{"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/revisiting-k-mer-profile-for-effective-and","title":"Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning","arxiv_id":"2411.02125","date":"2024-11-04","proceeding":null,"authors":["Abdulkadir Celikkanat","Andres R. Masegosa","Thomas D. Nielsen"],"abstract":"Obtaining effective representations of DNA sequences is crucial for genome analysis. Metagenomic binning, for instance, relies on genome representations to cluster complex mixtures of DNA fragments from biological samples with the aim of determining their microbial compositions. In this paper, we revisit k-mer-based representations of genomes and provide a theoretical analysis of their use in representation learning. Based on the analysis, we propose a lightweight and scalable model for performing metagenomic binning at the genome read level, relying only on the k-mer compositions of the DNA fragments. We compare the model to recent genome foundation models and demonstrate that while the models are comparable in performance, the proposed model is significantly more effective in terms of scalability, a crucial aspect for performing metagenomic binning of real-world datasets.","url_abs":"https://arxiv.org/abs/2411.02125v1","url_pdf":"https://arxiv.org/pdf/2411.02125v1.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":"revisiting-k-mer-profile-for-effective-and","repo_url":"https://github.com/abdcelikkanat/revisitingkmers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.02125","atlas_url":"https://app.syntology.ai/?focus=2411.02125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.02125"}},"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/abdcelikkanat/revisitingkmers","reach":null}],"summary":{"ran":1,"ran_fixture":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":4,"samples":[{"code_sha256_prefix":"c55d239688ccb919","entry":"NonLinearModel","repo":"abdcelikkanat/revisitingkmers","repo_kind":"official","path":"src/nonlinear.py","file_url":"https://github.com/abdcelikkanat/revisitingkmers/blob/HEAD/src/nonlinear.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c55d239688ccb919"}},{"code_sha256_prefix":"b8415a5ca4e28ff0","entry":"loss_func","repo":"abdcelikkanat/revisitingkmers","repo_kind":"official","path":"src/nonlinear.py","file_url":"https://github.com/abdcelikkanat/revisitingkmers/blob/HEAD/src/nonlinear.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8415a5ca4e28ff0"}},{"code_sha256_prefix":"fdf60a19696b351b","entry":"single_epoch","repo":"abdcelikkanat/revisitingkmers","repo_kind":"official","path":"src/nonlinear.py","file_url":"https://github.com/abdcelikkanat/revisitingkmers/blob/HEAD/src/nonlinear.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fdf60a19696b351b"}},{"code_sha256_prefix":"6ac11eed8defa8ca","entry":"set_seed","repo":"abdcelikkanat/revisitingkmers","repo_kind":"official","path":"src/nonlinear.py","file_url":"https://github.com/abdcelikkanat/revisitingkmers/blob/HEAD/src/nonlinear.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":"6ac11eed8defa8ca"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}