机器学习的打分方程汇总

机器学习的打分方程集合

  受到机器学习(Machine Learning)和深度学习(Deep Learning)等算法模型的创新性冲击,其应用范围涵盖了自然语言处理(Natural Language Processing)、自动驾驶(Autopilot)、金融分析(Financial analysis)和生物医药研发(Biopharmaceutical R&D)等多个领域。其中,应用深度学习算法在预测小分子药物与疾病靶点蛋白之间的结合亲和力方面的设计和应用变得日益重要。分子对接(Molecular Docking)计算中打分方程(Scoring Function)算法通常用于对药物活性数据进行评估、分类、排名或预测,其结果对于决策制定候选药物分子而言至关重要。因此,本文将介绍一些基于机器学习和深度学习的打分方程。

1. 亲和力预测模型

ModelAlgorithmRpRMSEReference
AGL-ScoreGBT0.831.27[13]
ECIFGBT0.871.17[14]
AEScoreMLP0.831.22[15]
OnionNet-2CNN0.861.16[16]
graphDeltaGNN0.871.05[17]
PointTransformerCNN+ATT0.851.19[18]

2. 机器学习打分方程

Scoring FunctionAlgorithmDescription of protein–ligand complexesReference
RF-ScoreRFProtein−ligand atom-type pair countsBallester et al. (2010)
NN-Score 2.0ANNAutodock Vina interaction terms, protein−ligand atom-type pair counts and electrostatic terms (BINANA)Durrant and McCammon (2011)
ID-ScoreSVMNine categories of descriptors related to protein–ligand interactionsLi et al. (2013)
SFCscore R F ^{RF} RFRFSFCscore interaction termsZilian and Sotriffer (2013)
ΔVinaRF 20 _{20} 20RFAutodock Vina interaction terms and additional molecular descriptorsWang and Zhang (2017)
RI-ScoreRFRigidity index descriptorsNguyen et al. (2017)
TNet-BPCNNAlgebraic topologyCang and Wei (2017)
K D E E P _{DEEP} DEEPCNNMolecular descriptors embedded into a 3D gridJiménez et al. (2018)
TopBP-MLGBTAlgebraic topologyCang et al. (2018)
TopBP-DLCNNAlgebraic topologyCang et al. (2018)
PafnucyCNNMolecular descriptors embedded into a 3D gridStepniewska-Dziubinska et al. (2018)
PLEC-nnDNNHashed fingerprint constructed by pairing ligand and protein atoms according to its environmentWójcikowski et al. (2019)
EIC-ScoreGBTDifferential geometry representationsNguyen and Wei (2019b)
AGL-ScoreGBTStatistical features of the adjacency and Laplacian matrices of multiscale weighted labeled algebraic subgraphsNguyen and Wei (2019a)
OnionNetCNNRotation-free element pair-specific contacts between ligands and protein atoms, grouped into different distance rangesZheng et al. (2019)
ΔVinaXGBXGBTAutodock Vina score and molecular descriptors, including water moleculesLu et al. (2019)
NNScore::LDFFNNNNScore 2.0 features and RDKit ligand descriptorsBoyles et al. (2020)
RosENetCNNMolecular mechanics energies from Rosetta force field and molecular descriptors embedded onto a 3D gridHassan-Harrirou et al. (2020)
ECIF-GBTGBTProtein−ligand atom-type pair counts considering each atoms connectivityNorberto et al. (2021)
ECIF::LD-GBTGBTProtein−ligand atom-type pair counts considering each atoms connectivity and RDKit ligand descriptorsNorberto et al. (2021)
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值