From 200a0397f8f53ee04fa2d9554a6d964594ea900d Mon Sep 17 00:00:00 2001 From: ChrisGadek1 Date: Tue, 7 Jul 2026 18:17:22 +0200 Subject: [PATCH 1/2] Add initial HTML documentation for FRIdata with styling and structure --- docs/index.html | 226 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 226 insertions(+) create mode 100644 docs/index.html diff --git a/docs/index.html b/docs/index.html new file mode 100644 index 0000000..74bedd3 --- /dev/null +++ b/docs/index.html @@ -0,0 +1,226 @@ + + + + + + FRIdata + + + + +
+

FRIdata

+

High-performance protein structure data processing with Dask

+
+ License + Python + CI + Dask +
+
+ View on GitHub + Issues +
+
+ +
+ +
+
+

Purpose

+

Generate sequences, coordinates, distograms, and embeddings from protein structures at scale.

+
+
+

Backend

+

Built on Dask for distributed, parallel processing on CPU and GPU clusters.

+
+
+

HPC Ready

+

Comes with SLURM scripts for PLGrid infrastructure. Supports AlphaFold DB (AFDB) structures.

+
+
+ +
+

Quick Start

+
    +
  1. Clone the repository + 
    git clone https://github.com/Tomasz-Lab/FRIdata.git
+cd FRIdata
    +
    2. +
  2. Install Miniconda, then install mamba: + 
    conda config --add channels conda-forge
+conda update -n base --all
+conda install -n base mamba
    +
    3. +
  3. Create and activate the environment + 
    mamba create -f toolbox_env_conda.yml
+eval "$(mamba shell hook --shell bash)"
+mamba activate tbe
    +
    4. +
+
+ +
+

Running on AFDB Structures

+ 
FRIDATA_PATH="<repository path>"
+AFDB_PATH="<AFDB structures directory>"
+IDS_PATH="<AFDB IDs file>"
+EMBEDDER_TYPE=esm2_t33_650M_UR50D
+
+# macOS: fix for OpenMP multiple runtime error
+export KMP_DUPLICATE_LIB_OK=TRUE
+
+PYTHONPATH='.' python3 -u fridata.py generate_data \
+  -t sequences,coordinates,distograms,embeddings \
+  -d AFDB -c subset --version test \
+  -i ${IDS_PATH} --input-path ${AFDB_PATH} \
+  -e ${EMBEDDER_TYPE}
+
+ +
+

CLI Usage

+ 
python3 -m pip install -e .
+fridata <...>
+
+ +
+

HPC (PLGrid / SLURM)

+

Set required environment variables (DEEPFRI_PATH, IDS_PATH, AFDB_PATH, DATA_PATH), then:

+ 
# CPU nodes
+sbatch --cpus-per-task=<cpus> --time=<HH:MM:SS> --nodes=<n> \
+  --account=<grant> scripts/hpc/run_slurm.sh sequences,coordinates
+
+# GPU nodes
+sbatch --gres=gpu --time=<HH:MM:SS> --account=<grant> \
+  --partition=<partition> --cpus-per-task=<cpus> \
+  scripts/hpc/run_slurm.sh embeddings
+
+ +
+

