metadata
library_name: multimolecule
license: agpl-3.0
pipeline: polyadenylation
pipeline_tag: other
tags:
- Biology
- RNA
- 3' UTR
- rna
widget:
- example_title: microRNA 21
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: UAGCUUAUCAGACUGAUGUUGA
- example_title: microRNA 146a
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: UGAGAACUGAAUUCCAUGGGUU
- example_title: microRNA 155
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: UUAAUGCUAAUCGUGAUAGGGGUU
- example_title: RNA component of mitochondrial RNA processing endoribonuclease
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: >-
GGUUCGUGCUGAAGGCCUGUAUCCUAGGCUACACACUGAGGACUCUGUUCCUCCCCUUUCCGCCUAGGGGAAAGUCCCCGGACCUCGGGCAGAGAGUGCCACGUGCAUACGCACGUAGACAUUCCCCGCUUCCCACUCCAAAGUCCGCCAAGAAGCGUAUCCCGCUGAGCGGCGUGGCGCGGGGGCGUCAUCCGUCAGCUCCCUCUAGUUACGCAGGCAGUGCGUGUCCGCGCACCAACCACACGGGGCUCAUUCUCAGCGCGGCUGUAAAAAAAAA
- example_title: 7SK small nuclear RNA
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: >-
GGAUGUGAGGGCGAUCUGGCUGCGACAUCUGUCACCCCAUUGAUCGCCAGGGUUGAUUCGGCUGAUCUGGCUGGCUAGGCGGGUGUCCCCUUCCUCCCUCACCGCUCCAUGUGCGUCCCUCCCGAAGCUGCGCGCUCGGUCGAAGAGGACGACCAUCCCCGAUAGAGGAGGACCGGUCUUCGGUCAAGGGUAUACGAGUAGCUGCGCUCCCCUGCUAGAACCUCCAAACAAGCUCUCAAGGUCCAUUUGUAGGAGAACGUAGGGUAGUCAAGCUUCCAAGACUCCAGACACAUCCAAAUGAGGCGCUGCAUGUGGCAGUCUGCCUUUCUUUU
- example_title: telomerase RNA component
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: >-
GGGUUGCGGAGGGUGGGCCUGGGAGGGGUGGUGGCCAUUUUUUGUCUAACCCUAACUGAGAAGGGCGUAGGCGCCGUGCUUUUGCUCCCCGCGCGCUGUUUUUCUCGCUGACUUUCAGCGGGCGGAAAAGCCUCGGCCUGCCGCCUUCCACCGUUCAUUCUAGAGCAAACAAAAAAUGUCAGCUGCUGGCCCGUUCGCCCCUCCCGGGGACCUGCGGCGGGUCGCCUGCCCAGCCCCCGAACCCCGCCUGGAGGCCGCGGUCGGCCCGGGGCUUCUCCGGAGGCACCCACUGCCACCGCGAAGAGUUGGGCUCUGUCAGCCGCGGGUCUCUCGGGGGCGAGGGCGAGGUUCAGGCCUUUCAGGCCGCAGGAAGAGGAACGGAGCGAGUCCCCGCGCGCGGCGCGAUUCCCUGAGCUGUGGGACGUGCACCCAGGACUCGGCUCACACAUGC
- example_title: vault RNA 2-1
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: >-
CGGGUCGGAGUUAGCUCAAGCGGUUACCUCCUCAUGCCGGACUUUCUAUCUGUCCAUCUCUGUGCUGGGGUUCGAGACCCGCGGGUGCUUACUGACCCUUUUAUGCAA
- example_title: brain cytoplasmic RNA 1
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: >-
