Add files using upload-large-folder tool

MODEL_FILE_MANIFEST.tsv

@@ -0,0 +1,13 @@
+file	size_bytes	sha256	package_path
+boltz1_conf.ckpt	3595352714	fea245d912c570ec117b2277c2719f312a6fc109c07b6f6ef741690ee775c2f5	weight/boltz1_conf.ckpt
+ccd.pkl	345859128	2d3b2f03a3c5665944adba51e33263511e51b21c9cd05d902f9c4b7c1e58d2f4	weight/ccd.pkl
+plddt.ckpt	462812900	cb32fa9cdc9e80406b793a8c09a929077534d9991a1d08f4c159d2e4ed81315f	weight/plddt.ckpt
+plddt_module_1.6B.ckpt	462812900	cb32fa9cdc9e80406b793a8c09a929077534d9991a1d08f4c159d2e4ed81315f	weight/plddt_module_1.6B.ckpt
+simplefold_1.1B.ckpt	4469540038	27b02b5939e995c7dca72c31bca87451de803c5f7defeba3915854767d8f116f	weight/simplefold_1.1B.ckpt
+simplefold_1.6B.ckpt	6354525226	aaac2d73dcc59c61153c58a1d56e74a8ada9d6057d67000f7836f3c87325312b	weight/simplefold_1.6B.ckpt
+simplefold_100M.ckpt	386772550	4cd0b8a0b317a6ab8634444fffd78ce84cfd49c20fe927b83c76c36fda5f54bd	weight/simplefold_100M.ckpt
+simplefold_360M.ckpt	1454881694	517338ec36b10ecc774f36b592ffe0fee6a24fa5c7d2fcfa3e3009282d48a49b	weight/simplefold_360M.ckpt
+simplefold_3B.ckpt	11460066894	88d4c7a240bf3815cb35342b4ddc1128ac243a2ea0256eb8a4df1209125868b5	weight/simplefold_3B.ckpt
+simplefold_700M.ckpt	2764152946	77a770e2dd1695397ab5943d5b31c99b9039b8a35ed86db12f2b2db1be9db7f8	weight/simplefold_700M.ckpt
+esm_models/esm2_t36_3B_UR50D.pt	5678116398	7de8b4082ba15891959ab368b77ce3886697af1efb16d3c9e9e7b0c5d3f07500	weight/esm_models/esm2_t36_3B_UR50D.pt
+esm_models/esm2_t36_3B_UR50D-contact-regression.pt	6759	4da500eab246481dc9c8c95bc7b1d02f2803d761c380b0e95186d4a07d0fc84e	weight/esm_models/esm2_t36_3B_UR50D-contact-regression.pt