Tests

+ 
pytest ./tests
+
+ +
+ + + + + From ddfd8fe467785ab243d63c13df7b0e44a4454744 Mon Sep 17 00:00:00 2001 From: ChrisGadek1 Date: Tue, 7 Jul 2026 19:14:53 +0200 Subject: [PATCH 2/2] Enhance HTML documentation layout and structure with responsive design and detailed sections for installation, usage, and troubleshooting --- docs/index.html | 602 +++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 564 insertions(+), 38 deletions(-) diff --git a/docs/index.html b/docs/index.html index 74bedd3..a5ad5f5 100644 --- a/docs/index.html +++ b/docs/index.html @@ -42,10 +42,13 @@ .badges img { height: 20px; } main { - max-width: 860px; + width: 75%; margin: 2.5rem auto; padding: 0 1.5rem; } + @media (max-width: 768px) { + main { width: 90%; } + } .cards { display: grid; @@ -68,15 +71,76 @@ } .card p { font-size: 0.95rem; color: #c9d1d9; } - section { margin-bottom: 2.5rem; } - section h2 { + details.section { + margin-bottom: 1rem; + background: #0f141a; + border: 1px solid #30363d; + border-radius: 8px; + overflow: hidden; + } + details.section > summary { font-size: 1.25rem; font-weight: 600; color: #e6edf3; - border-bottom: 1px solid #30363d; - padding-bottom: 0.4rem; - margin-bottom: 1rem; + padding: 1rem 1.4rem; + cursor: pointer; + list-style: none; + display: flex; + align-items: center; + gap: 0.6rem; + user-select: none; + } + details.section > summary::-webkit-details-marker { display: none; } + details.section > summary::before { + content: ""; + width: 0.5rem; + height: 0.5rem; + border-right: 2px solid #8b949e; + border-bottom: 2px solid #8b949e; + transform: rotate(-45deg); + transition: transform 0.15s ease; + flex-shrink: 0; } + details.section[open] > summary::before { transform: rotate(45deg); } + details.section > summary:hover { color: #58a6ff; } + details.section > summary:hover::before { border-color: #58a6ff; } + details.section .section-body { padding: 0 1.4rem 1.4rem; } + + details.subcmd { + background: #161b22; + border: 1px solid #30363d; + border-radius: 6px; + overflow: hidden; + margin-bottom: 0.6rem; + } + details.subcmd > summary { + padding: 0.65rem 1rem; + cursor: pointer; + list-style: none; + display: flex; + align-items: center; + gap: 0.55rem; + user-select: none; + font-family: "SFMono-Regular", Consolas, "Liberation Mono", monospace; + font-size: 0.92rem; + color: #e6edf3; + } + details.subcmd > summary::-webkit-details-marker { display: none; } + details.subcmd > summary::before { + content: ""; + width: 0.42rem; + height: 0.42rem; + border-right: 2px solid #8b949e; + border-bottom: 2px solid #8b949e; + transform: rotate(-45deg); + transition: transform 0.15s ease; + flex-shrink: 0; + } + details.subcmd[open] > summary::before { transform: rotate(45deg); } + details.subcmd > summary:hover { color: #58a6ff; } + details.subcmd > summary:hover::before { border-color: #58a6ff; } + details.subcmd > pre { margin: 0 1rem 1rem; } + ol, ul { padding-left: 1.4rem; } li { margin-bottom: 0.4rem; } @@ -91,6 +155,34 @@ margin: 0.75rem 0; } code { font-family: "SFMono-Regular", Consolas, "Liberation Mono", monospace; } + p code, li code, td code { + background: #161b22; + border: 1px solid #30363d; + border-radius: 4px; + padding: 0.1rem 0.35rem; + font-size: 0.85em; + } + + .table-wrap { overflow-x: auto; margin: 0.75rem 0; } + table { + border-collapse: collapse; + width: 100%; + font-size: 0.9rem; + } + th, td { + text-align: left; + padding: 0.55rem 0.8rem; + border: 1px solid #30363d; + vertical-align: top; + } + th { + background: #161b22; + color: #e6edf3; + font-weight: 600; + white-space: nowrap; + } + td:first-child { white-space: nowrap; } + tbody tr:nth-child(even) { background: #12171e; } .btn { display: inline-block; @@ -154,66 +246,500 @@

HPC Ready

-
-

Quick Start

+
+ Installation & Activation +
  1. Clone the repository 
    git clone https://github.com/Tomasz-Lab/FRIdata.git
 cd FRIdata
  2. Install Miniconda, then install mamba: - 
    conda config --add channels conda-forge
+        
    # prioritize the conda-forge channel
+conda config --add channels conda-forge
 conda update -n base --all
 conda install -n base mamba
    3. -
  3. Create and activate the environment - 
    mamba create -f toolbox_env_conda.yml
-eval "$(mamba shell hook --shell bash)"
-mamba activate tbe
    +
  4. Create the environment (recommended). The setup script creates the conda + environment, installs the pip dependencies, and installs a PyTorch build + matched to your GPU driver: + 
    # default install
+./scripts/setup_env.sh
+
+# custom environment name
+./scripts/setup_env.sh -n fridata_gpu_verify
+
+# CPU-only systems
+./scripts/setup_env.sh --cpu
    +
    5. +
  5. Activate the environment + 
    # shell type is one of: bash, cmd.exe, dash, fish, nu, posix, powershell, tcsh, xonsh, zsh
+eval "$(mamba shell hook --shell <shell type>)"
+mamba activate fridata_env
    +
    6. +
  6. (Optional) Run tests to verify the installation + 
    pytest ./tests
-
-
-

Running on AFDB Structures

+

Manual installation — if you prefer to run the steps yourself:

+ 
mamba env create -f fridata_env_conda.yml -n fridata_env
+mamba run -n fridata_env python -m pip install -r requirements-fridata.txt
+./scripts/install_pytorch.sh
+

Pip dependencies live in requirements-fridata.txt rather than + fridata_env_conda.yml so environment creation works from read-only + repository checkouts.

