--- datasets: - multimolecule/rnacentral library_name: multimolecule license: agpl-3.0 mask_token: pipeline_tag: fill-mask tags: - Biology - RNA - ncRNA - rna widget: - example_title: microRNA 21 mask_index: 11 mask_index_1based: 12 masked_char: A output: - label: G score: 0.168747 - label: U score: 0.146559 - label: A score: 0.145257 - label: C score: 0.139641 - label: '*' score: 0.100469 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: UAGCUUAUCAGCUGAUGUUGA - example_title: microRNA 146a mask_index: 10 mask_index_1based: 11 masked_char: A output: - label: C score: 0.155633 - label: U score: 0.148283 - label: G score: 0.142845 - label: A score: 0.137834 - label: '*' score: 0.104045 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: UGAGAACUGAUUCCAUGGGUU - example_title: microRNA 155 mask_index: 15 mask_index_1based: 16 masked_char: A output: - label: U score: 0.176903 - label: A score: 0.170807 - label: G score: 0.14713 - label: '*' score: 0.100737 - label: C score: 0.099537 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: UUAAUGCUAAUCGUGUAGGGGUU - example_title: RNA component of mitochondrial RNA processing endoribonuclease mask_index: 11 mask_index_1based: 12 masked_char: A output: - label: A score: 0.953098 - label: '?' score: 0.011311 - label: '*' score: 0.009707 - label: . score: 0.008587 - label: '|' score: 0.007325 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: GGUUCGUGCUGAGGCCUGUAUCCUAGGCUACACACUGAGGACUCUGUUCCUCCCCUUUCCGCCUAGGGGAAAGUCCCCGGACCUCGGGCAGAGAGUGCCACGUGCAUACGCACGUAGACAUUCCCCGCUUCCCACUCCAAAGUCCGCCAAGAAGCGUAUCCCGCUGAGCGGCGUGGCGCGGGGGCGUCAUCCGUCAGCUCCCUCUAGUUACGCAGGCAGUGCGUGUCCGCGCACCAACCACACGGGGCUCAUUCUCAGCGCGGCUGUAAAAAAAAA - example_title: 7SK small nuclear RNA mask_index: 13 mask_index_1based: 14 masked_char: A output: - label: A score: 0.878196 - label: '*' score: 0.025704 - label: '?' score: 0.025041 - label: '|' score: 0.023912 - label: . score: 0.019355 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: GGAUGUGAGGGCGUCUGGCUGCGACAUCUGUCACCCCAUUGAUCGCCAGGGUUGAUUCGGCUGAUCUGGCUGGCUAGGCGGGUGUCCCCUUCCUCCCUCACCGCUCCAUGUGCGUCCCUCCCGAAGCUGCGCGCUCGGUCGAAGAGGACGACCAUCCCCGAUAGAGGAGGACCGGUCUUCGGUCAAGGGUAUACGAGUAGCUGCGCUCCCCUGCUAGAACCUCCAAACAAGCUCUCAAGGUCCAUUUGUAGGAGAACGUAGGGUAGUCAAGCUUCCAAGACUCCAGACACAUCCAAAUGAGGCGCUGCAUGUGGCAGUCUGCCUUUCUUUU - example_title: telomerase RNA component mask_index: 23 mask_index_1based: 24 masked_char: A output: - label: G score: 0.198944 - label: C score: 0.173069 - label: A score: 0.118644 - label: '*' score: 0.108538 - label: U score: 0.102553 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: GGGUUGCGGAGGGUGGGCCUGGGGGGGUGGUGGCCAUUUUUUGUCUAACCCUAACUGAGAAGGGCGUAGGCGCCGUGCUUUUGCUCCCCGCGCGCUGUUUUUCUCGCUGACUUUCAGCGGGCGGAAAAGCCUCGGCCUGCCGCCUUCCACCGUUCAUUCUAGAGCAAACAAAAAAUGUCAGCUGCUGGCCCGUUCGCCCCUCCCGGGGACCUGCGGCGGGUCGCCUGCCCAGCCCCCGAACCCCGCCUGGAGGCCGCGGUCGGCCCGGGGCUUCUCCGGAGGCACCCACUGCCACCGCGAAGAGUUGGGCUCUGUCAGCCGCGGGUCUCUCGGGGGCGAGGGCGAGGUUCAGGCCUUUCAGGCCGCAGGAAGAGGAACGGAGCGAGUCCCCGCGCGCGGCGCGAUUCCCUGAGCUGUGGGACGUGCACCCAGGACUCGGCUCACACAUGC - example_title: vault RNA 2-1 mask_index: 12 mask_index_1based: 13 masked_char: A output: - label: A score: 0.496866 - label: G score: 0.320907 - label: '*' score: 0.043652 - label: '?' score: 0.038903 - label: '|' score: 0.037784 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: CGGGUCGGAGUUGCUCAAGCGGUUACCUCCUCAUGCCGGACUUUCUAUCUGUCCAUCUCUGUGCUGGGGUUCGAGACCCGCGGGUGCUUACUGACCCUUUUAUGCAA - example_title: brain cytoplasmic RNA 1 mask_index: 18 mask_index_1based: 19 masked_char: A output: - label: A score: 0.858781 - label: '*' score: 0.035093 - label: '|' score: 0.026986 - label: '?' score: 0.025596 - label: . score: 0.021575 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: GGCCGGGCGCGGUGGCUCCGCCUGUAAUCCCAGCUCUCAGGGAGGCUAAGAGGCGGGAGGAUAGCUUGAGCCCAGGAGUUCGAGACCUGCCUGGGCAAUAUAGCGAGACCCCGUUCUCCAGAAAAAGGAAAAAAAAAAACAAAAGACAAAAAAAAAAUAAGCGUAACUUCCCUCAAAGCAACAACCCCCCCCCCCCUUU - example_title: HIV-1 TAR-WT mask_index: 13 mask_index_1based: 14 masked_char: A output: - label: A score: 0.849498 - label: '*' score: 0.028416 - label: . score: 0.025998 - label: '?' score: 0.023328 - label: '-' score: 0.022898 pipeline_tag: fill-mask sequence_type: ncRNA task: fill-mask text: GGUCUCUCUGGUUGACCAGAUCUGAGCCUGGGAGCUCUCUGGCUAACUAGGGAACC - example_title: prion protein (Kanno blood group) mask_index: 21 mask_index_1based: 22 masked_char: A output: - label: C score: 0.248873 - label: G score: 0.194196 - label: A score: 0.107682 - label: '?' score: 0.093277 - label: '*' score: 0.087274 pipeline_tag: fill-mask sequence_type: mRNA task: fill-mask text: AUGGCGAACCUUGGCUGCUGGUGCUGGUUCUCUUUGUGGCCACAUGGAGUGACCUGGGCCUCUGC - example_title: interleukin 10 mask_index: 11 mask_index_1based: 12 masked_char: A output: - label: U score: 0.29524 - label: A score: 0.221026 - label: '*' score: 0.088464 - label: . score: 0.082645 - label: '?' score: 0.080371 pipeline_tag: fill-mask sequence_type: mRNA task: fill-mask text: AUGCACAGCUCGCACUGCUCUGUUGCCUGGUCCUCCUGACUGGGGUGAGGGCC - example_title: Zaire ebolavirus mask_index: 11 mask_index_1based: 12 masked_char: A output: - label: U score: 0.289199 - label: A score: 0.255983 - label: '*' score: 0.086748 - label: C score: 0.081984 - label: '?' score: 0.081224 pipeline_tag: fill-mask sequence_type: mRNA task: fill-mask text: AAUGUUCAAACCUUUGUGAAGCUCUGUUAGCUGAUGGUCUUGCUAAAGCAUUUCCUAGCAAUAUGAUGGUAGUCACAGAGCGUGAGCAAAAAGAAAGCUUAUUGCAUCAAGCAUCAUGGCACCACACAAGUGAUGAUUUUGGUGAGCAUGCCACAGUUAGAGGGAGUAGCUUUGUAACUGAUUUAGAGAAAUACAAUCUUGCAUUUAGAUAUGAGUUUACAGCACCUUUUAUAGAAUAUUGUAACCGUUGCUAUGGUGUUAAGAAUGUUUUUAAUUGGAUGCAUUAUACAAUCCCACAGUGUUAU - example_title: SARS coronavirus mask_index: 14 mask_index_1based: 15 masked_char: A output: - label: U score: 0.166609 - label: A score: 0.154665 - label: C score: 0.144368 - label: G score: 0.136409 - label: '?' score: 0.104779 pipeline_tag: fill-mask sequence_type: mRNA task: fill-mask text: AUGUUUAUUUUCUUUUAUUUCUUACUCUCACUAGUGGUAGUGACCUUGACCGGUGCACCACUUUUGAUGAUGUUCAAGCUCCUAAUUACACUCAACAUACUUCAUCUAUGAGGGGGGUUUACUAUCCUGAUGAAAUUUUUAGAUCAGACACUCUUUAUUUAACUCAGGAUUUAUUUCUUCCAUUUUAUUCUAAUGUUACAGGGUUUCAUACUAUUAAUCAUACGUUUGACAACCCUGUCAUACCUUUUAAGGAUGGUAUUUAUUUUGCUGCCACAGAGAAAUCAAAUGUUGUCCGUGGUUGGGUUUUUGGUUCUACCAUGAACAACAAGUCACAGUCGGUGAUUAUUAUUAACAAUUCUACUAAUGUUGUUAUACGAGCAUGUAACUUUGAAUUGUGUGACAACCCUUUCUUUGCUGUUUCUAAACCCAUGGGUACACAGACACAUACUAUGAUAUUCGAUAAUGCAUUUAAAUGCACUUUCGAGUACAUAUCU - example_title: insulin mask_index: 12 mask_index_1based: 13 masked_char: A output: - label: C score: 0.521012 - label: G score: 0.185957 - label: '?' score: 0.057102 - label: '*' score: 0.055505 - label: '-' score: 0.046003 pipeline_tag: fill-mask sequence_type: mRNA task: fill-mask text: AUGGCCCUGUGGUGCGCCUCCUGCCCCUGCUGGCGCUGCUGGCCCUCUGGGGACCUGACCCAGCCGCAGCCUUUGUGAACCAACACCUGUGCGGCUCACACCUGGUGGAAGCUCUCUACCUAGUGUGCGGGGAACGAGGCUUCUUCUACACACCCAAGACCCGCCGGGAGGCAGAGGACCUGCAGGUGGGGCAGGUGGAGCUGGGCGGGGGCCCUGGUGCAGGCAGCCUGCAGCCCUUGGCCCUGGAGGGGUCCCUGCAGAAGCGUGGCAUUGUGGAACAAUGCUGUACCAGCAUCUGCUCCCUCUACCAGCUGGAGAACUACUGCAACUAG - example_title: cyclin dependent kinase inhibitor 2A mask_index: 18 mask_index_1based: 19 masked_char: A output: - label: A score: 0.232033 - label: G score: 0.227 - label: C score: 0.111424 - label: '*' score: 0.091306 - label: '?' score: 0.085279 pipeline_tag: fill-mask sequence_type: mRNA task: fill-mask text: AUGGAGCCGGCGGCGGGGGCAGCAUGGAGCCUUCGGCUGACUGGCUGGCCACGGCCGCGGCCCGGGGUCGGGUAGAGGAGGUGCGGGCGCUGCUGGAGGCGGGGGCGCUGCCCAACGCACCGAAUAGUUACGGUCGGAGGCCGAUCCAGGUCAUGAUGAUGGGCAGCGCCCGAGUGGCGGAGCUGCUGCUGCUCCACGGCGCGGAGCCCAACUGCGCCGACCCCGCCACUCUCACCCGACCCGUGCACGACGCUGCCCGGGAGGGCUUCCUGGACACGCUGGUGGUGCUGCACCGGGCCGGGGCGCGGCUGGACGUGCGCGAUGCCUGGGGCCGUCUGCCCGUGGACCUGGCUGAGGAGCUGGGCCAUCGCGAUGUCGCACGGUACCUGCGCGCGGCUGCGGGGGGCACCAGAGGCAGUAACCAUGCCCGCAUAGAUGCCGCGGAAGGUCCCUCAGACAUCCCCGAUUGA - example_title: human papillomavirus type 16 E6 mask_index: 10 mask_index_1based: 11 masked_char: A output: - label: A score: 0.243365 - label: G score: 0.175646 - label: U score: 0.167163 - label: '*' score: 0.087594 - label: '?' score: 0.079787 pipeline_tag: fill-mask sequence_type: mRNA task: fill-mask text: AUGCACCAAAGAGAACUGCAAUGUUUCAGGACCCACAGGAGCGACCCAGAAAGUUACCACAGUUAUGCACAGAGCUGCAAACAACUAUACAUGAUAUAAUAUUAGAAUGUGUGUACUGCAAGCAACAGUUACUGCGACGUGAGGUAUAUGACUUUGCUUUUCGGGAUUUAUGCAUAGUAUAUAGAGAUGGGAAUCCAUAUGCUGUAUGUGAUAAAUGUUUAAAGUUUUAUUCUAAAAUUAGUGAGUAUAGACAUUAUUGUUAUAGUUUGUAUGGAACAACAUUAGAACAGCAAUACAACAAACCGUUGUGUGAUUUGUUAAUUAGGUGUAUUAACUGUCAAAAGCCACUGUGUCCUGAAGAAAAGCAAAGACAUCUGGACAAAAAGCAAAGAUUCCAUAAUAUAAGGGGUCGGUGGACCGGUCGAUGUAUGUCUUGUUGCAGAUCAUCAAGAACACGUAGAGAAACCCAGCUGUAA - example_title: NRAS proto-oncogene mask_index: 36 mask_index_1based: 37 masked_char: A output: - label: C score: 0.304276 - label: U score: 0.149828 - label: '*' score: 0.092997 - label: G score: 0.091145 - label: '?' score: 0.091003 pipeline_tag: fill-mask sequence_type: 5' UTR task: fill-mask text: GGGGCCGGAAGUGCCGCUCCUUGGUGGGGGCUGUUCUGGCGGUUCCGGGGUCUCCAACAUUUUUCCCGGCUGUGGUCCUAAAUCUGUCCAAAGCAGAGGCAGUGGAGCUUGAGGUUCUUGCUGGUGUGAA - example_title: amyloid beta precursor protein mask_index: 15 mask_index_1based: 16 masked_char: A output: - label: G score: 0.311659 - label: C score: 0.129073 - label: A score: 0.106234 - label: '*' score: 0.087032 - label: '?' score: 0.086813 pipeline_tag: fill-mask sequence_type: 5' UTR task: fill-mask text: GUCAGUUUCCUCGGCGCGGUAGGCGAGAGCACGCGGAGGAGCGUGCGCGGGGGCCCCGGGAGACGGCGGCGGUGGCGGCGCGGGCAGAGCAAGGACGCGGCGGAUCCCACUCGCACAGCAGCGCACUCGGUGCCCCGCGCAGGGUCGCG - example_title: RUNX family transcription factor 1 mask_index: 15 mask_index_1based: 