Saving a human life takes a village – in the metaphorical sense. Many different types of – doctors, physicians, scientists, pharma, healthcare companies – come together to make this happen. Practitioners spend much of their active lives driven to do their best. Out of the many many challenges, drug discovery is one of the most excruciating.
To ‘discover’ a single drug can take an entire lifetime. The successful discovery of medicine – on average – takes no less than 15 years from conceptualization to a commercially available medicine. This is a major hurdle when it comes to saving lives. In the past, researchers and scientists have had limited access to data for the development of new drugs.
When it comes to drug discovery, despite advancements in new technologies, the industry is still facing a productivity challenge. Discovering new drugs is taking longer and costing more. Industry leaders agree that there is a definite need to bring a fundamental shift in drug discovery to make it faster and more effective.
Due to the advances in technologies like sequencing and mass spectrometry, the amount of data being generated has grown exponentially. Scientists now realize the importance of using data science to boost their chances of success. Technology, such as big data analytics and artificial intelligence are disrupting how scientists look at data.
Here are some of the areas that benefit from adopting big data techniques and platforms:
Digital trial management and rapid data analysis
Conducting large population trials with enough diversity and across geographies is a mammoth task. From study design and patient enrollment and engagement to data collection, analysis and interpretation, the data points are large, diverse, and not always standardized—or even meaningful. Here, conventional data management proves insufficient. Data analytics and management platforms can help by enabling rapid turnaround. Allowing scientists and doctors to respond in real-time should help increase the chances of success of clinical trials.
Omics data analysis
In recent years, affordable genomic sequencing and mass spectrometry technologies have gained importance in pre-clinical research. These technologies combined with big data analytics will be useful in extracting salient features that can help in drug discovery. High-throughput genomic and metabolomic technologies have necessitated a change in how we handle and process data. Capability to process large data is required for even basic ‘omics’ analyses. Which is why platforms like Polly have become crucial to computational biologists. And in turn to the bench scientists, they are serving.
Algorithm-based pipeline development
Using complex algorithms to screen large databases containing biological, chemical, and clinical information can help whittle down the right candidates amongst thousands probable for testing. Advanced analytics is helping to analyze clinical data and candidate profiles.
Orphan drugs, rare diseases, and drug repurposing
With big data analytics, companies can also identify specific subpopulations for which a “failed” drug can still be a success. This practice of drug repurposing is especially beneficial to patients suffering from rare diseases that may not be commercially attractive for dedicated product development.
Through data science, biotech companies can rapidly gain insights from clinical and other data repositories to make better decisions. Data science has opened new gateways and is changing the way drugs are discovered big pharma and small biotech alike. The opportunity to understand diseases better is available to humanity. One hopes that this can bring healthcare costs down. Patients can get better medicines, and industry gets rewarded for providing better care.
Pharma is the next frontier of the digital revolution. Given our strengths in software and data, India is well-positioned to take advantage of this. Startups in India can help pharma speed-up the drug discovery process.
News article featured in The Economic Times – HealthWorld