Get started Console

Modern medicine75

Traditional medicine24

Cross-cutting12

Collections

Models8

License status and Mdexa hosting, recorded separatelyAll datasets

TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening

Verified by Mdexa · Checked against the source text under public rules.How we check

Commercial use
Yes
Derivatives
Yes
Redistribution
Yes
File on Mdexa
NoLink only

all parts permissive

PermissiveLink onlyCC-BY-SA-4.0Save

Badge

Mdexa verified · Permissive · 2026-11Mdexa verifiedPermissive · 2026-11

[![Mdexa verified · Permissive · 2026-11](https://mcp.mdexa.com/v1/badge/datasets/topu-lbvs.svg)](https://mdexa.com/datasets/topu-lbvs/)

Place it on a repository or dataset page; the status and date follow the verification. About badges

Cite this pageMdexa, TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening, https://mdexa.com/datasets/topu-lbvs/, verified 2026-11-14.

Source riskDerived

Key facts

Domain
Pharmacy and drugs Modern medicine
Content
DatabasesMulti-target benchmark for ligand-based virtual screening (LBVS) under hard-negative screening conditions: 93 protein targets across 7 protein classes, curated from ChEMBL 35.
Size
—As stated: 100K<n<1M
Language / modality
English / Text · Graph · Tabular
Publisher
introvoyz042
Year
—
Expert review
—
Verification
Verified: license text seen

Commercial use of TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening

Commercial use: Yes. The overall verdict takes the strictest part; the parts carry different licenses, listed below. License status: Permissive.

Conditions
Attribution, Share-alike, Notice kept
License part
main data — Permissive (CC-BY-SA-4.0)
License part
companion code — Permissive (MIT)
License part
ChEMBL source data — Permissive (CC-BY-SA-3.0)

Quoted statements and their sources are in TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening license evidence.

Verdicts record what sources state and are not legal advice.

Tags

Task format
Text classification

Quoted from the source**`tabular-classification`** — Per-target binary classification of compounds as active or inactive against a fixed protein target.Snapshot s01

Intended use
Evaluation

Quoted from the sourceThe benchmark is organised into **three evaluation protocols**:Snapshot s01

Specialty
Pharmacy
Source type
Built from a knowledge base
Data format
PARQUETCSVJSON
Official split
Train and test splits

Quoted from the sourceFor each target, the ChEMBL\* training pool is split 85% / 15% (stratified random, seed 2026/2027/2028) at a fixed 1:10 active-to-decoy ratio. The full TopU library is the test set at 1:40 active-to-decoy ratio.Snapshot s01

Author-statedInferredHuman-confirmed

TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening license evidence 8

Conditions are the union of the parts

  1. Hugging Face card metadataPage opened
    CC-BY-SA-4.0
    Third-party text · Hugging Face card metadatalicense: cc-by-sa-4.0

    Statement found in snapshot s01 (readme)

    huggingface.co2026-11-12 · s01
  2. READMEPage opened
    CC-BY-SA-4.0
    Third-party text · README📜 **License**: CC-BY-SA-4.0

    Statement found in snapshot s01 (readme)

    huggingface.co2026-11-12 · s01
  3. READMEPage opened
    CC-BY-SA-4.0
    Third-party text · READMEThe TopU-LBVS dataset is released under **CC-BY-SA-4.0**.

    Statement found in snapshot s01 (readme)

    huggingface.co2026-11-12 · s01
  1. READMEPage opened
    MIT
    Third-party text · READMEThe companion code (https://github.com/topu-benchmark/topu-lbvs) is released under the **MIT License**.

    Statement found in snapshot s01 (readme)

    huggingface.co2026-11-12 · s01
  2. READMEPage opened
    CC-BY-SA-3.0
    Third-party text · READMEChEMBL is released under CC-BY-SA-3.0.

    Statement found in snapshot s01 (readme)

    huggingface.co2026-11-12 · s01
  3. READMEPage opened
    CC-BY-SA-4.0
    Third-party text · READMEThe curated TopU-LBVS data inherits a compatible CC-BY-SA-4.0 license.

    Statement found in snapshot s01 (readme)

    huggingface.co2026-11-12 · s01
  4. READMEPage opened
    Third-party text · READMEUsers redistributing the data or derived works must preserve the CC-BY-SA terms and provide attribution to both ChEMBL and this dataset.

    Statement found in snapshot s01 (readme)

    huggingface.co2026-11-12 · s01
  5. Dataset pagePage opened
    CC-BY-SA-4.0
    Third-party text · Dataset page📜 License : CC-BY-SA-4.0

    Statement found in snapshot s02 (page)

    huggingface.co2026-11-12 · s02

Source and lineage

  • Derived fromChEMBL 35not in the database

Known issues with TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening

—

Preflight

Not run Runs only on ingested data; says nothing about quality.

Downloading TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening and API access

No file on Mdexa (see the verdict). Get it from the source and confirm the terms there:

Citing TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening

Mdexa, TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening, https://mdexa.com/datasets/topu-lbvs/, verified 2026-11-14.
More citation details

The source gives no citation text; the line above cites this card.

Machine-readable

topu-lbvs.jsontopu-lbvs.mdcatalog.json

Change log 11
2026-11-14Re-adjudicated under the current rules; all machine checks still pass.
2026-11-14Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Re-adjudicated under the current rules; all machine checks still pass.
2026-11-13Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions).

Listed in

Datasets similar to TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening

  • BindingDBVerified by MdexaPharmacyEvaluationPer-item review PermissiveLink only —

    License permissive, share-alike: all parts permissive; conditions are the union of the parts. Risk flag(s): derived. Link only.

    Pharmacy and drugs · Databases · Derived

    Open the cardSave

    Shared: Intended use Evaluation · Specialty Pharmacy · Source type Built from a knowledge base · domain Pharmacy and drugs · content Databases

  • Therapeutics Data CommonsVerified by MdexaPharmacyEvaluation UnstatedPending —

    License unstated: the source says licenses differ per subset and does not list them. Link only.

    Pharmacy and drugs · Clinical medicine · Databases

    Open the cardSave

    Shared: Intended use Evaluation · Specialty Pharmacy · Official split Train and test splits · domain Pharmacy and drugs · content Databases

  • CBLUEVerified by MdexaNamed entity recognitionEvaluation UnstatedPending 8 tasks

    License unstated: Only a code repository license; no data license stated; link only until resolved.

    Clinical medicine · Question banks and benchmarks · Annotated corpora

    Open the cardSave

    Shared: Task format Text classification · Intended use Evaluation · Data format JSON · Official split Train and test splits · system Modern medicine

  • jablonkagroup/chempile-liftVerified by MdexaFine-tuning RestrictedLink only —

    License restricted: restrictions are read broadly: CC-BY-NC-SA-4.0. Link only.

    Pharmacy and drugs · Databases · Annotated corpora

    Open the cardSave

    Shared: Intended use Evaluation · Data format PARQUET · Official split Train and test splits · domain Pharmacy and drugs · content Databases

  • DrugBankVerified by MdexaPharmacy RestrictedLink only —

    License restricted, judged by public rules and checked by a second-pass model. Link only.

    Pharmacy and drugs · Databases · Drug information

    Open the cardSave

    Shared: Specialty Pharmacy · Source type Built from a knowledge base · domain Pharmacy and drugs · content Databases