Blood-Brain Barrier
Model	A_BBB_I
Desc.	The entire dataset were collected from Shen's work, which included 1839 compounds (1438 BBB+ and 401 BBB- compounds).
Q	0.9429	SE	0.9861
SP	0.788	AUC	0.9517
Reference

Caco-2 Permeability
Model	A_Caco2_I
Desc.	In total, 674 compounds were collected from Hai Pham The et al, including 303 Coca2+ and 371 Coca- compounds. If a compound with the Caco-2 permeability value (Papp) ≥ 8×10-6 cm/s, it is labeled as high Caco-2 permeability, otherwise it is labeled as moderate-poor permeability.
Q	0.7463	SE	0.6964
SP	0.7871	AUC	0.8216
Reference

Human Intestinal Absorption
Model	A_HIA_I
Desc.	The entire dataset were collected from Shen's work, which included 578 compounds (500 HIA+ and 78 HIA- compounds). If a compound with the HIA% is less than 30%, it is labeled as HIA-, otherwise it is labeled as HIA+.
Q	0.9394	SE	0.98
SP	0.6795	AUC	0.9458
Reference

P-glycoprotein Inhibitor
Model	A_PgpI_I
Desc.	In total, 1273 compounds were collected from Chen et al. including 797 Pgp inhibitors and 476 Pgp non-inhibitors.
Q	0.7855	SE	0.872
SP	0.6408	AUC	0.8529
Reference

P-glycoprotein Inhibitor
Model	A_PgpI_II
Desc.	In total, 1275 compounds were collected from Broccatelli et al., including 666 Pgp inhibitors and 609 Pgp non-inhibitors.
Q	0.8659	SE	0.8709
SP	0.8604	AUC	0.9217
Reference

P-glycoprotein Substrate
Model	A_PgpS_I
Desc.	In total, 332 compounds were collected from Wang et al. including 206 Pgp substrates and 126 Pgp non-substrates.
Q	0.7349	SE	0.8689
SP	0.5159	AUC	0.7678
Reference

Subcellular localization
Model	D_SCL_I
Desc.	In total, 491 compounds, including 132 localized in lysosome, 190 in mitochondira, 81 in nucleus, and 88 in plasma membrane, were collected from literature and trained by support vector machine. The model will give the most likely localization in cell and the propability of the query compound.

Renal Organic Cation Transporter
Model	E_OCT2I_I
Desc.	In total, 906 molecules, including 244 inhibitors and 633 non-inhibitors against the renal organic cation transporter (OCT2/SLC22A2) were collected from Kido’s work for model building.
Q	0.7949	SE	0.4385
SP	0.9261	AUC	0.8074
Reference

Biodegradation
Model	M_BIO_I
Desc.	1604 compounds including 591 ready biodegradable chemicals and 1013 not ready biodegradable chemicals were collected from Cheng's work, Cheng et al.
Q	0.8323	SE	0.7513
SP	0.8796	AUC	0.8898
Reference

CYP450 1A2 Inhibitor
Model	M_CYP1A2I_I
Desc.	In total, 14903 compounds, including 7415 inhibitors and 7488 noninhibitors were collected from Cheng et al. A compound was assigned as a CYP inhibitor if the AC50 (the compound concentration leads to 50% of the activity of an inhibition control) value was e10 μM, and it was considered as a noninhibitor if AC50 was >57 μM. In addition, a compound was regarded as a CYP inhibitor if it has the PubChem activity score between 40 and 100, and as a noninhibitor if it has PubChem activity score equal to 0.
Q	0.8147	SE	0.7985
SP	0.8307	AUC	0.8832
Reference

CYP450 2C19 Inhibitor
Model	M_CYP2C19I_I
Desc.	In total, 14576 compounds, including 6041 inhibitors and 8535 noninhibitors were collected from Cheng et al. A compound was assigned as a CYP inhibitor if the AC50 (the compound concentration leads to 50% of the activity of an inhibition control) value was e10 μM, and it was considered as a noninhibitor if AC50 was >57 μM. In addition, a compound was regarded as a CYP inhibitor if it has the PubChem activity score between 40 and 100, and as a noninhibitor if it has PubChem activity score equal to 0.
Q	0.8054	SE	0.7479
SP	0.846	AUC	0.8712
Reference

