Biology

Artificial intelligence could build new drugs faster than any human team

May 7, 2017

Artificial intelligence algorithms are being taught to generate art, human voices, and even fiction stories all on their own—why not give them a shot at building new ways to treat disease?

Atomwise, a San Francisco-based startup and Y Combinator alum, has built a system it calls AtomNet (pdf), which attempts to generate potential drugs for diseases like Ebola and multiple sclerosis. The company has invited academic and non-profit researchers from around the country to detail which diseases they’re trying to generate treatments for, so AtomNet can take a shot. The academic labs will receive 72 different drugs that the neural network has found to have the highest probability of interacting with the disease, based on the molecular data it’s seen.

Atomwise’s system only generates potential drugs—the compounds created by the neural network aren’t guaranteed to be safe, and need to go through the same drug trials and safety checks as anything else on the market. The company believes that the speed at which it can generate trial-ready drugs based on previous safe molecular interactions is what sets it apart.

Atomwise touts two projects that show the potential of AtomNet, drugs for multiple sclerosis and Ebola. The MS drug has been licensed to an undisclosed UK pharmacology firm, according to Atomwise, and the Ebola drug is being prepared for submission to a peer-reviewed publication.

Alexander Levy, the company’s COO and cofounder, said that AtomNet learns the interactions between molecules much like artificial intelligence learns to recognize images. Image recognition finds reduces patterns in images’ pixels to simpler representations, teaching itself the bounds of an idea like a horse or a desk lamp through seeing hundreds or thousands of examples.

“It turns out that the same thing that works in images, also works in chemistry,” Levy says. “You can take an interaction between a drug and huge biological system and you can decompose that to smaller and smaller interactive groups. If you study enough historical examples of molecules … and we’ve studied tens of millions of those, you can then make predictions that are extremely accurate yet also extremely fast.”

Atomwise isn’t the only company working on this technique. Startup BenevolentAI, working with Johnson & Johnson subsidiary Janssen, is also developing new ways to find drugs. TwoXAR is working on an AI-driven glaucoma medication, and Berg is working on algorithmically-built cancer treatments.

One of Atomwise’s advantages, Levy says, is that the network works with 3D models. To generate the drugs, the model starts with a 3D model of a molecule—for example a protein that gives a cancer cell a growth advantage. The neural network then generates a series of synthetic compounds (simulated drugs), and predicts how likely it would be for the two molecules to interact. If a drug is likely to interact with the specific molecule, it can be synthesized and tested.

Levy likens the idea to the automated systems used to model airplane aerodynamics or computer chip design, where millions of scenarios are mapped out within software that accurately represents how the physical world works.

“Imagine if you knew what a biological mechanism looked like, atom by atom. Could you reason your way to a compound that did the thing that you wanted?” Levy says.

Artificial intelligence could build new drugs faster than any human team

Jeff Bezos, Mayo Clinic back anti-aging startup Unity Biotechnology for $116 million

March 30, 2017

Every once in a while someone in Silicon Valley brings up the possibility of living forever, or at least a really long time, but first we’re going to need to figure out a way to enjoy all those extra years. Unity Biotechnology is a startup focusing on medicines to help us do that by slowing the effects of age-related diseases. And the company announced it has pulled in a whopping $116 million in Series B financing today — some of which came from Amazon’s Jeff Bezos.

Sometimes your body keeps aging cells around longer. These cells stop dividing after some form of stress,which is an anti-cancer mechanism that keeps damaged cells from dividing and growing out of control. But too much build-up of those types of cells leads to other problems as we age. Unity looks for ways to help your body shed older cells causing inflammation and other diseases linked to aging.

Unity holds a great amount of potential in preventing our bodies from aging as fast and that has perked some of the top investors in science and medicine and is one of the larger private financings in biotech history.

But it’s not the first time Bezos has invested in biotech. The Amazon CEO placed his bets on Juno Therapeutics back in 2014, through his venture capital arm Bezos Expeditions. Juno is one of the IPO success stories in the biotech world for its breakthrough discoveries in cancer medicine.

The Scottish-based mutual fund Baillie Gifford, which has also invested in several biotech companies, also invested in this round — as did Venrock, ARCH Venture Capital, Mayo Clinic and WuXi Pharmaceuticals.

The company also announced it would be placing Keith Leonard — the former CEO of KYTHERA Biopharmaceuticals — in the role of CEO and that previous CEO and co-founder Nathaniel “Ned” David will now be Unity’s president.

Jeff Bezos, Mayo Clinic back anti-aging startup Unity Biotechnology for $116 million

10 Tech Trends That Made the World Better in 2016

March 30, 2017

2016 was an incredible year for technology, and for humanity.

Despite all the negative political-related news, there were 10 tech trends this year that positively transformed humanity.

For this “2017 Kick-Off” post, I reviewed 52 weeks of science and technology breakthroughs, and categorized them into the top 10 tech trends changing our world.

I’m blown away by how palpable the feeling of exponential change has become.

I’m also certain that 99.99% of humanity doesn’t understand or appreciate the ramifications of what is coming.

In this post, enjoy the top 10 tech trends of the past 12 months and why they are important to you.

Let’s dive in…

1. We Are Hyper-Connecting the World

In 2010, 1.8 billion people were connected. Today, that number is about 3 billion, and by 2022 – 2025, that number will expand to include every human on the planet, approaching 8 billion humans.

