A hyperlink network from English Wikipedia, with only 0.1% of articles (nodes) and their connections (edges) visualized. Seven different reader journeys through this network are highlighted in various colors. The network is organized by topic and displayed using a layout that groups related articles together. (Image: Dale Zhou)
At one point or another, you may have gone online looking for a specific bit of information and found yourself “going down the Wiki rabbit hole” as you discover wholly new, ever-more fascinating related topics — some trivial, some relevant — and you may have gone so far down the hole it’s difficult to piece together what brought you there to begin with.
According to the University of Pennsylvania’s Dani Bassett, who recently worked with a collaborative team of researcher to examine the browsing habits of 482,760 Wikipedia readers from 50 different countries, this style of information acquisition is called the “busybody.” This is someone who goes from one idea or piece of information to another, and the two pieces may not relate to each other much.
“The busybody loves any and all kinds of newness, they’re happy to jump from here to there, with seemingly no rhyme or reason, and this is contrasted by the ‘hunter,’ which is a more goal-oriented, focused person who seeks to solve a problem, find a missing factor, or fill out a model of the world,” says Bassett.
In the research, published in the journal Science Advances, Bassett and colleagues discovered stark differences in browsing habits between countries with more education and gender equality versus less equality, raising key questions about the impact of culture on curiosity and learning.
Dani S. Bassett is the J. Peter Skirkanich Professor at the University of Pennsylvania with a primary appointment in the School of Engineering and Applied Science’s Department of Bioengineering and secondary appointments in the School of Arts & Sciences’ Department of Physics & Astronomy, Penn Engineering’s Department of Electrical and Systems Engineering, and the Perelman School of Medicine’s Departments of Neurology and Psychiatry.
The NSF AIRFoundry will accelerate RNA research using the power of AI and educate the next generation of RNA researchers. (DesignCells via Getty Images)
In a typical foundry, raw materials like steel and copper are melted down and poured into molds to assume new shapes and functions. The U.S. National Science Foundation Artificial Intelligence-driven RNA Foundry (NSF AIRFoundry), led by the University of Pennsylvania and the University of Puerto Rico and supported by an $18-million, six-year grant, will serve much the same purpose, only instead of smithing metal, the “BioFoundry” will create molecules and nanoparticles.
NSF AIRFoundry is one of five newly created BioFoundries, each of which will have a different focus. Bringing together researchers from Penn Engineering, Penn Medicine’s Institute for RNA Innovation, the University of Puerto Rico–Mayagüez (UPR-M), Drexel University, the Children’s Hospital of Philadelphia (CHOP) and InfiniFluidics, the facility, which will be physically located in West Philadelphia and at UPR-M, will focus on ribonucleic acid (RNA), the tiny molecule essential to genetic expression and protein synthesis that played a key role in the COVID-19 vaccines and saved tens of millions of lives.
The facility will use AI to design, optimize and synthesize RNA and delivery vehicles by augmenting human expertise, enabling rapid iterative experimentation, and providing predictive models and automated workflows to accelerate discovery and innovation.
“With NSF AIRFoundry, we are creating a hub for innovation in RNA technology that will empower scientists to tackle some of the world’s biggest challenges, from health care to environmental sustainability,” says Daeyeon Lee, Russell Pearce and Elizabeth Crimian Heuer Professor in Chemical and Biomolecular Engineering in Penn Engineering and NSF AIRFoundry’s director.
“Our goal is to make cutting-edge RNA research accessible to a broad scientific community beyond the health care sector, accelerating basic research and discoveries that can lead to new treatments, improved crops and more resilient ecosystems,” adds Nobel laureate Drew Weissman, Roberts Family Professor in Vaccine Research in Penn Medicine, Director of the Penn Institute for RNA Innovation and NSF AIRFoundry’s senior associate director.
The facility will catalyze new innovations in the field by leveraging artificial intelligence (AI). AI has already shown great promise in drug discovery, poring over vast amounts of data to find hidden patterns. “By integrating artificial intelligence and advanced manufacturing techniques, the NSF AIRFoundry will revolutionize how we design and produce RNA-based solutions,” says David Issadore, Professor in Bioengineering and in Electrical and Systems Engineering at Penn Engineering and the facility’s associate director of research coordination.
