{"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/discobax-discovery-of-optimal-intervention","title":"DiscoBAX: Discovery of Optimal Intervention Sets in Genomic Experiment Design","arxiv_id":"2312.04064","date":"2023-12-07","proceeding":null,"authors":["Clare Lyle","Arash Mehrjou","Pascal Notin","Andrew Jesson","Stefan Bauer","Yarin Gal","Patrick Schwab"],"abstract":"The discovery of therapeutics to treat genetically-driven pathologies relies on identifying genes involved in the underlying disease mechanisms. Existing approaches search over the billions of potential interventions to maximize the expected influence on the target phenotype. However, to reduce the risk of failure in future stages of trials, practical experiment design aims to find a set of interventions that maximally change a target phenotype via diverse mechanisms. We propose DiscoBAX, a sample-efficient method for maximizing the rate of significant discoveries per experiment while simultaneously probing for a wide range of diverse mechanisms during a genomic experiment campaign. We provide theoretical guarantees of approximate optimality under standard assumptions, and conduct a comprehensive experimental evaluation covering both synthetic as well as real-world experimental design tasks. DiscoBAX outperforms existing state-of-the-art methods for experimental design, selecting effective and diverse perturbations in biological systems.","url_abs":"https://arxiv.org/abs/2312.04064v1","url_pdf":"https://arxiv.org/pdf/2312.04064v1.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":"discobax-discovery-of-optimal-intervention","repo_url":"https://github.com/amehrjou/discobax","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"experimental-design","task_name":"Experimental Design"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2312.04064","atlas_url":"https://app.syntology.ai/?focus=2312.04064","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.04064"}},"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/amehrjou/discobax","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"ran":3,"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":"0c13d48322f1eb74","entry":"find_optimal_number_clusters","repo":"amehrjou/discobax","repo_kind":"official","path":"discobax/models/clustering.py","file_url":"https://github.com/amehrjou/discobax/blob/HEAD/discobax/models/clustering.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"0c13d48322f1eb74"}},{"code_sha256_prefix":"5104a259cad33b36","entry":"rbf","repo":"amehrjou/discobax","repo_kind":"official","path":"discobax/models/toy_experiment_models.py","file_url":"https://github.com/amehrjou/discobax/blob/HEAD/discobax/models/toy_experiment_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"5104a259cad33b36"}},{"code_sha256_prefix":"06779451facf9d50","entry":"update_dictionary_keys_with_prefixes","repo":"amehrjou/discobax","repo_kind":"official","path":"discobax/apps/genedisco_single_cycle_experiment.py","file_url":"https://github.com/amehrjou/discobax/blob/HEAD/discobax/apps/genedisco_single_cycle_experiment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"06779451facf9d50"}},{"code_sha256_prefix":"d7a17e0058cd6c62","entry":"get_top_target_clusters","repo":"amehrjou/discobax","repo_kind":"official","path":"discobax/models/clustering.py","file_url":"https://github.com/amehrjou/discobax/blob/HEAD/discobax/models/clustering.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"d7a17e0058cd6c62"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}