{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2026-05-20T21:31:10.690274+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "SMARTBind_dataset.zip": { "access": { "hidden": false }, "checksum": "md5:7dab08d97433e23c72f462257ce9c1ee", "ext": "zip", "id": "e41f6e8a-3d88-4e10-9ebd-e4c5ecbd3834", "key": "SMARTBind_dataset.zip", "links": { "content": "https://zenodo.org/api/records/20252150/files/SMARTBind_dataset.zip/content", "self": "https://zenodo.org/api/records/20252150/files/SMARTBind_dataset.zip" }, "metadata": {}, "mimetype": "application/zip", "size": 2628666319, "storage_class": "L" } }, "order": [], "total_bytes": 2628666319 }, "id": "20252150", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/20252150/access", "access_grants": "https://zenodo.org/api/records/20252150/access/grants", "access_links": "https://zenodo.org/api/records/20252150/access/links", "access_request": "https://zenodo.org/api/records/20252150/access/request", "access_users": "https://zenodo.org/api/records/20252150/access/users", "archive": "https://zenodo.org/api/records/20252150/files-archive", "archive_media": "https://zenodo.org/api/records/20252150/media-files-archive", "communities": "https://zenodo.org/api/records/20252150/communities", "communities-suggestions": "https://zenodo.org/api/records/20252150/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.20252150", "draft": "https://zenodo.org/api/records/20252150/draft", "file_modification": "https://zenodo.org/api/records/20252150/file-modification", "files": "https://zenodo.org/api/records/20252150/files", "latest": "https://zenodo.org/api/records/20252150/versions/latest", "latest_html": "https://zenodo.org/records/20252150/latest", "media_files": "https://zenodo.org/api/records/20252150/media-files", "parent": "https://zenodo.org/api/records/17197892", "parent_doi": "https://doi.org/10.5281/zenodo.17197892", "parent_doi_html": "https://zenodo.org/doi/10.5281/zenodo.17197892", "parent_html": "https://zenodo.org/records/17197892", "preview_html": "https://zenodo.org/records/20252150?preview=1", "quota_increase": "https://zenodo.org/api/records/20252150/quota-increase", "request_deletion": "https://zenodo.org/api/records/20252150/request-deletion", "requests": "https://zenodo.org/api/records/20252150/requests", "reserve_doi": "https://zenodo.org/api/records/20252150/draft/pids/doi", "self": "https://zenodo.org/api/records/20252150", "self_doi": "https://doi.org/10.5281/zenodo.20252150", "self_doi_html": "https://zenodo.org/doi/10.5281/zenodo.20252150", "self_html": "https://zenodo.org/records/20252150", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:20252150/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:20252150/sequence/default", "versions": "https://zenodo.org/api/records/20252150/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development, University of Florida, Gainesville, FL 32610, USA" }, { "name": "Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611, USA" } ], "person_or_org": { "family_name": "Jiang", "given_name": "Shiyu", "identifiers": [ { "identifier": "0000-0001-9450-7379", "scheme": "orcid" } ], "name": "Jiang, Shiyu", "type": "personal" } }, { "affiliations": [ { "name": "Department of Chemistry, The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, 130 Scripps Way, Jupiter, FL 33458, USA" } ], "person_or_org": { "family_name": "Taghavi", "given_name": "Amirhossein", "identifiers": [ { "identifier": "0000-0001-9270-9145", "scheme": "orcid" } ], "name": "Taghavi, Amirhossein", "type": "personal" } }, { "affiliations": [ { "name": "Department of Chemistry, The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, 