‘The opportunities for AI to revolutionize the pharmaceutical industry are clear’: Report

By Melissa Fassbender

- Last updated on GMT

(Image: Getty/Jirsak)
(Image: Getty/Jirsak)

Related tags Artificial intelligence Preclinical services Research Small molecule

Researchers are using artificial intelligence to catalyze drug discovery and preclinical drug development - improving predictive models to guide efficient design and optimizing multi-drug regimens, as two recent examples.

A recent report​ published by PreScouter – a Chicago-based research intelligence company – focused on the applications of artificial intelligence (AI) in drug discovery and development.

In the report, Dr. Charles Wright, PreScouter project architect for the health care and life sciences industry, outlined three common challenges faced by all pharmaceutical companies: Timelines of about 15 years, costs in excess of $1bn, and a minuscule rate of success.

“It’s estimated that 1 in 10 small molecule projects become candidates for clinical trials,”​ said Wright, noting that millions of compounds are screened before a viable candidate is found. This, and only about one in 10 of those compounds will pass successfully through clinical trials.

“AI has the potential to revolutionize the current timescale and scope of drug discovery and development,”​ Wright told us.

He gave the example that by moving drug screening from the bench to a virtual lab and by removing biases based upon knowledge of structures of existing molecules.

Companies are currently applying AI to this process in areas including generating novel drug candidates, understanding disease mechanisms, as well as aggregating and synthesizing information.

Wright said, “Technical, ethical, and regulatory challenges remain, but the opportunities for AI to revolutionize the pharmaceutical industry are clear.”

Most surprising? The current state of development, Wright said.

“Although AI is still an emerging technology within this industry, due to a very active start-up and research ecosystem and intense interest from established pharmaceutical companies and investors, we are already moving past the proof-of-concept stage,”​ he explained.

“AI has started to generate real-world impacts, with novel drug candidates identified through this approach starting to successfully move through the development pipeline.” 


In September, Optibrium and Intellegens announced a partnership that combines Intellegens’ proprietary AI technology with Optibrium’s predictive modeling and compound design capabilities.

Per the collaboration, Optibrium’s clients will gain access to deep learning methods that the company said extend and improve predictive models to guide efficient design and selection of high-quality drug candidates.

In turn, by using Intellegens’ Alchemite technology, the partnership will create a “next generation”​ predictive modeling platform, according to the companies.

The platform is said to help inform more accurate predictions to enable better decision-making as it pertains to the optimization of compounds.

The deep learning tool can simultaneously model multiple endpoints to gain more information from available data, compared to traditional quantitative structure-activity relationship (SAR) models, according to the company.


A translational research team at The National University of Singapore (NUS) recently harnessed AI to better treat a patient with advanced cancer. 

The platform, CURATE.AI, enabled researchers to halt disease progression, marking a significant step forward in personalized medicine.

The clinical study involved a patient with metastatic castration-resistant prostate cancer (MCRPC) who was given a novel drug combination consisting of investigational drug ZEN-3694 and enzalutamide, an approved prostate cancer drug.

CURATE.AI was used to continuously identify the optimal doses of each drug.

Study lead Professor Dean Ho, director of the Singapore Institute for Neurotechnology (SINAPSE) at NUS said the clinical study has shown that dosing can affect the efficacy and safety of the treatment.

“A patient's clinical profile changes over time. The unique ability for CURATE.AI to rapidly identify the drug doses that result in the best possible treatment outcomes allows for actionable, and perpetually optimised personalised medicine,"​ said Ho.

The CURATE.AI platform uses the patient's own clinical data, including their drug doses and corresponding changes to tumour sizes or levels of cancer biomarkers in the blood. This data is then used to calibrate a unique treatment response.

Ho said, "Using CURATE.AI to dynamically modify drug doses and successfully treat a metastatic cancer patient represents a landmark breakthrough for the use of AI to truly personalise patient care.”

The researcher’s work is expected to dramatically improve response rates for all combination therapies being developed for oncology, as well as for other diseases, Ho said. He also expects the platform will “markedly reduce the costs of drug development.”

The first platform generation was previously done in the clinic for single drug optimization in post-transplant immunosuppression, though it is applicable to all diseases and patients.

According to the researchers, the new study demonstrates that CURATE.AI can optimise multi-drug regimens. Multiple clinical trials are underway using the platform to guide combination therapy for oncology and other applications, such as post-transplant immunosuppression.

In Singapore, patient recruitment for additional oncology trials has been approved.

The CURATE.AI team expects to deploy the platform broadly. 

Related news

Show more

Related products

show more

Saama accelerates data review processes

Saama accelerates data review processes

Content provided by Saama | 25-Mar-2024 | Infographic

In this new infographic, learn how Saama accelerates data review processes. Only Saama has AI/ML models trained for life sciences on over 300 million data...

More Data, More Insights, More Progress

More Data, More Insights, More Progress

Content provided by Saama | 04-Mar-2024 | Case Study

The sponsor’s clinical development team needed a flexible solution to quickly visualize patient and site data in a single location

Using Define-XML to build more efficient studies

Using Define-XML to build more efficient studies

Content provided by Formedix | 14-Nov-2023 | White Paper

It is commonly thought that Define-XML is simply a dataset descriptor: a way to document what datasets look like, including the names and labels of datasets...

Related suppliers

Follow us