The landscape of cancer research is undergoing a profound transformation as genomic sequencing moves from the realm of abstract discovery into the heart of clinical practice. Central to this evolution is the emergence of long-read sequencing technologies, which allow scientists to analyze extensive, continuous stretches of DNA. Unlike traditional methods that fragment DNA into tiny pieces, long-read sequencing provides a more holistic view of the genetic architecture. However, the sheer complexity of cancer genomes—often characterized by chaotic rearrangements and massive mutations—has historically outpaced the tools available to interpret them.
In a significant step toward overcoming these technical hurdles, a multi-institutional team of researchers has unveiled SAVANA, a sophisticated machine learning algorithm designed specifically to navigate the intricacies of cancer genomics. Recently described in the journal Nature Methods, SAVANA promises to refine the way clinicians and researchers detect structural variations, potentially leading to more accurate diagnoses and highly personalized treatment strategies for patients worldwide.
The Challenge of Complex Cancer Genomes
For years, the gold standard in genomics has been short-read sequencing, which is highly accurate for identifying small, single-letter changes in the genetic code. However, cancer is rarely a disease of small changes alone. It often involves large-scale structural variants (SVs)—massive deletions, insertions, duplications, and rearrangements where entire sections of chromosomes are moved or flipped. Short-read technologies struggle to map these large events because the "puzzle pieces" they produce are too small to provide context for where a large-scale rearrangement begins or ends.
Long-read sequencing was developed to solve this problem by providing much larger "puzzle pieces." Yet, even this technology has faced obstacles. The structural complexity of a tumor—which may contain a mixture of healthy cells and various sub-populations of cancerous cells—creates a "noisy" data environment. Existing analysis tools, many of which were designed for healthy genomes or general research purposes, frequently fail to distinguish between true biological mutations and sequencing artifacts. These false-positive results are more than just a technical nuisance; they can lead to unreliable interpretations of how a tumor evolves and how it might respond to specific therapies, ultimately compromising patient care.
To address this, researchers from EMBL’s European Bioinformatics Institute (EMBL-EBI) and the R&D laboratory of Genomics England collaborated with clinical experts from University College London (UCL), the Royal National Orthopaedic Hospital (RNOH), Instituto de Medicina Molecular João Lobo Antunes, and Boston Children’s Hospital. Together, they sought to create a tool that was not just powerful, but specifically "tuned" to the chaotic environment of a cancer cell.
The researchers often use a simple analogy to describe the necessity of this new tool: while it is technically possible to eat soup with a fork, the process is inefficient and the results are unsatisfying. Traditional tools were the "forks" of the genomic world—functional in some contexts but ill-suited for the liquid complexity of cancer data. SAVANA represents the "spoon," a tool tailored specifically for the task at hand, designed to deliver reliable results with efficiency and precision.
A Machine Learning Approach to Genomic Clarity
SAVANA operates by utilizing machine learning to identify structural variants and copy number aberrations—changes in the number of copies of a gene—within cancer genomes. By training the algorithm directly on long-read sequencing data derived from actual human cancer samples, the team ensured that the software could recognize the specific "signatures" of malignant genetic decay.
"Because other analysis tools are not developed to account for the particularities of cancer genomics data, they often pick up false positives that could lead to incorrect clinical and biological interpretations," explained Isidro Cortes-Ciriano, Group Leader at EMBL-EBI. "SAVANA changes this. By training the algorithm directly on long-read sequencing data from cancer samples, we created a new method that can tell the difference between true cancer-related genomic alterations and sequencing artefacts."
This ability to filter out the noise allows researchers to elucidate the mutational processes underlying cancer with an unprecedented level of resolution. The algorithm was rigorously developed and tested across 99 human tumor samples, ensuring its robustness across different types of malignancies and varying levels of genetic complexity.
Optimised for Clinical Use
While many algorithms remain confined to research laboratories, the developers of SAVANA were adamant that the tool be practical for the fast-paced environment of a hospital. Clinical diagnostics require tools that are not only accurate but also rapid and robust enough to handle the variability of real-world patient samples.
