ASSET Center Inaugural Seed Grants Will Fund Trustworthy AI Research in Healthcare

by

Illustration credit: Melissa Pappas

Penn Engineering’s newly established ASSET Center aims to make AI-enabled systems more “safe, explainable and trustworthy” by studying the fundamentals of the artificial neural networks that organize and interpret data to solve problems.

ASSET’s first funding collaboration is with Penn’s Perelman School of Medicine (PSOM) and the Penn Institute for Biomedical Informatics (IBI). Together, they have launched a series of seed grants that will fund research at the intersection of AI and healthcare.

Teams featuring faculty members from Penn Engineering, Penn Medicine and the Wharton School applied for these grants, to be funded annually at $100,000. A committee consisting of faculty from both Penn Engineering and PSOM evaluated 18 applications and  judged the proposals based on clinical relevance, AI foundations and potential for impact.

Artificial intelligence and machine learning promise to revolutionize nearly every field, sifting through massive amounts of data to find insights that humans would miss, making faster and more accurate decisions and predictions as a result.

Applying those insights to healthcare could yield life-saving benefits. For example, AI-enabled systems could analyze medical imaging for hard-to-spot tumors, collate multiple streams of disparate patient information for faster diagnoses or more accurately predict the course of disease.

Given the stakes, however, understanding exactly how these technologies arrive at their conclusions is critical. Doctors, nurses and other healthcare providers won’t use such technologies if they don’t trust that their internal logic is sound.

“We are developing techniques that will allow AI-based decision systems to provide both quantifiable guarantees and explanations of their predictions,” says Rajeev Alur, Zisman Family Professor in Computer and Information Science and Director of the ASSET Center. “Transparency and accuracy are key.”

“Development of explainable and trustworthy AI is critical for adoption in the practice of medicine,” adds Marylyn Ritchie, Professor of Genetics and Director of the Penn Institute for Biomedical Informatics. “We are thrilled about this partnership between ASSET and IBI to fund these innovative and exciting projects.”

 Seven projects were selected in the inaugural class, including projects from Dani S. Bassett, J. Peter Skirkanich Professor in the Departments of Bioengineering, Electrical and Systems Engineering, Physics & Astronomy, Neurology, and Psychiatry, and several members of the Penn Bioengineering Graduate Group: Despina Kontos, Matthew J. Wilson Professor of Research Radiology II, Department of Radiology, Penn Medicine and Lyle Ungar, Professor, Department of Computer and Information Science, Penn Engineering; Spyridon Bakas, Assistant Professor, Departments of Pathology and Laboratory Medicine and Radiology, Penn Medicine; and Walter R. Witschey, Associate Professor, Department of Radiology, Penn Medicine.

Optimizing clinical monitoring for delivery room resuscitation using novel interpretable AI

Elizabeth Foglia, Associate Professor, Department of Pediatrics, Penn Medicine and the Children’s Hospital of Philadelphia

Dani S. Bassett, J. Peter Skirkanich Professor, Departments of Bioengineering and Electrical and Systems Engineering, Penn Engineering

 This project will apply a novel interpretable machine learning approach, known as the Distributed Information Bottleneck, to solve pressing problems in identifying and displaying critical information during time-sensitive clinical encounters. This project will develop a framework for the optimal integration of information from multiple physiologic measures that are continuously monitored during delivery room resuscitation. The team’s immediate goal is to detect and display key target respiratory parameters during delivery room resuscitation to prevent acute and chronic lung injury for preterm infants. Because this approach is generalizable to any setting in which complex relations between information-rich variables are predictive of health outcomes, the project will lay the groundwork for future applications to other clinical scenarios.

Read the full list of projects and abstracts in Penn Engineering Today.

CAR T Cell Therapy Reaches Beyond Cancer

Penn Medicine researchers laud the early results for CAR T therapy in lupus patients, which point to broader horizons for the use of personalized cellular therapies.

Penn Medicine’s Carl June and Daniel Baker.

