GLOM TGITO: multiscale protein modelling and multiview landscape-guided sequence discovery

Motivation: Offline protein design can exploit surrogate-predictor errors, favouring high-scoring sequences lacking measured support. We test whether multiscale representations and local experimental evidence improve prediction and candidate prioritization. Results: GLOM-TGITO links a global-local fluorescence predictor to multiview landscape-guided optimization. Across 31,434 measured ppluGFP2 sequences, GLOM achieved random/depth-holdout RMSEs of 0.170/0.247 versus 0.247/0.324 for the strongest SaProt-650M controls. Averaged across three training seeds, 96.3%/97.3% of prediction-ranked Top 100 test variants were measured bright (log10 fluorescence >=4.2). Search from 900 peak regions yielded 2,594 distinct candidate sequences. The selected Top 100 showed 2.9-8.2% lower mean representation deviation than four comparator pipelines; 38 versus 11-16 met joint novelty-reliability filters. Deviation identified measured test errors >0.1 (AUROC