Restructure the project and rename it from intfold to intellifold

Author: fuxuliu

LICENSE

@@ -201,12 +201,12 @@
    See the License for the specific language governing permissions and
    limitations under the License.
 
-Implementation of the `LayerNorm` operators (in intfold/openfold/utils/layer_norm/) referred to [OneFlow]
+Implementation of the `LayerNorm` operators (in intellifold/openfold/utils/layer_norm/) referred to [OneFlow]
 (https://github.com/Oneflow-Inc/oneflow) and [FastFold](https://github.com/hpcaitech/FastFold). 
-Many components in `intfold/openfold/` are adapted from [OpenFold](https://github.com/aqlaboratory/openfold), with substantial modifications and improvements by our team (except for the `LayerNorm` part).  
+Many components in `intellifold/openfold/` are adapted from [OpenFold](https://github.com/aqlaboratory/openfold), with substantial modifications and improvements by our team (except for the `LayerNorm` part).  
 OneFlow, FastFold, and OpenFold are all licensed under the Apache License 2.0.
 
-The inference data pipeline in `intfold/data/` is adapted from [Boltz-1](https://github.com/jwohlwend/boltz).
+The inference data pipeline in `intellifold/data/` is adapted from [Boltz-1](https://github.com/jwohlwend/boltz).
 Boltz-1 is licensed under the MIT License.  
 The MIT License and copyright notice are included below.
 

README.md

@@ -1,8 +1,8 @@
-![IntFold Cover](assets/intfold-cover.png)
+![intellifold Cover](assets/intellifold-cover.png)
 
-# IntFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure Prediction
-[![HuggingFace Models](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Models-yellow)](https://huggingface.co/intelligenAI/intfold)
-[![PyPI](https://img.shields.io/pypi/v/intfold)](https://pypi.org/project/intfold/)
+# IntelliFold: A Controllable Foundation Model for General and Specialized Biomolecular Structure Prediction
+[![HuggingFace Models](https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Models-yellow)](https://huggingface.co/intelligenAI/intellifold)
+[![PyPI](https://img.shields.io/pypi/v/intellifold)](https://pypi.org/project/intellifold/)
 [![License](https://img.shields.io/badge/license-Apache%202.0-blue)](LICENSE)
 [![Email](https://img.shields.io/badge/Email-Contact-lightgrey?logo=gmail)](#contact-us)
 
@@ -13,17 +13,17 @@
 </div>
 
 
-![IntelliFold Model](assets/Intfold-Model-Arc.png)
+![IntelliFold Model](assets/Intellifold-Model-Arc.png)
 
 
 ## 🚀 Quick Start
 
 To quickly get started with IntelliFold, you can use the following commands:
 ```bash
-# Install IntFold from PyPI
-pip install intfold
+# Install intellifold from PyPI
+pip install intellifold
 # Run inference with an example YAML file
-intfold predict ./examples/5S8I_A.yaml --out_dir ./output
+intellifold predict ./examples/5S8I_A.yaml --out_dir ./output
 ```
 
 ## ⚙️ Installation
@@ -37,7 +37,7 @@ To more complete installation instructions and usage, please refer to the [Insta
 
 2. **Run Prediction**:
    ```bash
-   intfold predict your_input.yaml --out_dir ./results
+   intellifold predict your_input.yaml --out_dir ./results
    ```
 
 3. **Check Results**: Find predicted structures and confidence scores in the output directory, you can also check the section of **output format** in [output documentation](docs/input_yaml_format.md#output-format).
@@ -52,14 +52,14 @@ To comprehensively evaluate the performance of IntelliFold, we conducted a rigor
 
 For more details on the benchmarking process and results, please refer to our [Technical Report](https://arxiv.org/abs/2507.02025).
 
-![Benchmark Metrics](assets/intfold_metrics.png)
+![Benchmark Metrics](assets/intellifold_metrics.png)
 
 
 ## 🌐 IntelliFold Server
 
 **We highly recommend using the [IntelliFold Server](https://server.intfold.com) for the most accurate, complete, and convenient biomolecular structure predictions.** It requires no installation and provides an intuitive web interface to submit your sequences and visualize results directly in your browser. The server runs the **full, optimized, latest** IntelliFold implementation for optimal performance.
 
