ML Design Methods

Protein Design Methods

Browse and apply state-of-the-art machine learning methods for protein design, structure prediction, and sequence optimization.

14
Methods
505K
Generated
251K
Tested

Showing 14 of 14 methods

AF

AlphaFold 3

DeepMind
Structure Prediction

DeepMind's latest structure prediction model supporting proteins, DNA, RNA, and small molecules with unprecedented accuracy.

500Kgenerated
250Ktested
BG

BoltzGen

MIT
Diffusion

All-atom diffusion-based generative model developed for de novo design of protein and peptide binders across a wide array of target types.

2Kgenerated
543tested
RF

RFdiffusion

UW
Diffusion

A flexible de novo binder design workflow using RFdiffusion for backbone generation with high success rates across diverse protein targets.

2Kgenerated
109tested
BC

BindCraft

EPFL
Binder Design

Protein binder design pipeline that can be used to design miniprotein and peptide binders with high affinity and specificity.

594generated
171tested
MO

Mosaic

Open Source
Framework

Open-source framework for combining and composing a variety of structure prediction and other models for design, filtering, or guidance.

332generated
39tested
PR

ProtRL

Research
Language Model

Fine-tuning pipeline combining reinforcement learning algorithms (GRPO, DPO) with the ZymCTRL protein language model for enzyme design.

99generated
99tested
DS

DSM Synteract

Synteract
Diffusion

Protein language model trained with masked diffusion to enable both high-quality representation learning and generative protein design.

73generated
60tested
E2

ESM2 Optimization

Meta AI
Language Model

ESM2 is a masked language model trained on UniRef protein sequences. Used for structure prediction, property prediction, and functional annotation.

38generated
24tested
ED

EvoDiff

Microsoft
Diffusion

Motif-scaffolding pipeline that designs protein sequences around a given motif using the EvoDiff model for sequence-space diffusion.

26generated
26tested
B6

BLOSUM62

Classic
Alignment

BLOSUM (BLOcks SUbstitution Matrix) matrix is a substitution matrix used for sequence alignment of proteins, derived from conserved protein blocks.

22generated
1tested
P1

Pro-1

Research
Optimization

A reasoning model that proposes modifications to improve protein stability by analyzing structural context and evolutionary conservation.

20generated
20tested
AB

AntiBERTy

AbSci
Language Model

Antibody-specific transformer language model pre-trained on 558M natural antibody sequences for antibody design and optimization.

17generated
5tested
PT

ProTrek

Research
Language Model

ProTrek is a tri-modal protein language model that jointly models protein sequence, structure and function (SSF) for comprehensive protein understanding.

17generated
6tested
CT

co-TIMED

Research
Binder Design

A workflow for designing protein binders using co-TIMED, a method for co-designing sequences in a protein complex for improved binding.

16generated
16tested