GGCCGGGCGCGGUGGCUCACGCCUGUAAUCCCAGCUCUCAGGGAGGCUAAGAGGCGGGAGGAUAGCUUGAGCCCAGGAGUUCGAGACCUGCCUGGGCAAUAUAGCGAGACCCCGUUCUCCAGAAAAAGGAAAAAAAAAAACAAAAGACAAAAAAAAAAUAAGCGUAACUUCCCUCAAAGCAACAACCCCCCCCCCCCUUU
- example_title: HIV-1 TAR-WT
pipeline_tag: polyadenylation
sequence_type: ncRNA
task: polyadenylation
text: GGUCUCUCUGGUUAGACCAGAUCUGAGCCUGGGAGCUCUCUGGCUAACUAGGGAACC
- example_title: prion protein (Kanno blood group)
pipeline_tag: polyadenylation
sequence_type: mRNA
task: polyadenylation
text: AUGGCGAACCUUGGCUGCUGGAUGCUGGUUCUCUUUGUGGCCACAUGGAGUGACCUGGGCCUCUGC
- example_title: interleukin 10
pipeline_tag: polyadenylation
sequence_type: mRNA
task: polyadenylation
text: AUGCACAGCUCAGCACUGCUCUGUUGCCUGGUCCUCCUGACUGGGGUGAGGGCC
- example_title: Zaire ebolavirus
pipeline_tag: polyadenylation
sequence_type: mRNA
task: polyadenylation
text: >-
AAUGUUCAAACACUUUGUGAAGCUCUGUUAGCUGAUGGUCUUGCUAAAGCAUUUCCUAGCAAUAUGAUGGUAGUCACAGAGCGUGAGCAAAAAGAAAGCUUAUUGCAUCAAGCAUCAUGGCACCACACAAGUGAUGAUUUUGGUGAGCAUGCCACAGUUAGAGGGAGUAGCUUUGUAACUGAUUUAGAGAAAUACAAUCUUGCAUUUAGAUAUGAGUUUACAGCACCUUUUAUAGAAUAUUGUAACCGUUGCUAUGGUGUUAAGAAUGUUUUUAAUUGGAUGCAUUAUACAAUCCCACAGUGUUAU
- example_title: SARS coronavirus
pipeline_tag: polyadenylation
sequence_type: mRNA
task: polyadenylation
text: >-
AUGUUUAUUUUCUUAUUAUUUCUUACUCUCACUAGUGGUAGUGACCUUGACCGGUGCACCACUUUUGAUGAUGUUCAAGCUCCUAAUUACACUCAACAUACUUCAUCUAUGAGGGGGGUUUACUAUCCUGAUGAAAUUUUUAGAUCAGACACUCUUUAUUUAACUCAGGAUUUAUUUCUUCCAUUUUAUUCUAAUGUUACAGGGUUUCAUACUAUUAAUCAUACGUUUGACAACCCUGUCAUACCUUUUAAGGAUGGUAUUUAUUUUGCUGCCACAGAGAAAUCAAAUGUUGUCCGUGGUUGGGUUUUUGGUUCUACCAUGAACAACAAGUCACAGUCGGUGAUUAUUAUUAACAAUUCUACUAAUGUUGUUAUACGAGCAUGUAACUUUGAAUUGUGUGACAACCCUUUCUUUGCUGUUUCUAAACCCAUGGGUACACAGACACAUACUAUGAUAUUCGAUAAUGCAUUUAAAUGCACUUUCGAGUACAUAUCU
- example_title: insulin
pipeline_tag: polyadenylation
sequence_type: mRNA
task: polyadenylation
text: >-
AUGGCCCUGUGGAUGCGCCUCCUGCCCCUGCUGGCGCUGCUGGCCCUCUGGGGACCUGACCCAGCCGCAGCCUUUGUGAACCAACACCUGUGCGGCUCACACCUGGUGGAAGCUCUCUACCUAGUGUGCGGGGAACGAGGCUUCUUCUACACACCCAAGACCCGCCGGGAGGCAGAGGACCUGCAGGUGGGGCAGGUGGAGCUGGGCGGGGGCCCUGGUGCAGGCAGCCUGCAGCCCUUGGCCCUGGAGGGGUCCCUGCAGAAGCGUGGCAUUGUGGAACAAUGCUGUACCAGCAUCUGCUCCCUCUACCAGCUGGAGAACUACUGCAACUAG
- example_title: cyclin dependent kinase inhibitor 2A
pipeline_tag: polyadenylation
sequence_type: mRNA
task: polyadenylation
text: >-
