Drug discovery 2.0 - revolutionizing the quest for innovative drugs through data-driven insights

5 minute read


3rd October 2023




Worldwide the pharmaceutical industry is in crisis. Reliant on wet labs, the industry is stuck in ‘drug discovery 1.0’ - slow, expensive and outdated processes to deliver life-saving drugs to an aging and growing global population.


Worldwide the pharmaceutical industry is in crisis.


For pharma to succeed, urgent transformation is needed to speed up the entire drug development process. On average the process takes between 10-15 years; with between 5-7 years to identify and validate a target, and 3-7 years for clinical trials.


Drug discovery 2.0 - Lifebit’s solution for success


Drug Discovery 2.0 is the pharmaceutical industry’s opportunity to revolutionize pre-clinical drug development and clinical trials through federated data, analytics and AI. 

Data is pivotal in delivering fast and effective pre-clinical drug development. Moving from traditional processes to data-driven processes will accelerate discoveries and deliver faster, cost-effective, personalized medical treatments. 

Lifebit provides the three key elements of Drug Discovery 2.0:

  1. Multi-modal federated data: Managing, linking and extracting insights from diverse data types across various sources and modalities (e.g. clinical, molecular, imaging). Implementing a democratized, user-friendly, no-code point-and-click solution tailored to drug discovery researchers for swift and accurate insights in a matter of a couple of days or weeks.

  2. Data standardization: Seamless harmonization through automated tools to accelerate research capabilities

  3. End-to-end analytical solutions: Moving away from isolated point solutions to provide comprehensive disease insights, ultimately aiding in target identification and verification.


The right 123-1


Drug Discovery 2.0 is a shift away from traditional wet labs to data labs, which facilitate data science and experimentation, to accelerate target identification and validation to as little as a few months. In addition, data enables more accurate clinical trial design and recruitment with the possibility of doubling success rates and reducing time for trials from 6-7 years down to 3-4 years.


Drug Discovery 2.0 is the pharmaceutical industry’s opportunity to revolutionize pre-clinical drug development and clinical trials through federated data, analytics and AI.


Comparing traditional drug discovery processes with data-driven processes



Drug discovery 1.0
Traditional drug discovery

Drug discovery 2.0
Data-driven drug discovery

Average cost of bringing a new drug to market $2.2 billion

Opportunity to save over 25% in annual costs through analytics with big data by healthcare organizations

Average time to target identification and validation is 5-7 years

Some computationally-driven discovery efforts are claiming target to lead times as low as 1-2 months and target to clinic times under 1 year

Other estimates suggest significantly shorter times, ~9 months, to identify targets through use of AI

Suitable candidates for clinical trials produced only 50% of the time

Suitable candidate for clinical trials produced 90% of the time



Drug Discovery 2.0 (1)


Challenges with traditional drug discovery processes


The pharmaceutical industry is vital in providing life-saving therapeutics worldwide. However, the growing global population, coupled with the prevalence of chronic conditions, intensifies the demand for large-scale and fast clinical discovery and production. In turn, this is creating pressure for the pharmaceutical sector to deliver new medicine at pace.


The key challenges of traditional drug discovery processes are:

Very slow drug discovery taking 10+ years

Processes are time-consuming, typically spanning well over a decade from the initial concept to market approval. Prolonged timelines across multiple pipelines pose substantial challenges including declining revenue, share price, reputation, plus competitive pressure and, importantly for those patients in urgent need of treatment for severe or rare diseases.

Escalating costs averaging $2.2 billion per drug

Drug discovery is an expensive endeavor with an estimated average cost of over $2.2 billion for each new drug, with costs to bring an asset to market increasing by 67% since 2010. The costs are primarily attributed to rigorous research processes, clinical trials, and regulatory requirements. The financial burden often hinders innovation, for example in the development of new antibiotics, limiting the number of potential life-saving drugs that reach the market.