Penn Engineering and Stanford researchers leveraged AI to discover dozens of potential new antibiotics in the human gut microbiome. (ChrisChrisW via Getty Images)
The average human gut contains roughly 100 trillion microbes, many of which are constantly competing for limited resources. “It’s such a harsh environment,” says César de la Fuente, Presidential Assistant Professor in Bioengineering and in Chemical and Biomolecular Engineering within the School of Engineering and Applied Science, in Psychiatry and Microbiology within the Perelman School of Medicine, and in Chemistry within the School of Arts & Sciences. “You have all these bacteria coexisting, but also fighting each other. Such an environment may foster innovation.”
In that conflict, de la Fuente’s lab sees potential for new antibiotics, which may one day contribute to humanity’s own defensive stockpile against drug-resistant bacteria. After all, if the bacteria in the human gut have to develop new tools in the fight against one another to survive, why not use their own weapons against them?
In a new paper in Cell, the labs of de la Fuente and Ami S. Bhatt, Professor in Medicine (Hematology) and Genetics at Stanford, surveyed the gut microbiomes of nearly 2,000 people, discovering dozens of potential new antibiotics. “We think of biology as an information source,” says de la Fuente. “Everything is just code. And if we can come up with algorithms that can sort through that code, we can dramatically accelerate antibiotic discovery.”
BE’s award-winning team, Epilog, at the 2024 Senior Design Awards.
How do you make robotics kits affordable for children in low-income countries? Speed up the manufacturing of organs-on-a-chip? Lower the environmental impact of condiments in restaurants?
If you’re a senior at Penn Engineering, the answer is to team up with your peers in the Senior Design Project Competition, which every year draws interdisciplinary groups from across the School’s six majors to solve real-world problems. Championed by the late Walter Korn (EE’57, GEE’68), a past president of the Engineering Alumni Society (EAS), Senior Design also invites alumni back to campus to evaluate the seniors’ year-long capstone projects.
Since the program started nearly two decades ago, hundreds of alumni have shared centuries’ worth of their collective experience with soon-to-be-minted graduates in the form of constructive feedback. “Senior Design is really one of the best days at Penn Engineering,” says Bradley Richards (C’92, LPS’17), Director of Alumni Relations, who manages the program. “Faculty advisors work with students all year long to bring out the best in each group’s efforts, and the results speak for themselves.”
This year, three student teams from each of Penn Engineering’s six departments — Bioengineering (BE), Chemical and Biomolecular Engineering (CBE), Computer and Information Science (CIS), Electrical and Systems Engineering (ESE), Materials Science and Engineering (MSE), and Mechanical Engineering and Applied Mechanics (MEAM) — presented their work to more than 60 alumni in person and online.
Judges’ Choice Award
The Judges’ Choice Award, which recognizes overall excellence, went to ESE’s VivoDisk, which developed a novel machine to manufacture organs-on-a-chip for Vivodyne, a startup launched by Dan Huh, Associate Professor in BE.
As one of the team members, Akash Chauhan (ENG’24), learned while interning for Vivodyne, assembling the stacks of organs-on-a-chip, which are collections of plastic plates containing cells that simulate organs for preclinical drug testing, is extremely finicky and time consuming.
By developing a machine that could automatically align the plates with high precision using computer vision and AI, the team reduced the disks’ manufacturing time and expense, leading Vivodyne to adopt the device for commercial use, accelerating the process of drug discovery. VivoDisk’s team members included Chauhan; Angela Rodriguez (ENG’24), Aliris Tang (ENG’24, W’24), Dagny Lott (ENG’24), Simone Kwee (ENG’24) and Vraj Satashia (ENG’24, GEN’25) and was advised by Sid Deliwala, Alfred Moore Senior Fellow and Director of Lab Programs in ESE, and Jan Van der Spiegel, Professor in ESE.
Technology and Innovation Award
One of the greatest challenges for children with epilepsy is status epilepticus, an abnormal type of long-lasting seizure that is hard to distinguish from typical seizures and that has a mortality rate of 30%. There is currently no way to perform a test for status epilepticus at home, meaning that children suspected of having the condition must be rushed to the hospital for an electroencephalogram.
