IDBS BlogAccelerated drug discovery. Woman testing samples. Digital background.

IDBS Blog | 31st January 2024

Three tips for achieving accelerated drug discovery and development

Accelerated drug discovery. Woman testing samples. Digital background.

By Daniel Tabas, Senior Data Scientist, IDBS

One may ask how an industry that invested close to $58 billion in technology in 20221 to discover new therapies continues to allow the pharmaceutical lab to heavily rely on antiquated and manual processes, and siloed and unorganized data, to move those therapies toward development and commercialization.

Savvy researchers are beginning to unlock the potential of machine learning (ML), artificial intelligence (AI), digital twins and other advanced analytics by making data more accessible along the drug lifecycle and accelerate drug discovery and development.2 But these systems will only be as good as the data they are built upon. Improved decision-making could bring drugs to market 500 days faster and 25% cheaper, according to McKinsey & Company.3

The speed at which COVID-19 therapies were brought to market showed the pharma industry that development timelines can indeed be shortened. Development velocity is a new term being used to define the speed at which a therapy moves from discovery to development and toward commercialization.1 McKinsey says “the space from candidate nomination to investigational new drug presents a unique opportunity for accelerated drug development”3 and that this accelerated timeline can be achieved through digital technology and advanced analytics.1,3

In a recent edition of Lab Manager,2 Alberto Pascual, PhD, Director of Data Science & Analytics at IDBS, suggests that a digital analytics system can help accelerate discovery, and offers the following three factors for lab managers to consider as they take the digital transformation journey toward accelerated drug discovery and development.

1. Be honest about your data to maximize accelerated drug discovery

Before you can even begin to contemplate digital technology, it is important to truly understand what your data looks like, how it is managed, and if it can be contextualized. Pascual points to a leading CDMO that is spending upwards of 95% of its time cleaning data, a process that is necessary before that data can be leveraged and meaningfully analyzed and used. This exercise of cleaning data can often be attributed to the lack of standardization with paper-based systems and slows the path to insight and discovery. However, even labs that have begun their digital transformation may find that their data is not as clean as they think. In fact, a data architecture may lack the context needed for successful decision-making or to meet regulatory requirements.

He recommends that lab managers deploy the F.A.I.R. toolkit4 for assessing data quality and leveraging assets. As the life sciences industry continues to transform digitally, F.A.I.R. seeks to ensure that data is Findable, Accessible, Interoperable and Reusable. More effective management and collaboration of data, particularly that which resides in archives, can empower development and accelerate drug discovery and innovation.5

For a lab, this could translate into connecting instruments, standardizing data and centrally storing that data throughout a drug’s lifecycle.2 A CDMO relates to Pascual that, in early phases of discovery, data exchanges about a drug molecule may be simple, but as the drug progresses to the IND stage, the data being gathered is vast and creates a complete dossier of information to present to regulatory agencies. This is where a digital backbone, such as IDBS Polar,6 can securely manage a drug’s progression through its development lifecycle, collecting, structuring and organizing data from all processes and operational activities to accelerate early product and process insight. The IDBS Polar platform facilitates accurate process execution and captures equipment and instrument data yielding a curated process-centric data backbone.

2. Let scientists take the lead on the digital transformation journey

Global spending on digital transformation in the pharma industry is expected to reach $4.5 billion by 2030.7 Big pharma’s investments in data analytics are projected to increase to $1.2 billion by 2030 because of the promise of a 50% savings in testing time and a 20% improvement in development speed.8 Despite the opportunity for accelerated drug discovery, lab scientists remain skeptical as technology has more often benefitted stakeholders outside of the lab more than the actual lab itself, says Pascual.

Additionally, previous digital adoptions tended to become IT projects because the goal was simply to capture and store information for recordkeeping purposes. Today, the objective is much more extensive: structuring the data to solve scientific problems using new analytical and statistical practices. This, says Pascual, requires life sciences researchers to be involved from the beginning. “A new drug entity is defined by process data and data; a tool that works well for the bench scientist is a must have,” he writes.

Large BioPharma organizations often rely on IT to manage their data analytics and smaller organizations often don’t even have data science or analytics functions aside from basic IT support. In both cases, scientists do not tend to benefit from analytic initiatives. Forward-looking life sciences organizations will, instead, ensure that those responsible for data initiatives will be accountable to bench scientists. Pascual suggests that, at a larger company, this could involve an IT group embedding with R&D on the digital transformation journey. Smaller organizations could create a cross-functional team of IT and scientists.