16 masked_char: A output: - label: A score: 0.197562 - label: C score: 0.176787 - label: U score: 0.168496 - label: '*' score: 0.101014 - label: '?' score: 0.092522 pipeline_tag: fill-mask sequence_type: 5' UTR task: fill-mask text: ACUUCUUUGGGCCUCUAAACAACCACAGAACCACAAGUUGGGUAGCCUGGCAGUGUCAGAAGUCUGAACCCAGCAUAGUGGUCAGCAGGCAGGACGAAUCACACUGAAUGCAAACCACAGGGUUUCGCAGCGUGGUAAAAGAAAUCAUUGAGUCCCCCGCCUUCAGAAGAGGGUGCAUUUUCAGGAGGAAGCG - example_title: fragile X messenger ribonucleoprotein 1 mask_index: 15 mask_index_1based: 16 masked_char: A output: - label: G score: 0.188867 - label: C score: 0.181166 - label: A score: 0.123497 - label: U score: 0.102765 - label: '*' score: 0.095445 pipeline_tag: fill-mask sequence_type: 5' UTR task: fill-mask text: CUCAGUCAGGCGCUCGCUCCGUUUCGGUUUCACUUCCGGUGGAGGGCCGCCUCUGAGCGGGCGGCGGGCCGACGGCGAGCGCGGGCGGCGGCGGUGACGGAGGCGCCGCUGCCAGGGGGCGUGCGGCAGCGCGGCGGCGGCGGCGGCGGCGGCGGCGGCGGAGGCGGCGGCGGCGGCGGCGGCGGCGGCGGCUGGGCCUCGAGCGCCCGCAGCCCACCUCUCGGGGGCGGGCUCCCGGCGCUAGCAGGGCUGAAGAGAAG - example_title: MYC proto-oncogene mask_index: 10 mask_index_1based: 11 masked_char: A output: - label: G score: 0.198574 - label: U score: 0.195496 - label: C score: 0.115815 - label: '?' score: 0.095686 - label: A score: 0.093795 pipeline_tag: fill-mask sequence_type: 5' UTR task: fill-mask text: AACUCGCUGUGUAAUUCCAGCGAGAGGCAGAGGGAGCGAGCGGGCGGCCGGCUAGGGUGGAAGAGCCGGGCGAGCAGAGCUGCGCUGCGGGCGUCCUGGGAAGGGAGAUCCGGAGCGAAUAGGGGGCUUCGCCUCUGGCCCAGCCCUCCCGCUGAUCCCCCAGCCAGCGGUCCGCAACCCUUGCCGCAUCCACGAAACUUUGCCCAUAGCAGCGGGCGGGCACUUUGCACUGGAACUUACAACACCCGAGCAAGGACGCGACUCUCCCGACGCGGGGAGGCUAUUCUGCCCAUUUGGGGACACUUCCCCGCCGCUGCCAGGACCCGCUUCUCUGAAAGGCUCUCCUUGCAGCUGCUUAGACG - example_title: activating transcription factor 4 mask_index: 20 mask_index_1based: 21 masked_char: A output: - label: U score: 0.22132 - label: C score: 0.163486 - label: G score: 0.126038 - label: '*' score: 0.09895 - label: '?' score: 0.094678 pipeline_tag: fill-mask sequence_type: 5' UTR task: fill-mask text: CAUUUCUACUUUGCCCGCCCCAGAUGUAGUUUUCUCUGCGCGUGUGCGUUUUCCCUCCUCCCCGCCCUCAGGGUCCACGGCCACCAUGGCGUAUUAGGGGCAGCAGUGCCUGCGGCAGCAUUGGCCUUUGCAGCGGCGGCAGCAGCACCAGGCUCUGCAGCGGCAACCCCCAGCGGCUUAAGCCAUGGCGCUUCUCACGGCAUUCAGCAGCAGCGUUGCUGUAACCGACAAAGACACCUUCGAAUUAAGCACAUUCCUCGAUUCCAGCAAAGCACCGCAAC - example_title: Human GPI protein p137 mask_index: 11 mask_index_1based: 12 masked_char: A output: - label: A score: 0.26194 - label: G score: 0.157739 - label: '*' score: 0.102326 - label: U score: 0.096553 - label: C score: 0.089171 pipeline_tag: fill-mask sequence_type: 3' UTR task: fill-mask text: UUUUUAAAAGGAAAGAUACCAAAUGCCUGCUGCUACCACCCUUUUCAAUUGCUAUGUUUUGAAAGGCACCAGUAUGUGUUUUAGAUUGAUUUAAAUGUUUCAUUUAAAUCACGGACAGUAGUUUCAGUUCUGAUGGUAUAAGCAAAACAAAUAAAACGUUUAUAAAAGUUGUAUCUUGAAACACUGGUGUUCAACAGCUAGCAGCUUAUGUGAUUCACCCCAUGCCACGUUAGUGUCACAAAUUUUAUGGUUUAUCUCCAGCAACAUUUCUCUAGUACUUGCACUUAUUAUCUGAAUUC - example_title: nucleophosmin 1 mask_index: 11 mask_index_1based: 12 masked_char: A output: - label: U score: 0.303558 - label: A score: 0.127824 - label: '*' score: 0.09955 - label: '?' score: 0.090851 - label: C score: 0.085789 pipeline_tag: fill-mask sequence_type: 3' UTR task: fill-mask text: