Behind Insilico Medicine's Potential First-in-Class AI-Discovered and AI-Designed Drug for Idiopathic Pulmonary Fibrosis
A Phase 1 Breakthrough in AI Drug Discovery
There are very few truly novel drugs on the market – and the number is falling.
In 2022, just 37 new drugs were approved by the FDA, compared to 50 in 2021, and 53 in 2020. Many of the drugs approved were small molecules that modulated the function of well-known molecular targets. Discovering a novel molecule for a novel target for a broad disease indication is extremely rare.
There are a number of obstacles keeping new drug discoveries from advancing. The process to bring a new drug to market is incredibly complex — relying on a deep expertise of biological and chemical interactions. It is also expensive, to the tune of billions of dollars per drug, and the process can take a decade or more to come to fruition. And most of these drugs in development – some 90% of them – will fail, making it one of the riskiest endeavors out there.

Breakthrough 1
Using AI to Discover a New Target and New Drug for IPF
But these obstacles in traditional drug discovery have also presented a major opportunity for the introduction of artificial intelligence (AI) to bring new speed and efficiency to the process. And in 2020, Insilico Medicine used its end-to-end Pharma.AI platform — including its AI target-discovery engine, PandaOmics, and AI compound-generating engine Chemistry42, built on years of modeling large biological, chemical, and textual datasets, to discover a new target relevant for a broad range of fibrosis indications. Insilico used this newly discovered target as the basis for the structure-based design of a first-in-class novel small molecule inhibitor.

To achieve the preclinical candidate, Insilico's Pharma.AI designed and synthesized under 80 molecules and achieved unprecedented hit rates with several molecules at the preclinical candidate level. The small molecule selected showed outstanding efficacy for idiopathic pulmonary fibrosis and a good safety profile that led to its nomination as a preclinical drug candidate in December 2020 for IND-enabling studies.

It was a precedent among any existing AI systems at that time to achieve simultaneous success in target discovery and drug candidate generation for a broad indication such as fibrosis, and a historical proof of concept for the ability of deep learning to link biology and chemistry in an integral workflow.

Breakthrough 2
Advancing to Phase 1
in Under 30 Months
In February 2022, Insilico Medicine announced yet another milestone – the Company had brought its novel AI-discovered and AI-designed IPF drug to Phase 1 trials in record time, advancing from start to Phase 1 in under 30 months and for significantly less cost than traditional drug discovery.

Insilico's AI system, trained on disease and aging, had zeroed in on a compound that demonstrated highly promising results in multiple preclinical studies including in vitro biological studies, pharmacokinetic and safety studies. The compound also improved myofibroblast activation, a contributor to the development of fibrosis with a novel and was shown to have potential relevance in a broad range of fibrotic indications, not just IPF.

With these favorable findings, Insilico was able to advance the potentially first-in-class IPF drug to first-in-human studies with 8 healthy volunteers in Australia, successfully demonstrating clinical proof-of-concept.

The following Phase 1 clinical trial with 80 healthy volunteers was a double-blind, placebo controlled, single and multiple ascending dose study to evaluate the safety, tolerability, and pharmacokinetic of the compound. In the study, the healthy volunteers were enrolled in 10 cohorts consisting of 5 single ascending dose and 5 multiple ascending dose cohorts. The clinical study sought to determine maximum tolerated dose for a drug requiring regular peroral administration for the entire lifetime with very high safety requirements and establish dosage recommendations for future Phase 2 studies.

Breakthrough 3
Favorable Topline Results for Phase 1 Trial of AI-Discovered and AI-Designed Novel Drug
On Jan. 10, Insilico Medicine announced yet another milestone for its lead IPF drug and for the AI drug discovery industry – positive topline results for Phase 1 clinical trials of its novel drug for a novel target discovered and designed using AI.

The INS018_055 Phase 1 study was a randomized, double-blind, placebo-controlled Phase 1 study featured a single ascending dose (SAD) and multiple ascending dose (MAD) to evaluate the safety, tolerability, PK, food effects, and drug-drug interaction (DDI) potential of INS018_055 in 78 healthy volunteers in New Zealand (NZ). Enrollment in Insilico Medicine's Phase 1 clinical trial was initiated in Feb. 2022 and the last subject follow-up visit was completed in Nov. 2022. The safety and PK data collection has been completed for both SAD and MAD cohorts.

The observed human PK of INS018_055 in healthy volunteers was in line with the Company's preclinical modeling with no significant accumulation after 7 days and exhibited a favorable PK profile. INS018_055 was generally safe and well tolerated by healthy volunteers in the study. There were no deaths or SAEs reported during the study.

Pending FDA approval, the Company expects to initiate Phase 2a studies in IPF patients in early 2023.

This latest breakthrough is further validation of Insilico's Pharma.AI platform to identify new targets and design new therapeutics that can address diseases with high unmet need. Patients with IPF are eagerly awaiting new therapeutic options as there are few treatments available for this debilitating and chronic scarring lung disease characterized by a progressive and irreversible decline in lung function. The disease affects around 5 million people globally and has a median survival of 3 to 4 years.
The positive Phase I data enable the further evaluation of the drug efficacy in IPF patients in the Phase II trial. In addition, the continued progression of INS018_055 demonstrates again the power of our AI platform in drug discovery and development.
Feng Ren, PhD
Co-CEO and Chief Scientific Officer of Insilico Medicine
Stay tuned, follow us on social media!