130 Scripps Way, Jupiter, FL 33458, USA" }, { "name": "Department of Chemistry, The Scripps Research Institute, 130 Scripps Way, Jupiter, FL 33458, USA" } ], "person_or_org": { "family_name": "Wang", "given_name": "Tenghui", "identifiers": [ { "identifier": "0009-0001-9325-6667", "scheme": "orcid" } ], "name": "Wang, Tenghui", "type": "personal" } }, { "affiliations": [ { "name": "Department of Chemistry, The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, 130 Scripps Way, Jupiter, FL 33458, USA" } ], "person_or_org": { "family_name": "Sung", "given_name": "Kisu", "name": "Sung, Kisu", "type": "personal" } }, { "affiliations": [ { "name": "Department of Chemistry, The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, 130 Scripps Way, Jupiter, FL 33458, USA" }, { "name": "Department of Chemistry, The Scripps Research Institute, 130 Scripps Way, Jupiter, FL 33458, USA" } ], "person_or_org": { "family_name": "Meyer", "given_name": "Samantha M.", "identifiers": [ { "identifier": "0000-0003-3353-6939", "scheme": "orcid" } ], "name": "Meyer, Samantha M.", "type": "personal" } }, { "affiliations": [ { "name": "Department of Chemistry, The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, 130 Scripps Way, Jupiter, FL 33458, USA" }, { "name": "Department of Chemistry, The Scripps Research Institute, 130 Scripps Way, Jupiter, FL 33458, USA" } ], "person_or_org": { "family_name": "A. Springer", "given_name": "Noah", "identifiers": [ { "identifier": "0000-0001-8868-0415", "scheme": "orcid" } ], "name": "A. Springer, Noah", "type": "personal" } }, { "affiliations": [ { "name": "Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development, University of Florida, Gainesville, FL 32610, USA" }, { "name": "Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611, USA" } ], "person_or_org": { "family_name": "Wei", "given_name": "Jinhang", "identifiers": [ { "identifier": "0009-0003-6957-3472", "scheme": "orcid" } ], "name": "Wei, Jinhang", "type": "personal" } }, { "affiliations": [ { "name": "Department of Chemistry, The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, 130 Scripps Way, Jupiter, FL 33458, USA" } ], "person_or_org": { "family_name": "Childs-Disney", "given_name": "Jessica L.", "identifiers": [ { "identifier": "0009-0001-7829-3240", "scheme": "orcid" } ], "name": "Childs-Disney, Jessica L.", "type": "personal" } }, { "affiliations": [ { "name": "Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development, University of Florida, Gainesville, FL 32610, USA" } ], "person_or_org": { "family_name": "Li", "given_name": "Chenglong", "identifiers": [ { "identifier": "0000-0001-9460-3168", "scheme": "orcid" } ], "name": "Li, Chenglong", "type": "personal" } }, { "affiliations": [ { "name": "Department of Chemistry, The Herbert Wertheim UF Scripps Institute for Biomedical Innovation and Technology, 130 Scripps Way, Jupiter, FL 33458, USA" }, { "name": "Department of Chemistry, The Scripps Research Institute, 130 Scripps Way, Jupiter, FL 33458, USA" } ], "person_or_org": { "family_name": "Disney", "given_name": "Mattew D.", "identifiers": [ { "identifier": "0000-0001-8486-1796", "scheme": "orcid" } ], "name": "Disney, Mattew D.", "type": "personal" } }, { "affiliations": [ { "name": "Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development, University of Florida, Gainesville, FL 32610, USA" }, { "name": "Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611, USA" } ], "person_or_org": { "family_name": "Li", "given_name": "Yanjun", "identifiers": [ { "identifier": "0000-0002-6277-4189", "scheme": "orcid" } ], "name": "Li, Yanjun", "type": "personal" } } ], "description": "