README.md

@@ -0,0 +1,164 @@
+---
+license: mit
+language:
+- en
+- zh
+tags:
+- OneScience
+- protein-structure-prediction
+- pytorch
+---
+<p align="center">
+  <strong>
+    <span style="font-size: 30px;">SimpleFold</span>
+  </strong>
+</p>
+
+# Model Introduction
+
+SimpleFold is a generative protein folding model released by Apple. It supports protein structure prediction and provides training and fine-tuning entry points.
+
+# Model Description
+
+SimpleFold uses standard Transformer layers and a flow-matching objective to predict three-dimensional protein structures from FASTA sequences.
+
+This Hugging Face package includes a default FASTA example, SimpleFold weights, pLDDT weights, CCD auxiliary files, Boltz auxiliary weights, and local ESM-2 3B weights. The package is ready to use once the full download is complete.
+
+# Use Cases
+
+| Scenario | Description |
+| :---: | :--- |
+| Protein structure prediction | Takes a FASTA file as input and outputs structures in mmCIF or PDB format. |
+| Local offline inference | Stores example inputs and weights in `examples/` and `weight/`, allowing the scripts to run entirely from files in this repository. |
+| Training / fine-tuning pipeline validation | Supports training workflow validation after tokenized data have been prepared according to `config/data/*.yaml`. |
+| Hugging Face package layout | Uses the standard `config/`, `models/`, `scripts/`, and `weight/` directory structure. |
+
+# Usage Guide
+
+## 1. OneCode Usage
+
+Try one-click AI4S development in the OneCode online environment:
+
+[Try one-click AI4S development](https://web-2069360198568017922-iaaj.ksai.scnet.cn:58043/home)
+
+## 2. Manual Installation and Usage
+
+**Hardware Requirements**
+
+- GPU or DCU is recommended.
+- A CPU can be used for basic connectivity checks, but execution will be slow.
+- DCU users must install DTK in advance. DTK 25.04.2 or later is recommended, or a OneScience-recommended version matching the current cluster.
+
+**Software Requirements**
+
+For additional information about the adaptation, please contact liubiao@sugon.com.
+
+**Environment Check**
+
+- NVIDIA GPU:
+
+```bash
+nvidia-smi
+```
+
+- Hygon DCU:
+
+```bash
+hy-smi
+```
+
+## Quick Start
+
+### 1. Install the Runtime Environment
+
+```bash
+conda create -n onescience311 python=3.11 -y
+conda activate onescience311
+pip install onescience[bio] -i http://mirrors.onescience.ai:3141/pypi/simple/  --trusted-host mirrors.onescience.ai
+```
+
+If required libraries cannot be found, activate the CUDA compatibility environment as follows:
+
+```bash
+source ${ROCM_PATH}/cuda/env.sh
+export LD_LIBRARY_PATH="$CONDA_PREFIX/lib:$LD_LIBRARY_PATH"
+export LD_LIBRARY_PATH="$CONDA_PREFIX/lib/python3.11/site-packages/fastpt/torch/lib:$LD_LIBRARY_PATH"
+```
+
+### 2. Download the Model Package
+
+```bash
+hf download --model OneScience-Sugon/SimpleFold --local-dir ./SimpleFold
+cd SimpleFold
+```
+
+### Model Weights
+
+The trained model weights are included in the `weights/` directory, including SimpleFold-1B and SimpleFold-100M checkpoints, ESM weights, and other supporting weights.
+
+### 3. Run Inference
+
+```bash
+python scripts/run_inference.py \
+  --simplefold_model simplefold_100M \
+  --fasta_path examples/minimal.fasta \
+  --output_dir outputs/minimal_inference \
+  --num_steps 10 \
+  --tau 0.01 \
+  --nsample_per_protein 1 \
+  --backend torch
+```
+
+Output directory:
+
+```text
+outputs/minimal_inference/predictions_simplefold_100M/
+```
+
+### 4. Training — No Dataset Currently Provided
+
+Before training, prepare the following paths:
+
+```text
+datasets/
+datasets/tokenized/
+datasets/manifest.json
+```
+
+Data processing:
+
+```bash
+python scripts/process_data.py --data_dir /path/to/mmcif --out_dir datasets --num-processes 8
+python scripts/tokenize_data.py --target_dir datasets --token_dir datasets/tokenized
+```
+
+`process_data.py` uses the in-package `weight/ccd.pkl` by default; no additional CCD download or Redis setup is required. To use the legacy Redis CCD workflow, pass `--use-redis` explicitly.
+
+Training:
+
+```bash
+python scripts/train.py
+```
+
+FSDP training:
+
+```bash
+python scripts/train_fsdp.py experiment=train_fsdp
+```
+
+Fine-tuning / training-resumption example:
+
+```bash
+python scripts/train.py load_ckpt_path=weight/simplefold_100M.ckpt
+```
+
+# OneScience Official Information
+
+| Platform | OneScience Main Repository | Skills Repository |
+| --- | --- | --- |
+| Gitee | https://gitee.com/onescience-ai/onescience | https://gitee.com/onescience-ai/oneskills |
+| GitHub | https://github.com/onescience-ai/OneScience | https://github.com/onescience-ai/oneskills |
+
+# Citation & License
+
+The original SimpleFold implementation is released under the MIT License. This repository retains attribution to the original source and is organized to support automated execution through OneScience on Hugging Face. For scientific use, please cite the original SimpleFold paper and the relevant OneScience project materials.

config/base_eval.yaml

@@ -0,0 +1,15 @@
+# @package _global_
+defaults:
+  - data: cameo22
+  - model/architecture: foldingdit_100M
+  - model/sampler: euler_maruyama
+  - model: simplefold
+  - model/processor: protein_processor
+  - callbacks: default
+  - logger: null # set logger here or use command line (e.g. `python train.py logger=tensorboard`)
+  - trainer: default
+  - paths: default
+  - extras: default
+  - hydra: default
+  - _self_
+  - experiment: null