Engineered immune cells, known as CAR T cells, have shown the world what personalized immunotherapies can do to fight blood cancers. Now, investigators have reported highly promising early results for CAR T therapy in a small set of patients with the autoimmune disease lupus. Penn Medicine CAR T pioneer Carl June and Daniel Baker, a doctoral student in cell and molecular biology in the Perelman School of Medicine, discuss this development in a commentary published in Cell.

“We’ve always known that in principle, CAR T therapies could have broad applications, and it’s very encouraging to see early evidence that this promise is now being realized,” says June, who is the Richard W. Vague Professor in Immunotherapy in the department of Pathology and Laboratory Medicine at Penn Medicine and director of the Center for Cellular Immunotherapies at the Abramson Cancer Center.

T cells are among the immune system’s most powerful weapons. They can bind to, and kill, other cells they recognize as valid targets, including virus-infected cells. CAR T cells are T cells that have been redirected, through genetic engineering, to efficiently kill specifically defined cell types.

CAR T therapies are created out of each patient’s own cells—collected from the patient’s blood, and then engineered and multiplied in the lab before being reinfused into the patient as a “living drug.” The first CAR T therapy, Kymriah, was developed by June and his team at Penn Medicine, and received Food & Drug Administration approval in 2017. There are now six FDA-approved CAR T cell therapies in the United States, for six different cancers.

From the start of CAR T research, experts believed that T cells could be engineered to fight many conditions other than B cell cancers. Dozens of research teams around the world, including teams at Penn Medicine and biotech spinoffs who are working to develop effective treatments from Penn-developed personalized cellular therapy constructs, are examining these potential new applications. Researchers say lupus is an obvious choice for CAR T therapy because it too is driven by B cells, and thus experimental CAR T therapies against it can employ existing anti-B-cell designs. B cells are the immune system’s antibody-producing cells, and, in lupus, B cells arise that attack the patient’s own organs and tissues.

This story is by Meagan Raeke. Read more at Penn Medicine News.

Carl June is a member of the Penn Bioengineering Graduate Group. Read more stories featuring June’s research here.

The Penn Center for Precision Engineering for Health Announces First Round of Seed Funding

by Melissa Pappas

CPE4H is one of the focal points of Penn Engineering signature initiative on Engineering Health.

The Penn Center for Precision Engineering for Health (CPE4H) was established late last year to accelerate engineering solutions to significant problems in healthcare. The center is one of the signature initiatives for Penn’s School of Engineering and Applied Science and is supported by a $100 million commitment to hire faculty and support new research on innovative approaches to those problems.

Acting on that commitment, CPE4H solicited proposals during the spring of 2022 for seed grants of $80K per year for two years for research projects that address healthcare challenges in several key areas of strategic importance to Penn: synthetic biology and tissue engineering, diagnosis and drug delivery, and the development of innovative devices. While the primary investigators (PIs) for the proposed projects were required to have a primary faculty appointment within Penn Engineering, teams involving co-PIs and collaborators from other schools were eligible for support. The seed program is expected to continue for the next four years.

“It was a delight to read so many novel and creative proposals,” says Daniel A. Hammer, Alfred G. and Meta A. Ennis Professor in Bioengineering and the Inaugural Director of CPE4H. “It was very hard to make the final selection from a pool of such promising projects.”

Judged on technical innovation, potential to attract future resources, and ability to address a significant medical problem, the following research projects were selected to receive funding.

Evolving and Engineering Thermal Control of Mammalian Cells

Led by Lukasz Bugaj, Assistant Professor in Bioengineering, this project will engineer molecular switches that can be toggled on and off inside mammalian cells at near-physiological temperatures. Successful development of these switches will provide new ways to communicate with cells, an advance that could be used to make safer and more effective cellular therapies.  The project will use directed evolution to generate and find candidate molecular tools with the desired properties. Separately, the research will also develop new technology for manipulating cellular temperature in a rapid and programmable way. Such devices will enhance the speed and sophistication of studies of biological temperature regulation.

