20.500.12556/RUP-22965 Fast prediction of protein flexibility Motivation Advances in hardware have made molecular dynamics (MD) simulations of protein structures faster and more accessible to the scientific community. However, accurately estimating protein flexibility using MD remains computationally demanding, especially for large systems and long time scales. Several MD-based resources—including MdMD, the DynamD database, and more recently ATLAS and mdCATH—now provide MD trajectories for thousands of proteins, enabling the development of predictive models. Results Here, the Graphlet Degree Vector (GDV) is introduced as a lightweight, fast, and easy-to-implement linear model for predicting protein flexibility directly from atom coordinates. GDV is a 15-dimensional feature vector that captures local packing and the spatial connectivity of each atom with its nearby neighbors. Trained on a subset of globular-like proteins from the ATLAS database, the GDV model achieves a Spearman correlation of 0.828 compared to MD data. The model trained on ATLAS dataset was further evaluated on independent Nuclear Magnetic Resonance and cryo-electron microscopy datasets, demonstrating the robustness and generalizability of the GDV-based approach. A key advantage of the GDV model is that it requires no additional external or experimental data and can be applied in near real time (on the order of 10 seconds) even for large proteins with 20,000 atoms on a standard desktop or laptop. Overall, the results show that a lightweight, fast, and purely coordinate-based model can provide accurate and generalizable predictions of protein flexibility across diverse folds and sizes. Napredek na področju strojne opreme je omogočil, da so simulacije molekulske dinamike (MD) proteinskih struktur hitrejše in dostopnejše znanstveni skupnosti. Vendar natančno ocenjevanje fleksibilnosti proteinov z uporabo MD še vedno ostaja računsko zahtevno, zlasti za velike proteine in daljše časovne skale. Več podatkovnih zbirk, kot so MdMD, DynamD ter novejši ATLAS in mdCATH, zdaj vsebuje MD trajektorije za tisoče proteinov, kar omogoča razvoj napovednih modelov. V tem delu je predstavljen Graphlet Degree Vector (GDV) kot preprost, hiter in enostaven linearni model za napovedovanje fleksibilnosti proteinov neposredno iz koordinat atomov. GDV je 15-dimenzionalni vektor značilk, ki zajema lokalno pakiranje in prostorsko povezanost vsakega atoma z njegovimi bližnjimi sosedi. Model GDV, naučen na podmnožici globularnim podobnih proteinov iz baze ATLAS, doseže Spearmanovo korelacijo 0,828 v primerjavi z MD podatki. Model, naučen na podatkih ATLAS, je bil dodatno ovrednoten na neodvisnih podatkovnih zbirkah jedrske magnetne resonance (NMR) in krioelektronske mikroskopije, kar potrjuje robustnost in posplošljivost pristopa, ki temelji na GDV. Ključna prednost modela GDV je, da ne zahteva dodatnih zunanjih ali eksperimentalnih podatkov in ga je mogoče uporabiti skoraj v realnem času (približno 10 sekund), tudi za velike proteine z 20.000 atomi na običajnem namiznem ali prenosnem računalniku. Na splošno rezultati kažejo, da lahko lahek, hiter model, ki temelji izključno na koordinatah, zagotovi natančne in posplošljive napovedi fleksibilnosti proteinov pri raznolikih zgradbah in velikostih. protein flexibility graphlets predictive model prožnost proteinov grafki napovedni model true false true Angleški jezik Slovenski jezik Članek v reviji 2026-04-16 14:58:21 2026-04-16 14:58:25 2026-04-17 03:05:12 0000-00-00 00:00:00 2026 0 0 str. 1-9 issue , [article no.] btag175 Vol. 15 Apr. 2026 0000-00-00 PostprintKoncna NiDoloceno apc 0000-00-00 0000-00-00 2026-04-15 577:547.96 1367-4811 10.1093/bioinformatics/btag175 275501315 RAZ_Praznikar_Jure_2026.pdf RAZ_Praznikar_Jure_2026.pdf 1 044124A09598BFCA0B997932A8D93F48 bcdd05eb7c127518b8ee9e5d24714102a7c58f2c85f245272c1a6085e04beaff 07004c0f-3994-11f1-9e8d-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=33557 https://academic.oup.com/bioinformatics/advance-article/doi/10.1093/bioinformatics/btag175/8654525?login=false 1 e63eb3c7-3993-11f1-9e8d-005056ac49c0 https://repozitorij.upr.si/Dokument.php?lang=slv&id=33556 Inštitut Andrej Marušič 0 0 0