Skip to main content

Table 2 Highest and lowest-scoring classes using the LSTM algorithm

From: Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification

Class_id

f1_score

Class_name

Class_members

CHEBI:17984

1.000000

Acyl-CoA

696

CHEBI:37240

0.998350

Adenosine 3’,5’-bisphosphate

697

CHEBI:22251

0.995114

Adenosine bisphosphate

702

CHEBI:61078

0.993104

Purine nucleoside bisphosphate

706

CHEBI:58946

0.992382

Acyl-CoA oxoanion

707

CHEBI:61079

0.991522

Ribonucleoside bisphosphate

707

CHEBI:51277

0.990164

Thioester

745

CHEBI:37123

0.989925

Nucleoside bisphosphate

708

CHEBI:60971

0.989796

Aminophospholipid

104

CHEBI:18303

0.989796

Phosphatidyl-L-serine

104

CHEBI:64583

0.986667

Sphingomyelin

251

CHEBI:58342

0.985302

Acyl-CoA(4-)

613

CHEBI:74927

0.985222

Furopyran

934

CHEBI:35766

0.983871

Glycerophosphoserine

129

CHEBI:78799

0.983607

Hydroxy fatty acid ascaroside

152

CHEBI:52565

0.980769

Acylglycerophosphoserine

114

CHEBI:26875

0.980392

Terpenyl phosphate

133

CHEBI:36233

0.980392

Disaccharide

156

CHEBI:64482

0.979315

Phosphatidylcholine

623

CHEBI:57643

0.979315

1,2-diacyl-sn-glycero-3-phosphocholine

621

Class_id

f1_score

Class_name

Class_members

CHEBI:64365

0.333333

Aralkylamino compound

138

CHEBI:22715

0.333333

Benzimidazoles

352

CHEBI:23697

0.328358

Dichlorobenzene

452

CHEBI:48470

0.322581

Amidobenzoic acid

148

CHEBI:25235

0.320000

Monomethoxybenzene

247

CHEBI:46848

0.315789

N-arylpiperazine

176

CHEBI:51681

0.305085

Dimethoxybenzene

269

CHEBI:26455

0.294118

Pyrroles

200

CHEBI:83403

0.293333

Monochlorobenzenes

429

CHEBI:50995

0.292683

Secondary amino compound

417

CHEBI:27024

0.277778

Toluenes

135

CHEBI:37407

0.259887

Cyclic ether

806

CHEBI:73539

0.256410

Naphthyridine derivative

162

CHEBI:26878

0.251429

Tertiary alcohol

756

CHEBI:36786

0.246246

Tetralins

108

CHEBI:27116

0.235294

Trihydroxyflavone

150

CHEBI:38338

0.235294

Aminopyrimidine

149

CHEBI:33572

0.222222

Resorcinols

153

CHEBI:83812

0.114286

Non-proteinogenic amino acid derivative

145

CHEBI:13248

0.108108

Anilide

279