A Quantum Sensing Platform for Rapid and Accurate Point-of-Care Detection of Respiratory Viral Infections

Combining microfluidics and quantum photonics, PI Liang Feng, Professor in Materials Science and Engineering and Electrical and Systems Engineering, Ritesh Agarwal, Professor in Materials Science Engineering, and Shu Yang, Joseph Bordogna Professor in Materials Science and Engineering and Chemical and Biomolecular Engineering, are teaming up with Ping Wang, Professor of Pathology and Laboratory Medicine in Penn’s Perelman School of Medicine, to design, build and test an ultrasensitive point-of-care detector for respiratory pathogens. In light of the COVID-19 pandemic, a generalizable platform for rapid and accurate detection of viral pathogenesis would be extremely important and timely.

Versatile Coacervating Peptides as Carriers and Synthetic Organelles for Cell Engineering

PI Amish Patel, Associate Professor in Chemical and Biomolecular Engineering, and Matthew C. Good, Associate Professor of Cell and Developmental Biology in the Perelman School of Medicine and in Bioengineering, will design and create small proteins that self-assemble into droplet-like structures known as coacervates, which can then pass through the membranes of biological cells. Upon cellular entry, these protein coacervates can disassemble to deliver cargo that modulates cell behavior or be maintained as synthetic membraneless organelles. The team will design new chemistries that will facilitate passage across cell membranes, and molecular switches to sequester and release protein therapeutics. If successful, this approach could be used to deliver a wide range of macromolecule drugs to cells.

Towards an Artificial Muscle Replacement for Facial Reanimation

Cynthia Sung, Gabel Family Term Assistant Professor in Mechanical Engineering and Applied Mechanics and Computer Information Science, will lead a research team including Flavia Vitale, Assistant Professor of Neurology and Bioengineering, and Niv Milbar, Assistant Instructor in Surgery in the Perelman School of Medicine. The team will develop and validate an electrically driven actuator to restore basic muscle responses in patients with partial facial paralysis, which can occur after a stroke or injury. The research will combine elements of robotics and biology, and aims to produce a device that can be clinically tested.

“These novel ideas are a great way to kick off the activities of the center,” says Hammer. “We look forward to soliciting other exciting seed proposals over the next several years.”

This article originally appeared in Penn Engineering Today.

Researchers Develop Technology to Keep Track of Living Cells and Tissues

SAFE Bioorthogonal Cycling

Cells in complex organisms undergo frequent changes, and researchers have struggled to monitor these changes and create a comprehensive profile for living cells and tissues. Historically researchers have been limited to only 3-5 markers due to spectral overlaps in fluorescence microscopy, an essential tool required for imaging cells. With only this small handful of markers, it is difficult to monitor protein expressions of live cells and a comprehensive profile of cellular dynamics cannot be created. However, a new study in Nature Biotechnology addresses these limitations by demonstrating a new method for comprehensive profiling of living cells.

Jina Ko, PhD

Jina Ko, Assistant Professor in Bioengineering in the School of Engineering and Applied Science and in Pathology and Laboratory Medicine in the Perelman School of Medicine, conducted postdoctoral research at Massachusetts General Hospital (MGH) and the Wyss Institute at Harvard University, and the work for this study was done under the supervision of Jonathan Carlson M.D., Ph.D. and Ralph Weissleder M.D., Ph.D. of MGH. Ko’s lab at Penn develops novel technologies using bioengineering, molecular biology, and chemistry to address diagnostic challenges for precision medicine.

To address these limitations in microscopy, the team developed a new chemistry tool which was highly gentle to cells. This “scission-accelerated fluorophore exchange (or SAFE)” method utilizes “click” chemistry, a type of chemistry that follows examples found in nature to create fast and simple reactions. This new SAFE method functions with non-toxic conditions to living cells and tissues, whereas previous methods have used harsh chemicals that would strip off fluorophores and consequently would not work with living cells and tissues.

With the development of SAFE, the authors demonstrated that researchers can now effectively perform multiple cycles of cell profiling and can monitor cellular changes over the course of their observations. Instead of the previous limitation of 3-5 markers total, SAFE allows for many more cycles and can keep track of almost as many markers as the researcher wants. One can now stain cells and quench/release fluorophores and repeat the cycle multiple times for multiplexing on living cells. Each cycle can profile 3 markers, and so someone interested in profiling 15 markers could easily perform 5 cycles to achieve this much more comprehensive cell profile. With this breakthrough in more detailed imaging of cells, SAFE demonstrates broad applicability for allowing researchers to better investigate the physiologic dynamics in living systems.

