Monoclonal antibody engineering and machine learning applications in drug design have come a long way. What does this mean for mAbLab?
HISTORY
Orthoclone OKT3 is licensed and approved for preventing renal transplant rejection, marking the first approved mAb in history. This sets precedent for industry validity of mAbs, spurring further R&D.
Researchers Köhler and Milstein create the first mAb and publish the first paper on hybridoma tech. This becomes the standard for mAb development for decades to come.
First FDA-approved mAb, Adalimumab treats various conditions (arthritis, Crohn's, psoriasis, etc). Becomes the most sold drug in 2019, concreting mAbs in R&D.
The FDA approves Rituxan, the first cancer-fighting mAb. Used to treat leukemias and lymphomas, this drug binds to receptors on abnormal WBCs and destroy them.
Researchers at UCB develop first ML-produced mAb for psoriasis, Bimekizumab, which outperforms conventional alternatives.
Machine learning seeks to integrate itself into the fundamentals of monoclonal antibody engineering as researchers in the status quo seek to develop in silico modeling of ML-based mAb conformation, binding affinity, and efficacy. Moreover, the development of ML architectures like transformers provides parallelism that allows applications to be stronger as more research is conducted.