Study findings could lead to new clinical laboratory diagnostics that give pathologists a more detailed understanding about certain types of cancer
New studies proving artificial intelligence (AI) can be used effectively in clinical laboratory diagnostics and personalized healthcare continue to emerge. Scientists in the UK recently trained an AI model using machine learning and deep learning to enable earlier, more accurate detection of 13 different types of cancer.
DNA stores genetic information in sequences of four nucleotide bases: A (adenine), T (thymine), G (guanine) and C (cytosine). These bases can be modified through DNA methylation. There are millions of DNA methylation markers in every single cell, and they change in the early stages of cancer development.
One common characteristic of many cancers is an epigenetic phenomenon called aberrant DNA methylation. Modifications in DNA can influence gene expression and are observable in cancer cells. A methylation profile can differentiate tumor types and subtypes and changes in the process often come before malignancy appears. This renders methylation very useful in catching cancers while in the early stages.
However, deciphering slight changes in methylation patterns can be extremely difficult. According to the scientists, “identifying the specific DNA methylation signatures indicative of different cancer types is akin to searching for a needle in a haystack.”
Nevertheless, the researchers believe identifying these changes could become a useful biomarker for early detection of cancers, which is why they built their AI models.
“Computational methods such as this model, through better training on more varied data and rigorous testing in the clinic, will eventually provide AI models that can help doctors with early detection and screening of cancers,” said Shamith Samarajiwa, PhD (above), Senior Lecturer and Group Leader, Computational Biology and Genomic Data Science, Imperial College London, in a news release. “This will provide better patient outcomes.” With additional research, clinical laboratories and pathologists may soon have new cancer diagnostics based on these AI models. (Photo copyright: University of Cambridge.)
The researchers then used a combination of machine learning and deep learning techniques to train an AI algorithm to examine DNA methylation patterns of the collected data. The algorithm identified and differentiated specific cancer types, including breast, liver, lung and prostate, from non-cancerous tissue with a 98.2% accuracy rate. The team evaluated their AI model by comparing the results to independent research.
In their Biology Methods and Protocols paper, the authors noted that their model does require further training and testing and stressed that “the important aspect of this study was the use of an explainable and interpretable core AI model.” They also claim their model could help medical professionals understand “the underlying mechanisms that contribute to the development of cancer.”
Using AI to Lower Cancer Rates Worldwide
According to the Centers for Disease Control and Prevention (CDC), cancer ranks as the second leading cause of death in the United States with 608,371 deaths reported in 2022. The leading cause of death in the US is heart disease with 702,880 deaths reported in the same year.
Globally cancer diagnoses and death rates are even more alarming. World Health Organization (WHO) data shows an estimated 20 million new cancer cases worldwide in 2022, with 9.7 million persons perishing from various cancers that year.
The UK researchers are hopeful their new AI model will help lower those numbers. They state in their paper that “most cancers are treatable and curable if detected early enough.”
More research and studies are needed to confirm the results of this study, but it appears to be a very promising line of exploration and development of using AI to detect, identify, and diagnose cancer earlier. This type of probing could provide pathologists with improved tools for determining the presence of cancer and lead to better patient outcomes.
New technology could enable genetic scientists to identify antibiotic resistant genes and help physicians choose better treatments for genetic diseases
Genomic scientists at the Icahn School of Medicine at Mount Sinai Medical Center in New York City have developed what they call a “smart tweezer” that enables researchers to isolate a single bacterium from a patient’s microbiome in preparation for genetic sequencing. Though primarily intended for research purposes, the new technology could someday be used by clinical laboratories and microbiologists to help physicians diagnose chronic disease and choose appropriate genetic therapies.
The researchers designed their new technology—called mEnrich-seq—to improve the effectiveness of research into the complex communities of microorganisms that reside in the microbiomes within the human body. The discovery “ushers in a new era of precision in microbiome research,” according to a Mount Sinai Hospital press release.
“Imagine you’re a scientist who needs to study one particular type of bacteria in a complex environment. It’s like trying to find a needle in a large haystack,” said the study’s senior author Gang Fang, PhD (above), Professor of Genetics and Genomic Sciences at Icahn School of Medicine at Mount Sinai Medical Center, in a press release. “mEnrich-seq essentially gives researchers a ‘smart tweezer’ to pick up the needle they’re interested in,” he added. Might smart tweezers one day be used to help physicians and clinical laboratories diagnose and treat genetic diseases? (Photo copyright: Icahn School of Medicine.)
