Edge-specific signal propagation on mature chromophore-region 3D mechanism graphs for fluorescent protein quantum-yield prediction
2026-05-07 • Machine Learning
Machine Learning
AI summaryⓘ
The authors developed a new method to predict how well fluorescent proteins emit light, based on detailed 3D information about their important parts called chromophores. Instead of just looking at protein sequences, they created a graph model that focuses on different chromophore regions and how nearby parts interact. Their method outperformed existing models, especially for proteins that are less similar to known examples. They also identified specific structural features linked to fluorescence in different protein groups, making their predictions more understandable.
fluorescent proteinquantum yieldchromophorePDB structure3D residue graphExtraTrees regressionprotein homologyGFParomatic packingprotein fluorescence
Authors
Yuchen Xiong, Swee Keong Yeap, Steven Aw Yoong Kit
Abstract
Fluorescent protein quantum yield (QY) is governed by the mature chromophore and its three-dimensional microenvironment rather than sequence identity alone. Protein language models and emission-band averages capture global trends, but do not model how local physical signals act on specific chromophore regions. We present a chromophore-centred mechanism graph algorithm for QY prediction. Each PDB structure is converted into a typed 3D residue graph, registered to a mature-CRO state, partitioned into phenolate, bridge and imidazolinone regions, and transformed by channel-signal-region propagation. The representation contains 121 enrichment features; after removing identity shortcuts, 52 non-identity features are used for band-specific ExtraTrees regression. Because each feature encodes a contact channel, seed signal and target CRO region, interpretation is intrinsic rather than post hoc. On a 531-protein benchmark, the method achieved the best random-CV performance among model-based baselines (R = 0.772 +/- 0.008, MAE = 0.131 +/- 0.002), exceeding Band mean (R = 0.632), ESM-C (R = 0.734) and SaProt (R = 0.731), and ranked first in bright screening (Bright P@5 = 0.704). Under homology control, the advantage was clearest in the remote bucket (<50% similarity; R = 0.697 versus 0.633, 0.575 and 0.408), with the strongest overall bright/dark Top-K screening. Stable selected features recovered band-specific mechanisms: aromatic packing and clamp asymmetry in GFP-like proteins, charge/clamp balance in Red proteins, and flexibility-risk/bulky-contact features in Far-red proteins. Source code, feature tables and evaluation scripts are available from the first author upon request. Contact: yuchenak05@gmail.com