Epilog, a team from BE, developed a novel, wearable headset that analyzes brainwaves to accurately determine whether or not a child suffering a seizure is actually suffering from status epilepticus. The team, composed of Rohan Chhaya (ENG’24, GEN’24), Carly Flynn (ENG’24), Elena Grajales (ENG’24), Priya Shah (ENG’24, GEN’25) and Doris Xu (ENG’24) and advised by Erin Berlew, Research Scientist in the Department of Orthopaedic Surgery and Lecturer in BE, carefully validated the device’s accuracy.
The judges recognized Epilog’s technological expertise, which ran the gamut from software to hardware, including a custom app to work with the device and carefully considered features like electrodes whose position can be adjusted to accommodate a child’s growth over time.
Team Current Care (Andrew Lee, Antranig Baghdassarian, Johnson Liu, Leah Lackey, Brianna Leung, and Justin Liu), took home the $3,000 Grand Prize in the Cornell Hackathon.
Brianna Leung, a rising senior majoring in Bioengineering and minoring in Neuroscience and Healthcare Management at the University of Pennsylvania, led a diverse team of student scientists and engineers to resounding success at the 2024 Cornell Health Tech Hackathon, where the team won the $3,000 Grand Prize.
Held in March 2024 on Cornell’s campus in New York City, the event brought together students from 29 different universities for a weekend of finding “hacks” to patient wellness and healthcare issues inspired by the theme of “patient safety.”
ADAPT members enjoy a pancake-making marathon in preparation for their pancake sale.
Leung serves as President of Penn Assistive Devices and Prosthetic Technologies (ADAPT), a medical-device project club whose members pursue personal projects, community partnerships and national design competitions. Penn ADAPT’s activities range from designing, building and improving assistive medical devices for conditions such as cerebral palsy and limb loss, to community engagement activities like their semesterly 3D-printed pancake sale.
In her role, Leung has increased the program’s hackathon participation to give club members greater exposure to fast-paced, competition-based design. She also leads the HMS School project, which develops and manufactures switch interfaces for children with cerebral palsy, enabling these students to interact with computers.
Leung’s passion for medical devices extends to her academic research. As a member of the robotics lab of Cynthia Sung, Gabel Family Term Assistant Professor in Mechanical Engineering and Applied Mechanics, Computer and Information Science, and Electrical and Systems Engineering, Leung characterizes origami patterns for energy-saving applications in the heart and in facial reconstruction. Leung has also served as Vice President External for the Penn Lions and Vice President of Member Engagement for the Wharton Undergraduate Healthcare Club, and belongs to the Phi Gamma Nu professional business fraternity.
ADAPT members working on medical devices.
For the Cornell Hackathon, Leung’s team developed a prototype for Current Care, a closed-loop device to prevent pressure ulcers through electrical muscle stimulation. Pressure ulcers, often called bed sores, result from prolonged pressure, which often occurs during extended hospitalization or in patients who are bedridden. This condition is exacerbated by understaffing and strained resources, and can create an extra burden on hospitals, patients and healthcare workers. The U.S. Department of Health and Human Services estimates that pressure ulcers cost the U.S. healthcare system approximately $9.1 billion to $11.6 billion per year.
Current Care is designed to deliver electrical stimulation, which increases blood flow to affected body parts. Conceptualizing and designing complex devices on short notice is the nature of a hackathon, so the team focused their efforts on creating proof-of-concept prototypes for all the different sensors required for the device, as well as providing the judges with on-screen read-outs to demonstrate the logic and hypothetical inputs for the device.
For their design, the team was awarded the $3,000 Grand Prize in the Cornell Hackathon. In addition to Leung, the team consisted of Johnson Liu (Cornell ECE & MSE’26); Antranig Baghdassarian (Cornell BME’27); Andrew Lee (Weill Cornell M.D.’25); Leah Lackey (Cornell ECE Ph.D.’28); and Justin Liu (Northeastern CS’27).
In choosing a project, Leung was inspired by her late grandmother’s experiences. “My role on the team largely consisted of coordinating and leading aspects of its development as needed. I also ultimately presented our idea to the judges,” she says. “This was actually all of my teammates’ first hackathon, so it was really exciting to serve a new role (considering it was actually only my second hackathon!). I had a lot of fun working with them, and we have actually been meeting regularly since the event to continue to work on the project. We had a range of expertise and experience on our team, and I deeply appreciate their hard work and enthusiasm for a project that means so much to me.”