According to a renowned CDMO, getting a team to buy into a new IT solution is about recognizing the benefits to the entire company.9 And, early input from this company’s pharmaceutical scientists was crucial to the successful implementation of IDBS’ offering. As a result, the company’s project team leader of Knowledge Management Systems found that “people at the bench really like using it” 9; scientist satisfaction is essential to digital tools’ success.

3. Rely on advanced analytics to reveal deep and practical insights

Having scientists on the digital transformation team will ensure that the proper goals are being addressed. A digital transformation will reveal both deep and “common sense” insights about your processes and operations to make your organization more data-centric. According to McKinsey & Co., a deep insight could take the form of predictive modeling of biological processes and drugs. By leveraging the diversity of molecular and clinical data, predictive modeling could identify new potential candidate molecules with a high probability of being successfully developed into drugs.10 Rather than this data being held in department silos, it can be captured electronically and flow easily internally between discovery and clinical development, and externally to contract research organizations (CROs) or CDMOs for real-time and predictive analytics.10

And common-sense insight can be just as valuable. Pascual relates the common-sense goal of one scientist: “Which molecules won’t work—so we can stop wasting time with them.” If the scientist is not part of the digital adoption team, then this goal may not even be considered.

Working with the lab scientist to implement a data backbone to support future goals is crucial. This will ensure that the data is contextually appropriate and interoperable with other data sets and other departments. A well-curated quality data backbone, such as IDBS Polar,6 ensures that data is complete, accessible and reusable. IDBS Polar seamlessly captures data from systems, instruments and processes and facilitates model-based insights to accelerate drug discovery and development.

Save half the time in discovery

Pascual says these three steps are essential on the path toward digital transformation, and that accelerated drug discovery remains the goal. Industry experts believe advancements in AI and ML will make that goal a reality. Ongoing studies of deploying these advanced technologies reveal the potential time savings. For example, Boston Consulting Group (BCG) found that discovery and preclinical stages can take an average of six years. BCG studied the research pipelines of 20 AI-intensive pharma companies over a 10-year period and found that five of the drug candidates reached a clinical trial stage in historic time. In another study, BCG and research funder Wellcome found that AI can yield 25-50% time and cost savings in drug discovery up to the preclinical stage.11

Yet, capturing and transferring knowledge from discovery to post-commercialization remains one of the biggest challenges in the BioPharma industry. Adopting a highly contextualized backbone like IDBS Polar, with embedded AI/ML, offers insight and end-to-end analytics, through modeling and simulation, to make more accurate and data-driven decisions.12 This complete and contextualized data, combined with advanced analytics removes biases towards “success” data to enable innovation and accelerate drug discovery and development.


If you liked this blog post, read more from Daniel Tabas.

Six ways machine learning will transform the BioPharmaceutical lifecycle



About the author

Daniel Tabas - Three tips for achieving accelerated drug discovery and developmentDaniel Tabas works as a senior data scientist in the Data Science & Analytics group at IDBS. He is a computer scientist with a PhD in Bioinformatics, specialized in data science, analytics and artificial intelligence, and with wide experience in the biomedical/biopharma domains. After obtaining his BSc in Computer Science in the Complutense University of Madrid, he joined the Spanish National Center for Biotechnology, where he worked in a core facility group while he completed his PhD in Bioinformatics. Later, he worked in PerkinElmer as a principal AI engineer. 




  1. Forbes Tech Council. (2023, March 10). Accelerating Drug Development to Keep Pace with Drug Discovery. Forbes. Retrieved from []
  2. Lab Manager. (n.d.). Effective Data Management: Key to Accelerating Drug Discovery and Development. Retrieved from []
  3. McKinsey & Company. (n.d.). The pursuit of excellence in new drug development. Retrieved from []
  4. Pistoia Alliance. (n.d.). FAIR Implementation. Retrieved from []
  5. Drug Discovery Trends. (n.d.). Accelerating R&D with FAIR Data. Retrieved from []
  6. IDBS. (n.d.). IDBS Polar. Retrieved from []
  7. ABI Research. (n.d.). Pharma Industry to Spend $45 Billion on Digital Transformation by 2030. Retrieved from []
  8. Bamboo Agile. (n.d.). Pharma Digital Transformation. Retrieved from []
  9. IDBS. (2017, March). IDBS and Lonza Collaborate to Deliver Digital Solutions for Biopharmaceutical Development. Retrieved from []
  10. McKinsey & Company. (n.d.). How big data can revolutionize pharmaceutical R&D. Retrieved from []
  11. Nature. (2023). How AI is revolutionizing drug discovery. Nature, 599(7883), 325-327. []
  12. IDBS. (2021, June). Transforming Drug Discovery through Artificial Intelligence. Retrieved from []
Check out our Blog section for more like this

Flere nyheder