A low code solution for computationally predicting the properties of chemicals.
Explore the docs »
View Demo
·
Report Bug
·
Request Feature
Table of Contents
Protify is an open source platform designed to simplify and democratize workflows for chemical language models. With Protify, deep learning models can be trained to predict chemical properties at the click of a button, without requiring extensive coding knowledge or computational resources.
- Benchmark multiple models efficiently: Need to evaluate 10 different protein language models against 15 diverse datasets with publication-ready figures? Protify makes this possible without writing a single line of code.
- Flexible for all skill levels: Build custom pipelines with code or use our no-code interface depending on your needs and expertise.
- Accessible computing: No GPU? No problem. Synthyra offers precomputed embeddings for many popular datasets, which Protify can download for analysis with scikit-learn on your laptop.
- Cost-effective solutions: The upcoming Synthyra API integration will offer affordable GPU training options, while our Colab notebook provides an accessible entry point for GPU-reliant analysis.
Protify is currently in beta. We're actively working to enhance features and documentation to meet our ambitious goals.
Click to expand model list
pLM - Protein Language Model
| Model Name | Description | Size (parameters) | Type |
|---|---|---|---|
| ESM2-8 | Small pLM from Meta AI that learns evolutionary information from millions of protein sequences. | 8M | pLM |
| ESM2-35 | Medium-sized pLM trained on evolutionary data. | 35M | pLM |
| ESM2-150 | Large pLM with improved protein structure prediction capabilities. | 150M | pLM |
| ESM2-650 | Very large pLM offering state-of-the-art performance on many protein prediction tasks. | 650M | pLM |
| ESM2-3B | Largest ESM2 pLM with exceptional capability for protein structure and function prediction. | 3B | pLM |
| ESMC-300 | pLM optimized for classification tasks. | 300M | pLM |
| ESMC-600 | Larger pLM for classification. | 600M | pLM |
| ProtBert | BERT-based pLM trained on protein sequences from UniRef. | 420M | pLM |
| ProtBert-BFD | BERT-based pLM trained on BFD database with improved performance. | 420M | pLM |
| ProtT5 | T5-based pLM capable of both encoding and generation tasks. | 3B | pLM |
| ANKH-Base | Base version of the ANKH pLM focused on protein structure understanding. | 400M | pLM |
| ANKH-Large | Large version of the ANKH pLM with improved structural predictions. | 1.2B | pLM |
| ANKH2-Large | Improved second generation ANKH pLM. | 1.5B | pLM |
| GLM2-150 | Medium-sized general language model adapted for protein sequences. | 150M | pLM |
| GLM2-650 | Large general language model adapted for protein sequences. | 650M | pLM |
| GLM2-GAIA | Specialized GLM pLM with GAIA architecture improvements. | 650M | pLM |
| DPLM-150 | Diffusion pLM focused on joint sequence and structure. | 150M | pLM |
| DPLM-650 | Larger DPLM. | 650M parameters | pLM |
| DPLM-3B | Largest DPLM. | 3B | pLM |
| DSM-150 | Diffusion language model for proteins. | 150M | pLM |
| DSM-650 | Diffusion language model for proteins. | 650M | pLM |
| Random | Baseline model with randomly initialized weights, serving as a negative control. | Varies | Negative control |
| Random-Transformer | Randomly initialized transformer model serving as a homology-based control. | Varies | Homology control |
Click to expand dataset list
BC - Binary Classification
MCC - Multi-Class Classification
MLC - Multi-Label Classification
R - Regression
| Dataset Name | Description | Type | Task | Tokenwise | Dual inputs |
|---|---|---|---|---|---|
| EC | Enzyme Commission numbers dataset for predicting enzyme function classification. | MLC | Protein function prediction | No | No |
| GO-CC | Gene Ontology Cellular Component dataset for predicting protein localization in cells. | MLC | Protein localization prediction | No | No |
| GO-BP | Gene Ontology Biological Process dataset for predicting protein involvement in biological processes. | MLC | Protein function prediction | No | No |
| GO-MF | Gene Ontology Molecular Function dataset for predicting protein molecular functions. | MLC | Protein function prediction | No | No |
| MB | Metal ion binding dataset for predicting protein-metal interactions. | BC | Protein-metal binding prediction | No | No |
| DeepLoc-2 | Binary classification dataset for predicting protein localization in 2 categories. | BC | Protein localization prediction | No | No |
| DeepLoc-10 | Multi-class classification dataset for predicting protein localization in 10 categories. | MCC | Protein localization prediction | No | No |
| enzyme-kcat | Dataset for predicting enzyme catalytic rate constants (kcat). | R | Enzyme kinetics prediction | No | No |
| solubility | Dataset for predicting protein solubility properties. | BC | Protein solubility prediction | No | No |
| localization | Dataset for predicting subcellular localization of proteins. | MCC | Protein localization prediction | No | No |
| temperature-stability | Dataset for predicting protein stability at different temperatures. | BC | Protein stability prediction | No | No |
| optimal-temperature | Dataset for predicting the optimal temperature for protein function. | R | Protein property prediction | No | No |
| optimal-ph | Dataset for predicting the optimal pH for protein function. | R | Protein property prediction | No | No |
| fitness-prediction | Dataset for predicting protein fitness in various environments. | R | Protein fitness prediction | No | No |
| SecondaryStructure-3 | Dataset for predicting protein secondary structure in 3+1 classes. | MCC | Protein structure prediction | Yes | No |
| SecondaryStructure-8 | Dataset for predicting protein secondary structure in 8+1 classes. | MCC | Protein structure prediction | Yes | No |
| human-ppi | Dataset for predicting human protein-protein interactions. | BC | PPI prediction | No | Yes |
| human-ppi-pinui | Human protein-protein interaction dataset from PiNUI. | BC | PPI prediction | No | Yes |
| yeast-ppi-pinui | Yeast protein-protein interaction dataset from PiNUI. | BC | PPI prediction | No | Yes |
| peptide-HLA-MHC-affinity | Dataset for predicting peptide binding affinity to HLA/MHC complexes. | BC | Binding affinity prediction | No | Yes |
| gold-ppi | Gold standard dataset for protein-protein interaction prediction. | BC | PPI prediction | No | Yes |
| shs27-ppi | SHS27k dataset containing 27,000 protein-protein interactions. | MCC | PPI prediction type | No | Yes |
| shs148-ppi | SHS148k dataset containing 148,000 protein-protein interactions. | MCC | PPI prediction type | No | Yes |
| PPA-ppi | Protein-Protein Affinity dataset for quantitative binding predictions. | R | Protein-protein affinity prediction | No | Yes |
For more details about supported models and datasets, including programmatic access and command-line utilities, see the Resource Listing Documentation.
