Connect with us

Science

Where once were black boxes, NIST’s new LANTERN illuminates

Researchers at the National Institute of Standards and Technology (NIST) have developed a new statistical tool that they have used to predict protein function….

Published

on

Researchers at the National Institute of Standards and Technology (NIST) have developed a new statistical tool that they have used to predict protein function. Not only could it help with the difficult job of altering proteins in practically useful ways, but it also works by methods that are fully interpretable — an advantage over the conventional artificial intelligence (AI) that has aided with protein engineering in the past.

Credit: B. Hayes / NIST

Researchers at the National Institute of Standards and Technology (NIST) have developed a new statistical tool that they have used to predict protein function. Not only could it help with the difficult job of altering proteins in practically useful ways, but it also works by methods that are fully interpretable — an advantage over the conventional artificial intelligence (AI) that has aided with protein engineering in the past.

The new tool, called LANTERN, could prove useful in work ranging from producing biofuels to improving crops to developing new disease treatments. Proteins, as building blocks of biology, are a key element in all these tasks. But while it is comparatively easy to make changes to the strand of DNA that serves as the blueprint for a given protein, it remains challenging to determine which specific base pairs — rungs on the DNA ladder — are the keys to producing a desired effect. Finding these keys has been the purview of AI built of deep neural networks (DNNs), which, though effective, are notoriously opaque to human understanding.

Described in a new paper published in the Proceedings of the National Academy of Sciences, LANTERN shows the ability to predict the genetic edits needed to create useful differences in three different proteins. One is the spike-shaped protein from the surface of the SARS-CoV-2 virus that causes COVID-19; understanding how changes in the DNA can alter this spike protein might help epidemiologists predict the future of the pandemic. The other two are well-known lab workhorses: the LacI protein from the E. coli bacterium and the green fluorescent protein (GFP) used as a marker in biology experiments. Selecting these three subjects allowed the NIST team to show not only that their tool works, but also that its results are interpretable — an important characteristic for industry, which needs predictive methods that help with understanding of the underlying system.

“We have an approach that is fully interpretable and that also has no loss in predictive power,” said Peter Tonner, a statistician and computational biologist at NIST and LANTERN’s main developer. “There’s a widespread assumption that if you want one of those things you can’t have the other. We’ve shown that sometimes, you can have both.”

The problem the NIST team is tackling might be imagined as interacting with a complex machine that sports a vast control panel filled with thousands of unlabeled switches: The device is a gene, a strand of DNA that encodes a protein; the switches are base pairs on the strand. The switches all affect the device’s output somehow. If your job is to make the machine work differently in a specific way, which switches should you flip?

Because the answer might require changes to multiple base pairs, scientists have to flip some combination of them, measure the result, then choose a new combination and measure again. The number of permutations is daunting. 

“The number of potential combinations can be greater than the number of atoms in the universe,” Tonner said. “You could never measure all the possibilities. It’s a ridiculously large number.”

Because of the sheer quantity of data involved, DNNs have been tasked with sorting through a sampling of data and predicting which base pairs need to be flipped. At this, they have proved successful — as long as you don’t ask for an explanation of how they get their answers. They are often described as “black boxes” because their inner workings are inscrutable. 

“It is really difficult to understand how DNNs make their predictions,” said NIST physicist David Ross, one of the paper’s co-authors. “And that’s a big problem if you want to use those predictions to engineer something new.”

LANTERN, on the other hand, is explicitly designed to be understandable. Part of its explainability stems from its use of interpretable parameters to represent the data it analyzes. Rather than allowing the number of these parameters to grow extraordinarily large and often inscrutable, as is the case with DNNs, each parameter in LANTERN’s calculations has a purpose that is meant to be intuitive, helping users understand what these parameters mean and how they influence LANTERN’s predictions.

The LANTERN model represents protein mutations using vectors, widely used mathematical tools often portrayed visually as arrows. Each arrow has two properties: Its direction implies the effect of the mutation, while its length represents how strong that effect is. When two proteins have vectors that point in the same direction, LANTERN indicates that the proteins have similar function.

