Skip to main content
New Technologies for Accelerating Drug Development

The View from Bio-IT World: New Technologies for Accelerating Drug Development

Innovative Artificial Intelligence and Machine Learning Technologies can improve Pharma R&D, Reduce Costs and Benefit Patients

The Pharma industry is constantly searching for more effective, more efficient tools and technologies to improve the drug discovery process. The statistics are well-known, and make gloomy reading: it takes 10-15 years to develop a new drug, at a cost of up to $1 billion. There is currently vigorous discussion over whether new tools and technologies can significantly impact these metrics. Big data, blockchain, artificial intelligence (AI) and machine learning (ML) are much talked-about as holding the key to digital transformation of drug discovery.

At the Bio-IT World Conference & Expo last month, many of these themes were explored. Across the dozen or so session tracks, there were talks and workshops to share information and best practises on how scientists in biotech, pharma, academic institutes and vendor companies are applying AI and ML for a variety of use case, such as models for adaptive clinical trials, imaging analytics (e.g. for pathology or clinical sample data), lead design, QSAR, analysing data streams from mobile monitoring devices, and more. Some snippets from the talks include:

  • Anastasia Christianson, Janssen, talked about the drive for real time data access and data analysis, to make best use data for decisions that ensure delivery of safe effective medicines to patients.
  • Alex Ivliev from Clarivate presented on a collaboration with Merck, using a broad range of data types (processes, cellular localisation, KO mouse, gene expression, protein-protein interactions, text-mined data from PubMed and more) to feed into a random forest model, for genetic drivers of Parkinson’s Disease.
  • Yue Webster, Lilly, talked about network-based approaches to understanding drug toxicity
  • Shyamal Patel, Pfizer, discussed application of ML to develop digital biomarkers, from data captured by wearables, smartphones, or voice-operated digital assistants.
  • Philip Ross, BMS, talked about leveraging machine learning to identify composite biomarkers for the optimal treatment regime for each individual patient, in immune-oncology.
  • Joseph Lehar, Merck, discussed some of the initiatives at Merck where digital health and AI collaborations are making an impact, including discovery of new therapeutics, getting clearer phenotypic disease signals from digital tools, and improving development strategies with real world data (RWD).

Artificial Intelligence isn’t New

Of course, artificial intelligence isn’t new. In 1950, Alan Turing proposed the Turing test as a metric for machine intelligence (which also happens to be the year that Isaac Asimov published his Three Laws of Robotics). Closer to our industry, Professor Desmond Higgins, the Benjamin Franklin Award laureate for 2018, gave one of the Bio-IT World key note addresses. He talked about the evolution of databases and tools for genetic and genomic manipulation – including search and alignment software such as BLAST, Clustal. Building algorithms to align and cluster nucleotide sequences wasn’t called AI in those days; but in taking away the huge manual effort involved, these tools are indeed AI.

Natural Language Processing is an AI Technology for Better Scientific Search

Another manually intensive area where AI can help is in scientific search. At all stages of drug discovery and development, there is a community of bench scientists and researchers who aren’t experts in search, but need answers to business critical questions. Typically, they spend over 8 hours per week, struggling with different tools to find the key information that will inform each decision point. This is of course a huge drag on the R&D pipeline, but there are AI tools that can bring benefits. Natural Language Processing (NLP) is an established AI technology that enables written text to be interpreted, and rapidly transforms the key content in text documents into quantitative, actionable insights.

You too can get your Hands on a Cutting-Edge AI Technology

At Bio-IT World, Linguamatics won Best of Show for our new product iScite, putting the precision and power of Linguamatics text analytics directly into the hands of scientists. The premise of iScite is to take behaviour that people already have, a key word search behaviour, and convert that into an advanced knowledge search. The Award panel said,

Our judges were blown away with the natural language processing power it delivers at a very affordable price point. It puts Big Pharma power into the hands of the small guy, one judge said. And the judges issued a challenge to the Bio-IT community. Linguamatics just made this tool broadly accessible, so let’s see what a whole community of really smart people can accomplish with it.

Linguamatics have many customers in pharma, biotech and healthcare organisations, gaining better value from their unstructured text, finding answers they could not before, reducing time spent on projects from bench to bedside. Contact us to find out more about the power of iScite.

Learn more about drug development safety 

Ready to get started?

Request a demo

Questions? Ask our experts