- Multiple interfaces: Run experiments via an intuitive GUI, CLI, or prepared YAML files
- Efficient embeddings: Leverage fast and efficient embeddings from ESM2 and ESMC via FastPLMs
- Coming soon: Additional protein, SMILES, SELFIES, codon, and nucleotide language models
- Flexible model probing: Use efficient MLPs for sequence-wise tasks or transformer probes for token-wise tasks
- Coming soon: Full model fine-tuning, hybrid probing, and LoRA
- Automated model selection: Find optimal scikit-learn models for your data with LazyPredict, enhanced by automatic hyperparameter optimization
- Coming soon: GPU acceleration
- Complete reproducibility: Every session generates a detailed log that can be used to reproduce your entire workflow
- Publication-ready visualizations: Generate cross-model and dataset comparisons with radar and bar plots, embedding analysis with PCA, t-SNE, and UMAP, and statistically sound confidence interval plots
- Extensive dataset support: Access 25 protein datasets by default, or easily integrate your own local or private datasets
- Coming soon: Additional protein, SMILES, SELFIES, codon, and nucleotide property datasets
- Advanced interaction modeling: Support for protein-protein interaction datasets
- Coming soon: Protein-small molecule interaction capabilities
Help us grow by sharing online, starring our repository, or contributing through our bounty program.
From pip
pip install Protify
To get started locally
git clone https://@github.com/Synthyra/Protify.git
cd Protify
python -m pip install -r requirements.txt
git submodule update --init --remote --recursive
cd src/protifyIf you would like a Python virtual environment with the requirements
chmod +x setup_bioenv.sh
./setup_bioenv.shToggle
To launch the gui, run
python -m guiIt's recommended to use the user interface alongside an open terminal, as helpful messages and progressbars will show in the terminal while you press the GUI buttons.
Here, we will compare various protein models against a random vector baseline (negative control) and random transformer (homology based control).
1.) Start the session
2.) Select the models you would like to benchmark
3.) Select the datasets you are interested in. Here we chose Enzynme Comission numbers (multi-label classification), metal-ion binding (binary classificaiton), solubility (deeploc2, binary classification), and catalytic rate (kcat, regression).
4.) Embed the proteins in the selected datasets. If your machine does not have a GPU, you can download precomputed embeddings for many common sequences.
Note: If you download embeddings, it will be faster to use the scikit model tab than the probe tab
5.) Select which probe and configuration you would like. Here, we will use a simple linear probe, a type neural network. It is the fastest (by a large margin) but worst performing option (by a small margin usually).
6.) Select your settings for training. Like most of the tabs, the defaults are pretty good. If you need information about what setting does what, the ? button provides a helpful note. The documentations has more extensive information
This will train your models!
7.) After training, you can render helpful visualizations by passing the log ID from before. If you forget it, you can look for the file generated in the logs folder.
Here's a sample of the many plots produced. You can find them all inside plots/your_log_id/*
8.) Need to replicate your findings for a report or paper? Just input the generated log into the replay tab
To run the same session from the command line instead, you would simply execute
python -m main --model_names ESM2-8 ESM2-35 ESMC-300 Random Random-Transformer --data_names EC DeepLoc-2 enzyme-kcat --patience 3
Or, set up a yaml file with your desired settings (so you don't have to type out everything in the CLI)
python -m main --yaml_path yamls/your_custom_yaml_path.yaml
Replaying from the CLI is just as simple
python -m main --replay_path logs/your_log_id.txt
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
We work with a bounty system. You can find bounties on this page. Contributing bounties will get you listed on the Protify consortium and potentially coauthorship on published papers involving the framework.
Simply open a pull request with the bounty ID in the title to claim one. For additional features not on the bounty list simply use a descriptive title.
For bugs and general suggestions please use GitHub issues.
Distributed under the Protify License. See LICENSE.md for more information.
Email: [email protected]
Website: https://synthyra.com
If you use this package, please cite the following papers. (Coming soon)