Unlike when I was connected 20 years ago at 9,600 baud via AOL, the world today is coming online at one megabit per second or greater, with access to the world’s information on Google, access to the world’s products on Amazon, access to massive computing power on AWS and artificial intelligence with Watson… not to mention crowdfunding for capital and crowdsourcing for expertise.

Looking back at 2016, you can feel the acceleration. Here are seven stories that highlight the major advances in our race for global connectivity:

a) Google’s 5G Solar Drones Internet Service: Project Skybender is Google’s secretive 5G Internet drone initiative. News broke this year that they have been testing these solar-powered drones at Spaceport America in New Mexico to explore ways to deliver high-speed Internet from the air. Their purported millimeter wave technology could deliver data from drones up to 40 times faster than 4G.

b) Facebook’s Solar Drone Internet Service: Even before Google, Facebook has been experimenting with a solar-powered drone, also for the express purpose of providing Internet to billions. The drone has the wingspan of an airliner and flies with roughly the power of three blowdryers.

c) ViaSat Plans 1 Terabit Internet Service: ViaSat, a U.S.-based satellite company, has teamed up with Boeing to launch three satellites to provide 1 terabit-per-second Internet connections to remote areas, aircraft and maritime vehicles. ViaSat is scheduled to launch its satellite ViaSat2 in early 2017.

d) OneWeb Raises $1.2B for 900 Satellite Constellation: An ambitious low-Earth orbit satellite system proposed by my friends Greg Wyler, Paul Jacobs and Richard Branson just closed $1.2 billion in financing. This 900-satellite system will offer global internet services as soon as 2019.

e) Musk Announces 4,425 Internet Satellite System: Perhaps the most ambitious plan for global internet domination was proposed this year by SpaceX founder Elon Musk, with plans for SpaceX to deploy a 4,425 low-Earth orbit satellite system to blanket the entire planet in broadband.

2. Solar/Renewables Cheaper Than Coal

We’ve just exceeded a historic inflection point. 2016 was the year solar and renewable energy became cheaper than coal.

In December, the World Economic Forum reported that solar and wind energy is now the same price or cheaper than new fossil fuel capacity in more than 30 countries.

“As prices for solar and wind power continue their precipitous fall, two-thirds of all nations will reach the point known as ‘grid parity’ within a few years, even without subsidies,” they added.

This is one of the most important developments in the history of humanity, and this year marked a number of major milestones for renewable energy.

Here’s 10 data points (stories) I’ve hand-picked to hammer home the historic nature of this 2016 achievement.

a) 25 percent of the World’s Power Comes From Renewables: REN21, a global renewable energy policy network, published a report showing that a quarter of the world’s power now comes from renewable energy. International investment in renewable energy reached $286 billion last year (with solar accounting for over $160b of this), and it’s accelerating.

b) In India, Solar Is Now Cheaper Than Coal: An amazing milestone indeed, and India is now on track to deploy >100 gigawatts of solar power by 2022.

c) The UK Is Generating More Energy From Solar Than Coal: For the first time in history, this year the U.K. has produced an estimated 6,964 GWh of electricity from solar cells, 10% higher than the 6,342 GWh generated by coal.

d) Coal Plants Being Replaced by Solar Farms: The Nanticoke Generating Station in Ontario, once North America’s largest coal plant, will be turned into a solar farm.

e) Coal Will Never Recover: The coal industry, once the backbone of U.S. energy, is fading fast on account of renewables like solar and wind. Official and expert reports now state that it will never recover (e.g., coal power generation in Texas is down from 39% in early 2015 to 24.8% in May 2016).

f) Scotland Generated 106% Energy From Wind: This year, high winds boosted renewable energy output to provide 106% of Scotland’s electricity needs for a day.

g) Costa Rica Ran on Renewables for 2+ Months: The country ran on 100% renewable energy for 76 days.

h) Google to Run 100% on Renewable Energy: Google has announced its entire global business will be powered by renewable energy in 2017.

i) Las Vegas’ City Government Meets Goal of 100% Power by Renewables: Las Vegas is now the largest city government in the country to run entirely on renewable energy.

j) Tesla’s Gigafactory: Tesla’s $5 billion structure in Nevada will produce 500,000 lithium ion batteries annually and Tesla’s Model III vehicle. It is now over 30 percent complete… the 10 million square foot structure is set to be done by 2020. Musk projected that a total of 100 Gigafactories could provide enough storage capacity to run the entire planet on renewables.

3. Glimpsing the End of Cancer and Disease

Though it may seem hard to believe, the end of cancer and disease is near.

Scientists and researchers have been working diligently to find novel approaches to combating these diseases, and 2016 saw some extraordinary progress in this regard.

