Research Article
Optimization Method of an Antibreast Cancer Drug Candidate Based on Machine Learning
Table 1
The contribution of the top 224 important molecular descriptors (from low to high).
| Descriptor | Importance |
| Smax11 | 0.00065 | MATSp7 | 0.00065 | CIC4 | 0.000652 | MDEC-14 | 0.000656 | S17 | 0.000659 | minHCsats | 0.00066 | Smin34 | 0.000661 | SHaaCH | 0.000664 | SIC3 | 0.000664 | SHCsats | 0.000681 | Smin | 0.000681 | CrippenLogP | 0.000682 | maxsOH | 0.000684 | ATSc1 | 0.000684 | bcutm13 | 0.000684 | phi | 0.000686 | MATSm3 | 0.000688 | CIC3 | 0.000688 | VSAEstate7 | 0.000691 | SPC-4 | 0.000695 | EstateVSA7 | 0.000702 | Smin8 | 0.000704 | WTPT-5 | 0.000706 | TPSA1 | 0.000708 | naccr | 0.00071 | MATSm7 | 0.000712 | maxdsN | 0.000712 | CIC1 | 0.000713 | Smin35 | 0.000714 | ATSe5 | 0.000716 | minHCsatu | 0.000725 | GATSp3 | 0.000726 | GATSm5 | 0.000727 | ALogp2 | 0.000729 | GATSp7 | 0.00073 | EstateVSA1 | 0.000737 | IDE | 0.000741 | mindO | 0.000744 | mChi1 | 0.000745 | SaasC | 0.00076 | bcute9 | 0.000761 | nAtomLAC | 0.000762 | maxdssC | 0.000771 | GATSe7 | 0.000775 | Smax | 0.000781 | ETA_Epsilon_1 | 0.000787 | MATSv5 | 0.000789 | bcutp5 | 0.000793 | IC1 | 0.000796 | maxHBint7 | 0.000797 | QCss | 0.000823 | CIC6 | 0.000823 | ALogP | 0.000826 | bcutm3 | 0.00083 | SsOH | 0.000847 | BertzCT | 0.000851 | EstateVSA4 | 0.000851 | SdssC | 0.000855 | bcutm2 | 0.000866 | MAXDN | 0.000868 | PC6 | 0.000872 | MATSm6 | 0.000891 | SHBint5 | 0.000897 | SaaCH | 0.0009 | MATSp5 | 0.000901 | MRVSA6 | 0.000904 | slogPVSA1 | 0.000904 | MATSm5 | 0.000922 | bcute12 | 0.000926 | J | 0.000927 | GATSm4 | 0.000927 | MRVSA5 | 0.000933 | MATSm1 | 0.000934 | GATSm8 | 0.000939 | Smin12 | 0.000946 | hmin | 0.00095 | VC-4 | 0.000962 | MATSe5 | 0.000963 | MATSp4 | 0.000964 | PEOEVSA5 | 0.000967 | minHBd | 0.000971 | GATSv3 | 0.000974 | bcutm9 | 0.000979 | PEOEVSA8 | 0.00098 | ECCEN | 0.000987 | MATSm8 | 0.000988 | IC2 | 0.000995 | BCUTp-1l | 0.001004 | minssCH2 | 0.001017 | QHss | 0.001019 | Smax16 | 0.00102 | bcutm12 | 0.001026 | ETA_EtaP_F | 0.001026 | ETA_dEpsilon_D | 0.001038 | bcute4 | 0.001038 | WTPT-3 | 0.001042 | MAXDP2 | 0.001042 | knotpv | 0.001043 | MDEO-11 | 0.001043 | maxHCsats | 0.00105 | Chiv5ch | 0.001063 | GATSe5 | 0.001072 | VPC-5 | 0.001081 | MATSv8 | 0.00109 | maxsF | 0.001096 | QNmin | 0.001109 | ETA_BetaP_s | 