Having found success at the Cornell hackathon, the team is discussing next steps for Current Care. “Our team is still very motivated to continue working on the project, and we’ve been speaking with professors across all of our schools to discuss feasibility and design plans moving forward,” says Leung.
Several other projects developed by Penn ADAPT members were recognized in the Cornell Hackathon:
ADAPT members and Hackathon participants, left to right: Brianna Leung, Rebecca Wang, Claire Zhang, Amy Luo, Mariam Rizvi, Natey Kim, Joe Kojima. Also in attendance but not pictured: Suhani Patel, Harita Trivedi, Dwight Koyner.
Claire Zhang, a sophomore studying Bioengineering and Biology in the VIPER program, was a member and presenter for team CEDAR (winner of Most Innovative/2nd Place), a portable ultrasound imaging device used to monitor carotid artery stenosis development in rural areas.
Natey Kim, a sophomore in Bioengineering, was a member and presenter for team HMSS (finalist), a low-cost digital solution for forecasting infections in hospitals.
Rebecca Wang, a sophomore in Bioengineering and Social Chair of Penn ADAPT, was a member of Team Femnostics (winner of Most Market Ready/4th Place) which developed QuickSense, an all-in-one diagnostic tool that streamlines testing for a handful of the most common vaginal disease infections simultaneously.
Mariam Rizvi, a sophomore in Computational Biology, was a member of team IPVision (winner of Most Potential Impact/5th Place), an application programming interface (or API) that integrates into electronic health records such as Epic, leveraging AI to detect intimate partner violence cases and provide personalized treatment in acute-care settings.
Suhani Patel and Dwight Koyner worked with team RealAIs, which developed a full-stack multi-platform application using React Native and Vertex AI on the Google Cloud Platform (GCP). Patel, a sophomore double majoring in Bioengineering and Computer and Information Science in Penn Engineering, serves as ADAPT’s treasurer, while Koyner is a first-year M&T student studying Business and Systems Engineering in Penn Engineering and Wharton.
Team Femnostics from left to right: Antonia Li, Bhavishya Agarwal, Urmila Sehrawat, Rebecca Wang, Justin Xiang, and Edward Kim.Team IPVision from left to right: Elizabeth Madamidola, Keshika Gopinathan, Emily L. Leventhal, Mariam Rizvi, Raquel Castromonte, and Lina ChihoubTeam Cedar from left to right: Claire Zhang, Ethan Tse, Danny Nguyen, Allen Dinh, and Reem UllayTeam RealAIs from left to right: Rishi Shah, Suhani Patel, Saanvi Mehra, Dwight Koyner, Chimdi Ejiogu, and Garrett Breslin
Learn more about Penn ADAPT here and follow their Instagram.
Read more about the 2024 Cornell Tech Hackathon in the Cornell Chronicle.
Cesar de la Fuente (left), Fangping Wan (center), and Marcelo der Torossian Torres (right). Fangping holds a 3D model of a unique ATP synthase fragment, identified by their lab’s deep learning model, APEX, as having potent antibiotic properties.
“Make sure you finish your antibiotics course, even if you start feeling better’ is a medical mantra many hear but ignore,” says Cesar de la Fuente of the University of Pennsylvania.
He explains that this phrase is, however, crucial as noncompliance could hamper the efficacy of a key 20th century discovery, antibiotics. “And in recent decades, this has led to the rise of drug-resistant bacteria, a growing global health crisis causing approximately 4.95 million deaths per year and threatens to make even common infections deadly,” he says.
De la Fuente, a Presidential Assistant Professor, and a team of interdisciplinary researchers have been working on biomedical innovations tackling this looming threat. In a new study, published in Nature Biomedical Engineering, they developed an artificial intelligence tool to mine the vast and largely unexplored biological data—more than 10 million molecules of both modern and extinct organisms— to discover new candidates for antibiotics.