Here’re my top 10 picks that give me great faith about our abilities to cure cancer and most diseases:

a) Cancer Immunotherapy Makes Strides (Extraordinary Results): Immunotherapy involves using a patient’s own immune system (in this case, T cells) to fight cancer. Doctors remove immune cells from patients, tag them with “receptor” molecules that target the specific cancer, and then infuse the cells back in the body. During the study, 94% of patients with acute lymphoblastic leukemia (ALL) saw symptoms vanish completely. Patients with other blood cancers had response rates greater than 80%, and more than half experienced complete remission.

b) In China, CRISPR/Cas9 used in First Human Trial: A team of scientists in China (Sichuan University) became the first to treat a human patient with an aggressive form of lung cancer with the groundbreaking CRISPR-Cas9 gene-editing technique.

c) NIH Approves Human Trials Using CRISPR: A team of physicians at the University of Pennsylvania’s School of Medicine had their project of modifying the immune cells of 18 different cancer patients with the CRISPR-Cas9 system approved by the National Institute of Health. Results are TBD.

d) Giant Leap in Treatment of Diabetes from Harvard: For the first time, Harvard stem cell researchers created “insulin producing” islet cells to cure diabetes in mice. This offers a promising cure in humans as well.

e) HIV Genes Cut Out of Live Animals Using CRISPR: Scientists at the Comprehensive NeuroAIDS Center at Temple University were able to successfully cut out the HIV genes from live animals, and they had over a 50% success rate.

f) New Treatment Causes HIV Infected Cells to Vanish: A team of scientists in the U.K. discovered a new treatment for HIV. The patient was treated with vaccines that helped the body recognize the HIV-infected cells. Then, the drug Vorinostat was administered to activate the dormant cells so they could be spotted by the immune system.

g) CRISPR Cures Mice of Sickle Cell Disease: CRISPR was used to completely cure sickle cell by editing the errant DNA sequence in mice. The treatment may soon be used to cure this disease, which affects about 100,000 Americans.

h) Eradicating Measles (in the U.S.): The World Health Organization (WHO) announced that after 50 years, they have successfully eradicated measles in the U.S. This is one of the most contagious diseases around the world.

i) New Ebola Vaccine Proved to be 100% Effective: None of the nearly 6,000 individuals vaccinated with rVSV-ZEBOV in Guinea, a country with more than 3,000 confirmed cases of Ebola, showed any signs of contracting the disease.

j) Eradicating Polio: The World Health Organization has announced that it expects to fully eradicate polio worldwide by Early 2017.

4. Progress on Extending Human Life

I am personally convinced that we are on the verge of significantly impacting human longevity. At a minimum, making “100 years old the new 60,” as we say at Human Longevity Inc.

This year, hundreds of millions of dollars were poured into research initiatives and companies focused on extending life.

Here are five of the top stories from 2016 in longevity research:

a) 500-Year-Old Shark Discovered: A Greenland shark that could have been over 500 years old was discovered this year, making the species the longest-lived vertebrate in the world.

b) Genetically Reversing Aging: With an experiment that replicated stem cell-like conditions, Salk Institute researchers made human skin cells in a dish look and behave young again, and mice with premature aging disease were rejuvenated with a 30% increase in lifespan. The Salk Institute expects to see this work in human trials in less than 10 years.

c) 25% Life Extension Based on Removal of Senescent Cells: Published in the medical journal Nature, cell biologists Darren Baker and Jan van Deursen have found that systematically removing a category of living, stagnant cells can extend the life of mice by 25 percent.

d) Funding for Anti-Aging Startups: Jeff Bezos and the Mayo Clinic-backed Anti-Aging Startup Unity Biotechnology with $116 million. The company will focus on medicines to slow the effects of age-related diseases by removing senescent cells (as mentioned in the article above).

e) Young Blood Experiments Show Promising Results for Longevity: Sakura Minami and her colleagues at Alkahest, a company specializing in blood-derived therapies for neurodegenerative diseases, have found that simply injecting older mice with the plasma of young humans twice a week improved the mice’s cognitive functions as well as their physical performance. This practice has seen a 30% increase in lifespan, and increase in muscle tissue and cognitive function.

More at: https://singularityhub.com/2017/01/05/10-tech-trends-that-made-the-world-better-in-2016/

Scientists reverse aging in mice by repairing damaged DNA

March 30, 2017

Could lead to an anti-aging drug that counters damage from old age, cancer, and radiation.

A research team led by Harvard Medical School professor of genetics David Sinclair, PhD, has made a discovery that could lead to a revolutionary new drug that allows cells to repair DNA damaged by aging, cancer, and radiation.

In a paper published in the journal Science on Friday (March 24), the scientists identified a critical step in the molecular process related to DNA damage.

The researchers found that a compound known as NAD (nicotinamide adenine dinucleotide), which is naturally present in every cell of our body, has a key role as a regulator in protein-to-protein interactions that control DNA repair. In an experiment, they found that treating mice with a NAD+ precursor called NMN (nicotinamide mononucleotide) improved their cells’ ability to repair DNA damage.

“The cells of the old mice were indistinguishable from the young mice, after just one week of treatment,” said senior author Sinclair.

Disarming a rogue agent: When the NAD molecule (red) binds to the DBC1 protein (beige), it prevents DBC1 from attaching to and incapacitating a protein (PARP1) that is critical for DNA repair. (credit: David Sinclair)

Human trials of NMN therapy will begin within the next few months to “see if these results translate to people,” he said. A safe and effective anti-aging drug is “perhaps only three to five years away from being on the market if the trials go well.”

What it means for astronauts, childhood cancer survivors, and the rest of us

The researchers say that in addition to reversing aging, the DNA-repair research has attracted the attention of NASA. The treatment could help deal with radiation damage to astronauts in its Mars mission, which could cause muscle weakness, memory loss, and other symptoms (see “Mars-bound astronauts face brain damage from galactic cosmic ray exposure, says NASA-funded study“), and more seriously, leukemia cancer and weakened immune function (see “Travelers to Mars risk leukemia cancer, weakend immune function from radiation, NASA-funded study finds“).

