Data Analytics Addresses Common Biopharma Process Development Problems
One of the major challenges facing the biopharmaceutical industry today is reducing the costs and time to market involved with new product development. Data analytics has emerged as an important tool that helps companies use their data to optimize processes, reduce waste, ensure compliance and shorten development cycles.
This article is posted on our Science Snippets Blog
The costs and time involved in creating new products for the pharmaceutical market today is extraordinary. For every drug successfully put on the market, pharmaceutical development involves laboratory screening of 5,000-10,000 compounds1, which comes with an estimated cost of $2.6 billion and can take 10 to 15 years.2
That’s a lot of time and resources needed. Reducing that number by just a few percentage points would be a huge savings for biopharmaceutical manufacturers. It stands to reason, then, that creating more efficient processes and reducing waste makes sense.
For every drug successfully put on the market, pharmaceutical development involves laboratory screening of 5,000-10,000 compounds, which comes with an estimated cost of $2.6 billion and can take 10 to 15 years.
Common Process Development & Production Problems
Some common problems with pharmaceutical production stem from how the process was initially developed. It’s no longer enough to have an empirically validated process. In-depth process knowledge and statistical basis for validation has become an important aspect of regulatory approvals. In fact, the FDA and other regulatory agencies encourage the use of advanced data models, especially for continuous manufacturing processes.
Such approaches require integration of advanced data analytics at every stage of the product lifecycle. Consider some of the problems that occur in process development and production.
- Process not robust enough (design space too small).
For many companies, current production processes are dependent on following a specific recipe, or steps, rather than being sensitive to changes in the quality of raw materials, contaminants, environmental factors or other process impacts.
While it might not be practical (or cost-effective) to explore every possible variable when creating your design space (the outer limits for your process control), having a very limited design space could limit options for dealing with deviations. More advanced process knowledge from the start can help in creating a better understanding of the true outer limits for acceptable ranges, and account for accuracy limits of sensors.
Read more: Creating a Design of Experiments Study to Predict Formula Robustness
- Process deviations (production problems happen).
There could be many unknowns in your production process or factors that impact each other in combination. Multiple unknown variables could be affecting each other and leading to deviations in your processes.
If your process is interrupted for some reason, whether from equipment failure, power outage or another reason, your processes could be compromised. It’s important that you have the metrics and data available to be able to validate the critical process parameters to know if a short power interruption or other issue has caused an irreparable deviation to your process.
In addition, changes made during production must follow a documented process in order to stay compliant. Without having a clear understanding of how various interactions affected the outcome, processes typically have very narrow bandwidths for variation. Operators might not know for certain, was the temperature or pH more critical in the resulting cell volume, or what other factors impacted it? Relying only on empirical data from trial and error to get a final result makes a process less robust.
Read more: Seven Common Causes of Pharma Process Deviations
- Raw material problems (contamination or variation).
In complex manufacturing processes, variability in raw materials can lead to unexpected and undesirable changes in the final products. In regulated industries such as biopharmaceuticals, this is especially problematic due to the need to maintain carefully controlled processes that stay within approved regulatory parameters for drug development and production.
If there is a problem with the raw material that goes undiscovered, perhaps because it’s not properly measured or tested, you had a change in supplier or media, or it was contaminated during transport, you could start seeing unexpected deviations. These are often easy to spot because they create specific variations, but the sooner you discover them the better. They could impact the quality of production otherwise.
- Lost batches (batch contamination or failure).
Lost batches can result from human error, contamination, equipment failure or other reasons. If a process is not followed correctly, perhaps a stainless-steel reactor wasn’t completely cleaned between batches, or chemicals were not properly flushed away, it could affect the next production run. There could be an impurity of some kind, such as contamination with bacteria, mycoplasma, or viruses. Technicians might not realize it until they notice cells are dying but aren’t sure what is killing them. Having the right data analysis processes can help you better identify the source of contamination early.
Read more: Reducing Batch-to-Batch Variability of Botanical Drug Products
Addressing Common Problems
Within biopharma and pharmaceutical development, a number of data analytics methods play an important role in helping to create quality products, ensuring more consistent production processes and reducing the time to market.
Create more robust processes: Design of Experiments (DOE) is a statistical method of testing variables to understand the affect they have on your process and product quality. DOE helps scientists reduce the number of experiments needed to create robust processes. This can, in turn, reduce the time to market for products.
Reduce batch variability or uncover contamination in raw materials: Multivariate Data Analysis (MVDA) is a statistical technique used to analyze data that originates from more than one source or has multiple variables. It’s a more robust way of analyzing data than univariate data analysis, which evaluates at one variable at time. MVDA helps you look for trends in your data.
Optimize production in real time (and find root causes for deviations): Real-time data analytic uses real-time process monitoring combined with data analysis to provide insights about your processes in real-time. When connected digitally with a continuous feedback loop, it can be used to control processes and predict future production quality.
DOE helps you generate the right data or reduce the amount of data you need to understand cause and effect in a process. MVDA helps you find trends in your data over time. Real-time data analytics helps you keep track of what’s currently happening in your processes.
Why Use Data Analytics?
In a nutshell, data analytics provides actionable insight to improve product design and process development. Data analytics helps production teams understand cause and effect, determine which parameters will affect a process, know which attributes are critical to the quality outcome, and even predict that outcome based on what’s happening with the process now.
For many companies, data analytics can also help set actionable goals. Data analytics helps your team outline the steps needed to put specific actions in place (or perhaps even to define which goals are realistic and can be achieved at all).
What changes will reduce time to market? How much time can you realistically cut from the process? Are your production volume goals realistic? How will they affect quality?
When you start to put specific numbers and actions around the goals, it makes it a lot easier for the entire organization to get behind them and to understand what you’re trying to achieve. Some key areas in which data analytics can help include:
- Create robust, well-documented, regulatory approved processes
- Shorten process development times by reducing the number of experiments needed
- Find ways to optimize processes that can save time and reduce steps
- Eliminate deviations in batch and continuous processes
- Identify critical process parameters and understand how they affect other variables
- Uncover contamination or defects in raw materials that may impact final quality
- Quickly pivot or adjust processes while staying within approved process frameworks
Data Analytics Grows Bottom Line
In the biopharmaceutical industry, data analytics is an essential tool to accelerate product development, reduce manufacturing costs and manage quality control. Enlisting advanced data analytics at every stage of the product lifecycle helps companies develop processes to deliver high quality products – even minimizing impacts of environmental or raw material deviations – and directly impact the bottom line.
Read more: What Today’s Biopharma Leaders Need to Know about Data Analytics
References:
1. Britannica, “Drug discovery and development,” Drug Development Process, Accessed Feb. 18, 2022.
2. DiMasi, Grabowski, Hansen, “Innovation in the pharmaceutical industry: New estimates of R&D costs,” Journal of Health Economics, vol. 47, 2016, p 20-33.
3. McKinley, “How pharma can accelerate business impact from advanced analytics,” Jan. 2018.
4. C. Wurth et al., “Quality by Design Approaches to Formulation Robustness- An Antibody Case Study,”Journal of Pharmaceutical Sciences (2016) 1e9
