Hugging Face's logo

multimolecule
/
framepool

Other
MultiMolecule
PyTorch
Safetensors
framepool
Biology
RNA
5' UTR
Translation
rna
Model card Files
xet
 Community
framepool / README.md
ZhiyuanChen's picture
ZhiyuanChen
Upload folder using huggingface_hub
1cd8302 verified
preview code
|
raw
history blame contribute delete
18.5 kB
metadata 
library_name: multimolecule
license: agpl-3.0
pipeline: mean-ribosome-load
pipeline_tag: other
tags:
  - Biology
  - RNA
  - 5' UTR
  - Translation
  - rna
widget:
  - example_title: microRNA 21
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: UAGCUUAUCAGACUGAUGUUGA
  - example_title: microRNA 146a
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: UGAGAACUGAAUUCCAUGGGUU
  - example_title: microRNA 155
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: UUAAUGCUAAUCGUGAUAGGGGUU
  - example_title: RNA component of mitochondrial RNA processing endoribonuclease
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: >-
      GGUUCGUGCUGAAGGCCUGUAUCCUAGGCUACACACUGAGGACUCUGUUCCUCCCCUUUCCGCCUAGGGGAAAGUCCCCGGACCUCGGGCAGAGAGUGCCACGUGCAUACGCACGUAGACAUUCCCCGCUUCCCACUCCAAAGUCCGCCAAGAAGCGUAUCCCGCUGAGCGGCGUGGCGCGGGGGCGUCAUCCGUCAGCUCCCUCUAGUUACGCAGGCAGUGCGUGUCCGCGCACCAACCACACGGGGCUCAUUCUCAGCGCGGCUGUAAAAAAAAA
  - example_title: 7SK small nuclear RNA
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: >-
      GGAUGUGAGGGCGAUCUGGCUGCGACAUCUGUCACCCCAUUGAUCGCCAGGGUUGAUUCGGCUGAUCUGGCUGGCUAGGCGGGUGUCCCCUUCCUCCCUCACCGCUCCAUGUGCGUCCCUCCCGAAGCUGCGCGCUCGGUCGAAGAGGACGACCAUCCCCGAUAGAGGAGGACCGGUCUUCGGUCAAGGGUAUACGAGUAGCUGCGCUCCCCUGCUAGAACCUCCAAACAAGCUCUCAAGGUCCAUUUGUAGGAGAACGUAGGGUAGUCAAGCUUCCAAGACUCCAGACACAUCCAAAUGAGGCGCUGCAUGUGGCAGUCUGCCUUUCUUUU
  - example_title: telomerase RNA component
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: >-
      GGGUUGCGGAGGGUGGGCCUGGGAGGGGUGGUGGCCAUUUUUUGUCUAACCCUAACUGAGAAGGGCGUAGGCGCCGUGCUUUUGCUCCCCGCGCGCUGUUUUUCUCGCUGACUUUCAGCGGGCGGAAAAGCCUCGGCCUGCCGCCUUCCACCGUUCAUUCUAGAGCAAACAAAAAAUGUCAGCUGCUGGCCCGUUCGCCCCUCCCGGGGACCUGCGGCGGGUCGCCUGCCCAGCCCCCGAACCCCGCCUGGAGGCCGCGGUCGGCCCGGGGCUUCUCCGGAGGCACCCACUGCCACCGCGAAGAGUUGGGCUCUGUCAGCCGCGGGUCUCUCGGGGGCGAGGGCGAGGUUCAGGCCUUUCAGGCCGCAGGAAGAGGAACGGAGCGAGUCCCCGCGCGCGGCGCGAUUCCCUGAGCUGUGGGACGUGCACCCAGGACUCGGCUCACACAUGC
