GIST researchers develop “AMP-BERT”: A new AI-based “finder” of antimicrobial peptides
Scientists propose a deep neural network-based platform for identifying candidate antimicrobial peptides
2023-02-23
(Press-News.org)
Over the last few decades, antimicrobial resistance has become a major public health concern globally. This has led to a search for alternative methods of treating microbial infections. One such innovation is the discovery of antimicrobial properties of certain peptides. Antimicrobial peptides (AMPs) are short peptides found in most animals, plants, and microorganisms as a natural defense against infections. AMPs combat harmful bacteria via a nonspecific mechanism that prevents them from developing antimicrobial resistance. Despite these exceptional abilities, research on AMPs is being hindered because the existing systems for identifying candidate AMPs are like a black box, where the outputs are not easily interpretable for further analysis.
Now, in a recent breakthrough published in Protein Science, a team of researchers from Gwangju Institute of Science and Technology, including Prof. Hojung Nam and Mr. Hansol Lee, proposed an AMP-BERT classification system that uses AI-based bidirectional encoder representation from transformers (BERT) architecture to improve upon the existing AMP classification models. Their findings were published online on 3 December 2022 and in print in Volume 32, Issue 1 of the journal in January 2023.
When asked about the motivation behind developing the classification system, Prof. Nam explains: “The misuse and overuse of antibiotics have resulted in the development of bacteria that cannot be effectively treated with these antibiotics. This has resulted in an increased health risk not only in humans but also agriculture. So, we wanted to develop an AMP pre-screening platform that isn’t a black box of algorithms but can be easily interpreted for further research.”
The team incorporated a natural language processing (NLP)-based deep neural network that was pre-trained with billions of protein sequences then fine-tuned with thousands of peptide sequences from a benchmark AMP database. This enabled the AMP-BERT model to not only extract the structural and functional information from the input peptide sequences but also differentiate AMPs from non-AMPs. This enhanced the prediction power allowed the model to make better classifications even with external data.
The team also designed the model to assign individual attention scores to each amino acid from the input peptide sequence. The attention feature then revealed the important subregions of AMPs that play a major role in deciding whether a peptide has antimicrobial properties or not. Furthermore, the prediction results indicated the AMP-BERT model’s applicability extends even to unseen peptide data and that it can learn meaningful functional and structural information from those peptides.
The novel AMP-BERT peptide pre-screening model can open new doors for the discovery and development of AMP-based drug candidates for treating antimicrobial-resistant illnesses. The important peptide subregion information provided by this prediction platform can also be used to optimize the antibiotic efficiency of peptides. “As more AMPs are experimentally validated and new structural information is uncovered using computational methods, we will be able to make more effective antibiotic drugs and potentially stop a new pandemic from spreading across the world in near future” concludes Prof Nam.
AMP-BERT will certainly be a powerful weapon in our war against antimicrobial resistance!
***
Reference
Authors: Hansol Lee1, Songyeon Lee1, Ingoo Lee1, Hojung Nam1,2
DOI: https://doi.org/10.1002/pro.4529
Affiliations:
1 School of Electrical Engineering and Computer Science, Gwangju Institute of
Science and Technology (GIST)
2 AI Graduate School, Gwangju Institute of Science and Technology
About the Gwangju Institute of Science and Technology (GIST)
The Gwangju Institute of Science and Technology (GIST) is a research-oriented university situated in Gwangju, South Korea. Founded in 1993, GIST has become one of the most prestigious schools in South Korea. The university aims to create a strong research environment to spur advancements in science and technology and to promote collaboration between international and domestic research programs. With its motto of “A Proud Creator of Future Science and Technology,” GIST has consistently received one of the highest university rankings in Korea.
Website: http://www.gist.ac.kr/
About the author
Hojung Nam is an Associate Professor in the School of Electrical Engineering and Computer Science, and the AI Graduate School at Gwangju Institute of Science and Technology (GIST). She received her Ph.D. in the Dept. of Bio and Brain Engineering at the Korea Advanced Institute of Science and Technology (KAIST) and completed her postdoctoral training in the Dept. of Bioengineering at the University of California, San Diego (UCSD). Currently, her research group is working on the development of various computational tools for drug discovery, development, and models for the prediction of drug side effects.
Hansol Lee is a Ph.D. candidate at GIST under Prof. Hojung Nam’s instruction. During his Ph.D. course, he has carried out research on AMP-related deep learning models, including AMP class prediction and AMP sequence generation.
END
ELSE PRESS RELEASES FROM THIS DATE:
2023-02-23
The sheer volume of ‘Big Data’ produced today by various sectors is beginning to overwhelm even the extremely efficient computational techniques developed to sift through all that information. But a new computational framework based on random sampling looks set to finally tame Big Data’s ever-growing communication, memory and energy costs into something more manageable.
