By John Cassidy and Harry Clifford

Due to an explosion in machine learning and genomics research, coupled with the widespread availability of compute power through services such as Amazon’s AWS and Microsoft’s Azure, multiple startups have been founded to help bridge the gap between genomics, medicine, and machine learning.

Deep Genomics uses machine learning to help researchers interpret genetic variation, specifically patterns of SNPs, and to understand how this variation can affect crucial cellular processes such as metabolism and DNA repair.

Cambridge Cancer Genomics focuses on using cancer sequencing data to help clinicians understand how best to tailor treatment plans to individual patients. The company translates a tumour’s ‘DNA fingerprint’ into personalised treatment recommendations and uses liquid biopsies to monitor both how well these treatments are working and how the patient’s tumour is evolving over time.

Desktop Genetics have developed a platform for researchers to design CRISPR guide RNAs using ML. Initially for in vitro and in vivo experiments, this could evolve into a personalised drug discovery platform as more information on gene editing and CRISPR safety becomes known. More directly clinical, Freenome uses ML to identify multi-omic cancer risk signatures from blood samples, it is hoped that this technology could lead to a low invasive screening test for multiple cancers.

In order to best take advantage of machine learning in medicine, numerous initiatives are underway to  integrate ML into the clinical workflow and thus remove gaps in the data available to healthcare professionals. As evidenced by Intel’s Analytics Toolkit for breast cancer therapy, integrating genetic and clinical information is vital to better understand treatment and patient care.

 

Read more about the crossovers of artificial intelligence (AI) and biology

Part 1: HOW DO BIOLOGY AND MACHINE LEARNING INSPIRE ONE ANOTHER?

Part 2: HOW IS MACHINE LEARNING AIDING IN THE UNDERSTANDING OF GENOMICS DATASETS?

Part 4: DISCOVERING BIOLOGICAL TRUTHS IN HEALTHCARE DATA WITH MACHINE LEARNING

BIOS

treatment genomics artificial intelligence medicine healthcare AI machine learning

John Cassidy:

John is Co-founder and CEO at Cambridge Cancer Genomics, a precision oncology startup building software solutions for iterative medicine. CCG uses integrated bioinformatic and machine learning pipelines for liquid biopsy analysis, in order to guide doctors on tumour treatment in real time. John is actively involved in the biotech startup community as a Venture Partner at the Pioneer Fund, Director of SiliconBio and a lecturer at Anglia Ruskin University. He holds a Masters in Pharmacology (1st Class) from the University of Glasgow and pursued a PhD in functional genomics at the University of Cambridge. His research career in academia (CRUK) and industry (MedImmune) focused on understanding how tumours evolve and become resistant to treatment. He has published numerous scientific papers, book chapters and literature reviews, and has 300+ citations.

 

 

treatment genomics artificial intelligence medicine healthcare AI machine learning

Harry Clifford:

Harry is Co-founder and Chief Technology Officer at Cambridge Cancer Genomics. He leads CCG’s tech team of AI researchers, data scientists and bioinformaticians to conduct innovative R&D and develop the underlying tumor analysis pipelines and cloud architecture of CCG’s smart genomics systems. Harry has a PhD in bioinformatics from Oxford University and experience in postdoctoral roles, including at Cambridge University with Cancer Research UK; and in the biopharma industry, where he worked on developing biomarker-based medical diagnostics.