e learning

Machine Learning Techniques for Classifying the Mutagenic Origins of Point Mutations [Methods, Technology, [amp ] Resources]

There is increasing interest in developing diagnostics that discriminate individual mutagenic mechanisms in a range of applications that include identifying population-specific mutagenesis and resolving distinct mutation signatures in cancer samples. Analyses for these applications assume that mutagenic mechanisms have a distinct relationship with neighboring bases that allows them to be distinguished. Direct support for this assumption is limited to a small number of simple cases, e.g., CpG hypermutability. We have evaluated whether the mechanistic origin of a point mutation can be resolved using only sequence context for a more complicated case. We contrasted single nucleotide variants originating from the multitude of mutagenic processes that normally operate in the mouse germline with those induced by the potent mutagen N-ethyl-N-nitrosourea (ENU). The considerable overlap in the mutation spectra of these two samples make this a challenging problem. Employing a new, robust log-linear modeling method, we demonstrate that neighboring bases contain information regarding point mutation direction that differs between the ENU-induced and spontaneous mutation variant classes. A logistic regression classifier exhibited strong performance at discriminating between the different mutation classes. Concordance between the feature set of the best classifier and information content analyses suggest our results can be generalized to other mutation classification problems. We conclude that machine learning can be used to build a practical classification tool to identify the mutation mechanism for individual genetic variants. Software implementing our approach is freely available under an open-source license.




e learning

Harnessing Population Pedigree Data and Machine Learning Methods to Identify Patterns of Familial Bladder Cancer Risk

Background:

Relatives of patients with bladder cancer have been shown to be at increased risk for kidney, lung, thyroid, and cervical cancer after correcting for smoking-related behaviors that may concentrate in some families. We demonstrate a novel approach to simultaneously assess risks for multiple cancers to identify distinct multicancer configurations (multiple different cancer types that cluster in relatives) surrounding patients with familial bladder cancer.

Methods:

This study takes advantage of a unique population-level data resource, the Utah Population Database (UPDB), containing vast genealogy and statewide cancer data. Familial risk is measured using standardized incidence risk (SIR) ratios that account for sex, age, birth cohort, and person-years of the pedigree members.

Results:

We identify 1,023 families with a significantly higher bladder cancer rate than population controls (familial bladder cancer). Familial SIRs are then calculated across 25 cancer types, and a weighted Gower distance with K-medoids clustering is used to identify familial multicancer configurations (FMC). We found five FMCs, each exhibiting a different pattern of cancer aggregation. Of the 25 cancer types studied, kidney and prostate cancers were most commonly enriched in the familial bladder cancer clusters. Laryngeal, lung, stomach, acute lymphocytic leukemia, Hodgkin disease, soft-tissue carcinoma, esophageal, breast, lung, uterine, thyroid, and melanoma cancers were the other cancer types with increased incidence in familial bladder cancer families.

Conclusions:

This study identified five familial bladder cancer FMCs showing unique risk patterns for cancers of other organs, suggesting phenotypic heterogeneity familial bladder cancer.

Impact:

FMC configurations could permit better definitions of cancer phenotypes (subtypes or multicancer) for gene discovery and environmental risk factor studies.






e learning

Want a Really Hard Machine Learning Problem? Try Agriculture, Says John Deere Labs

John Deere, the nearly 200-year-old tractor manufacturer, now considers itself a software company



  • robotics
  • robotics/artificial-intelligence

e learning

Researchers Are Learning How Asian Elephants Think—in Order to Save Them

As the pachyderms increasingly clash with farmers and villagers over disappearing land, scientists study the way the animals' minds work




e learning

Best language learning apps to perfect your skills before your next trip

Learning a language is good for brain-training so get out your smartphone and start downloading




e learning

"Very messy": Principals question premier's part-time learning plan

Premier Gladys Berejiklian wants students to resume learning under a roster system, but principals have slammed the idea as confusing and unrealistic




e learning

'Very messy': Principals question Premier's part-time learning plan

Premier Gladys Berejiklian wants students to resume learning under a roster system, but principals have slammed the idea as confusing and unrealistic.




e learning

"Very messy": Principals question premier's part-time learning plan

Premier Gladys Berejiklian wants students to resume learning under a roster system, but principals have slammed the idea as confusing and unrealistic




e learning

'Very messy': Principals question Premier's part-time learning plan

Premier Gladys Berejiklian wants students to resume learning under a roster system, but principals have slammed the idea as confusing and unrealistic.




