Connect with us

Artificial Intelligence

European Commission Reveals Rules & Actions for AI in the European Union

Published

on

Today, the European Commission proposed new rules and actions as part of an effort to turn the European Union into a global hub for Artificial Intelligence (AI).

The “first-ever” legal framework is designed to ensure trust and safety while fostering AI innovation.

In a speech by EC Executive Vice President Margarethe Vestager, five obligations were outlined for AI in Europe:

  • AI providers are required to feed their systems with high-quality data to make sure the results don’t come out biased or discriminating;
  • They also need to give detailed documentation about how their AI systems work, for authorities to assess their compliance;
  • Providers must share substantial information with users to help them understand and properly use AI systems;
  • they have to ensure an appropriate level of human oversight both in the design and implementation of Artificial Intelligence;
  • and finally, they must respect the highest standards of cybersecurity and accuracy.

Vestager said that their strategy for Europe’s digital future, is to create, “an ecosystem of trust goes together with an ecosystem of excellence.”

“For Europe to become a global leader in trustworthy AI, we need to give businesses access to the best conditions to build advanced AI systems,” said Vestager. ” This is the idea behind our revised coordinated plan on Artificial Intelligence. It coordinates the investments across Member States to ensure that money from Digital Europe and Horizon Europe programs is spent where we need it the most. For instance in high-performance computing or to create facilities to test and improve AI systems.”

In a statement by the Commission, high-risk AI systems were outlined:

  • Critical infrastructures (e.g. transport), that could put the life and health of citizens at risk;
  • Educational or vocational training, that may determine the access to education and professional course of someone’s life (e.g. scoring of exams);
  • Safety components of products (e.g. AI application in robot-assisted surgery);
  • Employment, workers management and access to self-employment (e.g. CV-sorting software for recruitment procedures);
  • Essential private and public services (e.g. credit scoring denying citizens opportunity to obtain a loan);
  • Law enforcement that may interfere with people’s fundamental rights (e.g. evaluation of the reliability of evidence);
  • Migration, asylum and border control management (e.g. verification of authenticity of travel documents);
  • Administration of justice and democratic processes (e.g. applying the law to a concrete set of facts).
  • High-risk AI systems will be subject to strict obligations before they can be put on the market:

Adequate risk assessment and mitigation systems;

  1. High quality of the datasets feeding the system to minimise risks and discriminatory outcomes;
  2. Logging of activity to ensure traceability of results;
  3. Detailed documentation providing all information necessary on the system and its purpose for authorities to assess its compliance;
  4. Clear and adequate information to the user;
  5. Appropriate human oversight measures to minimise risk;
  6. High level of robustness, security and accuracy.

Overall, the goal is to create “enabling conditions for AI to grow and develop. Next steps in the policy initiative include having European Parliament and the Member States adopting the Commission’s proposals on the approach for AI, as well as Machinery Products, in the legislative procedure. Once adopted, the Regulations will be directly applicable across the EU.

Of course, AI is already fairly prolific within various industries – financial services being a key benefactor from the technology.

The EU plans to dedicate €1 billion per year in AI while attracting over €20 billion in overall investment in AI – each year.

Only time will tell if this structured approach will drive greater innovation and adoption or if a more laissez-faire policy may be superior.

The new rules, as well as Q&As, are available here.

Coinsmart. Beste Bitcoin-Börse in Europa
Source: https://www.crowdfundinsider.com/2021/04/174467-european-commission-reveals-rules-actions-for-ai-in-the-european-union/

AI

This AI Performs Seamless Video Manipulation Without Deep Learning or Datasets

Published

on

Have you ever wanted to edit a video to remove or add someone, change the background, make it last a bit longer, or change the resolution to fit a specific aspect ratio without compressing or stretching it? For those of you who already ran advertisement campaigns, you certainly wanted to have variations of your videos for AB testing and see what works best. Well, this new research by Niv Haim et al. can help you do all of the about in a single video and in HD! Indeed, using a simple video, you can perform any tasks I just mentioned in seconds or a few minutes for high-quality videos. You can basically use it for any video manipulation or video generation application you have in mind. It even outperforms GANs in all ways and doesn’t use any deep learning fancy research nor requires a huge and impractical dataset! And the best thing is that this technique is scalable to high-resolution videos

image

Louis Bouchard Hacker Noon profile picture

Louis Bouchard

I explain Artificial Intelligence terms and news to non-experts.

