June 30, 2022

Medical Trend

Medical News and Medical Resources

Artificial intelligence discovered new mechanism of idiopathic pulmonary fibrosis drugs

Artificial intelligence discovered new mechanism of idiopathic pulmonary fibrosis drugs



 

Artificial intelligence discovered new mechanism of idiopathic pulmonary fibrosis drugs.   

 

For the first time in the world! Artificial intelligence discovers new mechanism of idiopathic pulmonary fibrosis drugs.

 

Insilico Medicine, a leader in the development of artificial intelligence drugs, recently announced that it has used artificial intelligence to discover a new mechanism for idiopathic pulmonary fibrosis drugs for the first time in the world. This is a landmark event on a global scale.

 

On March 2, Insilico Medicine joined hands with two top investment institutions-Qiming Venture Capital and Innovation Works, to jointly grasp the industrial pulse from “AI + medical” to “digital medical” and share the latest and most professional industry insights.

 

Artificial intelligence discovered new mechanism of idiopathic pulmonary fibrosis drugs

 

 

How does AI make medicine?

Generally speaking, the development of a new drug needs to go through the stages of drug target determination, lead compound screening, lead compound optimization, and clinical trials.

In terms of time cost, the time to market for a new drug is more than 10 years. In terms of funding, Tufts Drug Development and Research Center once gave a figure of 2.6 billion US dollars.

But the end result is that only 10% of drug candidates can enter the market after high human and financial resources, and 90% of projects aborted.

Ren Feng, Chief Scientific Officer of Insilico, explained the detailed process of IPF new drug development:

 

1. Find the target.

Insilico uses the PandaOmics target discovery system to score the complex genes and pathways published in Nature Communications, and obtains relevant targets through deep feature selection, causal reasoning, and de novo pathway reconstruction.

Target novelty and disease association scores are evaluated by a natural language processing (NLP) engine that analyzes data from millions of data files, including patents, research publications, research funding, and clinical trial databases.

As a result, PandaOmics found 20 targets for verification, narrowed it down to a new intracellular target, and further analyzed it.

 

2. Select the compound and test the safety. Insilico’s artificial intelligence chemical generation system

Chemistry42 automatically generates molecular structures with appropriate physicochemical properties and high druggability.

This time, Chemistry42 has designed a library of small molecules that bind to the new intracellular targets discovered by PandaOmics and are validated.

 

3. Select preclinical compounds.

After continuous design, synthesis, evaluation and optimization, clinical candidate compounds are finally confirmed.

Fourth, enter the clinical trial stage.

Insilico said that it is currently undergoing IND application trials, and the goal is to put this drug in the clinical phase in 2022.

 

On the whole, from target discovery to the invention of pre-clinical drug candidates, Insilico achieved target discovery, molecular generation and verification through traditional experiments in less than 18 months, confirming the efficacy and safety evaluation of IPF in animals.

The total cost is approximately US$1.8 million, and the total cost of other fibrotic diseases research is approximately US$800,000. No more than 80 small molecule compounds have been synthesized and tested.

 

A report by Tech Emergence predicts that artificial intelligence can increase the success rate of new drug development from 12% to 14%, which can save the biopharmaceutical industry billions of dollars.

 

 

The artificial intelligence drug design platform is complete and comprehensive

It is understood that the Insilico Medicine team has spent several years building and integrating hundreds of artificial intelligence models, each of which is responsible for a specific task, and integrates them on a platform that can generate hypotheses and select targets , Generate compounds and predict the results of clinical trials.

It is understood that this is the most complete and comprehensive artificial intelligence drug design platform on the market.

 

Starting from 2016-2017, AI pharmaceuticals began to attract the attention of pharmaceutical companies and technology giants.

As we all know, the development of artificial intelligence relies on data, especially high-quality large data sets. And each step of the drug discovery process will generate a lot of data, these data have laid the foundation for the development of modern artificial intelligence technology.

 

Now, the role of deep learning models and natural language processing technologies in modeling large complex multi-dimensional data sets such as genomics, proteomics, clinical data, target structure data and unstructured text cannot be underestimated.

 

 

 

(source:internet, reference only)


Disclaimer of medicaltrend.org