What Is the Translational Gap and How Do You Close It?

Drug discovery has a translatability problem.

The National Institutes of Health (NIH) once famously reported that for every drug that receives FDA approval, another 1,000 fail. In drug development, translatability refers to the basic principle of taking scientific findings from a laboratory setting and successfully translating them as therapeutic patient treatments in a clinical setting. This is sometimes also referred to as the bench-to-bedside process.

But the drug discovery landscape is notoriously difficult to navigate and translatability can be elusive; pre-clinical failure rates for novel therapies are at around ninety percent, with an average time-to-market of 10-15 years and costs ticking upwards of US $2.5 billion.

As a result, the entire biopharmaceutical industry is under increasing pressure to transform drug discovery, particularly its slow and costly R&D processes, in order to find novel ways to close the translational gap – what’s been termed the “valley of death” in drug development.

What is the translational gap?

The translational gap in drug development refers to the routine failure of the bench-to-bedside process – literally the lack of successful drug candidates that make it all the way through discovery and research to clinical implementation in patients.

What is translational medicine?

Translational medicine, sometimes also called translational science, is a multidisciplinary field of investigation that seeks to improve outcomes where they matter most: for patients. The goal of translational medicine is to find novel and effective ways to move basic scientific discoveries into real-world applications and practices with greater speed and efficiency – ultimately improving prevention, diagnosis and therapies.

Why do we need translational medicine?

Translational medicine is helping to bring more efficiency and predictability to diagnostics, therapeutics and medical procedures. The last decade has seen immense progress across a range of translational areas, particularly inside drug development where

AI-powered applications like deep learning, machine learning and natural language processing are being used to help close the translational gap, advancing to trial the drug candidates that have the best chance of success. These AI technologies can detect patterns and find meaningful relationships faster than conventional methods, giving them the ability to sort millions of potential molecular compounds, looking for candidates with the right properties to move forward in early lab experiments.

AI-enabled translational medicine can also help streamline trial design, improve drug efficacy and safety, accelerate speed-to-market, and significantly cut costs and reduce waste. This translational approach is helping biopharmaceutical companies mitigate their risk and scale their operations, using AI techniques that go far beyond the powers of standard modeling to prioritize the experiments that show the most promise. In this way, translational medicine is helping produce better, more targeted therapies that can reach more patients in need.

What are the 3 types of translational research?

There are 3 primary types of translational research, which fall into the following broad categories: benchside, bedside, and community. These translational research types are further classified according to their phase of translation.


  • T0: Basic science research (pre-clinical or animal studies)
    This translational research tests findings from basic research for clinical significance or impact, and yields knowledge about potential human interventions.


  • T1: Translation to humans (phase 1 clinical trials)
    This translational research tests new biomedical interventions in a small group of people to determine efficacy and safety (i.e. safe dosage; side effects).

  • T2: Translation to patients (phases 2 & 3 of clinical trials)
    This translational research tests new interventions in broader groups of people in controlled environments in order to provide the foundation for clinical application and evidence-based guidelines.


  • T3: Translation to practice (phase 4 & clinical outcomes research)
    This translational research finds different ways of applying recommendations or guidelines in general practice, yielding insights about how interventions are working in real-world settings.
  • T4: Translation to community (phase 5 & population-level outcomes research)
    This translational research looks at factors and interventions that influence the health of populations.

7 Principles for Closing the Translational Gap

According to the National Center for Advancing Translational Sciences (NCATS), translational medicine relies on these 7 scientific and operational principles, which can be used as tips to help guide researchers and drug developers who are working to improve translatability.

  1. Prioritize initiatives the address unmet needs
    Look to pursue initiatives that will contribute new research or solutions in under-investigated areas, like currently untreatable diseases.

  2. Produce crosscutting solutions for common and persistent challenges
    Address challenges through generalizable solutions, particularly those that can reach across multiple, disparate research areas, diseases and conditions. For example, problem solving for common R&D roadblocks.

  3. Emphasize creativity and innovation
    Increase the impact of your research by investing in innovations that can amplify and transform entrenched research methods and processes. AI-enabled technologies, for example, have demonstrated their ability to accelerate discovery through optimization of traditional screening systems, also serving to reduce late-stage drug attrition.

  4. Leverage cross-disciplinary team science
    Pool expertise across disciplines to produce more comprehensive, holistic research that not only aids translatability, but which also produces applications with more real-world relevance and potential.

  5. Enhance the efficiency and speed of translational research
    Accelerate the pace of research by improving and streamlining essential work and operational functions. For example, enabling rapid redirection of resources after a failure is detected.

  6. Utilize boundary-crossing partnerships
    Use cross-disciplinary research teams and cross-agency partnerships to advance translation. For example, incentivizing collaboration or designing science policy and/or funding opportunities that support cross-disciplinary relationships.
  1. Use bold and rigorous research approaches
    Embrace risk-taking and challenge the traditional research ecosystem by developing ambitious approaches that address even the most complex problems in translational research.

Closing the translational gap in drug R&D will mean developing solutions that directly address its most long standing roadblocks. While very real progress has been made toward closing the translational gap using AI-based tools, barriers remain, particularly when it comes to clinical implementation. However, as innovations in AI tech continues to transform translational medicine into a more predictive science, we can expect to see more novel therapies making it from bench to bedside.

VeriSIM Life’s BIOiSIM platform and unique Translational Index™️ technology are helping close the translational gap in drug R&D. Contact us to find out how, and check out our publications for peer-reviewed research, white papers and a range of resources on topics related to AI-powered drug development.

Learn more about VeriSIM Life’s BIOiSIM platform and unique Translational Index™️ technology.