{"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/eccdnamamba-a-pre-trained-model-for-ultra","title":"eccDNAMamba: A Pre-Trained Model for Ultra-Long eccDNA Sequence Analysis","arxiv_id":"2506.18940","date":"2025-06-22","proceeding":null,"authors":["Zhenke Liu","Jien Li","Ziqi Zhang"],"abstract":"Extrachromosomal circular DNA (eccDNA) plays key regulatory roles and contributes to oncogene overexpression in cancer through high-copy amplification and long-range interactions. Despite advances in modeling, no pre-trained models currently support full-length circular eccDNA for downstream analysis. Existing genomic models are either limited to single-nucleotide resolution or hindered by the inefficiency of the quadratic attention mechanism. Here, we introduce eccDNAMamba, the first bidirectional state-space encoder tailored for circular DNA sequences. It combines forward and reverse passes for full-context representation learning with linear-time complexity, and preserves circular structure through a novel augmentation strategy. Tested on two real-world datasets, eccDNAMamba achieves strong classification performance and scales to sequences up to 200 Kbp, offering a robust and efficient framework for modeling circular genomes. Our codes are available at https://github.com/zzq1zh/GenAI-Lab.","url_abs":"https://arxiv.org/abs/2506.18940v1","url_pdf":"https://arxiv.org/pdf/2506.18940v1.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":"eccdnamamba-a-pre-trained-model-for-ultra","repo_url":"https://github.com/zzq1zh/genai-lab","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2506.18940","atlas_url":"https://app.syntology.ai/?focus=2506.18940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18940"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zzq1zh/genai-lab","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"d02d4a2ae6122ca6","entry":"compute_metrics","repo":"zzq1zh/genai-lab","repo_kind":"official","path":"finetune_sample.py","file_url":"https://github.com/zzq1zh/genai-lab/blob/HEAD/finetune_sample.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d02d4a2ae6122ca6"}},{"code_sha256_prefix":"c4c3134ec6ce2148","entry":"integrated_gradients_margin","repo":"zzq1zh/genai-lab","repo_kind":"official","path":"ig.py","file_url":"https://github.com/zzq1zh/genai-lab/blob/HEAD/ig.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c4c3134ec6ce2148"}},{"code_sha256_prefix":"0be44262a2994a5c","entry":"patch_mixer_forward_to_accept_embeddings","repo":"zzq1zh/genai-lab","repo_kind":"official","path":"BiMambaForMaskedLM.py","file_url":"https://github.com/zzq1zh/genai-lab/blob/HEAD/BiMambaForMaskedLM.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0be44262a2994a5c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}