These vectors’ directions often map onto biological mechanisms. For example, LANTERN learned a direction associated with protein folding in all three of the datasets the team studied. (Folding plays a critical role in how a protein functions, so identifying this factor across datasets was an indication that the model functions as intended.) When making predictions, LANTERN just adds these vectors together — a method that users can trace when examining its predictions.

Other labs had already used DNNs to make predictions about what switch-flips would make useful changes to the three subject proteins, so the NIST team decided to pit LANTERN against the DNNs’ results. The new approach was not merely good enough; according to the team, it achieves a new state of the art in predictive accuracy for this type of problem.

“LANTERN equaled or outperformed nearly all alternative approaches with respect to prediction accuracy,” Tonner said. “It outperforms all other approaches in predicting changes to LacI, and it has comparable predictive accuracy for GFP for all except one. For SARS-CoV-2, it has higher predictive accuracy than all alternatives other than one type of DNN, which matched LANTERN’s accuracy but didn’t beat it.”

LANTERN figures out which sets of switches have the largest effect on a given attribute of the protein — its folding stability, for example — and summarizes how the user can tweak that attribute to achieve a desired effect. In a way, LANTERN transmutes the many switches on our machine’s panel into a few simple dials.

“It reduces thousands of switches to maybe five little dials you can turn,” Ross said. “It tells you the first dial will have a big effect, the second will have a different effect but smaller, the third even smaller, and so on. So as an engineer it tells me I can focus on the first and second dial to get the outcome I need. LANTERN lays all this out for me, and it’s incredibly helpful.”

Rajmonda Caceres, a scientist at MIT’s Lincoln Laboratory who is familiar with the method behind LANTERN, said she values the tool’s interpretability. 

“There are not a lot of AI methods applied to biology applications where they explicitly design for interpretability,” said Caceres, who is not affiliated with the NIST study. “When biologists see the results, they can see what mutation is contributing to the change in the protein. This level of interpretation allows for more interdisciplinary research, because biologists can understand how the algorithm is learning and they can generate further insights about the biological system under study.” 

Tonner said that while he is pleased with the results, LANTERN is not a panacea for AI’s explainability problem. Exploring alternatives to DNNs more widely would benefit the entire effort to create explainable, trustworthy AI, he said.

“In the context of predicting genetic effects on protein function, LANTERN is the first example of something that rivals DNNs in predictive power while still being fully interpretable,” Tonner said. “It provides a specific solution to a specific problem. We hope that it might apply to others, and that this work inspires the development of new interpretable approaches. We don’t want predictive AI to remain a black box.” 


Read More

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Government

New Hampshire Governor Vetoes Ivermectin Bill

New Hampshire Governor Vetoes Ivermectin Bill

Authored by Alice Giordano via The Epoch Times (emphasis ours),

New Hampshire’s Republican…

Published

on

New Hampshire Governor Vetoes Ivermectin Bill

Authored by Alice Giordano via The Epoch Times (emphasis ours),

New Hampshire’s Republican Gov. Chris Sununu vetoed a bill that would have made Ivermectin available without a prescription.

Ivermectin tablets packaged for human use. (Natasha Holt/The Epoch Times)

The Republican governor vetoed the bill on June 24, the same day that the U.S. Supreme Court overturned Roe v. Wade. Some fellow Republicans questioned the timing.

It certainly seemed like a convenient way to bury a veto of a bill that won support from the vast majority of Republicans in New Hampshire,” JR Hoell, co-founder of the conservative watchdog group RebuildNH, told The Epoch Times.

Hoell is a former four-term House Republican planning to seek re-election after a four-year hiatus from the the New Hampshire legislature.

Earlier this year, the New Hampshire Department of Children Youth and Family (DCYF) tried to take custody of Hoell’s 13-year old son after a nurse reported him for giving human-grade ivermectin to the teen months earlier.

Several states have introduced bills to make human-grade ivermectin available without a prescription at a brick and mortar store. Currently, it can be ordered online from another country. In April, Tennessee became the the first state to sign such a measure into law. New Hampshire lawmakers were first to introduce the idea.

Both chambers of the state’s Republican controlled legislature approved the bill.

In his statement explaining the veto, Sununu noted that there are only four other controlled medications available without a prescription in New Hampshire and that each were only made available after “rigorous reviews and vetting to ensure” before being dispensed.