Have you ever wanted to edit a video to remove or add someone, change the background, make it last a bit longer, or change the resolution to fit a specific aspect ratio without compressing or stretching it? For those of you who already ran advertisement campaigns, you certainly wanted to have variations of your videos for AB testing and see what works best.

Well, this new research by Niv Haim et al. can help you do all of the about in a single video and in HD!

Indeed, using a simple video, you can perform any tasks I just mentioned in seconds or a few minutes for high-quality videos. You can basically use it for any video manipulation or video generation application you have in mind. It even outperforms GANs in all ways and doesn’t use any deep learning fancy research nor requires a huge and impractical dataset!

And the best thing is that this technique is scalable to high-resolution videos…

Watch the video

References

►Read the full article: https://www.louisbouchard.ai/vgpnn-ge…
►Paper covered: Haim, N., Feinstein, B., Granot, N., Shocher, A., Bagon, S., Dekel, T., & Irani, M. (2021). Diverse Generation from a Single Video Made Possible. ArXiv, abs/2109.08591.
►The technique that was adapted from images to videos: Niv Granot, Ben Feinstein, Assaf Shocher, Shai Bagon, and Michal Irani. Drop the gan: In defense of patches nearest neighbors as single image generative models. arXiv preprint arXiv:2103.15545, 2021.
►Code (available soon): https://nivha.github.io/vgpnn/
►My Newsletter (A new AI application explained weekly to your emails!): https://www.louisbouchard.ai/newsletter/