  - example_title: vault RNA 2-1
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: >-
      CGGGUCGGAGUUAGCUCAAGCGGUUACCUCCUCAUGCCGGACUUUCUAUCUGUCCAUCUCUGUGCUGGGGUUCGAGACCCGCGGGUGCUUACUGACCCUUUUAUGCAA
  - example_title: brain cytoplasmic RNA 1
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: >-
      GGCCGGGCGCGGUGGCUCACGCCUGUAAUCCCAGCUCUCAGGGAGGCUAAGAGGCGGGAGGAUAGCUUGAGCCCAGGAGUUCGAGACCUGCCUGGGCAAUAUAGCGAGACCCCGUUCUCCAGAAAAAGGAAAAAAAAAAACAAAAGACAAAAAAAAAAUAAGCGUAACUUCCCUCAAAGCAACAACCCCCCCCCCCCUUU
  - example_title: HIV-1 TAR-WT
    pipeline_tag: mean-ribosome-load
    sequence_type: ncRNA
    task: mean-ribosome-load
    text: GGUCUCUCUGGUUAGACCAGAUCUGAGCCUGGGAGCUCUCUGGCUAACUAGGGAACC
  - example_title: prion protein (Kanno blood group)
    pipeline_tag: mean-ribosome-load
    sequence_type: mRNA
    task: mean-ribosome-load
    text: AUGGCGAACCUUGGCUGCUGGAUGCUGGUUCUCUUUGUGGCCACAUGGAGUGACCUGGGCCUCUGC
  - example_title: interleukin 10
    pipeline_tag: mean-ribosome-load
    sequence_type: mRNA
    task: mean-ribosome-load
    text: AUGCACAGCUCAGCACUGCUCUGUUGCCUGGUCCUCCUGACUGGGGUGAGGGCC
  - example_title: Zaire ebolavirus
    pipeline_tag: mean-ribosome-load
    sequence_type: mRNA
    task: mean-ribosome-load
    text: >-
      AAUGUUCAAACACUUUGUGAAGCUCUGUUAGCUGAUGGUCUUGCUAAAGCAUUUCCUAGCAAUAUGAUGGUAGUCACAGAGCGUGAGCAAAAAGAAAGCUUAUUGCAUCAAGCAUCAUGGCACCACACAAGUGAUGAUUUUGGUGAGCAUGCCACAGUUAGAGGGAGUAGCUUUGUAACUGAUUUAGAGAAAUACAAUCUUGCAUUUAGAUAUGAGUUUACAGCACCUUUUAUAGAAUAUUGUAACCGUUGCUAUGGUGUUAAGAAUGUUUUUAAUUGGAUGCAUUAUACAAUCCCACAGUGUUAU
  - example_title: SARS coronavirus
    pipeline_tag: mean-ribosome-load
    sequence_type: mRNA
    task: mean-ribosome-load
    text: >-
      AUGUUUAUUUUCUUAUUAUUUCUUACUCUCACUAGUGGUAGUGACCUUGACCGGUGCACCACUUUUGAUGAUGUUCAAGCUCCUAAUUACACUCAACAUACUUCAUCUAUGAGGGGGGUUUACUAUCCUGAUGAAAUUUUUAGAUCAGACACUCUUUAUUUAACUCAGGAUUUAUUUCUUCCAUUUUAUUCUAAUGUUACAGGGUUUCAUACUAUUAAUCAUACGUUUGACAACCCUGUCAUACCUUUUAAGGAUGGUAUUUAUUUUGCUGCCACAGAGAAAUCAAAUGUUGUCCGUGGUUGGGUUUUUGGUUCUACCAUGAACAACAAGUCACAGUCGGUGAUUAUUAUUAACAAUUCUACUAAUGUUGUUAUACGAGCAUGUAACUUUGAAUUGUGUGACAACCCUUUCUUUGCUGUUUCUAAACCCAUGGGUACACAGACACAUACUAUGAUAUUCGAUAAUGCAUUUAAAUGCACUUUCGAGUACAUAUCU
