About X-Tour
We are a computational biology company building AI tools and simulation pipelines for protein engineering. We work at the intersection of machine learning and molecular biophysics — where predictive models meet atomistic simulations.
Who We Are
Our work spans the full computational stack for protein science: from sequence-based ML classifiers that predict aggregation-prone regions and stability properties, to all-atom molecular dynamics simulations that reveal the conformational dynamics underlying those predictions.
We believe the most impactful tools in computational biology come from combining data-driven approaches with physics-based methods. Machine learning captures patterns in large datasets; molecular simulations provide the mechanistic insight to understand why those patterns exist. We build tools that bring both together.
The goal is straightforward: build computational tools that make real contributions to protein engineering and biotherapeutic development.
What We Believe
Models should know their limits
In protein science, a confident but wrong prediction can send research down the wrong path for months. We build uncertainty quantification into every model and are transparent about where our tools work well and where they don't.
Physics and data are complementary, not competing
Pure ML models can learn spurious correlations. Pure physics is computationally expensive. The best tools in computational biology use both — data-driven pattern recognition grounded in physical principles.
Built at the intersection of research and engineering
We combine academic rigor in biophysics and ML research with the pragmatism of building production software. Our tools are scientifically sound and practically usable.
Computational tools should accelerate real science
The value of a prediction model is measured by how much it accelerates experimental work. We focus on tools that reduce the time from hypothesis to validated result in the lab.