Computational Antibody Papers
Filter by tags
structure prediction
Filter by published year
All
TitleKey points
2026-05-29
Language Modeling Materializes a World Model of Protein Biology
- language models
- protein design
- structure prediction
- New versions of ESM and ESMFold, ESMC (ESM Cambrian) and ESMFold2 to model protein sequence, structure, and function.
- Like previous versions, ESMC is trained entirely on sequences using a masked language modeling (MLM) objective. However, it scales up to 2.8 billion metagenomic sequences, nearly a 100-fold increase over the 50 million sequences used for ESM2.
- ESMFold2 achieves state-of-the-art atomic resolution and directly outperforms AlphaFold3 on complex antibody-antigen predictions (even when AlphaFold3 is given multiple sequence alignments and ESMFold2 operates from sequence alone).
- To design therapeutic antibody fragments (scFvs), they input the target sequence and lock in a stable, known antibody framework template, leaving only the target-recognizing loops (CDRs) to be filled in.
- AI-guided optimization: The system uses mathematical backpropagation through both ESMC and ESMFold2 to iteratively optimize the CDR sequences. It automatically mutates the loops to maximize structural interface confidence scores.
- They synthesized and tested these computational designs in the wet lab, achieving high experimental hit rates and discovering entirely novel binders with therapeutically relevant nanomolar affinities.
- PromptMOL: a PyMOL plugin that enables direct interaction with molecular structures using natural language commands.
- While PyMOL is a gold standard in structural biology, its interface can be complex; PromptMOL removes the barrier to entry by replacing convoluted script syntax with simple, descriptive prompts.
- By hooking directly into LLMs (via local models like LM Studio, or cloud providers like OpenAI and Anthropic), the plugin intelligently handles selections, coloring, structural analysis, and rendering tasks on the fly.
2026-04-17
Sampling antibody conformational ensembles with ABodyBuilder4-STEROIDS
- structure prediction
- Fourth version of ABodyBuilder: Now uses a generative flow matching model (ABB4-STEROIDS) specifically designed to sample antibody conformational ensembles.
- Trained on FlAbDab and all-atom MD, utilizes 4.2 million frames from ~136,000 coarse-grained simulations, plus a new fine-tuning set of 83 all-atom MD simulations.
- Shows marginal improvements over ABB3 but is less accurate than Boltz-1 for single-structure RMSD; it also exhibits a higher number of atomic clashes than Boltz-1.
- Outperforms alternative models (including Boltz-1 and AlphaFlow) at reproducing MD ensemble metrics and matching experimental evidence of CDR loop diversity.
2026-04-03
Evaluating Deep Learning Based Structure Prediction Methods on Antibody-Antigen Complexes
- structure prediction
- Authors benchmark co-folding methods on their ability to identify true positives given deep sampling.
- AlphaFold3 consistently outperforms AlphaFold2, Chai-1, and Boltz-1 in predicting antibody-antigen complexes, though its accuracy declines if the target lacks structural similarity to its training data.
- For all methods, increased sampling improves the probability of generating a correct model in a roughly log-linear manner; however, the improvement is limited by a significant gap between the "best" model generated and the "top-ranked" model.
- Internal confidence metrics (like ipTM) struggle to identify the most accurate structures for a given target, primarily because the models cannot yet accurately predict their own aligned errors.
2026-03-13
Structural Plausibility Without Binding Specificity: Limits of AI-Based Antibody-Antigen Structure Prediction Confidence Scores
- binding prediction
- nanobodies
- structure prediction
- The authors evaluated AlphaFold3, Boltz-2, and Chai-1 on their ability to distinguish cognate (correct) nanobody-antigen pairs from incorrect, non-binding pairings.
- They used 106 experimental complexes and generated a combinatorial matrix of 11,132 shuffled non-cognate pairings to serve as ground-truth "incorrect" decoys.
- Internal confidence scores (specifically ipTM) were very weakly predictive of true binding. In terms of Average Precision (PR-AUC), AF3 performed best, followed by Chai-1 and then Boltz-2.
- Increased sampling improves structural geometry but does not help models "select" the correct binder. Most quality gains occur within 10–25 samples; deeper sampling primarily increases the number of plausible-looking false positives.