  - example_title: insulin
    pipeline_tag: mean-ribosome-load
    sequence_type: mRNA
    task: mean-ribosome-load
    text: >-
      AUGGCCCUGUGGAUGCGCCUCCUGCCCCUGCUGGCGCUGCUGGCCCUCUGGGGACCUGACCCAGCCGCAGCCUUUGUGAACCAACACCUGUGCGGCUCACACCUGGUGGAAGCUCUCUACCUAGUGUGCGGGGAACGAGGCUUCUUCUACACACCCAAGACCCGCCGGGAGGCAGAGGACCUGCAGGUGGGGCAGGUGGAGCUGGGCGGGGGCCCUGGUGCAGGCAGCCUGCAGCCCUUGGCCCUGGAGGGGUCCCUGCAGAAGCGUGGCAUUGUGGAACAAUGCUGUACCAGCAUCUGCUCCCUCUACCAGCUGGAGAACUACUGCAACUAG
  - example_title: cyclin dependent kinase inhibitor 2A
    pipeline_tag: mean-ribosome-load
    sequence_type: mRNA
    task: mean-ribosome-load
    text: >-
      AUGGAGCCGGCGGCGGGGAGCAGCAUGGAGCCUUCGGCUGACUGGCUGGCCACGGCCGCGGCCCGGGGUCGGGUAGAGGAGGUGCGGGCGCUGCUGGAGGCGGGGGCGCUGCCCAACGCACCGAAUAGUUACGGUCGGAGGCCGAUCCAGGUCAUGAUGAUGGGCAGCGCCCGAGUGGCGGAGCUGCUGCUGCUCCACGGCGCGGAGCCCAACUGCGCCGACCCCGCCACUCUCACCCGACCCGUGCACGACGCUGCCCGGGAGGGCUUCCUGGACACGCUGGUGGUGCUGCACCGGGCCGGGGCGCGGCUGGACGUGCGCGAUGCCUGGGGCCGUCUGCCCGUGGACCUGGCUGAGGAGCUGGGCCAUCGCGAUGUCGCACGGUACCUGCGCGCGGCUGCGGGGGGCACCAGAGGCAGUAACCAUGCCCGCAUAGAUGCCGCGGAAGGUCCCUCAGACAUCCCCGAUUGA
  - example_title: human papillomavirus type 16 E6
    pipeline_tag: mean-ribosome-load
    sequence_type: mRNA
    task: mean-ribosome-load
    text: >-
      AUGCACCAAAAGAGAACUGCAAUGUUUCAGGACCCACAGGAGCGACCCAGAAAGUUACCACAGUUAUGCACAGAGCUGCAAACAACUAUACAUGAUAUAAUAUUAGAAUGUGUGUACUGCAAGCAACAGUUACUGCGACGUGAGGUAUAUGACUUUGCUUUUCGGGAUUUAUGCAUAGUAUAUAGAGAUGGGAAUCCAUAUGCUGUAUGUGAUAAAUGUUUAAAGUUUUAUUCUAAAAUUAGUGAGUAUAGACAUUAUUGUUAUAGUUUGUAUGGAACAACAUUAGAACAGCAAUACAACAAACCGUUGUGUGAUUUGUUAAUUAGGUGUAUUAACUGUCAAAAGCCACUGUGUCCUGAAGAAAAGCAAAGACAUCUGGACAAAAAGCAAAGAUUCCAUAAUAUAAGGGGUCGGUGGACCGGUCGAUGUAUGUCUUGUUGCAGAUCAUCAAGAACACGUAGAGAAACCCAGCUGUAA
  - example_title: NRAS proto-oncogene
    pipeline_tag: mean-ribosome-load
    sequence_type: 5' UTR
    task: mean-ribosome-load
    text: >-
      GGGGCCGGAAGUGCCGCUCCUUGGUGGGGGCUGUUCAUGGCGGUUCCGGGGUCUCCAACAUUUUUCCCGGCUGUGGUCCUAAAUCUGUCCAAAGCAGAGGCAGUGGAGCUUGAGGUUCUUGCUGGUGUGAA
  - example_title: amyloid beta precursor protein
    pipeline_tag: mean-ribosome-load
    sequence_type: 5' UTR
    task: mean-ribosome-load