+ +

Troubleshooting — if you see + Error opening for writing ".../mambaf..." while creating the + environment, libmamba is trying to write a temporary pip requirements file next + to the environment YAML. Use ./scripts/setup_env.sh instead, or + ensure the directory containing fridata_env_conda.yml is writable.

+ + + +
+ Running on AFDB Structures Locally +
+

Requires a directory of AFDB structures and a text file listing AFDB IDs (one + per line, \n delimited). Assumes the installation steps above succeeded.

FRIDATA_PATH="<repository path>"
-AFDB_PATH="<AFDB structures directory>"
-IDS_PATH="<AFDB IDs file>"
+AFDB_PATH="<AFDB structures directory path>"
+IDS_PATH="<AFDB IDs file path>"
+
+cd ${FRIDATA_PATH}
+
 EMBEDDER_TYPE=esm2_t33_650M_UR50D
 
-# macOS: fix for OpenMP multiple runtime error
+# (macOS only) fix for OpenMP multiple runtime error
 export KMP_DUPLICATE_LIB_OK=TRUE
 
-PYTHONPATH='.' python3 -u fridata.py generate_data \
+PYTHONPATH='.' python3 -u ${FRIDATA_PATH}/fridata.py \
+  generate_data \
   -t sequences,coordinates,distograms,embeddings \
-  -d AFDB -c subset --version test \
-  -i ${IDS_PATH} --input-path ${AFDB_PATH} \
+  -d AFDB \
+  -c subset \
+  --version test \
+  -i ${IDS_PATH} \
+  --input-path ${AFDB_PATH} \
   -e ${EMBEDDER_TYPE}
-
+

For subset runs with --input-path, new datasets store canonical keys + as {line_from_ids_file}_{chain} (for example A0A2K6V5L6_A), + not the full AlphaFold CIF filename stem. The dataset's + input_structures.idx maps each canonical key to the source structure + filename. Older datasets created before this convention may still use long + AF-style keys.

+ + -
-

CLI Usage

+
+ Running as a CLI Tool +
+

From the FRIdata directory, install it as a CLI tool:

python3 -m pip install -e .
+
+# now available as
 fridata <...>
-
+

Use ids_file tokens (e.g. plain UniProt) plus chain as the canonical + dataset index keys.

+ + + +
+ Running on HPC (PLGrid / SLURM) +
+

Running FRIdata on HPC differs between CPU and GPU nodes. These instructions are + valid for HPC hosted in PLGrid infrastructure; other infrastructures may require + additional adjustments.

+ +

Prerequisites:

+
    +
  • An active grant valid on the HPC
    • +
  • Loaded modules: miniconda3 and gcc
    • +
  • Mandatory environment variables (ideally set in .bashrc): +
      +
    • DEEPFRI_PATH — parent directory of this repo
      • +
    • IDS_PATH — text file with AFDB indexes listed
      • +
    • AFDB_PATH — path to AFDB structures (may be an empty + directory — structures will be fetched there)
      • +
    • DATA_PATH — parent directory of all generated output data
      • +
    +
    • +
  • Optional environment variables (with defaults): +
      +
    • COMMON_SLURM_PATH — defaults to $DEEPFRI_PATH/FRIdata/scripts/hpc/common_slurm.sh
      • +
    • LAUNCH_WORKER_SLURM_PATH — defaults to $DEEPFRI_PATH/FRIdata/scripts/hpc/launch_workers_slurm.sh
      • +
    • MEMORY_LIMIT — memory limit per Dask worker, defaults to 288GiB
      • +
    • IP_INTERFACE — network interface where Dask workers connect, defaults to ens1f0
      • +
    • CONDA_ENV_PATH — path to conda environment, defaults to $DEEPFRI_PATH/conda_dev
      • +
    +
    • +
+ +

Preperation steps:

+ 
# 1. Clone the repo
+git clone https://github.com/Tomasz-Lab/FRIdata.git
+cd FRIdata
+
+# 2. Update run permissions
+chmod u+x -R scripts/hpc/cpu
 
-  

-    
HPC (PLGrid / SLURM)

-    
Set required environment variables (DEEPFRI_PATH, IDS_PATH, AFDB_PATH, DATA_PATH), then:

+# 3. Initialize SLURM (add --cpu when running on a CPU cluster)
+./scripts/hpc/initialize_slurm.sh <path to .conda> [--cpu]
+ +

Then, schedule the sbatch script. Operations: sequences, + coordinates, embeddings, distograms.

