Data Summary for microsoft_Dayhoff-170m-UR90, Dayhoff-3b-UR90, Dayhoff-170m-GR, Dayhoffm-UR-50-BRn, Dayhoff-3b-GR-HM-c, Dayhoff-3b-GR-HM, Dayhoff-170m-UR50, Dayhoff-170m-UR50-BRq, Dayhoff-170m-UR50-BRu
1. General information
1.0.1 Version of the Summary: 1.0
1.0.2 Last update: 4-Dec-2025
1.1 Model Developer Identification
1.1.1 Model Developer name and contact details: Microsoft Corporation at One Microsoft Way, Redmond, WA 98052. Tel: 425-882-8080
1.2 Model Identification
1.2.1 Versioned model name(s): Dayhoff
1.2.2 Model release date: 25-Jul-2025
1.3 Overall training data size and characteristics
1.3.1 Size of dataset and characteristics
1.3.1.A Text training data size: Not applicable.
1.3.1.B Text training data content: Not applicable. Text data is not part of the training data.
1.3.1.C Image training data size: Not applicable.
1.3.1.D Image training data content: Not applicable. Images are not part of the training data.
1.3.1.E Audio training data size: Not applicable.
1.3.1.F Audio training data content: Not applicable. Audio data is not part of the training data.
1.3.1.G Video training data size: Not applicable.
1.3.1.H Video training data content: Not applicable. Video data is not part of the training data.
1.3.1.I Other training data size: Training data consists of protein sequences and multiple sequence alignments; sizes include 3.34 billion sequences across 1.7 billion clusters (Gigaref), 46 million structure-derived synthetic sequences (BackboneRef), and 16 million MSAs (OpenProteinSet)
1.3.1.J Other training data content:
1.3.2 Latest date of data acquisition/collection for model training: Uniref (January 2024), Gigaref (July 2024), BackboneRef (July 2024), OpenProteinSet (August 2023)
1.3.3 Is data collection ongoing to update the model with new data collection after deployment? No
1.3.4 Date the training dataset was first used to train the model: April 2024
1.3.5 Rationale or purpose of data selection: Datasets combine large-scale metagenomic and structure-based synthetic protein sequences to maximize coverage, diversity, and novelty of protein sequence space, supporting tasks like zero-shot mutation effect prediction, motif scaffolding, and guided generation of novel proteins with improved cellular expression rates
2. List of data sources
2.1 Publicly available datasets
2.1.1 Have you used publicly available datasets to train the model? Yes
2.2 Private non-publicly available datasets obtained from third parties
2.2.1 Datasets commercially licensed by rights holders or their representatives
2.2.1.A Have you concluded transactional commercial licensing agreement(s) with rights holder(s) or with their representatives? No
2.2.2 Private datasets obtained from other third-parties
2.2.2.A Have you obtained private datasets from third parties that are not licensed as described in Section 2.2.1, such as data obtained from providers of private databases, or data intermediaries? No
2.3 Personal Information
2.3.1 Was personal data used to train the model? Microsoft follows all relevant laws and regulations pertaining to personal information.
2.4 Synthetic data
2.4.1 Was any synthetic AI-generated data used to train the model? Yes
3. Data processing aspects
3.1 Respect of reservation of rights from text and data mining exception or limitation
3.1.1 Does this dataset include any data protected by copyright, trademark, or patent? Microsoft follows all required regulations and laws for processing data protected by copyright, trademark, or patent.
3.2 Other information
3.2.1 Does the dataset include information about consumer groups without revealing individual consumer identities? Microsoft follows all required regulations and laws for protecting consumer identities.
3.2.2 Was the dataset cleaned or modified before model training? Yes