AUGGAGCCGGCGGCGGGGAGCAGCAUGGAGCCUUCGGCUGACUGGCUGGCCACGGCCGCGGCCCGGGGUCGGGUAGAGGAGGUGCGGGCGCUGCUGGAGGCGGGGGCGCUGCCCAACGCACCGAAUAGUUACGGUCGGAGGCCGAUCCAGGUCAUGAUGAUGGGCAGCGCCCGAGUGGCGGAGCUGCUGCUGCUCCACGGCGCGGAGCCCAACUGCGCCGACCCCGCCACUCUCACCCGACCCGUGCACGACGCUGCCCGGGAGGGCUUCCUGGACACGCUGGUGGUGCUGCACCGGGCCGGGGCGCGGCUGGACGUGCGCGAUGCCUGGGGCCGUCUGCCCGUGGACCUGGCUGAGGAGCUGGGCCAUCGCGAUGUCGCACGGUACCUGCGCGCGGCUGCGGGGGGCACCAGAGGCAGUAACCAUGCCCGCAUAGAUGCCGCGGAAGGUCCCUCAGACAUCCCCGAUUGA
- example_title: human papillomavirus type 16 E6
pipeline_tag: polyadenylation
sequence_type: mRNA
task: polyadenylation
text: >-
AUGCACCAAAAGAGAACUGCAAUGUUUCAGGACCCACAGGAGCGACCCAGAAAGUUACCACAGUUAUGCACAGAGCUGCAAACAACUAUACAUGAUAUAAUAUUAGAAUGUGUGUACUGCAAGCAACAGUUACUGCGACGUGAGGUAUAUGACUUUGCUUUUCGGGAUUUAUGCAUAGUAUAUAGAGAUGGGAAUCCAUAUGCUGUAUGUGAUAAAUGUUUAAAGUUUUAUUCUAAAAUUAGUGAGUAUAGACAUUAUUGUUAUAGUUUGUAUGGAACAACAUUAGAACAGCAAUACAACAAACCGUUGUGUGAUUUGUUAAUUAGGUGUAUUAACUGUCAAAAGCCACUGUGUCCUGAAGAAAAGCAAAGACAUCUGGACAAAAAGCAAAGAUUCCAUAAUAUAAGGGGUCGGUGGACCGGUCGAUGUAUGUCUUGUUGCAGAUCAUCAAGAACACGUAGAGAAACCCAGCUGUAA
- example_title: NRAS proto-oncogene
pipeline_tag: polyadenylation
sequence_type: 5' UTR
task: polyadenylation
text: >-
GGGGCCGGAAGUGCCGCUCCUUGGUGGGGGCUGUUCAUGGCGGUUCCGGGGUCUCCAACAUUUUUCCCGGCUGUGGUCCUAAAUCUGUCCAAAGCAGAGGCAGUGGAGCUUGAGGUUCUUGCUGGUGUGAA
- example_title: amyloid beta precursor protein
pipeline_tag: polyadenylation
sequence_type: 5' UTR
task: polyadenylation
text: >-
GUCAGUUUCCUCGGCAGCGGUAGGCGAGAGCACGCGGAGGAGCGUGCGCGGGGGCCCCGGGAGACGGCGGCGGUGGCGGCGCGGGCAGAGCAAGGACGCGGCGGAUCCCACUCGCACAGCAGCGCACUCGGUGCCCCGCGCAGGGUCGCG
- example_title: RUNX family transcription factor 1
pipeline_tag: polyadenylation
sequence_type: 5' UTR
task: polyadenylation
text: >-
ACUUCUUUGGGCCUCAUAAACAACCACAGAACCACAAGUUGGGUAGCCUGGCAGUGUCAGAAGUCUGAACCCAGCAUAGUGGUCAGCAGGCAGGACGAAUCACACUGAAUGCAAACCACAGGGUUUCGCAGCGUGGUAAAAGAAAUCAUUGAGUCCCCCGCCUUCAGAAGAGGGUGCAUUUUCAGGAGGAAGCG
- example_title: fragile X messenger ribonucleoprotein 1
pipeline_tag: polyadenylation
sequence_type: 5' UTR
task: polyadenylation
text: >-
CUCAGUCAGGCGCUCAGCUCCGUUUCGGUUUCACUUCCGGUGGAGGGCCGCCUCUGAGCGGGCGGCGGGCCGACGGCGAGCGCGGGCGGCGGCGGUGACGGAGGCGCCGCUGCCAGGGGGCGUGCGGCAGCGCGGCGGCGGCGGCGGCGGCGGCGGCGGCGGAGGCGGCGGCGGCGGCGGCGGCGGCGGCGGCUGGGCCUCGAGCGCCCGCAGCCCACCUCUCGGGGGCGGGCUCCCGGCGCUAGCAGGGCUGAAGAGAAG
