Two studies show the accuracy of perception-based systems in detecting disease biomarkers without needing molecular recognition elements, such as antibodies
Researchers from multiple academic and research institutions have collaborated to develop a non-conventional machine learning-based technology for identifying and measuring biomarkers to detect ovarian cancer without the need for molecular identification elements, such as antibodies.
Traditional clinical laboratory methods for detecting biomarkers of specific diseases require a “molecular recognition molecule,” such as an antibody, to match with each disease’s biomarker. However, according to a Lehigh University news release, for ovarian cancer “there’s not a single biomarker—or analyte—that indicates the presence of cancer.
“When multiple analytes need to be measured in a given sample, which can increase the accuracy of a test, more antibodies are required, which increases the cost of the test and the turnaround time,” the news release noted.
Unveiled in two sequential studies, the new method for detecting ovarian cancer uses machine learning to examine spectral signatures of carbon nanotubes to detect and recognize the disease biomarkers in a very non-conventional fashion.
“Carbon nanotubes have interesting electronic properties,” said Daniel Heller, PhD (above), in the Lehigh University news release. “If you shoot light at them, they emit a different color of light, and that light’s color and intensity can change based on what’s sticking to the nanotube. We were able to harness the complexity of so many potential binding interactions by using a range of nanotubes with various wrappings. And that gave us a range of different sensors that could all detect slightly different things, and it turned out they responded differently to different proteins.” This method differs greatly from traditional clinical laboratory methods for identifying disease biomarkers. (Photo copyright: Memorial Sloan-Kettering Cancer Center.)
Perception-based Nanosensor Array for Detecting Disease
In the Science Advances paper, the researchers described their development of “a perception-based platform based on an optical nanosensor array that leverages machine learning algorithms to detect multiple protein biomarkers in biofluids.
“Perception-based machine learning (ML) platforms, modeled after the complex olfactory system, can isolate individual signals through an array of relatively nonspecific receptors. Each receptor captures certain features, and the overall ensemble response is analyzed by the neural network in our brain, resulting in perception,” the researchers wrote.
“This work demonstrates the potential of perception-based systems for the development of multiplexed sensors of disease biomarkers without the need for specific molecular recognition elements,” the researchers concluded.
In the Nature Biomedical Engineering paper, the researchers described a fined-tuned toolset that could accurately differentiate ovarian cancer biomarkers from biomarkers in individuals who are cancer-free.
“Here we show that a ‘disease fingerprint’—acquired via machine learning from the spectra of near-infrared fluorescence emissions of an array of carbon nanotubes functionalized with quantum defects—detects high-grade serous ovarian carcinoma in serum samples from symptomatic individuals with 87% sensitivity at 98% specificity (compared with 84% sensitivity at 98% specificity for the current best [clinical laboratory] screening test, which uses measurements of cancer antigen 125 and transvaginal ultrasonography,” the researchers wrote.
“We demonstrated that a perception-based nanosensor platform could detect ovarian cancer biomarkers using machine learning,” said Yoona Yang, PhD, a postdoctoral research associate in Lehigh’s Department of Chemical and Biomolecular Engineering and co-first author of the Science Advances article, in the news release.
How Perception-based Machine Learning Platforms Work
According to Yang, perception-based sensing functions like the human brain.
“The system consists of a sensing array that captures a certain feature of the analytes in a specific way, and then the ensemble response from the array is analyzed by the computational perceptive model. It can detect various analytes at once, which makes it much more efficient,” Yang said.
“SWCNTs have unique optical properties and sensitivity that make them valuable as sensor materials. SWCNTS emit near-infrared photoluminescence with distinct narrow emission bands that are exquisitely sensitive to the local environment,” the researchers wrote in Science Advances.
“Carbon nanotubes have interesting electronic properties,” said Daniel Heller, PhD, Head of the Cancer Nanotechnology Laboratory at Memorial Sloan Kettering Cancer Center and Associate Professor in the Department of Pharmacology at Weill Cornell Medicine of Cornell University, in the Lehigh University news release.
“If you shoot light at them, they emit a different color of light, and that light’s color and intensity can change based on what’s sticking to the nanotube. We were able to harness the complexity of so many potential binding interactions by using a range of nanotubes with various wrappings. And that gave us a range of different sensors that could all detect slightly different things, and it turned out they responded differently to different proteins,” he added.
The researchers put their technology to practical test in the second study. The wanted to learn if it could differentiate symptomatic patients with high-grade ovarian cancer from cancer-free individuals.
The research team used 269 serum samples. This time, nanotubes were bound with a specific molecule providing “an extra signal in terms of data and richer data from every nanotube-DNA combination,” said Anand Jagota PhD, Professor, Bioengineering and Chemical and Biomolecular Engineering, Lehigh University, in the news release.
This year, 19,880 women will be diagnosed with ovarian cancer and 12,810 will die from the disease, according to American Cancer Society data. While more research and clinical trials are needed, the above studies are compelling and suggest the possibility that one day clinical laboratories may detect ovarian cancer faster and more accurately than with current methods.
Use of such precision diagnostics offer ‘early detection, localization, and the opportunity to monitor response to therapy,’ say the MIT scientists
Oncologists and medical laboratory scientists know that most clinical laboratory tests currently used to diagnose cancer are either based on medical imaging technologies—such as CT scans and mammography—or on molecular diagnostics that detect cancer molecules in the body’s urine or blood.
