Penn Engineers have developed PeptiVerse, an AI-powered platform that predicts key chemical and biological properties of peptides. Trained on diverse data sets, the open-source tool can assess solubility, cell entry, toxicity, and stability. Researchers can use its web interface to evaluate…
Penn Engineers from the Chatterjee Lab have created PeptiVerse, an artificial intelligence platform designed to predict essential chemical and biological characteristics of peptides. Peptides are short strings of amino acids, and their medical potential has been highlighted by the success of GLP-1 drugs, which are widely used for weight loss treatment. The research was published in Nature Communications on July 21, 2026, in an article authored by Ian Scheffler.
To build PeptiVerse, the research team gathered data from many separate studies. Some data sets described whether peptides dissolve easily. Others measured whether peptides enter cells, avoid damaging red blood cells, resist unwanted protein buildup, or remain active over time. Sophia Vincoff, a doctoral student in Bioengineering and co-author of the study, explained that each data set came from a different type of experiment. The researchers had to understand what each experiment was measuring, standardize the data for each property, and organize it so that machine-learning models could learn from it and be tested fairly. They then compared many model architectures to find the best approach for each prediction task.
Rather than assuming that one model works best for every task, PeptiVerse uses the strongest-performing model for each property. In some cases, simpler models performed as well as or better than more sophisticated approaches. In other cases, the opposite was true. Yinuo Zhang, a doctoral student in Bioengineering and the paper’s first author, said the team wanted PeptiVerse to function like a toolkit. Instead of having each predictor live separately, PeptiVerse brings them together in a platform that can grow as new data and models become available. Pranam Chatterjee, Africk-Lesley Distinguished Scholar of Innovation in Engineering, Assistant Professor in Bioengineering and in Computer and Information Science, and senior author of the study, said that peptide drugs have enormous potential, but binding to the right target is only one part of what makes a molecule useful. He added that in drug discovery, one of the worst outcomes is finding out too late that a promising molecule cannot actually become a medicine. PeptiVerse gives researchers a way to check many of those make-or-break properties earlier, before they invest the time and resources required to synthesize and test candidate drugs.
Most new computational tools come in the form of libraries or packages, bundles of code that researchers can download and run on their own computers but that typically require some level of programming skill to operate. PeptiVerse, by contrast, includes a web interface that allows users to simply type in a peptide sequence, select properties, and receive predictions through a visual dashboard. That design makes the platform especially useful for experimental researchers, like biologists, who may have peptide candidates they are already studying and want a fast way to assess whether those molecules are likely to have the properties needed for further testing.
Yinuo Zhang noted that she comes from a biology perspective and is a very visual person. The team wanted researchers to be able to see what was going on, not just download a Python package. The interface makes PeptiVerse something people can interact with directly. The platform also lets users view the data used to train the models, helping them understand how their own peptide candidates compare with molecules that have already been experimentally characterized. Sophia Vincoff emphasized that for experimentalists, it matters where the data came from. PeptiVerse makes it easier to look at the data behind the predictions, which helps users interpret what the models are telling them.
Members of the Chatterjee Lab have demonstrated the platform. Elizabeth Mahood and Yesol Kim were pictured showing how PeptiVerse, whose web client is open on a laptop, can be used by experimentalists to make predictions about peptides. Those predictions can then be used to guide the synthesis of peptides using a machine like the one shown in the photographs. The photographs were credited to Sylvia Zhang.
One immediate use of PeptiVerse is as a screening tool. Instead of synthesizing and testing peptide candidates one by one, researchers in both academia and industry can use the platform to quickly assess which molecules appear most promising before moving into the lab. The platform could also play a more ambitious role in AI-driven drug discovery. In addition to evaluating existing candidates, PeptiVerse can be paired with generative AI tools that propose entirely new peptides. That approach has already helped the Chatterjee Lab develop new peptide-design innovations, including PepTune, TR2-D2, MOG-DFM, and moPPIt. These systems use property predictions from PeptiVerse to guide the design of peptides with desired therapeutic features.
In this framework, rather than serving only as a filter to screen existing peptides, PeptiVerse can shape the search for new drug candidates. The system’s powerful predictions allow generative AI models to prioritize candidates with desirable characteristics such as stronger binding, reduced nonspecific interactions with other proteins, better solubility, greater permeability, and lower toxicity. This happens before selecting particular molecules for synthesis and real-world testing. Pranam Chatterjee said that the property predictions become part of the search itself. Instead of evaluating peptides only after they are generated, researchers can use those predictions to guide generative AI models toward molecules with the characteristics they want from the very beginning.
The PeptiVerse platform, symbolized by its rocket-shaped mascot in some images, can predict the properties of peptides that can then be synthesized by a machine. The researchers also described how the platform can be used by experimentalists before incurring the time and expense to synthesize peptides using such a machine.
The researchers designed PeptiVerse to keep growing. As more peptide data becomes available, the platform can be updated with new data sets, improved models, and additional properties. That matters because some peptide properties are still harder to predict than others, largely because there is less experimental data available to train models about them. More measurements could help PeptiVerse improve existing predictions and add new ones, such as whether a peptide is likely to activate or block a receptor, thereby activating or shutting down a particular biochemical pathway. Pranam Chatterjee said that PeptiVerse is not meant to be finished. The more data the community contributes, the better these models can become.
Since PeptiVerse is open source, researchers can adapt it for their own purposes. Academic labs can use the existing platform, contribute data, or build new predictors. Companies developing peptide therapeutics could also use the framework with their own internal data sets, creating versions of PeptiVerse tailored to the kinds of molecules they are trying to develop. Chatterjee emphasized that the universe of possible peptides is too large for any one lab to map on its own. PeptiVerse was built so that other researchers can help expand the map, adding new data and models that accelerate the search for new and better peptide drugs.
Peptides referenced: GLP-1.
Related reading: University of Mississippi Investigates Obstacles in GLP-1 Insurance Coverage, AI-Powered PeptiVerse Could Accelerate Peptide Drug Discovery, Ole Miss Researchers Examine Insurance Barriers for GLP-1 Coverage, Ascletis to Present Superior Weight Loss Data for ASC36_35 FDC at EASD.