Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

chai

Estrellas11

Forks0

Actualizado4 de marzo de 2026 a las 07:22

Structure prediction using Chai-1, a foundation model for molecular structure. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For ESM-based analysis, use esm.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

BioTender-max

BioTender-max/ProteinClaw

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Bioquímicos y biofísicosCiencias de la vida, físicas y sociales·SOC 19-1021

SKILL.md

readonly

name	chai
description	Structure prediction using Chai-1, a foundation model for molecular structure. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For ESM-based analysis, use esm.
license	MIT
category	design-tools
tags	["structure-prediction","validation","foundation-model"]
source	https://github.com/adaptyvbio/protein-design-skills

Chai-1 Structure Prediction

Prerequisites

Requirement	Minimum	Recommended
Python	3.10+	3.11
CUDA	12.0+	12.1+
GPU VRAM	24GB	40GB (A100)
RAM	32GB	64GB

How to run

Option 1: Modal

cd biomodals
modal run modal_chai1.py \
  --input-faa complex.fasta \
  --out-dir predictions/

Option 2: Chai API (recommended)

pip install chai_lab
python -c "
from chai_lab.chai1 import run_inference
run_inference(fasta_file='complex.fasta', output_dir='predictions/', num_trunk_recycles=3)
"

FASTA Format

>binder
MKTAYIAKQRQISFVKSHFSRQLE...
>target
MVLSPADKTNVKAAWGKVGAHAGE...

Protein + ligand

>protein
MKTAYIAKQRQISFVKSHFSRQLE...
>ligand|smiles
CCO

Key parameters

Parameter	Default	Description
`num_trunk_recycles`	3	Recycles (more = better)
`num_diffn_timesteps`	200	Diffusion steps

Output format

predictions/
├── pred.model_idx_0.cif    # Best model
├── scores.json             # pTM, ipTM, ranking_score
├── pae.npy                 # PAE matrix
└── plddt.npy               # pLDDT values

Chai vs AF2

Aspect	Chai-1	AlphaFold2
MSA required	No	Yes
Small molecules	Yes	No
Speed	Faster	Slower
Accuracy	Comparable	Reference

Typical performance

Campaign	Time (A100)	Cost (Modal)
100 complexes	30-60 min	~$10
500 complexes	2-4h	~$45

Troubleshooting

Error	Cause	Fix
`CUDA out of memory`	Complex too large	Use A100-80GB
`KeyError: 'iptm'`	Single chain	Ensure FASTA has 2+ chains
`ValueError: invalid SMILES`	Malformed ligand	Validate SMILES with RDKit

Next: protein-qc for filtering and ranking.

Más de este repositorio

mismo repositorio

protein-design

BioTender-max/ProteinClaw

Computational protein design toolkit. Use this skill group when: (1) Designing protein binders from scratch, (2) Predicting protein structures (Chai, Boltz, Protenix), (3) Sequence design with ProteinMPNN/LigandMPNN/SolubleMPNN, (4) Quality control and filtering of protein designs, (5) Planning and managing binder design campaigns, (6) Experimental characterization (SPR, BLI, cell-free expression), (7) Searching protein databases (PDB, UniProt, AFDB), (8) Antibody/nanobody design (IgGM, mBER). This is the top-level index. Sub-skills handle specific tools.

2026-03-0411

binder-design

BioTender-max/ProteinClaw

Guidance for choosing the right protein binder design tool. Use this skill when: (1) Deciding between BoltzGen or BindCraft, (2) Planning a binder design campaign, (3) Understanding trade-offs between different approaches, (4) Selecting tools for specific target types.

2026-03-0411

binding-characterization

BioTender-max/ProteinClaw

Guidance for SPR and BLI binding characterization experiments. Use when: (1) Planning binding kinetics experiments, (2) Troubleshooting poor/no binding signal, (3) Interpreting kinetic data artifacts, (4) Choosing between SPR vs BLI platforms.

2026-03-0411

boltz

BioTender-max/ProteinClaw

Structure prediction using Boltz-1/Boltz-2, an open biomolecular structure predictor. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Need open-source alternative to AF2, (4) Predicting protein-ligand complexes, (5) Using local GPU resources. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For Chai prediction, use chai.

2026-03-0411

boltzgen

BioTender-max/ProteinClaw

All-atom protein design using BoltzGen diffusion model. Use this skill when: (1) Need side-chain aware design from the start, (2) Designing around small molecules or ligands, (3) Want all-atom diffusion (not just backbone), (4) Require precise binding geometries, (5) Using YAML-based configuration. For sequence-only design, use proteinmpnn. For structure validation, use boltz.

2026-03-0411

campaign-manager

BioTender-max/ProteinClaw

Goal-oriented binder design campaign planning and health assessment. Use this skill when: (1) Planning a complete binder design campaign, (2) Converting high-level goals into runnable pipelines, (3) Assessing campaign health and pass rates, (4) Diagnosing why designs are failing QC, (5) Estimating time, cost, and expected yields, (6) Selecting between design tools for a specific target. This skill orchestrates the other protein design tools.

2026-03-0411

name	chai
description	Structure prediction using Chai-1, a foundation model for molecular structure. Use this skill when: (1) Predicting protein-protein complex structures, (2) Validating designed binders, (3) Predicting protein-ligand complexes, (4) Using the Chai API for high-throughput prediction, (5) Need an alternative to AlphaFold2. For QC thresholds, use protein-qc. For AlphaFold2 prediction, use alphafold. For ESM-based analysis, use esm.
license	MIT
category	design-tools
tags	["structure-prediction","validation","foundation-model"]
source	https://github.com/adaptyvbio/protein-design-skills

Chai-1 Structure Prediction

Prerequisites

Requirement	Minimum	Recommended
Python	3.10+	3.11
CUDA	12.0+	12.1+
GPU VRAM	24GB	40GB (A100)
RAM	32GB	64GB

How to run

Option 1: Modal

cd biomodals
modal run modal_chai1.py \
  --input-faa complex.fasta \
  --out-dir predictions/

Option 2: Chai API (recommended)

pip install chai_lab
python -c "
from chai_lab.chai1 import run_inference
run_inference(fasta_file='complex.fasta', output_dir='predictions/', num_trunk_recycles=3)
"

FASTA Format

>binder
MKTAYIAKQRQISFVKSHFSRQLE...
>target
MVLSPADKTNVKAAWGKVGAHAGE...

Protein + ligand

>protein
MKTAYIAKQRQISFVKSHFSRQLE...
>ligand|smiles
CCO

Key parameters

Parameter	Default	Description
`num_trunk_recycles`	3	Recycles (more = better)
`num_diffn_timesteps`	200	Diffusion steps

Output format

predictions/
├── pred.model_idx_0.cif    # Best model
├── scores.json             # pTM, ipTM, ranking_score
├── pae.npy                 # PAE matrix
└── plddt.npy               # pLDDT values

Chai vs AF2

Aspect	Chai-1	AlphaFold2
MSA required	No	Yes
Small molecules	Yes	No
Speed	Faster	Slower
Accuracy	Comparable	Reference

Typical performance

Campaign	Time (A100)	Cost (Modal)
100 complexes	30-60 min	~$10
500 complexes	2-4h	~$45

Troubleshooting

Error	Cause	Fix
`CUDA out of memory`	Complex too large	Use A100-80GB
`KeyError: 'iptm'`	Single chain	Ensure FASTA has 2+ chains
`ValueError: invalid SMILES`	Malformed ligand	Validate SMILES with RDKit

Next: protein-qc for filtering and ranking.