- example_title: MYC proto-oncogene
pipeline_tag: polyadenylation
sequence_type: 5' UTR
task: polyadenylation
text: >-
AACUCGCUGUAGUAAUUCCAGCGAGAGGCAGAGGGAGCGAGCGGGCGGCCGGCUAGGGUGGAAGAGCCGGGCGAGCAGAGCUGCGCUGCGGGCGUCCUGGGAAGGGAGAUCCGGAGCGAAUAGGGGGCUUCGCCUCUGGCCCAGCCCUCCCGCUGAUCCCCCAGCCAGCGGUCCGCAACCCUUGCCGCAUCCACGAAACUUUGCCCAUAGCAGCGGGCGGGCACUUUGCACUGGAACUUACAACACCCGAGCAAGGACGCGACUCUCCCGACGCGGGGAGGCUAUUCUGCCCAUUUGGGGACACUUCCCCGCCGCUGCCAGGACCCGCUUCUCUGAAAGGCUCUCCUUGCAGCUGCUUAGACG
- example_title: activating transcription factor 4
pipeline_tag: polyadenylation
sequence_type: 5' UTR
task: polyadenylation
text: >-
CAUUUCUACUUUGCCCGCCCACAGAUGUAGUUUUCUCUGCGCGUGUGCGUUUUCCCUCCUCCCCGCCCUCAGGGUCCACGGCCACCAUGGCGUAUUAGGGGCAGCAGUGCCUGCGGCAGCAUUGGCCUUUGCAGCGGCGGCAGCAGCACCAGGCUCUGCAGCGGCAACCCCCAGCGGCUUAAGCCAUGGCGCUUCUCACGGCAUUCAGCAGCAGCGUUGCUGUAACCGACAAAGACACCUUCGAAUUAAGCACAUUCCUCGAUUCCAGCAAAGCACCGCAAC
- example_title: Human GPI protein p137
pipeline_tag: polyadenylation
sequence_type: 3' UTR
task: polyadenylation
text: >-
UUUUUAAAAGGAAAAGAUACCAAAUGCCUGCUGCUACCACCCUUUUCAAUUGCUAUGUUUUGAAAGGCACCAGUAUGUGUUUUAGAUUGAUUUAAAUGUUUCAUUUAAAUCACGGACAGUAGUUUCAGUUCUGAUGGUAUAAGCAAAACAAAUAAAACGUUUAUAAAAGUUGUAUCUUGAAACACUGGUGUUCAACAGCUAGCAGCUUAUGUGAUUCACCCCAUGCCACGUUAGUGUCACAAAUUUUAUGGUUUAUCUCCAGCAACAUUUCUCUAGUACUUGCACUUAUUAUCUGAAUUC
- example_title: nucleophosmin 1
pipeline_tag: polyadenylation
sequence_type: 3' UTR
task: polyadenylation
text: >-
GAAAAUAGUUUAAACAAUUUGUUAAAAAAUUUUCCGUCUUAUUUCAUUUCUGUAACAGUUGAUAUCUGGCUGUCCUUUUUAUAAUGCAGAGUGAGAACUUUCCCUACCGUGUUUGAUAAAUGUUGUCCAGGUUCUAUUGCCAAGAAUGUGUUGUCCAAAAUGCCUGUUUAGUUUUUAAAGAUGGAACUCCACCCUUUGCUUGGUUUUAAGUAUGUAUGGAAUGUUAUGAUAGGACAUAGUAGUAGCGGUGGUCAGACAUGGAAAUGGUGGGGAGACAAAAAUAUACAUGUGAAAUAAAACUCAGUAUUUUAAUAAAGUAGCACGGUUUCUAUUGA
- example_title: superoxide dismutase 1
pipeline_tag: polyadenylation
sequence_type: 3' UTR
task: polyadenylation
text: >-
ACAUUCCCUUGGAUGUAGUCUGAGGCCCCUUAACUCAUCUGUUAUCCUGCUAGCUGUAGAAAUGUAUCCUGAUAAACAUUAAACACUGUAAUCUUAAAAGUGUAAUUGUGUGACUUUUUCAGAGUUGCUUUAAAGUACCUGUAGUGAGAAACUGAUUUAUGAUCACUUGGAAGAUUUGUAUAGUUUUAUAAAACUCAGUUAAAAUGUCUGUUUCAAUGACCUGUAUUUUGCCAGACUUAAAUCACAGAUGGGUAUUAAACUUGUCAGAAUUUCUUUGUCAUUCAAGCCUGUGAAUAAAAACCCUGUAUGGCACUUAUUAUGAGGCUAUUAAAAGAAUCCAAAUUCAAACUAAA
