RSRebeca T. Stiepel

Rebeca T. Stiepel

*This is an algorithmically generated author record based on publicly available information.

Rebeca T. Stiepel has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Data-efficient molecular and nanoparticle design via fine-tuned large language models

    by Yan Xiang, Zilu Zhang, Rebeca T. Stiepel, Lauren A. Onweller, Zachary Fralish, Daniel Reker

    Designing molecules with prescribed properties is central to pharmaceutical and materials innovation, but vast chemical design spaces make development lengthy and costly. Generative artificial intelligence can accelerate molecular discovery, but its deployment in many real-world domains remains limited by the need for large task-specific training datasets. To enable generative design when property-labeled data are scarce, we present a data-efficient foundation-model adaptation strategy combining complementary positive and negative property prompts with parameter-efficient fine-tuning. Generated molecules are then ranked by molecular graph-kernel Gaussian process regression for structure-aware prioritization. In a controlled computational setting, the platform generated candidates with novel scaffolds satisfying multiple design objectives, including predicted target binding, synthesizability, and drug-likeness. Although only a few hundred training molecules per target met all three criteria, the model generated thousands of new molecules matching the desired profiles. For prospective validation, we applied the model to nanoparticle design, a domain of high clinical potential but limited excipient diversity. Fine-tuning on only 1,521 labeled drug-excipient pairs - including just 139 nanoparticle-forming examples identified new nanoparticle-forming excipients for the anticancer drug sorafenib. The model proposed lithocholic acid and the sorafenib metabolite M6, and experiments confirmed that both form stable sorafenib nanoparticles with high encapsulation efficiency and increased in vitro potency. These findings show that foundation-model fine-tuning with complementary prompts and graph-based prioritization enables data-efficient molecular design in low-data chemical domains.

  • Open Access

    Physics-informed design of drug-excipient nanoparticles via free energy calculation and yoked deep learning

    by Yan Xiang, Zilu Zhang, Rebeca T. Stiepel, Chinmay S. Potnis, Lauren A. Onweller, Joseph R. Laforet Jr., Hrshita Gowda, Daniel Reker

    The discovery of self-assembling molecular systems is often constrained by the high computational cost of physics-based simulations and the limited generalizability of data-driven models trained on experimental datasets. This limits our ability to efficiently navigate massive design spaces. Here, we introduce a physics-informed discovery framework that integrates free-energy calculations with sequential-pool active learning and adaptive yoked deep learning to effectively navigate vast chemical coassembly spaces. Using pairwise free energy as a physically grounded descriptor of co-assembly propensity and excipient net charge as a proxy for interfacial stabilization, our approach predicts nanoparticle-forming drug–excipient combinations without relying on experimental data for model training. Our sequential-pool yoked deep learning strategy utilizes adaptive machine learning to reduce the number of expensive simulations required while maintaining predictive accuracy, enabling screening of 18 million molecular pairs. Prospective validations identified 24 drug nanoparticles using eight previously unknown stabilizing molecules. The new nanoparticles exhibit ultra-high drug loading, effectively improve the aqueous solubility of drugs, and maintain in vitro drug efficacy. Together, this work establishes a generalizable framework coupling molecular simulations and yoked deep learning to accelerate discovery in self-assembling molecular systems.

  • Open Access

    Supervised machine learning for predicting drug release from acetalated dextran nanofibers

    by Ryan N. Woodring, Elizabeth G. Gurysh, Tanvi Pulipaka, Kevin E. Shilling, Rebeca T. Stiepel, Erik S. Pena, Eric M. Bachelder, Kristy M. Ainslie

    We present a novel machine learning workflow to assess in vitro drug release from electrospun Ace-DEX nanofibers. The model reliably predicts release across all scaffolds and demonstrates a drug-agnostic approach to cheracterize release rates.


  • Induction of Antigen-Specific Tolerance in a Multiple Sclerosis Model without Broad Immunosuppression

    by Rebeca T. Stiepel, Sean R. Simpson, Nicole Rose Lukesh, Denzel D. Middleton, Dylan A. Hendy, Luis Ontiveros-Padilla, Stephen A. Ehrenzeller, Jahirul Islam, Erik S. Pena, Michael A. Carlock, et al.

    Multiple sclerosis (MS) is a severe autoimmune disorder that wreaks havoc on the central nervous system, leading to a spectrum of motor and cognitive impairments. There is no cure, and current treatment strategies rely on broad immunosuppression, leaving patients vulnerable to infections. To address this problem, our approach aims to induce antigen-specific tolerance, a much-needed shift in MS therapy. We have engineered a tolerogenic therapy consisting of spray-dried particles made of a degradable biopolymer, acetalated dextran, and loaded with an antigenic peptide and tolerizing drug, rapamycin (Rapa). After initial characterization and optimization, particles were tested in a myelin oligodendrocyte glycoprotein (MOG)-induced experimental autoimmune encephalomyelitis model of MS. Representing the earliest possible time of diagnosis, mice were treated at symptom onset in an early therapeutic model, where particles containing MOG and particles containing Rapa+MOG evoked significant reductions in clinical score. Particles were then applied to a highly clinically relevant late therapeutic model during peak disease, where MOG particles and Rapa+MOG particles each elicited a dramatic therapeutic effect, reversing hind limb paralysis and restoring fully functional limbs. To confirm the antigen specificity of our therapy, we immunized mice against the influenza antigen hemagglutinin (HA) and treated them with MOG particles or Rapa+MOG particles. The particles did not suppress antibody responses against HA. Our findings underscore the potential of this particle-based therapy to reverse autoimmunity in disease-relevant models without compromising immune competence, setting it apart from existing treatments.


  • Comparative study of acetalated-dextran microparticle fabrication methods for a clinically translatable subunit-based influenza vaccine

    by Erik S. Pena, Cole J. Batty, Dylan A. Hendy, Shuangshuang Yang, Luis Ontiveros-Padilla, Rebeca T. Stiepel, Jenny P.-Y. Ting, Kristy M. Ainslie, Eric M. Bachelder


  • Open Access

    Micro and nanotechnologies: The little formulations that could

    by Rebeca T. Stiepel, Eliza Duggan, Cole J. Batty, Kristy M. Ainslie

    The first publication of micro‐ and nanotechnology in medicine was in 1798 with the use of the Cowpox virus by Edward Jenner as an attenuated vaccine against Smallpox. Since then, there has been an explosion of micro‐ and nanotechnologies for medical applications. The breadth of these micro‐ and nanotechnologies is discussed in this piece, presenting the date of their first report and their latest progression (e.g., clinical trials, FDA approval). This includes successes such as the recent severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) vaccines from Pfizer, Moderna, and Janssen (Johnson & Johnson) as well as the most popular nanoparticle therapy, liposomal Doxil. However, the enormity of the success of these platforms has not been without challenges. For example, we discuss why the production of Doxil was halted for several years, and the bankruptcy of BIND therapeutics, which relied on a nanoparticle drug carrier. Overall, the field of micro‐ and nanotechnology has advanced beyond these challenges and continues advancing new and novel platforms that have transformed therapies, vaccines, and imaging. In this review, a wide range of biomedical micro‐ and nanotechnology is discussed to serve as a primer to the field and provide an accessible summary of clinically relevant micro‐ and nanotechnology platforms.