Daniel Lobo has a knack for using artificial intelligence to solve biological puzzles, and his latest scientific paper is proof of concept that computer simulations can predict never-before-seen biological outcomes. The new article in Scientific Reports focuses on a model Lobo, assistant professor of biological sciences at UMBC, developed in collaboration with Michael Levin’s lab at the Allen Discovery Center at Tufts University.

Lobo’s model examines the development of pigment cells in frog embryos. He codified dozens of experiments on tadpole development and input the data into his program, which then “learned” how different drugs and proteins affect the growth of pigment cells in the frog. The model the computer discovered explained how certain combinations of treatments could induce cancer-like cell behaviors in tadpoles. Lobo envisions using the same process of teaching a computer to understand complex drug effects to predict, for example, the most effective drug treatment plans for individual cancer patients.

In the experiments, tadpoles either developed normally or were completely covered with invading pigment cells that had converted to a cancer-like state; there were no tadpoles with a mix of cancer-like and normal pigment cells. To test the predictive power of his model, Lobo wanted to determine if he could use it to find a combination of drugs that could generate a different outcome: an “in-between” tadpole, with some normal and some cancer-like pigment cells. Among 576 simulated experiments, the program identified only one specific combination of treatments that it predicted would produce that result.

Levin and Maria Lobikin, a past member of Levin’s lab, collaborated on the new paper to test the model’s prediction with real tadpoles, and it proved to be correct. Frog embryos given the specific cocktail that Lobo’s program identified (two drugs and a specific small strand of genetic material called an mRNA) developed into tadpoles that contained both normal areas without pigment cells and areas covered with invading cancer-like pigment cells.

Using traditional methods to identify the drug cocktail would have been much more costly and laborious, if it were possible at all. And it would have required a huge number of frog embryos and experiments. Alternatively, explains Lobo, “You can do a lot of cheap experiments inside a computer.” Plus, he says, “It only uses virtual frogs.”

Lobo hopes the method he used to create his new model can be put to work to find more effective treatments for human diseases, and his first target is cancer. The first—and by far most challenging—step is to generate a program with artificial intelligence that can learn from the data in published studies to create a model for the disease. Lobo’s lab is in the early stages of that process with cancer.

Once his program has used the data to generate a model, predicting a desired outcome should be straightforward, says Lobo. “You can simulate any drug, any intervention,” and in any combination, he explains, as long as the effects of any single intervention are understood. The ultimate goal, Lobo says, “is to find the best intervention or combination of interventions to get the person back to a normal state.”

His work may have started with frogs, but Lobo believes the predictive power of computer simulations has the potential to revolutionize human disease research and treatment. Focusing more intensive research on the specific interventions that computer simulations predict will be most effective would dramatically speed up the timeline for getting patients treatments that work.

Using artificial intelligence this way might also enable “very targeted, personalized medicine,” says Lobo. With human patients, doctors don’t have the luxury of hundreds of trials. “You may only have one chance, and it may be life or death,” he says. “You want to be sure the first treatment has the best chance of curing the disease.”

Read “Discovering novel phenotypes with automatically inferred dynamic models: a partial melanocyte conversion in Xenopus” in Scientific Reports.

Image: Daniel Lobo at UMBC. Photo by Marlayna Demond ’11 for UMBC.

UMBC and nine fellow members of the Baltimore Area Higher Education Coalition Against Sexual Violence have received a three-year, $750,000 grant from the U.S. Department of Justice (DOJ) Office on Violence against Women to create new strategies to prevent, respond to, and investigate sexual assault, domestic violence, relationship violence, and stalking, and to strengthen trauma-informed survivor services.

Specific coalition objectives include increasing awareness of and access to victim services on and off campus, and assessing and enhancing the capacity of campus response teams to address sexual violence. The coalition is also working to provide more comprehensive and actively inclusive survivor-centered trainings to serve the needs of all groups, including specific information on serving LGBT students and students of color, among other goals.

The grant is part of a $25 million funding package announced by the DOJ in fall 2016. Loyola University Maryland is administering the Baltimore coalition’s award. In addition to the ten participating universities, this partnership includes collaboration with the Baltimore City Police Department, Baltimore Collegetown Network, and TurnAround, Inc., a Baltimore-based service provider for victims of domestic violence and sexual assault.

Concurrent with applying for this grant, and in accordance with the Maryland Higher Education Commission (MHEC), UMBC’s Office of Human Relations administered a Campus Climate and Sexual Assault (CCSA) survey in spring 2016. The survey sought to better understand student perceptions, experiences, and awareness related to sexual assault and relationship violence.The UMBC Office of Human Relations, in collaboration with the Division of Student Affairs, has created a one-page infographic highlighting the main CCSA survey findings.

MHEC has also published a more comprehensive Report on Campus Climate and Sexual Violence at Maryland Colleges and Universities (see volume 1 and volume 2, that includes combined data from UMBC and other institutions.

Students who have experienced sexual assault or relationship violence, or know of someone who has, can access confidential support and resources through the Counseling Center and University Health Services at UMBC’s main campus, or the Center for Counseling and Consultation at the Universities at Shady Grove campus. Members of the UMBC community can file reports with UMBC Police and Title IX Coordinator Bobbie L. Hoye, and can access the Women’s Center as a quasi-confidential resource. Additional resources and the university’s policy on sexual misconduct are available through the Office of Human Relations.

In a new article in The Conversation, Political Science Professor Roy Meyers argues that any repeal, replacement, or revision of the Affordable Care Act (ACA) should have established, specific goals for reform and build on existing processes for tracking attainment of those goals.