This dataset supports SMARTBind (Small Molecule Approaches to RNA Targeting Binder Discovery), a structure-agnostic ligand discovery framework that combines an RNA large language model with contrastive learning and a ligand-specific decoy enhancement strategy. Please cite the following publication when using the dataset:

\n
\n

Jiang, Shiyu, Amirhossein Taghavi, Tenghui Wang, Kisu Sung, Samantha M. Meyer, Noah A. Springer, Jinhang Wei, Jessica L. Childs-Disney, Chenglong Li, Mattew D. Disney, and Yanjun Li. \"Small Molecule Approach to RNA Targeting Binder Discovery (SMARTBind) Using Deep Learning Without Structural Input.\" bioRxiv (2025): 2025-09.

\n
\n

Overview

\n

The dataset contains model checkpoint and training data for SMARTBind including RNAmigos1 and HARIBOSS 10-fold random-split, HARIBOSS 5-fold cross-validation splits. All data is organized under the archive file SMARTBind_dataset.zip.

\n

Contents

\n

SMARTBind_weight.zip: saved checkpoint of the 10-fold SMARTBind model for binding score and binding site prediction.

\n

10-fold cross-validation.zip: the folder contains HARIBOSS 10-fold random split dataset and RNAmigos1 10-fold rnadom split dataset.

\n

5-fold cross-validations.zip: the folder contains five HARIBOSS 5-fold cross-validation splits, including RNA sequence-based, RNA structure-based, RNA pocket-based, pair-based, ligand-existence splittings. 

\n

5-fold cross-validations gbsubset.zip: the folder contains five HARIBOSS 5-fold cross-validation splits (GerNA-Bind subset), including RNA sequence-based, RNA structure-based, RNA pocket-based, pair-based, ligand-existence splittings. 

\n

Chemspace_Screening_Compounds_SMlLES_sampled1M.smi.zip: the virtual screening background library used for benchmarking time-dependent test set.

\n

Decoy library.smi.zip: a chemical diverse decoy library with 92,626 entries that is curated for the ligand-specific decoy enhancement strategy.

\n

decoys.zip: DecoyFinder- and DeepCoy-generated decoy datasets for virtual screening evaluation.

", "publication_date": "2025-10-02", "publisher": "Zenodo", "related_identifiers": [ { "identifier": "10.1101/2025.09.24.678312", "relation_type": { "id": "issupplementto", "title": { "de": "Erg\u00e4nzt", "en": "Is supplement to" } }, "resource_type": { "id": "publication-preprint", "title": { "de": "Preprint", "en": "Preprint" } }, "scheme": "doi" } ], "resource_type": { "id": "dataset", "title": { "de": "Datensatz", "en": "Dataset" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "title": "Small Molecule Approach to RNA Targeting Binder Discovery (SMARTBind) Using Deep Learning Without Structural Input" }, "parent": { "access": { "owned_by": { "user": "1376554" }, "settings": { "accept_conditions_text": null, "allow_guest_requests": false, "allow_user_requests": false, "secret_link_expiration": 0 } }, "communities": { "default": "9923e016-4f21-4ccb-9b34-08a4d46f47d0", "entries": [ { "access": { "member_policy": "open", "members_visibility": "public", "record_submission_policy": "closed", "review_policy": "closed", "visibility": "public" }, "children": { "allow": false }, "created": "2025-07-21T02:49:18.155798+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "id": "9923e016-4f21-4ccb-9b34-08a4d46f47d0", "links": {}, "metadata": { "description": "AI-driven Drug Discovery, Molecule Design and Optimization, Molecular Recognition, AI4Science", "organizations": [ { "id": "02y3ad647" } ], "title": "AIDD-LiLab", "website": "https://yanjun-li.com" }, "revision_id": 5, "slug": "aidd-lilab", "updated": "2025-09-25T15:19:18.788634+00:00" } ], "ids": [ "9923e016-4f21-4ccb-9b34-08a4d46f47d0" ] }, "id": "17197892", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.17197892", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.20252150", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:20252150", "provider": "oai" } }, "revision_id": 4, "stats": { "all_versions": { "data_volume": 367215684595.0, "downloads": 141, "unique_downloads": 135, "unique_views": 611, "views": 666 }, "this_version": { "data_volume": 26261281606.0, "downloads": 10, "unique_downloads": 10, "unique_views": 50, "views": 50 } }, "status": "published", "swh": {}, "updated": "2026-05-20T21:31:10.871647+00:00", "versions": { "index": 3, "is_latest": true } }