- example_title: hemoglobin subunit alpha 2
pipeline_tag: polyadenylation
sequence_type: 3' UTR
task: polyadenylation
text: >-
CUGGAGCCUCGGUAGCCGUUCCUCCUGCCCGCUGGGCCUCCCAACGGGCCCUCCUCCCCUCCUUGCACCGGCCCUUCCUGGUCUUUGAAUAAAGUCUGAGUGGGCAGCA
- example_title: BRAF proto-oncogene
pipeline_tag: polyadenylation
sequence_type: 3' UTR
task: polyadenylation
text: >-
AACAAAUGAGUGAGAGAGUUCAGGAGAGUAGCAACAAAAGGAAAAUAAAUGAACAUAUGUUUGCUUAUAUGUUAAAUUGAAUAAAAUACUCUCUUUUUUUUUAAGGUGAACCAAAGAACACUUGUGUGGUUAAAGACUAGAUAUAAUUUUUCCCCAAACUAAAAUUUAUACUUAACAUUGGAUUUUUAACAUCCAAGGGUUAAAAUACAUAGACAUUGCUAAAAAUUGGCAGAGCCUCUUCUAGAGGCUUUACUUUCUGUUCCGGGUUUGUAUCAUUCACUUGGUUAUUUUAAGUAGUAAACUUCAGUUUCUCAUGCAACUUUUGUUGCCAGCUAUCACAUGUCCACUAGGGACUCCAGAAGAAGACCCUACCUAUGCCUGUGUUUGCAGGUGAGAAGUUGGCAGUCGGUUAGCCUGGG
- example_title: H3 clustered histone 1
pipeline_tag: polyadenylation
sequence_type: 3' UTR
task: polyadenylation
text: UUACUGUGGUCUCUCUGACGGUCCAAGCAAAGGCUCUUUUCAGAGCCACCACCUUUUC
APARENT2
Deep residual neural network for predicting human 3' UTR Alternative Polyadenylation (APA) and cleavage magnitude at nucleotide resolution, and for deciphering the impact of genetic variants on polyadenylation.
Disclaimer
This is an UNOFFICIAL implementation of Deciphering the impact of genetic variation on human polyadenylation using APARENT2 by Johannes Linder, Samantha E. Koplik, et al.
The OFFICIAL repository of APARENT2 is at johli/aparent-resnet.
The MultiMolecule team has confirmed that the provided model and checkpoints are producing the same intermediate representations as the original implementation.
The team releasing APARENT2 did not write this model card for this model so this model card has been written by the MultiMolecule team.
Model Details
APARENT2 is a residual convolutional neural network (a ResNet successor to the original APARENT) trained on a 3' UTR massively parallel reporter assay (MPRA). Given a fixed 205 nt polyadenylation signal (PAS) sequence, it predicts a nucleotide-resolution cleavage probability distribution as well as the overall isoform abundance. It is primarily used to score the effect of genetic variants on polyadenylation by comparing the predictions for a reference and an alternate sequence.