Video Transcript

00:00

have you ever wanted to edit a video

00:02

remove or add someone change the

00:04

background make it last a bit longer or

00:06

change the resolution to fit a specific

00:08

aspect ratio without compressing or

00:10

stretching it for those of you who

00:12

already ran advertisement campaigns you

00:14

certainly wanted to have variations of

00:16

your videos for a b testing and see what

00:19

works best well this new research by niv

00:22

haim ital can help you do all of these

00:24

out of a single video and in high

00:27

definition indeed using a simple video

00:29

you can perform any tasks i just

00:32

mentioned in seconds or in a few minutes

00:34

for high quality videos you can

00:36

basically use it for any video

00:38

manipulation or video generation

00:40

application you have in mind it even

00:42

outperforms guns in any ways and doesn’t

00:45

use any deep learning fancy research nor

00:48

requires a huge and impractical data set

00:51

and the best thing is that this

00:52

technique is scalable to high resolution

00:55

videos it is not only for research

00:57

purposes with 256 by 256 pixel videos oh

01:01

and of course you can use it with images

01:04

let’s see how it works the model is

01:06

called video based generative patch

01:08

nearest neighbors vgpnn instead of using

01:11

complex algorithms and models like gans

01:14

or transformers the researchers that

01:16

developed vgpn opt for a much simpler

01:19

approach but revisited the nearest

01:22

neighbor algorithm first they downscale

01:24

the image in a pyramid way where each

01:26

level is a flower resolution than the

01:28

one above then they add random noise to

01:31

the coarsest level to generate a

01:33

different image similar to what guns do

01:36

in the compressed space after encoding

01:38

the image note that here i will say

01:40

image for simplicity but in this case

01:42

since it’s applied to videos the process

01:45

is made on three frames simultaneously

01:48

adding a time dimension but the

01:49

explanation stays the same with an extra

01:52

step at the end the image at the

01:54

coarsest scale with noise added is

01:56

divided into multiple small square

01:59

patches all patches in the image with

02:01

noise added are replaced with the most

02:04

similar patch from the initial scaled

02:06

down image without noise this most

02:09

similar patch is measured with the

02:11

nearest neighbor algorithm as we will

02:13

see most of these patches will stay the

02:15

same but depending on the added noise

02:17

some patches will change just enough to

02:19

make them look more similar to another

02:21

patch in the initial image this is the

02:24

vpn output you see here these changes

02:27

are just enough to generate a new

02:29

version of the image then this first

02:31

output is upscaled and used to compare

02:34

with the input image of the next scale

02:36

to act as a noisy version of it and the

02:38

same steps are repeated in this next

02:41

iteration we split these images into

02:43

small patches and replace the previously

02:45

generated ones with the most similar

02:48

ones at the current step let’s get into

02:50

this vpn module we just covered as you

02:53

can see here the only difference from

02:55

the initial step with noise added is

02:58

that we compare the upscale generated

03:00

image here denoted as q with an upscaled

03:03

version of the previous image just so it

03:06

has the same level of details denoted as

03:09

k basically using the level below as

03:12

comparisons we compare q and k and then

03:15

select corresponding patches in the

03:17

image from this current level v to

03:20

generate the new image for this step

03:22

which will be used for the next

03:24

iteration as you see here with the small

03:26

arrows k is just an upscale version of

03:28

the image we created downscaling v in

03:31

the initial step of this algorithm where

03:33

we created the pyramidal scaling

03:35

versions of our image this is done to

03:38

compare the same level of sharpness in

03:40

both images as the upscale generated

03:42

image from the previous layer q will be

03:45

much more blurry than the image at the

03:48

current step v and it will be very hard

03:50

to find similar patches this is repeated

03:53

until we get back to the top of the

03:54

pyramid with high resolution results

03:57

then all these generated patches are

03:59

folded into a video and voila you can

04:02

repeat this with different noises or

04:04

modifications to generate any variations

04:06

you want on your videos let’s do a quick

04:09

recap the image is downscaled at

04:11

multiple scales noise is added to the

04:13

corsa scale image which is divided into

04:16

small square patches each noisy patch is

04:18

then replaced with the most similar

04:20

patches from the same compressed image

04:23

without noise causing few random changes

04:26

in the image while keeping realism both

04:28

the newly generated image and image

04:31

without noise of this step are upscaled

04:33

and compared to find the most similar

04:36

patches with the nearest neighbor again

04:38

these most similar patches are then

04:40

chosen from the image at the current

04:42

resolution to generate a new image for

04:45

the step again and we repeat this

04:47

upscaling and comparing steps until we

04:49

get back to the top of the pyramid with

04:52

high resolution results of course the

04:54

results are not perfect you can still

04:56

see some artifacts like people appearing

04:58

and disappearing at weird places or

05:00

simply copy-pasting someone in some

05:02

cases making it very obvious if you

05:05

focus on it still it’s only the first

05:07

paper attacking video manipulations with

05:09

the nearest neighbor algorithm and

05:11

making it scalable to high resolution

05:13

videos it’s always awesome to see

05:15

different approaches i’m super excited

05:18

to see the next paper improving upon

05:20

this one also the results are still

05:22

quite impressive and they could be used

05:24

as a data augmentation tool for models

05:26

working on videos due to their very low

05:29

run time allowing other models to train

05:31

on larger and more diverse data sets

05:33

without much cost if you are interested

05:35

in learning more about this technique i

05:37

will strongly recommend reading their

05:38

paper it is the first link in the

05:40

description thank you for watching and

05:42

to everyone supporting my work on

05:44

patreon or by commenting and liking the

05:46

videos here on youtube

05:54

you

English (auto-generated)

All

Recently uploaded

Watched

Tags

Join Hacker Noon

Create your free account to unlock your custom reading experience.

PlatoAi. Web3 Reimagined. Data Intelligence Amplified.
Click here to access.

Source: https://hackernoon.com/this-ai-performs-seamless-video-manipulation-without-deep-learning-or-datasets?source=rss

Continue Reading

Artificial Intelligence

DeFi and Web 3.0: Unleashing creative juices with decentralized finance

Published

on

Decentralized technologies are starting to revolutionize the world of finance, with cryptocurrencies applied in different ways to recreate traditional financial instruments. However, since cryptocurrencies aren’t backed by anything but people’s faith in them, they are extremely volatile. That means, when it comes to loaning value with crypto, neither party can be sure that they will get a fair deal.

There needs to be a way to secure the value of the assets loaned, which can be done by backing them up with a value in the real world. Here is where the tokenization of real assets comes in. This process is pretty straightforward when we consider tangible assets like a building or gold bars, but what about intangible assets like intellectual property?

Related: Understanding the systemic shift from digitization to tokenization of financial services

The rise of the creator economy has led to intangible assets accounting for over 90% of the S&P 500’s market value, a figure that is only set to grow. There needs to be a way to unlock more creativity to realize the potential of human capital.

Kickstarting creator financing

Finding a start with financing in the creator economy is a great challenge, especially for newcomers. As many entrepreneurs in this segment discover, sometimes it is much easier to give away a good idea than to create a business out of that idea.