Read the paper, “Spatiotemporal multiplexed immunofluorescence imaging of living cells and tissues with bioorthogonal cycling of fluorescent probes,” in Nature Biotechnology.

This study was supported by the Schmidt Science Fellows in Partnership with the Rhodes Trust and National Institutes of Health, National Cancer Institute (K99CA256353).

Bioengineering Contributes to “New COVID-19 Testing Technology at Penn”

César de la Fuente, Ph.D., a Presidential Assistant Professor in Psychiatry, Microbiology, and Bioengineering, is leading a team to develop an electrode that can be easily printed at low cost to provide COVID-19 test results from your smart phone.

A recent Penn Medicine blog post surveys the efforts across Penn and the Perelman School of Medicine to develop novel says to detect SARS-CoV-2 and features several Department of Bioengineering faculty and Graduate Group members, including César de la Fuente, Presidential Assistant Professor in Psychiatry, Microbiology, and Bioengineering; Arupa Ganguly, Professor in Genetics; A.T. Charlie Johnson, Rebecca W. Bushnell Professor in Physics and Astronomy; Lyle Ungar, Professor in Computer and Information Science; and Ping Wang, Associate Professor in Pathology and Laboratory Medicine.

Read “We’ll Need More than Vaccines to Vanquish the Virus: New COVID-19 Testing Technology at Penn” by Melissa Moody in Penn Medicine News.

Hao Huang Named AIMBE Fellow

Hao Huang, Ph.D.

Hao Huang, Research Associate Professor of Radiology in the Perelman School of Medicine and member of the Penn Bioengineering Graduate Group, has been named an American Institute for Medical and Biological Engineering (AIMBE) Fellow.

Election to the AIMBE College of Fellows is among the highest professional distinctions accorded to a medical and biological engineer. “The College of Fellows is comprised of the top two percent of medical and biological engineers in the country. The most accomplished and distinguished engineering and medical school chairs, research directors, professors, innovators, and successful entrepreneurs comprise the College of Fellows. AIMBE Fellows are regularly recognized for their contributions in teaching, research, and innovation.”

Huang was “nominated, reviewed, and elected by peers and members of the College of Fellows for contributions to the development and applications of innovative MR methods to study the developing brain.”

A formal induction ceremony will be held during AIMBE’s virtual 2021 Annual Event on March 26. Huang will be inducted along with 174 colleagues who make up the AIMBE Fellow Class of 2021.

Read the full press release.

BE Seminar: “Deconstructing and Reconstructing Human Tissues” (Kelly Stevens)

Kelly Stevens, PhD

Speaker:  Kelly Stevens, Ph.D.
Assistant Professor, Department of Bioengineering and Department of Laboratory Medicine & Pathology
University of Washington

Date: Thursday, January 21, 2021
Time: 3:00-4:00 PM EST
Zoom – check email for link or contact ksas@seas.upenn.edu

Title: “Deconstructing and Reconstructing Human Tissues”

Abstract:

Although much progress has been made in building artificial human tissues over the past several decades, replicating complex tissue structure remains an enormous challenge. To overcome this challenge, our field first needs to create better three-dimensional spatial maps, or “blueprints” of human tissues and organs. We also need to then understand how these spatial blueprints encode positional processes in tissues. My group is developing new advanced biofabrication technologies to address both of these issues. Here, I will describe some of our work in both attaining transcriptomic maps as well as in controlling spatiogenetic wiring of human artificial tissues.

Bio:

Dr. Kelly Stevens is an Assistant Professor of Bioengineering, and Laboratory Medicine & Pathology at the University of Washington. Dr. Stevens’ research focuses on mapping and building artificial human tissues to treat liver and heart disease. She has made contributions to improve human cell sourcing, vascularization, structure and physiology of human bioartificial tissues. Dr. Stevens has received several awards in recognition of this work, including the NIH New Innovator Award, BMES CMBE Rising Star Award, John Tietze Stem Cell Scientist Award, and Gree Foundation Scholar Award.