Machine Learning Helps Researchers in Hot Pursuit of New Drugs

#artificialintelligence

Researchers have designed a machine learning algorithm for drug discovery which has been shown to be twice as efficient as the industry standard, which could accelerate the process of developing new treatments for disease. The researchers, led by the University of Cambridge, used their algorithm to identify four new molecules that activate a protein which is thought to be relevant for symptoms of Alzheimer's disease and schizophrenia. The results are reported in the journal PNAS. A key problem in drug discovery is predicting whether a molecule will activate a particular physiological process. It's possible to build a statistical model by searching for chemical patterns shared among molecules known to activate that process, but the data to build these models is limited because experiments are costly and it is unclear which chemical patterns are statistically significant.


New machine learning algorithm can help search new drugs

#artificialintelligence

LONDON, Feb 12: Researchers say they have developed a machine learning algorithm for drug discovery which is twice as efficient as the industry standard, and could accelerate the process of developing new treatments for diseases such as Alzheimer's. The team led by researchers at the University of Cambridge in the UK used the algorithm to identify four new molecules that activate a protein thought to be relevant for symptoms of Alzheimer's disease and schizophrenia. A key problem in drug discovery is predicting whether a molecule will activate a particular physiological process, according to the study published in the journal PNAS. It is possible to build a statistical model by searching for chemical patterns shared among molecules known to activate that process, but the data to build these models is limited because experiments are costly and it is unclear which chemical patterns are statistically significant. Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed "Machine learning has made significant progress in areas such as computer vision where data is abundant," said Alpha Lee from Cambridge's Cavendish Laboratory.


Machine Learning Algorithm Helps In The Search For New Drugs

#artificialintelligence

Researchers have designed a machine learning algorithm for drug discovery which has been shown to be twice as efficient as the industry standard, which could accelerate the process of developing new treatments for disease. The researchers, led by the University of Cambridge, used their algorithm to identify four new molecules that activate a protein which is thought to be relevant for symptoms of Alzheimer's disease and schizophrenia. The results are reported in the journal PNAS.


Noisy Quantum Computers Could Be Good for Chemistry Problems

WIRED

Scientists and researchers have long extolled the extraordinary potential capabilities of universal quantum computers, like simulating physical and natural processes or breaking cryptographic codes in practical time frames. Yet important developments in the technology--the ability to fabricate the necessary number of high-quality qubits (the basic units of quantum information) and gates (elementary operations between qubits)--is most likely still decades away. However, there is a class of quantum devices--ones that currently exist--that could address otherwise intractable problems much sooner than that. These near-term quantum devices, coined Noisy Intermediate-Scale Quantum (NISQ) by Caltech professor John Preskill, are single-purpose, highly imperfect, and modestly sized. Dr. Anton Toutov is the cofounder and chief science officer of Fuzionaire and holds a PhD in organic chemistry from Caltech.


Predicting drug-target interaction using 3D structure-embedded graph representations from graph neural networks

arXiv.org Machine Learning

Accurate prediction of drug-target interaction (DTI) is essential for in silico drug design. For the purpose, we propose a novel approach for predicting DTI using a GNN that directly incorporates the 3D structure of a protein-ligand complex. We also apply a distance-aware graph attention algorithm with gate augmentation to increase the performance of our model. As a result, our model shows better performance than docking and other deep learning methods for both virtual screening and pose prediction. In addition, our model can reproduce the natural population distribution of active molecules and inactive molecules.