High failure rates and depleting pipelines

The drug development process is fraught with uncertainty. Many potential drug candidates fail to progress beyond preclinical stages or fall short during clinical trials due to issues like safety concerns or insufficient efficacy. These failures represent significant setbacks in terms of time and resources invested and result in depleted pipelines.

Slow identification and validation of targets

Identifying the right molecular targets for specific diseases is challenging. Validating these targets to ensure they are modifiable by drugs is equally critical but far from straightforward and on average takes between 5-7 years through traditional wet lab processes.

Loss of productivity through scientific complexity

The complexity of human biology presents significant challenges in understanding diseases and identifying suitable drug targets, particularly for those targeting complex, chronic or rare disease. Researchers must decipher complex molecular interactions and pathways, requiring cutting-edge tools and interdisciplinary collaboration or face loss of productivity in drug development for these more complex conditions.

Regulatory hurdles

Regulatory agencies, while vital for ensuring drug safety, impose stringent requirements for approval. Navigating the regulatory landscape, which vary from country to country, is a complex and resource-intensive aspect of drug discovery.

Difficult data access and poor data quality

Advances in technology have led to an explosion of biological data. However, data available for research and trials are siloed, fragmented and often of poor quality with estimates that 97% of healthcare data are unused.

Ethical and moral considerations

Balancing the drive for profits with ethical considerations can be challenging. Pharmaceutical companies often face scrutiny over pricing, accessibility, and the ethics of drug development practices. In addition, there are considerations about lack of data diversity, resulting in inequity in research outputs and access to new drugs and therapies.

Resistance and evolution

Microorganisms and cancer cells can develop resistance to drugs over time, rendering previously effective treatments ineffective. Researchers must continually innovate to stay ahead of these evolving challenges.

Rare diseases and orphan drugs

Developing drugs for rare diseases, known as orphan drugs, presents unique challenges due to limited patient populations and financial incentives. These challenges underscore the need for innovative approaches to drug discovery.

AI & Data Federation - the golden thread of the next generation drug discovery 2.0


Artificial intelligence (AI) promises a revolution for drug discovery, allowing computer systems and software to perform tasks that typically require human intelligence. While there have been success stories, investments in technology aimed at elevating data and analytics have not yet achieved the profound impact required by the pharmaceutical sector. 

Notably, some high-profile endeavors have not fulfilled their pioneering promises to transform health and life sciences. First generation data and technology solutions have fallen short; unable to support multi-modal data, end-to-end analytics, or secure accessibility for everyday researchers and unable to identify targets as quickly as needed in vital health research.

The introduction of federated technologies can overcome these challenges by enabling collaborative insights without needing to move or centralize the data, ensuring data privacy and security, which is crucial in the pharmaceutical industry. Federated technology is a software process that enables numerous databases to work together as one. 

Combining AI and federated technologies through federated machine learning in drug development processes can allow the safe linkage of distributed health datasets and the fast and accurate analysis of these data to achieve target results. This has the potential to reduce the time to access vital health data from up to 6 months down to just two weeks and generate results from the data in 2-4 weeks rather than 9-16 months.


This has the potential to reduce the time to access vital health data from up to 6 months down to just two weeks




Traditional processes for drug discovery are marked by slow pipelines, scientific complexity, and soaring costs. Overcoming these challenges requires Drug Discovery 2.0 - more effective use of data, next-generation technology to enable federation and data linkage, automations and cutting-edge AI tools such as Federated Machine Learning.

Without rapid transformation of processes and use of scalable innovative technologies for data and analytics, the pharmaceutical industry is at risk of failure and, more importantly, patients will miss out on life-saving treatments



About Lifebit


Lifebit provides federated data analysis services for clients, including Genomics England, Boehringer Ingelheim, Flatiron Health and more, to help researchers transform data into discoveries.


Interested in learning more about Lifebit’s data services and how we accelerate research insights for academia, healthcare and pharmaceutical companies worldwide?


Contact us  Request a demo