“Patients should always consult their doctor before taking medications so that they are fully aware of treatment options and potential unintended consequences of taking a medication that may limit other treatment options in the future,” Sununu said in his statement.

Sununu’s statement is very similar to testimony given by Paula Minnehan, senior vice president of state government regulations for the New Hampshire Hospital Association, at hearings on the bill.

Minnehan too placed emphasis on the review that went into the four prescription medications the state made available under a standing order. They include naloxone, the generic name for Narcan, which is used to counter opioid overdoses, hormone replacement therapy drugs, and a prescription-version of the morning after pill.

It also includes a collection of smoking cessation therapy drugs like Chantix, which has been linked to suicide, depression, and other neuropsychiatric conditions. Last year, Pfizer, the leading maker of the FDA-approved drug, conducted a voluntarily recall of Chantix. Narcan has also been linked to deaths caused by severe withdrawals that have led to acute respiratory distress.

Rep. Melissa Blasek, a Republican co-sponsor of the New Hampshire ivermectin bill, told The Epoch Times, that one could veto any drug-related bill under the pretense of overdose concerns.

The reality is you can overdose on Tylenol,” she said. “Ivermectin has one of the safest track records of any drug.”

The use of human-grade ivermectin became controversial when some doctors began promoting it for the treatment and prevention of COVID-19. Government agencies including the FDA and CDC issued warnings against its use while groups like Front Line COVID-19 Critical Care Alliance (FLCCC) heavily promoted it.

Some doctors were  disciplined for prescribing human-grade ivermectin for COVID-19 including a Maine doctor whose medical license was suspended by the state.

Read more here...

Tyler Durden Thu, 06/30/2022 - 20:30

Read More

Continue Reading

Spread & Containment

Aging-US | Time makes histone H3 modifications drift in mouse liver

BUFFALO, NY- June 30, 2022 – A new research paper was published in Aging (Aging-US) on the cover of Volume 14, Issue 12, entitled, “Time makes histone…

Published

on

BUFFALO, NY- June 30, 2022 – A new research paper was published in Aging (Aging-US) on the cover of Volume 14, Issue 12, entitled, “Time makes histone H3 modifications drift in mouse liver.”

Credit: Hillje et al.

BUFFALO, NY- June 30, 2022 – A new research paper was published in Aging (Aging-US) on the cover of Volume 14, Issue 12, entitled, “Time makes histone H3 modifications drift in mouse liver.”

Aging is known to involve epigenetic histone modifications, which are associated with transcriptional changes, occurring throughout the entire lifespan of an individual.

“So far, no study discloses any drift of histone marks in mammals which is time-dependent or influenced by pro-longevity caloric restriction treatment.”

To detect the epigenetic drift of time passing, researchers—from Istituto di Ricovero e Cura a Carattere Scientifico, University of Urbino ‘Carlo Bo’, University of Milan, and University of Padua—determined the genome-wide distributions of mono- and tri-methylated lysine 4 and acetylated and tri-methylated lysine 27 of histone H3 in the livers of healthy 3, 6 and 12 months old C57BL/6 mice. 

“In this study, we used chromatin immunoprecipitation sequencing technology to acquire 108 high-resolution profiles of H3K4me3, H3K4me1, H3K27me3 and H3K27ac from the livers of mice aged between 3 months and 12 months and fed 30% caloric restriction diet (CR) or standard diet (SD).”

The comparison of different age profiles of histone H3 marks revealed global redistribution of histone H3 modifications with time, in particular in intergenic regions and near transcription start sites, as well as altered correlation between the profiles of different histone modifications. Moreover, feeding mice with caloric restriction diet, a treatment known to retard aging, reduced the extent of changes occurring during the first year of life in these genomic regions.

“In conclusion, while our data do not establish that the observed changes in H3 modification are causally involved in aging, they indicate age, buffered by caloric restriction, releases the histone H3 marking process of transcriptional suppression in gene desert regions of mouse liver genome most of which remain to be functionally understood.”