Creativity, by definition, disrupts what came before; it’s about new ideas, new technologies, new products, new services and new ways of doing things. Driven in large part by the digital revolution, many creative industries are not just innovative in what they do but in how they do it.

Related: Bull or bear market, creators are diving headfirst into crypto

Raising funds may be difficult for several reasons. For one, banks and investors tend to be conservative. They like certainty and are unlikely to be impressed by an enthusiastic entrepreneur convinced that an entirely new and untried idea — whether it is a design, a software tool, a fashion concept or a video game — will be a commercial success. Furthermore, banks want collateral for their loans, but many creative businesses have no capital assets to offer.

Stumbling blocks in the state of play

Investors specializing in creative industries may indeed recognize an entrepreneur’s genius. But in return for their investment, they often want some ownership of the idea and, therefore, some control over its development and marketing. This may not seem acceptable to the creative entrepreneur who prefers debt-finance in the form of a loan rather than equity finance in the form of sharing ownership and control over the work with the investor.

Alex Shkor, the founder of DEIP — a company that is building a protocol for the creator economy — explained to me, “For creators to be able to tokenize their works and collateralize them for funding, there needs to be a set of smart contracts, which can register assets on-chain, issue NFTs, evaluate assets and manage both collateralization and liquidation in case of default.”

Loan framework for the creative economy

Just as loans can be issued in the real economy based on collateral, so can they be in the creator economy.

Imagine a game developer (let’s call them Jane) who begins working on a side project. After a while and some positive encouragement from friends and family, Jane decides to take the leap into converting their side project into a full-time job. But a few months down the line, and with slower progress than first anticipated, Jane’s funds start to dwindle; they begin to consider full-time roles again. This situation is a common one for budding creators out there.

However, with a decentralized platform for intellectual assets, Jane’s progress on their work could be assessed by a decentralized assessment system that pools the expertise of people in the domain to give the unfinished creation an appraisal guided by the intrinsic value of the idea. This inherent value is used as the input for the collateralization calculation, the loan value that it can be issued for. Jane can use the loan offered to them for whatever they like; in this case, to support themself while they finish the game’s development.

Moreover, with or without collateral, a small loan can be issued to newcomers. If Jane doesn’t have any project, ready-made or part-made creation, they still have the chance for initial financing as a newcomer to the platform. The loan amount will be smaller as it is unsecured, and the loan itself is backed by the segment decentralized autonomous organization (DAO) and budgets originating from its ecosystem fund. Sources of this fund come from transaction fees and bandwidth allocation payments of the underlying blockchain.

If loans are paid back on time, Jane’s personal credit rating will be upgraded. In this case, if Jane would like to apply for another loan, the collateralization factor will be less, enabling them to borrow more.

Should Jane default on their loan, any collateralized assets are assumed by the platform and can be sold off to recoup the funds via smart liquidation contracts. If Jane hasn’t collateralized anything, the default risk is realized by the platform and covered by the DAO.

As long as the creator’s credit history is solid and positively confirmed with each new loan, the next tranche can be issued with iteratively improved terms and conditions. Credit history becomes an integral and immutable part of the reputational profile of the creator. As Shkor noted:

“he whole purpose of Web 3.0 is to enable a decentralized creator economy nd all the tech for this already exists.”

He continued, “We just need to foster adoption of these technologies in real industries, in creative industries, for the assets produced by creators. It will not only increase liquidity of the creator economy assets, it will also open a flow of capital to creators.”

The views, thoughts and opinions expressed here are the author’s alone and do not necessarily reflect or represent the views and opinions of Cointelegraph.

Alexandra Luzan is a Ph.D. student researching the connection between new technologies and art at Ca’ Foscari University in Venice. For about a decade, Alexandra has been organizing tech conferences and other events in Europe dedicated to blockchain technology and artificial intelligence. She is equally interested in the relationship between blockchain tech and art.


PlatoAi. Web3 Reimagined. Data Intelligence Amplified.

Click here to access.

Source: https://cointelegraph.com/news/defi-and-web-3-0-unleashing-creative-juices-with-decentralized-finance

PlatoAi. Web3 Reimagined. Data Intelligence Amplified.
Click here to access.

