Exploring Possibilities for AI and ML for Drug Discovery
Developing new medicines is not for the faint-hearted! On average, it takes about a decade of research with an expenditure that amasses US$2.6 billion to shepherd an experimental drug from lab to market.
The field of artificial intelligence and machine learning (AI/ ML) has witnessed sharp upturns, particularly concerning deep learning (DL) methods that are pillared with the availability of big data. Biomedical data is humongous and becoming increasingly available in ML-ready digital formats, it is now possible to deploy AI/ML algorithms to support healthcare research and services. However, within the larger healthcare ecosystem, biopharmaceutical companies, in particular, have been criticized for the skyrocket pricing of prescription drugs. Artificial Intelligence and Machine learning have the power to improve drug discovery and medical research which may reduce drug prices in the long-term.
Out of the total drug discovery done only about 5 per cent of experimental drugs make it to market!
This paves way for drug makers and pharma companies to invest hugely in artificial intelligence and machine learning with the hope that these technologies will make the drug discovery process faster and cheaper.
Machine Learning Applications at Biopharma Companies
The high prices of the drugs are attributed to the significant costs of drug research and development, done by the pharma giants. This figure has recently been estimated to average around UD$2.6 billion per treatment. It takes up to 15 years to bring a new therapy to market. Less than 12% of drugs that enter clinical trials end up being commercialized, leading to pharma’s and investors turning their gaze to making drug discovery a faster process in the recent times especially post Covid-19 aftermath.
Artificial Intelligence (AI) has recently been earmarked as a debated topic of interest in the area of medical care. Biopharmaceutical industries are putting their efforts to expand their viewpoint in AI to enhance the drug discovery process, diminish failure rates in clinical trials, generate superior medicines and reduce research and development expenses.
Accessibility of methodological statistics in life sciences coupled with speedy developments in machine learning algorithms has led to an evolution of AI-based start-up companies focused on drug discovery over the recent years.
Fostering Global Pharma Alliances
Several prominent AI and ML companies bog and small have focused some of their resources to address the inefficiencies of this space-
• Pfizer, has partnered with IBM Watson to identify more robust targets during the discovery phase, process thousands of scientific publications to determine novel combinations of drugs for improved efficacy, and optimize the patient selection for clinical trials.
• Insilico Medicine and Exscientia, are attempting to utilize genomics and artificial intelligence tools for computational design of new drug candidates.
If the integration of AI into the drug discovery and design process works, it can have incredible disruptive effects. It could disrupt the entire drug discovery ecosystem throwing many chemoinformatics out of jobs. However, cutting down drug discovery from years to months especially after Covid-19 pandemic would mean an incalculable effect on the larger pharma environment.
An industry which justifies its high drug prices by the lengthy and costly research undertaken at the development phase, it ‘ll be a tectonic shift, that seems like a gamble worth taking.
CLICK HERE TO WATCH MAKING OF B-AIM: