https://github.com/b05611038/ebgmcr_solver.
Signal unmixing analysis decomposes data into basic patterns and is widely applied in chemical and biological research. Multivariate curve resolution (MCR), a branch of signal unmixing, separates mixed chemical signals into base patterns (components) and their concentrations, playing a key role in understanding composition. Classical MCR is typically framed as matrix factorization (MF) and requires a user-specified component count, usually unknown in real data. As dataset size or component count increases, the scalability and reliability of MF-based MCR face significant challenges. This study reformulates MCR as a generative process (gMCR), and introduces an energy-based deep learning solver, EB-gMCR, that automatically discovers the smallest component set able to reconstruct the data faithfully. EB-gMCR starts from a large candidate pool (e.g., 1024 spectra) and employs a differentiable gating network to retain only active components while estimating their concentrations. On noisy synthetic datasets containing up to 256 latent sources, EB-gMCR maintained R^2 >= 0.98 and recovered the component count within 5% of the ground truth; at lower noise it achieved R^2 >= 0.99 with near exact component estimation. Additional chemical priors, such as non-negativity or nonlinear mixing, enter as simple plug-in functions, enabling adaptation to other instruments or domains without altering the core learning process. By uniting high-capacity generative modeling and hard component selection, EB-gMCR offers a practical route to large-scale signal unmixing analysis, including chemical library-driven scenarios. The source code is available at