Interview
How do you define the mission and key differentiators of Intelligencia AI within the pharmaceutical and life sciences industries?
Inherently long. Incredibly costly. Low success rates.
These are three common descriptors associated with the drug development process. We’ve all heard the numbers: a decade from early R&D to approval, with hundreds of millions to more than two billion dollars invested in bringing a drug to market. These numbers are staggering by themselves, but what makes the situation even worse is the high risk associated with drug development: approximately 90% of the drugs in Phase 1 clinical trials never make it through approval.
While we have seen remarkable technical advances in research and development and the science of drugs over the last few decades, drug development has lagged behind, becoming slower and more expensive.
There is even a “law” for it. Eroom’s Law (Moore’s law spelled backwards) states that the cost of developing a new drug doubles roughly every nine years, despite technological advancements. Since time and cost are extremely hard to change, at Intelligencia AI, we set out to optimize the one lever we have some level of control over: risk.
The questions that drove the founding of our company and the evident need for a new approach:
● How can we de-risk drug development?
● How can we help pharmaceutical companies identify the winners early and, just as importantly, weed out the losers quickly?
● How can we lower that 90% failure rate by focusing on the most promising candidates?
De-risking drug development is our mission, a lofty yet laser-focused purpose we’re all aligned on. What sets us apart from other companies working in the drug development space is the thoroughness and dedication with which we execute our mission. We chose artificial intelligence as the driving engine behind our solutions before the AI hype started. We realized, even then, that AI is just a tool that will only work well if the foundation is solid.
The foundation in our case is comprehensive and highly curated clinical and biological data, along with our proprietary ontologies that provide granularity across multiple biological entities, such as indications, targets, and drugs.
Inherently long. Incredibly costly. Low success rates.
These are three common descriptors associated with the drug development process. We’ve all heard the numbers: a decade from early R&D to approval, with hundreds of millions to more than two billion dollars invested in bringing a drug to market. These numbers are staggering by themselves, but what makes the situation even worse is the high risk associated with drug development: approximately 90% of the drugs in Phase 1 clinical trials never make it through approval.
While we have seen remarkable technical advances in research and development and the science of drugs over the last few decades, drug development has lagged behind, becoming slower and more expensive.
There is even a “law” for it. Eroom’s Law (Moore’s law spelled backwards) states that the cost of developing a new drug doubles roughly every nine years, despite technological advancements. Since time and cost are extremely hard to change, at Intelligencia AI, we set out to optimize the one lever we have some level of control over: risk.
The questions that drove the founding of our company and the evident need for a new approach:
● How can we de-risk drug development?
● How can we help pharmaceutical companies identify the winners early and, just as importantly, weed out the losers quickly?
● How can we lower that 90% failure rate by focusing on the most promising candidates?
De-risking drug development is our mission, a lofty yet laser-focused purpose we’re all aligned on. What sets us apart from other companies working in the drug development space is the thoroughness and dedication with which we execute our mission. We chose artificial intelligence as the driving engine behind our solutions before the AI hype started. We realized, even then, that AI is just a tool that will only work well if the foundation is solid.
The foundation in our case is comprehensive and highly curated clinical and biological data, along with our proprietary ontologies that provide granularity across multiple biological entities, such as indications, targets, and drugs.
The importance of pristine data curation cannot be overstated. AI is very powerful: it can create valuable insights in a few seconds, but it can also generate complete nonsense if it is not trained correctly. Curated data is the fuel that feeds the machine.
Our data is unrivaled in the industry in its depth and quality. We built the foundation with the utmost care and have layered solutions that support drug developers making important decisions, such as assessing the probability of regulatory and technical success (PTRS).
Could you elaborate on how the growing trend of artificial intelligence is currently impacting pharmaceutical companies, and what tangible results can they expect to see?
Our data is unrivaled in the industry in its depth and quality. We built the foundation with the utmost care and have layered solutions that support drug developers making important decisions, such as assessing the probability of regulatory and technical success (PTRS).
Could you elaborate on how the growing trend of artificial intelligence is currently impacting pharmaceutical companies, and what tangible results can they expect to see?
There aren’t enough hours in the day to tackle this, so I selected what I believe are the top three areas of application of AI in the pharmaceutical industry.
Let’s start at the beginning of the drug development journey: the discovery of novel molecules with desired biological and ADMET properties. Deep learning or reinforcement learning frameworks can enhance this process, making it faster and enabling the design of molecules from the start to be more effective and avoid toxicity issues. This approach continues to mature, but the first AI-designed drugs have already reached clinical trials. This is a critically important application because feeding better drug candidates into the pipeline from the start increases the chances of success.