GAAAAUAGUUUAACAAUUUGUUAAAAAAUUUUCCGUCUUAUUUCAUUUCUGUAACAGUUGAUAUCUGGCUGUCCUUUUUAUAAUGCAGAGUGAGAACUUUCCCUACCGUGUUUGAUAAAUGUUGUCCAGGUUCUAUUGCCAAGAAUGUGUUGUCCAAAAUGCCUGUUUAGUUUUUAAAGAUGGAACUCCACCCUUUGCUUGGUUUUAAGUAUGUAUGGAAUGUUAUGAUAGGACAUAGUAGUAGCGGUGGUCAGACAUGGAAAUGGUGGGGAGACAAAAAUAUACAUGUGAAAUAAAACUCAGUAUUUUAAUAAAGUAGCACGGUUUCUAUUGA - example_title: superoxide dismutase 1 mask_index: 12 mask_index_1based: 13 masked_char: A output: - label: C score: 0.203252 - label: A score: 0.182873 - label: U score: 0.133046 - label: '*' score: 0.098951 - label: '?' score: 0.092725 pipeline_tag: fill-mask sequence_type: 3' UTR task: fill-mask text: ACAUUCCCUUGGUGUAGUCUGAGGCCCCUUAACUCAUCUGUUAUCCUGCUAGCUGUAGAAAUGUAUCCUGAUAAACAUUAAACACUGUAAUCUUAAAAGUGUAAUUGUGUGACUUUUUCAGAGUUGCUUUAAAGUACCUGUAGUGAGAAACUGAUUUAUGAUCACUUGGAAGAUUUGUAUAGUUUUAUAAAACUCAGUUAAAAUGUCUGUUUCAAUGACCUGUAUUUUGCCAGACUUAAAUCACAGAUGGGUAUUAAACUUGUCAGAAUUUCUUUGUCAUUCAAGCCUGUGAAUAAAAACCCUGUAUGGCACUUAUUAUGAGGCUAUUAAAAGAAUCCAAAUUCAAACUAAA - example_title: hemoglobin subunit alpha 2 mask_index: 13 mask_index_1based: 14 masked_char: A output: - label: G score: 0.249439 - label: C score: 0.132491 - label: U score: 0.124968 - label: '*' score: 0.098374 - label: '?' score: 0.093836 pipeline_tag: fill-mask sequence_type: 3' UTR task: fill-mask text: CUGGAGCCUCGGUGCCGUUCCUCCUGCCCGCUGGGCCUCCCAACGGGCCCUCCUCCCCUCCUUGCACCGGCCCUUCCUGGUCUUUGAAUAAAGUCUGAGUGGGCAGCA - example_title: BRAF proto-oncogene mask_index: 12 mask_index_1based: 13 masked_char: A output: - label: A score: 0.446064 - label: U score: 0.15514 - label: G score: 0.086402 - label: '*' score: 0.071098 - label: . score: 0.066937 pipeline_tag: fill-mask sequence_type: 3' UTR task: fill-mask text: AACAAAUGAGUGGAGAGUUCAGGAGAGUAGCAACAAAAGGAAAAUAAAUGAACAUAUGUUUGCUUAUAUGUUAAAUUGAAUAAAAUACUCUCUUUUUUUUUAAGGUGAACCAAAGAACACUUGUGUGGUUAAAGACUAGAUAUAAUUUUUCCCCAAACUAAAAUUUAUACUUAACAUUGGAUUUUUAACAUCCAAGGGUUAAAAUACAUAGACAUUGCUAAAAAUUGGCAGAGCCUCUUCUAGAGGCUUUACUUUCUGUUCCGGGUUUGUAUCAUUCACUUGGUUAUUUUAAGUAGUAAACUUCAGUUUCUCAUGCAACUUUUGUUGCCAGCUAUCACAUGUCCACUAGGGACUCCAGAAGAAGACCCUACCUAUGCCUGUGUUUGCAGGUGAGAAGUUGGCAGUCGGUUAGCCUGGG - example_title: H3 clustered histone 1 mask_index: 17 mask_index_1based: 18 masked_char: A output: - label: A score: 0.185575 - label: G score: 0.163741 - label: U score: 0.136054 - label: C score: 0.105364 - label: '*' score: 0.102284 pipeline_tag: fill-mask sequence_type: 3' UTR task: fill-mask text: UUACUGUGGUCUCUCUGCGGUCCAAGCAAAGGCUCUUUUCAGAGCCACCACCUUUUC --- # ERNIE-RNA Pre-trained model on non-coding RNA (ncRNA) using a masked language modeling (MLM) objective. ## Disclaimer This is an UNOFFICIAL implementation of the [ERNIE-RNA: An RNA Language Model with Structure-enhanced Representations](https://doi.org/10.1101/2024.03.17.585376) by Weijie Yin, Zhaoyu Zhang, Liang He, et al. The OFFICIAL repository of ERNIE-RNA is at [Bruce-ywj/ERNIE-RNA](https://github.com/Bruce-ywj/ERNIE-RNA). > [!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 ERNIE-RNA did not write this model card for this model so this model card has been written by the MultiMolecule team.