A paper describing the framework was published in the journal Big Data Mining and Analytics on Jan. 26.
The amount of data being produced from social networks, business transactions, the ‘Internet of Things’, finance, healthcare and beyond has exploded ...
2023-02-23
Insilico Medicine, a clinical-stage biotech company powered by generative AI, today announces that China National Medical Products Administration (NMPA) has approved the Investigational New Drug (IND) application for ISM3312, an orally available 3CLpro inhibitor generated and designed with the support of Insilico’s proprietary generative chemistry platform Chemistry42 for the treatment of COVID-19.
ISM3312 is a highly selective small molecule inhibitor with a novel molecular structure optimized from compounds which were generated and designed by Chemistry42 based on the structure of 3CL protease. It binds to ...
2023-02-23
As air pollution in Stockholm has decreased, so has the lung capacity of children and adolescents has improved, a new study published in the European Respiratory Journal reports. The researchers from Karolinska Institutet consider the results important, since the lung health of the young greatly affects the risk of their developing chronic lung diseases later in life.
“Fortunately, we’ve seen a decrease in air pollutants and therefore an increase in air quality in Stockholm over the past 20 years,” says the study’s last author ...
2023-02-23
Sensing a hug from each other via the internet may be a possibility in the near future. A research team led by City University of Hong Kong (CityU) recently developed a wireless, soft e-skin that can both detect and deliver the sense of touch, and form a touch network allowing one-to-multiuser interaction. It offers great potential for enhancing the immersion of distance touch communication.
“With the rapid development of virtual and augmented reality (VR and AR), our visual and auditory senses are not sufficient for us to create an ...
2023-02-23
PARAMUS, N.J. (Feb. 23, 2023) – Octapharma USA has submitted a Biologics License Application Supplement (sBLA) to the U.S. Food and Drug Administration (FDA) to expand the approval of wilate®, von Willebrand Factor/Coagulation Factor VIII Complex (Human) Lyophilized Powder for Solution for Intravenous Injection, to include routine prophylaxis to reduce the frequency of bleeding episodes in children and adults with any type of von Willebrand disease (VWD).
“We look forward to working with the FDA on this sBLA for wilate® ...
2023-02-23
February 23, 2023-- Using ensemble learning techniques and longitudinal data from a large naturalistic driving study, researchers at Columbia University’s Mailman School of Public Health, Fu Foundation School of Engineering and Applied Science, and Vagelos College of Physicians and Surgeons have developed a novel, interpretable and highly accurate algorithm for predicting mild cognitive impairment and dementia in older drivers. Digital markers refer to variables generated from data captured through recording devices in the real-world setting. These data could be processed to measure driving behavior, performance and tempo-spatial pattern in exceptional detail. ...
2023-02-23
Teens and young adults who reduced their social media use by 50% for just a few weeks saw significant improvement in how they felt about both their weight and their overall appearance compared with peers who maintained consistent levels of social media use, according to research published by the American Psychological Association.
“Adolescence is a vulnerable period for the development of body image issues, eating disorders and mental illness,” said lead author Gary Goldfield, PhD, of Children's Hospital of Eastern Ontario Research Institute. “Youth ...
2023-02-23
A decade-long international study into kidney cancer has shown that doctors can predict the likelihood of a patient’s disease returning by looking at DNA mutations in their tumours.
The research, undertaken by a team of 44 researchers at 23 institutions across Europe and Canada, and published today, is the largest to link the genetic changes that occur in kidney cancer to patient outcomes.
More than 400,000 people are diagnosed with kidney cancer each year globally, including 13,000 ...
2023-02-23
Getting good sleep can play a role in supporting your heart and overall health—and maybe even how long you live—according to new research being presented at the American College of Cardiology’s Annual Scientific Session Together With the World Congress of Cardiology. The study found that young people who have more beneficial sleep habits are incrementally less likely to die early. Moreover, the data suggest that about 8% of deaths from any cause could be attributed to poor sleep patterns.
“We saw ...
2023-02-23
People with gender dysphoria taking hormone replacements as part of gender affirmation therapy face a substantially increased risk of serious cardiac events, including stroke, heart attack and pulmonary embolism, according to a study presented at the American College of Cardiology’s Annual Scientific Session Together With the World Congress of Cardiology.
Gender dysphoria occurs when a person’s gender identity conflicts with the sex they were assigned at birth. Gender affirmation therapy, part of a process known as transitioning, includes a variety of medical, psychological and behavioral interventions to help ...
LAST 30 PRESS RELEASES:
[Press-News.org] GIST researchers develop “AMP-BERT”: A new AI-based “finder” of antimicrobial peptides
Scientists propose a deep neural network-based platform for identifying candidate antimicrobial peptides
