Experimentally validated model for drug discovery gets a stamp of mathematical approval

October 14, 2019

14th of October, Hong Kong - Insilico Medicine, a biotechnology company developing an end-to-end drug discovery pipeline utilizing next-generation artificial intelligence, is proud to present its paper "A Prior of a Googol Gaussians: a Tensor Ring Induced Prior for Generative Models" at the 33rd Conference on Neural Information Processing Systems (NeurIPS).

Generative models produce realistic objects in many domains, including text, image, video, and audio synthesis. Most popular models, such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), usually employ a standard Gaussian distribution as a prior. It was previously shown by research that a richer family of prior distributions may help to avoid the mode collapse problem in GANs and to improve the evidence lower bound in VAEs.

Insilico scientists proposed a new family of prior distributions: Tensor Ring Induced Prior (TRIP) that packs an exponential number of Gaussians into a high-dimensional lattice with a relatively small number of parameters. They showed that this prior improves Fréchet Inception Distance for GANs and Evidence Lower Bound for VAEs. They also studied generative models with TRIP in the conditional generation setup with missing conditions.

"We are excited to present a novel prior distribution that can be used in any generative model, including variational autoencoders (VAE) and generative adversarial networks (GAN)," said Daniil Polykovskiy, Senior Research Scientist at Insilico Medicine.

Recently, Nature Biotechnologypublished a paper by Insilico Medicine scientists and collaborators that described the use of a Generative Tensorial Reinforcement Learning (GENTRL) model to propose molecules that would bind to DDR1 kinase. These molecules were later synthesized and experimentally validated in cells and animals.

"Earlier this month, we published our work in Nature Biotechnology describing an unprecedented experimental validation of generative machine learning pipeline. Now, this model, improved and distilled to its mathematical core, will be showcased at the most impactful AI conference in the field. We continue transforming early-stage drug discovery while delivering strong research results in theoretical machine learning." - said Alex Zhebrak, CTO of Insilico Medicine.

"We are very excited to have a paper by Insilico scientists accepted at NeurIPS, one of the elite conferences on artificial intelligence. Insilico is focused on extending human life by accelerating and improving the drug discovery process, and we are proud to have some of the most creative AI teams in the industry to help us do this," said Alex Zhavoronkov, PhD, founder, and CEO of Insilico Medicine.

Insilico was the Gold Sponsor of ICML 2018 and NeurIPS 2018. This year it will host a reception near the conference venue as the company seeks to recruit the best bioinformatics and deep learning talent to focus on target identification, small molecule generation, and prediction of clinical trials outcomes.

The Conference on Neural Information Processing Systems (NeurIPS) is a machine learning and computational neuroscience conference held every December. The conference includes invited talks as well as oral and poster presentations of accepted papers. In 2018-2019 the registrations were sold out in less than 12 minutes. The conference is scheduled to be held Dec 8th through the 14th, 2019 at Vancouver Convention Center.
-end-
For further information, images or interviews, please contact:

Contact: Klug Gehilfe ai@pharma.ai

Website: http://insilico.com/



About Insilico Medicine


Insilico Medicine is an artificial intelligence company headquartered in Hong Kong, with R&D and management resources in six countries sourced through hackathons and competitions. The company and its scientists are dedicated to extending human productive lifetime and transforming every step of the drug discovery and drug development process through excellence in biomarker discovery, drug development, digital medicine, and aging research.

Insilico pioneered the applications of generative adversarial networks (GANs) and reinforcement learning for generation of novel molecular structures for diseases with a known target as well as with no known targets. In addition to collaborations with large pharmaceutical companies, the company is pursuing internal drug discovery programs in cancer, dermatological diseases, fibrosis, Parkinson's Disease, Alzheimer's Disease, ALS, diabetes, sarcopenia, and aging. In 2017, NVIDIA selected Insilico Medicine as one of the Top 5 AI companies in its potential for social impact. In 2018, the company was named one of the global top 100 AI companies by CB Insights. In 2018 it received the Frost & Sullivan 2018 North American Artificial Intelligence for Aging Research and Drug Development Award.

InSilico Medicine

Related Artificial Intelligence Articles from Brightsurf:

Physics can assist with key challenges in artificial intelligence
Two challenges in the field of artificial intelligence have been solved by adopting a physical concept introduced a century ago to describe the formation of a magnet during a process of iron bulk cooling.

A survey on artificial intelligence in chest imaging of COVID-19
Announcing a new article publication for BIO Integration journal. In this review article the authors consider the application of artificial intelligence imaging analysis methods for COVID-19 clinical diagnosis.

Using artificial intelligence can improve pregnant women's health
Disorders such as congenital heart birth defects or macrosomia, gestational diabetes and preterm birth can be detected earlier when artificial intelligence is used.

Artificial intelligence (AI)-aided disease prediction
Artificial Intelligence (AI)-aided Disease Prediction https://doi.org/10.15212/bioi-2020-0017 Announcing a new article publication for BIO Integration journal.

Artificial intelligence dives into thousands of WW2 photographs
In a new international cross disciplinary study, researchers from Aarhus University, Denmark and Tampere University, Finland have used artificial intelligence to analyse large amounts of historical photos from WW2.

Applying artificial intelligence to science education
A new review published in the Journal of Research in Science Teaching highlights the potential of machine learning--a subset of artificial intelligence--in science education.

New roles for clinicians in the age of artificial intelligence
New Roles for Clinicians in the Age of Artificial Intelligence https://doi.org/10.15212/bioi-2020-0014 Announcing a new article publication for BIO Integration journal.

Artificial intelligence aids gene activation discovery
Scientists have long known that human genes are activated through instructions delivered by the precise order of our DNA.

Artificial intelligence recognizes deteriorating photoreceptors
A software based on artificial intelligence (AI), which was developed by researchers at the Eye Clinic of the University Hospital Bonn, Stanford University and University of Utah, enables the precise assessment of the progression of geographic atrophy (GA), a disease of the light sensitive retina caused by age-related macular degeneration (AMD).

Classifying galaxies with artificial intelligence
Astronomers have applied artificial intelligence (AI) to ultra-wide field-of-view images of the distant Universe captured by the Subaru Telescope, and have achieved a very high accuracy for finding and classifying spiral galaxies in those images.

Read More: Artificial Intelligence News and Artificial Intelligence Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.