The treatment could also help travelers aboard aircraft flying across the poles. A 2011 NASA study showed that passengers on polar flights receive about 12 percent of the annual radiation limit recommended by the International Committee on Radiological Protection.

The other group that could benefit from this work is survivors of childhood cancers, who are likely to suffer a chronic illness by age 45, leading to accelerated aging, including cardiovascular disease, Type 2 diabetes, Alzheimer’s disease, and cancers unrelated to the original cancer, the researchers noted.

For the past four years, Sinclair’s team has been working with spinoff MetroBiotech on developing NMN as a drug. Sinclair previously made a link between the anti-aging enzyme SIRT1 and resveratrol. “While resveratrol activates SIRT1 alone, NAD boosters [like NMN] activate all seven sirtuins, SIRT1-7, and should have an even greater impact on health and longevity,” he says.

Sinclair is also a professor at the University of New South Wales School of Medicine in Sydney, Australia.

Abstract of A conserved NAD+ binding pocket that regulates protein-protein interactions during aging

DNA repair is essential for life, yet its efficiency declines with age for reasons that are unclear. Numerous proteins possess Nudix homology domains (NHDs) that have no known function. We show that NHDs are NAD+ (oxidized form of nicotinamide adenine dinucleotide) binding domains that regulate protein-protein interactions. The binding of NAD+ to the NHD domain of DBC1 (deleted in breast cancer 1) prevents it from inhibiting PARP1 [poly(adenosine diphosphate–ribose) polymerase], a critical DNA repair protein. As mice age and NAD+ concentrations decline, DBC1 is increasingly bound to PARP1, causing DNA damage to accumulate, a process rapidly reversed by restoring the abundance of NAD+. Thus, NAD+ directly regulates protein-protein interactions, the modulation of which may protect against cancer, radiation, and aging.

References:

http://www.kurzweilai.net/scientists-reverse-aging-in-mice-by-repairing-damaged-dna

New gene-editing technology partially restores vision in blind animals

February 25, 2017

shutterstock_353873630

Salk Institute researchers have discovered a holy grail of gene editing — the ability to, for the first time, insert DNA at a target location into the non-dividing cells that make up the majority of adult organs and tissues. The technique, which the team showed was able to partially restore visual responses in blind rodents, will open new avenues for basic research and a variety of treatments, such as for retinal, heart and neurological diseases.

“We are very excited by the technology we discovered because it’s something that could not be done before,” says Juan Carlos Izpisua Belmonte, a professor in Salk’s Gene Expression Laboratory and senior author of the paper published on November 16, 2016 in Nature. “For the first time, we can enter into cells that do not divide and modify the DNA at will. The possible applications of this discovery are vast.”

Until now, techniques that modify DNA — such as the CRISPR-Cas9 system — have been most effective in dividing cells, such as those in skin or the gut, using the cells’ normal copying mechanisms. The new Salk technology is ten times more efficient than other methods at incorporating new DNA into cultures of dividing cells, making it a promising tool for both research and medicine. But, more importantly, the Salk technique represents the first time scientists have managed to insert a new gene into a precise DNA location in adult cells that no longer divide, such as those of the eye, brain, pancreas or heart, offering new possibilities for therapeutic applications in these cells.

To achieve this, the Salk researchers targeted a DNA-repair cellular pathway called NHEJ (for “non-homologous end-joining”), which repairs routine DNA breaks by rejoining the original strand ends. They paired this process with existing gene-editing technology to successfully place new DNA into a precise location in non-dividing cells.

“Using this NHEJ pathway to insert entirely new DNA is revolutionary for editing the genome in live adult organisms,” says Keiichiro Suzuki, a senior research associate in the Izpisua Belmonte lab and one of the paper’s lead authors. “No one has done this before.”

First, the Salk team worked on optimizing the NHEJ machinery for use with the CRISPR-Cas9 system, which allows DNA to be inserted at very precise locations within the genome. The team created a custom insertion package made up of a nucleic acid cocktail, which they call HITI, or homology-independent targeted integration. Then they used an inert virus to deliver HITI’s package of genetic instructions to neurons derived from human embryonic stem cells.

“That was the first indication that HITI might work in non-dividing cells,” says Jun Wu, staff scientist and co-lead author. With that feat under their belts, the team then successfully delivered the construct to the brains of adult mice. Finally, to explore the possibility of using HITI for gene-replacement therapy, the team tested the technique on a rat model for retinitis pigmentosa, an inherited retinal degeneration condition that causes blindness in humans. This time, the team used HITI to deliver to the eyes of 3-week-old rats a functional copy of Mertk, one of the genes that is damaged in retinitis pigmentosa. Analysis performed when the rats were 8 weeks old showed that the animals were able to respond to light, and passed several tests indicating healing in their retinal cells.

“We were able to improve the vision of these blind rats,” says co-lead author Reyna Hernandez-Benitez, a Salk research associate. “This early success suggests that this technology is very promising.”

The team’s next steps will be to improve the delivery efficiency of the HITI construct. As with all genome editing technologies, getting enough cells to incorporate the new DNA is a challenge. The beauty of HITI technology is that it is adaptable to any targeted genome engineering system, not just CRISPR-Cas9. Thus, as the safety and efficiency of these systems improve, so too will the usefulness of HITI.

