Better requirements + rename command to chai-lab

.devcontainer/devcontainer.json

@@ -17,7 +17,8 @@
         "--memory=1000g"
     ],
     "shutdownAction": "none",
-    "postCreateCommand": "uv pip install -e . && pre-commit install -f",
+    // This contains a separate requirements file for devcontainer specific packages e.g. ruff
+    "postCreateCommand": "uv pip install -e . && uv pip install -r requirements.dev && pre-commit install -f",
     "customizations": {
         "vscode": {
             "settings": {

.github/workflows/pytest.yml

@@ -23,5 +23,6 @@ jobs:
           # install requirements, except torch and potentially nvidia-related stuff
           uv pip install --system -r <( cat requirements.in | grep -v nvidia | grep -v torch )
           uv pip install --system --no-deps -e .
+          uv pip install -r requirements.dev
       - name: Run pytest
         run: pytest ./tests/

.github/workflows/ruff.yml

@@ -18,7 +18,7 @@ jobs:
           python-version: "3.10"
           cache: "pip"
       - name: Install
-        run: pip install pre-commit
+        run: pip install -r requirements.dev
       - name: Run pre-commit checks on all files
         # run specific ruff pre-commit hooks on all files
         run: >

README.md

@@ -26,21 +26,21 @@ This Python package requires Linux, and a GPU with CUDA and bfloat16 support. We
 
 You can fold a FASTA file containing all the sequences (including modified residues, nucleotides, and ligands as SMILES strings) in a complex of interest by calling:
 ```shell
-chai fold input.fasta output_folder
+chai-lab fold input.fasta output_folder
 ```
 
-By default, the model generates five sample predictions, and uses embeddings without MSAs or templates. For additional information about how to supply MSAs, templates, and restraints to the model, see the documentation below, or run `chai fold --help`.
+By default, the model generates five sample predictions, and uses embeddings without MSAs or templates. For additional information about how to supply MSAs, templates, and restraints to the model, see the documentation below, or run `chai-lab fold --help`.
 
 For example, to run the model with MSAs (which we recommend for improved performance), pass the `--use-msa-server` and `--use-templates-server` flags:
 
 ```shell
-chai fold --use-msa-server --use-templates-server input.fasta output_folder
+chai-lab fold --use-msa-server --use-templates-server input.fasta output_folder
 ```
 
 If you are hosting your own ColabFold server, additionally pass the `--msa-server` flag with your server:
 
 ```shell
-chai fold --use-msa-server --msa-server-url "https://api.internalcolabserver.com" input.fasta output_folder
+chai-lab fold --use-msa-server --msa-server-url "https://api.internalcolabserver.com" input.fasta output_folder
 ```
 
 We also provide additional utility functions for tasks such as MSA file format conversion; see `chai --help` for details.

examples/msas/README.md

@@ -61,7 +61,7 @@ aligned_pqt.head()
 
 ## Additional MSA generation strategies
 
-Multiple strategies can be used for generating MSAs. In our [technical report](https://chaiassets.com/chai-1/paper/technical_report_v1.pdf), we generated MSAs using [jackhmmer](https://github.com/EddyRivasLab/hmmer). Other algorithms such as [MMseqs2](https://github.com/soedinglab/MMseqs2) can also be used. In this vein, we provide support for automatic MSA generation via the [ColabFold](https://github.com/sokrypton/ColabFold) server using `chai fold input.fasta output_directory --msa-server` or by invoking `run_inference` as follows:
+Multiple strategies can be used for generating MSAs. In our [technical report](https://chaiassets.com/chai-1/paper/technical_report_v1.pdf), we generated MSAs using [jackhmmer](https://github.com/EddyRivasLab/hmmer). Other algorithms such as [MMseqs2](https://github.com/soedinglab/MMseqs2) can also be used. In this vein, we provide support for automatic MSA generation via the [ColabFold](https://github.com/sokrypton/ColabFold) server using `chai-lab fold input.fasta output_directory --msa-server` or by invoking `run_inference` as follows:
 
 ```python
 candidates = run_inference(

pyproject.toml

@@ -71,4 +71,4 @@ exclude = [
 # should use packages from sdist section
 
 [project.scripts]
-chai = "chai_lab.main:cli"
+chai-lab = "chai_lab.main:cli"

requirements.dev

@@ -0,0 +1,6 @@
+# dev-deps
+pre-commit
+ruff==0.6.3 # in sync with pre-commit-hook
+mypy
+pytest
+ipykernel~=6.27 # needed by vs code to run notebooks in devcontainer

requirements.in

@@ -1,9 +1,3 @@
-# dev-deps, still placed in the same requirements file
-ruff==0.6.3 # in sync with pre-commit-hook
-mypy
-pytest
-pre-commit
-
 # types/stubs are required by mypy
 pandas-stubs
 types-pyyaml
@@ -15,8 +9,6 @@ types-requests
 typer~=0.12        # CLI generator
 # pydantic~=2.5      # serialization/deserialization of configs
 
-# notebooks, plotting
-ipykernel~=6.27    # needed by vs code to run notebooks in devcontainer
 # seaborn
 matplotlib