{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/model-decides-how-to-tokenize-adaptive-dna","title":"Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA","arxiv_id":"2412.13716","date":"2024-12-18","proceeding":null,"authors":["Lifeng Qiao","Peng Ye","Yuchen Ren","Weiqiang Bai","Chaoqi Liang","Xinzhu Ma","Nanqing Dong","Wanli Ouyang"],"abstract":"Foundation models have made significant strides in understanding the genomic language of DNA sequences. However, previous models typically adopt the tokenization methods designed for natural language, which are unsuitable for DNA sequences due to their unique characteristics. In addition, the optimal approach to tokenize DNA remains largely under-explored, and may not be intuitively understood by humans even if discovered. To address these challenges, we introduce MxDNA, a novel framework where the model autonomously learns an effective DNA tokenization strategy through gradient decent. MxDNA employs a sparse Mixture of Convolution Experts coupled with a deformable convolution to model the tokenization process, with the discontinuous, overlapping, and ambiguous nature of meaningful genomic segments explicitly considered. On Nucleotide Transformer Benchmarks and Genomic Benchmarks, MxDNA demonstrates superior performance to existing methods with less pretraining data and time, highlighting its effectiveness. Finally, we show that MxDNA learns unique tokenization strategy distinct to those of previous methods and captures genomic functionalities at a token level during self-supervised pretraining. Our MxDNA aims to provide a new perspective on DNA tokenization, potentially offering broad applications in various domains and yielding profound insights.","url_abs":"https://arxiv.org/abs/2412.13716v1","url_pdf":"https://arxiv.org/pdf/2412.13716v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"model-decides-how-to-tokenize-adaptive-dna","repo_url":"https://github.com/qiaoqiaolf/mxdna","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"adopt","method_name":"ADOPT"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"deformable-convolution","method_name":"Deformable Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.13716","atlas_url":"https://app.syntology.ai/?focus=2412.13716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13716"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/qiaoqiaoLF/MxDNA","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ML-Bioinfo-CEITEC/genomic_benchmarks","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/qiaoqiaolf/mxdna","reach":{"status":"ok"}}],"summary":{"ran":1,"ran_honours":1,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"found_in_text":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"cbd67f3ca95798ed","entry":"check_seq_lengths","repo":"ML-Bioinfo-CEITEC/genomic_benchmarks","repo_kind":"found_in_text","path":"src/genomic_benchmarks/dataset_getters/utils.py","file_url":"https://github.com/ML-Bioinfo-CEITEC/genomic_benchmarks/blob/HEAD/src/genomic_benchmarks/dataset_getters/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cbd67f3ca95798ed"}},{"code_sha256_prefix":"2b59f06b73779328","entry":"find_closest_factor","repo":"qiaoqiaoLF/MxDNA","repo_kind":"official","path":"mxdna.py","file_url":"https://github.com/qiaoqiaoLF/MxDNA/blob/HEAD/mxdna.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2b59f06b73779328"}},{"code_sha256_prefix":"8fbbffe8d2eae23f","entry":"reorder_fn","repo":"qiaoqiaoLF/MxDNA","repo_kind":"official","path":"mxdna.py","file_url":"https://github.com/qiaoqiaoLF/MxDNA/blob/HEAD/mxdna.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8fbbffe8d2eae23f"}},{"code_sha256_prefix":"3e8676a1c26806c3","entry":"download_from_cloud_cache","repo":"ML-Bioinfo-CEITEC/genomic_benchmarks","repo_kind":"found_in_text","path":"src/genomic_benchmarks/loc2seq/cloud_caching.py","file_url":"https://github.com/ML-Bioinfo-CEITEC/genomic_benchmarks/blob/HEAD/src/genomic_benchmarks/loc2seq/cloud_caching.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e8676a1c26806c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}