In his article, Meyers, who is an expert in American politics and public administration and policy, traced the origins of the ACA and the accountability measures established in 2010 to track progress of the law.

“Some of the goals the Obama administration set for the health sector included how many people it aimed to enroll in the new health insurance marketplaces, the share of the non-elderly population still uninsured and hospital readmission rates,” Meyers wrote. “As one example, the Health and Human Services Department wanted to get 10 million people enrolled in ACA health insurance marketplaces in 2016, up from its target of 9 million the year before. In March 2016, the department reported that it had surpassed its goal by 2.7 million.”

Meyers added that any repeal or reform process could face several potential roadblocks due to the Byrd rule, which ensures reconciliation bills affect spending or revenue. “One of its elements also says that provisions with a different purpose from the bill in question – such as, in the ACA repeal’s case, killing a health care regulation – have to be excluded. And since the health sector is very complex, any effort to repeal and replace the ACA would have many provisions that would be prohibited by the Byrd rule,” wrote Meyers.

While Meyers notes that he thinks some parts of the ACA should be revised, he argues that it should be done through a bipartisan process.

“If Democrats and Republicans jointly agree on establishing specific goals for the reform, building on the existing process for monitoring attainment of those targets, it could lead to measurable improvements in the health system. In doing so, the ‘repeal and replace’ campaign slogan could be transformed into ‘repair with results.’”

Read the full article in The Conversation.

This article was also republished in Newsweek. Read “How Democrats can hold Republicans accountable for healthcare fix.”

Image: Former President Barack Obama speaks to a joint session of Congress regarding health care reform, September 9, 2009. Public domain image, whitehouse.gov photo by Lawrence Jackson.

As a form of public service, public historians can help create historical understanding with a variety of partners by sharing authority and inquiry in the communities that they serve. But what does studying the origins of public history reveal about the discipline?

Denise Meringolo, an associate professor of history and director of public history, recently published an article that studies roots of this question on the National Council on Public History website (NCPH). She contributed the article as part of the “Radical Roots: Civic Engagement, Public History, and a Tradition of Social Justice Activism,” a collaborative research project that “identifies new historical precedents for the values and practices that have come to define the field, particularly those now associated with civic engagement,” according to the NCPH website.

In her article, Meringolo argues how public history largely centers around collaborative scholarship, community-based education, and university-community partnership.

“By identifying experiments in community-based education less strictly tied to university and college departments of history, we can open up more nuanced critical perspectives on the intersections among teaching, learning, and community development,” she wrote.

Meringolo references The American Civilization Institute (ACIM) of Morristown, New Jersey as an early example of community-based education and teaching due to its engagement with local students and faculty in its community.

“Founders of the ACIM recognized that growing interest in historic preservation provided them with an opportunity to connect research and interpretation to political activism and advocacy,” she wrote.

Professor Meringolo is leading a project to archive materials from the Baltimore Uprising through a website that was launched in 2015. The aim is to gather and preserve a diverse range of perspectives and experiences from the events surrounding the Uprising, and there have been thousands of submissions from community members. Read more about her work on the history department website.

Image: Denise Meringolo. Photo by Marlayna Demond ’11 for UMBC.

Update from 2/1/18 Blackboard Analytics Symposium: Using Bb Predict and UMBC's FYI alert program together is more accurate than using either service alone.

------------------------------------------

Recent high profile articles in both the Baltimore Sun and the New York Times have highlighted the important and growing role of analytics in higher education. UMBC in particular is working to develop accurate means to predict and subsequently support student academic success. Of particular interest is faculty and student Blackboard (Bb) Grade Center use.

Based on a pilot project looking at UMBC Bb data for the past two years, it is possible to predict with 83% accuracy whether or not a student will earn a C or better in any given course before the term begins using prior academic and demographic characteristics. By the start of week 4, however, student grades in a Bb course become the most important predictor throughout the remainder of the term. The model was developed using an 80% random sample of all UMBC Bb courses, tested against the remaining 20%, and included several demographic and academic factors. It was 83% accurate thru week 3, 87% accurate by week 4, and 93% accurate by week 12 (final 20% of a 15-week term).

These findings echo prior research on first year students in UMBC Bb courses. Specifically, when viewing student activity and if faculty enabled the Grade Center, students were up to two and a half times more likely to earn a C or better in Bb courses that used the Grade Center compared to courses that did not. The highest student activity and Grade Center interaction effect occurred among Freshmen (1). These findings also complement research by the Educause Center for Applied Research (ECAR) that students value faculty use of the grade center more than any other LMS function (2). Finally, a recent Bb study found that students’ frequent checking their grades online was highly predictive of their course success (3).

By increasing the use of of the Grade Center, faculty can enhance students’ potential for self-efficacy while furthering the effectiveness of systematic efforts to enhance student engagement.

(1) Fritz, J. L. (2016). Using analytics to encourage student responsibility for learning and identify course designs that help (Ph.D.). University of Maryland, Baltimore County, United States -- Maryland. Retrieved from http://umbc.box.com/johnfritzdissertation, pp. 168-169.

(2) Caruso, J., & Salaway, G. (2007). The ECAR study of undergraduate students and information technology, 2007 (Key Findings) (pp. 1–15). Educause Center for Applied Research. Retrieved from https://net.educause.edu/ir/library/pdf/ers0706/ekf0706.pdf. 

(3) Young, J. (2016, September 7). What Clicks From 70,000 Courses Reveal About Student Learning. The Chronicle of Higher Education. Retrieved from http://www.chronicle.com/article/What-Clicks-From-70000/237704/