AI Model Uncovers Cancer Clues at Unprecedented Speed

by Shivam Kashyap


Glycans, complex arrangements of sugar molecules within our cells, are essential in identifying various forms of cancer within cells. Mass spectrometry can be used to measure these structures, but accurately determining the glycan structure from the fragmentation data requires careful human analysis. The process, which can take several hours to several days per sample, can only be carried out with a high level of certainty by a small group of experts worldwide, as it requires extensive investigative skills developed over many years.

Automating the Detective Work

The lengthy and complex process of glycan analysis presents a significant bottleneck in cancer detection, particularly when multiple samples need to be examined. Researchers at the University of Gothenburg have tackled this issue by developing an AI model, Candycrunch, which automates this detective work. Remarkably, Candycrunch can perform these analyses in just a few seconds per test. The findings were published in the journal Nature Methods.

Training and Accuracy

Candycrunch was trained on a vast database containing over 500,000 examples of various glycan fragmentations and their corresponding structures. This extensive training allows Candycrunch to accurately determine the sugar structure in a sample 90% of the time. “The training has enabled Candycrunch to calculate the exact sugar structure in a sample in 90 percent of cases,” explains Daniel Bojar, Associate Senior Lecturer in Bioinformatics at the University of Gothenburg.

Accelerating Biomarker Discovery

The AI model’s rapid and precise results mean it could soon match the accuracy levels of other biological sequence analyses, such as DNA, RNA, or proteins. Its efficiency and accuracy could significantly speed up the discovery of glycan-based biomarkers for both the diagnosis and prognosis of cancer. “We believe that glycan analysis will become a bigger part of biological and clinical research now that we have automated the biggest bottleneck,” says Bojar.

Enhanced Detection Capabilities

Candycrunch can detect structures that are often overlooked by human analysis due to their low concentrations, thus assisting researchers in identifying new glycan-based biomarkers. The ability to revolutionize cancer detection and biomarker discovery highlights the potential of Candycrunch, making glycan analyzes a more essential component of biological and clinical research.


Candycrunch represents a substantial advancement in the field of glycan analysis. By automating the previously complex and arduous task of interpreting mass spectrometry data, Candycrunch expedites the process of cancer detection and biomarker discovery. The potential to enhance diagnostic and prognostic capabilities in clinical settings and further our understanding of cancer is present due to the exceptional accuracy and ability to detect structures with minimal amounts. Candycrunch has the potential to improve the efficiency and visibility of glycan analyses as a tool in biological and clinical research. This has the capacity to revolutionize the detection and treatment of cancer.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

✓ Customized M.Tech Projects | ✓ Thesis Writing | ✓ Research Paper Writing | ✓ Plagiarism Checking | ✓ Assignment Preparation | ✓ Electronics Projects | ✓ Computer Science | ✓ AI ML | ✓ NLP Projects | ✓ Arduino Projects | ✓ Matlab Projects | ✓ Python Projects | ✓ Software Projects | ✓ Readymade M.Tech Projects | ✓ Java Projects | ✓ Manufacturing Projects M.Tech | ✓ Aerospace Projects | ✓ AI Gaming Projects | ✓ Antenna Projects | ✓ Mechatronics Projects | ✓ Drone Projects | ✓ Mtech IoT Projects | ✓ MTech Project Source Codes | ✓ Deep Learning Projects | ✓ Structural Engineering Projects | ✓ Cloud Computing Mtech Projects | ✓ Cryptography Projects | ✓ Cyber Security | ✓ Data Engineering | ✓ Data Science | ✓ Embedded Projects | ✓ AWS Projects | ✓ Biomedical Engineering Projects | ✓ Robotics Projects | ✓ Capstone Projects | ✓ Image Processing Projects | ✓ Power System Projects | ✓ Electric Vehicle Projects | ✓ Energy Projects Mtech | ✓ Simulation Projects | ✓ Thermal Engineering Projects

© 2024 All Rights Reserved Engineer’s Planet

Digital Media Partner #magdigit 

This website uses cookies to improve your experience. We'll assume you're ok with this, but you can opt-out if you wish. OK Read More

Privacy & Cookies Policy