May 20, 2020 – A big data analytics tool that uses information from multiple cancer types could help researchers identify potential treatments and accelerate precision medicine, a study published in the Journal of Clinical Oncology Clinical Cancer Informatics revealed.

Developed by researchers at the University of Michigan Rogel Cancer Center, the tool combines multiple datasets to help turn information into meaningful clinical insights. Recent efforts to categorize the molecular data of multiple cancer types has produced an overwhelming amount of data, researchers noted, and this tool could help researchers make sense of it all.

“Our idea was to combine three sources of data sets – molecular data from both cancer cell lines and patients and drug profiling data – to understand proper preclinical models that are most representative of these tumors,” said Veerabhadran Baladandayuthapani, PhD, professor of biostatistics at the University of Michigan School of Public Health.

The tool, called TransPRECISE, uses data from 7,714 patient samples across 31 cancer types, collected as part of the Cancer Proteome Atlas. This information is combined with 640 cancer cell lines from the MD Anderson Cell Lines Project and drug sensitivity data representing 481 drugs from the Genomics of Drug Sensitivity in Cancer model system.

“The good thing is this is a very dynamic process. We can have this whole system set up in a computer. As new patients come in or new data comes in, you can keep adding it,” said Rupam Bhattacharrya, MStat, a doctoral student and first author on the paper. 

The new tool builds on an earlier model from the team, called PRECISE (personalized cancer-specific integrated network estimation model). The PRECISE model aimed to analyze the changes that occur to the molecular structure of individual patients’ individual tumors.

TransPRECISE adds in data from cell lines and drug sensitivity, which will be helpful for researchers translating cancer cell biology into drug discovery.

“Now that we have tens of thousands of tumors on these patients, we can evaluate what might be the potential therapeutic efficiency of these drugs. The key idea was to develop an analytic tool to do that,” said Baladandayuthapani, who is also director of the Rogel Cancer Center’s cancer data science shared resource. 

The research team validated the tool by comparing known drug responses and clinical outcomes in patient data. The model identified the differences in proteins among individual tumors, and accurately tied it back to actual patient outcomes.

Researchers also looked at several pathways to predict potential drug targets, which generated results that reflected current treatment recommendations or targets being tested in clinical trials, such as ibrutinib for BRCA-positive breast cancer.

In addition to the published study, researchers have made a comprehensive database and visualization of their findings publicly available. The team expects the tool to lead to accelerated drug discovery for different types of cancer.

“We have so much data, how do we drill it down to make it more informative so an oncologist can understand? Our work would potentially help oncologists or researchers develop concrete hypotheses based on which mechanism is working, potentially bringing to the top drugs that might warrant more evaluation,” Baladandayuthapani said.

The results demonstrate the potential for analytics tools to advance precision medicine for cancer and other types of complex diseases.

“In summary, TransPRECISE offers the potential to bridge the gap between human and preclinical models to delineate actionable cancer-pathway-drug interactions to assist personalized systems biomedicine approaches in the clinic,” researchers stated.

The post Big Data Analytics Tool Could Help Guide Cancer Precision Medicine appeared first on Artificial Intelligence.

Advances in next generation sequencing mean we are now enjoying the era of the sub-1000-dollar genome, and the world’s genomic databases are expanding exponentially with primary sequence data from more and more individuals daily. These terabytes of genomic data, alongside the growing wealth of digital health records and clinical trials, bring invaluable insights into the biological mechanisms of human health, aging and disease.

In order to fully exploit these data, it is essential to foster the cross-disciplinary connections between computational and experimental approaches, and the transfer of state-of-the-art knowledge between the two areas. This is what the [BC]2 Basel Computational Biology conference at BASEL LIFE sets out to do, through a series of workshops and plenary sessions detailing the current level status of research, discoveries and computational methods on “Big Data in Molecular Medicine”.

The [BC]2 conference highlights five focus areas, with invited experts and selected speakers: single-cell data, evolutionary medicine, clinical population genomics, systems biology of disease, and multi-level data integration. These focus areas converge into three key themes:

From single-cell data analysis to precision oncology. Being able to identify and interpret the consequences of mutations in the individual cells of a tumour is key to classify the tumour’s stage, and to apply adequate therapies. Keynote speaker Peter Kharchenko, from the Harvard Medical School (US), studies tumour heterogeneity, as well as the interactions between tumour cells and their microenvironment – his talk will provide new insights on the joint analysis of heterogenous single-cell data collections.

From pathogen sequencing to fighting infectious diseases. Many diseases are caused by rapidly mutating pathogens (bacteria, fungi, viruses) which can eventually become drug resistant. Understanding the molecular properties of pathogens is thus essential when designing drugs and vaccines, and when allocating resources for the monitoring of disease outbreaks. Keynote speaker Roy Kishony, from Technion (Israel Institute of Technology, IL) combines experimental and theoretical approaches on the evolution of pathogens and antibiotic resistance, and will present the latest views on predicting antibiotic resistance.

Biological big data analysis and methods. Big data from basic research is made up of many different sources and formats, including (but not limited to) RNA or DNA sequencing, genome-wide association studies, and mass spectrometry. Extracting useful information from these data requires tailored tools and methods, such as algorithms derived from machine learning. Keynote speaker and systems biologist Yves Moreau (KU Leuven, BE) studies how the genetic variation in a person’s genome can influence the risk or severity of a disease – he will talk about Bayesian matrix factorization and deep learning data fusion to predict drug-target interaction.

Selected presentations and posters will further highlight research and efforts to facilitate data-driven precision medicine and give scientists an unprecedented opportunity to learn from one another. Practical sessions will include tutorials on machine learning in the context of DNA sequencing and drug sensitivity prediction models, pathogen genome analysis strategies, and reproducible data management, curation and analysis.

The post Next generation molecular medicine: unlocking big data for precision oncology and infectious disease appeared first on Artificial Intelligence.