“We now have a technology that allows us to modify the DNA of non-dividing cells, to fix broken genes in the brain, heart and liver,” says Izpisua Belmonte. “It allows us for the first time to be able to dream of curing diseases that we couldn’t before, which is exciting.”

Story Source:

Materials provided by Salk Institute. Note: Content may be edited for style and length.

Artificial intelligence to generate new cancer drugs on demand

December 18, 2016

687474703a2f2f6d7573796f6b752e6769746875622e696f2f696d616765732f706f73742f323031362d30382d30392f73656d692d737570657276697365642f64696d5f726564756374696f6e2f6c6162656c65645f7a5f313030302e706e67

Summary:

  • Clinical trial failure rates for small molecules in oncology exceed 94% for molecules previously tested in animals and the costs to bring a new drug to market exceed $2.5 billion
  • There are around 2,000 drugs approved for therapeutic use by the regulators with very few providing complete cures
  • Advances in deep learning demonstrated superhuman accuracy in many areas and are expected to transform industries, where large amounts of training data is available
  • Generative Adversarial Networks (GANs), a new technology introduced in 2014 represent the “cutting edge” in artificial intelligence, where new images, videos and voice can be produced by the deep neural networks on demand
  • Here for the first time we demonstrate the application of Generative Adversarial Autoencoders (AAEs), a new type of GAN, for generation of molecular fingerprints of molecules that kill cancer cells at specific concentrations
  • This work is the proof of concept, which opens the door for the cornucopia of meaningful molecular leads created according to the given criteria
  • The study was published in Oncotarget and the open-access manuscript is available in the Advance Open Publications section
  • Authors speculate that in 2017 the conservative pharmaceutical industry will experience a transformation similar to the automotive industry with deep learned drug discovery pipelines integrated into the many business processes
  • The extension of this work will be presented at the “4th Annual R&D Data Intelligence Leaders Forum” in Basel, Switzerland, Jan 24-26th, 2017

Thursday, 22nd of December Baltimore, MD – Scientists at the Pharmaceutical Artificial Intelligence (pharma.AI) group of Insilico Medicine, Inc, today announced the publication of a seminal paper demonstrating the application of generative adversarial autoencoders (AAEs) to generating new molecular fingerprints on demand. The study was published in Oncotarget on 22nd of December, 2016. The study represents the proof of concept for applying Generative Adversarial Networks (GANs) to drug discovery. The authors significantly extended this model to generate new leads according to multiple requested characteristics and plan to launch a comprehensive GAN-based drug discovery engine producing promising therapeutic treatments to significantly accelerate pharmaceutical R&D and improve the success rates in clinical trials.

Since 2010 deep learning systems demonstrated unprecedented results in image, voice and text recognition, in many cases surpassing human accuracy and enabling autonomous driving, automated creation of pleasant art and even composition of pleasant music.

GAN is a fresh direction in deep learning invented by Ian Goodfellow in 2014. In recent years GANs produced extraordinary results in generating meaningful images according to the desired descriptions. Similar principles can be applied to drug discovery and biomarker development. This paper represents a proof of concept of an artificially-intelligent drug discovery engine, where AAEs are used to generate new molecular fingerprints with the desired molecular properties.

“At Insilico Medicine we want to be the supplier of meaningful, high-value drug leads in many disease areas with high probability of passing the Phase I/II clinical trials. While this publication is a proof of concept and only generates the molecular fingerprints with the very basic molecular properties, internally we can now generate entire molecular structures according to a large number of parameters. These structures can be fed into our multi-modal drug discovery pipeline, which predicts therapeutic class, efficacy, side effects and many other parameters. Imagine an intelligent system, which one can instruct to produce a set of molecules with specified properties that kill certain cancer cells at a specified dose in a specific subset of the patient population, then predict the age-adjusted and specific biomarker-adjusted efficacy, predict the adverse effects and evaluate the probability of passing the human clinical trials. This is our big vision”, said Alex Zhavoronkov, PhD, CEO of Insilico Medicine, Inc.

Previously, Insilico Medicine demonstrated the predictive power of its discovery systems in the nutraceutical industry. In 2017 Life Extension will launch a range of natural products developed using Insilico Medicine’s discovery pipelines. Earlier this year the pharmaceutical artificial intelligence division of Insilico Medicine published several seminal proof of concept papers demonstrating the applications of deep learning to drug discovery, biomarker development and aging research. Recently the authors published a tool in Nature Communications, which is used for dimensionality reduction in transcriptomic data for training deep neural networks (DNNs). The paper published in Molecular Pharmaceutics demonstrating the applications of deep neural networks for predicting the therapeutic class of the molecule using the transcriptional response data received the American Chemical Society Editors’ Choice Award. Another paper demonstrating the ability to predict the chronological age of the patient using a simple blood test, published in Aging, became the second most popular paper in the journal’s history.

“Generative AAE is a radically new way to discover drugs according to the required parameters. At Pharma.AI we have a comprehensive drug discovery pipeline with reasonably accurate predictors of efficacy and adverse effects that work on the structural data and transcriptional response data and utilize the advanced signaling pathway activation analysis and deep learning. We use this pipeline to uncover the prospective uses of molecules, where these types of data are available. But the generative models allow us to generate completely new molecular structures that can be run through our pipelines and then tested in vitro and in vivo. And while it is too early to make ostentatious claims before our predictions are validated in vivo, it is clear that generative adversarial networks coupled with the more traditional deep learning tools and biomarkers are likely to transform the way drugs are discovered”, said Alex Aliper, president, European R&D at the Pharma.AI group of Insilico Medicine.