“With traditional methods, it takes around six years to develop new preclinical drug candidates to treat infections and the process is incredibly painstaking and expensive,” de la Fuente says. “Our deep learning approach can dramatically reduce that time, driving down costs as we identified thousands of candidates in just a few hours, and many of them have preclinical potential, as tested in our animal models, signaling a new era in antibiotic discovery.” César de la Fuente holds a 3D model of a unique ATP synthase fragment, identified by his lab’s deep learning model, APEX, as having potent antibiotic properties. This molecular structure, resurrected from ancient genetic data, represents a promising lead in the fight against antibiotic-resistant bacteria.
These latest findings build on methods de la Fuente has been working on since his arrival at Penn in 2019. The team asked a fundamental question: Can machines be used to accelerate antibiotic discovery by mining the world’s biological information? He explains that this idea is based on the notion that biology, at its most basic level, is an information source, which could theoretically be explored with AI to find new useful molecules.
Almost a century ago, the discovery of antibiotics like penicillin revolutionized medicine by harnessing the natural bacteria-killing abilities of microbes. Today, a new study co-led by researchers at the Perelman School of Medicine at the University of Pennsylvania suggests that natural-product antibiotic discovery is about to accelerate into a new era, powered by artificial intelligence (AI).
The study, published in Cell, the researchers used a form of AI called machine learning to search for antibiotics in a vast dataset containing the recorded genomes of tens of thousands of bacteria and other primitive organisms. This unprecedented effort yielded nearly one million potential antibiotic compounds, with dozens showing promising activity in initial tests against disease-causing bacteria.
“AI in antibiotic discovery is now a reality and has significantly accelerated our ability to discover new candidate drugs. What once took years can now be achieved in hours using computers” said study co-senior author César de la Fuente, PhD, a Presidential Assistant Professor in Psychiatry, Microbiology, Chemistry, Chemical and Biomolecular Engineering, and Bioengineering.
Nature has always been a good place to look for new medicines, especially antibiotics. Bacteria, ubiquitous on our planet, have evolved numerous antibacterial defenses, often in the form of short proteins (“peptides”) that can disrupt bacterial cell membranes and other critical structures. While the discovery of penicillin and other natural-product-derived antibiotics revolutionized medicine, the growing threat of antibiotic resistance has underscored the urgent need for new antimicrobial compounds.
In recent years, de la Fuente and colleagues have pioneered AI-powered searches for antimicrobials. They have identified preclinical candidates in the genomes of contemporary humans, extinct Neanderthals and Denisovans, woolly mammoths, and hundreds of other organisms. One of the lab’s primary goals is to mine the world’s biological information for useful molecules, including antibiotics.
The growing threat of antimicrobial resistance demands innovative solutions in drug discovery. Scientists are turning to artificial intelligence (AI) and machine learning (ML) to accelerate the discovery and development of antimicrobial peptides (AMPs). These short strings of amino acids are promising for combating bacterial infections, yet transitioning them into clinical use has been challenging. Leveraging novel AI-driven models, researchers aim to overcome these obstacles, heralding a new era in antimicrobial therapy.
A new article in Nature Reviews Bioengineering illuminates the promises and challenges of using AI for antibiotic discovery. Cesar de la Fuente, Presidential Assistant Professor in Microbiology and Psychiatry in the Perelman School of Medicine, in Bioengineering and Chemical and Biomolecular Engineering in the School of Engineering and Applied Science, and Adjunct Assistant Professor in Chemistry in the School of Arts and Sciences, collaborated with James J. Collins, Termeer Professor of Medical Engineering and Science at MIT, to provide an introduction to this emerging field, outlining both its current limitations and its massive potential.
In the past five years, groundbreaking work in the de la Fuente Lab has dramatically accelerated the discovery of new antibiotics, reducing the timeline from years to mere hours. AI-driven approaches employed in his laboratory have already yielded numerous preclinical candidates, showcasing the transformative potential of AI in antimicrobial research and offering new potential solutions against currently untreatable infections.
Recent advancements in AI and ML are revolutionizing drug discovery by enabling the precise prediction of biomolecular properties and structures. By training ML models on high-quality datasets, researchers can accurately forecast the efficacy, toxicity and other crucial attributes of novel peptides. This predictive power expedites the screening process, identifying promising candidates for further evaluation in a fraction of the time required by conventional methods.
