RaMP: Post-Baccalaureate Training Program in Biomolecular Structure Prediction and Design
The Rosetta Commons Research and Mentoring Program (RaMP) is a one-year fellowship program intended for students from groups underrepresented in STEM, first generation college students, and students at under-resourced institutions to gain research experience to succeed in PhD programs.
Trainees in this geographically distributed RaMP program participate in research using the Rosetta Commons software. The Rosetta Commons software library includes physics-based and deep learning algorithms for biomolecular modeling and design. It has enabled notable scientific advances in computational biology, including de novo protein design, enzyme design, ligand docking, and structure prediction of biological macromolecules and macromolecular complexes.
The RaMP Provides:
- Rosetta Code School: where trainees will learn the inner details of the Rosetta Python code and community coding environment, so you are fully prepared to research using the software.
- Research experience: Trainees conduct hypothesis-driven research in their Mentor’s lab, with day-to-day guidance by an experienced PhD student or postdoc. Scholars participate fully in weekly lab meetings, attend weekly research seminars in their department, attend a vibrant PhD program retreat and a national conference of their choice.
- Participation: in the Winter Rosetta Conference, where you will connect with Rosetta developers from around the world.
- Compensation: Salary, health benefits, and funding for conference travel are included.
- Preparation: for graduate school applications and interviews.
- Community: Trainees come together each month for ‘Journal Club’ events to present and discuss their research with peers and faculty mentors. These meetings include professional development mini-lessons on topics like the NSF-GRFP, graduate school applications, research posters, and more.
- Project meetings: Trainees gain confidence by organizing, preparing for, and convening monthly project meetings with the program's PI, Dr. Jeff Gray. Scholars benefit both scientifically and professionally by building strong working relationships with multiple faculty members who are experts in their field of interest.
- Specialized mentoring: Mentors will participate in a four-part Culturally Responsive Mentoring Workshop series will guide them in increasing their capacity for and self-awareness of culturally responsive mentoring best practices. This series will be facilitated by Steven Thomas. The mentor, co-mentor, and participant will form a “mentorship triad,” a tight interpersonal structure functioning to enhance a student’s potential
- Individuals from groups underrepresented in STEM, first generation college students, and students at under-resourced institutions.
- U.S. citizens, U.S. nationals, or permanent residents of the United States are eligible.
- Participants must have a baccalaureate college degree before participating in the program (applicants must apply to the program before or within four years of graduation, with extensions allowed for family, medical leave, or military service). Individuals currently enrolled or accepted into a graduate program are not eligible.
- Undergraduate major in computer science, engineering, mathematics, chemistry, biology, and/or biophysics.
- While not required, we seek candidates with some combination of experiences in scientific or academic research, C++/Python/*nix/databases, software engineering, object-oriented programming, and/or collaborative development.
- Unofficial transcript
Personal statement that summarizes why you are an appropriate candidate (up to 5000 characters) including:
- Why this program interests you
- Brief summary of research and computing experience
- Research career goals
- Two recommendation letters, completed recommendations can be sent to firstname.lastname@example.org
- Select top three labs and projects of interest from the list below.
- Deadline for receipt of applications is February 20, 2023.
- Deadline for receipt of recommendation letters is February 22, 2023.
- Program contact: Camille Mathis, email@example.com.
Gray Lab @ Johns Hopkins University in Baltimore, MD
“Antibody engineering by deep learning"
Antibodies are an excellent model system for loop structure prediction and design, a difficult problem in the field. Highresolution models of the loop structure are necessary for successful docking to antigens or for design for improved affinities, yet traditional loop prediction methods have been frustrated on antibody loops because of their extreme variability. In this project, the participant will apply deep learning methods, including transfer learning and attention gating, to leverage data from a large set of protein structures and focus predictions on the key loop. The participant will learn antibody engineering, homology modeling and docking, and machine learning.
Hosseinzadeh Lab @ University of Oregon in Eugene Oregon
" Design of protein binders for detection of post-translational modifications"
A big portion of the human proteome is post-translationally modified (PTM). The highly dynamic interplay between these modified proteins has an essential role in determining cell fate and relaying signals across the cell. Despite the importance of PTMs, identifying the sites of modification in the entire proteome is currently a challenging task. Since many of these modifications happen in small quantities, enrichment is required. For many PTMs, we do not have access to selective binders to enrich them from the proteome. Even for those where there are antibodies available, there are challenges regarding reproducibility, affinity, and selectivity. To overcome these limitations and shed light on this dark space of proteome, we will be using computational protein design combined with high throughput screening to designing selective PTM binders. These binders will then be used to identify the location of PTMs on the entire proteome across healthy cells and diseased cells. We will also use this knowledge in knockout cells to identify enzymes responsible for these modifications.