-![IntelliFold Server](assets/intfold-server-screenshot.png)
+![IntelliFold Server](assets/intellifold-server-screenshot.png)
 
 
 ## 📜 Citation
@@ -82,14 +82,14 @@ If you use IntelliFold in your research, please cite our paper:
 ## 🔗 Acknowledgements
 
 - The implementation of **fast layernorm operators** is inspired by [OneFlow](https://github.com/Oneflow-Inc/oneflow) and [FastFold](https://github.com/hpcaitech/FastFold), following [Protenix](https://github.com/bytedance/Protenix)'s usage. 
-- Many components in `intfold/openfold/` are adapted from [OpenFold](https://github.com/aqlaboratory/openfold), with substantial modifications and improvements by our team (except for the `LayerNorm` part).  
+- Many components in `intellifold/openfold/` are adapted from [OpenFold](https://github.com/aqlaboratory/openfold), with substantial modifications and improvements by our team (except for the `LayerNorm` part).  
 - This repository, the implementation of **Inference Data Pipeline**(Data/Feature Processing and MSA generation tasks) referred to [Boltz-1](https://github.com/jwohlwend/boltz), and modify some codes to adapt to the input of our model.
 
 
 
 ## ⚖️ License
 
-The IntFold project, including code and model parameters, is made available under the [Apache 2.0 License](./LICENSE), it is free for both academic research and commercial use.
+The IntelliFold project, including code and model parameters, is made available under the [Apache 2.0 License](./LICENSE), it is free for both academic research and commercial use.
 
 ## 📬 Contact Us
 

assets/Intfold-Model-Arc.png renamed to assets/Intellifold-Model-Arc.png

@@ -3,48 +3,48 @@
 
 1. **Clone the repository**
     ```bash
-    git clone https://github.com/IntelliGen-AI/IntFold.git
-    cd IntFold
+    git clone https://github.com/IntelliGen-AI/IntelliFold.git
+    cd IntelliFold
     ```
 
 2. **Create and activate the environment(recommended)**
     ```bash
     conda env create -f environment.yaml
-    conda activate intfold
+    conda activate intellifold
     ```
 
 3. **Install the package**
     - From PyPI (recommended):
       ```bash
-      pip install intfold
+      pip install intellifold
       ```
     - From local wheel:
       ```bash
-      pip install pypi/intfold-0.1.3-py3-none-any.whl
+      pip install pypi/intellifold-0.1.0-py3-none-any.whl
       ```
     - Editable install:
       ```bash
       pip install -e .
       ```
 
-4. **(Optional) Download IntFold Cache Data Manually**<br>
-    By default, model weights and CCD data are downloaded automatically(the directory is `~/.intfold`) when you run the inference. But you can also download by yourself.
-    To download manually from [Our HuggingFace Repository](https://huggingface.co/intelligenAI/intfold):
+4. **(Optional) Download IntelliFold Cache Data Manually**<br>
+    By default, model weights and CCD data are downloaded automatically(the directory is `~/.intellifold`) when you run the inference. But you can also download by yourself.
+    To download manually from [Our HuggingFace Repository](https://huggingface.co/intelligenAI/intellifold):
 
     ```bash
     mkdir -p cache_data
     cd cache_data
-    wget https://huggingface.co/intelligenAI/intfold/resolve/main/intfold_v0.1.0.pt
-    wget https://huggingface.co/intelligenAI/intfold/resolve/main/ccd.pkl
-    wget https://huggingface.co/intelligenAI/intfold/resolve/main/unique_protein_sequences.fasta 
-    wget https://huggingface.co/intelligenAI/intfold/resolve/main/unique_nucleic_acid_sequences.fasta 
-    wget https://huggingface.co/intelligenAI/intfold/resolve/main/protein_id_groups.json
-    wget https://huggingface.co/intelligenAI/intfold/resolve/main/nucleic_acid_id_groups.json
+    wget https://huggingface.co/intelligenAI/intellifold/resolve/main/intellifold_v0.1.0.pt
+    wget https://huggingface.co/intelligenAI/intellifold/resolve/main/ccd.pkl
+    wget https://huggingface.co/intelligenAI/intellifold/resolve/main/unique_protein_sequences.fasta 
+    wget https://huggingface.co/intelligenAI/intellifold/resolve/main/unique_nucleic_acid_sequences.fasta 
+    wget https://huggingface.co/intelligenAI/intellifold/resolve/main/protein_id_groups.json
+    wget https://huggingface.co/intelligenAI/intellifold/resolve/main/nucleic_acid_id_groups.json
     ```
     Your directory should look like:
     ```
     cache_data/
-    ├── intfold_v0.1.0.pt
+    ├── intellifold_v0.1.0.pt
     ├── ccd.pkl
     ├── unique_protein_sequences.fasta
     ├── unique_nucleic_acid_sequences.fasta

