[ad_1]
Researchers at City of Hope and the Translational Genomics Research Institute (TGen) have developed and tested a machine learning approach that they suggest could one day enable earlier detection of cancer in patients’ blood, using only small blood extractions. The technology is based on an algorithm called Alu Profile Learning Using Sequencing (A-PLUS), which the team developed, validated and tested in four patient cohorts, covering thousands of patient samples with breast, colon and rectum, esophagus, lung . , liver, pancreas, ovarian or stomach cancers.
A-PLUS distinguishes individuals with cancer from those without cancer based on the representation of Alu elements in their plasma cell-free DNA. Results from the recently reported study found that the A-PLUS tool identified half of the cancers among the 11 tumor types studied. The test was also very accurate, with a false positive occurring in only one in 100. Importantly, most of the cancer samples tested came from people with early-stage disease, who had few or no metastatic lesions at the time of the test. diagnosis.
“A large body of evidence shows that cancer detected at later stages kills people,” said Cristian Tomasetti, PhD, director of City of Hope’s Center for Cancer Prevention and Early Detection and corresponding author of the researchers’ study in Scientific translational medicine. “This new technology brings us closer to a world where people will receive a blood test annually to detect cancer earlier, when it is most treatable and possibly curable.” The researchers’ article is titled “Machine learning to detect cancer SINE.” In their report, they concluded: “Therefore, evaluation of Alu elements may have the potential to improve the performance of several methods designed for earlier detection of cancer.”
Tomasetti explained that 99% of people diagnosed with stage 1 breast cancer will be alive five years later; However, if it is in stage 4, when the disease has spread to other organs, the five-year survival drops to 31%.
Alu elements are short interspersed nuclear elements (SINE) of ~300 base pairs, with more than a million copies distributed throughout the human genome, the authors explained. While these elements are the subject of ongoing research, some have already been shown to be involved in the regulation of tissue-specific genes. “In cancer cells, they participate in structural changes, probably through homologous recombination given their wide distribution throughout the genome and very similar sequences… there is much precedent that Alu sequence elements are especially prone to epigenetic changes in several cancers,” the scientists wrote.
Instead of analyzing specific DNA mutations by looking for one misordered letter among billions of letters, the researchers devised a new approach to detect the difference in fragmentation patterns in repetitive regions of cancer and normal cell-free DNA (cfDNA). This fragmentomic approach requires about eight times less blood than required by whole genome sequencing, Tomasetti said.
When a cell dies, it breaks down and some of the cell’s DNA material leaks into the bloodstream. Signs of cancer can be found in this cfDNA. Normal cell cfDNA breaks down into a typical size, but cancer cfDNA fragments break down into altered spots. It is assumed that this alteration is more present in repetitive regions of the genome. “Alu elements also reflect the altered fragmentation patterns found in free DNA from cancer patients,” the scientists continued. They hypothesized that the representation of specific Alu elements might be different in cell-free DNA (cfDNA) from plasma of cancer patients than in cfDNA from normal controls.
Because there are so many Alu elements in the genome, testing this hypothesis required the development of machine learning tools, and the team developed A-PLUS to distinguish individuals with cancer from those without cancer based on the representation of Alu elements in the genome. your free DNA. .
The machine learning platform was trained and validated on four different patient cohorts, with a total of 7,615 samples from 5,178 people, including 2,073 with solid cancers and the rest without cancer. “Samples from cancer patients and controls were prespecified into four cohorts used for model training, analyte integration, and threshold determination, validation, and reproducibility,” the team explained.
Their results showed that in the validation cohort, A-PLUS alone provided a sensitivity of 40.5% across 11 different cancer types, with a specificity of 98.5%. The combination of A-PLUS with aneuploidy and eight common protein biomarkers detected 51% of cancers with a specificity of 98.9%.
The team said the power of A-PLUS could be attributed to a single feature: “…the global reduction of AluS subfamily elements in the circulating DNA of solid cancer patients.” They further commented: “…our study shows that the representations of Alu elements, in general, and AluS subfamily elements, in particular, are altered in the free DNA of patients with many different types of cancer… The Future investigation of the mechanisms underlying their altered representation will be facilitated by their abundance in the genome and their similar sequences and structures.”
“Our technique is more practical for clinical applications as it requires smaller amounts of genomic material from a blood sample,” said co-first author Kamel Lahouel, PhD, assistant professor in TGen’s Division of Integrated Cancer Genomics. “Continued success in this area and clinical validation opens the door to the introduction of routine testing to detect cancer in its early stages.”
Tomasetti is set to open a clinical trial in summer 2024 to compare this fragmentomic blood testing approach to standard care in adults ages 65 to 75. The prospective trial will determine the effectiveness of the biomarker panel in detecting an earlier stage of cancer when it is more treatable.