Data Science in the Pharmaceutical Industry
This post goes over how Data Science is helping big Pharmaceutical companies make informed decisions by analysing the historical data they have to make predictive models. To understand the pain point that predictive modelling addresses in the pharma industry, let us go over some numbers:
- It takes approximately 8 years for a new drug to be approved by the FDA.
- Each new drug approved costs an average of $500 million dollars.
- Only three out of 20 new drug therapies make enough profit to cover the losses experienced when the drug is undergoing testing.
Since companies are bound by the above financial and time investments, any drug that is created to cure a disease takes a lot of time to reach the customers. Companies and the government strive to make the process of successful drug creation that can pass the lab tests to reach the market.
In this scenario, leveraging the power of inhouse data becomes inevitable as it helps in predicting the compounds that could make a successful drug. Machine Learning techniques such as supervised learning and reinforcement learning can be applied to the data to predict what compounds make a successful drug.
The adoption of Data Science in the pharmaceutical industry is yet another great opportunity for upcoming data scientists to make a positive impact on the society with their work and also craft a bright future for themselves.
By: Abhishek Vigg