Secondly, I want to mention clinical trial design and optimization. Clinical trials account for between 50% and 70% of total drug development costs, so it’s easy to understand the importance of improvements. AI can help by simulating trial scenarios, optimizing protocol design, predicting enrollment bottlenecks, and selecting sites with the highest performance. Trial delays and protocol changes are among the most costly issues in clinical development; AI helps proactively prevent these.
Risk assessment, the application Intelligencia AI focuses on, unsurprisingly, also makes it into my top three list.
What makes reliable, AI-driven, objective, and fast risk assessment so powerful is that it allows drug developers to use it as a metric they apply repeatedly throughout the entire development pipeline. Traditionally, assessing the probability of a drug’s success was done by selected domain experts; these processes were time-consuming, expensive, and subjective, and were used sparingly. Now, with the patented Intelligencia Portfolio Optimizer™, drug developers can frequently assess the PTRS based on new information, examine the ever-changing competitive landscape, and better inform and adjust their decisions.
What are some of the challenges you’ve encountered in the industry, and how have your solutions effectively addressed those challenges?
We address the challenge of risk and uncertainty in decision-making in drug development. Now, we did not invent risk assessment; the process existed before, but it was expensive, slow, and subjective, driven by the experience of a select few and based on very incomplete data. We took that outdated and frankly flawed process. We built our flagship solution and offering of AI-driven probability of technical and regulatory success (PTRS) assessment on a solid foundation of data and customized algorithms for analyzing that data, performing advanced pattern recognition to generate real-time, relevant and actionable insights that users can access through a convenient SaaS platform.
I mentioned our data-driven approach earlier, and I’d like to dive a bit deeper. We transform scattered, unstructured, and complex clinical data into clear insights that drug developers can confidently base their decisions on. We not only connect but also enrich information from a wide range of trusted sources, including clinicaltrials.gov, NIH, UniProt, scientific publications, and conference abstracts, among many others, to deliver detailed, up-to-date insights that help teams predict outcomes.
The SaaS platform aspect is also very critical: our users don’t need to be data scientists or AI experts; they can access, filter, track history and changes, create notifications, and dashboards online through an intuitive user interface.
In short, we have eliminated time, cost, hassle and subjectivity from risk assessment in drug development, transforming a formerly inefficient process into one that users can perform quickly and reliably, with access to real-time data when needed.
In such a rapidly evolving sector, how does your team remain at the forefront of emerging trends and anticipate the evolving needs of your clients?
Let’s start at the beginning of the drug development journey: the discovery of novel molecules with desired biological and ADMET properties. Deep learning or reinforcement learning frameworks can enhance this process, making it faster and enabling the design of molecules from the start to be more effective and avoid toxicity issues. This approach continues to mature, but the first AI-designed drugs have already reached clinical trials. This is a critically important application because feeding better drug candidates into the pipeline from the start increases the chances of success.
Secondly, I want to mention clinical trial design and optimization. Clinical trials account for between 50% and 70% of total drug development costs, so it’s easy to understand the importance of improvements. AI can help by simulating trial scenarios, optimizing protocol design, predicting enrollment bottlenecks, and selecting sites with the highest performance. Trial delays and protocol changes are among the most costly issues in clinical development; AI helps proactively prevent these.
Risk assessment, the application Intelligencia AI focuses on, unsurprisingly, also makes it into my top three list.
What makes reliable, AI-driven, objective, and fast risk assessment so powerful is that it allows drug developers to use it as a metric they apply repeatedly throughout the entire development pipeline. Traditionally, assessing the probability of a drug’s success was done by selected domain experts; these processes were time-consuming, expensive, and subjective, and were used sparingly. Now, with the patented Intelligencia Portfolio Optimizer™, drug developers can frequently assess the PTRS based on new information, examine the ever-changing competitive landscape, and better inform and adjust their decisions.
What are some of the challenges you’ve encountered in the industry, and how have your solutions effectively addressed those challenges?
We address the challenge of risk and uncertainty in decision-making in drug development. Now, we did not invent risk assessment; the process existed before, but it was expensive, slow, and subjective, driven by the experience of a select few and based on very incomplete data. We took that outdated and frankly flawed process. We built our flagship solution and offering of AI-driven probability of technical and regulatory success (PTRS) assessment on a solid foundation of data and customized algorithms for analyzing that data, performing advanced pattern recognition to generate real-time, relevant and actionable insights that users can access through a convenient SaaS platform.