Recent advances in deep learning and specifically in generative adversarial networks have demonstrated surprising results in generating new images and videos upon request, even when using natural language as input. In this study the group developed a 7-layer AAE architecture with the latent middle layer serving as a discriminator. As an input and output AAE uses a vector of binary fingerprints and concentration of the molecule. In the latent layer the group introduced a neuron responsible for tumor growth inhibition index, which when negative it indicates the reduction in the number of tumour cells after the treatment. To train AAE, the authors used the NCI-60 cell line assay data for 6252 compounds profiled on MCF-7 cell line. The output of the AAE was used to screen 72 million compounds in PubChem and select candidate molecules with potential anti-cancer properties.

“I am very happy to work alongside the Pharma.AI scientists at Insilico Medicine on getting the GANs to generate meaningful leads in cancer and, most importantly, age-related diseases and aging itself. This is humanity’s most pressing cause and everyone in machine learning and data science should be contributing. The pipelines these guys are developing will play a transformative role in the pharmaceutical industry and in extending human longevity and we will continue our collaboration and invite other scientists to follow this path”, said Artur Kadurin, the head of the segmentation group at Mail.Ru, one of the largest IT companies in Eastern Europe and the first author on the paper.

###

About Insilico Medicine, Inc

Insilico Medicine, Inc. is a bioinformatics company located at the Emerging Technology Centers at the Johns Hopkins University Eastern campus in Baltimore with Research and Development (“R&D”) resources in Belgium, UK and Russia hiring talent through hackathons and competitions. The company utilizes advances in genomics, big data analysis, and deep learning for in silico drug discovery and drug repurposing for aging and age-related diseases. The company pursues internal drug discovery programs in cancer, Parkinson’s Disease, Alzheimer’s Disease, sarcopenia, and geroprotector discovery. Through its Pharma.AI division, the company provides advanced machine learning services to biotechnology, pharmaceutical, and skin care companies. Brief company video: https://www.youtube.com/watch?v=l62jlwgL3v8

From: https://eurekalert.org/pub_releases/2016-12/imi-ait122016.php

Ageing process may be reversible, scientists claim

December 18, 2016

5079

Wrinkles, grey hair and niggling aches are normally regarded as an inevitable part of growing older, but now scientists claim that the ageing process may be reversible.

The team showed that a new form of gene therapy produced a remarkable rejuvenating effect in mice. After six weeks of treatment, the animals looked younger, had straighter spines and better cardiovascular health, healed quicker when injured, and lived 30% longer.

Juan Carlos Izpisua Belmonte, who led the work at the Salk Institute in La Jolla, California, said: “Our study shows that ageing may not have to proceed in one single direction. With careful modulation, ageing might be reversed.”

The genetic techniques used do not lend themselves to immediate use in humans, and the team predict that clinical applications are a decade away. However, the discovery raises the prospect of a new approach to healthcare in which ageing itself is treated, rather than the various diseases associated with it.

The findings also challenge the notion that ageing is simply the result of physical wear and tear over the years. Instead, they add to a growing body of evidence that ageing is partially – perhaps mostly – driven by an internal genetic clock that actively causes our body to enter a state of decline.

The scientists are not claiming that ageing can be eliminated, but say that in the foreseeable future treatments designed to slow the ticking of this internal clock could increase life expectancy.

“We believe that this approach will not lead to immortality,” said Izpisua Belmonte. “There are probably still limits that we will face in terms of complete reversal of ageing. Our focus is not only extension of lifespan but most importantly health-span.”

Wolf Reik, a professor of epigenetics at the Babraham Institute, Cambridge, who was not involved in the work, described the findings as “pretty amazing” and agreed that the idea of life-extending therapies was plausible. “This is not science fiction,” he said.

On the left is muscle tissue from an aged mouse. On the right is muscle tissue from an aged mouse that has been subjected to “reprogramming”.
Photograph: Salk Institute
On the left is muscle tissue from an aged mouse. On the right is muscle tissue from an aged mouse that has been subjected to “reprogramming”.

The rejuvenating treatment given to the mice was based on a technique that has previously been used to “rewind” adult cells, such as skin cells, back into powerful stem cells, very similar to those seen in embryos. These so-called induced pluripotent stem (iPS) cells have the ability to multiply and turn into any cell type in the body and are already being tested in trials designed to provide “spare parts” for patients.

The latest study is the first to show that the same technique can be used to partially rewind the clock on cells – enough to make them younger, but without the cells losing their specialised function.

“Obviously there is a logic to it,” said Reik. “In iPS cells you reset the ageing clock and go back to zero. Going back to zero, to an embryonic state, is probably not what you want, so you ask: where do you want to go back to?”

The treatment involved intermittently switching on the same four genes that are used to turn skin cells into iPS cells. The mice were genetically engineered in such a way that the four genes could be artificially switched on when the mice were exposed to a chemical in their drinking water.

The scientists tested the treatment in mice with a genetic disorder, called progeria, which is linked to accelerated ageing, DNA damage, organ dysfunction and dramatically shortened lifespan.

