{"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/are-learned-molecular-representations-ready","title":"Analyzing Learned Molecular Representations for Property Prediction","arxiv_id":"1904.01561","date":"2019-04-02","proceeding":null,"authors":["Kevin Yang","Kyle Swanson","Wengong Jin","Connor Coley","Philipp Eiden","Hua Gao","Angel Guzman-Perez","Timothy Hopper","Brian Kelley","Miriam Mathea","Andrew Palmer","Volker Settels","Tommi Jaakkola","Klavs Jensen","Regina Barzilay"],"abstract":"Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.","url_abs":"https://arxiv.org/abs/1904.01561v5","url_pdf":"https://arxiv.org/pdf/1904.01561v5.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":"are-learned-molecular-representations-ready","repo_url":"https://github.com/swansonk14/chemprop","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"are-learned-molecular-representations-ready","repo_url":"https://github.com/anonymous20201002/chemprop","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"are-learned-molecular-representations-ready","repo_url":"https://github.com/jbr-ai-labs/lipophilicity-prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"are-learned-molecular-representations-ready","repo_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"molecular-representation","task_name":"molecular representation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"D-MPNN","rank_in_archive_order":11,"of":20,"metrics":{"ROC-AUC":"80.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"D-MPNN","rank_in_archive_order":19,"of":29,"metrics":{"ROC-AUC":"71.0"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-esol","task":"Molecular Property Prediction","dataset":"ESOL","model":"D-MPNN","rank_in_archive_order":20,"of":20,"metrics":{"RMSE":"1.050"},"uses_additional_data":true},{"leaderboard":"/sota/molecular-property-prediction-on-freesolv","task":"Molecular Property Prediction","dataset":"FreeSolv","model":"D-MPNN","rank_in_archive_order":17,"of":22,"metrics":{"RMSE":"2.082"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on","task":"Molecular Property Prediction","dataset":"Lipophilicity","model":"D-MPNN","rank_in_archive_order":4,"of":13,"metrics":{"RMSE":"0.683"},"uses_additional_data":true},{"leaderboard":"/sota/molecular-property-prediction-on-qm7","task":"Molecular Property Prediction","dataset":"QM7","model":"D-MPNN","rank_in_archive_order":7,"of":8,"metrics":{"MAE":"103.5"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-qm8","task":"Molecular Property Prediction","dataset":"QM8","model":"D-MPNN","rank_in_archive_order":3,"of":8,"metrics":{"MAE":"0.0190"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-qm9","task":"Molecular Property Prediction","dataset":"QM9","model":"D-MPNN","rank_in_archive_order":3,"of":8,"metrics":{"MAE":"0.00814"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"D-MPNN","rank_in_archive_order":16,"of":19,"metrics":{"ROC-AUC":"57.0"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"D-MPNN","rank_in_archive_order":11,"of":20,"metrics":{"ROC-AUC":"75.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-toxcast-1","task":"Molecular Property Prediction","dataset":"ToxCast","model":"D-MPNN","rank_in_archive_order":6,"of":8,"metrics":{"ROC-AUC":"65.5"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"D-MPNN","rank_in_archive_order":7,"of":20,"metrics":{"ROC-AUC":"90.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.01561","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01561"}},"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/swansonk14/chemprop","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jbr-ai-labs/lipophilicity-prediction","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anonymous20201002/chemprop","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":12},"by_repo_kind":{"listed":{"samples":15,"ran":3,"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":"8efee7d886650920","entry":"compute_gnorm","repo":"anonymous20201002/chemprop","repo_kind":"listed","path":"chemprop/nn_utils.py","file_url":"https://github.com/anonymous20201002/chemprop/blob/HEAD/chemprop/nn_utils.py","link_basis":"harvester_set","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":"8efee7d886650920"}},{"code_sha256_prefix":"c4eed975523e1ed4","entry":"compute_pnorm","repo":"anonymous20201002/chemprop","repo_kind":"listed","path":"chemprop/nn_utils.py","file_url":"https://github.com/anonymous20201002/chemprop/blob/HEAD/chemprop/nn_utils.py","link_basis":"harvester_set","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":"c4eed975523e1ed4"}},{"code_sha256_prefix":"f1cc5264ce058bab","entry":"param_count","repo":"anonymous20201002/chemprop","repo_kind":"listed","path":"chemprop/nn_utils.py","file_url":"https://github.com/anonymous20201002/chemprop/blob/HEAD/chemprop/nn_utils.py","link_basis":"harvester_set","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":"f1cc5264ce058bab"}},{"code_sha256_prefix":"ca7675a6350f0967","entry":"compute_gnorm","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/nn_utils.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/nn_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":"ca7675a6350f0967"}},{"code_sha256_prefix":"e415ae10bb5a4e3b","entry":"compute_pnorm","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/nn_utils.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/nn_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":"e415ae10bb5a4e3b"}},{"code_sha256_prefix":"37db24e9e0f38c01","entry":"evaluate_predictions","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/train/evaluate.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/train/evaluate.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":"37db24e9e0f38c01"}},{"code_sha256_prefix":"513750ee5fcea171","entry":"get_atom_fdim","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/features/featurization.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/features/featurization.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":"513750ee5fcea171"}},{"code_sha256_prefix":"963d26c20eb3e4da","entry":"get_bond_fdim","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/features/featurization.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/features/featurization.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":"963d26c20eb3e4da"}},{"code_sha256_prefix":"8fb802f2499b4ccb","entry":"get_checkpoint_paths","repo":"anonymous20201002/chemprop","repo_kind":"listed","path":"chemprop/args.py","file_url":"https://github.com/anonymous20201002/chemprop/blob/HEAD/chemprop/args.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":"8fb802f2499b4ccb"}},{"code_sha256_prefix":"76e27ba5baa89e9f","entry":"load_args","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/utils.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/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":"76e27ba5baa89e9f"}},{"code_sha256_prefix":"5045ed0a87b443be","entry":"load_features","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/features/utils.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/features/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":"5045ed0a87b443be"}},{"code_sha256_prefix":"3e07b9e0170215ca","entry":"onek_encoding_unk","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/features/featurization.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/features/featurization.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":"3e07b9e0170215ca"}},{"code_sha256_prefix":"49ebe299656c7302","entry":"onek_encoding_unk","repo":"anonymous20201002/chemprop","repo_kind":"listed","path":"chemprop/features/featurization.py","file_url":"https://github.com/anonymous20201002/chemprop/blob/HEAD/chemprop/features/featurization.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":"49ebe299656c7302"}},{"code_sha256_prefix":"d68ff6a82a950b49","entry":"param_count","repo":"tingweidaniel/chemprop_atomicfp_save_depth_final","repo_kind":"listed","path":"chemprop/nn_utils.py","file_url":"https://github.com/tingweidaniel/chemprop_atomicfp_save_depth_final/blob/HEAD/chemprop/nn_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":"d68ff6a82a950b49"}},{"code_sha256_prefix":"c9a8d90e903cc480","entry":"predict","repo":"anonymous20201002/chemprop","repo_kind":"listed","path":"chemprop/sklearn_train.py","file_url":"https://github.com/anonymous20201002/chemprop/blob/HEAD/chemprop/sklearn_train.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":"c9a8d90e903cc480"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}