We are uploading terabytes of patient data each day into our platform to train our machine learning target identification models. Using tens of thousands of genomic, transcriptomic, and proteomic sequences, we are working to uncover new biological drivers of disease.
Traditional in silico drug screening requires sifting through billions of compounds in chemical libraries to ﬁnd molecules with a high probability of clinical efﬁcacy. Our novel approach employs deep reinforcement learning to design molecules that already meet our requirements. Our de novo generation prototype dreams up new compounds with speciﬁed parameters suitable for neurotherapeutics.
By leveraging computational tools and our team's chemistry and pharmacology expertise, we can rigorously screen candidate molecules before reaching the lab and increase the probability of success in clinical trials.
We aim to utilize machine learning to identify and treat neurodegenerative diseases that affect millions of people each year. Using the current methods of brute force, high throughput drug screening, the traditional players in the pharmaceutical industry has been unable to tackle elusive diseases such as Alzheimer's.
In bringing our novel approach to the industry, we are working diligently to bring viable drug candidates to trials and reinvigorate the neurodegenerative pipeline.