Abstract
The detection of disease biomarkers faces numerous challenges, primarily due to the low concentration of biomarkers in the body, the complexity of samples, and the insufficient sensitivity and specificity of detection technologies.[1] Traditional detection methods in clinical settings, such as Enzyme-Linked Immunosorbent Assay (ELISA), Radioimmunoassay (RIA), and mass spectrometry, although widely used, typically suffer from slow detection speeds, high costs, and the requirement for large sample volumes. Additionally, these methods often lack the sensitivity needed to detect low-concentration biomarkers, which can lead to false-negative results and further impact the accuracy and timeliness of diagnosis.
To address these challenges, our team has proposed an innovative strategy that leverages artificial intelligence (AI) to establish connections between proteins and diseases. Our primary objective is to develop a model capable of assessing the correlation between proteins and diseases. By utilizing AI technology, we aim to rapidly identify potential biomarkers that are highly relevant to specific diseases. Subsequently, we plan to adopt electrochemical detection technology, which offers high sensitivity and specificity, allowing for the detection of low-concentration biomarkers in samples within a short timeframe.[2] Through this approach, we hope to overcome the current bottlenecks in detection technologies, providing a more efficient and cost-effective pathway for the early diagnosis and timely treatment of diseases. This not only helps to shorten diagnostic times but also improves diagnostic accuracy and patient treatment outcomes.
Finally, we listed the top ten highly relevant diseases and removed those with unclear definitions, leaving Hepatitis C, liver cirrhosis, and leukemia. However, since Hepatitis C and liver cirrhosis currently have a diagnostic accuracy of up to 90% through imaging examinations.[3] Also, the main method for detecting leukemia is peripheral blood smears, which cannot be used for differential diagnosis with other diseases, a bone marrow biopsy is required.[4] Based on the above reasons, we chose leukemia as the target disease for rapid detection, using this target to prove the feasibility of our concept. In the future, we plan to extend this process to the screening and detection of biomarkers for other diseases, thereby achieving widespread early diagnosis and monitoring of diseases. This innovative approach not only effectively addresses current challenges in disease detection but also provides strong support for the future development of precision medicine.
Introduction to Leukemia
Leukemia, commonly known as blood cancer, is a malignant disease caused by genetic mutations during the growth and replication of hematopoietic cells in the bone marrow, leading to abnormal proliferation that affects the bone marrow's ability to produce blood.[5] In patients with leukemia, an excessive number of white blood cells are produced, but these white blood cells are unable to function properly, thereby weakening the immune system.
Leukemia can be classified as either acute or chronic. In acute leukemia, the abnormal blood cells (blasts) are highly immature and cannot function normally. The number of blasts increases rapidly, leading to a rapid deterioration of the condition.[6] In chronic leukemia, some blasts are present, but these cells are usually more mature and can perform some of their normal functions. The number of blasts in chronic leukemia increases more slowly, resulting in a slower progression of the disease. Additionally, in chronic myeloid leukemia (CML), although early symptoms are not very noticeable, if not treated aggressively, it will eventually transform into acute leukemia, with a very poor prognosis.[5]
Our Project
Our primary focus is on detecting Acute Myeloid Leukemia (AML), a disease that occurs in both adults and children and is the most common type of leukemia. AML has a high recurrence rate when treated with chemotherapy, with a cure rate of only 20% to 30%.[8] We aim to use our model and electrochemical detection technology to identify potential biomarkers for AML and enable rapid detection. This approach could significantly improve the early detection rate of this deadly disease, thereby increasing the chances of successful treatment.
Based on the results from our model, we selected CD97 as the target biomarker for detection. Next, we will predict sequences that can bind to CD97 and attach these sequences to the Lpp-OmpA protein. These will then be inserted into Escherichia coli (E. coli) so that these sequences can be expressed on the outer membrane of the E. coli cells.[9] Subsequently, we will place the E. coli on a chip and introduce samples. By measuring the electrochemical signals, we can determine the expression levels or activity of the protein.
Future Outlook
In the future, we plan to continue expanding our database and collaborate with doctors or clinical data generation companies to validate proteins that are highly correlated with diseases. This will enhance the accuracy of biomarker and disease detection. Ultimately, our goal is to develop a platform capable of simultaneously detecting multiple diseases.
Reference
- New Powers Co., Ltd. (n.d.). Evolution and challenges—LC/MS new trend report.
- State Intellectual Property Office (SIPO). (2017). State Intellectual Property Office homepage.
- Chi Mei Medical Center. (n.d.). Chi Mei Medical Center photo album.
- Veterans General Hospital Taichung. (n.d.). Hematology and oncology department residency handbook.
- Tri-Service General Hospital. (n.d.). Tri-Service General Hospital homepage.
- Canceraway Foundation. (n.d.). Canceraway Foundation homepage.
- National Cancer Institute. (n.d.). Cancer stat facts: Leukemia. SEER.
- Bowtie Insurance. (n.d.). Leukemia—A closer look at blood cancer.
- Yuan, S. F., Chen, T. J., Zhao, J., & Xu, S. X. (2021). Efficient metabolic engineering of Escherichia coli for high-level production of 5-aminovalerate from glucose. Microbial Cell Factories, 20(1), 1-13.