config/base_train.yaml

@@ -0,0 +1,31 @@
+# @package _global_
+
+# specify here default configuration
+# order of defaults determines the order in which configs override each other
+defaults:
+  - data: pdb
+  - model/architecture: foldingdit_100M
+  - model/sampler: euler_maruyama
+  - model/processor: protein_processor
+  - model: simplefold
+  - callbacks: default
+  - logger: null # set logger here or use command line (e.g. `python train.py logger=tensorboard`)
+  - trainer: default
+  - paths: default
+  - extras: default
+  - hydra: default
+  - _self_
+
+  # experiment configs allow for version control of specific hyperparameters
+  # e.g. best hyperparameters for given model and datamodule
+  - experiment: null
+
+# set False to skip model training
+train: True
+
+# evaluate on test set, using best model weights achieved during training
+# lightning chooses best weights based on the metric specified in checkpoint callback
+test: False
+
+# seed for random number generators in pytorch, numpy and python.random
+seed: null

config/data/codnas.yaml

@@ -0,0 +1,3 @@
+_target_: onescience.datapipes.simplefold.test_datamodule.SimpleFoldInferenceDataModule
+target_dir: data/codnas/
+num_workers: 1

config/data/pdb.yaml

@@ -0,0 +1,45 @@
+_target_: onescience.datapipes.simplefold.train_datamodule.SimpleFoldTrainingDataModule
+
+datasets:
+  - _target_: onescience.datapipes.simplefold.train_datamodule.DatasetConfig
+    data_name: rcsb_protein
+    tokenized_dir: ./datasets/tokenized
+    target_dir: ./datasets
+    manifest_path: ./datasets/manifest.json
+    cropper:
+      _target_: onescience.datapipes.boltz_data_pipeline.crop.boltz.BoltzCropper
+      min_neighborhood: 0
+      max_neighborhood: 40
+    filters:
+      - _target_: onescience.datapipes.boltz_data_pipeline.filter.dynamic.resolution.ResolutionFilter
+        resolution: 5.0
+      - _target_: onescience.datapipes.boltz_data_pipeline.filter.dynamic.date.DateFilter
+        date: "2027-05-01"
+        ref: released
+
+filters:
+    - _target_: onescience.datapipes.boltz_data_pipeline.filter.dynamic.size.SizeFilter
+      min_chains: 1
+      max_chains: 300
+
+tokenizer:
+  _target_: onescience.datapipes.boltz_data_pipeline.tokenize.boltz_protein.BoltzTokenizer
+
+featurizer:
+  _target_: onescience.datapipes.boltz_data_pipeline.feature.featurizer.BoltzFeaturizer
+
+symmetries: data/symmetry.pkl
+max_tokens: 256
+max_atoms: 2304
+pad_to_max_tokens: False
+pad_to_max_atoms: False
+batch_size: 256
+num_workers: 16
+pin_memory: True
+return_train_symmetries: False
+min_dist: 2.0
+max_dist: 22.0
+num_bins: 64
+atoms_per_window_queries: 32
+rotation_augment_ref_pos: False
+rotation_augment_coords: True

config/train.yaml

@@ -0,0 +1,31 @@
+# @package _global_
+
+# specify here default configuration
+# order of defaults determines the order in which configs override each other
+defaults:
+  - data: pdb_sp
+  - model/architecture: foldingdit_100M
+  - model/sampler: euler_maruyama
+  - model/processor: protein_processor
+  - model: simplefold
+  - callbacks: default
+  - logger: tensorboard # set logger here or use command line (e.g. `python train.py logger=tensorboard`)
+  - trainer: default
+  - paths: default
+  - extras: default
+  - hydra: default
+  - _self_
+
+  # experiment configs allow for version control of specific hyperparameters
+  # e.g. best hyperparameters for given model and datamodule
+  - experiment: null
+
+# set False to skip model training
+train: True
+
+# evaluate on test set, using best model weights achieved during training
+# lightning chooses best weights based on the metric specified in checkpoint callback
+test: False
+
+# seed for random number generators in pytorch, numpy and python.random
+seed: null

weight/simplefold_1.1B.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b02b5939e995c7dca72c31bca87451de803c5f7defeba3915854767d8f116f
+size 4469540038

weight/simplefold_1.6B.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaac2d73dcc59c61153c58a1d56e74a8ada9d6057d67000f7836f3c87325312b
+size 6354525226

weight/simplefold_360M.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517338ec36b10ecc774f36b592ffe0fee6a24fa5c7d2fcfa3e3009282d48a49b
+size 1454881694

weight/simplefold_3B.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d4c7a240bf3815cb35342b4ddc1128ac243a2ea0256eb8a4df1209125868b5
+size 11460066894