DOI: https://doi.org/10.18632/aging.204107 

Corresponding Author: Marco Giorgio – marco.giorgio@unipd.it 

Keywords: epigenetics, aging, histones, ChIP-seq, diet

Sign up for free Altmetric alerts about this article:  https://aging.altmetric.com/details/email_updates?id=10.18632%2Faging.204107

About Aging-US:

Launched in 2009, Aging (Aging-US) publishes papers of general interest and biological significance in all fields of aging research and age-related diseases, including cancer—and now, with a special focus on COVID-19 vulnerability as an age-dependent syndrome. Topics in Aging go beyond traditional gerontology, including, but not limited to, cellular and molecular biology, human age-related diseases, pathology in model organisms, signal transduction pathways (e.g., p53, sirtuins, and PI-3K/AKT/mTOR, among others), and approaches to modulating these signaling pathways.

Follow Aging on social media: 

  • SoundCloud – https://soundcloud.com/Aging-Us
  • Facebook – https://www.facebook.com/AgingUS/
  • Twitter – https://twitter.com/AgingJrnl
  • Instagram – https://www.instagram.com/agingjrnl/
  • YouTube – https://www.youtube.com/agingus​
  • LinkedIn – https://www.linkedin.com/company/aging/
  • Pinterest – https://www.pinterest.com/AgingUS/

For media inquiries, please contact media@impactjournals.com.

Aging (Aging-US) Journal Office
6666 E. Quaker Str., Suite 1B
Orchard Park, NY 14127
Phone: 1-800-922-0957, option 1

###


Read More

Continue Reading

Government

5 Top Biotech Stocks To Watch In July 2022

Amid choppy markets, could there be potential in these top biotech stocks?
The post 5 Top Biotech Stocks To Watch In July 2022 appeared first on Stock…

Published

on

Should Investors Be Watching These Top Biotech Stocks In The Stock Market Now?

Just as most people think that pandemic woes are behind us, we now have the emergence of the monkeypox. While this virus may not be as contagious as the coronavirus, there is still a real cause for concern. On Tuesday, the Centers for Disease Control and Prevention (CDC) announced the activation of an emergency operations unit for monkeypox. This signals the initial stages of a public health concern. Epidemiologist Dr. Eric Feigl-Ding believes that the number of cases could reach 100,000 worldwide by August. In light of these circumstances, biotech stocks could be gaining more attention in the stock market. 

Furthermore, the coronavirus is not going away anytime soon. Recently, the U.S. Food and Drug Administration (FDA) Vaccines and Related Biological Products Advisory Committee (VRBPAC) voted that there is a need to modify the current strain composition of available COVID-19 vaccines to target the Omicron variant. If this is approved, vaccine makers such as Pfizer/BioNTech, and Moderna (NASDAQ: MRNA) will need to provide modified boosters of their coronavirus vaccines. In fact, Pfizer (NYSE: PFE) and BioNTech (NASDAQ: BNTX) just announced a new vaccine supply agreement with the U.S. government. Under the agreement, the U.S. government will receive 105 million doses with an option of up to 195 million additional doses. With all this in mind, here are five of the top biotech stocks to note in the stock market today. 

Biotech Stocks For Your July 2022 Watchlist

Regeneron Pharmaceuticals 

biotech stocks to buy (regn stock)

First up, we have the integrated biotech company, Regeneron Pharmaceuticals. Essentially, the company discovers, invents, manufactures, and commercializes medicines for serious diseases. For the most part, its medicines and products aim to help patients with eye diseases, allergic and inflammatory diseases, cancer, cardiovascular, and metabolic diseases. REGN stock has been trading sideways over the past year. 

Having said that, the company received a boost on Wednesday as the U.S. FDA has accepted for review the EYLEA Injection supplemental Biologics License Application for every 16-week 2 mg dosing regimen. This specifically caters to patients with diabetic retinopathy. Should this go according to plan, the 16-week dosing regimen could offer patients a potentially longer treatment interval. Also, it will allow doctors to have greater flexibility to individualize treatment. Given such a positive development, should investors be paying more attention to REGN stock?