Source: https://coingenius.news/defi-and-web-3-0-unleashing-creative-juices-with-decentralized-finance/?utm_source=rss&utm_medium=rss&utm_campaign=defi-and-web-3-0-unleashing-creative-juices-with-decentralized-finance

Continue Reading

Artificial Intelligence

‘Iron Men’ to Rise in AI-Augmented Business Landscape

Published

on

A World Economic Forum study projects up to 85 million jobs could be lost to these smart machines. The same study also projects that the new division of labour between humans and machines will create 97 million new roles to offset what was lost. The rise of personal computers, which was predicted to cause massive job losses, created even more jobs (19.3 million) in the US than it destroyed (3.5 million) from 1970 to 2015. In the end, AI will always just be a tool, says Emapta’s Chief Technology Officer.

image

Emapta Hacker Noon profile picture

Emapta

Emapta is a full-service outsourcing company that helps businesses lower labor costs, and scale fast.

“Robots” are here, and they are here to stay.

Artificial Intelligence (AI) is silently taking its roots in the modern world. It has created smart homes and offices, boosted security with facial recognition technology, assisted drivers in navigating rush hour traffic, and made people like or buy things through behaviour-reading predictive algorithms.

While AI is making a lot of things easier, some people fear that these “robots” will take over their jobs. With AI demonstrating its incredible ability to mimic or even surpass human capabilities, their fear. Or is it?

World Economic Forum study published in 2020 projects up to 85 million jobs could be lost to these smart machines. On a positive note, the same study also projects that the new division of labour between humans and machines will create 97 million new roles to offset what was lost.

There is historical data to support how AI can lead to more jobs even in the Business Process Outsourcing (BPO) industry, a veteran IT leader said, citing how the first Industrial Revolutions could have a massive negative impact on human work.

“People were scared that the development of machines during the Industrial Revolution was going to take away jobs, but instead it changed the way we work and in fact created more jobs,” said Henry Vassall Jones, Emapta’s Chief Technology Officer.

A McKinsey Global Institute research published in 2017 shared some proof of this outcome, showing how the rise of personal computers, which was predicted to cause massive job losses, created even more jobs (19.3 million) in the US than it destroyed (3.5 million) from 1970 to 2015.

image

It even gave rise to some of the industry giants today like Oracle, IBM, and Microsoft.

The same goes with rise of AI or the so-called “Fourth Industrial Revolution,” the McKinsey study said, stressing that adopting smart automated systems will have varied effects in different industries. It also suggested that parts of work, not actual job roles per se, will feel the impact of AI adoption.

“Activities most susceptible to automation include physical ones in predictable environments, such as operating machinery and preparing fast food. Collecting and processing data are two other categories of activities that increasingly can be done better and faster with machines,” the paper showed.

“It is important to note, however, that even when some tasks are automated, employment in those occupations may not decline but rather workers may perform new tasks,” it added, stressing AI will have lesser impact on roles that involve managing people, applying expertise, and social interactions.

Some of the industries that are projected to see employment growth with the rise of AI include IT professionals, technology specialists, engineers, scientists, accountants, machine educators, artists, healthcare providers, builders, and manual service jobs in unpredictable environments.

Harnessing AI to create working “Iron Men”

In the end, AI will always just be a tool, added Roy Figueroa, whose job as Emapta’s Client Solutions Director includes managing and dealing with leaders from different industries. These smart machines, he stressed, will always need human intervention.

“AIs need to be programmed correctly to be useful and efficient. And they’ll need constant reprogramming as our needs change. AIs have and will continue to replace humans in the performance of routinary tasks just like machines took over the production lines in factories,” he said.

“However, the software engineers and the people involved in the training of AIs will always be a necessity just like the mechanical engineers are now to machines or robots in production lines,” he added.

Henry added that while AIs can collect and organise data faster than humans, in the end, it will still be the people who will have to interpret the information.

“A machine can do things faster. It can analyse much larger data sets, provide analytics and statistics which would take a human longer, but also somebody needs to be there to interpret, and it’s still going to be the people,” he said.

The same goes for labour, a 2018 research by accounting firm PwC explained, noting that the combination of AI and humans – “Iron Men” of sorts – will become the new normal in the workforce of the future.

“A human engineer defines a part’s materials, desired features, and various constraints, and inputs it into an AI system, which generates a number of simulations. Engineers then either choose one of the options or refine their inputs and ask the AI to try again,” it said.

