Artificial intelligence-driven prediction and validation of blood–brain barrier permeability and absorption, distribution, metabolism, excretion profiles in natural product research laboratory compounds
2024

AI Predictions for Blood-Brain Barrier Permeability in Natural Products

Sample size: 2461 publication Evidence: moderate

Author Information

Author(s): Yang Jai-Sing, Huang Eddie TC, Liao Ken YK, Bau Da-Tian, Tsai Shih-Chang, Chen Chao-Jung, Chen Kuan-Wen, Liu Ting-Yuan, Chiu Yu-Jen, Tsai Fuu-Jen

Primary Institution: China Medical University Hospital

Hypothesis

The study aims to investigate the pharmacokinetic ADME properties and BBB permeability coefficients of NPRL compounds.

Conclusion

AI prediction models have effectively identified the potential ADME characteristics of various compounds.

Supporting Evidence

  • 4956 compounds could cross the blood-brain barrier (BBB+).
  • 2461 BBB+ and 2184 BBB− compounds were used in the NPRL-CMUH dataset for testing.
  • The permeability coefficient of temozolomide (TMZ) and 21 other BBB + compounds exceeded 10 × 10−7 cm/s.
  • Computer-based predictions for the NPRL of CMUH compounds regarding their capacity to traverse the BBB are verified by the findings.

Takeaway

The study used computers to guess which natural products can get through the brain's protective barrier, and it found that many can do so safely.

Methodology

A combined model using a transformer-based MegaMolBART encoder and XGBoost classifier was employed to predict BBB permeability, along with in vitro assays to evaluate cytotoxic effects.

Limitations

The study's predictions need further validation through in vivo research to fully understand the mechanisms of action.

Statistical Information

P-Value

p<0.001

Statistical Significance

p<0.001

Digital Object Identifier (DOI)

10.37796/2211-8039.1474

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication