Innovate

The ICH M7(R2) Guideline (2023) continues to recommend the bacterial reverse mutation assay (Ames test), conducted in accordance with OECD 471, as a primary tool for assessing the mutagenic potential of pharmaceutical impurities, including nitrosamines. While the Ames test is generally predictive of rodent carcinogenicity, concerns remain about its sensitivity under standard conditions, particularly when […]

A new paper, “Data-driven federated learning in drug discovery with knowledge distillation”, was recently published in Nature Machine Intelligence, the leading journal for Machine Learning and AI. It explores the potential for federated learning to advance drug discovery through secure, collaborative research, representing a major step forward in privacy-preserving machine learning.   What is Federated

At Lhasa we know that there are many challenges involved in carrying out risk assessments for drug substances and drug products, to ultimately ensure a safe and effective product for patients. Forced degradation studies are essential in pharmaceutical development to assess drug stability and ensure product quality and safety. These studies help identify degradation pathways,

The use of in silico prediction systems has become an essential part of regulatory submissions when assessing the genotoxic potential of chemicals. Guidelines such as those from the EMA, US FDA, and ICH highlight their importance. Most notably, the ICH M7 guidance explicitly requires the application of two complementary quantitative/qualitative structure-activity relationship ((Q)SAR) systems to

Identification and control of impurities in active pharmaceutical ingredients (APIs) and pharmaceutical drug products is critical in drug development. Mirabilis is our innovative solution designed to address this challenge. In this post, we’ll answer ten frequently asked questions about Mirabilis.   What is Mirabilis? Mirabilis is an in silico tool developed by Lhasa Limited that