Singapore researchers reveal a common deficiency in genetic prediction methods

August 28, 2019

A study conducted by researchers from the Cancer Science Institute of Singapore (CSI Singapore) at the National University of Singapore and the School of Biological Sciences at Nanyang Technological University, Singapore (NTU Singapore) revealed a common deficiency in existing artificial intelligence methods used to predict enhancer-promoter interactions, that may result in inflated performance measurements. The findings, published in scientific journal Nature Genetics in July 2019, provides an enhanced road map for the understanding of gene regulation.

An enhancer is a short sequence of DNA that works to speed up genetic transcription while a promoter is a piece of DNA which acts to initiate gene transcription. Understanding the interactions between an enhancer and a promoter is critical for gene regulation studies as there is great scientific interest in whether interactions may be dysfunctional in cancer cells, and present an opportunity for clinical intervention. In order to study enhancer-promoter interactions on a large scale and in a cost-effective manner, artificial intelligence methods for predicting such interactions are vital to facilitate researchers in their studies and enable them to extend the availability of such data to new cell types.

In the study conducted by Dr Cao Fan, a research fellow at CSI Singapore, and Dr Melissa J. Fullwood, Principal Investigator at CSI Singapore and a Nanyang Assistant Professor at NTU Singapore, the research team attempted to develop an enhancer-promoter interaction prediction method using existing datasets from TargetFinder, an advanced machine learning method that predicts enhancer-promoter interactions based on transcription factor and histone modification profiles in the window regions between enhancers and promoters. During then, the team observed that enhancer-promoter interactions were predicted at random DNA sequence features in the window regions, indicating high performance.

However, upon careful examination of the TargetFinder datasets, the team realised the reported high performances could be attributed to the high overlap between window regions of positive samples in the datasets, affecting the predicted performance. To mitigate the issue of overlapping samples, the team then evaluated enhancer-promoter interaction methods using a chromosome-split strategy. TargetFinder achieved significantly lower performance with the chromosome-split strategy, which proved that the performance measurements were indeed inflated in the earlier prediction.

The team also examined another method, JEME, a supervised machine learning method that makes use of datasets with significant differences in distance distributions between positive and negative samples to predict enhancer-promoter interactions. Their investigation revealed that JEME too, results in inflated performance measurements due to erroneous use of input data.

"Our study highlights the need for careful experimental design when applying machine learning to genomic research. It is key to properly evaluate an enhancer-promoter interaction method, and take into account the possibility of generating highly inflated performance measurement." said Dr Cao.

"Accurate enhancer-promoter interactions prediction is essential in gene regulation studies in order to facilitate our ability to understand if there are any differences between cancer samples, such as different clinical subtypes of cancers, in order to better develop biomarkers and therapies for cancer in the future," said Dr Fullwood.

Moving forward, the research team will be working on a new accurate machine learning approach for the prediction of enhancer-promoter interactions, and applying the method to the analysis of cancer cohorts in order to understand alterations in enhancer-promoter interactions in cancer.
-end-


National University of Singapore

Related Cancer Articles from Brightsurf:

New blood cancer treatment works by selectively interfering with cancer cell signalling
University of Alberta scientists have identified the mechanism of action behind a new type of precision cancer drug for blood cancers that is set for human trials, according to research published in Nature Communications.

UCI researchers uncover cancer cell vulnerabilities; may lead to better cancer therapies
A new University of California, Irvine-led study reveals a protein responsible for genetic changes resulting in a variety of cancers, may also be the key to more effective, targeted cancer therapy.

Breast cancer treatment costs highest among young women with metastic cancer
In a fight for their lives, young women, age 18-44, spend double the amount of older women to survive metastatic breast cancer, according to a large statewide study by the University of North Carolina at Chapel Hill.

Cancer mortality continues steady decline, driven by progress against lung cancer
The cancer death rate declined by 29% from 1991 to 2017, including a 2.2% drop from 2016 to 2017, the largest single-year drop in cancer mortality ever reported.

Stress in cervical cancer patients associated with higher risk of cancer-specific mortality
Psychological stress was associated with a higher risk of cancer-specific mortality in women diagnosed with cervical cancer.

Cancer-sniffing dogs 97% accurate in identifying lung cancer, according to study in JAOA
The next step will be to further fractionate the samples based on chemical and physical properties, presenting them back to the dogs until the specific biomarkers for each cancer are identified.

Moffitt Cancer Center researchers identify one way T cell function may fail in cancer
Moffitt Cancer Center researchers have discovered a mechanism by which one type of immune cell, CD8+ T cells, can become dysfunctional, impeding its ability to seek and kill cancer cells.

More cancer survivors, fewer cancer specialists point to challenge in meeting care needs
An aging population, a growing number of cancer survivors, and a projected shortage of cancer care providers will result in a challenge in delivering the care for cancer survivors in the United States if systemic changes are not made.

New cancer vaccine platform a potential tool for efficacious targeted cancer therapy
Researchers at the University of Helsinki have discovered a solution in the form of a cancer vaccine platform for improving the efficacy of oncolytic viruses used in cancer treatment.

American Cancer Society outlines blueprint for cancer control in the 21st century
The American Cancer Society is outlining its vision for cancer control in the decades ahead in a series of articles that forms the basis of a national cancer control plan.

Read More: Cancer News and Cancer Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.