Tuesday, February 25, 2020
Artificial intelligence yields new antibiotic
A deep-learning model identifies a powerful new drug that can kill many species of antibiotic-resistant bacteria
February 20, 2020Massachusetts Institute of TechnologyUsing a machine-learning algorithm, researchers have identified a powerful new antibiotic compound. In laboratory tests, the drug killed many of the world's most problematic disease-causing bacteria, including some strains that are resistant to all known antibiotics. It also cleared infections in two different mouse models.
https://www.sciencedaily.com/releases/2020/02/200220141748.htm
Using a machine-learning algorithm, MIT researchers have identified a powerful new antibiotic compound. In laboratory tests, the drug killed many of the world's most problematic disease-causing bacteria, including some strains that are resistant to all known antibiotics. It also cleared infections in two different mouse models.
The computer model, which can screen more than a hundred million chemical compounds in a matter of days, is designed to pick out potential antibiotics that kill bacteria using different mechanisms than those of existing drugs.
"We wanted to develop a platform that would allow us to harness the power of artificial intelligence to usher in a new age of antibiotic drug discovery," says James Collins, the Termeer Professor of Medical Engineering and Science in MIT's Institute for Medical Engineering and Science (IMES) and Department of Biological Engineering. "Our approach revealed this amazing molecule which is arguably one of the more powerful antibiotics that has been discovered."
In their new study, the researchers also identified several other promising antibiotic candidates, which they plan to test further. They believe the model could also be used to design new drugs, based on what it has learned about chemical structures that enable drugs to kill bacteria.
"The machine learning model can explore, in silico, large chemical spaces that can be prohibitively expensive for traditional experimental approaches," says Regina Barzilay, the Delta Electronics Professor of Electrical Engineering and Computer Science in MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL).
Barzilay and Collins, who are faculty co-leads for MIT's Abdul Latif Jameel Clinic for Machine Learning in Health, are the senior authors of the study, which appears today in Cell. The first author of the paper is Jonathan Stokes, a postdoc at MIT and the Broad Institute of MIT and Harvard.
A new pipeline
Over the past few decades, very few new antibiotics have been developed, and most of those newly approved antibiotics are slightly different variants of existing drugs. Current methods for screening new antibiotics are often prohibitively costly, require a significant time investment, and are usually limited to a narrow spectrum of chemical diversity.
"We're facing a growing crisis around antibiotic resistance, and this situation is being generated by both an increasing number of pathogens becoming resistant to existing antibiotics, and an anemic pipeline in the biotech and pharmaceutical industries for new antibiotics," Collins says.
To try to find completely novel compounds, he teamed up with Barzilay, Professor Tommi Jaakkola, and their students Kevin Yang, Kyle Swanson, and Wengong Jin, who have previously developed machine-learning computer models that can be trained to analyze the molecular structures of compounds and correlate them with particular traits, such as the ability to kill bacteria.
The idea of using predictive computer models for "in silico" screening is not new, but until now, these models were not sufficiently accurate to transform drug discovery. Previously, molecules were represented as vectors reflecting the presence or absence of certain chemical groups. However, the new neural networks can learn these representations automatically, mapping molecules into continuous vectors which are subsequently used to predict their properties.
In this case, the researchers designed their model to look for chemical features that make molecules effective at killing E. coli. To do so, they trained the model on about 2,500 molecules, including about 1,700 FDA-approved drugs and a set of 800 natural products with diverse structures and a wide range of bioactivities.
Once the model was trained, the researchers tested it on the Broad Institute's Drug Repurposing Hub, a library of about 6,000 compounds. The model picked out one molecule that was predicted to have strong antibacterial activity and had a chemical structure different from any existing antibiotics. Using a different machine-learning model, the researchers also showed that this molecule would likely have low toxicity to human cells.
This molecule, which the researchers decided to call halicin, after the fictional artificial intelligence system from "2001: A Space Odyssey," has been previously investigated as possible diabetes drug. The researchers tested it against dozens of bacterial strains isolated from patients and grown in lab dishes, and found that it was able to kill many that are resistant to treatment, including Clostridium difficile, Acinetobacter baumannii, and Mycobacterium tuberculosis. The drug worked against every species that they tested, with the exception of Pseudomonas aeruginosa, a difficult-to-treat lung pathogen.
To test halicin's effectiveness in living animals, the researchers used it to treat mice infected with A. baumannii, a bacterium that has infected many U.S. soldiers stationed in Iraq and Afghanistan. The strain of A. baumannii that they used is resistant to all known antibiotics, but application of a halicin-containing ointment completely cleared the infections within 24 hours.
Preliminary studies suggest that halicin kills bacteria by disrupting their ability to maintain an electrochemical gradient across their cell membranes. This gradient is necessary, among other functions, to produce ATP (molecules that cells use to store energy), so if the gradient breaks down, the cells die. This type of killing mechanism could be difficult for bacteria to develop resistance to, the researchers say.
"When you're dealing with a molecule that likely associates with membrane components, a cell can't necessarily acquire a single mutation or a couple of mutations to change the chemistry of the outer membrane. Mutations like that tend to be far more complex to acquire evolutionarily," Stokes says.
