Solving The Data Problem For AI In Drug Discovery

While artificial intelligence has proven its value in drug discovery, for most companies, the power of their AI systems is only as strong as the data those systems are trained on. However, stakeholders – from individual companies to consortiums and service vendors -- are finding creative approaches to overcome the so-called data problem and strengthen their AI models.  

AI Systems Are Limited By The Size Of Data Training Sets
• Source: Shutterstock

AI-driven drug discovery platforms have been yielding impressive results. The first completely AI-driven drug is now in clinical trials and AI systems are being used to optimize the safety and efficacy of existing molecules. However, the performance of AI models remains limited by the amount of data they take in – the so-called data problem. Moreover, as AI models become more complex, their hunger for data becomes increasingly insatiable.

The problem may not last for long, however, as industry is finding ways to increase the amount of data available to individual AI platforms.

Read the full article – start your free trial today!

Join thousands of industry professionals who rely on In Vivo for daily insights

  • Start your 7-day free trial
  • Explore trusted news, analysis, and insights
  • Access comprehensive global coverage
  • Enjoy instant access – no credit card required

More from Innovation

Leaders At The Frontier: Conversations From SynBioBeta 2025

 
• By 

Mini-profiles of five synthetic biology companies and their leaders from SynBioBeta 2025 reveal how AI integration, data-driven platforms and interdisciplinary teams are revolutionizing drug discovery and manufacturing.

From IVF Failure To Fertility Breakthroughs: Freya’s Microbiome Mission

 
• By 

Named after the Norse goddess of fertility, Freya Biosciences is mapping the reproductive microbiome with a host of women's health indications as the final destination.

ML-Assisted Genetic Risk Score Predicts GLP-1 Adverse Events

 
• By 

Phenomix Science presented new data at Digestive Disease Week 2025 showing its machine learning-assisted genetic risk score can predict nausea and side effects from GLP-1 receptor agonists, aiding personalized obesity treatment.

The pre|CISION Approach: How Avacta Is Making Toxic Cancer Drugs Safe And More Effective

 
• By 

Avacta's approach to drug delivery is showing how 'masked' chemotherapy can dramatically improve safety profiles while maintaining or enhancing efficacy where it matters most.

More from In Vivo

US Health System Redesign Critical, NAM’s Medical Experts Warn Trump Government

 
• By 

The whirlwind back-and-forth on US tariffs and Robert F. Kennedy jr.’s plans to deregulate health care have become all-preoccupying, but the National Academy of Medicine was first to set out President Trump’s health administration priorities.

Podcast: “Powerful Yet Unexplored”: Commit Biologics Tackles The Complement System

 

Mikkel Wandahl Pederson, CEO and chief scientific officer at Commit Biologics, discussed the company’s mission to harness the powerful complement system for the treatment of serious diseases.

ML-Assisted Genetic Risk Score Predicts GLP-1 Adverse Events

 
• By 

Phenomix Science presented new data at Digestive Disease Week 2025 showing its machine learning-assisted genetic risk score can predict nausea and side effects from GLP-1 receptor agonists, aiding personalized obesity treatment.