** ## Model Details ERNIE-RNA is a [bert](https://huggingface.co/google-bert/bert-base-uncased)-style model pre-trained on a large corpus of non-coding RNA sequences in a self-supervised fashion. This means that the model was trained on the raw nucleotides of RNA sequences only, with an automatic process to generate inputs and labels from those texts. Please refer to the [Training Details](#training-details) section for more information on the training process. ### Variants - **[multimolecule/ernierna](https://huggingface.co/multimolecule/ernierna)**: The ERNIE-RNA model pre-trained on non-coding RNA sequences. - **[multimolecule/ernierna-ss](https://huggingface.co/multimolecule/ernierna-ss)**: The ERNIE-RNA model fine-tuned on RNA secondary structure prediction. ### Model Specification | Num Layers | Hidden Size | Num Heads | Intermediate Size | Num Parameters (M) | FLOPs (G) | MACs (G) | Max Num Tokens | | ---------- | ----------- | --------- | ----------------- | ------------------ | --------- | -------- | -------------- | | 12 | 768 | 12 | 3072 | 85.67 | 96.92 | 48.34 | 1024 | ### Links - **Code**: [multimolecule.ernierna](https://github.com/DLS5-Omics/multimolecule/tree/master/multimolecule/models/ernierna) - **Data**: [multimolecule/rnacentral](https://huggingface.co/datasets/multimolecule/rnacentral) - **Paper**: [ERNIE-RNA: An RNA Language Model with Structure-enhanced Representations](https://doi.org/10.1101/2024.03.17.585376) - **Developed by**: Weijie Yin, Zhaoyu Zhang, Liang He, Rui Jiang, Shuo Zhang, Gan Liu, Xuegong Zhang, Tao Qin, Zhen Xie - **Model type**: [BERT](https://huggingface.co/google-bert/bert-base-uncased) - [ERNIE](https://huggingface.co/nghuyong/ernie-3.0-base-zh) - **Original Repository**: [Bruce-ywj/ERNIE-RNA](https://github.com/Bruce-ywj/ERNIE-RNA) ## Usage The model file depends on the [`multimolecule`](https://multimolecule.danling.org) library. You can install it using pip: ```bash pip install multimolecule ``` ### Direct Use #### Masked Language Modeling You can use this model directly with a pipeline for masked language modeling: ```python import multimolecule # you must import multimolecule to register models from transformers import pipeline predictor = pipeline("fill-mask", model="multimolecule/ernierna") output = predictor("gguccucugguuagaccagaucugagccu") ``` ### Downstream Use #### Extract Features Here is how to use this model to get the features of a given sequence in PyTorch: ```python from multimolecule import RnaTokenizer, ErnieRnaModel tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna") model = ErnieRnaModel.from_pretrained("multimolecule/ernierna") text = "UAGCUUAUCAGACUGAUGUUG" input = tokenizer(text, return_tensors="pt") output = model(**input) ``` #### Sequence Classification / Regression > [!NOTE] > This model is not fine-tuned for any specific task. You will need to fine-tune the model on a downstream task to use it for sequence classification or regression. Here is how to use this model as backbone to fine-tune for a sequence-level task in PyTorch: ```python import torch from multimolecule import RnaTokenizer, ErnieRnaForSequencePrediction tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna") model = ErnieRnaForSequencePrediction.from_pretrained("multimolecule/ernierna") text = "UAGCUUAUCAGACUGAUGUUG" input = tokenizer(text, return_tensors="pt") label = torch.tensor([1]) output = model(**input, labels=label) ``` #### Token Classification / Regression > [!NOTE] > This model is not fine-tuned for any specific task. You will need to fine-tune the model on a downstream task to use it for token classification or regression. Here is how to use this model as backbone to fine-tune for a nucleotide-level task in PyTorch: ```python import torch from multimolecule import RnaTokenizer, ErnieRnaForTokenPrediction tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna") model = ErnieRnaForTokenPrediction.from_pretrained("multimolecule/ernierna") text = "UAGCUUAUCAGACUGAUGUUG" input = tokenizer(text, return_tensors="pt") label = torch.randint(2, (len(text), )) output = model(**input, labels=label) ``` #### Contact Classification / Regression > [!NOTE] > This model is not fine-tuned for any specific task. You will need to fine-tune the model on a downstream task to use it for contact classification or regression. Here is how to use this model as backbone to fine-tune for a contact-level task in PyTorch: ```python import torch from multimolecule import RnaTokenizer, ErnieRnaForContactPrediction tokenizer = RnaTokenizer.from_pretrained("multimolecule/ernierna") model = ErnieRnaForContactPrediction.from_pretrained("multimolecule/ernierna") text = "UAGCUUAUCAGACUGAUGUUG" input = tokenizer(text, return_tensors="pt") label = torch.randint(2, (len(text), len(text))) output = model(**input, labels=label) ``` ## Training Details ERNIE-RNA used Masked Language Modeling (MLM) as the pre-training objective: taking a sequence, the model randomly masks 15% of the tokens in the input then runs the entire masked sentence through the model and has to predict the masked tokens. This is comparable to the Cloze task in language modeling. ### Training Data The ERNIE-RNA model was pre-trained on [RNAcentral](https://multimolecule.danling.org/datasets/rnacentral). RNAcentral is a free, public resource that offers integrated access to a comprehensive and up-to-date set of non-coding RNA sequences provided by a collaborating group of [Expert Databases](https://rnacentral.org/expert-databases) representing a broad range of organisms and RNA types. ERNIE-RNA applied [CD-HIT (CD-HIT-EST)](https://sites.google.com/view/cd-hit) with a cut-off at 100% sequence identity to remove redundancy from the RNAcentral, resulting 25 million unique sequences. Sequences longer than 1024 nucleotides were subsequently excluded. The final dataset contains 20.4 million non-redundant RNA sequences. ERNIE-RNA preprocessed all tokens by replacing "T"s with "S"s. Note that [`RnaTokenizer`][multimolecule.RnaTokenizer] will convert "T"s to "U"s for you, you may disable this behaviour by passing `replace_T_with_U=False`. ### Training Procedure #### Preprocessing ERNIE-RNA used masked language modeling (MLM) as the pre-training objective. The masking procedure is similar to the one used in BERT: - Mask rate: 15% - Replacement: `` for 80% of masked tokens - Replacement: random token for 10% of masked tokens - Replacement: unchanged token for 10% of masked tokens #### Pre-training The model was trained on 24 NVIDIA