e learning

"Very messy": Principals question premier's part-time learning plan

Premier Gladys Berejiklian wants students to resume learning under a roster system, but principals have slammed the idea as confusing and unrealistic




e learning

'Very messy': Principals question Premier's part-time learning plan

Premier Gladys Berejiklian wants students to resume learning under a roster system, but principals have slammed the idea as confusing and unrealistic.




e learning

Kate Middleton reveals what Prince George and Princess Charlotte are learning at school

The Duchess of Cambridge revealed that her eldest children, Prince George and Princess...




e learning

GSK hires computational drug design expert Dr Kim Branson as new head of machine learning and AI

British multinational GlaxoSmithKline have hired computational drug design expert Dr Kim Branson as the company’s new Senior Vice President, Global Head of Artificial Intelligence and Machine Learning.

In his new role, the biotech veteran will oversee projects which use AI to identify novel targets for potential medicines.

Dr Branson brings to the role more than 15 years’ worth of experience in biotech and academia having held positions at a number of Silicon Valley firms including Gliimpse, Lumia and Hessian Informatics.

read more




e learning

Justice Department Reaches Agreement with Indiana School District to Provide a Safe and Supportive Learning Environment for All Students

The Justice Department announced today that it reached a settlement agreement with the Metropolitan School District of Decatur Township, Ind., to prevent and respond to peer on peer harassment in schools.



  • OPA Press Releases

e learning

The COVID-19 Distance Learning: Insight from Ukrainian students

Nenko, Yuliia and Кybalna, Nelia and Snisarenko, Yana The COVID-19 Distance Learning: Insight from Ukrainian students. Revista Brasileira de Educação do Campo, 2020, vol. 5, pp. 1-19. [Journal article (Paginated)]




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

COVID-19 has thrust universities into online learning⁠—how should they adapt?

There is one golden rule for flying with an infant or toddler: Do whatever it takes to get through the flight peacefully with no harm done. Every parent knows this means relaxing their standards. Planting your kid in front of an iPad screen or giving them not so healthy treats might not win you a…

       




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Accumulating Evidence Using Crowdsourcing and Machine Learning: A Living Bibliography about Existential Risk and Global Catastrophic Risk

The study of existential risk — the risk of human extinction or the collapse of human civilization — has only recently emerged as an integrated field of research, and yet an overwhelming volume of relevant research has already been published. To provide an evidence base for policy and risk analysis, this research should be systematically reviewed. In a systematic review, one of many time-consuming tasks is to read the titles and abstracts of research publications, to see if they meet the inclusion criteria. The authors show how this task can be shared between multiple people (using crowdsourcing) and partially automated (using machine learning), as methods of handling an overwhelming volume of research.




e learning

Investigations into using data to improve learning

In 2010, the Australian Commonwealth Government, in partnership with the Australian states and territories, created an online tool called My School. The objective of My School was to enable the collation and publication of data about the nearly 10,000 schools across the country. Effectively offering a report card for each Australian school,[1] My School was…

      
 
 




e learning

5 traps that will kill online learning (and strategies to avoid them)

For perhaps the first time in recent memory, parents and teachers may be actively encouraging their children to spend more time on their electronic devices. Online learning has moved to the front stage as 90 percent of high-income countries are using it as the primary means of educational continuity amid the COVID-19 pandemic. If March will forever…

       




e learning

5 traps that will kill online learning (and strategies to avoid them)

For perhaps the first time in recent memory, parents and teachers may be actively encouraging their children to spend more time on their electronic devices. Online learning has moved to the front stage as 90 percent of high-income countries are using it as the primary means of educational continuity amid the COVID-19 pandemic. If March will forever…

       




e learning

5 traps that will kill online learning (and strategies to avoid them)

For perhaps the first time in recent memory, parents and teachers may be actively encouraging their children to spend more time on their electronic devices. Online learning has moved to the front stage as 90 percent of high-income countries are using it as the primary means of educational continuity amid the COVID-19 pandemic. If March will forever…

       




e learning

Where is the Learning? Measuring Schooling Efforts in Developing Countries

INTRODUCTION—

Achieving universal education is a twofold challenge: to get children and youth into school and then to teach them something meaningful while they are there. While important progress has been made on the first challenge, there is a crisis unfolding in relation to learning. Around the world, there have been major gains in primary school enrollment partly due to the United Nations’ Millennium Development Goals and the abolition of school fees by many national governments. However in many countries, students are spending years in school without learning core competencies, such as reading and writing. To address this learning crisis, the global community and national governments need to place a much greater focus on the ultimate objective of education—to acquire knowledge and develop skills.

