{"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/self-focusing-virtual-screening-with-active","title":"Self-focusing virtual screening with active design space pruning","arxiv_id":"2205.01753","date":"2022-05-03","proceeding":null,"authors":["David E. Graff","Matteo Aldeghi","Joseph A. Morrone","Kirk E. Jordan","Edward O. Pyzer-Knapp","Connor W. Coley"],"abstract":"High-throughput virtual screening is an indispensable technique utilized in the discovery of small molecules. In cases where the library of molecules is exceedingly large, the cost of an exhaustive virtual screen may be prohibitive. Model-guided optimization has been employed to lower these costs through dramatic increases in sample efficiency compared to random selection. However, these techniques introduce new costs to the workflow through the surrogate model training and inference steps. In this study, we propose an extension to the framework of model-guided optimization that mitigates inferences costs using a technique we refer to as design space pruning (DSP), which irreversibly removes poor-performing candidates from consideration. We study the application of DSP to a variety of optimization tasks and observe significant reductions in overhead costs while exhibiting similar performance to the baseline optimization. DSP represents an attractive extension of model-guided optimization that can limit overhead costs in optimization settings where these costs are non-negligible relative to objective costs, such as docking.","url_abs":"https://arxiv.org/abs/2205.01753v1","url_pdf":"https://arxiv.org/pdf/2205.01753v1.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":"self-focusing-virtual-screening-with-active","repo_url":"https://github.com/coleygroup/dsp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"self-focusing-virtual-screening-with-active","repo_url":"https://github.com/coleygroup/molpal","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.01753","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.01753"}},"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/coleygroup/molpal","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coleygroup/dsp","reach":null}],"summary":{"ran_draft_wrong":3,"ran_fixture":2,"unverified":7},"by_repo_kind":{"official":{"samples":12,"ran":5,"repositories":2}},"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":"568360a66fa1f1d9","entry":"append_arrays","repo":"coleygroup/dsp","repo_kind":"official","path":"scripts/collate.py","file_url":"https://github.com/coleygroup/dsp/blob/HEAD/scripts/collate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"568360a66fa1f1d9"}},{"code_sha256_prefix":"a9e738a1e258c757","entry":"pad","repo":"coleygroup/dsp","repo_kind":"official","path":"scripts/collate.py","file_url":"https://github.com/coleygroup/dsp/blob/HEAD/scripts/collate.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a9e738a1e258c757"}},{"code_sha256_prefix":"cd882dcbb6797d2f","entry":"plot_acquired_points","repo":"coleygroup/dsp","repo_kind":"official","path":"scripts/figures.py","file_url":"https://github.com/coleygroup/dsp/blob/HEAD/scripts/figures.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd882dcbb6797d2f"}},{"code_sha256_prefix":"effa38928fa09a38","entry":"plot_surface_discrete","repo":"coleygroup/dsp","repo_kind":"official","path":"scripts/figures.py","file_url":"https://github.com/coleygroup/dsp/blob/HEAD/scripts/figures.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"effa38928fa09a38"}},{"code_sha256_prefix":"b7cd86bfe4f28fe6","entry":"prune","repo":"coleygroup/dsp","repo_kind":"official","path":"scripts/figures.py","file_url":"https://github.com/coleygroup/dsp/blob/HEAD/scripts/figures.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7cd86bfe4f28fe6"}},{"code_sha256_prefix":"42358142a588e362","entry":"batches","repo":"coleygroup/molpal","repo_kind":"official","path":"molpal/utils.py","file_url":"https://github.com/coleygroup/molpal/blob/HEAD/molpal/utils.py","link_basis":"harvester_set","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":"42358142a588e362"}},{"code_sha256_prefix":"beeecd27d428b9ca","entry":"build_name_dict","repo":"coleygroup/molpal","repo_kind":"official","path":"molpal/cli/extract.py","file_url":"https://github.com/coleygroup/molpal/blob/HEAD/molpal/cli/extract.py","link_basis":"harvester_set","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":"beeecd27d428b9ca"}},{"code_sha256_prefix":"8c90c9a5d3cf36b5","entry":"calc","repo":"coleygroup/molpal","repo_kind":"official","path":"molpal/acquirer/metrics.py","file_url":"https://github.com/coleygroup/molpal/blob/HEAD/molpal/acquirer/metrics.py","link_basis":"harvester_set","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":"8c90c9a5d3cf36b5"}},{"code_sha256_prefix":"0f7275ce83ed510e","entry":"get_metric","repo":"coleygroup/molpal","repo_kind":"official","path":"molpal/acquirer/metrics.py","file_url":"https://github.com/coleygroup/molpal/blob/HEAD/molpal/acquirer/metrics.py","link_basis":"harvester_set","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":"0f7275ce83ed510e"}},{"code_sha256_prefix":"70126cde14b5ecb5","entry":"get_needs","repo":"coleygroup/molpal","repo_kind":"official","path":"molpal/acquirer/metrics.py","file_url":"https://github.com/coleygroup/molpal/blob/HEAD/molpal/acquirer/metrics.py","link_basis":"harvester_set","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":"70126cde14b5ecb5"}},{"code_sha256_prefix":"5f9a63793db4c090","entry":"mve_loss","repo":"coleygroup/molpal","repo_kind":"official","path":"molpal/models/nnmodels.py","file_url":"https://github.com/coleygroup/molpal/blob/HEAD/molpal/models/nnmodels.py","link_basis":"harvester_set","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":"5f9a63793db4c090"}},{"code_sha256_prefix":"7f37d5583055f1c5","entry":"read_top_k","repo":"coleygroup/molpal","repo_kind":"official","path":"molpal/cli/extract.py","file_url":"https://github.com/coleygroup/molpal/blob/HEAD/molpal/cli/extract.py","link_basis":"harvester_set","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":"7f37d5583055f1c5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}