Nav: Home

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:

A hidden history of artificial intelligence in primary care
Artificial intelligence methods are being utilized in radiology, cardiology and other medical specialty fields to quickly and accurately process large quantities of health data to improve the diagnostic and treatment power of health care teams.
Identifying light sources using artificial intelligence
Identifying sources of light plays an important role in the development of many photonic technologies, such as lidar, remote sensing, and microscopy.
Artificial intelligence could serve as backup to radiologists' eyes
Deploying artificial intelligence could help radiologists to more accurately classify lung diseases.
Reducing the carbon footprint of artificial intelligence
MIT system cuts the energy required for training and running neural networks.
Researchers rebuild the bridge between neuroscience and artificial intelligence
In an article in the journal Scientific Reports, researchers reveal that they have successfully rebuilt the bridge between experimental neuroscience and advanced artificial intelligence learning algorithms.
Artificial intelligence can help some businesses but may not work for others
The temptation for businesses to use artificial intelligence and other technology to improve performance, drive down labor costs, and better the bottom line is understandable.
Artificial intelligence could help predict future diabetes cases
A type of artificial intelligence called machine learning can help predict which patients will develop diabetes, according to an ENDO 2020 abstract that will be published in a special supplemental section of the Journal of the Endocrine Society.
Artificial intelligence for very young brains
Montreal's CHU Sainte-Justine children's hospital and the ÉTS engineering school pool their expertise to develop an innovative new technology for the segmentation of neonatal brain images.
Putting artificial intelligence to work in the lab
An Australian-German collaboration has demonstrated fully-autonomous SPM operation, applying artificial intelligence and deep learning to remove the need for constant human supervision.
Composing new proteins with artificial intelligence
Scientists have long studied how to improve proteins or design new ones.
More Artificial Intelligence News and Artificial Intelligence Current Events

Trending Science News

Current Coronavirus (COVID-19) News

Top Science Podcasts

We have hand picked the top science podcasts of 2020.
Now Playing: TED Radio Hour

Our Relationship With Water
We need water to live. But with rising seas and so many lacking clean water – water is in crisis and so are we. This hour, TED speakers explore ideas around restoring our relationship with water. Guests on the show include legal scholar Kelsey Leonard, artist LaToya Ruby Frazier, and community organizer Colette Pichon Battle.
Now Playing: Science for the People

#568 Poker Face Psychology
Anyone who's seen pop culture depictions of poker might think statistics and math is the only way to get ahead. But no, there's psychology too. Author Maria Konnikova took her Ph.D. in psychology to the poker table, and turned out to be good. So good, she went pro in poker, and learned all about her own biases on the way. We're talking about her new book "The Biggest Bluff: How I Learned to Pay Attention, Master Myself, and Win".
Now Playing: Radiolab

Uncounted
First things first: our very own Latif Nasser has an exciting new show on Netflix. He talks to Jad about the hidden forces of the world that connect us all. Then, with an eye on the upcoming election, we take a look back: at two pieces from More Perfect Season 3 about Constitutional amendments that determine who gets to vote. Former Radiolab producer Julia Longoria takes us to Washington, D.C. The capital is at the heart of our democracy, but it's not a state, and it wasn't until the 23rd Amendment that its people got the right to vote for president. But that still left DC without full representation in Congress; D.C. sends a "non-voting delegate" to the House. Julia profiles that delegate, Congresswoman Eleanor Holmes Norton, and her unique approach to fighting for power in a virtually powerless role. Second, Radiolab producer Sarah Qari looks at a current fight to lower the US voting age to 16 that harkens back to the fight for the 26th Amendment in the 1960s. Eighteen-year-olds at the time argued that if they were old enough to be drafted to fight in the War, they were old enough to have a voice in our democracy. But what about today, when even younger Americans are finding themselves at the center of national political debates? Does it mean we should lower the voting age even further? This episode was reported and produced by Julia Longoria and Sarah Qari. Check out Latif Nasser's new Netflix show Connected here. Support Radiolab today at Radiolab.org/donate.