After six weeks of treatment, the mice looked visibly younger, skin and muscle tone improved and they lived 30% longer. When the same genes were targeted in cells, DNA damage was reduced and the function of the cellular batteries, called the mitochondria, improved.

“This is the first time that someone has shown that reprogramming in an animal can provide a beneficial effect in terms of health and extend their lifespan,” said Izpisua Belmonte.

Crucially, the mice did not have an increased cancer risk, suggesting that the treatment had successfully rewound cells without turning them all the way back into stem cells, which can proliferate uncontrollably in the body.

The potential for carcinogenic side-effects means that the first people to benefit are likely to be those with serious genetic conditions, such as progeria, where there is more likely to be a medical justification for experimental treatments. “Obviously the tumour risk is lurking in the background,” said Reik.

The approach used in the mice could not be readily applied to humans as it would require embryos to be genetically manipulated, but the Salk team believe the same genes could be targeted with drugs.

“These chemicals could be administrated in creams or injections to rejuvenate skin, muscle or bones,” said Izpisua Belmonte. “We think these chemical approaches might be in human clinical trials in the next ten years.”

The findings are published in the journal Cell.
This article was amended on 16 December 2016. A previous version erroneously gave Wolf Reik’s affiliation as the University of Cambridge. This has now been corrected to the Babraham Institute, Cambridge.

https://www.theguardian.com/science/2016/dec/15/ageing-process-may-be-reversible-scientists-claim#img-1

Mark Zuckerberg and Priscilla Chan’s $3 billion effort aims to rid world of major diseases by end of century

September 24, 2016

imrs-php

Facebook co-founder Mark Zuckerberg and his wife, Priscilla Chan, on Wednesday announced a $3 billion effort to accelerate scientific research with the wildly ambitious goal of “curing all disease in our children’s lifetime.”

The many components of the initiative include creating universal technology “tools” based on both traditional science and engineering on which all researchers can build, including a map of all cell types, a way to continuously monitor blood for early signs of illness, and a chip that can diagnose all diseases (or at least many of them). The money will also help fund what they referred to as 10 to 15 “virtual institutes” that will bring together investigators from around the world to focus on individual diseases or other goals — an idea that has the potential to upend biomedical science.

Being a scientist in academia today can often be a solitary endeavor as the system is set up to encourage colleagues to keep data exclusive in the hopes that this strategy helps them be more competitive at getting publications and grants. But as more Silicon Valley entrepreneurs like Zuckerberg are seeking to make their mark in the biological sciences, they are emphasizing the power of collaboration and openness.

A centerpiece of the new effort, called Chan Zuckerberg Science, involves creating a “Biohub” at the University of California at San Francisco (UCSF) Mission Bay campus that will bring together scientists from Stanford, the University of California at Berkeley and UCSF.

Zuckerberg and Chan, among the world’s 10 wealthiest couples, with a net worth of $55.2 billion, emphasized that their timeline is long — by the end of the century.

“We have to be patient. This is hard stuff,” Zuckerberg said.

Chan said, “That doesn’t mean no one will ever get sick, but it means our children and their children should get sick a lot less.”

Many of themes articulated by Zuckerberg and Chan on Wednesday in San Francisco echo ideas furthered by other technology philanthropists who have donated substantial amounts of money to medical science. Sean Parker, a Napster co-founder, earlier this year set up a multi-center, $250 million effort to bring together top researchers from around the country to focus on immunotherapy for cancer. Microsoft’s Paul Allen has already invested $100 million in a cell-biology institute to try to create models of the fundamental building blocks of life.

https://www.washingtonpost.com/news/to-your-health/wp/2016/09/21/mark-zuckerberg-and-priscilla-chans-3-billion-scientific-effort-aims-to-rid-world-of-major-diseases-by-end-of-century/

Scientists Talk Privately About Creating a Synthetic Human Genome

July 10, 2016

14GENoME2-master768

George Church, a professor of genetics at Harvard Medical School and an organizer of the proposed project, said there had been a misunderstanding. The project was not aimed at creating people, just cells, and would not be restricted to human genomes, he said. Rather it would aim to improve the ability to synthesize DNA in general, which could be applied to various animals, plants and microbes.

“They’re painting a picture which I don’t think represents the project,” Dr. Church said in an interview.

He said the meeting was closed to the news media, and people were asked not to tweet because the project organizers, in an attempt to be transparent, had submitted a paper to a scientific journal. They were therefore not supposed to discuss the idea publicly before publication. He and other organizers said ethical aspects have been amply discussed since the beginning.

The project was initially called HGP2: The Human Genome Synthesis Project, with HGP referring to the Human Genome Project. An invitation to the meeting at Harvard said that the primary goal “would be to synthesize a complete human genome in a cell line within a period of 10 years.”

George Church, one of the organizers of the proposed project, at his lab at Harvard Medical School in 2013. Jessica Rinaldi/Reuters

But by the time the meeting was held, the name had been changed to “HGP-Write: Testing Large Synthetic Genomes in Cells.”

The project does not yet have funding, Dr. Church said, though various companies and foundations would be invited to contribute, and some have indicated interest. The federal government will also be asked. A spokeswoman for the National Institutes of Health declined to comment, saying the project was in too early a stage.

