[!TIP]
The MultiMolecule team has confirmed that the provided model and checkpoints are producing the same intermediate representations as the original implementation.
The team releasing BPNet did not write this model card for this model so this model card has been written by the MultiMolecule team.
Model Details
BPNet is a convolutional neural network (CNN) trained to predict base-resolution transcription-factor binding signal (ChIP-nexus) from primary DNA sequence. It uses a convolutional motif stem followed by a stack of dilated residual convolutions that aggregate ~1 kb of genomic context. The output is factorized into profile and count branches, and the usable base-resolution prediction is reconstructed by BpNetForProfilePrediction.postprocess. Please refer to the Training Details section for more information on the training process.
Developed by: Žiga Avsec, Melanie Weilert, Avanti Shrikumar, Sabrina Krueger, Amr Alexandari, Khyati Dalal, Robin Fropf, Charles McAnany, Julien Gagneur, Anshul Kundaje, Julia Zeitlinger
Model type: 1D dilated CNN with factorized profile-and-count heads for base-resolution transcription-factor binding prediction
The recombined track is the usable base-resolution prediction. The last dimension stacks num_tasks (Oct4, Sox2, Nanog, Klf4) by num_strands (forward, reverse).
Interface
Input length: 1000 bp DNA window
Output: factorized (profile_logits, count_logits); recombine the usable base-resolution track via BpNetForProfilePrediction.postprocess
BPNet was trained to predict the base-resolution ChIP-nexus binding profiles of the pluripotency transcription factors Oct4, Sox2, Nanog and Klf4 in mouse embryonic stem cells.
Training Data
The published BPNet-OSKN model was trained on ChIP-nexus profiles for Oct4, Sox2, Nanog and Klf4, using 1 kb genomic windows centered on detected binding peaks. The training regions and trained model files are distributed as part of the BPNet manuscript data.
Training Procedure
Pre-training
The model was trained with a composite loss: a multinomial negative log-likelihood on the per-position profile shape plus a mean-squared-error regression on the log total counts.
Optimizer: Adam
Citation
bibtex
1@article{avsec2021baseresolution,
2 author = {Avsec, {\v{Z}}iga and Weilert, Melanie and Shrikumar, Avanti and Krueger, Sabrina and Alexandari, Amr and Dalal, Khyati and Fropf, Robin and McAnany, Charles and Gagneur, Julien and Kundaje, Anshul and Zeitlinger, Julia},
3 title = {Base-resolution models of transcription-factor binding reveal soft motif syntax},
4 journal = {Nature Genetics},
5 volume = 53,
6 number = 3,
7 pages = {354--366},
8 year = 2021,
9 publisher = {Nature Publishing Group},
10 doi = {10.1038/s41588-021-00782-6}
11}
[!NOTE]
The artifacts distributed in this repository are part of the MultiMolecule project.
If MultiMolecule supports your research, please cite the MultiMolecule project as follows:
bibtex
1@software{chen_2024_12638419,
2 author = {Chen, Zhiyuan and Zhu, Sophia Y.},
3 title = {MultiMolecule},
4 doi = {10.5281/zenodo.12638419},
5 publisher = {Zenodo},
6 url = {https://doi.org/10.5281/zenodo.12638419},
7 year = 2024,
8 month = may,
9 day = 4
10}
Contact
Please use GitHub issues of MultiMolecule for any questions or comments on the model card.
Please contact the authors of the BPNet paper for questions or comments on the paper/model.
