Novel tool to predict patient survival rate of lung cancer patients

NUS-led study leverage Big Data to identify 29 unique biomarkers for a personalized predictive indicator.

Professor Lim Chwee Teck (right) and PhD student Ms Lim Su Bin (left) from the Department of Biomedical Engineering at National University of Singapore developed a personalised risk assessment tool based on 29 novel genes to predict survival rate and treatment outcomes of early-stage lung cancer patients.
Professor Lim Chwee Teck (right) and PhD student Ms Lim Su Bin (left) from the Department of Biomedical Engineering at National University of Singapore developed a personalised risk assessment tool based on 29 novel genes to predict survival rate and treatment outcomes of early-stage lung cancer patients.

Lung cancer is the leading cause of cancer death among both men and women, there is still a lack of definitive genetic “signature” to effectively predict how early-stage lung cancer patients would respond to adjuvant therapy like chemotherapy before patients begin treatment.

The conventional method for focusing on growth has been a “one size fits all” approach for patients. However, albeit two people may have a similar sort of malignancy, how the malady shows and advances are one of a kind to every person.

Now, NUS scientists have leveraged open source data to develop a personalized risk assessment tool that can potentially predict patient survival rate and treatment outcomes of early-stage lung cancer patients. The tool uses a novel panel of 29 unique extracellular matrix (ECM) genes which the researchers have identified based on their abnormal expression in lung cancers compared to healthy lung tissues.

ECM is the space that encompasses cells and gives auxiliary and biochemical help to encompassing cells. Late examinations have demonstrated the relationship between tissue firmness and the danger of malignancy, especially bosom disease. This is on account of a portion of the cells in the tumor produces stringy like collagen proteins that shape into a framework structure (ECM) for these disease cells to append to.

NUS Ph.D. candidate Ms. Lim Su Bin said, “In our research, we look at non-small cell lung cancer, which is the most common type of lung cancer. Our novel tool successfully identified early-stage patients who derived survival benefit from adjuvant chemotherapy. This is a very exciting development as we have taken a big step forward in enabling treatments to be customized for cancer patients to improve survival rates.”

“As we begin to know more about such tumor variability, or heterogeneity, the potential of personalized medicine is fast becoming a reality. The goal of precision medicine is to provide the right treatment to the right person at the right dose and at the right time. When precision medicine meets Big Data, its potential is even greater. With the increase of global joint efforts in sharing large-scale data, we were able to explore the genomic data across multiple cancer types through various databases.”

From their examination of the open databases, the group found a wide heterogeneity as far as ECM quality articulation inside beginning period lung disease patients. They were likewise ready to recognize 29 particular ECM segments that could conceivably fill in as biomarkers for the malady’s determination and forecast, thinking about their anomalous flow amid disease movement. The examination group at that point formed these biomarkers into a novel quality board for clinical application.

The quality board’s strong execution in anticipating survival results and chemotherapy achievement rate was approved in excess of 2,000 beginning period lung growth patients. The analysts likewise decided a typical cut-off score for quiet stratification.

Prof Lim said, “Our study demonstrates how we can harness and transform unprecedented amount of genomic data into a useful decision-making tool that can be implemented in routine clinical practice. We are excited about the potential of applying our novel bioinformatics approach into the emerging area of liquid biopsy, which serves as an alternative to invasive and painful tissue biopsy.”

The team is currently looking into the relevance of this 29-ECM gene panel biomarkers in predicting patient survival rate and treatment outcomes in 11 other cancer types. They are also developing an integrative platform using the principles of bioinformatics, microfluidics, and cancer genomics for actual testing of local patient’s samples, and to translate these scientific findings for true precision medicine in future.