Addressing a Technology Gap in Genetic Research
Any imbalance or decrease in the variety of the body’s microorganisms can lead to an increased risk of illness and disease.
In researching the microbiome, many scientists “focus on studying specific types of bacteria within a sample, rather than looking at each type of bacteria present,” the press release states. The limitation of this method is that a specific bacterium is just one part of a complicated environment that includes other bacteria, viruses, fungi and host cells, each with their own unique DNA.
“mEnrich-seq effectively distinguishes bacteria of interest from the vast background by exploiting the ‘secret codes’ written on bacterial DNA that bacteria use naturally to differentiate among each other as part of their native immune systems,” the press release notes. “This new strategy addresses a critical technology gap, as previously researchers would need to isolate specific bacterial strains from a given sample using culture media that selectively grow the specific bacterium—a time-consuming process that works for some bacteria, but not others. mEnrich-seq, in contrast, can directly recover the genome(s) of bacteria of interest from the microbiome sample without culturing.”
Isolating Hard to Culture Bacteria
To conduct their study, the Icahn researchers used mEnrich-seq to analyze urine samples taken from three patients with urinary tract infections (UTIs) to reconstruct Escherichia coli (E. Coli) genomes. They discovered their “smart tweezer” covered more than 99.97% of the genomes across all samples. This facilitated a comprehensive examination of antibiotic-resistant genes in each genome. They found mEnrich-seq had better sensitivity than standard study methods of the urine microbiome.
They also used mEnrich-seq to selectively examine the genomes of Akkermansia muciniphila (A. muciniphila), a bacterium that colonizes the intestinal tract and has been shown to have benefits for obesity and Type 2 diabetes as well as a response to cancer immunotherapies.
“Akkermansia is very hard to culture,” Fang told GenomeWeb. “It would take weeks for you to culture it, and you need special equipment, special expertise. It’s very tedious.”
mEnrich-seq was able to quickly segregate it from more than 99.7% of A. muciniphila genomes in the samples.
Combatting Antibiotic Resistance Worldwide
According to the press release, mEnrich-seq could potentially be beneficial to future microbiome research due to:
Cost-Effectiveness: It offers a more economical approach to microbiome research, particularly beneficial in large-scale studies where resources may be limited.
Broad Applicability: The method can focus on a wide range of bacteria, making it a versatile tool for both research and clinical applications.
Medical Breakthroughs: By enabling more targeted research, mEnrich-seq could accelerate the development of new diagnostic tools and treatments.
“One of the most exciting aspects of mEnrich-seq is its potential to uncover previously missed details, like antibiotic resistance genes that traditional sequencing methods couldn’t detect due to a lack of sensitivity,” Fang said in the news release. “This could be a significant step forward in combating the global issue of antibiotic resistance.”
More research and clinical trials are needed before mEnrich-seq can be used in the medical field. The Icahn researchers plan to refine their novel genetic tool to improve its efficiency and broaden its range of applications. They also intend to collaborate with physicians and other healthcare professionals to validate how it could be used in clinical environments.
Should all this come to pass, hospital infection control teams, clinical laboratories, and microbiology labs would welcome a technology that would improve their ability to detect details—such as antibiotic resistant genes—that enable a faster and more accurate diagnosis of a patient’s infection. In turn, that could contribute to better patient outcomes.
Disruptive technology drops the cost of DNA methylation sequencing by 100-fold
As sequencing of individual human genomes becomes more affordable and useful, the next big hurdle in genetic science will be to map the human epigenome. While DNA provides the blueprint for building a human being, the epigenome determines the details of how that blueprint is expressed in an individual. Pathologists and clinical laboratory administrators will want to track efforts to map and understand the human epigenome.
The epigenome is a set of chemical modifications to the genome that are not encoded in the DNA but which modulate how and when genes are expressed. Methylation is only one marker in the complex epigenetic map, but it is an important one. Methylation suppresses gene activity, and is thought to be responsible for suppressing some genes that prevent cancer. Though researchers are a long way from using this knowledge to cure cancer or other diseases, faster, more affordable DNA methylation sequencing will help move that research forward.