V100 GPUs with 32GiB memories. - Learning rate: 1e-4 - Learning rate warm-up: 20,000 steps - Weight decay: 0.01 ## Citation ```bibtex @article {Yin2024.03.17.585376, author = {Yin, Weijie and Zhang, Zhaoyu and He, Liang and Jiang, Rui and Zhang, Shuo and Liu, Gan and Zhang, Xuegong and Qin, Tao and Xie, Zhen}, title = {ERNIE-RNA: An RNA Language Model with Structure-enhanced Representations}, elocation-id = {2024.03.17.585376}, year = {2024}, doi = {10.1101/2024.03.17.585376}, publisher = {Cold Spring Harbor Laboratory}, abstract = {With large amounts of unlabeled RNA sequences data produced by high-throughput sequencing technologies, pre-trained RNA language models have been developed to estimate semantic space of RNA molecules, which facilities the understanding of grammar of RNA language. However, existing RNA language models overlook the impact of structure when modeling the RNA semantic space, resulting in incomplete feature extraction and suboptimal performance across various downstream tasks. In this study, we developed a RNA pre-trained language model named ERNIE-RNA (Enhanced Representations with base-pairing restriction for RNA modeling) based on a modified BERT (Bidirectional Encoder Representations from Transformers) by incorporating base-pairing restriction with no MSA (Multiple Sequence Alignment) information. We found that the attention maps from ERNIE-RNA with no fine-tuning are able to capture RNA structure in the zero-shot experiment more precisely than conventional methods such as fine-tuned RNAfold and RNAstructure, suggesting that the ERNIE-RNA can provide comprehensive RNA structural representations. Furthermore, ERNIE-RNA achieved SOTA (state-of-the-art) performance after fine-tuning for various downstream tasks, including RNA structural and functional predictions. In summary, our ERNIE-RNA model provides general features which can be widely and effectively applied in various subsequent research tasks. Our results indicate that introducing key knowledge-based prior information in the BERT framework may be a useful strategy to enhance the performance of other language models.Competing Interest StatementOne patent based on the study was submitted by Z.X. and W.Y., which is entitled as "A Pre-training Approach for RNA Sequences and Its Applications"(application number, no 202410262527.5). The remaining authors declare no competing interests.}, URL = {https://www.biorxiv.org/content/early/2024/03/17/2024.03.17.585376}, eprint = {https://www.biorxiv.org/content/early/2024/03/17/2024.03.17.585376.full.pdf}, journal = {bioRxiv} } ``` > [!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 @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](https://github.com/DLS5-Omics/multimolecule/issues) for any questions or comments on the model card. Please contact the authors of the [ERNIE-RNA paper](https://doi.org/10.1101/2024.03.17.585376) for questions or comments on the paper/model. ## License This model implementation is licensed under the [GNU Affero General Public License](license.md). For additional terms and clarifications, please refer to our [License FAQ](license-faq.md). ```spdx SPDX-License-Identifier: AGPL-3.0-or-later ```