    text: >-
      GUCAGUUUCCUCGGCAGCGGUAGGCGAGAGCACGCGGAGGAGCGUGCGCGGGGGCCCCGGGAGACGGCGGCGGUGGCGGCGCGGGCAGAGCAAGGACGCGGCGGAUCCCACUCGCACAGCAGCGCACUCGGUGCCCCGCGCAGGGUCGCG
  - example_title: RUNX family transcription factor 1
    pipeline_tag: mean-ribosome-load
    sequence_type: 5' UTR
    task: mean-ribosome-load
    text: >-
      ACUUCUUUGGGCCUCAUAAACAACCACAGAACCACAAGUUGGGUAGCCUGGCAGUGUCAGAAGUCUGAACCCAGCAUAGUGGUCAGCAGGCAGGACGAAUCACACUGAAUGCAAACCACAGGGUUUCGCAGCGUGGUAAAAGAAAUCAUUGAGUCCCCCGCCUUCAGAAGAGGGUGCAUUUUCAGGAGGAAGCG
  - example_title: fragile X messenger ribonucleoprotein 1
    pipeline_tag: mean-ribosome-load
    sequence_type: 5' UTR
    task: mean-ribosome-load
    text: >-
      CUCAGUCAGGCGCUCAGCUCCGUUUCGGUUUCACUUCCGGUGGAGGGCCGCCUCUGAGCGGGCGGCGGGCCGACGGCGAGCGCGGGCGGCGGCGGUGACGGAGGCGCCGCUGCCAGGGGGCGUGCGGCAGCGCGGCGGCGGCGGCGGCGGCGGCGGCGGCGGAGGCGGCGGCGGCGGCGGCGGCGGCGGCGGCUGGGCCUCGAGCGCCCGCAGCCCACCUCUCGGGGGCGGGCUCCCGGCGCUAGCAGGGCUGAAGAGAAG
  - example_title: MYC proto-oncogene
    pipeline_tag: mean-ribosome-load
    sequence_type: 5' UTR
    task: mean-ribosome-load
    text: >-
      AACUCGCUGUAGUAAUUCCAGCGAGAGGCAGAGGGAGCGAGCGGGCGGCCGGCUAGGGUGGAAGAGCCGGGCGAGCAGAGCUGCGCUGCGGGCGUCCUGGGAAGGGAGAUCCGGAGCGAAUAGGGGGCUUCGCCUCUGGCCCAGCCCUCCCGCUGAUCCCCCAGCCAGCGGUCCGCAACCCUUGCCGCAUCCACGAAACUUUGCCCAUAGCAGCGGGCGGGCACUUUGCACUGGAACUUACAACACCCGAGCAAGGACGCGACUCUCCCGACGCGGGGAGGCUAUUCUGCCCAUUUGGGGACACUUCCCCGCCGCUGCCAGGACCCGCUUCUCUGAAAGGCUCUCCUUGCAGCUGCUUAGACG
  - example_title: activating transcription factor 4
    pipeline_tag: mean-ribosome-load
    sequence_type: 5' UTR
    task: mean-ribosome-load
    text: >-
      CAUUUCUACUUUGCCCGCCCACAGAUGUAGUUUUCUCUGCGCGUGUGCGUUUUCCCUCCUCCCCGCCCUCAGGGUCCACGGCCACCAUGGCGUAUUAGGGGCAGCAGUGCCUGCGGCAGCAUUGGCCUUUGCAGCGGCGGCAGCAGCACCAGGCUCUGCAGCGGCAACCCCCAGCGGCUUAAGCCAUGGCGCUUCUCACGGCAUUCAGCAGCAGCGUUGCUGUAACCGACAAAGACACCUUCGAAUUAAGCACAUUCCUCGAUUCCAGCAAAGCACCGCAAC
  - example_title: Human GPI protein p137
    pipeline_tag: mean-ribosome-load
    sequence_type: 3' UTR
    task: mean-ribosome-load
    text: >-