# CPU nodes
-sbatch --cpus-per-task=<cpus> --time=<HH:MM:SS> --nodes=<n> \
-  --account=<grant> scripts/hpc/run_slurm.sh sequences,coordinates
+sbatch --cpus-per-task=<cpus> --time=<HH:MM:SS> --nodes=<nodes> \
+  --account=<grant name> scripts/hpc/run_slurm.sh sequences,coordinates
 
 # GPU nodes
-sbatch --gres=gpu --time=<HH:MM:SS> --account=<grant> \
-  --partition=<partition> --cpus-per-task=<cpus> \
+sbatch --gres=gpu[:gpu-number] --time=<HH:MM:SS> --account=<grant name> \
+  --nodes=1 --partition=<partition name> --cpus-per-task=<cpus> \
   scripts/hpc/run_slurm.sh embeddings
- +
+
+ +
+ Available Parameters +
+ +

FRIdata is organized into sub-commands. The most common is generate_data, + which creates a dataset and generates the requested data types in one run.

+ +

Sub-commands

+
+ + + + + + + + + + + + + + + + + + + +
CommandDescription
generate_dataCreate a dataset and generate sequences, coordinates, distograms and embeddings
create_datasetCreate a protein dataset only
generate_sequenceGenerate sequences from a dataset
generate_distogramsGenerate distograms from a dataset
generate_embeddingsGenerate embeddings from a dataset
read_distogramsRead distograms from a dataset
read_pdbsRead PDBs (print to terminal or extract with --to_directory)
verify_chainsVerify chains in a dataset
create_archiveBuild one merged PDB .zip from the dataset index
create_dashboardExport a single-file HTML report for dataset indexes
inspect_h5Inspect an .h5 file (tree, keys, structures, numeric dumps)
inspect_idxPretty-print an .idx (JSON) file
remove_datasetRemove all traces of a dataset
+
+ +

Dataset options

+
+ + + + + + + + + + + + + + + + + + + + + + + + +
FlagDescription
-p, --file-pathExisting dataset directory (with dataset.json) or path to dataset.json
-d, --dbDatabase type (see choices below)
-c, --collectionCollection type (see choices below)
-t, --typeComma-separated types to generate: dataset, sequences, coordinates, distograms, embeddings, or all (generate_data only)
-e, --embedderEmbedder type (see choices below)
-i, --idsFile with IDs used to create a subset
-s, --seqresFASTA file to use as the sequence source
--input-pathInput directory or archive (zip/tar.gz) of protein files (pdb/cif)
--archivePath to a tar.gz archive containing structure files
--proteomePrecise proteome of an AFDB part dataset
--versionString to differentiate datasets (default: current date)
-b, --batch-sizeBatch size
-o, --overwriteOverwrite existing files (default: false)
--binaryDownload binary CIF in the PDB database
--slurmUse the SLURM job scheduler
-v, --verboseEnable verbose logging
--log-filePath to a log file for file logging
--configPath to a config JSON file (default: ./config.json)
+
+ +

Choices

+
+ + + + + + + + + +
OptionAccepted values
-d, --dbPDB, AFDB, ESMatlas, other
-c, --collectionall, clust, part, subset
-e, --embedderesm2_t30_150M_UR50D, esm2_t33_650M_UR50D, esmc_300m, esmc_600m, gLM2_150M, gLM2_650M
+
+
+
+ +
+ Example usage +
+

Each sub-command below shows its --help output. Run + fridata <subcommand> --help to reproduce it.

