0

Machine learning model helps characterize compounds for drug discovery

Posted on

chemical
Credit: CC0 Public Domain

Tandem mass spectrometry is a powerful analytical tool used to characterize complex mixtures in drug discovery and other fields.


Now, Purdue University innovators have created a new method of applying machine learning concepts to the tandem mass spectrometry process to improve the flow of information in the development of new drugs. Their work is published in Chemical Science.

“Mass spectrometry plays an integral role in drug discovery and development,” said Gaurav Chopra, an assistant professor of analytical and physical chemistry in Purdue’s College of Science. “The specific implementation of bootstrapped machine learning with a small amount of positive and negative training data presented here will pave the way for becoming mainstream in day-to-day activities of automating characterization of compounds by chemists.”

Chopra said there are two major problems in the field of machine learning used for chemical sciences. Methods used do not provide chemical understanding of the decisions that are made by the algorithm, and new methods are not typically used to do blind experimental tests to see if the proposed models are accurate for use in a chemical laboratory.

“We have addressed both of these items for a methodology that is isomer selective and extremely useful in chemical sciences to characterize complex mixtures, identify chemical reactions and drug metabolites, and in fields such as proteomics and metabolomics,” Chopra said.

The Purdue researchers created statistically robust machine learning models to work with less training data—a technique that will be useful for drug discovery. The model looks at a common neutral reagent—called 2-methoxypropene (MOP) – and predicts how compounds will interact with MOP in a tandem mass spectrometer in order to obtain structural information for the compounds.

“This is the first time that machine learning has been coupled with diagnostic gas-phase ion-molecule reactions, and it is

0

Discovery of synchronous firefly population expected to draw more visitors to Watoga |

Posted on

West Virginians through the generations have marveled at the intermittent flashes of light that take place in the night skies of late spring and summer, as swarms of fireflies emerge from the ground to perform their annual bioluminescence-enhanced mating ritual.

While such displays can be spectacular, particularly if large populations of fireflies are involved, imagine viewing a light show created by thousands of lightning bugs all flashing at the same time, at the same intervals.

Such displays are created by synchronous fireflies, members of two or three of the 2,000 species of fireflies known to exist in North America. Until recently, synchronous fireflies could be found on public lands in the U.S. only in portions of Great Smoky Mountains National Park in Tennessee, Pennsylvania’s Allegheny National Forest, the Oak Ridge Wildlife Management Area in east Tennessee, and South Carolina’s Congaree National Park.

As of this year, Watoga State Park in Pocahontas County has joined that list.

A now-retired Division of Natural Resources biologist happened to be visiting at Watoga during the 2019 firefly mating season and discovered what appeared to be a population of rare synchronous fireflies. She passed along information on the sighting, including the GPS coordinates for where it occurred, to Mack Frantz, State Zoologist for the DNR, who was organizing a study of firefly populations across West Virginia using data from citizen observations.

Not long after learning about the possible West Virginia synchronous firefly population, Frantz said, the Watoga State Park Foundation contacted him about their Dark Sky Initiative, a project aimed at having Watoga designated as the state’s first Dark Sky Park.

To qualify for the designation, a park must meet criteria established by the International Dark Sky Association. They include being able to see the Milky Way with the naked eye, having night sky brightness

0

Turkey to Revise Upward Its Major Gas Discovery in Black Sea

Posted on

(Bloomberg) —



a bridge over a body of water


© Photographer: Ali Mohammadi/Bloomberg


Turkey expects to raise its estimate for the amount of natural gas discovered in the Black Sea and plans to announce the new guidance as early as next week, according to people with direct knowledge of the matter.

Loading...

Load Error

The government will outline a sizable revision to the initial discovery of 320 billion cubic meters of recoverable gas, unveiled in August, once exploratory drilling is completed this month, the people said, asking not to be named due to the sensitivity of the find.

The energy discovery in the Black Sea is critical for Turkey’s current-account balance which is dragged down by the need to import nearly all of the 50 billion cubic meters of gas the country consumes annually.

Drilling to a depth of around 4,500 meters (15,000 feet) at the Tuna-1 discovery would penetrate two additional formations that appear promising, a senior Turkish energy official said last month. A second drill ship is likely to be moved to the region next year.

Ankara has dramatically expanded energy exploration in the Black Sea and contested waters of the eastern Mediterranean. It’s keen to find sizable energy reserves to ease its heavy reliance on imports from Iran, Iraq and Russia, and support one of the biggest economies in the Middle East.

Shares of Turkish oil refiner Turkiye Petrol Rafinerileri AS, or Tupras, gained as much as 2% following the news, while petrochemical company Petkim Petrokimya Holding AS climbed as much as 4.5%. They were trading 1.7% higher and 3.8% higher as of 4:05 p.m., respectively. Shares of energy companies Aksa Enerji Uretim AS and Aygaz each rose 2.3%.

But the searches have mired the government in territorial disputes with Greece and Cyprus in the Mediterranean.

(Updates with moves in Turkish energy companies in the