Boosting AlphaFold protein tertiary structure prediction through MSA engineering and extensive model sampling and ranking in CASP16

Abstract

AlphaFold2 and AlphaFold3 have revolutionized protein structure prediction by enabling high-accuracy structure predictions for most single-chain proteins. However, obtaining high-quality predictions for difficult targets with shallow or noisy multiple sequence alignments and complicated multi-domain architectures remains challenging. We present MULTICOM4, an integrative structure prediction system that uses diverse MSA generation, large-scale model sampling, and an ensemble model quality assessment strategy to improve model generation and ranking of AlphaFold2 and AlphaFold3. In the 16th Critical Assessment of Techniques for Protein Structure Prediction, our predictors built on MULTICOM4 ranked among the top out of 120 predictors in tertiary structure prediction and outperformed a standard AlphaFold3 predictor. Our best predictor achieved an average TM-score of 0.902 for 84 CASP16 domains, with top-1 predictions reaching high accuracy (TM-score>0.9) for 73.8% and correct folds (TM-score>0.5) for 97.6% of domains. For best-of-top-5 predictions, all domains were correctly folded. The results show that MSA engineering using different sequence databases, alignment tools, and domain segmentation along with extensive model sampling is critical to generate accurate structural models. Combining complementary QA methods with model clustering further improves ranking reliability. These advances provide practical strategies for modeling difficult single-chain proteins in structural biology and drug discovery.

Fig. 1. The overall performance of top 20 out of 120 CASP16 predictors and the detailed performance of MULTICOM across 75 unique domains.

A The cumulative Z-scores of top 20 predictors. The standard AlphaFold3 predictor (AF3-server) run by Elofsson’s group ranked 29th with a cumulative Z-score 25.71 (not shown); B The Z-score of the top-1 prediction of MULTICOM for each of the 75 domains.

Fig. 2. The structural comparison between the native structures (green) and the top-1 models submitted by MULTICOM (blue).

A T1267s1-D1 (GDT-TS = 0.878), B T1237-D1 (GDT-TS = 0.905), C T1210-D1 (GDT-TS = 0.724), D T1207-D1 (GDT-TS = 0.564), E T1257-D1 (GDT-TS = 0.780).

Fig. 3. The TM-scores of the top-1 and best-of-top-5 models submitted by MULTICOM for the 84 domains.

A The TM-scores of the top-1 models for the 84 domains. B TM-scores of top-1 models vs TM-scores of best-of-top-5 models on the 84 domains.

Fig. 4. Head-to-head TM-score comparison between MULTICOM and AF3-server on 84 protein domains.

A Top-1 models and B best-of-top-5 models.

Fig. 5. Comparison of GDT-TS performance between the in-house AlphaFold2, the in-house AlphaFold3 predictor, and CASP16 AF3-server for the 12 single-chain monomer targets.

The plots show the top-1 and best-of-top-5 models generated by our in-house AlphaFold2, our in-house AlphaFold3 predictors, and AF3-server.

Fig. 6. Comparison of predicted structures for target T1226-D1.

A Native structure; B best model among the top-5 predictions of the in-house AlphaFold3 (GDT-TS = 0.650); C top-1 model of the in-house AlphaFold3 (GDT-TS = 0.336); D top-1 model of the in-house AlphaFold2 (GDT-TS = 0.334). The best-of-top-5 model of the in-house AlphaFold3 correctly predicted the folding of the C-terminal helices and their long-range interaction with other regions, while the other models did not.

Fig. 7. Comparison of GDT-TS performance for top-1 models generated using different MSA sources.

Each MSA was evaluated using AlphaFold2 under identical input settings.

Fig. 8. Comparison of predicted structures for target T1266-D1 using full-length MSA and domain-based MSAs.

A Native structure; B Full-length MSAs, including ColabFold, DeepMSA_qMSA, DeepMSA_dMSA, Default_AF2, ESM-MSA and DHR; C Domain-based MSAs with different domain segmentation methods: DomainParser, HHsearch, UniDoc and Manual.

Fig. 9. GDT-TS scores of the top-1 models selected by different QA methods across 12 single-chain monomer targets.

The five QA methods include AlphaFold2 plDDT, pairwise similarity score (PSS), GATE, EnQA, and GCPNet-EMA. MULTICOM represents the result of the final top-1 models submitted by the MULTICOM predictor, which integrated the multiple QA methods. Best (the virtual line) represents the upper bound (highest) of the GDT-TS in the model pool for each target.

Fig. 10. Overview of the tertiary structure prediction module of MULTICOM4.

The module begins with multiple sequence alignment (MSA) sampling on both general protein sequence databases (e.g., UniRef30, UniRef90) and specialized metagenomic sources (e.g., BFD, MGnify) using different alignment tools. For multi-domain targets, in addition to generating full-length MSAs, domain-based MSA construction is performed by segmenting the target sequence into domains, generating individual domain MSAs, and combining them into full-length MSAs through alignment pairing and gap padding. Templates are identified by aligning sequence profiles against the PDB70 and PDB_sort90 databases. Structure prediction is carried out using multiple deep learning-based predictors, including a customized AlphaFold2 pipeline with various MSAs and templates as input (mainly), AlphaFold3 web server (extensive sampling, mainly), and ESMFold (for single-protein sequence modeling only). Predicted models are evaluated by multiple model quality assessment (QA) methods/metrics (e.g., GATE, PSS, and plDDT) to select high-confidence final predictions.