      UUUUUAAAAGGAAAAGAUACCAAAUGCCUGCUGCUACCACCCUUUUCAAUUGCUAUGUUUUGAAAGGCACCAGUAUGUGUUUUAGAUUGAUUUAAAUGUUUCAUUUAAAUCACGGACAGUAGUUUCAGUUCUGAUGGUAUAAGCAAAACAAAUAAAACGUUUAUAAAAGUUGUAUCUUGAAACACUGGUGUUCAACAGCUAGCAGCUUAUGUGAUUCACCCCAUGCCACGUUAGUGUCACAAAUUUUAUGGUUUAUCUCCAGCAACAUUUCUCUAGUACUUGCACUUAUUAUCUGAAUUC
  - example_title: nucleophosmin 1
    pipeline_tag: mean-ribosome-load
    sequence_type: 3' UTR
    task: mean-ribosome-load
    text: >-
      GAAAAUAGUUUAAACAAUUUGUUAAAAAAUUUUCCGUCUUAUUUCAUUUCUGUAACAGUUGAUAUCUGGCUGUCCUUUUUAUAAUGCAGAGUGAGAACUUUCCCUACCGUGUUUGAUAAAUGUUGUCCAGGUUCUAUUGCCAAGAAUGUGUUGUCCAAAAUGCCUGUUUAGUUUUUAAAGAUGGAACUCCACCCUUUGCUUGGUUUUAAGUAUGUAUGGAAUGUUAUGAUAGGACAUAGUAGUAGCGGUGGUCAGACAUGGAAAUGGUGGGGAGACAAAAAUAUACAUGUGAAAUAAAACUCAGUAUUUUAAUAAAGUAGCACGGUUUCUAUUGA
  - example_title: superoxide dismutase 1
    pipeline_tag: mean-ribosome-load
    sequence_type: 3' UTR
    task: mean-ribosome-load
    text: >-
      ACAUUCCCUUGGAUGUAGUCUGAGGCCCCUUAACUCAUCUGUUAUCCUGCUAGCUGUAGAAAUGUAUCCUGAUAAACAUUAAACACUGUAAUCUUAAAAGUGUAAUUGUGUGACUUUUUCAGAGUUGCUUUAAAGUACCUGUAGUGAGAAACUGAUUUAUGAUCACUUGGAAGAUUUGUAUAGUUUUAUAAAACUCAGUUAAAAUGUCUGUUUCAAUGACCUGUAUUUUGCCAGACUUAAAUCACAGAUGGGUAUUAAACUUGUCAGAAUUUCUUUGUCAUUCAAGCCUGUGAAUAAAAACCCUGUAUGGCACUUAUUAUGAGGCUAUUAAAAGAAUCCAAAUUCAAACUAAA
  - example_title: hemoglobin subunit alpha 2
    pipeline_tag: mean-ribosome-load
    sequence_type: 3' UTR
    task: mean-ribosome-load
    text: >-
      CUGGAGCCUCGGUAGCCGUUCCUCCUGCCCGCUGGGCCUCCCAACGGGCCCUCCUCCCCUCCUUGCACCGGCCCUUCCUGGUCUUUGAAUAAAGUCUGAGUGGGCAGCA
  - example_title: BRAF proto-oncogene
    pipeline_tag: mean-ribosome-load
    sequence_type: 3' UTR
    task: mean-ribosome-load
    text: >-
      AACAAAUGAGUGAGAGAGUUCAGGAGAGUAGCAACAAAAGGAAAAUAAAUGAACAUAUGUUUGCUUAUAUGUUAAAUUGAAUAAAAUACUCUCUUUUUUUUUAAGGUGAACCAAAGAACACUUGUGUGGUUAAAGACUAGAUAUAAUUUUUCCCCAAACUAAAAUUUAUACUUAACAUUGGAUUUUUAACAUCCAAGGGUUAAAAUACAUAGACAUUGCUAAAAAUUGGCAGAGCCUCUUCUAGAGGCUUUACUUUCUGUUCCGGGUUUGUAUCAUUCACUUGGUUAUUUUAAGUAGUAAACUUCAGUUUCUCAUGCAACUUUUGUUGCCAGCUAUCACAUGUCCACUAGGGACUCCAGAAGAAGACCCUACCUAUGCCUGUGUUUGCAGGUGAGAAGUUGGCAGUCGGUUAGCCUGGG
  - example_title: H3 clustered histone 1
    pipeline_tag: mean-ribosome-load
    sequence_type: 3' UTR
    task: mean-ribosome-load
    text: UUACUGUGGUCUCUCUGACGGUCCAAGCAAAGGCUCUUUUCAGAGCCACCACCUUUUC