Now, in a study being conducted at the Massachusetts Institute of Technology (MIT), researchers have developed diagnostic nanoparticles that can not only detect cancer cells in bodily fluids but also image the cancer’s location. This is the latest example of how scientists are combining technologies in new ways in their efforts to develop more sensitive diagnostic tests that clinical laboratories and other providers can use to detect cancer and other health conditions.
Precision diagnostics such as molecular, imaging, and analytics technologies are key tools in the pursuit of precision medicine.
“Therapeutic outcomes in oncology may be aided by precision diagnostics that offer early detection, localization, and the opportunity to monitor response to therapy,” the authors wrote, adding, “Through tailored target specificities, this modular platform has the capacity to be engineered as a pan-cancer test that may guide treatment decisions for numerous tumor type.”
Development of Multimodal Diagnostics
The MIT scientists are developing a “multimodal” diagnostic that uses molecular screening combined with imaging techniques to locate where a cancer began in the body and any metastases that are present.
“In principle, this diagnostic could be used to detect cancer anywhere in the body, including tumors that have metastasized from their original locations,” an MIT new release noted.
“This is a really broad sensor intended to respond to both primary tumors and their metastases,” said biological engineer Sangeeta Bhatia, MD, PhD (above), in the news release. Bhatia is the John and Dorothy Wilson Professor of Health Sciences and Technology and Electrical Engineering and Computer Science at MIT and senior author of the study.
“It can trigger a urinary signal and also allow us to visualize where the tumors are,” she added. Bhatia previously worked on the development of cancer diagnostics that can produce synthetic biomarkers which are detectable in urine samples.
“The vision is that you could use this in a screening paradigm—alone or in conjunction with other tests—and we could collectively reach patients that do not have access to costly screening infrastructure today,” said Sangeeta Bhatia, MD, PhD (above), in the MIT news release. “Every year you could get a urine test as part of a general check-up. You would do an imaging study only if the urine test turns positive to then find out where the signal is coming from. We have a lot more work to do on the science to get there, but that’s where we would like to go in the long run.” (Photo copyright: NBC News.)
Precision Diagnostic Assists Assessment of Response to Cancer Therapy
For their research, the scientists added a radioactive tracer known as copper-64 to the nanoparticles. This enabled the particles to be used for positron emission tomography (PET) imaging. The particles were coated with a peptide that induced them to accumulate at tumor sites and insert themselves into cell membranes, producing a strong imaging signal for tumor detection.
The researchers tested their diagnostic nanoparticles in mouse models of metastatic colon cancer where tumor cells had traversed to the liver or the lungs. After treating the cancer cells with a chemotherapy regimen, the team successfully used both urine and imaging to determine how the tumors were responding to the treatment.
Bhatia is hopeful that this type of diagnostic could be utilized in assessing how patients are responding to treatment therapies and the monitoring of tumor recurrence or metastasis, especially for colon cancer.
What is unique about the approach used by Bhatia’s team is that one application of the copper-64 tracer can be used in vivo, in combination with imaging technology. The other application of the copper-64 tracer is in vitro in a urine specimen that can be tested by clinical laboratories.
“Those patients could be monitored with the urinary version of the test every six months, for instance. If the urine test is positive, they could follow up with a radioactive version of the same agent for an imaging study that could indicate where the disease had spread,” Bhatia said in the news release. “We also believe the regulatory path may be accelerated with both modes of testing leveraging a single formulation.”
The graphic above, taken from the MIT news release, shows how “multimodal nanosensors (1) are engineered to target and respond to hallmarks in the tumor microenvironment. The nanosensors provide both a noninvasive urinary monitoring tool (2) and an on-demand medical imaging agent (3) to localize tumor metastasis and assess response to therapy,” the news release states. (Photo and caption copyright: Massachusetts Institute of Technology.)
Precision Medicine Cancer Screening Using Nano Technologies
Bhatia hopes that the nanoparticle technology may be used as a screening tool in the future to detect any type of cancer.
Her previous research with nanoparticle technology determined that a simple urine test could diagnose bacterial pneumonia and indicate if antibiotics could successfully treat that illness, the news release noted.
Nanoparticle-based technology might be adapted in the future to be part of a screening assay that determines if cancer cells are present in a patient. In such a scenario, clinical laboratories would be performing tests on urine samples while imaging techniques are simultaneously being used to diagnose and monitor cancers.
Surgical pathologists may also want to monitor the progress of this research, as it has the potential to be an effective tool for monitoring cancer patients following surgery, chemotherapy, or radiation therapy.
Goal is to shift glucose testing away from medical laboratories and make it easier for diabetics to do their own testing, while capturing glucose test results in patient records
Because of the tremendous volume of glucose tests performed daily throughout the world, many companies are developing non-invasive methods for glucose testing. Their goal is a patient-friendly technology that does not require a needle stick or venipuncture and may even eliminate the need to send specimens to a medical laboratory.
What is intriguing about these initiatives is that, in their final form, they may create a flow of useful diagnostic data reported to clinical laboratories in real time. This would create the opportunity for pathologists and lab scientists to consult with the patients’ physicians, while archiving this test result data in the laboratory information system (LIS).
These glucose monitoring methods would also ensure that a complete longitudinal record of patient tests results is available to all the physicians practicing in an accountable care organization (ACO), medical home, or hospital. (more…)
