{"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/learning-genomic-sequence-representations","title":"Learning Genomic Sequence Representations using Graph Neural Networks over De Bruijn Graphs","arxiv_id":"2312.03865","date":"2023-12-06","proceeding":null,"authors":["Kacper Kapuśniak","Manuel Burger","Gunnar Rätsch","Amir Joudaki"],"abstract":"The rapid expansion of genomic sequence data calls for new methods to achieve robust sequence representations. Existing techniques often neglect intricate structural details, emphasizing mainly contextual information. To address this, we developed k-mer embeddings that merge contextual and structural string information by enhancing De Bruijn graphs with structural similarity connections. Subsequently, we crafted a self-supervised method based on Contrastive Learning that employs a heterogeneous Graph Convolutional Network encoder and constructs positive pairs based on node similarities. Our embeddings consistently outperform prior techniques for Edit Distance Approximation and Closest String Retrieval tasks.","url_abs":"https://arxiv.org/abs/2312.03865v1","url_pdf":"https://arxiv.org/pdf/2312.03865v1.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":"learning-genomic-sequence-representations","repo_url":"https://github.com/ratschlab/genomic-gnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.03865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03865"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/ratschlab/genomic-gnn","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":9,"unverified":1},"by_repo_kind":{"official":{"samples":10,"ran":9,"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":0,"samples":[{"code_sha256_prefix":"ada8792296b3465d","entry":"build_deBruijn_graph","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ada8792296b3465d"}},{"code_sha256_prefix":"31823930fdfb0734","entry":"count_edge_types","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/representations/gnn_tasks_miniBatch/utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/representations/gnn_tasks_miniBatch/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"31823930fdfb0734"}},{"code_sha256_prefix":"461609f0a0623b19","entry":"interpret_layers_config","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/representations/gnn_common/gnn_models.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/representations/gnn_common/gnn_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"461609f0a0623b19"}},{"code_sha256_prefix":"2c08899864cd705c","entry":"kf_faiss_to_edge_index_weight","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/representations/gnn_common/gnn_utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/representations/gnn_common/gnn_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c08899864cd705c"}},{"code_sha256_prefix":"ba2b450fcf984a4f","entry":"kmer_onehot_fit","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/representations/kmer_onehot.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/representations/kmer_onehot.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba2b450fcf984a4f"}},{"code_sha256_prefix":"04290dd7558a55b9","entry":"networkx_to_dataloader","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/representations/gnn_tasks/utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/representations/gnn_tasks/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04290dd7558a55b9"}},{"code_sha256_prefix":"0d7ac6c324afb915","entry":"seq_to_kmers","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0d7ac6c324afb915"}},{"code_sha256_prefix":"a91306cf73d67638","entry":"setup_faiss_index","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/representations/gnn_common/gnn_utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/representations/gnn_common/gnn_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a91306cf73d67638"}},{"code_sha256_prefix":"5a7bdd65bed14ce9","entry":"weighted_directed_edges","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5a7bdd65bed14ce9"}},{"code_sha256_prefix":"fd4c11670c02f2ed","entry":"compute_dirichlet_energy","repo":"ratschlab/genomic-gnn","repo_kind":"official","path":"src/representations/gnn_common/gnn_utils.py","file_url":"https://github.com/ratschlab/genomic-gnn/blob/HEAD/src/representations/gnn_common/gnn_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fd4c11670c02f2ed"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}