2026-02-26
Disulphide and sequence-encoded conformational priors guide nanobody structure prediction
- nanobodies
- structure prediction
- Authors propose a new method to train a nanobody structure predictor by using ‘blueprints’.
- They developed a classifier (NbFrame) to identify whether the HCDR3 loop adopts a kinked (framework-contacting) or extended (solvent-exposed) conformation. This allows the model to use sequence-encoded priors and explicit constraints during the folding process.
- The model itself is very lightweight and runs significantly faster than "heavy" models like AF or Boltz. NbForge achieves sub-second inference speeds, predicting structures in less than a second on both CPU and GPU. In comparison, models like AlphaFold3 or Boltz1 typically require tens of seconds to minutes per structure - MSA is a different story altogether.
- The model matches the HCDR3 prediction quality of heavy models while being much more efficient. While AF3 and Boltz1 are more accurate at modeling the rigid framework, NbForge achieves parity in the hypervariable HCDR3 region—the part most critical for binding. Its speed and high recovery of disulphide bonds make it ideal for triaging millions of candidates in large-scale discovery campaigns.
- ‘Evolution’ of AlphaFold from Isomorphic labs.
- IsoDDE achieves 39% accuracy in high fidelity regime ((DockQ > 0.8)) which corresponds to near-experimental precision with an interface RMSD (iRMSD) typically below 1.0Å. That’s a 2.3x improvement over AF3.
- Using a single model seed, IsoDDE successfully predicts 63% of interfaces DockQ > 0.23 (correlating to an iRMSD$ of roughly 4.0Å or less, which is a 1.4x improvement over AF3's single-seed performance.
- IsoDDE accurately models the backbone of the highly variable CDR-H3 loop for 70% of antibodies (<2Å) in the test set, outperforming AF3’s success rate of 58% 1.2x.
- When scaled to 1,000 seeds, IsoDDE reaches an 82% success rate for correct interfaces and 59% for high-accuracy predictions. So to get results one cannot exactly do it on a laptop.
- It is a technical report, architecture is not discussed.
2026-02-16
Surpassing AlphaFold3 via Architectural Refinement and Structural Consistency
- structure prediction
- New open source reproduction of AlphaFold3 that either matches or surpasses it.
- IntelliFold-2-Pro achieves a success rate of 58.2% (DockQ > 0.23 so about 4A irmsd) on antibody-antigen interactions, outperforming AlphaFold 3's 47.9%.
- For small molecule co-folding, IntelliFold-2-Pro reaches 67.7%, surpassing AlphaFold 3’s 64.9%.
- Interface Precision vs. Monomers: IntelliFold-2 shows marginal gains in protein monomer accuracy (LDDT of 0.89 vs AF3's 0.88).
2026-02-16
AbTune: layer-wise selective Fine-Tuning of protein language models for Antibodies
- structure prediction
- A strategy for layer-wise selective fine-tuning of general protein language models.
- Instead of full fine-tuning, they found that adapting only the first 50-75% of layers via LoRA provides optimal performance while saving computational costs.
- For example, they perform sequence-specific "test-time" training where they optimize the model using a Masked Language Modeling (MLM) objective on the target sequence itself before predicting its properties. This approach led to a 18.4% accuracy boost in predicting the notoriously difficult CDR-H3 antibody loop
2026-02-05
Multiple protein structure alignment at scale with FoldMason
- non-antibody stuff
- structure prediction
- Protocol for ultra fast protein structure alignment.
- FoldMason represents protein structures as 1D sequences using a structural alphabet (3Di+AA), which allows it to perform multiple alignments using fast string comparison algorithms and a parallelized progressive alignment following a minimum spanning tree.
- It operates two to three orders of magnitude faster than traditional structure-based methods, achieving a 722x speedup over tools like MUSTANG and scaling to align 10,000 structures in a fraction of the time required by competitors for just 100.
- It matches the accuracy of gold-standard structure aligners and exceeds sequence-based tools, particularly in aligning distantly related proteins or flexible structures that global superposition-based methods struggle to handle.
- It is used for large-scale structural analysis of massive databases like AlphaFoldDB, building structure-based phylogenies for proteins that have diverged past the "twilight zone" of sequence similarity, and providing interactive web-based visualizations of complex MSTAs