BERG using AI in pancreatic cancer research


Massachusetts-based biopharma company BERG has begun a phase 2 trial for a new pancreatic cancer treatment with the help of its artificial intelligence analytics technology.

The company is taking a unique approach to drug discovery, with its 'Interrogative Biology' machine learning platform at the core of its R&D efforts.

The trial will investigate the combination therapy consisting of BERG's coenzyme Q10 candidate BPM 31510 (ubidecarenone) and gemcitabine in the treatment of 25 patients with metastatic pancreatic adenocarcinoma.

BERG's Interrogative Biology platform will identify those patients who would respond better to the combination therapy, based on "molecular maps" constructed from blood and tissue samples taken from the participants.

The process works by patient samples being collected in both diseased and healthy states, and are then processed through a high throughput mass spectrometer forkflow. The biological activity of the sample is then analysed - including the genome, proteome, lipidome and metabolome.

Berg also looks at mitochondrial function, oxidative states and ATP production to understand how cells are functioning. This process produces trillions of data points from a single sample, which are then combined with patient clinical information and analysed by its proprietary artificial intelligence machine learning analytics program.

The company believes this combination of systems biology and artificial intelligence will help become a leader in developing 'precision medicine', treatments closely tailored to sub-groups of patients.

"We are working diligently to make a difference in the lives of patients with pancreatic cancer and are very pleased to be starting this trial," said Niven R. Narain, BERG co-founder, president and Chief Executive Officer. "With use of BERG's Interrogative Biology platform, we will be applying our precision medicine approach where output from this trial will allow us to match patients to this given combination based on their biological profile."

BERG is not the first to utilise machine learning in this fashion. Many start-ups and big pharma companies are starting to integrate AI platforms into their research to aid in the gradual push towards a more personalised approach to medicine.

Last week, radiology specialist Imaging Advantage were the latest to announce a venture to create an AI capable of pre-reading x-rays to identify disease, following in the footsteps of AstraZeneca and Human Longevity Inc's 'genome mining' project.

BPM 31510 performed well in phase 1 trials with results suggesting it is well tolerated both as a monotherapy and in combination treatment with chemotherapy. The drug works by reversing cancer cell metabolism and reactivating cell death pathways.

profile mask

Marco Ricci

3 May, 2016