CYP450 2C9 Inhibitor
Model	M_CYP2C9I_I
Desc.	In total, 14709 compounds, including 4978 inhibitors and 9731 noninhibitors were collected from Cheng et al. A compound was assigned as a CYP inhibitor if the AC50 (the compound concentration leads to 50% of the activity of an inhibition control) value was e10 μM, and it was considered as a noninhibitor if AC50 was >57 μM. In addition, a compound was regarded as a CYP inhibitor if it has the PubChem activity score between 40 and 100, and as a noninhibitor if it has PubChem activity score equal to 0.
Q	0.8018	SE	0.637
SP	0.8861	AUC	0.8582
Reference

CYP450 2C9 Substrate
Model	M_CYP2C9S_I
Desc.	In total, 673 drugs including 142 substrates and 531 non-substrates were collected from Carbon-Mangles's work.
Q	0.7875	SE	0.0423
SP	0.9868	AUC	0.5748
Reference

CYP450 2D6 Inhibitor
Model	M_CYP2D6I_I
Desc.	In total, 14741 compounds, including 3060 inhibitors and 11681 noninhibitors were collected from Cheng et al. A compound was assigned as a CYP inhibitor if the AC50 (the compound concentration leads to 50% of the activity of an inhibition control) value was e10 μM, and it was considered as a noninhibitor if AC50 was >57 μM. In addition, a compound was regarded as a CYP inhibitor if it has the PubChem activity score between 40 and 100, and as a noninhibitor if it has PubChem activity score equal to 0.
Q	0.8551	SE	0.4556
SP	0.9598	AUC	0.8396
Reference

CYP450 2D6 Substrate
Model	M_CYP2D6S_I
Desc.	In total, 671 drugs including 191 substrates and 480 non-substrates were collected from Carbon-Mangles's work.
Q	0.7586	SE	0.377
SP	0.9104	AUC	0.7456
Reference

CYP450 3A4 Inhibitor
Model	M_CYP3A4I_I
Desc.	In total, 18561 compounds, including 6707 inhibitors and 11854 non-inhibitors were collected from Cheng' work. A compound was assigned as a CYP inhibitor if the AC50 (the compound concentration leads to 50% of the activity of an inhibition control) value was 10 μM, and it was considered as a non-inhibitor if AC50 was >57 μM. In addition, a compound was regarded as a CYP inhibitor if it has the PubChem activity score between 40 and 100, and as a non-inhibitor if it has PubChem activity score equal to 0.
Q	0.645	SE	0.865
SP	0.525	AUC	0.848
Reference

CYP450 3A4 Substrate
Model	M_CYP3A4S_I
Desc.	In total, 671 drugs including 357 substrates and 317 non-substrates were collected from Carbon-Mangles's work.
Q	0.638	SE	0.7059
SP	0.5615	AUC	0.6735
Reference

CYP Inhibitory Promiscuity
Model	M_CYPPro_I
Desc.	In total, 5461 compounds, including 3269 high P450 inhibitory promiscuous compounds (Iinh≥0.8) and 2192 low P450 inhibitory promiscuous compounds (Iinh≤0.2) were collected from Cheng's work.
Q	0.821	SE	0.885
SP	0.725	AUC	0.879
Reference

AMES Toxicity
Model	T_AMES_I
Desc.	8445 Compounds including 4912 AMES toxic chemicals and 3533 non AMES toxic chemicals were collected from 10 published papers.
Q	0.8514	SE	0.8827
SP	0.8078	AUC	0.9082
Reference

Acute Oral Toxicity
Model	T_AO_I
Desc.	12,204 diverse compounds with LD50 were classified into four categories based on the criterion of US EPA (Category I contains compounds with LD50 values less than or equal to 50mg/kg. Category II contains compounds with LD50 values greater than 50mg/kg but less than 500mg/kg. Category III includes compounds with LD50 values greater than 500mg/kg but less than 5000mg/kg. Category IV consisted of compounds with LD50 values greater than 5000mg/kg).

