AI Reduces Time and Costs for Drug Discovery

The drug discovery process is time-consuming and expensive. Insilico Medicine is using an AI-powered platform to reduce researchers’ time and costs during drug discovery and the preclinical trial phase.

Article Key

Image credit: Insilico Medicine

Hong Kong and New York based Insilico Medicine created a three-part artificial intelligence-based platform to streamline pharmaceutical research. On average, the traditional path from target drug discovery to market takes ten years and costs more than $2 billion. The Insilico Medicine platform, known as Pharma.AI, allows researchers to reduce the time and cost of drug discovery while maintaining a high level of clinical efficacy, increasing the overall chance of successful clinical trials.  

Pharma.AI consists of three AI-engines, each designed for a specific step in drug research. PandaOmics, Chemistry42, and InClinico. Step one of the platform is PandaOmics. PandaOmics includes AI algorithms that analyze natural language processing and OMICs data, which includes various levels of biological information, to determine what targets, or molecules, best connect with researchers’ disease. Researchers can use their own OMICs data, or they can use public data sets available within the Pharma.AI platform. 

IPF research timeline

Image credit: Insilico Medicine

End-to-End AI

PandaOmics gives each target an AI-calculated score and then suggests possible hypotheses researchers can use to build clinical trials. Typically, this step is time-consuming. PandaOmics reduces the time spent on target research from years to days, according to the company. Insilico Medicine used PandaOmics to discover a target for idiopathic pulmonary fibrosis (IPF) in only seven days. 

Following the discovery of the target, Insilico Medicine used Chemistry42, the second step in Pharma.AI, to develop a drug molecule for use in clinical testing. Chemistry42 is a scalable, automated machine learning molecular design platform that determines drug-like molecules for use in clinical trials.

In 2021, Insilico Medicine began the first human study of its AI-derived drug for IPF. The whole process up until that point took less than 18 months and cost about $2.5 million, a fraction of the time and cost of a traditional drug journey. 

The final step of Insilico Medicine’s end-to-end AI-powered drug discovery platform is InClinico. InClinico uses AI to analyze data from the target, the disease, and the trial. With that data analysis, InClinico can identify weak points of a clinical trial’s design, predict the success rate of the clinical trial, and suggest alternative trial designs to increase the project’s efficacy. 

Traditionally, few drugs make it to the clinical trial phase, and even fewer are successful. AI has the potential to change this, supporting medical advancements and the creation of new, and often necessary, drugs.  

IPF drug research graphic

Image credit: Insilico Medicine

AI Aids COVID-19 Research

Amid the pandemic, Insilico Medicine, with the help of Intel technology, used Pharma.AI, known at the time as COVIDomic, to support COVID-19 research. COVIDomic uses Intel® Xeon® processors to quickly examine large amounts of data. 

“Analyzing massive amounts of data–quickly–across geographies and data sets is essential for gaining insights into how COVID-19 affects people across the world,” notes Rick Echevarria, Intel Vice President, Sales, Marketing, and Communications Group in a statement. “Intel computing power enables AI that can help researchers in the fight against COVID-19.”

The cloud-based COVIDomic platform used bioinformatics and AI to analyze health data from COVID-19 patients. By assessing blood test results and transcriptomic sequencing of lung fluid, COVIDomic was able to determine the origin and severity of COVID-19 strains and other viral diseases. Recently, the platform discovered a novel preclinical candidate targeting 3C-like (3CL) protease inhibitors that could be used to treat COVID-19 patients. 

Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries.

Find Intel® IoT Market Ready Solutions

Search the Intel® IoT partner ecosystem and discover 130+ end-to-end IoT solutions.

Become a Member of the Intel® Partner Alliance

If you are delivering repeatable and scalable IoT offerings using Intel technology, the Intel® Partner Alliance program gives you more opportunities to build your business. Get started.