In this study, the researchers found that E. coli did not develop any resistance to halicin during a 30-day treatment period. In contrast, the bacteria started to develop resistance to the antibiotic ciprofloxacin within one to three days, and after 30 days, the bacteria were about 200 times more resistant to ciprofloxacin than they were at the beginning of the experiment.
The researchers plan to pursue further studies of halicin, working with a pharmaceutical company or nonprofit organization, in hopes of developing it for use in humans.
Optimized molecules
After identifying halicin, the researchers also used their model to screen more than 100 million molecules selected from the ZINC15 database, an online collection of about 1.5 billion chemical compounds. This screen, which took only three days, identified 23 candidates that were structurally dissimilar from existing antibiotics and predicted to be nontoxic to human cells.
In laboratory tests against five species of bacteria, the researchers found that eight of the molecules showed antibacterial activity, and two were particularly powerful. The researchers now plan to test these molecules further, and also to screen more of the ZINC15 database.
The researchers also plan to use their model to design new antibiotics and to optimize existing molecules. For example, they could train the model to add features that would make a particular antibiotic target only certain bacteria, preventing it from killing beneficial bacteria in a patient's digestive tract.
Story Source:
Materials provided by Massachusetts Institute of Technology. Original written by Anne Trafton. Note: Content may be edited for style and length.
Journal Reference:
Jonathan M. Stokes, Kevin Yang, Kyle Swanson, Wengong Jin, Andres Cubillos-Ruiz, Nina M. Donghia, Craig R. MacNair, Shawn French, Lindsey A. Carfrae, Zohar Bloom-Ackerman, Victoria M. Tran, Anush Chiappino-Pepe, Ahmed H. Badran, Ian W. Andrews, Emma J. Chory, George M. Church, Eric D. Brown, Tommi S. Jaakkola, Regina Barzilay, James J. Collins. A Deep Learning Approach to Antibiotic Discovery. Cell, 2020; 180 (4): 688 DOI: 10.1016/j.cell.2020.01.021
New Polls Show Bernie Surge In Battleground States
BERN NOTICE: New Polls Show Bernie Surge In Battleground States
Axios: "The evidence doesn't back Democrats' panic that Bernie can't win"
David Sirota Feb 24
Bern Notice is a production of the Bernie 2020 campaign. Please forward this on to your friends and tell them to subscribe. The views expressed here are solely of the bylined author.
A series of new polls show that after his big wins in Iowa, New Hampshire and Nevada, Bernie is surging in some of the major states that could decide the Democratic primary and the general election. This follows news that the RealClearPolitics average of national polls shows Bernie with the widest lead of any Democratic candidate in a head-to-head general election matchup with Trump.
Here are the new data points:
• BERNIE IS STRONGEST AGAINST TRUMP IN WI, MI & PA: A new Wisconsin State Journal poll finds Bernie leading in the Democratic primaries and in the general election in Wisconsin, Michigan and Pennsylvania — the three previously Democratic states that helped deliver the election to Donald Trump. Bernie is leading Trump by the largest margins of any Democratic candidate in Michigan (+7) and Pennsylvania (+2), and also gets the largest amount of total support in Wisconsin (46%).
• BERNIE IS THE STRONGEST AGAINST TRUMP IN VIRGINIA: A new Roanoke College poll shows Bernie leading Trump by nine points in the swing state of Virginia — the largest margin of any Democratic candidate.
• BERNIE IS STRONGEST AGAINST TRUMP IN TEXAS: Vanity Fair reports “A Texas Lyceum poll just this week showed Sanders performing better against Trump in Texas than any Democrat, losing by just three points. That’s on top of a raft of polls showing Sanders beating Trump back those precious Upper Midwest states of Wisconsin, Michigan, and Pennsylvania. These polls aren’t totally hypothetical, either: Sanders boasts near universal Name ID. Most voters know who Sanders is and what he stands for—and they’re still choosing him.”
• BERNIE SURGING AHEAD OF BLOOMBERG IN NEW YORK: NY 1 reports that “A new Siena College poll finds that New Yorkers are backing Bernie Sanders over Mike Bloomberg.” Bernie leads the entire field, and has a four point lead over the billionaire former New York mayor in the major Democratic primary state.
Surmising these and other data points, Axios editor Jim Vandehei today wrote: “Lots of Democrats are in full panic that Bernie Sanders will win the nomination and get clobbered in the general election — and bring the party down, too. But the evidence, particularly the polling, doesn't back those doomsday warnings.”