+ +
+ generate_data + 
usage: fridata generate_data [-h] [--slurm] [-p FILE_PATH] [-d name] [-c name]
+                             [-t [name]] [--proteome [name]]
+                             [--version VERSION] [-i IDS] [-s SEQRES] [-o]
+                             [-b BATCH_SIZE] [--binary]
+                             [--input-path INPUT_PATH] [--archive ARCHIVE]
+                             [-v] [-e name]
+
+options:
+  -h, --help            show this help message and exit
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+                        Existing dataset directory (with dataset.json) or path
+                        to dataset.json
+  -d name, --db name    Database Types: PDB AFDB ESMatlas other
+  -c name, --collection name
+                        Collection Types: all clust part subset
+  -t [name], --type [name]
+                        Comma-separated types to generate: dataset, sequences,
+                        coordinates, distograms, embeddings; or 'all'. For
+                        generate_data only; ignored by create_dataset.
+  --proteome [name]     Precise proteome of AFDB part dataset
+  --version VERSION     String to differentiate datasets; default: current
+                        date
+  -i IDS, --ids IDS     File with ids to create subset
+  -s SEQRES, --seqres SEQRES
+                        fasta file to use as sequence source
+  -o, --overwrite       Should overwrite existing files? Default - false
+  -b BATCH_SIZE, --batch-size BATCH_SIZE
+  --binary              Download binary CIF in PDB db
+  --input-path INPUT_PATH
+                        Path to input directory or archive (zip/tar.gz) with
+                        protein files (pdb/cif)
+  --archive ARCHIVE     Path to tar.gz archive containing structure files
+  -v, --verbose         Enable verbose logging mode
+  -e name, --embedder name
+                        Embedder Types: esm2_t30_150M_UR50D
+                        esm2_t33_650M_UR50D esmc_300m esmc_600m gLM2_150M
+                        gLM2_650M
+
+ +
+ create_dataset + 
usage: fridata create_dataset [-h] [--slurm] -d name -c name [-t [name]]
+                              [--proteome [name]] [--version VERSION] [-i IDS]
+                              [-s SEQRES] [-o] [-b BATCH_SIZE] [--binary]
+                              [--input-path INPUT_PATH] [--archive ARCHIVE]
+                              [-v] [-e name]
+
+options:
+  -h, --help            show this help message and exit
+  --slurm               Use SLURM job scheduler
+  -d name, --db name    Database Types: PDB AFDB ESMatlas other
+  -c name, --collection name
+                        Collection Types: all clust part subset
+  -t [name], --type [name]
+                        Comma-separated types to generate: dataset, sequences,
+                        coordinates, distograms, embeddings; or 'all'. For
+                        generate_data only; ignored by create_dataset.
+  --proteome [name]     Precise proteome of AFDB part dataset
+  --version VERSION     String to differentiate datasets; default: current
+                        date
+  -i IDS, --ids IDS     File with ids to create subset
+  -s SEQRES, --seqres SEQRES
+                        fasta file to use as sequence source
+  -o, --overwrite       Should overwrite existing files? Default - false
+  -b BATCH_SIZE, --batch-size BATCH_SIZE
+  --binary              Download binary CIF in PDB db
+  --input-path INPUT_PATH
+                        Path to input directory or archive (zip/tar.gz) with
+                        protein files (pdb/cif)
+  --archive ARCHIVE     Path to tar.gz archive containing structure files
+  -v, --verbose         Enable verbose logging mode
+  -e name, --embedder name
+                        Embedder Types: esm2_t30_150M_UR50D
+                        esm2_t33_650M_UR50D esmc_300m esmc_600m gLM2_150M
+                        gLM2_650M
+
+ +
+ generate_sequence + 
usage: fridata generate_sequence [-h] [--slurm] -p FILE_PATH [-v]
+                                 [--log-file LOG_FILE] [--ca_mask]
+                                 [--no_substitution]
+
+options:
+  -h, --help            show this help message and exit
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+  -v, --verbose         Enable verbose logging
+  --log-file LOG_FILE   Path to log file for file logging
+  --ca_mask             Require a carbon alpha atom to include an amino acid
+                        in a sequence
+  --no_substitution     Don't substitute non standard amino acids
+
+ +
+ generate_distograms + 
usage: fridata generate_distograms [-h] [--slurm] -p FILE_PATH [-v]
+                                   [--log-file LOG_FILE]
+
+options:
+  -h, --help            show this help message and exit
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+  -v, --verbose         Enable verbose logging
+  --log-file LOG_FILE   Path to log file for file logging
+
-
-