This shift in focus away from just enrollment to enrollment plus quality learning requires measuring learning outcomes. However, the global education community is not yet systematically using effective instruments for measuring primary school learning in low- and middle-income countries. This policy brief reviews the global efforts among the primary donors to support the measurement of learning outcomes. It then suggests steps needed to transition global education policy into a new paradigm of enrollment plus quality learning, which includes: scaling up the implementation of national education accounts and national assessment systems; increasing attention to monitoring early learning during child development to improve readiness for school; and expanding the systematic use of simple assessments of basic cognitive functions in the early grades to help teachers improve their practice.

Downloads

Authors

     
 
 




e learning

Water on the Brain. We're Learning. Slowly.

Residents of the driest inhabited continent, Australia, have evidently been cottoning onto the fact that water means life and we need to be more thoughtful in our use of this rather precious resource. Since the year 2000, Australians have managed to




e learning

Thousands of children in Malawi are learning how to grow food at school

The Malawi Schools Permaculture Clubs, a recipient of the 2018 Lush Spring Prize, provides basic gardening kits and lesson packs to teachers in order to teach valuable agricultural skills.




e learning

Bayer Pledges 1 Million Hands-On Science Learning Experiences For Children By 2020 To Help Inspire Next Generation Of Innovators - Bayer MSMS “Say TkU” Campaign

Bayer MSMS “Say TkU” Campaign




e learning

Halfway through one of the strangest earnings seasons ever, here's what we are learning

Most companies are not giving earnings guidance, leaving investors and analysts in the dark, yet the market is still rewarding better-than-expected results.




e learning

Helping journalists understand the power of machine learning

Editor’s note: What impact can AI and machine learning have on journalism? That is a question the Google News Initiative is exploring through a partnership with Polis, the international journalism think tank at the London School of Economics and Political Science. The following post is written by Mattia Peretti, who manages the program, called JournalismAI.

In the global survey we conducted last year about the use of artificial intelligence (AI) by news organizations, most respondents highlighted the urgent need to educate and train their newsroom on the potential offered by machine learning and other AI-powered technologies. Improving AI literacy was seen as vital to change culture and improve understanding of new tools and systems:

AI literacy is crucial. The more the newsroom at large embraces the technology and generates the ideas and expertise for AI projects, the better the outcome. New powers, new responsibilities:
A global survey of journalism and AI

The message from newsrooms was loud and clear. So we decided to do something about it. That’s why we’re announcing a free training course produced by JournalismAI in collaboration with VRT News and the Google News Initiative. 

This Introduction to Machine Learning is built by journalists, for journalists, and it will help answer questions such as: What is machine learning? How do you train a machine learning model? What can journalists and news organizations do with it and why is it important to use it responsibly?

The course is available in 17 different languages on the Google News Initiative Training Center. By logging in, you can track your progress and get a certificate when you complete the course. The Training Center also has a variety of other courses to help you find, verify and tell news stories online.


The Introduction to Machine Learning is available on the Google News Initiative Training Center in 17 different languages.

It’s a tough time for journalists and news organizations worldwide, as they try to assess the impact that COVID-19 will have on the business and editorial side of the industry. With JournalismAI, we want to play our role in helping to minimize costs and enhance opportunities for the industry through these new technologies. This course complements our recently launched collaborative experiment, as well as our effort to highlight profiles and experiments that show the transformative potential of AI and machine learning in shaping the journalist, and the journalism, of the future.

At the end of the course, you’ll find a list of recommended resources, produced by journalism and technology experts across the world, that have been instrumental in designing our Introduction to Machine Learning and will help you dive even deeper in the world of AI and automation. 

And we are not done. After this course, and the previous training module with strategic suggestions on AI adoption, we are planning to design more training resources on AI and machine learning for journalists later this year. Sign up for the JournalismAI newsletter to stay updated.



