{"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/a-systematic-survey-of-molecular-pre-trained","title":"A Systematic Survey of Chemical Pre-trained Models","arxiv_id":"2210.16484","date":"2022-10-29","proceeding":null,"authors":["Jun Xia","Yanqiao Zhu","Yuanqi Du","Stan Z. Li"],"abstract":"Deep learning has achieved remarkable success in learning representations for molecules, which is crucial for various biochemical applications, ranging from property prediction to drug design. However, training Deep Neural Networks (DNNs) from scratch often requires abundant labeled molecules, which are expensive to acquire in the real world. To alleviate this issue, tremendous efforts have been devoted to Molecular Pre-trained Models (CPMs), where DNNs are pre-trained using large-scale unlabeled molecular databases and then fine-tuned over specific downstream tasks. Despite the prosperity, there lacks a systematic review of this fast-growing field. In this paper, we present the first survey that summarizes the current progress of CPMs. We first highlight the limitations of training molecular representation models from scratch to motivate CPM studies. Next, we systematically review recent advances on this topic from several key perspectives, including molecular descriptors, encoder architectures, pre-training strategies, and applications. We also highlight the challenges and promising avenues for future research, providing a useful resource for both machine learning and scientific communities.","url_abs":"https://arxiv.org/abs/2210.16484v3","url_pdf":"https://arxiv.org/pdf/2210.16484v3.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":"a-systematic-survey-of-molecular-pre-trained","repo_url":"https://github.com/junxia97/awesome-pretrain-on-molecules","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":{"status":"ok"}},{"paper_slug":"a-systematic-survey-of-molecular-pre-trained","repo_url":"https://github.com/junxia97/mole-bert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"drug-design","task_name":"Drug Design"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"survey","task_name":"Survey"},{"task_slug":"molecular-representation","task_name":"molecular representation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.16484","atlas_url":"https://app.syntology.ai/?focus=2210.16484","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.16484"}},"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/junxia97/awesome-pretrain-on-molecules","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junxia97/mole-bert","reach":null}],"summary":{"ran_honours":1,"ran_violates":2,"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":5,"samples":[{"code_sha256_prefix":"1d31c46fec1fe3d1","entry":"compute_accuracy","repo":"junxia97/mole-bert","repo_kind":"official","path":"pretrain.py","file_url":"https://github.com/junxia97/mole-bert/blob/HEAD/pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d31c46fec1fe3d1"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"fc2efb619b6ee2c4","entry":"top_k","repo":"junxia97/mole-bert","repo_kind":"official","path":"vqvae.py","file_url":"https://github.com/junxia97/mole-bert/blob/HEAD/vqvae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc2efb619b6ee2c4"}},{"code_sha256_prefix":"7f8f4d93d36639a4","entry":"eval","repo":"junxia97/mole-bert","repo_kind":"official","path":"finetune.py","file_url":"https://github.com/junxia97/mole-bert/blob/HEAD/finetune.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":"7f8f4d93d36639a4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}