Model Specification
| Num Layers | Hidden Size | Num Parameters (M) | FLOPs (G) | MACs (G) | Max Num Tokens |
|---|---|---|---|---|---|
| 28 | 32 | 0.19 | 0.08 | 0.04 | 205 |
Links
- Code: multimolecule.aparent2
- Data: Massively-parallel polyadenylation MPRA with variant-effect evaluation data
- Paper: Deciphering the impact of genetic variation on human polyadenylation using APARENT2
- Developed by: Johannes Linder, Samantha E. Koplik, Anshul Kundaje, Georg Seelig
- Model type: 1D residual CNN successor to APARENT for polyadenylation isoform, cleavage, and variant-effect prediction
- Original Repository: johli/aparent-resnet
Usage
The model file depends on the multimolecule library. You can install it using pip:
pip install multimolecule
Direct Use
Polyadenylation Cleavage Prediction
You can use this model directly to predict the cleavage distribution of a 205 nt polyadenylation signal sequence (core hexamer starting at position 70):
>>> import torch
>>> from multimolecule import RnaTokenizer, Aparent2Model
>>> tokenizer = RnaTokenizer.from_pretrained("multimolecule/aparent2")
>>> model = Aparent2Model.from_pretrained("multimolecule/aparent2")
>>> sequence = "A" * 70 + "AAUAAA" + "A" * 129
>>> output = model(**tokenizer(sequence, return_tensors="pt"))
>>> output.logits.shape
torch.Size([1, 206])
Variant Effect Scoring
Score a reference and an alternate sequence separately, then compare:
>>> import torch
>>> ref = "A" * 70 + "AAUAAA" + "A" * 129
>>> alt = "A" * 70 + "AAUACA" + "A" * 129
>>> ref_prob = torch.softmax(model(**tokenizer(ref, return_tensors="pt")).logits, dim=-1)
>>> alt_prob = torch.softmax(model(**tokenizer(alt, return_tensors="pt")).logits, dim=-1)
>>> ref_iso = ref_prob[:, 77:127].sum(dim=-1)
>>> alt_iso = alt_prob[:, 77:127].sum(dim=-1)
>>> delta_logodds = torch.log(alt_iso / (1 - alt_iso)) - torch.log(ref_iso / (1 - ref_iso))
Interface
- Input length: fixed 205 nt window
- Hexamer position: core hexamer (e.g.,
AAUAAA) at position 70 (0-indexed) of the 205 nt window - Output: 206-dim cleavage distribution (one score per input position + trailing "no cleavage in window" bucket)
Variant Effect
- Score reference and alternate sequences separately and compare their cleavage / isoform predictions
- There is no separate ref/alt output dataclass
Training Details
APARENT2 was trained to predict nucleotide-resolution cleavage and isoform abundance from 3' UTR MPRA measurements.
Training Data
The model was trained on the 3' UTR MPRA library used by the original APARENT, re-processed with additional improvements (exact cleavage positions for the Alien1 Random sublibrary and a 20 nt random barcode upstream of the USE in the Alien1 sublibrary). The measured variant data and processed data repository are available at the original APARENT GitHub.
Training Procedure
Pre-training
The model minimizes a combination of a sigmoid KL-divergence isoform loss and a KL-divergence cleavage loss, weighted equally. The released inference model corresponds to the residual-network model trained for 5 epochs on all sublibraries (excluding ClinVar wild-type sequences), with dropout disabled for inference.
Citation
@article{linder2022deciphering,
author = {Linder, Johannes and Koplik, Samantha E. and Kundaje, Anshul and Seelig, Georg},
title = {Deciphering the impact of genetic variation on human polyadenylation using APARENT2},
journal = {Genome Biology},
volume = {23},
number = {1},
pages = {232},
year = {2022},
doi = {10.1186/s13059-022-02799-4},
publisher = {Springer Science and Business Media LLC}
}
The artifacts distributed in this repository are part of the MultiMolecule project. If MultiMolecule supports your research, please cite the MultiMolecule project as follows:
@software{chen_2024_12638419,
author = {Chen, Zhiyuan and Zhu, Sophia Y.},
title = {MultiMolecule},
doi = {10.5281/zenodo.12638419},
publisher = {Zenodo},
url = {https://doi.org/10.5281/zenodo.12638419},
year = 2024,
month = may,
day = 4
}
Contact
Please use GitHub issues of MultiMolecule for any questions or comments on the model card.
Please contact the authors of the APARENT2 paper for questions or comments on the paper/model.
License
This model implementation is licensed under the GNU Affero General Public License.
For additional terms and clarifications, please refer to our License FAQ.
SPDX-License-Identifier: AGPL-3.0-or-later