Huang Lab @ Stanford University in Stanford, CA
" Protein design for immunological intervention"
The Huang lab develops ML based protein design tools and wet lab driven molecular platforms for intervention with the immune system. We recently developed a new monobody engineering software pipeline and a molecular platform that can specifically target MHC antigens. The participant will combine these areas and learn Rosetta, neural networks and yeast display.
Kortemme Lab @ University of California, San Francisco in San Francisco, CA
" Computational design of de novo proteins to control biological signaling"
We are working towards engineering synthetic signaling systems built from de novo designed protein components that can recognize inputs, transduce signals, and control programmable outputs. We have a range of projects to create proteins with custom-designed shapes to recognize specific signals, and to engineer switchable protein structures. The participant will integrate computational design and experimental characterization in vitro and in cellular systems, and will explore new opportunities through advances in deep learning.
Kuhlman Lab @ University of North Carolina, Chapel Hill in Chapel Hill, NC
"Applying machine learning to protein design"
Advances in machine learning are revolutionizing the fields of protein structure prediction and design. The participant will help create and test protocols that make use of Rosetta in combination with machine learning to design new protein structures and complexes.
O'Meara Lab @ University of Michigan, Ann Arbor in Ann Arbor, MI
“Bayesian methods for modeling function in structure to function studies”
The O’Meara Lab develops methods for simulation-based inference. The aim of this project is to develop Bayesian statistical methods to better capture complex experimental designs typical in biochemistry and biophysics. The participant will develop Bayesian workflows in R and Stan for foundational pharmacology models including Hill-equation dose-response, enzyme kinetic models, etc., and apply them to benchmark Rosetta simulations and computational biophysics modeling more broadly.
Rocklin Lab @ Northwestern University in Chicago, IL
"Applying high-throughput experimental data to guide computational protein design"
Today, most computational protein design tools like Rosetta use the features of natural protein structures (which amino acids like to be near each other, what types of structures are very common, etc) to guide the design of new proteins. However, for many applications, we want to design proteins with properties far beyond what already exists in nature. To achieve this, we need new sources of data - not just natural protein structures - that can guide design into new territory. Our lab develops new experimental methods to measure properties like folding stability, binding affinity, and dynamics for tens to hundreds of thousands of designed or natural proteins at the same time. We then use these new large datasets to guide protein design proteins. We have a range of different projects focused on basic science, therapeutic development, and tools for synthetic biology.
Siegel Lab @ University of California, Davis in Davis, CA
"Computational enzyme design and modeling"
The Siegel Lab engineers enzymes to address human-centered challenges in health, food, and environmental systems; the group is primarily focused on work with direct applications in these spaces. The postbac will use Rosetta to model and design enzymes that catalyze novel biochemical reactions in projects that align with the mission of the lab. Using insights from in-silico experiments, he/she will characterize and evaluate their designs in the wet-lab, learning both computational and benchwork skills.
Whitehead Lab @ University of Colorado, Boulder in Boulder, CO
" Seeing the Unseen: High-Throughput Prospective Profiling of viral sequence variants"
The ongoing rapid and widespread transmission of SARS-CoV-2 across the world has resulted in myriad viral strains, but immunity in most humans has been acquired from vaccination against a single (Wuhan-Hu-1) strain and/or previous infection with a handful of strains. However, the scientific community currently lacks the tools to prospectively identify novel highly-substituted viral strains capable of immune evasion. Our proposal is enabled by results from the our laboratory and collaborator Prof. Sagar Khare at Rutgers, in which we developed high-throughput structure-based computational and experimental approaches for predicting and characterizing the binding of diverse SARS-CoV-2 RBD variants with the ACE2 and a set of neutralizing antibodies (nAbs) to effectively recapitulate variant S function and immune evasion properties. We will apply our technologies to broadly sample heavily substituted (10-20 substitutions) but functional RBD variants and identify those that are predicted to abrogate binding to a representative set of nAb raised against two key (Class 1 and Class 2) epitope regions of the RBD. This project will involve both experimental and computational components; a broad platform will be constructed as well for other viruses of significant global concern (HIV, influenza).
Award Number: 2216011