0.001109 | Chiv6ch | 0.00111 | IC3 | 0.001117 | VPC-6 | 0.001119 | VSAEstate2 | 0.001121 | MATSp3 | 0.001137 | slogPVSA2 | 0.00114 | WTPT-4 | 0.001162 | gmin | 0.001163 | minHBint6 | 0.001176 | minHBint7 | 0.001195 | Smax24 | 0.001225 | MATSp6 | 0.001229 | PEOEVSA1 | 0.001234 | SIC2 | 0.001237 | S34 | 0.001257 | bcute1 | 0.001278 | MATSv3 | 0.001281 | SC-5 | 0.001283 | dchi0 | 0.00129 | SIC1 | 0.001291 | maxHBd | 0.001307 | PEOEVSA7 | 0.001342 | MDEC-24 | 0.001345 | SCH-7 | 0.001347 | SHBd | 0.001349 | MATSe8 | 0.001375 | MATSv1 | 0.001375 | SHCsatu | 0.001386 | Smin15 | 0.001398 | BCUTp-1h | 0.00141 | GATSm3 | 0.001461 | bcutp12 | 0.001465 | MLFER_BH | 0.001485 | GATSv1 | 0.001559 | QOmax | 0.001589 | slogPVSA0 | 0.001592 | bcute10 | 0.001605 | Smin24 | 0.001609 | MATSp1 | 0.001616 | Chiv3 | 0.001662 | QNmax | 0.001663 | bcutv4 | 0.00168 | VCH-5 | 0.001717 | VSAEstate4 | 0.001785 | ATSc5 | 0.001813 | C3SP2 | 0.001831 | mindssC | 0.001846 | ATSc2 | 0.001859 | minHBint10 | 0.001866 | ATSc3 | 0.001892 | MDEC-22 | 0.001909 | MAXDP | 0.001935 | knotp | 0.001942 | GATSm1 | 0.002 | GATSp4 | 0.002026 | maxsssCH | 0.002031 | S25 | 0.002032 | bcutp1 | 0.002049 | ETA_Shape_Y | 0.002124 | bcutp9 | 0.002186 | XLogP | 0.002237 | ATSc4 | 0.002298 | maxHBint5 | 0.002321 | maxHBint8 | 0.002379 | minsOH | 0.002424 | GATSm2 | 0.002443 | SPC-6 | 0.00248 | MATSe3 | 0.002549 | MLFER_S | 0.002597 | SHBint6 | 0.002733 | ndssC | 0.002743 | bcutv1 | 0.002787 | VCH-7 | 0.002879 | BCUTc-1l | 0.002923 | QCmax | 0.00298 | Scar | 0.003191 | minssO | 0.003312 | BCUTc-1h | 0.003494 | MLFER_A | 0.003711 | TopoPSA | 0.003768 | MDEO-12 | 0.003868 | minHBa | 0.004054 | Smin33 | 0.004253 | SHsOH | 0.004402 | GATSe8 | 0.004485 | PEOEVSA6 | 0.00461 | Mnc | 0.004826 | MATSe1 | 0.004978 | LDI | 0.005205 | MDEC-33 | 0.005471 | GATSe1 | 0.005843 | bcute2 | 0.005866 | VC-5 | 0.006197 | nC | 0.0064 | nHBAcc | 0.006408 | LogP2 | 0.006781 | SHBint10 | 0.006873 | Hy | 0.007517 | kappam3 | 0.007695 | VSAEstate1 | 0.007799 | QNss | 0.009891 | minsssN | 0.01014 | LogP | 0.011371 | maxssO | 0.011647 | ATSp4.1 | 0.013044 | QHmax | 0.014923 | C1SP2 | 0.01631 | minHBint5 | 0.017225 | ATSv5 | 0.017404 | Smax35 | 0.018515 | minHsOH | 0.025883 | maxHsOH | 0.028849 | LipoaffinityIndex | 0.031403 | QOmin | 0.041317 | Qmin | 0.043254 | MDEC-23 | 0.049635 | ATSp5.1 | 0.143226 |
|
|