🧬 BioReason-ProAdvancing Protein Function Prediction withMultimodal Biological Reasoning
0
3 commits
1 linked in READMEs
updated Aug 19, 2026
Precomputed text embeddings for 43,248 Gene Ontology terms, one per term, produced
with Qwen/Qwen3-Embedding-4B over the
GO term name and definition.
BioReason-Pro's GO graph encoder (a 3-layer GAT over go-basic.obo) is initialised from
these vectors rather than learning term representations from scratch. They are required
for training, evaluation, and checkpoint conversion — passed as --precomputed_embeddings_path.
git clone https://github.com/bowang-lab/BioReason-Pro.git && cd BioReason-Pro
pip install -e .
python scripts/download_assets.py --dest /data/bioreason --skip-structures
# -> /data/bioreason/go_embeddings (pass as GO_EMBEDDINGS_PATH)
A single go_embeddings.tar.gz that extracts to a flat directory:
go_embeddings/
GO_0000001.safetensors
GO_0000002.safetensors
... # 43,248 files, 338 MB extracted
Each file holds one tensor of dimension 2560 under the key embedding.
These vectors can be rebuilt from scratch, though downloading is strongly preferred — regenerating on a different model revision produces different vectors and will not match the released checkpoints:
python -m bioreason2.utils.go_embed \
--model_name Qwen/Qwen3-Embedding-4B \
--output_dir /data/bioreason/go_embeddings \
--batch_size 32 --device cuda
If you find this work useful, please cite our papers:
@article {Fallahpour2026.03.19.712954,
author = {Fallahpour, Adibvafa and Seyed-Ahmadi, Arman and Idehpour, Parsa and Ibrahim, Omar and Gupta, Purav and Naimer, Jack and Zhu, Kevin and Shah, Arnav and Ma, Shihao and Adduri, Abhinav and G{\"u}loglu, Talu and Liu, Nuo and Cui, Haotian and Jain, Arihant and de Castro, Max and Fallahpour, Amirfaham and Cembellin-Prieto, Antonio and Stiles, John S. and Nem{\v c}ko, Filip and Nevue, Alexander A. and Moon, Hyungseok C. and Sosnick, Lucas and Markham, Olivia and Duan, Haonan and Lee, Michelle Y. Y. and Salvador, Andrea F. M. and Maddison, Chris J. and Thaiss, Christoph A. and Ricci-Tam, Chiara and Plosky, Brian S. and Burke, Dave P. and Hsu, Patrick D. and Goodarzi, Hani and Wang, Bo},
title = {BioReason-Pro: Advancing Protein Function Prediction with Multimodal Biological Reasoning},
elocation-id = {2026.03.19.712954},
year = {2026},
doi = {10.64898/2026.03.19.712954},
publisher = {Cold Spring Harbor Laboratory},
URL = {https://www.biorxiv.org/content/early/2026/03/20/2026.03.19.712954},
eprint = {https://www.biorxiv.org/content/early/2026/03/20/2026.03.19.712954.full.pdf},
journal = {bioRxiv}
}
@misc{fallahpour2025bioreasonincentivizingmultimodalbiological,
title={BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model},
author={Adibvafa Fallahpour and Andrew Magnuson and Purav Gupta and Shihao Ma and Jack Naimer and Arnav Shah and Haonan Duan and Omar Ibrahim and Hani Goodarzi and Chris J. Maddison and Bo Wang},
year={2025},
eprint={2505.23579},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2505.23579},
}
🧬 BioReason-ProAdvancing Protein Function Prediction withMultimodal Biological Reasoning
0
3 commits
1 linked in READMEs
updated Aug 19, 2026
Precomputed text embeddings for 43,248 Gene Ontology terms, one per term, produced
with Qwen/Qwen3-Embedding-4B over the
GO term name and definition.
BioReason-Pro's GO graph encoder (a 3-layer GAT over go-basic.obo) is initialised from
these vectors rather than learning term representations from scratch. They are required
for training, evaluation, and checkpoint conversion — passed as --precomputed_embeddings_path.
git clone https://github.com/bowang-lab/BioReason-Pro.git && cd BioReason-Pro
pip install -e .
python scripts/download_assets.py --dest /data/bioreason --skip-structures
# -> /data/bioreason/go_embeddings (pass as GO_EMBEDDINGS_PATH)
A single go_embeddings.tar.gz that extracts to a flat directory:
go_embeddings/
GO_0000001.safetensors
GO_0000002.safetensors
... # 43,248 files, 338 MB extracted
Each file holds one tensor of dimension 2560 under the key embedding.
These vectors can be rebuilt from scratch, though downloading is strongly preferred — regenerating on a different model revision produces different vectors and will not match the released checkpoints:
python -m bioreason2.utils.go_embed \
--model_name Qwen/Qwen3-Embedding-4B \
--output_dir /data/bioreason/go_embeddings \
--batch_size 32 --device cuda
If you find this work useful, please cite our papers:
@article {Fallahpour2026.03.19.712954,
author = {Fallahpour, Adibvafa and Seyed-Ahmadi, Arman and Idehpour, Parsa and Ibrahim, Omar and Gupta, Purav and Naimer, Jack and Zhu, Kevin and Shah, Arnav and Ma, Shihao and Adduri, Abhinav and G{\"u}loglu, Talu and Liu, Nuo and Cui, Haotian and Jain, Arihant and de Castro, Max and Fallahpour, Amirfaham and Cembellin-Prieto, Antonio and Stiles, John S. and Nem{\v c}ko, Filip and Nevue, Alexander A. and Moon, Hyungseok C. and Sosnick, Lucas and Markham, Olivia and Duan, Haonan and Lee, Michelle Y. Y. and Salvador, Andrea F. M. and Maddison, Chris J. and Thaiss, Christoph A. and Ricci-Tam, Chiara and Plosky, Brian S. and Burke, Dave P. and Hsu, Patrick D. and Goodarzi, Hani and Wang, Bo},
title = {BioReason-Pro: Advancing Protein Function Prediction with Multimodal Biological Reasoning},
elocation-id = {2026.03.19.712954},
year = {2026},
doi = {10.64898/2026.03.19.712954},
publisher = {Cold Spring Harbor Laboratory},
URL = {https://www.biorxiv.org/content/early/2026/03/20/2026.03.19.712954},
eprint = {https://www.biorxiv.org/content/early/2026/03/20/2026.03.19.712954.full.pdf},
journal = {bioRxiv}
}
@misc{fallahpour2025bioreasonincentivizingmultimodalbiological,
title={BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model},
author={Adibvafa Fallahpour and Andrew Magnuson and Purav Gupta and Shihao Ma and Jack Naimer and Arnav Shah and Haonan Duan and Omar Ibrahim and Hani Goodarzi and Chris J. Maddison and Bo Wang},
year={2025},
eprint={2505.23579},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2505.23579},
}