Near future
Contact us
  • Home
  • Tech
  • Health
  • Environment
  • Architecture
  • Energy
  • Transportation
  • Spazio
  • AI
  • concepts
  • Gadgets
  • Italy Next
  • H+
August 7 2022

Coronavirus / Russia-Ukraine

Near future

News to understand, anticipate, improve the future.

No Result
View All Result

News to understand, anticipate, improve the future.

Read in:  Chinese (Simplified)EnglishFrenchGermanItalianJapanesePortugueseRussianSpanish

Machine learning now generates realistic genomes of people who don't exist

We have seen GAN generate faces, fake biographies, songs. Now they also generate artificial genomes, mostly indistinguishable from the real one.

Gianluca Ricciodi Gianluca Riccio
in Technology
Share23Pin6Tweet14SendShare4ShareShare3
artificial genome
February 5 2021
⚪ Reads in 3 minutes
A A

Between new algorithms and IT advances, machines can now learn increasingly complex models. They come to generate high quality synthetic data such as photorealistic images, and even resumes of imaginary humans.

Time a study published in the international journal PLOS Genetics shows the advanced use of machine learning on biometric data. From existing biobanks, the system generates entire blocks of human genome that do not belong to real humans but have the characteristics of a real genome.

Bypassing the privacy issue

“Existing genomic databases are an invaluable resource for biomedical research," He says Burak Yelmen, first author of the study and Junior Research Fellow of Modern Population Genetics at the University of Tartu. “The problem is that they are not publicly accessible or protected by lengthy and exhausting enforcement procedures due to valid ethical concerns. This creates an important scientific barrier for researchers. A genome generated by machines, an "artificial genome", can help us overcome the problem within a safe ethical framework ".

A chromosome emerges from random digital noise. Credit: Burak Yelmen

The multidisciplinary team performed more analyzes to assess the quality of the genome generated by machine learning compared to the real one. "Surprisingly, this genome mimics the complexities that we can observe within real human populations and, for most properties, they are indistinguishable from the other genomes of the biobank used to train our algorithm. Except for one detail: they don't belong to any gene donor, ”said the dr. Luca Pagani, one of the study's senior authors and fellow Mobilitas Pluss.

The article continues after the related links

Denmark, an AI-led “Synthetic Party” points to parliament

New hardware from MIT with analog synapses: 1 million faster than the human brain

Customer support: Will it be in the hands of chatbots within 5 years?

Moving Beehive Mobility, autonomous hives with AI for the beekeeping of the future

A machine-generated genome, an "artificial genome", can help us overcome the problem within a safe ethical framework

Burak Yelmen
artificial genome
A generating machine makes a random noise while a discriminating machine tests the generated data against a database of available real data. Once the process is complete, the algorithm will generate artificial data that looks like real data, but is actually completely new. Credit: Yelmen et al. 2021

Is it really original genome or a "spit" copy?

The study also provides for the assessment of the proximity of the artificial genome to the real genome to verify whether the privacy of the original samples is preserved. “While detecting privacy leaks across thousands of genomes might seem like a search for a needle in a haystack, the combination of multiple statistical measures allows us to closely monitor all models. Interestingly, the detailed exploration of complex dispersion patterns leads in turn to other improvements in the evaluation of GAN and it will fuel the field of machine learning ”. To say it is Dr. Flora Jay, study coordinator and researcher of the CNRS, French National Center for Scientific Research).

All in all, the machine learning approaches already provided turned, biographies and many other features to a handful of imaginary human beings. We now know more about their biology as well. These fictional humans with realistic genomes could serve as an experimental bench in place of real genomes that are not publicly available.

The research could remove an important accessibility barrier in genomic research, particularly for under-represented populations.

tags: genomeartificial intelligenceMachine learning
Previous post

A self-sustainable “mini continent” against ocean waste

Next Post

Does the universe have a new particle and a fifth dimension?

COLLABORATE

To submit articles, disclose the results of a research or scientific discoveries write to the editorial staff
  • New hardware from MIT with analog synapses: 1 million faster than the human brain

    New hardware from MIT with analog synapses: 1 million faster than the human brain

    44 Shares
    Share 17 Tweet 11
  • Nuclear, for Goldman Sachs is not a transformative technology

    26 Shares
    Share 10 Tweet 7
  • Transforming dead spiders into robots: a few words on necrobotics

    25 Shares
    Share 10 Tweet 6
  • Denmark, an AI-led “Synthetic Party” points to parliament

    15 Shares
    Share 5 Tweet 3
  • Cobi, 'Transformer' wheelchair that becomes a cane and walker

    12 Shares
    Share 5 Tweet 3

archive

Have a look here:

USA and China
Military

How could we slide into a war between the US and China

Two nations on the road, a thousand reasons for conflict and a battleground that could trigger the spark. USA...

Read More
Forget the foam: the "liquid" helmet mimics the brain to protect the head.

Forget the foam: the "liquid" helmet mimics the brain to protect the head.

Tasmania claims to be powered 100% by renewable electricity

Tasmania claims to be powered 100% by renewable electricity

Here are the nanoverms, future allies of our health

Here are the nanoverms, future allies of our health

A conflict between China and Taiwan would be the semiconductor apocalypse

A conflict between China and Taiwan would be the semiconductor apocalypse

The daily tomorrow

Futuroprossimo.it provides news on the future of technology, science and innovation: if there is something that is about to arrive, here it has already arrived. FuturoProssimo is part of the network ForwardTo, studies and skills for future scenarios.

Subscribe to our newsletter

Environment
Architecture
Artificial intelligence
Gadgets
concepts
Design

Staff
Archives
Advertising
Privacy Policy

Medicine
Spazio
Robotica
Work
Transportation
Energy

To contact the FuturoProssimo editorial team, write to [email protected]

Chinese Version
Édition Française
Deutsche Ausgabe
Japanese version
English Edition
Edição Portuguesa
Русское издание
Spanish edition

This work is distributed under license Creative Commons Attribution 4.0 International.
© 2021 Futuroprossimo

No Result
View All Result
  • Home
  • Tech
  • Health
  • Environment
  • Architecture
  • Energy
  • Transportation
  • Spazio
  • AI
  • concepts
  • Gadgets
  • Italy Next
  • H+