Artificial intelligence algorithm to predict and prevent spread of infectious diseases

Team of researchers from USC Viterbi School of Engineering has created an algorithm that can help policymakers reduce the overall spread of disease. The algorithm is optimized to make the most of limited resources, such as advertising budgets, thus helping cash strapped public health agencies.

To create the artificial intellegence algorithm, the researchers used behavioral, demographic and epidemic disease trends data to generate a model of disease spread that captures underlying population dynamics and contact patterns between people. Using computer simulations, the researchers tested the algorithm on tuberculosis (TB) spread in India and gonorrhea in the United States. In both cases, they found the algorithm did a better job at reducing disease cases than current health outreach policies by sharing information about these diseases with individuals who might be most at risk.

The study was published in the AAAI Conference on Artificial Intelligence. The authors are Bryan Wilder, a candidate for a PhD in computer science, Milind Tambe, the Helen N. and Emmett H. Jones Professor in Engineering, a professor of computer science and industrial and systems engineering and co-founder of the USC Center for AI in Society and Sze-chuan Suen, an assistant professor in industrial and systems engineering.

“Our study shows that a sophisticated algorithm can substantially reduce disease spread overall,” says Wilder, the first author of the paper. “We can make a big difference, and even save lives, just by being a little bit smarter about how we use resources and share health information with the public.”

The algorithm also appeared to make more strategic use of resources. The team found it concentrated heavily on particular groups and did not simply allocate more budget to groups with a high prevalence of the disease. This seems to indicate that the algorithm is leveraging non-obvious patterns and taking advantage of sometimes-subtle interactions between variables that humans may not be able to pinpoint. The team’s mathematical models also take into account that people move, age, and die, reflecting more realistic population dynamics than many existing algorithms for disease control.

Adapted from press release by University of South California.

New approach to tuberculosis treatment: targeting LD-transpeptidase enzyme

Researchers at Johns Hopkins report they have laid the foundation to develop novel antibiotics that work against incurable, antibiotic-resistant bacteria like tuberculosis by targeting an enzyme essential to the production and integrity of bacterial cell walls. The findings, they say, suggest that antibiotic drugs specifically targeting the recently discovered LD-transpeptidase enzyme, which is needed to build bacterial cell walls in some bacteria, could potentially cure many antibiotic-resistant infections.

An additional implication of the research, the Johns Hopkins team says, is that drugs targeting the enzyme could offer quicker, cheaper and more easily accessible treatment against tuberculosis, a disease that still kills more people worldwide than any other infection, according to the Centers for Disease Control and Prevention. A summary of the findings is published on Nov. 7 in Nature Chemical Biology.

At the root of their investigation, Gyanu Lamichhane, Ph.D. associate professor of medicine at the Johns Hopkins University School of Medicine says, is the fact than more than half of antibiotics prescribed today are of a class called beta-lactams, which work by interrupting the function of the DD-transpeptidase enzyme that creates bacterial cell walls. Without it, bacteria quickly die. However, in 2005, a team of researchers found a second wall-building enzyme, LD-transpeptidase, that allows bacteria like the ones that cause TB to survive antibiotic treatments.

Pankaj Kumar, Ph.D., postdoctoral fellow in infectious diseases at the Johns Hopkins University School of Medicine, began the research in the new study by extracting LD-transpeptidase from many species of bacteria and examining its detailed molecular structure with a sophisticated imaging system known as protein X-ray crystallography using the Advanced Photon Source at the Argonne National Laboratory in Chicago.

By analyzing the enzyme’s structure, Johns Hopkins researchers were able to design new compounds in the carbapenem group, a subclass of the beta-lactam antibiotics that bind to the LD-transpeptidase wall-building enzyme and stop its function.

In live bacterial cultures, the carbapenems were shown by Lamichhane’s and Townsend’s groups to stop the enzyme’s wall-building activity. The new compounds were even effective against the ESKAPE pathogens, a group of six bacterial species that the Centers for Disease Control and Prevention has identified as a threat because of their propensity for developing antibiotic resistance.
Following these successes, Amit Kaushik, Ph.D., a postdoctoral fellow in infectious diseases at the Johns Hopkins University School of Medicine, tested two carbapenems in vivo against TB in mice infected with TB.

Researchers infected mice with tuberculosis bacteria and separated them into different treatment groups. The rodents’ lungs were sampled periodically over a period of three weeks, and the results showed that even without use of classic TB antibiotic treatments, the new carbapenems, specifically biapenem, cured TB infection in mice.

Townsend and Lamichhane say the focus of their research is now on creating variations of their original compound that are designed to target specific bacteria. The researchers are now in the process of initiating clinical trials to test the safety and efficacy of some of these new compounds.

Citation: Pankaj Kumar, Amit Kaushik, Evan P Lloyd, Shao-Gang Li, Rohini Mattoo, Nicole C Ammerman, Drew T Bell, Alexander L Perryman, Trevor A Zandi, Sean Ekins, Stephan L Ginell, Craig A Townsend, Joel S Freundlich & Gyanu Lamichhane. “Non-classical transpeptidases yield insight into new antibacterials”. Nature Chemical Biology (2016)
Research funding: National Institutes of Health, DOE/Office of Biological and Environmental Research
Adapted from press release by Johns Hopkins University School of Medicine.

Role of TB specific antibodies in Tuberculosis infection found

A study led by investigators from the Ragon Institute of MGH, MIT, and Harvard finds evidence that antibody protection may help control infection with the bacteria that causes tuberculosis. In their study receiving online publication in Cell, the research team describes finding consistent differences in both the structure and function of antibodies targeting the TB bacteria between individuals with active TB disease and those with latent TB, which neither produces symptoms nor can be transmitted.

“A more effective vaccine against TB could substantially contribute towards that goal, impacting the nearly one in three people worldwide who are infected and addressing the leading killer of individuals infected with HIV.” The only currently available preventive against infection with the TB bacteria – the BCG vaccine – has been available since the 1920s; but its effectiveness against pulmonary TB, the most common form of the disease, has always been uncertain.

Previous investigations into a possible role for antibodies in the immune response to TB have had conflicting results, but the Ragon team – led by Galit Alter, Ph.D., of MGH Department of Medicine and Sarah Fortune, MD, of the Harvard T.H. Chan School of Public Health – used a novel approach.
In addition to binding to their target pathogens and marking them for destruction by the immune system, antibodies also directly stimulate pathogen-killing cells of the innate immune system by binding to a cell-surface protein called the Fc receptor.

The Ragon team profiled TB-specific antibodies from 22 individuals with latent TB and 20 with active TB for 70 different features associated with Fc-mediated antibody function. They first identified nine characteristics that differentiated between antibodies of the two groups of participants, and further investigation identified the biomarker that best distinguished between them.

A key regulator of the Fc-mediated immune function is the addition to antibodies of compounds called glycans, made up of sugar molecules; and distinct differences in glycosylation patterns were found to clearly distinguish latent TB antibodies from active TB antibodies.

To confirm these results in the initial group of participants, who were from South Africa, the team conducted a similar analysis of antibodies from 20 individuals from Texas and Mexico – half with latent and half with active TB – and had the same results. Further experiments revealed that application of latent TB antibodies to TB-infected human macrophages not only increased the activation of several antimicrobial processes but also reduced the survival of the TB bacteria.

Press release: Antibody function may help keep tuberculosis infection under control
Journal article: