3a:I[603186,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],"PageMetadata"] 3b:I[831915,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],"SearchResultsImage"] 3c:I[430295,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],""] 3d:I[299632,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],"default"] 3e:I[400402,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],"EndpointCTA"] 3f:I[331699,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],"ModelContent"] 42:I[402003,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],"default"] 43:I[946424,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/0ru0lffoswy0r.js","/_next/static/chunks/3ku5jwxt0m0j7.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/1p9dpv--te6vb.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/287gwk2yxvb9p.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0lt_qhq2z_c0z.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/42l8y0s3rkz96.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/295ffwyuqa4b6.js","/_next/static/chunks/0dhg9kgcvw3jk.js","/_next/static/chunks/2tbc_4m20jg4-.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/1vp9tib1kqhyk.js"],"default"] 37:["$","$L3a",null,{"hasPartnerEndpoint":false}] 40:T2111,## Model Overview ### Description: ProteinMPNN (Protein Message Passing Neural Network) is a deep learning-based graph neural network designed to predict amino acid sequences for given protein backbones. This network leverages evolutionary, functional, and structural information to generate sequences that are likely to fold into the desired 3D structures. This model is available for commercial use.
### Third-Party Community Consideration This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case. #### License / Terms of Use GOVERNING TERMS: This trial service is governed by the [NVIDIA API Trial Service Terms of Use](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [NVIDIA Community Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/). Additional Information: [MIT](https://github.com/dauparas/ProteinMPNN/blob/8907e6671bfbfc92303b5f79c4b5e6ce47cdef57/LICENSE). The NIM container is governed by the [NVIDIA Software License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/) and [Product-Specific Terms for AI Products](https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/). Users must accept the license terms on the [NGC container page](https://catalog.ngc.nvidia.com/orgs/nim/teams/ipd/containers/proteinmpnn) before pulling the container image. Use of the models in this Blueprint is governed by the [NVIDIA AI Foundation Models Community License](https://docs.nvidia.com/ai-foundation-models-community-license.pdf). **You are responsible for ensuring that your use of NVIDIA provided models complies with all applicable laws.** ### Deployment Geography Global ### Use Case ProteinMPNN enables researchers and commercial entities in the Drug Discovery, Life Sciences, and Protein Engineering fields to design amino acid sequences that fold into desired 3D protein structures. It is particularly useful for de novo protein design, enzyme engineering, and therapeutic protein development. ### Release Date build.nvidia.com: 7/27/2026 via [build.nvidia.com/ipd/proteinmpnn](https://build.nvidia.com/ipd/proteinmpnn)
NGC: 7/27/2026 via [catalog.ngc.nvidia.com](https://catalog.ngc.nvidia.com/orgs/nim/teams/ipd/containers/proteinmpnn)
### References: ``` @article{dauparas2022robust, title={Robust deep learning--based protein sequence design using ProteinMPNN}, author={Dauparas, Justas and Anishchenko, Ivan and Bennett, Nathaniel and Bai, Hua and Ragotte, Robert J and Milles, Lukas F and Wicky, Basile IM and Courbet, Alexis and de Haas, Rob J and Bethel, Neville and others}, journal={Science}, volume={378}, number={6615}, pages={49--56}, year={2022}, publisher={American Association for the Advancement of Science} } ```
### Model Architecture: **Architecture Type:** Protein Amino Acid Sequence Prediction
**Network Architecture:** ProteinMPNN
**Number of Model Parameters:** 1.7 million
### Input: **Input Type(s):** Protein in Protein Data Bank (PDB) format
**Input Format(s):** String
**Input Parameters:** One-Dimensional (1D)
**Other Properties Related to Input:** Accepts protein backbone structures in PDB format.
### Output: **Output Type(s):** Amino Acid Sequence
**Output Format:** Multi-FASTA (text file)
**Output Parameters:** One-Dimensional (1D)
**Other Properties Related to Output:** Generates sequences predicted to fold into the input backbone structure.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
### Software Integration: **Runtime Engine(s):** * Triton
**Supported Hardware Microarchitecture Compatibility:**
* NVIDIA Blackwell, NVIDIA Hopper, NVIDIA Ampere, NVIDIA Lovelace
**Supported Operating System:**
* [Linux]
* The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment. ### Model Version(s): ProteinMPNN 1.0.0
## Training & Evaluation: ### Training Dataset: ** Data Modality
* [Other: 3D Protein Structures] **Link:** [The Protein Data Bank](https://www.rcsb.org/)
** Data Collection Method by dataset
* Hybrid: Automatic, Human
For PDB dataset, scientists worldwide submit structural data determined by X-ray crystallography or cryo-electron microscopy (cryo-EM). This includes atomic coordinates, experimental data, and metadata about the biological macromolecules. ** Labeling Method by dataset
* Hybrid: Automatic, Human
For PDB dataset, expert biocurators review the submitted data to ensure accuracy and completeness. This involves checking the plausibility of the data and annotating it with relevant biological and chemical information. CATH 4.1 dataset is derived from the PDB dataset. The CATH (Class, Architecture, Topology, Homologous superfamily) database hierarchically classifies protein domain structures that are obtained from protein structures deposited in the PDB. The data in CATH are specifically sourced from PDB files and include structures determined at a resolution of 4 angstrom or better. The classification process involves both manual and automated methods to ensure accurate domain identification and classification. For ProteinMPNN, the data underwent quality filtering to ensure high accuracy, this involved removing structures with low resolution and potential errors. **Properties:** Model was trained by Institute for Protein Design. The dataset for training consisted of 23,358 sequences. Dataset: CATH 4.2, PDB. Sensors: X-ray crystallography, cryoEM. ### Evaluation Dataset: **Link:** [The Protein Data Bank](https://www.rcsb.org/)
** Data Collection Method by dataset
* Automatic: random splits from PDB dataset.
** Labeling Method by dataset
* Automatic: random splits from PDB dataset.
**Properties:** The training, validation, and test splits were derived from protein assemblies in the PDB, which includes structures determined by X-ray crystallography or cryo-electron microscopy (cryoEM). The dataset was divided into random splits with 23,358 sequences for training, 1,464 for validation, and 1,529 for testing. ### Inference: **Acceleration Engine:** Triton
**Test Hardware:**
* NVIDIA Ampere A100
* NVIDIA Blackwell B200
* NVIDIA Blackwell B300
* NVIDIA Blackwell RTX PRO 6000 Blackwell Workstation Edition
* NVIDIA Grace Blackwell GB10 Superchip (DGX Spark)
* NVIDIA Grace Blackwell GB200 Superchip
* NVIDIA Grace Blackwell GB300 Superchip
* NVIDIA Grace Hopper GH200 Superchip
* NVIDIA Hopper H100
* NVIDIA Hopper H200
* NVIDIA Lovelace L40S
* NVIDIA RTX6000-Ada
### Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). **You are responsible for ensuring the physical properties of model-generated molecules are appropriately evaluated, and comply with applicable safety regulations and ethical standards.** # Get Help ## Enterprise Support Get access to knowledge base articles and support cases or [submit a ticket](https://www.nvidia.com/en-us/data-center/products/ai-enterprise-suite/support/).41:Td06,## Step 1. Generate API Key ::generate-api-key ## Step 2. Start NIM 1. Export `NGC_API_KEY` variable. ``` export NGC_API_KEY= ``` 2. NIM container automatically downloads models. To save time and bandwidth it is recommended to provide local cache directory. This way NIM will be able to reuse already downloaded models. Execute following command to setup cache directory. ```bash export LOCAL_NIM_CACHE=~/.cache/nim mkdir -p "$LOCAL_NIM_CACHE" sudo chmod 0777 -R "$LOCAL_NIM_CACHE" ``` 3. Run the NIM container with the following commands. ```bash $ docker login nvcr.io Username: $oauthtoken Password: ``` ```bash docker run -it \ --runtime=nvidia \ --gpus='"device=0"' \ -p 8000:8000 \ -e NGC_API_KEY \ -v "$LOCAL_NIM_CACHE":/home/nvs/.cache/nim \ nvcr.io/nim/ipd/proteinmpnn:latest ``` This command will start the NIM container and expose port 8000 for the user to interact with the NIM. 4. Open a new terminal, leaving the terminal open with the just launched service. In the new terminal, wait until the health check end point returns `{"status":"ready"}` before proceeding. This may take a couple of minutes. You can use the following command to query the health check. ```bash curl http://localhost:8000/v1/health/ready ``` ## Step 3. Test the NIM ### Python client example 1. Save following Python example to a file named `nim_client.py`. ```python #!/usr/bin/env python3 import requests import os import json from pathlib import Path def get_reduced_pdb(): pdb = Path("1R42.pdb") if not pdb.exists(): pdb.write_text(requests.get(f"https://files.rcsb.org/download/{pdb}").text) lines = filter(lambda line: line.startswith("ATOM"), pdb.read_text().split("\n")) return "\n".join(list(lines)[:200]) r = requests.post( url="http://localhost:8000/biology/ipd/proteinmpnn/predict", json={ "input_pdb": get_reduced_pdb(), "ca_only": False, "use_soluble_model": False, "sampling_temp": [0.1], }, ) print(r, "Saving to output.fa:\n", r.text[:200], "...") Path("output.fa").write_text(json.loads(r.text)["mfasta"]) ``` 2. Execute the example. ```bash chmod +x nim_client.py ./nim_client.py ``` 3. The NIM saves results to the `output.fa` file in Multi-FASTA format. You can quickly view the file using the following command. ```bash cat output.fa ``` ### Shell client example 1. Save the following Shell example to a file named `nim_client.sh`. ```bash #!/usr/bin/env bash set -e URL=http://localhost:8000/biology/ipd/proteinmpnn/predict if [ ! -e 1R42.pdb ]; then curl -O https://files.rcsb.org/download/1R42.pdb; fi pdb=$(cat 1R42.pdb | grep ^ATOM | head -n 200 | awk '{printf "%s\\n", $0}') request='{ "input_pdb": "'"$pdb"'", "ca_only": false, "use_soluble_model": false, "sampling_temp": [0.1] }' curl -H 'Content-Type: application/json' \ -d "$request" "$URL" ``` 2. Execute the example. ```bash chmod +x nim_client.sh ./nim_client.sh ``` 3. The NIM displays the results to the terminal in JSON format. You can configure the NIM to display the results, scores, and probabilities in the Multi-FASTA output format. For more details on getting started with this NIM, visit the [NVIDIA NIM Docs](https://docs.nvidia.com/nim/index.html#bionemo). 38:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L3b",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/proteinmpnn.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L3c",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/ipd","children":"IPD"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"proteinmpnn"}],[["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"ProteinMPNN is a deep learning model for predicting amino acid sequences for protein backbones."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L3d",null,{"artifactType":"ENDPOINT","density":"standard","labels":["BioNemo","Protein Generation","biology","nim","nimType:endpoint:nim_type_run_anywhere","usecase:endpoint:usecase_drug_discovery"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L3e",null,{"cta":"$undefined","isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L3f",null,{"artifact":{"artifactType":"ENDPOINT","name":"proteinmpnn","displayName":"proteinmpnn","publisher":"ipd","shortDescription":"ProteinMPNN is a deep learning model for predicting amino acid sequences for protein backbones.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/proteinmpnn.jpg","labels":"$38:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"PREVIEW","value":"false"},{"key":"last_month_api_invocation_count","value":"6041"},{"key":"last_month_download_count","value":"0"}],"updatedDate":"2025-07-22T08:47:16.211Z","canGuestDownload":true,"createdDate":"2024-08-02T22:12:04.498Z","description":"$40","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy"},"endpointName":"proteinmpnn","endpointSpec":{"openAPISpec":{"openapi":"3.1.0","info":{"title":"NVIDIA NIM API for ProteinMPNN","description":"The NVIDIA NIM REST API for protein sequence design with ProteinMPNN.","termsOfService":"https://nvidia.com/legal/terms-of-use","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"MIT","url":"https://github.com/dauparas/ProteinMPNN/blob/8907e6671bfbfc92303b5f79c4b5e6ce47cdef57/LICENSE"},"version":"1.1.0"},"paths":{"/biology/ipd/proteinmpnn/predict":{"post":{"summary":"Predict amino acid sequences","operationId":"proteinmpnn_predict_biology_ipd_proteinmpnn_predict_post","requestBody":{"content":{"application/json":{"schema":{"$ref":"#/components/schemas/ProteinMPNNInputs"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ProteinMPNNOutputs"}}}},"422":{"description":"Validation Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/HTTPValidationError"}}}}},"x-nvai-meta":{"name":"proteinmpnn","version":"1.1.0","returns":"Returns predicted amino acid sequences for given protein backbones.","path":"/biology/ipd/proteinmpnn/predict","examples":[{"name":"Predict amino acid sequences for protein backbone (PDB: 1R42)","requestJson":"{'input_pdb': '', 'ca_only': false, 'use_soluble_model': false, 'sampling_temp': [0.1]}","responseJson":"{\n \"mfasta\": \">input, score=1.1846, global_score=1.1846, fixed_chains=[], designed_chains=['A', 'B', 'C'], model_name=v_48_020, git_hash=unknown, seed=879\\nNMYSYKKIGNKYIVSINNHTEIVKALNAFCKEKGILSGSINGIGAIGELTLRFFNPKTKAYDDKTFREQMEISNLTGNISSMNEQVYLHLHITVGRSDYSALAGHLLSAIQNGAGEFVVEDYSERISRTYNPDLGLNIYDFER/NMYSYKKIGNKYIVSINNHTEIVKALNAFCKEKGILSGSINGIGAIGELTLRFFNPKXXXXDDKTFREQMEISNLTGNISSMNEQVYLHLHITVGRSDYSALAGHLLSAIQNGAGEFVVEDYSERISRTYNPDLGLNIYDFER/NMYSYKKIGNKYIVSINNHTEIVKALNAFCKEKGILSGSINGIGAIGELTLRFFNPKTKAYDDKTFREQME...\",\n \"scores\": [\n 0.7704594135284424\n ]\n}"}],"templates":[{"title":"Synchronous requests","requestEjs":{"curl":"#!/usr/bin/env bash\nset -e\n\nURL=${URL:-https://health.api.nvidia.com/v1/biology/ipd/proteinmpnn/predict}\n\nif [ ! -e 1R42.pdb ]; then curl -O https://files.rcsb.org/download/1R42.pdb; fi\n\npdb=$(cat 1R42.pdb | grep ^ATOM | head -n 200 | awk '{printf \"%s\\\\n\", $0}')\n\nrequest='{\n \"input_pdb\": \"'\"$pdb\"'\",\n \"ca_only\": false,\n \"use_soluble_model\": false,\n \"sampling_temp\": [0.1]\n}'\ncurl -H 'Content-Type: application/json' \\\n -H \"Authorization: Bearer $NVIDIA_API_KEY\" \\\n -H \"nvcf-poll-seconds: 300\" \\\n -d \"$request\" \"$URL\"\n","python":"#!/usr/bin/env python3\nimport requests\nimport os\nimport json\nfrom pathlib import Path\n\ndef get_reduced_pdb():\n pdb = Path(\"1R42.pdb\")\n if not pdb.exists():\n pdb.write_text(requests.get(f\"https://files.rcsb.org/download/{pdb}\").text)\n lines = filter(lambda line: line.startswith(\"ATOM\"), pdb.read_text().split(\"\\n\"))\n return \"\\n\".join(list(lines)[:200])\n\nr = requests.post(\n url=os.getenv(\"URL\", \"https://health.api.nvidia.com/v1/biology/ipd/proteinmpnn/predict\"),\n headers={\"Authorization\": \"Bearer $NVIDIA_API_KEY\"},\n json={\n \"input_pdb\": get_reduced_pdb(),\n \"ca_only\": False,\n \"use_soluble_model\": False,\n \"sampling_temp\": [0.1],\n },\n)\nprint(r, \"Saving to output.fa:\\n\", r.text[:200], \"...\")\nPath(\"output.fa\").write_text(json.loads(r.text)[\"mfasta\"])\n"}}]},"description":"Predict amino acid sequences"}}},"components":{"schemas":{"HTTPValidationError":{"properties":{"error":{"type":"string"}},"type":"object","title":"HTTPValidationError"},"LicenseEndpointModel":{"properties":{"name":{"type":"string","title":"Name","description":"The name of the license for the NIM container."},"path":{"type":"string","title":"Path","description":"The filepath within the container containing the license content."},"sha":{"type":"string","title":"Sha","description":"A SHA1 hash of the license contents."},"size":{"type":"integer","title":"Size","description":"The number of characters in the license content."},"url":{"type":"string","title":"Url","description":"The url where this license is hosted externally."},"type":{"type":"string","const":"file","title":"Type","description":"The format of the license content."},"content":{"type":"string","title":"Content","description":"The license text."}},"type":"object","required":["name","path","sha","size","url","type","content"],"title":"LicenseEndpointModel","description":"A model representing the license response."},"ManifestEndpointModel":{"properties":{"manifest_file":{"type":"string","title":"Manifest File","description":"The content of the manifest file describing the required model artifacts."},"repository_override":{"type":"string","title":"Repository Override","description":"Alternate location used to retrieve artifacts from manifest file."}},"type":"object","required":["manifest_file","repository_override"],"title":"ManifestEndpointModel","description":"A model representing the manifest response."},"MetadataEndpointModel":{"properties":{"assetInfo":{"items":{"type":"string"},"type":"array","title":"Assetinfo","description":"A list of required container assets excluding model artifacts"},"licenseInfo":{"$ref":"#/components/schemas/LicenseEndpointModel","description":"The license info."},"modelInfo":{"items":{"$ref":"#/components/schemas/ModelInfo"},"type":"array","title":"Modelinfo","description":"A list of models being served by the NIM."},"repository_override":{"type":"string","title":"Repository Override","description":"Alternate location used to retrieve artifacts from manifest file."},"version":{"type":"string","title":"Version","description":"The version of the NIM service."},"selectedModelProfileId":{"type":"string","title":"Selectedmodelprofileid","description":"The ID of the currently selected model profile."}},"type":"object","required":["assetInfo","licenseInfo","modelInfo","repository_override","version","selectedModelProfileId"],"title":"MetadataEndpointModel","description":"A model representing the metadata response."},"ModelInfo":{"properties":{"modelUrl":{"type":"string","title":"Modelurl"},"shortName":{"type":"string","title":"Shortname"}},"type":"object","required":["modelUrl","shortName"],"title":"ModelInfo","description":"A model representing the model response."},"NIMErrorResponse":{"properties":{"error":{"additionalProperties":true,"type":"object","title":"Error","description":"Error details"}},"type":"object","required":["error"],"title":"NIMErrorResponse","description":"Error response model."},"NIMHealthSuccessResponse":{"properties":{"object":{"type":"string","title":"Object","description":"The object of the health response.","default":"health.response"},"message":{"type":"string","title":"Message","description":"The message of the health response."},"status":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Status","description":"The status of the health response for backwards compatibility."}},"type":"object","required":["message"],"title":"NIMHealthSuccessResponse","description":"A model representing the health success response."},"NIMVersionResponse":{"properties":{"release":{"type":"string","title":"Release","description":"The product release version of NIM for LLMs."},"api":{"type":"string","title":"Api","description":"The server API version running inside the NIM."}},"type":"object","required":["release","api"],"title":"NIMVersionResponse","description":"A model representing versions of the NIM"},"ProteinMPNNInputs":{"properties":{"input_pdb":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Input protein content (or file name if assets are used)","description":"Input protein for which amino acid sequences need to be predicted","numpy_dtype":"bytes","triton_shape":[1]},"input_pdb_asset":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Input protein asset","description":"Optional pre-uploaded NVCF Asset ID. If using this field, original file name should be provided via input_pdb argument.","numpy_dtype":"bytes","triton_shape":[1]},"input_pdb_chains":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"title":"Chains from input_pdb that are selected for design task","description":"The model will design amino acid sequences for the given chains in the input protein. If not specified, default is to design for all chains in the protein.","numpy_dtype":"bytes","pmpnn_arg_name":"pdb_path_chains","triton_shape":[-1]},"ca_only":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"CA-Only (alpha carbons) model enable flag","description":"CA-only model helps to address specific needs in protein design where focusing on the alpha carbon (CA) atoms can be advantageous","default":false,"numpy_dtype":"bool_","triton_shape":[1]},"use_soluble_model":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Soluble model enable flag","description":"ProteinMPNN offers both soluble and non-soluble models to cater to the specific needs of different protein design tasks. Soluble models are better suited for applications requiring high solubility, such as biotechnological processes, pharmaceutical development, and biochemical assays. Non-soluble models are advantageous for membrane protein studies, structural biology, and certain industrial applications where solubility is less critical or where proteins need to function in hydrophobic environments. This flexibility allows researchers to choose the appropriate model based on the specific requirements of their project.","default":false,"numpy_dtype":"bool_","triton_shape":[1]},"random_seed":{"anyOf":[{"type":"integer"},{"type":"null"}],"title":"Random Seed","description":"The model allows users to set or not set the random seed based on the specific needs. For example, if reproducibility is crucial, it is recommended to set a fixed seed. However, for tasks requiring exploration and diversity, users might choose not to set the seed, allowing the model to leverage the benefits of randomness.","numpy_dtype":"int64","pmpnn_arg_name":"seed","triton_shape":[1]},"num_seq_per_target":{"anyOf":[{"type":"integer","maximum":100,"minimum":1},{"type":"null"}],"title":"Number of amino acid sequences to generate [per target protein]","description":"This parameter specifies the number of sequences to generate per target protein structure. By setting num_seq_per_target, users can determine how many different sequences the model should predict that will fold into the given protein backbone structure.","default":1,"numpy_dtype":"int64","triton_shape":[1]},"sampling_temp":{"anyOf":[{"items":{"type":"number","maximum":1,"exclusiveMinimum":0},"type":"array","maxItems":100,"minItems":1},{"type":"null"}],"title":"Sampling temperatures","description":"The units for sampling temperatures in ProteinMPNN are dimensionless and range from 0 to 1. This parameter is used to adjust the probability values for the 20 amino acids at each position in the sequence, thereby controlling the diversity of the design outcomes. Higher values lead to increased diversity in the designed results, while lower values result in less diversity and more conservative designs. Recommended range is from 0.1 to 0.3.","numpy_dtype":"float","triton_shape":[-1]},"pssm_jsonl":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Position-Specific Scoring Matrix (PSSM)","description":"PSSM in the context of ProteinMPNN is a tool that incorporates evolutionary information into the protein design process. It helps guide mutations and enhance prediction accuracy by leveraging the conservation patterns observed in homologous protein sequences. This makes the designed proteins more likely to be stable and functional, improving the overall success of the design process. Note: The top-level key will always be overridden to 'input'; users do not need to supply a file name as the key.","numpy_dtype":"bytes","triton_shape":[1]},"pssm_multi":{"anyOf":[{"type":"number"},{"type":"null"}],"title":"Position-Specific Scoring Matrix (PSSM) multiplication factor","description":"This parameter is used to adjust the influence of PSSMs on the protein sequence design process, allowing users to balance between evolutionary data and the model's predictions to achieve desired design outcomes. A value of 0.0 means that the PSSM is not used at all, and the design relies entirely on the ProteinMPNN model's predictions. A value of 1.0 means that the design process completely ignores the ProteinMPNN model's predictions and relies solely on the PSSM. Intermediate values allow for a blend of both the PSSM and the model's predictions.","default":0,"numpy_dtype":"float","triton_shape":[1]},"pssm_threshold":{"anyOf":[{"type":"number"},{"type":"null"}],"title":"Position-Specific Scoring Matrix (PSSM) threshold","description":"Parameter can take any value between negative infinity and positive infinity. A higher threshold value will be more restrictive, allowing only amino acids with PSSM scores above the threshold to be included in the design. A lower threshold value will be less restrictive, allowing more amino acids to be considered. Setting the threshold to a very low value (for example, negative infinity) effectively means that all amino acids are allowed, while a very high value (for example, positive infinity) could exclude all amino acids.","default":0,"numpy_dtype":"float","triton_shape":[1]},"pssm_bias_flag":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Position-Specific Scoring Matrix (PSSM) bias enable flag","description":"This is parameter determines whether to apply a bias based on a Position-Specific Scoring Matrix (PSSM) during the protein sequence design process.","default":false,"numpy_dtype":"bool_","triton_shape":[1]},"pssm_log_odds_flag":{"anyOf":[{"type":"boolean"},{"type":"null"}],"title":"Position-Specific Scoring Matrix (PSSM) log-odds enable flag","description":"This parameter controls whether the PSSM values are transformed into log-odds scores. Log-odds scores are a common way to represent the likelihood of observing a particular amino acid at a given position relative to a background distribution. This transformation can make the PSSM values more interpretable and useful for guiding the design process","default":false,"numpy_dtype":"bool_","triton_shape":[1]},"fixed_positions_jsonl":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Fixed Position Residues","description":"This parameter allows to control which residues in the protein sequence remain unchanged during the design process, providing users with the ability to enforce specific constraints based on experimental or functional requirements. Note: fixed positions are indexed starting from 1, and relative to new sequence. Note: The top-level key will always be overridden to 'input'; users do not need to supply a file name as the key.","numpy_dtype":"bytes","triton_shape":[1]},"omit_AAs":{"anyOf":[{"items":{"type":"string"},"type":"array"},{"type":"null"}],"title":"Amino acids to omit globally","description":"This parameter allows to control which amino acids in the protein sequence should be excluded. Amino acids are specified as one-letter FASTA representations.","numpy_dtype":"bytes","triton_shape":[-1]},"omit_AA_jsonl":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Amino acids to omit at specific locations","description":"This parameter allows to exclude specific amino acids from the designed protein sequences at designated chain indices, providing users with greater control over the properties and functionality of the generated proteins. Example: '{\"input\": {\"A\": [[[1], \"V\"]]}}', would omit valine in chain A at first AA position (indexing starts from 1.) Note: The top-level key will always be overridden to 'input'; users do not need to supply a file name as the key.","numpy_dtype":"bytes","triton_shape":[1]},"bias_AA_jsonl":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Amino Acid biases","description":"By providing a bias dictionary, users can fine-tune the amino acid composition of the designed sequences. This can help in achieving specific design goals, such as avoiding certain amino acids that might lead to undesirable properties or promoting amino acids that enhance the desired characteristics of the protein. Dictionary is specified as a JSON object, for example, {\"A\": -1.1, \"F\": 0.7} would result in alanine amino acid less likely to appear in the designed protein and phenylalanine more likely. Note: The top-level key will always be overridden to 'input'; users do not need to supply a file name as the key.","numpy_dtype":"bytes","triton_shape":[1]},"bias_by_res_jsonl":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Amino Acid position-specific biases","description":"By providing a position-specific bias dictionary, users can fine-tune the amino acid composition of the designed sequences at specific residue positions. This can help in achieving specific design goals, such as promoting amino acids that enhance the desired characteristics of the protein at particular sites or avoiding amino acids that might lead to undesirable properties. Note: The top-level key will always be overridden to 'input'; users do not need to supply a file name as the key.","numpy_dtype":"bytes","triton_shape":[1]},"tied_positions_jsonl":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Tied positions","description":"By providing a dictionary of tied positions, users can ensure that specific residues are identical across different positions or chains. This is particularly important for designing proteins with internal repeats, cyclic symmetries, or multi-chain assemblies where certain residues must be the same to maintain the desired structure and function. Note: The top-level key will always be overridden to 'input'; users do not need to supply a file name as the key.","numpy_dtype":"bytes","triton_shape":[1]}},"additionalProperties":false,"type":"object","title":"ProteinMPNNInputs"},"ProteinMPNNOutputs":{"additionalProperties":true,"type":"object"}},"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}}},"servers":[{"url":"https://health.api.nvidia.com/v1/"}],"security":[{"Token":[]}]},"namespace":"qc69jvmznzxy","updatedDate":"2026-08-10T16:35:48.710Z","nvcfFunctionId":"77598af7-e712-44a2-8e91-d3522725740c","createdDate":"2024-08-02T22:12:04.876Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/ipd-proteinmpnn","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA AI Foundation Models Community License and the MIT License.\n","showUnavailableBanner":false,"projects":[{"name":"BioNemo Examples","url":"https://github.com/NVIDIA/BioNeMo/tree/main/examples/nims","imageUrl":"https://assets.ngc.nvidia.com/products/api-catalog/images/github-logo.jpg","workbench":false}],"deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$41"}],"modelCapability":{"functionCalling":false}},"artifactName":"proteinmpnn"},"isLoginRequired":true,"playgroundElement":"$42","publisherName":"ipd","searchParams":{},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/ipd/proteinmpnn","aliases":["/ipd/proteinmpnn/experience"]},{"label":"Model Card","icon":"book","kind":"default","id":"modelcard","href":"/ipd/proteinmpnn/modelcard","aliases":"$undefined"},{"label":"Projects","kind":"default","id":"projects","href":"/ipd/proteinmpnn/projects","aliases":"$undefined"},{"label":"Deploy","kind":"default","id":"deploy","href":"/ipd/proteinmpnn/deploy","aliases":"$undefined"}]}]}]}]]}]] 39:["$","$L43",null,{"spec":"$38:0:props:children:1:props:children:props:children:props:endpointSpec"}]