I mentioned our data-driven approach earlier, and I’d like to dive a bit deeper. We transform scattered, unstructured, and complex clinical data into clear insights that drug developers can confidently base their decisions on. We not only connect but also enrich information from a wide range of trusted sources, including clinicaltrials.gov, NIH, UniProt, scientific publications, and conference abstracts, among many others, to deliver detailed, up-to-date insights that help teams predict outcomes.
The SaaS platform aspect is also very critical: our users don’t need to be data scientists or AI experts; they can access, filter, track history and changes, create notifications, and dashboards online through an intuitive user interface.
In short, we have eliminated time, cost, hassle and subjectivity from risk assessment in drug development, transforming a formerly inefficient process into one that users can perform quickly and reliably, with access to real-time data when needed.
In such a rapidly evolving sector, how does your team remain at the forefront of emerging trends and anticipate the evolving needs of your clients?
One of our core company values is to raise the bar. Excellence is not a destination for us, but a continuous journey of improvement. Therefore, we are committed to staying at the forefront of technological development. We have a diverse team of exceptional professionals who follow what’s happening from both a scientific and a business operations standpoint. The end goal is continuous innovation to keep the pharmaceutical industry equipped with the right solution it needs.
We are currently working on integrating generative AI approaches into our processes. A bit further out, agentic AI will play an important role. It won’t replace the foundational models behind PTRS, but it can amplify their utility by making predictions more accessible, interpretable and actionable across the pharma development lifecycle.
However, technology is only a means to an end, and to understand that end, we must have a deep understanding of the challenges and needs of our customers. Seeking constant dialogue and exchange of ideas with our customers and the broader drug development community is at least as important as the latest technological advances.
That’s why you have seen us at so many conferences over the last two years. We want to be seen, but just as much we want to learn and understand, connect with professionals, and have conversations so we can solve real problems using the latest tools.
Intelligencia AI’s solutions appear to be highly tailored to the pharmaceutical sector. How do you envision the evolution of your company over the next 5 to 10 years?
We are currently working on integrating generative AI approaches into our processes. A bit further out, agentic AI will play an important role. It won’t replace the foundational models behind PTRS, but it can amplify their utility by making predictions more accessible, interpretable and actionable across the pharma development lifecycle.
However, technology is only a means to an end, and to understand that end, we must have a deep understanding of the challenges and needs of our customers. Seeking constant dialogue and exchange of ideas with our customers and the broader drug development community is at least as important as the latest technological advances.
That’s why you have seen us at so many conferences over the last two years. We want to be seen, but just as much we want to learn and understand, connect with professionals, and have conversations so we can solve real problems using the latest tools.
Intelligencia AI’s solutions appear to be highly tailored to the pharmaceutical sector. How do you envision the evolution of your company over the next 5 to 10 years?
Without venturing into the realm of utter speculation, we have built an industry-leading foundation, both in terms of data and AI. We will continue to develop the gold standard solution that drug developers rely on to invest in the most promising drugs and identify the quickest way to market. Ultimately, this will benefit the patients by ensuring they have access to the treatments they need sooner.
Our job is never done, as we continually seek to add new functionalities and expand our platform to meet the industry’s evolving needs. For example, our platform is an excellent fit for competitive intelligence, and our database can also streamline target product profiles (TPPs) and support decision-making processes throughout the entire drug development process. We will always have an open ear for our customers and will continue to focus on creating solutions that make their drug development process smoother and faster.
At a high level, our core competency is leveraging data and AI to make more accurate predictions. PTRS is the first area where we applied these capabilities, but there are many others we can tackle in and beyond drug development.
That’s where I see Intelligencia AI going: evolving from a PTRS pioneer into a broader end-to-end intelligence engine that helps life sciences companies make high-stakes decisions with greater speed, clarity, and confidence. Wherever uncertainty slows innovation, we intend to be the platform that turns data into direction.
Our job is never done, as we continually seek to add new functionalities and expand our platform to meet the industry’s evolving needs. For example, our platform is an excellent fit for competitive intelligence, and our database can also streamline target product profiles (TPPs) and support decision-making processes throughout the entire drug development process. We will always have an open ear for our customers and will continue to focus on creating solutions that make their drug development process smoother and faster.
At a high level, our core competency is leveraging data and AI to make more accurate predictions. PTRS is the first area where we applied these capabilities, but there are many others we can tackle in and beyond drug development.
That’s where I see Intelligencia AI going: evolving from a PTRS pioneer into a broader end-to-end intelligence engine that helps life sciences companies make high-stakes decisions with greater speed, clarity, and confidence. Wherever uncertainty slows innovation, we intend to be the platform that turns data into direction.
