fbpx

Human Progress Logo Human Progress

01 / 05
AI Predicts Location of Virtually Any Protein Within a Human Cell

MIT News | Scientific Research

AI Predicts Location of Virtually Any Protein Within a Human Cell

“A protein located in the wrong part of a cell can contribute to several diseases, such as Alzheimer’s, cystic fibrosis, and cancer. But there are about 70,000 different proteins and protein variants in a single human cell, and since scientists can typically only test for a handful in one experiment, it is extremely costly and time-consuming to identify proteins’ locations manually.

A new generation of computational techniques seeks to streamline the process using machine-learning models that often leverage datasets containing thousands of proteins and their locations, measured across multiple cell lines. One of the largest such datasets is the Human Protein Atlas, which catalogs the subcellular behavior of over 13,000 proteins in more than 40 cell lines. But as enormous as it is, the Human Protein Atlas has only explored about 0.25 percent of all possible pairings of all proteins and cell lines within the database.

Now, researchers from MIT, Harvard University, and the Broad Institute of MIT and Harvard have developed a new computational approach that can efficiently explore the remaining uncharted space. Their method can predict the location of any protein in any human cell line, even when both protein and cell have never been tested before.”

From MIT News.

Import AI | Scientific Research

Fully Automated AI Research Will Likely Arrive by 2028

“I’m writing this post because when I look at all the publicly available information I reluctantly come to the view that there’s a likely chance (60%+) that no-human-involved AI R&D – an AI system powerful enough that it could plausibly autonomously build its own successor – happens by the end of 2028.

This is a big deal.

I don’t know how to wrap my head around it.

It’s a reluctant view because the implications are so large that I feel dwarfed by them, and I’m not sure society is ready for the kinds of changes implied by achieving automated AI R&D.

I now believe we are living in the time that AI research will be end-to-end automated. If that happens, we will cross a Rubicon into a nearly-impossible-to-forecast future. More on this later.

The purpose of this essay is to enumerate why I think the takeoff towards fully automated AI R&D is happening.”

From Import AI.

Reuters | Health Systems

J&J Sees AI Halving the Time to Generate Drug Development Leads

“Johnson & Johnson is using artificial intelligence to slash by half the time it ‌takes to generate new leads for developing drugs, the company’s chief information officer said on Monday.

Discovering new products outright and bringing them to market using AI is not yet possible, but J&J is using the new technology to screen the “potential universe” for promising chemical compounds or ​biologics, CIO Jim Swanson said at the Reuters Momentum AI event in New York…

J&J is also using AI to streamline preparation of documents for regulators. The traditional process for a clinical trial report can take 700 to 900 hours, the CIO ​said.
That time has gone from ‘700 ​hours to about 15 ⁠minutes,’ Swanson said.”

From Reuters.

The Guardian | Scientific Research

A Breakthrough in Solving Mystery of Volcanic Lightning

“Researchers are a step closer to understanding volcanic lightning, one of the most spectacular atmospheric phenomena, which can be seen playing among the clouds of smoke and ash during an eruption. The intensity is extreme: the Hunga Tonga-Hunga Ha‘apai eruption, in the Tongan archipelago in 2022, produced more than 2,600 lightning flashes a minute stretching up to 19 miles (31km) above sea level.

We know that storm clouds become electrically charged as a result of collisions between ice crystals rising in updraughts and falling particles of graupel, or soft hail. The ice picks up positive charge and the hail negative. What has puzzled scientists is how a volcanic plume, which is dry and consists of ash and rock fragments, could pick up charge. Particles made from the same rocky material should not do that during collisions.

New research published in Nature from the Institute of Science and Technology Austria shows the secret lies in a fine coating of carbon-rich molecules. Perfectly clean particles of silica did not tend to pick up charge, but where there was a carbon coating, charge transfer happened in collisions. The effect could be produced simply by heating the silica, as there are enough carbon-containing molecules in normal air to produce surface contamination.”

From The Guardian.

Epoch AI | Scientific Research

First AI Solution on FrontierMath: Open Problems

“AI has solved one of the problems in FrontierMath: Open Problems, our benchmark of real research problems that mathematicians have tried and failed to solve.

The newly-solved problem came from Will Brian, who had placed it in the Moderately Interesting category. It is a conjecture from a paper he wrote with Paul Larson in 2019. They were unable to solve it at the time, or in several attempts since.”

From Epoch AI.