AI will need continual tweaking and customising for it to be adopted by businesses, the study added, which will need “functional specialists” like economists, analysts, and traders who can identify where the AI can best support human asset managers, help design and train the AI.

An AI-augmented BPO industry

Henry believes the BPO industry will play a major role when businesses begin to fully embrace AI. Offshoring firms like Emapta will be able to respond to a potential increase in demand.

“I think that the start-up industry and the IT sector can definitely benefit from Emapta’s services because we’re able to provide skilled resources that would be able to work on these projects,” he said.

image

AI will also help workers of the BPO industry to reduce routine or repetitive tasks, like data entry, transcription, approvals, request updates — tasks that consume precious work hours — so the workers can focus on the most important aspects of the job.

“A closer review of what everyone does versus what available technology offers in terms of data management, and customer relationship management, will show that we perform a lot of repetitive tasks that otherwise would bog down businesses,” Roy added.

Roy said harnessing AI and bots is aligned with the clients’ primary objective when outsourcing or offshoring, which is to reduce cost through employment of less expensive but higher quality team members.

Henry and Roy also agree that if there’s one thing that can’t be replicated by AIs is to have an emotional connection to the work being done. This human element is important, especially when understanding and empathising with the customers.

The Philippines, through the Department of Trade and Industry (DTI), has already launched its “AI Roadmap” last May. The program’s goal is to make the Philippines a “central AI hub” in Southeast Asia.

With the continuous improvement of the country’s infrastructures and the entry of new players in the telecommunications industry, the future of tech and AI in the Philippines is bright, and Emapta is ready to reap its benefits.

And while AI is seen to make work efficient for people, Emapta continues to make business efficient for companies of all sizes. Emapta is a full-service outsourcing specialist that has been helping businesses reduce risk and lower cost across the globe for over a decade now.

With the mantra “Your Team, Your Way,” Emapta provides total flexibility to businesses with fully customizable office/home setup, culture and IT configuration. It has been helping businesses scale by leveraging top talent and business process expertise.

Tags

Join Hacker Noon

Create your free account to unlock your custom reading experience.

PlatoAi. Web3 Reimagined. Data Intelligence Amplified.
Click here to access.

Source: https://hackernoon.com/iron-men-to-rise-in-ai-augmented-business-landscape?source=rss

Continue Reading

Artificial Intelligence

Deep learning helps predict new drug combinations to fight Covid-19

Published

on

The existential threat of Covid-19 has highlighted an acute need to develop working therapeutics against emerging health concerns. One of the luxuries deep learning has afforded us is the ability to modify the landscape as it unfolds — so long as we can keep up with the viral threat, and access the right data. 

As with all new medical maladies, oftentimes the data need time to catch up, and the virus takes no time to slow down, posing a difficult challenge as it can quickly mutate and become resistant to existing drugs. This led scientists from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Jameel Clinic for Machine Learning in Health to ask: How can we identify the right synergistic drug combinations for the rapidly spreading SARS-CoV-2? 

Typically, data scientists use deep learning to pick out drug combinations with large existing datasets for things like cancer and cardiovascular disease, but, understandably, they can’t be used for new illnesses with limited data.

Without the necessary facts and figures, the team needed a new approach: a neural network that wears two hats. Since drug synergy often occurs through inhibition of biological targets (like proteins or nucleic acids), the model jointly learns drug-target interaction and drug-drug synergy to mine new combinations. The drug-target predictor models the interaction between a drug and a set of known biological targets that are related to the chosen disease. The target-disease association predictor learns to understand a drug’s antiviral activity, which means determining the virus yield in infected tissue cultures. Together, they can predict the synergy of two drugs. 

Two new drug combinations were found using this approach: remdesivir (currently approved by the FDA to treat Covid-19) and reserpine, as well as remdesivir and IQ-1S, which, in biological assays, proved powerful against the virus. The study has been published in the Proceedings of the National Academy of Sciences.

“By modeling interactions between drugs and biological targets, we can significantly decrease the dependence on combination synergy data,” says Wengong Jin SM ’18, a postdoc at the Broad Institute of MIT and Harvard who recently completed his doctoral work in CSAIL, and who is the lead author on a new paper about the research. “In contrast to previous approaches using drug-target interaction as fixed descriptors, our method learns to predict drug-target interaction from molecular structures. This is advantageous since a large proportion of compounds have incomplete drug-target interaction information.” 

