These findings establish AF3 as reliable for the prediction of monomer disorder but unpredictable for multimers, confirming that disorder prediction emerges from training data, not model design.
Abstract
AlphaFold3 represents a major advance in protein structure prediction, yet its performance on intrinsically disordered proteins remains uncharacterized. We present the first systematic evaluation of AF3 on disordered systems, revealing a striking dichotomy. For monomers, AF3’s pLDDT scores reliably predict disorder (MCC: 0.693), matching AlphaFold2 and rivaling dedicated predictors. This consistency across fundamentally different architectures confirms that disorder prediction emerges from training data, not model design. For multimers, the picture grows complex. Despite comparable aggregate performance (mean DockQ: 0.563 vs 0.571), AF3 and AF2 achieve these results through fundamentally different mechanisms. Conventional structural features explain 58% of AF2’s variance but only 42% of AF3’s. Users cannot predict when AF3 will succeed or fail from interface properties alone. On disorder-to-order transitions (MFIB benchmark), both models perform equally well, successfully predicting final folded states. Yet seed variance analysis reveals that AF3 rarely converges reliably as most cases show substantial variance across independent runs, with occasional high-scoring outlier seeds within an otherwise low-scoring distribution, indicating the model can sometimes locate a correct solution without consistently identifying it. Our findings establish AF3 as reliable for the prediction of monomer disorder but unpredictable for multimers. Architectural innovation alone cannot overcome training data bias. Progress demands disorder-enriched datasets and ensemble sampling, not merely novel architectures.
This review synthesizes three complementary strategies for extending AF2 beyond a static prediction by perturbing the multiple sequence alignment (MSA) it receives: sequence-similarity clustering of MSA rows (AF-Cluster), stochastic subsampling of MSA depth combined with dropout and repeated inference, and random maski...
Yu-Qi Sun· Theoretical and Natural Scie...· 0 citations
AlphaFold's internal representation linearly encodes residue burial well beyond amino-acid identity, and more sharply than a sequence-only language model, providing an interpretable account of how hydrophobic structural information is reflected in AlphaFold's predictions and representations.
Ioan Sima, Daniela-Maria Cristea, Emilia-Loredana Pop· Proceedings of the 35th ACM...· 0 citations
Abstract AlphaFold2 (AF2) has become one of the most established and leading tools for predicting protein structures, although it often favors a single conformation. While it has been shown that sampling different conformations is possible by manipulating the multiple sequence alignment (MSA), the potential for multi‐s...
Many proteins, particularly in eukaryotes, contain intrinsically disordered regions (IDRs) in their sequences. IDRs lack a stable tertiary structure under physiological conditions, yet they are essential for a broad range of cellular functions. They can be efficiently and accurately identified with computational method...
Kui Wang, Gang Hu, Lukasz Kurgan· Current Protocols· 0 citations
With more than one third of the human proteome being structurally disordered, intrinsically disordered proteins (IDPs) are key contributors to complex cellular functions, despite their highly dynamic conformational ensembles remaining elusive to conventional techniques in structural biology. Coarse-grained (CG) simulat...
Mina Cullen, Carmen Biancaniello, Katerina Taškova et al.· Proceedings of the National...· 0 citations
Beyond predicting unique native globular protein structures, AlphaFold has been used to sample conformational diversity in globular proteins. Here, we asked whether this capacity can be transferred to amyloid fibrils formed by short peptides, despite the fundamental difficulties posed by their polymorphism, sensitivity...
Francesca Peccati· Journal of Chemical Informat...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.