Mapping cell distributions across spatial locations with whole-genome coverage is essential for understanding cellular responses and signaling pathways. However, current deconvolution models, which aim to estimate the proportions of distinct cell types in each spatial transcriptomics spot by integrating reference single-cell data, often assume strong overlap between reference and spatial datasets, neglecting biology-grounded constraints like sparsity and cell-type variations and technical sparsity resulting in noise. As a result, these methods rely on over-permissive algorithms that ignore given constraints leading to inaccurate predictions, particularly in heterogeneous or unmatched datasets. We introduce Weight-Induced Sparse Regression (WISpR), a machine learning algorithm that integrates spot-specific hyperparameters and sparsity-driven modeling. Unlike conventional approaches that neglect biology-grounded constraints, WISpR accurately predicts cell-type distributions while preserving biological coherence, i.e., spatially and functionally consistent cell-type localization, even in unmatched datasets. Benchmarking against five alternative methods across ten datasets, WISpR consistently outperformed competitors and predicted cellular landscapes in both normal and cancerous tissues. By leveraging sparse cell-type arrangements, WISpR provides biologically informed, high-resolution cellular maps. Its ability to decode tissue organization in both healthy and diseased states highlights WISpR’s practical utility for spatial transcriptomics, particularly in challenging settings involving noise, sparsity, or reference mismatches.