Machine-learning discovery and design of membrane-active peptides for biomedicine

November 15, 2016

There are approximately 1,100 known antimicrobial peptides (AMP) with diverse sequences that can permeate microbial membranes. To help discover the "blueprint" for natural AMP sequences, researchers from the University of Illinois at Urbana-Champaign and the University of California, Los Angeles, have developed a new machine learning approach to discover and design alpha-helical membrane active peptides based on their physicochemical properties.

"In this work, we have trained a machine learning classifier--known as a support vector machine--to recognize membrane activity and experimentally calibrated the recognition metric by peptide synthesis and characterization," explained Andrew Ferguson, an assistant professor of materials science and engineering at Illinois. "We use machine learning to not only discover new membrane active peptides, but to also identify membrane activity in known peptides with previously defined functions leading us to discover membrane activity in diverse and unexpected peptide families.

"Since getting cargo into a cell is important for many applications, we anticipate that this tool can have broad biomedical implications including in immunotherapy and in broad-spectrum membrane-active antimicrobial peptides to combat the rising incidence of drug resistance, design of cationic cell-penetrating peptides for nucleic acid transfection into cells, and in targeting and permeating anticancer therapeutics into tumors," added Ferguson, who was the senior computational investigator for the project.

In this collaborative work, the Illinois researchers developed the computational innovations, with the experimental testing of the predictions accomplished at UCLA. The results, which highlight the difference between the efficacy of an antimicrobial and its recognizability as such, are surprising.

"AMPs do not share a common core structure, but tend to be short, cationic , and amphiphilic," Ferguson said. "By training our machine learning classifier over a training set comprising peptides with known antimicrobial activity (hits) and decoy peptides with no activity (misses), the classifier learned the physical and chemical properties of a peptide that make for good membrane activity. We anticipated that the classifier would learn to discriminate the 'antimicrobial-ness' of a particular peptide sequence, but through experimental testing of its predictions we found that it actually learned a much more general and physical rule to discriminate peptides based on membrane activity. In effect, the classifier learned membrane activity as the underlying physical determinant of antimicrobial activity within the training set, and allows us to use our classifier to discover membrane active peptides in other diverse peptide classes."

"Using the SVM as an efficient discovery tool for membrane activity, we performed a guided search of peptide sequence space to discover new membrane active peptides that would be difficult for nature to evolve by simple mutation from existing alpha-helical membrane active peptides.," stated Ernest Y. Lee, first author of the paper, "Mapping membrane activity in undiscovered peptide sequence space using machine learning," appearing in the Proceedings of the National Academy of Sciences.

"What emerges is a diverse taxonomy of sequences that are expected to be not only just as membrane-active as known antimicrobial peptides, but also have a broad range of putative primary functions beyond antimicrobial activity including neuropeptides, viral fusion proteins, topogenic peptides, and amyloids," said Gerard Wong, a professor of bioengineering at UCLA and senior experimental investigator on the study. "Had their primary functions been undiscovered, these peptides could have been classified as AMPs. Not only is membrane activity not coextensive with antimicrobial activity, it is surprisingly common for many classes of natural peptides as one component of multiplexed functionality."
Co-authors of the article include Lee and Wong from UCLA, Benjamin Fulan (mathematics) and Ferguson at the University of Illinois.

University of Illinois College of Engineering

Related Antimicrobial Articles from Brightsurf:

Antimicrobial peptides with anticancer properties
Announcing a new article publication for BIO Integration journal. In this article the authors Zhong, Cuiyu; Zhang, Lei; Huang, Jiandong; Huang, Songyin; Yao, Yandan from Sun Yat-sen University, Guangzhou, China; Guangzhou Regenerative Medicine and Health Guangdong Laboratory, Guangzhou, China and Shenzhen Institutes of Advanced Technology, Guangdong, China review antimicrobial peptides with anticancer properties.

Treating COVID-19 could lead to increased antimicrobial resistance
Research led by the University of Plymouth suggests the increased use of antibiotics in the treatment of COVID-19 patients could be placing an additional burden on waste water treatment works, particularly those serving large or emergency hospitals

To prevent antimicrobial resistance, vaccinate the world's kids
Childhood vaccination may be a powerful tool in the fight against antimicrobial resistance in low- and middle-income countries, finds a new analysis led by researchers University of California, Berkeley.

Aquaculture at the crossroads of global warming and antimicrobial resistance
Antimicrobial resistance is responsible for some 700 000 deaths each year worldwide.

Who will lead the global surveillance of antimicrobial resistance via sewage?
In the journal Science, a DTU professor calls for someone to carry on a global surveillance of antimicrobial resistance and infectious diseases via sewage.

Sequencing sewage for antimicrobial resistance surveillance
In this Policy Forum, Frank Aarestrup and Mark Woolhouse advocate for the immediate establishment of a global antimicrobial resistance surveillance system based on the metagenomic sequencing of human sewage.

Novel composite antimicrobial film could take a bite out of foodborne illnesses
A novel composite film -- created by the bonding of an antimicrobial layer to conventional, clear polyethylene plastic typically used to vacuum-package foods such as meat and fish -- could help to decrease foodborne illness outbreaks, according to researchers in Penn State's College of Agricultural Sciences.

Squid pigments have antimicrobial properties
Ommochromes, the pigments that color the skin of squids and other invertebrates, could be used in the food and health sectors for their antioxidant and antimicrobial properties.

Antimicrobial resistance poses significant risk to people, the economy
CCA expert panel study provides new data on potential impact of antimicrobial resistance in Canada.

Antimicrobial resistance is drastically rising
An international team of researchers led by ETH has shown that antimicrobial-resistant infections are rapidly increasing in animals in low and middle income countries.

Read More: Antimicrobial News and Antimicrobial Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to