Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/BioT5

BioT5

Reported on 27 benchmarks across 3 tasks · 1 paper · 13 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical27 results

Drug DiscoveryonChEBI-20
BLEU· 2023-10-11
86.7
best: 92.6 (LDMol)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
Exact Match· 2023-10-11
41.3
best: 53.3 (LDMol)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
Validity· 2023-10-11
100
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Molecule CaptioningonChEBI-20
BLEU-2· 2023-10-11
63.5
best: 73.2 (Mol-LLM (Mistral-Instruct-v0.2))
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Molecule CaptioningonChEBI-20
BLEU-4· 2023-10-11
55.6
best: 60.8 (MolReFlect)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Molecule CaptioningonChEBI-20
METEOR· 2023-10-11
65.6
best: 68.1 (BioT5+)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Molecule CaptioningonChEBI-20
ROUGE-1· 2023-10-11
69.2
best: 71 (BioT5+)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Molecule CaptioningonChEBI-20
ROUGE-2· 2023-10-11
55.9
best: 61.8 (XMolCap)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Molecule CaptioningonChEBI-20
ROUGE-L· 2023-10-11
63.3
best: 65.3 (PEIT-GEN)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Molecule CaptioningonChEBI-20
Text2Mol· 2023-10-11
60.3
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
BLEU· 2023-10-11
86.7
best: 92.6 (LDMol)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
Exact Match· 2023-10-11
41.3
best: 53.3 (LDMol)
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
Validity· 2023-10-11
100
SOTA
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
Frechet ChemNet Distance (FCD)· 2023-10-11
0.43
best: 2.49 (MolT5-small)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
Levenshtein· 2023-10-11
15.097
best: 28.54 (Text+Chem T5 small)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
MACCS FTS· 2023-10-11
88.6
best: 97.3 (LDMol)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
Morgan FTS· 2023-10-11
73.4
best: 93.1 (LDMol)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
Parameter Count· 2023-10-11
252000000
best: 770000000 (MolT5-Large)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
RDK FTS· 2023-10-11
80.1
best: 95 (LDMol)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Drug DiscoveryonChEBI-20
Text2Mol· 2023-10-11
57.6
best: 59.3 (MolReGPT (GPT-4-0413))
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
Frechet ChemNet Distance (FCD)· 2023-10-11
0.43
best: 2.49 (MolT5-small)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
Levenshtein· 2023-10-11
15.097
best: 28.54 (Text+Chem T5 small)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
MACCS FTS· 2023-10-11
88.6
best: 97.3 (LDMol)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
Morgan FTS· 2023-10-11
73.4
best: 93.1 (LDMol)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
Parameter Count· 2023-10-11
252000000
best: 770000000 (MolT5-Large)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
RDK FTS· 2023-10-11
80.1
best: 95 (LDMol)
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276
Text-based de novo Molecule GenerationonChEBI-20
Text2Mol· 2023-10-11
57.6
best: 59.3 (MolReGPT (GPT-4-0413))
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations arXiv:2310.07276