[Read More] Stock Market Today: Dow Jones, S&P 500 Falter; Walgreens Stock Slides Despite Strong Quarter

Sanofi

best health care stocks to buy now (SNY stock)

Another top biotech name making waves this week is Sanofi. The France-based company engages in the research, development, and marketing of therapeutic solutions. Over the past week, there have been several key developments that could potentially excite investors. For starters, the company and GSK (NYSE: GSK) announced positive data from their vaccine trial last Friday. The vaccine candidate is the first to ever demonstrate efficacy in a placebo-controlled trial in an environment of high Omicron variant circulation. 

Furthermore, Sanofi’s Nexviadyme (avalglucosidase alfa) has recently gained marketing authorization from the European Commission. For the uninitiated, this is an enzyme replacement therapy for long-term treatment of both late-onset and infantile-onset Pompe disease. This is a significant development because Nexviadyme is the first and only newly approved medicine for Pompe disease in Europe since 2006. On that note, would you say that SNY stock is a top biotech stock to watch?

Novavax

best biotech stocks (NVAX stock)

Following that, let us look at the biotech company, Novavax. In detail, it promotes improved health globally through the discovery, development, and commercialization of vaccines to prevent serious infectious diseases. Its recombinant technology platform harnesses the power and speed of genetic engineering. As a result, the company produces immunogenic nanoparticles designed to address urgent global health needs. That said, NVAX stock has been struggling to find its footing since the start of the year. 

During the VRBPAC meeting, Novavax highlighted data showing that its protein-based coronavirus vaccine showed epitopes across both the original strain and emerging variants. Therefore, it will be able to contribute to the generation of broadly cross-reacting antibodies. The company also provided pre-clinical data that suggests boosting with Novavax’s Omicron or prototype vaccine will induce an immune response against Omicron variants. Overall, there are reasons to believe that Novavax will close the second half of the year on a better note. With that in mind, would you consider adding NVAX stock to the top of your watchlist?

Arrowhead Pharmaceuticals 

ARWR stock

Arrowhead Pharmaceuticals develops medicines that treat intractable diseases by silencing the genes that cause them. It uses a portfolio of ribonucleic acid (RNA) chemistries and modes of delivery. Most of its therapies trigger the RNA interference mechanism to induce rapid, deep, and durable knockdown of target genes. Those following the medical space would notice that gene therapies have been gaining popularity within the industry over the past few years. Hence, it would not be surprising if investors are taking note of Arrowhead. 

As a matter of fact, the company recently claimed that its experimental drug fazirsiran can reduce the accumulation of mutant protein known as Z-AAT by 83%. This result is based on an open-label phase 2 trial involving 16 volunteers with alpha1-antitrypsin deficiency disease. For now, there is still no approved treatment for such genetic liver disease. All in all, Arrowhead appears to be making strides in the right direction. Thus, should you be keeping a closer tab on ARWR stock?

[Read More] Best Long-Term Stocks To Buy Now? 5 Semiconductor Stocks To Know

Global Blood Therapeutics

gbt stock

To sum it all up, we have the biopharmaceutical company, Global Blood Therapeutics. As its name suggests, this is a company that specializes in blood-related treatments. The company is currently focused on Oxbryta, an FDA-approved medicine that inhibits sickle hemoglobin polymerization. In addition, it is also advancing its pipeline program in Sickle Cell Disease with inclacumab, and GBT021601. Impressively, GBT stock has been on bullish momentum lately, rising more than 28% within the past month.

Not to mention, the company announced on Thursday that it initiated the Phase 2 portion of its Phase 2/3 trial of GBT021601. The study aims to evaluate the safety, tolerability, efficacy, pharmacokinetics, and pharmacodynamics of the drug. So far, the preclinical results and data have been encouraging. Smith-Whitley, the company’s head of research and development, believes the drug has “the potential to improve on the clinical results achieved with Oxbryta® at a lower daily dose.” If so, this would be a huge boost for the company as it continues to work towards its long-term goals. All things considered, is GBT stock a buy right now?

If you enjoyed this article and you’re interested in learning how to trade so you can have the best chance to profit consistently then you need to checkout this YouTube channel. CLICK HERE RIGHT NOW!!

The post 5 Top Biotech Stocks To Watch In July 2022 appeared first on Stock Market News, Quotes, Charts and Financial Information | StockMarket.com.

Read More

Continue Reading

Trending