Besides Dr. Church, the organizers include Jef Boeke, director of the institute for systems genetics at NYU Langone Medical Center, and Andrew Hessel, a self-described futurist who works at the Bay Area software company Autodesk and who first proposed such a project in 2012.

Scientists and companies can now change the DNA in cells, for example, by adding foreign genes or changing the letters in the existing genes. This technique is routinely used to make drugs, such as insulin for diabetes, inside genetically modified cells, as well as to make genetically modified crops. And scientists are now debating the ethics of new technology that might allow genetic changes to be made in embryos.

But synthesizing a gene, or an entire genome, would provide the opportunity to make even more extensive changes in DNA.

For instance, companies are now using organisms like yeast to make complex chemicals, like flavorings and fragrances. That requires adding not just one gene to the yeast, like to make insulin, but numerous genes in order to create an entire chemical production process within the cell. With that much tinkering needed, it can be easier to synthesize the DNA from scratch.

Right now, synthesizing DNA is difficult and error-prone. Existing techniques can reliably make strands that are only about 200 base pairs long, with the base pairs being the chemical units in DNA. A single gene can be hundreds or thousands of base pairs long. To synthesize one of those, multiple 200-unit segments have to be spliced together.

But the cost and capabilities are rapidly improving. Dr. Endy of Stanford, who is a co-founder of a DNA synthesis company called Gen9, said the cost of synthesizing genes has plummeted from $4 per base pair in 2003 to 3 cents now. But even at that rate, the cost for three billion letters would be $90 million. He said if costs continued to decline at the same pace, that figure could reach $100,000 in 20 years.

J. Craig Venter, the genetic scientist, synthesized a bacterial genome consisting of about a million base pairs. The synthetic genome was inserted into a cell and took control of that cell. While his first synthetic genome was mainly a copy of an existing genome, Dr. Venter and colleagues this year synthesized a more original bacterial genome, about 500,000 base pairs long.

Dr. Boeke is leading an international consortium that is synthesizing the genome of yeast, which consists of about 12 million base pairs. The scientists are making changes, such as deleting stretches of DNA that do not have any function, in an attempt to make a more streamlined and stable genome.

But the human genome is more than 200 times as large as that of yeast and it is not clear if such a synthesis would be feasible.

Jeremy Minshull, chief executive of DNA2.0, a DNA synthesis company, questioned if the effort would be worth it.

“Our ability to understand what to build is so far behind what we can build,” said Dr. Minshull, who was invited to the meeting at Harvard but did not attend. “I just don’t think that being able to make more and more and more and cheaper and cheaper and cheaper is going to get us the understanding we need.”

Japanese scientists have used skin cells to restore a patient’s vision for the first time

July 10, 2016

314152310_1024

Japanese scientists have reported the first successful skin-to-eye stem cell transplant in humans, where stem cells derived from a patient’s skin were transplanted into her eye to partially restore lost vision.

The patient, a 70-year-old woman diagnosed with age-related macular degeneration (AMD) – the leading cause of vision impairment in older people – received the experimental treatment back in 2014 as part of a pilot study. Now, closing in on two years after the transplant took place, the scientists are sharing the results.

The researchers took a small piece of skin from her arm (4 mm in diameter) and modified its cells, effectively reprogramming them into induced pluripotent stem cells (iPSC).

Pluripotent stem cells have the ability to differentiate into almost any type of tissue within the body, which is why skin cells taken from an arm can be repurposed into retinal tissue.

Once the cells were coaxed to develop into retinal pigment epithelium (RPE), they were cultured in the lab to grow into an ultra-thin sheet, which was then transplanted behind the retina of the patient.

“I am very pleased that there were no complications with the transplant surgery,” said project leader Masayo Takahashi from the Riken Centre for Developmental Biology in 2014. “However, this is only the first step for use of iPSC in regenerative medicine. I have renewed my resolve to continue forging ahead until this treatment becomes available to many patients.”

While it’s definitely still early days for this experimental procedure, the signs so far are promising.

The team held off on reporting their results until now to monitor the patient’s progress and gauge how successfully the modified cells lasted, but they’ve just reported that the transplanted cells survived without any adverse events for over a year, resulting in slightly improved vision for the patient.

“The transplanted RPE sheet survived well without any findings [or] indication of immune rejections nor adverse unexpected proliferation for one and a half years, achieving our primary purpose of this pilot study,” the team said in a statement this week.

“I am glad I received the treatment,” the patient told The Japan Times last year. “I feel my eyesight has brightened and widened.”

While it’s not a complete restoration of the patient’s vision, the study shows a significant step forward in the use of induced pluripotent stem cells – which scientists think might be used to treat a range of illnesses, such as Parkinson’s and Alzheimer’s disease, not just vision problems.

A number of other studies are also showing positive results in restoring sight with stem cell treatments. Earlier in the year, researchers in China and the US were able to improve the vision of babies with cataracts by manipulating protein levels in stem cells.

Even more remarkably, a woman in Baltimore who was blind for more than five years had some of her vision restored after stem cells were extracted from her bone marrow and injected into her eyes. While many questions remain about that particular treatment, there’s no denying that stem cell research is a hugely exciting field of study.

The findings were presented at the 2016 annual meeting of the Association for Research in Vision and Ophthalmology (ARVO) in Seattle.

http://www.sciencealert.com/japanese-scientists-have-used-skin-cells-to-restore-a-patient-s-vision-for-the-first-time