Back to Table of contents

Primeur weekly 2020-03-23

Crowd computing

Crowdsourced supercomputing project sets sights on coronavirus ...

Focus on Europe

LEXIS: novel computing systems at IT4Innovations and Leibniz Rechenzentrum (LRZ) ...

Exscalate4CoV supercomputing platform wins 3 million euro EU funding to hunt for new drugs against coronavirus pandemic ...

Open collaborative infrastructure to tackle public health emergencies ...

AMPERE Project: Strengthening European leadership in energy-efficiency and parallel computing ...

The European Commission offers significant support to Europe's AI excellence ...

Middleware

Atipa Technologies becomes the latest organisation to join the Bright Reseller Programme in North America ...

Hardware

Rittal announces its first HPC Direct Chip Cooling solution with ZutaCore ...

Intel scales neuromorphic research system to 100 million neurons ...

COVID-19 to have significant effect on worldwide semiconductor market in 2020, according to IDC ...

Foundry revenue estimated to grow by 30% YoY in 1Q20, while COVID-19 pandemic may hinder future market demand, according to TrendForce ...

MEGWARE to provide IBM Power in its Benchmark Center ...

Rescale partners with Google Cloud and Microsoft Azure to accelerate the race for COVID-19 vaccine with Cloud supercomputers for researchers ...

Applications

Cadence digital full flow optimized to deliver improved quality of results with up to 3x faster throughput ...

Supercomputers unlock reproductive mysteries of viruses and life ...

RIKEN is exploring the molecular dynamics of the new coronavirus ...

Rensselaer offers AiMOS supercomputing capabilities to battle COVID-19 ...

Scientists discover critical protein that lets COVID-19 virus hide from immune system ...

NVIDIA gives COVID-19 researchers free access to Parabricks ...

Pioneers of modern computer graphics recognized with ACM A.M. Turing Award ...

Data Science Institute alumni use machine learning to discover coronavirus treatments ...

Berkeley lab cosmologists are top contenders in machine learning challenge ...

New satellite-based algorithm pinpoints crop water use ...

Northern Data announces revenue and earnings forecast for 2020 ...

The Cloud

Qumulo offers free Cloud software to help medical and health care research organisations fight the COVID-19 outbreak ...

Data Science Institute alumni use machine learning to discover coronavirus treatments

19 Mar 2020 - Two graduates of the Data Science Institute (DSI) at Columbia University are using computational design to quickly discover treatments for the coronavirus.

Andrew Satz and Brett Averso are chief executive officer and chief technology officer, respectively, of EVQLV, a start-up creating algorithms capable of computationally generating, screening, and optimizing hundreds of millions of therapeutic antibodies. They apply their technology to discover treatments most likely to help those infected by the virus responsible for COVID-19. The machine learning algorithms rapidly screen for therapeutic antibodies with a high probability of success.

Conducting antibody discovery in a laboratory typically takes years; it takes just a week for the algorithms to identify antibodies that can fight against the virus. Expediting the development of a treatment that could help infected people is critical, said Andrew Satz, who is a 2018 DSI alumnus and 2015 graduate of Columbia's School of General Studies.

"We are reducing the time it takes to identify promising antibody candidates", he stated. "Studies show it takes an average of five years and a half billion dollars to discover and optimize antibodies in a lab. Our algorithms can significantly reduce that time and cost."

Speeding up the first stage of the process - antibody discovery - goes a long way toward expediting the discovery of a treatment for COVID-19. After EVQLV performs computational antibody discovery and optimization, it sends the promising antibody gene sequences to its laboratory partners. Laboratory technicians then engineer and test the antibodies, a process that takes a few months, as opposed to several years. Antibodies found to be successful will move onto animal studies and, finally, human studies.

Given the international urgency to combat the coronavirus, Andrew Satz said it may be possible to have a treatment ready for patients before the end of 2020.