  • Google News Initiative

e learning

Make at-home learning more fun with 3D and AR in Search

Augmented reality (AR) in Search lets you bring 3D objects and animals into your space so you can turn your living room into a virtual zoo, explore the Apollo 11spacecraft up close, or take a picture with Santa. I love seeing how much fun families are having with this experience at home. AR in Search can also help you discover and explore new concepts. Here are a few new ways you can use AR (and a little imagination) to learn at home.

Take a virtual trip through the human body

It’s one thing to read about the human heart, and another to see one up close to understand how it pumps blood to provide oxygen. We’re partnering with BioDigital so that you can explore 11 human body systems with AR in Search on mobile. Search for circulatory system and tap “View in 3D” to see a heart up close or look up skeletal system to trace the bones in the human body and see how they connect. Read labels on each body part to learn more about it or view life-size images in AR to better understand its scale.

Get a magnified view of our microscopic world

Seeing is often understanding. But tiny organisms, like cells, are hard to visualize unless you can magnify them to understand what’s inside. We’ve partnered with Visible Bodyto create AR models of animal, plant and bacteria cells, including some of their key organelles. Search for animal cell and zoom into its nucleus to see how it stores DNA or search for mitochondria to learn what’s inside it. With AR, you can bring a 3D cell into your space to rotate it, zoom in and view details about its different components.

Turn your home into a museum

Many museums may be closed right now, but with Google Arts & Culture and institutions like the Smithsonian National Air and Space Museum, you can turn your home into one using AR. Search for Apollo 11 on your phone to see its command module in 3D, look up Neil Armstrong to get a life-size view of his spacesuit, or step inside the Chauvet Cave to get an up-close look at some of the world's oldest known cave paintings, which are usually closed off to the public.

Easily explore, record and share 

To help you quickly explore related content, we’re rolling out a new carousel format on Android, as well as a recording option to share social-worthy AR videos with friends and family.

Explore content with the carousel format on Android

We hope that you enjoy exploring all of these 3D and AR experiences on Google. Tag us on social with #Google3Dand let us know how you’re using AR to learn and explore new things in your home. We can’t wait to hear where your imagination takes you next!




e learning

Machine Learning at Arraignments can Cut Repeat Domestic Violence

In the United States, the typical pre-trial process proceeds from arrest to preliminary arraignment to a mandatory court appearance, when appropriate.




e learning

Tips on Effective Online Learning: How to Structure an Optimum Program That Delivers

What really works when it comes to an online learning module/program? Do all online learning solutions offer and ensure an effective and efficient learning experience for the person on the other side of the screen? "Online", "Remote", "Virtual". The...




e learning

Distance learning: best apps, tools and online services

Distance learning solutions and online educational tools are rapidly growing in popularity and effectiveness with teachers, colleges and university-level programs worldwide. One recent survey estimated that...




e learning

Online and Correspondence Learning Courses A New Technique Of Education

Many latest developments are made in educational system of not only India but also of the world. In last few years students prefer to select distance education while doing part time job. Besides this, married...




e learning

Online learning marketplace Udemy raises $50M at a $2B valuation from Japanese publisher Benesse

The internet has, for better or worse, become the default platform for people seeking information, and today one of the companies leveraging that to deliver educational content has raised some funding to fuel its next stage of growth. Udemy, which provides a marketplace offering some 150,000 different online learning courses from business analytics to ukulele […]




e learning

Prince George and Princess Charlotte are learning to 'lean on each other' and share unique bond

A source told People magazine that Prince George, six, and Princess Charlotte, four, are learning to 'lean on each other' as they grow up, because they're so close in age.




e learning

Liverpool are learning a harsh lesson over Emre Can

MERSEY BEAT — DOMINIC KING: Can you play football by numbers? This is an era when statistics have become king and a player’s importance is measured by the digits they produce.




e learning

At one with nature while learning about wildlife


Have you ever wondered how forensic scientists help bring poachers to trial? Or how it feels to walk in forest land for three hours amidst torrential rain? From theory to practice, the exhilarating experience of wildlife conservation comes alive in a course for enthusiasts. Deepa Mohan recounts her experience.




e learning

Google is Offering Journalists Free Courses in AI, Machine Learning

The course is available in 17 different languages on the Google News Initiative Training Centre.




e learning

[ASAP] From Absorption Spectra to Charge Transfer in Nanoaggregates of Oligomers with Machine Learning

ACS Nano
DOI: 10.1021/acsnano.0c00384