Traditional approaches to AMP development have encountered hurdles such as toxicity and poor stability. AI models help overcome these challenges by designing peptides with enhanced properties, improving stability, efficacy and safety profiles, and fast-tracking the peptides’ clinical application.
While AI-driven drug discovery has made significant strides, challenges remain. The availability of high-quality data is a critical bottleneck, necessitating collaborative efforts to curate comprehensive datasets to train ML models. Furthermore, ensuring the interpretability and transparency of AI-generated results is essential for fostering trust and wider adoption in clinical settings. However, the future is promising, with AI set to revolutionize antimicrobial therapy development and address drug resistance.
Integrating AI and ML into antimicrobial peptide development marks a paradigm shift in drug discovery. By harnessing these cutting-edge technologies, researchers can address longstanding challenges and accelerate the discovery of novel antimicrobial therapies. Continuous innovation in AI-driven approaches is likely to spearhead a new era of precision medicine, augmenting our arsenal against infectious diseases.
The de la Fuente Lab uses use the power of machines to accelerate discoveries in biology and medicine. The lab’s current projects include using AI for antibiotic discovery, molecular de-extinction, reprogramming venom-derived peptides to discover new antibiotics, and developing low-cost diagnostics for bacterial and viral infections. Read more posts featuring de la Fuente’s work in the BE Blog.
Susan Davidson, Cesar de la Fuente, Surbhi Goel and Chris Callison-Burch speak on AI in Engineering in episode 4 of the Innovation & Impact podcast.
With AI technologies finding their way into every industry, important questions must be considered by the research community: How can deep learning help identify new drugs? How can large language models disseminate information? Where and how are researchers using AI in their own work? And, how are humans anticipating and defending against potential harmful consequences of this powerful technology?
In this episode of Innovation & Impact, host Susan Davidson, Weiss Professor in Computer and Information Science (CIS), speaks with three Penn Engineering experts about leveraging AI to advance scientific discovery and methods to protect its users. Panelists include:
Chris Callison-Burch, Associate Professor in CIS, who researches the applications of large language models and AI tools in current and future real-world problems with a keen eye towards safety and ethical use of AI;
Surbhi Goel, Magerman Term Assistant Professor in CIS, who works at the intersection of theoretical computer science and machine learning. Her focus on developing theoretical foundations for modern machine learning paradigms expands the possibilities of deep learning; and
Cesar de la Fuente, Presidential Assistant Professor in Bioengineering, Psychiatry and Microbiology with a secondary appointment in Chemical and Biomolecular Engineering, who leads research on technology in the medical field, using computers to find antibiotics in extinct organisms and identify pre-clinical candidates to advance drug discovery.
Each episode of Penn Engineering’s Innovation & Impact podcast shares insight from leading experts at Penn and Penn Engineering on science, technology and medicine.
Computing at the speed of light may reduce the energy cost of training AI. (Narongrit Doungmanee via Getty Images)
Penn Engineers have developed a new chip that uses light waves, rather than electricity, to perform the complex math essential to training AI. The chip has the potential to radically accelerate the processing speed of computers while also reducing their energy consumption.
The silicon-photonic (SiPh) chip’s design is the first to bring together Benjamin Franklin Medal Laureate and H. Nedwill Ramsey Professor Nader Engheta’s pioneering research in manipulating materials at the nanoscale to perform mathematical computations using light — the fastest possible means of communication — with the SiPh platform, which uses silicon, the cheap, abundant element used to mass-produce computer chips.
The interaction of light waves with matter represents one possible avenue for developing computers that supersede the limitations of today’s chips, which are essentially based on the same principles as chips from the earliest days of the computing revolution in the 1960s.
In a paper in Nature Photonics, Engheta’s group, together with that of Firooz Aflatouni, Associate Professor in Electrical and Systems Engineering, describes the development of the new chip. “We decided to join forces,” says Engheta, leveraging the fact that Aflatouni’s research group has pioneered nanoscale silicon devices.
Their goal was to develop a platform for performing what is known as vector-matrix multiplication, a core mathematical operation in the development and function of neural networks, the computer architecture that powers today’s AI tools.
Nader Engheta is the H. Nedwill Ramsey Professor in Electrical and Systems Engineering, Bioengineering, Materials Science and Engineering, and in Physics and Astronomy.
