Precision Medicine Lab

The Precision Medicine Lab is a cross-disciplinary laboratory that allows data analysts and deep learning experts to work very closely with biologists, geneticists and clinicians to leverage the power of genome-scale datasets, big data from the hospital and machine learning to improve cancer patient outcomes. Our aim is to 1) establish a robust, well-maintained and secure biorepository that can store samples collected from patients, 2) develop an ‘-omics’ stack beginning with exome and microbiome data from cancer patients along with matched clinical data including health records and images from radiology and pathology, 3) use machine learning methods to analyse the rich stack of datasets and predict new therapeutic targets and pathways and 4) experimentally validate all predictions in cell lines and in vivo models. This is Pakistan’s first concerted attempt to pilot precision cancer medicine funded by the Federal Government. The lab has an unfair advantage of being located at the heart of Phase-V biomedical cluster in Hayatabad, Peshawar – which is arguably the densest healthcare cluster in the country, attracting patients from all over the country and the broader region.

The Precision Medicine Lab, as an affiliate Lab of the National Center for Big Data and Cloud Computing, funded by the Government of Pakistan that aims to develop integrated genomic and health datasets and use computational methods to help improve individual patient outcomes, especially in cancer, and to improve development of new drugs and to provide enabling technology for drug combination studies and targeted drug delivery.

The Precision Medicine Lab (CECOS) has the following two goals:

  • Goal 1: Develop a National Cancer Genome Repository to enable personalized cancer care in Pakistan.
  • Goal 2: Develop a computational framework for drug re-purposing and side-effect prediction.

Why now?

Biology is developing at a rapid pace and increasingly becoming data-driven, thanks to the exponentially decreasing cost of DNA sequencing – or our ability to read the human genome. The first human genome was sequenced in 2001 when an international coalition announced the first draft. The total project cost was close to 3 billion US dollars. The same genome can now, breathtakingly, be sequenced for almost $1000. Genome data gives us a glimpse of our past (our pedigree and ethnic background), our present (from our wellness to our illnesses) and our future (diseases we are genetically more prone to have in the future as we age). Genome data also helps us ‘personalize’ medicine by understanding how different patients (of different genetic backgrounds) respond to different drugs. Adding this giant, and growing, corpus of data to digital data from hospitals (like electronic health records, images from radiology and pathology) and other new-age sources like our mobile phones, digital watches and wearable gadgets, and even digital sensors at home and at work has the potential to give us unforeseen predictive power when it comes to our health and well-being.

A recent study at the Mayo Clinic (US) has shown that there is 30% decrease in hospitalization if the patient’s genomic data is used in diagnosis. Another study has shown that (in women of 50 years and above) a 37% decrease in cost of cancer treatment is observed if genomics data is available. Research has also shown that 20% of cancer patients die because of side effects of drugs and not the diseases itself. Finally, against a global cancer survival rate of about 60%, the figure in Pakistan is a mere 30%. This clearly indicates the potential healthcare as well as economic impact of genomic data and a better understanding of  drug responses in patients.