"What our algorithms do is reduce the likelihood of drug-discovery failure in the lab", he added. "We fail in the computer as much as possible to reduce the possibility of downstream failure in the laboratory. And that shaves a significant amount of time from laborious and time-consuming work."

Brett Averso, who is also a 2018 DSI alumnus, says some of the antibodies EVQLV is designing are intended to prevent the coronavirus from attaching to the human body. "The right-shaped antibodies bind to proteins that sit on the surface of human cells and the coronavirus, similar to a lock and key. Such binding can prevent the proliferation of the virus in the human body, potentially limiting the effects of the disease."

He also noted that the scientific community and the biotech industry are galvanized to forge collaborations that bring about therapeutics, diagnostics, and vaccines as quickly as possible.

EVQLV collaborates with Immunoprecise Antibodies (IPA), a company focused on the discovery of therapeutic antibodies. The collaboration will accelerate the effort to develop therapeutic candidates against COVID-19. EVQLV will identify and screen hundreds of millions of potential antibody treatments in only a few days - far beyond the capacity of any laboratory. IPA will produce and test the most promising antibody candidates.

Andrew Satz and Brett Averso, who met while students at DSI, are deeply committed to using "data for good". The pair has worked together for several years at the intersection of data science and health care and formed EVQLV in December 2019 to use AI to accelerate the speed at which healing is discovered, developed, and delivered. The company has already grown to 12 team members with skills ranging from machine learning and molecular biology to software engineering and antibody design, cloud computing, and clinical development.

Both DSI graduates typically put in 100-hour work weeks because they are passionate about and committed to using data science to "help heal those in need".

"We are building a company that sits at the frontiers of AI and biotech", Andrew Satz stated. "We are hard at work accelerating the speed at which healing is discovered and delivered and could not ask for a more fulfilling mission."

Source: Data Science Institute at Columbia

Back to Table of contents

Primeur weekly 2020-03-23

Crowd computing

Crowdsourced supercomputing project sets sights on coronavirus ...

Focus on Europe

LEXIS: novel computing systems at IT4Innovations and Leibniz Rechenzentrum (LRZ) ...

Exscalate4CoV supercomputing platform wins 3 million euro EU funding to hunt for new drugs against coronavirus pandemic ...

Open collaborative infrastructure to tackle public health emergencies ...

AMPERE Project: Strengthening European leadership in energy-efficiency and parallel computing ...

The European Commission offers significant support to Europe's AI excellence ...

Middleware

Atipa Technologies becomes the latest organisation to join the Bright Reseller Programme in North America ...

Hardware

Rittal announces its first HPC Direct Chip Cooling solution with ZutaCore ...

Intel scales neuromorphic research system to 100 million neurons ...

COVID-19 to have significant effect on worldwide semiconductor market in 2020, according to IDC ...

Foundry revenue estimated to grow by 30% YoY in 1Q20, while COVID-19 pandemic may hinder future market demand, according to TrendForce ...

MEGWARE to provide IBM Power in its Benchmark Center ...

Rescale partners with Google Cloud and Microsoft Azure to accelerate the race for COVID-19 vaccine with Cloud supercomputers for researchers ...

Applications

Cadence digital full flow optimized to deliver improved quality of results with up to 3x faster throughput ...

Supercomputers unlock reproductive mysteries of viruses and life ...

RIKEN is exploring the molecular dynamics of the new coronavirus ...

Rensselaer offers AiMOS supercomputing capabilities to battle COVID-19 ...

Scientists discover critical protein that lets COVID-19 virus hide from immune system ...

NVIDIA gives COVID-19 researchers free access to Parabricks ...

Pioneers of modern computer graphics recognized with ACM A.M. Turing Award ...

Data Science Institute alumni use machine learning to discover coronavirus treatments ...

Berkeley lab cosmologists are top contenders in machine learning challenge ...

New satellite-based algorithm pinpoints crop water use ...

Northern Data announces revenue and earnings forecast for 2020 ...

The Cloud

Qumulo offers free Cloud software to help medical and health care research organisations fight the COVID-19 outbreak ...