Framepool

Frame-aware pooling convolutional network for predicting mean ribosome load from variable-length 5'UTR sequences.

Disclaimer

This is an UNOFFICIAL implementation of Predicting mean ribosome load for 5'UTR of any length using deep learning by Alexander Karollus, et al.

The OFFICIAL repository of Framepool is at Karollus/5UTR and the published Kipoi wrapper is at kipoi/models.

The MultiMolecule team has confirmed that the provided model and checkpoints are producing the same intermediate representations as the original implementation.

The team releasing Framepool did not write this model card for this model so this model card has been written by the MultiMolecule team.

Model Details

Framepool is a small 1D convolutional network that predicts the mean ribosome load (MRL) of a human 5' untranslated region from sequence alone. It extends the fixed-length network of Sample et al., 2019 with a frame-aware pooling layer that reverses the sequence to anchor reading frames at the start codon, slices the convolutional feature map into the three reading frames, and applies global max and masked global average pooling per frame. The pooled representation is length-independent and is consumed by a small dense head followed by a per-sub-library scaling regression that recalibrates the prediction across the two training libraries (egfp_unmod_1 and random). Please refer to the Training Details section for more information on the training process.

The released combined_residual model is recommended by the upstream authors for variant effect scoring.

Model Specification

Num Layers Hidden Size Num Parameters (M) FLOPs (G) MACs (G) Max Num Tokens
4 768 0.28 0.05 0.02 unlimited

Links

Usage

The model file depends on the multimolecule library. You can install it using pip:

pip install multimolecule

Direct Use

Mean Ribosome Load Prediction

You can use this model directly to predict the mean ribosome load of a 5'UTR sequence:

>>> from multimolecule import RnaTokenizer, FramepoolForSequencePrediction

>>> tokenizer = RnaTokenizer.from_pretrained("multimolecule/framepool")
>>> model = FramepoolForSequencePrediction.from_pretrained("multimolecule/framepool")
>>> output = model(**tokenizer("ACGUACGUACGUACGUACGUACGUACGUACGUACGUACGUACGUACGUAC", return_tensors="pt"))

>>> output.keys()
odict_keys(['logits'])

Interface

  • Input length: variable; the upstream MPRA training data is 25-100 nt 5'UTR but the model accepts any length because of frame-aware pooling
  • Alphabet: RNA (A, C, G, U); [RnaTokenizer][multimolecule.RnaTokenizer] converts T to U; N and other non-canonical tokens are encoded as all-zero columns and ignored by the masked pooling
  • Padding: zero-padding is supported via attention_mask and is excluded from pooling
  • Output: single scalar per sequence — predicted mean ribosome load (logits, shape (batch_size, 1))
  • Auxiliary inputs: optional library_indicator (shape (batch_size, library_size)) selecting one of the two training sub-libraries for the scaling regression. Defaults to the random library, matching the upstream Kipoi variant effect interface

Variant Effect

Framepool supports paired reference/alternative scoring through the optional alternative_input_ids argument:

  • Single sequence (reference only): logits is the predicted mean ribosome load (one scalar per sequence)
  • Reference + alternative: logits is the log2 mean ribosome load fold change log2(MRL_alt / MRL_ref), matching the Kipoi UTRVariantEffectModel.predict_on_batch mrl_fold_change output
  • Reference and alternative sequences are scored independently; both must use the same library_indicator so that the scaling regression cancels out of the fold change
  • For the upstream "shifted-frame" variant effect outputs (shift_1, shift_2), prepend one or two zero columns (or N tokens) to both reference and alternative inputs before scoring, matching the Kipoi loop

Training Details

Framepool was trained on polysome-profiling MPRA data measuring the mean ribosome load of randomized 5'UTR sequences and uses frame-aware pooling so that a single network can score sequences of arbitrary length.

Training Data

Framepool was trained on the eGFP polysome-profiling MPRA libraries of Sample et al., 2019 in HEK293T cells: the fixed-length library (egfp_unmod_1, 50 nt) and the variable-length library (random, 25-100 nt). Approximately 260,000 sequences were used for training, with 20,000 held out for testing; additional validation was performed on endogenous data.

Training Procedure

Pre-training

  • Loss: mean squared error between the predicted and measured mean ribosome load
  • Optimizer: Adam with lr = 1e-3, beta_1 = 0.9, beta_2 = 0.999, epsilon = 1e-8
  • Epochs: 6
  • Mini-batch sampling: the two training libraries are mixed within every batch; a one-hot library indicator is fed to the scaling regression layer so that the network can absorb the library-specific offset

Citation 

@article{karollus2021predicting,
  author    = {Karollus, Alexander and Avsec, {\v Z}iga and Gagneur, Julien},
  title     = {Predicting mean ribosome load for 5{\textquoteright}UTR of any length using deep learning},
  journal   = {PLOS Computational Biology},
  volume    = {17},
  number    = {5},
  pages     = {e1008982},
  year      = {2021},
  publisher = {Public Library of Science},
  doi       = {10.1371/journal.pcbi.1008982}
}

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 Framepool 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