BAGEL: Protein engineering via exploration of an energy landscape

Despite recent breakthroughs in deep learning methods for protein design, existing computational pipelines remain rigid, highly specific, and ill-suited for tasks requiring non-differentiable or multi-objective design goals. In this report, we introduce BAGEL, a modular, open-source framework for programmable protein engineering, enabling flexible exploration of sequence space through model-agnostic and gradient-free exploration of an energy landscape. BAGEL formalizes protein design as the sampling of an energy function, either to optimize (find a global optimum) or to explore a basin of interest (generate diverse candidates). This energy function is composed of user-defined terms capturing geometric constraints, sequence embedding similarities, or structural confidence metrics. BAGEL also natively supports multi-state optimization and advanced Monte Carlo techniques, providing researchers with a flexible alternative to fixed-backbone and inverse-folding paradigms common in current design workflows. Moreover, the package seamlessly integrates a wide range of publicly available deep learning protein models, allowing users to rapidly take full advantage of any future improvements in model accuracy and speed. We illustrate the versatility of BAGEL on four archetypal applications: designing de novo peptide binders, targeting intrinsically disordered epitopes, selectively binding to species-specific variants, and generating enzyme variants with conserved catalytic sites. By offering a modular, easy-to-use platform to define custom protein design objectives and optimization strategies, BAGEL aims to speed up the design of new proteins. Our goal with its release is to democratize protein design, abstracting the process as much as possible from technical implementation details and thereby making it more accessible to the broader scientific community, unlocking untapped potential for innovation in biotechnology and therapeutics.Author summary: Proteins underpin much of modern biotechnology. To harness them, we need practical ways to computationally design sequences that meet clear goals while remaining stable and functional. Recent deep learning methods have boosted success rates, yet most design pipelines still follow rigid workflows, making it difficult to specify non-differentiable goals, or constraints spanning multiple functional contexts. Here, we introduce BAGEL, a Python package that formalizes protein design as exploration of an energy landscape built from simple, user-defined terms. In practice, this lets a researcher specify straightforward constraints – keep a region confident, avoid sticky surface patches, bring two parts into contact, maintain a catalytic motif – and combine them in one place. A stochastic search then proposes beneficial sequence changes, testing whether the design is evolving in the right direction. We demonstrate this on four use cases: de novo peptide binders, targeting intrinsically disordered epitopes, selective binding across species variants, and enzyme variants that preserve an active site. The ability to compose arbitrary goals, including the use of the ever-expanding suite of protein deep learning models makes BAGEL a tool making programmable protein engineering more accessible, accelerating practical applications in biotechnology and therapeutics.