Carcinogenicity (Three-class)
Model	T_Carc3_I
Desc.	981 structurally diverse chemicals for rat carcinogenicity extracted from Carcinogenic Potency Database (CPDB) were divided into three classes, labeled "Danger", "Warning" and "Non-required", according to the TD50 values. Carcinogenic compounds with TD50 <= 10 mg/kg body wt/day were assigned as "Danger", those with TD50 > 10 mg/kg body wt/day were assigned as "Warning", and non-carcinogenic chemicals were assigned as "Non-required".

Carcinogens
Model	T_Carc_I
Desc.	In total, 293 chemicals, including 64 carcinogens and 229 noncarcinogens were collected from Lagunin et al.,
Q	0.884	SE	0.5625
SP	0.9738	AUC	0.8356
Reference

Fish Toxicity
Model	T_FHMT_I
Desc.	In total, 554 compounds, including 336 high fathead minnow toxicity (FHMT) compounds and 188 low FHMT compounds were collected from EPA Fathead Minnow Acute Toxicity Database EPAFHM. If a compound with the value of LC50 more than 0.5 mmol/L were assigned as high acute FHMT compound, whereas it was assigned as low acute FHMT compounds.
Q	0.8141	SE	0.8962
SP	0.6543	AUC	0.88
Reference

Honey Bee Toxicity
Model	T_HBT_I
Desc.	In total, 195 pesticides or pesticide-like molecules, including 99 high honey bee toxicity compounds and 96 low HBT compounds were collected from US EPA ECOTOX Database. If a compound with the value of LD50 more than 100 μg/bee were assigned as high acute HBT compound, while it was assigned as low acute HBT compound.
Q	0.759	SE	0.7576
SP	0.7604	AUC	0.824
Reference

Human Ether-a-go-go-Related Gene Inhibition
Model	T_hERG_I
Desc.	368 molecules including 79 strong hERG inhibitors (pIC50> 6.0 mol/L)and 289 weak hERG inhibitors (pIC50≤6.0 mol/L) were collected from Marchese Robinson et al.
Q	0.8696	SE	0.4937
SP	0.9723	AUC	0.82
Reference

Human Ether-a-go-go-Related Gene Inhibition
Model	T_hERG_II
Desc.	806 molecules including 433 hERG inhibitors (IC50> 50 μM) and 373 hERG noninhibitors (pIC50≤50 μM) were collected from Wang's work,.
Q	0.7841	SE	0.7829
SP	0.7855	AUC	0.8492
Reference

Tetrahymena Pyriformis Toxicity
Model	T_TPT_I
Desc.	In total, 1571 compounds, including 1217 high Tetrahymena Pyriformis Toxicity (TPT) compounds and 354 low TPT compounds, were collected from Cheng et al. If a compound with the pIGC50 (the negative logarithm of 50% growth inhibitory concentration) > -0.5 was assigned as TPT, otherwise as non-TPT.
Q	0.9173	SE	0.9581
SP	0.7768	AUC	0.9562
Reference

Caco-2 Permeability
Model	R_A_Caco2_I
Desc.	In total, 674 drug or drug-like molecules with Caco-2 permeability values were used.
R2	0.564	RMSD	0.339
Reference

Aqueous solubility
Model	R_A_WS_I
Desc.	In total, 1708 molecules with LogS value were collected from Wang's work.
R2	0.81	RMSD	0.823
Reference

Fish Toxicity
Model	R_T_FHMT_I
Desc.	In total, 554 pesticides or pesticide-like molecules with pLC50 (mg/L) value were collected from EPA Fathead Minnow Acute Toxicity Database EPAFHM.
R2	0.574	RMSD	0.666
Reference

Rat Acute Toxicity
Model	R_T_RAT_I
Desc.	In total, 10207 molecules with LD50 (mg/L) against rat were collected from Zhu's work.
R2	0.613	RMSD	0.324
Reference

Tetrahymena Pyriformis Toxicity
Model	R_T_TPT_I
Desc.	In total, 1571 compounds with pIGC50 (ug/L) value against Tetrahymena pyriformis were collected from Cheng's work.
R2	0.761	RMSD	0.256
Reference