SOTAVerified

Protein Design

Formally, given the design requirements of users, models are required to generate protein amino acid sequences that align with those requirements.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 71–80 of 175 papers

TitleStatusHype
RNACG: A Universal RNA Sequence Conditional Generation model based on Flow-Matching—0
Context-Guided Diffusion for Out-of-Distribution Molecular and Protein DesignCode1
Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design—0
Reinforcement Learning for Sequence Design Leveraging Protein Language Models—0
Fast uncovering of protein sequence diversity from structure—0
RNAFlow: RNA Structure & Sequence Design via Inverse Folding-Based Flow MatchingCode2
UniIF: Unified Molecule Inverse Folding—0
Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient—0
Learning the Language of Protein StructureCode1
Out of Many, One: Designing and Scaffolding Proteins at the Scale of the Structural Universe with Genie 2Code2
Show:102550
← PrevPage 8 of 18Next →
All datasetsCATH 4.2CATH 4.3

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1GraphTransPerplexity6.63—Unverified
2StructGNNPerplexity6.4—Unverified
3AlphaDesignPerplexity6.3—Unverified
4GCAPerplexity6.05—Unverified
5GVPPerplexity5.36—Unverified
6ProteinMPNNPerplexity4.61—Unverified
7PiFoldPerplexity4.55—Unverified
8Knowledge-DesignPerplexity3.46—Unverified
#ModelMetricClaimedVerifiedStatus
1ESM-IFPerplexity6.44—Unverified
2GVP-largePerplexity6.17—Unverified