Tests

- 
pytest ./tests
-
+
+ generate_embeddings + 
usage: fridata generate_embeddings [-h] [--slurm] -p FILE_PATH [-v]
+                                   [--log-file LOG_FILE] -e name
+
+options:
+  -h, --help            show this help message and exit
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+  -v, --verbose         Enable verbose logging
+  --log-file LOG_FILE   Path to log file for file logging
+  -e name, --embedder name
+                        Embedder Types: esm2_t30_150M_UR50D
+                        esm2_t33_650M_UR50D esmc_300m esmc_600m gLM2_150M
+                        gLM2_650M
+
+ +
+ read_distograms + 
usage: fridata read_distograms [-h] [--slurm] -p FILE_PATH [-v]
+                               [--log-file LOG_FILE]
+
+options:
+  -h, --help            show this help message and exit
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+  -v, --verbose         Enable verbose logging
+  --log-file LOG_FILE   Path to log file for file logging
+
+ +
+ read_pdbs + 
usage: fridata read_pdbs [-h] [--print] [--to_directory TO_DIRECTORY] [-i IDS]
+                         [--slurm] -p FILE_PATH [-v] [--log-file LOG_FILE]
+
+options:
+  -h, --help            show this help message and exit
+  --print               Print PDB files to the terminal
+  --to_directory TO_DIRECTORY
+                        Extract PDB files to the provided directory
+  -i IDS, --ids IDS     File with ids to extract
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+  -v, --verbose         Enable verbose logging
+  --log-file LOG_FILE   Path to log file for file logging
+
+ +
+ verify_chains + 
usage: fridata verify_chains [-h] [--slurm] -p FILE_PATH [-v]
+                             [--log-file LOG_FILE]
+
+options:
+  -h, --help            show this help message and exit
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+  -v, --verbose         Enable verbose logging
+  --log-file LOG_FILE   Path to log file for file logging
+
+ +
+ create_archive + 
usage: fridata create_archive [-h] [--keep-shard-zips] [--slurm] -p FILE_PATH
+                              [-v] [--log-file LOG_FILE]
+
+options:
+  -h, --help            show this help message and exit
+  --keep-shard-zips     Keep per-shard zip files under _staging/ after merge
+                        (default: remove staging)
+  --slurm               Use SLURM job scheduler
+  -p FILE_PATH, --file-path FILE_PATH
+  -v, --verbose         Enable verbose logging
+  --log-file LOG_FILE   Path to log file for file logging
+
+Working directory: a `mate` helper (if you use it) often cd's into deepFRI2-toolbox-dev; after that, pass an absolute -p/--file-path to the dataset directory (the folder containing dataset.json), or cd to <data_path>/datasets first if you want to use a short folder name.
+Invocation: run `python fridata.py create_archive ...` from the repo unless fridata.py is installed on PATH.
+
+ +
+ create_dashboard + 
usage: fridata create_dashboard [-h] [--root ROOT] [--index-types INDEX_TYPES]
+                                [--output-dir OUTPUT_DIR]
+                                dataset
+
+positional arguments:
+  dataset               Dataset: filesystem path (directory or dataset.json),
+                        slug (folder suffix after --), or full folder name
+                        under --root when not an existing path
+
+options:
+  -h, --help            show this help message and exit
+  --root ROOT           Override datasets root (default: <data_path>/datasets)
+  --index-types INDEX_TYPES
+                        Comma-separated index types
+                        (dataset,sequences,coordinates,embeddings,distograms)
+                        or 'all'
+  --output-dir OUTPUT_DIR
+                        Output directory for reports (default:
+                        <repo_root>/reports)
+
+ +
+ inspect_h5 + 
usage: fridata inspect_h5 [-h]
+                          [--mode {preview,structures,keys,distograms,coordinates,embeddings}]
+                          [--name KEYS] [--save [FILEPATH]]
+                          file
+
+positional arguments:
+  file                  Path to h5 file
+
+options:
+  -h, --help            show this help message and exit
+  --mode {preview,structures,keys,distograms,coordinates,embeddings}
+                        preview: H5 tree; keys: id list; structures: full PDB
+                        text (files group); distograms|coordinates|embeddings:
+                        numeric preview (or full dump with --name)
+  --name KEYS           Comma-separated protein keys. Only with --mode
+                        structures|distograms|coordinates|embeddings. For
+                        numeric modes, emits a full array dump. Use inspect_h5
+                        --mode keys to list keys.
+  --save [FILEPATH]     Write output to a file instead of vi. Omit FILEPATH to
+                        write a persistent temp file and print its path.
+
+ +
+ inspect_idx + 
usage: fridata inspect_idx [-h] file
+
+positional arguments:
+  file        Path to idx file
+
+options:
+  -h, --help  show this help message and exit
+
+ +
+ remove_dataset + 
usage: fridata remove_dataset [-h] name
+
+positional arguments:
+  name        Dataset name (e.g. AFDB-subset--20250609_1333)
+
+options:
+  -h, --help  show this help message and exit
+
+
+