Bern after reading,
Sirota
Climate News links to articles, podcasts
Everyone’s Worried, Poll Shows: A new poll shows that climate change is one of the top issues for Democratic voters in states with upcoming primaries and caucuses, the Atlantic reports. The poll, conducted by Climate Nexus, the Yale University Program on Climate Change Communication and the George Mason University Center for Climate Change Communication finds that climate change is the second-most important issue for Democratic voters in 26 states – a sample including swing states like Arizona, Florida, North Carolina and Michigan. Overall, climate change ranks behind only healthcare in Democratic voter concern, while it is the top issue for self-described liberal Dems. “This is the first time in American political history where climate change is not just a top-tier issue—it is the top-tier issue,” Anthony Leiserowitz, the director of the Yale Program on Climate Change Communication, told the Atlantic. (The Atlantic)
The River’s in Trouble: The Colorado River is drying up, and a new study finds that climate change is responsible for half of the 16 percent decrease in flow between 2000 and 2017. As warming continues, the study, published in the journal Science, finds that the river may lose up to one-fourth of its flow in the next 30 years due to precipitation and snowpack decline and evaporation increases. The river is a crucial water source for the West, providing water for 5 million acres of farmland and 40 million people across 7 states, and the decrease in flow in recent years, caused partially by overuse, has forced Western states to reconsider and restructure water policy. “There’s not a drop of that water that no one has a claim on,” coauthor Christopher Milly told the Arizona Daily Star. “If and when that supply is reduced by 10 to 20 to 30%, someone is going to have to stop using as much water.” (Arizona Daily Star, Arizona Republic, Ars Technica, Newsweek, CNN, Scientific American)
Thru-Hiking...Over a Pipeline: The Supreme Court will hear arguments Monday that may determine if a controversial pipeline is allowed to cross the iconic Appalachian Trail. Environmental groups are challenging a permit issued by the Forest Service allowing Dominion Energy and Duke Energy to build a section of the Atlantic Coast Pipeline across a stretch of the 2,200-mile trail in Virginia, arguing that only Congress can grant a permit, since the trail is considered a part of the National Parks system. A lower court agreed with the environmental groups and tossed the permit in December of 2018, and the pipeline owners are depending on a decision from the Supreme Court to get the crucial permit to continue construction on the 600-mile project. (Washington Post $, AP, NPR. Commentary: New York Times, Will Harlan essay $, WSJ editorial $)
POLLING: These swing voters don't like Trump’s environmental rollbacks (Axios), climate change a rising concern for Western voters, poll finds (The Hill), poll: registered Vermont voters divided over state's response to climate change (Vermont Public Radio), Colorado voters care about climate change – this is where the 2020 Democratic presidential candidates stand (Colorado Public Radio)
2020: Mike Bloomberg tries to talk up climate change during an otherwise brutal Nevada Democratic debate (Washington Post $), on climate change, a priority for Nevada voters, debate reveals divide over how they would address fossil fuels (The Nevada Independent), that time Mike Bloomberg installed an AC unit in his SUV (Politico)
NAT GAS: Durham approves $1.4 million to help housing authority install electric stoves (Raleigh News & Observer), California approves natural gas limits on new buildings in nine Bay Area cities (San Francisco Chronicle), natural-gas exporters struggle to lock up buyers despite ‘freedom gas’ pitch (Wall Street Journal $), Ducey OKs bill barring city natural gas hookup bans (AP)
DENIERS: Meet the anti-Greta: A young YouTuber campaigning against ‘climate alarmism’ (Washington Post $), revealed: quarter of all tweets about climate crisis produced by bots (The Guardian, BBC)
IMPACTS: Adapting to rising seas, schools move to the rafters and cats swim (New York Times $), warmest January ever puts 2020 on track to be one of top 10 hottest years (New York Times $), the fires are out, but Australia’s climate disasters aren’t over (New York Times $), Australia's next danger: mudslides (NPR), climate change may doom 1 in 3 species of plants and animals in the next 50 years (CNN), Zimbabwe’s rural elderly battle hunger amid severe drought (AP)
TRUMP ADMIN: One side of a nuclear waste fight: Trump. The other: his administration (New York Times $), US agriculture secretary breaks ranks to endorse carbon pricing (FT $), climate change gets first mention in G20 finance communique of Trump era (Reuters)
CITIES & STATES: In liberal Takoma Park, a bold new climate proposal: Banning fossil fuels (Washington Post $), Gov. Edwards creates task force to respond to climate change (AP), New England states to regulate group of industrial chemicals (AP), Vermont House advances climate change bill (AP)
CRITTERS: A climate-sensitive bird hints at global warming's lasting impact (NBC), 46,000-year-old bird found frozen in Siberia sheds light on the end of the ice age (Washington Post $)
INT’L: Canada’s Teck Resources withdraws application for controversial mine days before government decision (Washington Post $, Wall Street Journal $), for Canada’s Trudeau, the $15.5 billion Teck mine decision may be a lose-lose situation (Washington Post $)
MEDIA: A pipeline runs through Southern news deserts (Columbia Journalism Review)
RENEWABLES: Solar power just miles from the Arctic Circle? In icy Nordic climes, it’s become the norm (InsideClimate News), super-size solar farms are taking over the world (Bloomberg)
PIPELINES: North Dakota approves extension to controversial Dakota Access Pipeline (New York Post)
BUSINESS: What corporate leadership on fighting climate change really looks like (Washington Monthly), can corporations stop climate change? (New York Times $), ‘Greta effect' boosting demand for climate change careers, RSC claims (Business Green)
ECONOMICS: Finance ministers grapple over economic threat of climate change (New York Times $), JP Morgan economists warn climate crisis is threat to human race (The Guardian)
[...]
Subscribe to:
Posts (Atom)