assets/intfold-cover.png renamed to assets/intellifold-cover.png

@@ -1,45 +1,45 @@
 ### Run with Command line
 
-If you set up `IntFold` by `pip`, you can run the following command to do model inference:
+If you set up `IntelliFold` by `pip`, you can run the following command to do model inference:
 
 ```bash
 
 # run with example yaml, which contains precomputed msa files(.a3m or .csv). the default seed is 42.
 ## a3m MSA file type
-intfold predict ./examples/5S8I_A.yaml --out_dir ./output 
+intellifold predict ./examples/5S8I_A.yaml --out_dir ./output 
 ## csv MSA file type
-intfold predict ./examples/7yds.yaml --out_dir ./output 
+intellifold predict ./examples/7yds.yaml --out_dir ./output 
 
 # Predict with a directory of YAMLs
-intfold predict ./examples --out_dir ./output
+intellifold predict ./examples --out_dir ./output
 
 # run with 5 seeds(mutiple seeds are splited them by comma) and 5 samples (the default parameters for AlphaFold3).
-intfold predict ./examples/5S8I_A.yaml --seed 42,43,44,45,46 --num_diffusion_samples 5 --out_dir ./output
+intellifold predict ./examples/5S8I_A.yaml --seed 42,43,44,45,46 --num_diffusion_samples 5 --out_dir ./output
 
 # if the input yaml file do not contain precomputed msa paths, you can set --use_msa_server to search msa(need internet connection and would take some time) 
 # and use greedy msa pairing strategy
 # and then predict
-intfold predict examples/examples_wo_msa/example_without_msa.yaml --out_dir ./output --seed 42,66 --use_msa_server --msa_pairing_strategy greedy
+intellifold predict examples/examples_wo_msa/example_without_msa.yaml --out_dir ./output --seed 42,66 --use_msa_server --msa_pairing_strategy greedy
 
 # only run the data processing step, and not run the model.
-intfold predict ./examples/5S8I_A.yaml --out_dir ./output --only_run_data_process
+intellifold predict ./examples/5S8I_A.yaml --out_dir ./output --only_run_data_process
 
 ```
 
 ### Run with Bash Script
 
-The aurguments is the same as `intfold predict`, and you can set the parameters in the script.
-you can get the help information by running `intfold predict --help` or `python run_intfold.py --help`
+The aurguments is the same as `intellifold predict`, and you can set the parameters in the script.
+you can get the help information by running `intellifold predict --help` or `python run_intellifold.py --help`
 ```bash
 bash predict.sh
 ## or
-## python run_intfold.py ....
+## python run_intellifold.py ....
 ```
-Common arguments of this `scripts`/`intfold predict` are explained as follows:
+Common arguments of this `scripts`/`intellifold predict` are explained as follows:
 * `--out_dir` (`PATH`, default: `./`)  
   The path where to save the predictions.
-* `--cache` (`PATH`, default: `~/.intfold`)  
-  The directory where to download the data and model. Will use environment variable `INTFOLD_CACHE` as an absolute path if set.
+* `--cache` (`PATH`, default: `~/.intellifold`)  
+  The directory where to download the data and model. Will use environment variable `INTELLIFOLD_CACHE` as an absolute path if set.
 * `--num_workers` (`INTEGER`, default: `4`)  
   The number of dataloader workers to use for prediction.
 * `--precision` (`str`, default: `bf16`)  

assets/intfold-server-screenshot.png renamed to assets/intellifold-server-screenshot.png

@@ -1,4 +1,4 @@
-name: intfold
+name: intellifold
 channels:
   - bioconda
   - conda-forge