Using multiple medications to maximize potency, while also decreasing side effects, is practically ubiquitous for aforementioned cancer and cardiovascular disease, including a host of others such as tuberculosis, leprosy, and malaria. Using specialized drug cocktails can, quite importantly, reduce the grave and sometimes public threat of resistance (think methicillin-resistant Staphylococcus aureus known as “MRSA”), since many drug-resistant mutations are mutually exclusive. It’s much harder for a virus to develop two mutations at the same time and then become resistant to two drugs in a combination therapy. 

Importantly, the model isn’t limited to just one SARS-CoV-2 strain — it could also potentially be used for the increasingly contagious Delta variant or other variants of concern that may arise. To extend the model’s efficacy against these strains, you’d only need additional drug combination synergy data for the relevant mutation(s). In addition, the team applied their approach to HIV and pancreatic cancer.

To further refine their biological modeling down the line, the team plans to incorporate additional information such as protein-protein interaction and gene regulatory networks. 

Another direction for future work they’re exploring is something called “active learning.” Many drug combination models are biased toward certain chemical spaces due to their limited size, so there’s high uncertainty in predictions. Active learning helps guide the data collection process and improve accuracy in a wider chemical space. 

Jin wrote the paper alongside Jonathan M. Stokes, Banting Fellow at The Broad Institute of MIT and Harvard; Richard T. Eastman, a scientist at the National Center for Advancing Translational Sciences; Zina Itkin, a scientist at National Institutes of Health; Alexey V. Zakharo, informatics lead at the National Center for Advancing Translational Sciences (NCATS); James J. Collins, professor of biological engineering at MIT; and Tommi S. Jaakkola and Regina Barzilay, MIT professors of electrical engineering and computer science at MIT.

This project is supported by the Abdul Latif Jameel Clinic for Machine Learning in Health; the Defense Threat Reduction Agency; Patrick J. McGovern Foundation; the DARPA Accelerated Molecular Discovery program; and in part by the Intramural/Extramural Research Program of the National Center for Advancing Translational Sciences within the National Institutes of Health.

PlatoAi. Web3 Reimagined. Data Intelligence Amplified.
Click here to access.

Source: https://news.mit.edu/2021/deep-learning-helps-predict-new-drug-combinations-fight-covid-19-0924

Continue Reading
Esports4 days ago

How to start a Private Queue in CS:GO

Esports3 days ago

Can You Play Diablo II: Resurrected Offline?

Esports4 days ago

How to complete all week one missions in Operation Riptide

Esports4 days ago

Failed to Enter Game, Character Could Not be Found: How to Fix Error in Diablo II: Resurrected

Esports4 days ago

Valkyrae says YouTube is working on gifted members and a feature similar to Twitch Prime

Esports2 days ago

Fall Guys achieves Guinness World Record for most downloaded PlayStation Plus game ever

Esports4 days ago

Valkyrae says YouTube is working on gifted members and a feature similar to Twitch Prime

Esports4 days ago

Initial reactions to the Worlds 2021 group draw: How does each team stack up against the field?

Esports5 days ago

Pokémon UNITE APK and OBB download links for Android

Esports3 days ago

Microsoft’s The Initiative brings on Crystal Dynamics to help develop its Perfect Dark reboot

Esports4 days ago

CS:GO Riptide Case: Full List of New Skins

Esports3 days ago

How to check Diablo 2: Resurrected server status

Esports5 days ago

Some players unable to claim Pokémon UNITE mobile pre-registration rewards due to new error

Esports3 days ago

Best Stats for the Druid in Diablo II: Resurrected

Blockchain4 days ago

United States Infrastructure Bill Brings Cardano Billionaire to Washington.

Esports5 days ago

How to redeem Operation Riptide’s rewards in CS:GO

Energy5 days ago

Carbon Nanotubes Market size worth $ 20.31 Billion, Globally, by 2028 at 17.27% CAGR: Verified Market Research®

Cyber Security4 days ago

Apple bans Epic Games from App Store

Esports4 days ago

Failed to Enter Game, Character Could Not be Found: How to Fix Error in Diablo II: Resurrected

Esports2 days ago

NBA 2K22 ‘Meet the Designers’ Quest Guide: How to Complete

Trending