based bioinformatic pipeline for PKD1 variant detection: development and validation with clinical samples. BMC Bioinformatics. https://doi.org/10.1186/s12859-026-06644-4

Image Credits: AI Generated

DOI: 10.1186/s12859-026-06644-4

Keywords: Oxford Nanopore Technology, PKD1, ADPKD, long-read sequencing, bioinformatic pipeline, variant detection, pseudogene, long-range PCR, Sanger sequencing, polycystic kidney disease, low-resource sequencing, clinical genomics

Nanopore sequencing has transformed genomics by allowing DNA and RNA molecules to be read in their entirety, producing long reads that span entire transcripts and reveal complex splicing patterns that short-read technologies often miss. Oxford Nanopore platforms thread individual molecules through protein nanopores and infer their sequence from disruptions in an electrical current. This approach delivers reads that can stretch tens of thousands of bases, capturing full-length transcript isoforms and preserving modifications that are lost when RNA is fragmented and amplified. Yet the technology has long been hampered by a higher raw error rate compared with Illumina short-read sequencing, and this limitation has been particularly consequential for SNP calling, where a single misread base can be mistaken for a genuine variant.

Conventional approaches to correcting these errors typically rely on consensus building, aligning many reads to a reference genome and counting the frequency of each base at every position. Such methods work reasonably well for DNA sequencing at high coverage, but transcriptome data presents unique complications. Expression levels vary enormously across genes, meaning some transcripts are covered by thousands of reads while others yield only a handful. Low-coverage transcripts offer too few observations for statistical consensus methods to separate signal from noise, and highly expressed genes can harbor natural RNA editing events that complicate variant interpretation further. The result has been a landscape in which SNP detection from nanopore transcriptome data has demanded heavy computational filtering and often produced inconsistent results across tools and datasets.

NanoTS takes a fundamentally different approach by framing SNP calling as a pattern recognition problem that deep learning is exceptionally well suited to solve. Rather than relying solely on base-level alignments, the tool learns from the rich features embedded in nanopore signal data, the raw electrical current measurements that underlie every base call. Neural networks can detect subtle signatures that distinguish systematic sequencing errors, which tend to follow repeatable patterns tied to sequence context and pore dynamics, from genuine genetic variation, which manifests consistently across independent molecules. This capacity to model complex, high-dimensional relationships in the data allows NanoTS to make confident genotype calls even in regions where traditional statistical methods falter.

The implications of accurate SNP calling from direct RNA sequencing extend across a wide range of biological and biomedical applications. Variant detection at the transcript level reveals which alleles are actively expressed, a dimension invisible to DNA-based genotyping. Allele-specific expression, in which one copy of a gene is transcribed more abundantly than the other, plays a critical role in imprinted genes, autoimmune disease, cancer biology and X-chromosome inactivation. Researchers studying these phenomena have historically needed to combine DNA genotyping with RNA expression analysis from separate experiments, introducing uncertainty about whether observed expression patterns truly reflect the same cells and conditions. A tool that can call genotypes directly from transcriptome data collapses these two measurements into a single, internally consistent dataset.

The deep learning architecture at the heart of NanoTS represents part of a broader movement in genomics toward learned models that outperform hand-crafted algorithms. Basecalling, the process of converting raw nanopore current signals into nucleotide sequences, was revolutionized years ago by neural networks that replaced earlier hidden Markov model approaches, dramatically improving read accuracy. Variant calling is now following a similar trajectory. DeepVariant, developed by Google, demonstrated that convolutional neural networks could outperform classical statistical variant callers on Illumina data by treating genomic alignment piles as images. NanoTS extends this paradigm to the specific and demanding context of long-read transcriptome sequencing, where error profiles, coverage distributions and biological variation patterns differ substantially from genomic DNA sequencing.

Training such a model requires data of exceptional quality, since the network must learn to associate signal and alignment patterns with known ground-truth genotypes. The developers of NanoTS tackled this challenge by curating training examples in which true variants could be established with high confidence, allowing the network to internalize the distinctions between authentic polymorphism and sequencing artifact. Once trained, the model generalizes across genes, transcripts and coverage regimes, producing variant calls that remain reliable even for transcripts sequenced at low depth, a scenario that has historically been the Achilles heel of long-read transcriptome analysis.

The clinical dimension of this work is particularly compelling. Personalized medicine increasingly depends on knowing both which variants a patient carries and how those variants are expressed in relevant tissues. RNA sequencing of patient samples, whether from tumor biopsies or blood cells, is already routine in many clinical and research settings. If those same RNA reads can yield accurate genotype information without a parallel DNA sequencing run, the cost and complexity of comprehensive molecular profiling drops considerably. Cancer genomics stands to benefit substantially, as tumor transcripts carry both expressed mutations and the allele-specific expression patterns that reveal loss of heterozygosity and other genome alterations relevant to treatment decisions.

Beyond clinical applications, NanoTS opens doors for basic research into population genetics and evolutionary biology at the transcript level. Understanding how genetic variation shapes transcript diversity across individuals and species requires tools that can reliably measure both. Long-read transcriptome sequencing captures the full complexity of isoform expression, and with accurate SNP calling layered on top, researchers can begin to map how specific variants influence splicing, expression levels and transcript structure in ways that short-read studies have only approximated. The combination of full-length isoform resolution and direct genotype calling provides a uniquely integrated view of the relationship between genome and transcriptome.

The publication of NanoTS in Nature Methods underscores the growing recognition that computational innovation is as essential to unlocking the potential of new sequencing technologies as the hardware itself. As nanopore sequencing continues its rapid improvements in accuracy and throughput, tools like NanoTS ensure that the analytical pipeline keeps pace, converting noisy raw signals into biologically meaningful and clinically actionable insights. For laboratories worldwide working with direct RNA sequencing, the arrival of a robust deep learning solution for SNP calling marks a significant step toward making long-read transcriptomics a complete, standalone platform for both discovery and diagnosis.

Subject of Research: A deep learning tool for accurate SNP calling and genotype detection in nanopore long-read transcriptome sequencing data.

Article Title: NanoTS: a deep learning tool for accurate SNP calling in nanopore long-read transcriptome data

Article References: NanoTS: a deep learning tool for accurate SNP calling in nanopore long-read transcriptome data. (n.d.). https://doi.org/10.1038/s41592-026-03225-4

Image Credits: AI Generated

DOI: 10.1038/s41592-026-03225-4

Keywords: NanoTS, deep learning, SNP calling, nanopore sequencing, long-read transcriptomics, genotyping, direct RNA sequencing, variant detection, neural networks, Nature Methods, allele-specific expression, computational genomics