Hillary Elrick, a former Predoctoral Fellow at EMBL-EBI and currently a Postdoctoral Fellow at the Francis Crick Institute, emphasized this focus during the development phase. "When we developed SAVANA, our focus was clear: create a tool sophisticated enough to characterise complex cancer genomes but practical enough for clinical use," she said.
The practical utility of SAVANA lies in its comprehensive output. It does more than just identify mutations; it provides a detailed profile of the tumor’s biology. Carolin Sauer, a Postdoctoral Fellow at EMBL-EBI, noted that the algorithm can accurately distinguish somatic structural variants, copy number aberrations, tumor purity, and ploidy. Purity refers to the proportion of cancer cells versus healthy cells in a sample, while ploidy refers to the number of sets of chromosomes in a cell—both of which are critical factors in determining the aggressiveness of a tumor and the most effective course of treatment.
The real-world efficacy of the algorithm was recently demonstrated in a study of osteosarcoma, a rare and particularly aggressive form of bone cancer that predominantly affects children and young adults. Because osteosarcoma genomes are notoriously rearranged and complex, they served as the ultimate testing ground for SAVANA. The algorithm helped researchers uncover previously unknown genomic rearrangements, providing novel insights into how this specific cancer evolves and progresses.
Furthermore, the team conducted a head-to-head comparison between SAVANA’s long-read analysis and the current clinical standard: Illumina short-read sequencing. The results were highly consistent across both technologies. Crucially, while SAVANA matched the performance of current standards, it also revealed additional cancer-relevant alterations that the standard pipelines had missed, proving its potential to add significant value to clinical reporting.
"The capability to accurately detect structural variants is transformative for clinical diagnostics," said Adrienne Flanagan, Professor at UCL and Consultant Histopathologist at RNOH. "SAVANA could help us confidently identify genomic alterations relevant for diagnosis and prognosis. Ultimately, this means we would be better placed to deliver personalised treatments for cancer patients."
UK Investment in Clinical Genomics
The development of SAVANA comes at a pivotal moment for the United Kingdom’s healthcare infrastructure. The UK is currently making substantial investments in genomic sequencing through the NHS Genomic Medicine Service. This initiative is a global pioneer, being the first of its kind to offer whole-genome sequencing as a routine part of patient care. By embedding these advanced technologies into the everyday workflow of the National Health Service, the UK aims to drastically improve diagnostic accuracy and provide a foundation for personalized medicine.
However, the success of this massive investment hinges on the ability to interpret the data. Without specialized analytical tools like SAVANA, the vast amounts of data generated by the NHS could become a bottleneck rather than a breakthrough. Genomics England has been exploring SAVANA’s integration as part of its broader mission to evaluate the clinical potential of long-read sequencing to support earlier and faster cancer diagnoses.
Greg Elgar, Director of Sequencing R&D at Genomics England, highlighted the importance of reliability in this transition. "Using SAVANA will ensure clinicians receive accurate and reliable genomic data, enabling them to confidently integrate advanced genomic sequencing methods such as long-read sequencing into routine patient care," he stated.
Expanding the Reach of Genomic Research
The impact of SAVANA is already extending into specialized nationwide and international initiatives. It is being deployed as a core component of the UK Stratified Medicine Paediatrics project. Co-led by Cortes-Ciriano and funded by Cancer Research UK and Children With Cancer UK, this project aims to develop more effective and less toxic treatments for childhood cancers. By using SAVANA to better understand tumor biology and monitor disease recurrence in children, researchers hope to move away from "one-size-fits-all" chemotherapy and toward targeted interventions.
Beyond the UK, SAVANA is playing a role in addressing global health inequities through the Societal, Ancestry, Molecular and Biological Analyses of Inequalities (SAMBAI) project. This Cancer Grand Challenges initiative is focused on understanding and addressing cancer disparities in populations of recent African heritage. By providing a more accurate tool for genomic analysis, SAVANA helps ensure that the benefits of the genomic revolution are accessible to diverse populations, regardless of their ancestral background.
As long-read sequencing continues to move toward the center of oncology, tools like SAVANA represent the vital link between raw biological data and actionable medical insights. By providing a clearer, more accurate map of the cancer genome, this new algorithm is helping to pave the way for a future where every patient’s treatment is as unique as their own genetic code.
