The Development of Target-Specific Machine Learning Models as Scoring Functions for Docking-Based Target Prediction

被引:39
|
作者
Nogueira, Mauro S. [1 ]
Koch, Oliver [1 ,2 ]
机构
[1] TU Dortmund Univ, Fac Chem & Chem Biol, Otto Hahn Str 6, D-44227 Dortmund, Germany
[2] Westfalische Wilhelms Univ Munster, Inst Pharmaceut & Med Chem, Corrensstr 48, D-48149 Munster, Germany
关键词
WEB SERVER; MACROMOLECULAR TARGETS; INTERACTION FINGERPRINT; DRUG DISCOVERY; CLASSIFICATION; IDENTIFICATION; PHARMACOLOGY; MECHANISMS; MOLECULES; UPDATE;
D O I
10.1021/acs.jcim.8b00773
中图分类号
R914 [药物化学];
学科分类号
100701 ;
摘要
The identification of possible targets for a known bioactive compound is of the utmost importance for drug design and development. Molecular docking is one possible approach for in-silico protein target prediction, whereas a molecule is docked into several different protein structures to identify potential targets. This reverse docking approach is hampered by the limitation of current scoring functions to correctly discriminate between targets and nontargets. In this work, a development of target-specific scoring functions is described that showed improved prediction performances for the correct target prediction of both actives and decoys on three validation data sets. In contrast to pure ligand-based approaches, that are in general faster and include a greater target space, docking-based approaches can cover also unknown chemical space that lies outside the known bioactivity data. These target-specific scoring functions are based on known bioactivity data retrieved from ChEMBL and supervised machine learning approaches. Neural Networks and Support Vector Machines (SVMs) models were trained for 20 different protein targets. Our protein-ligand interaction fingerprint PADIF (Protein Atom Score Contributions Derived Interaction Fingerprint) represents the input for training, whereas the PADIFs are calculated based on docking poses of active and inactive compounds. Different data sets of previously unseen molecules were used for the final evaluation and analysis of the prediction performance of the created models. For a single-target selectivity data set, the correct target model returns in most of the cases the highest probabilities scores for their active molecules and with statistically significant differences from the other targets. These probability scores were also predicted and successfully used to rank the targets for molecules of a multitarget data set with activity data described simultaneously for two, three, and four to seven protein targets.
引用
收藏
页码:1238 / 1252
页数:15
相关论文
共 50 条
  • [41] Author Correction: Prediction-based highly sensitive CRISPR off-target validation using target-specific DNA enrichment
    Seung-Hun Kang
    Wi-jae Lee
    Ju-Hyun An
    Jong-Hee Lee
    Young-Hyun Kim
    Hanseop Kim
    Yeounsun Oh
    Young-Ho Park
    Yeung Bae Jin
    Bong-Hyun Jun
    Junho K. Hur
    Sun-Uk Kim
    Seung Hwan Lee
    Nature Communications, 12
  • [42] Using diverse potentials and scoring functions for the development of improved machine-learned models for protein–ligand affinity and docking pose prediction
    Omar N. A. Demerdash
    Journal of Computer-Aided Molecular Design, 2021, 35 : 1095 - 1123
  • [43] Development of Target-specific Gene Therapy System by Controlling Distribution of Interferon
    Takahashi, Yuki
    YAKUGAKU ZASSHI-JOURNAL OF THE PHARMACEUTICAL SOCIETY OF JAPAN, 2012, 132 (09): : 1057 - 1061
  • [44] Impact of scoring functions on enrichment in docking-based virtual screening: An application study on renin inhibitors
    Krovat, EM
    Langer, T
    JOURNAL OF CHEMICAL INFORMATION AND COMPUTER SCIENCES, 2004, 44 (03): : 1123 - 1129
  • [45] Impact of target-specific oral anticoagulants on transitions of care and outpatient care models
    Wittkowsky, Ann K.
    JOURNAL OF THROMBOSIS AND THROMBOLYSIS, 2013, 35 (03) : 304 - 311
  • [46] Impact of target-specific oral anticoagulants on transitions of care and outpatient care models
    Ann K. Wittkowsky
    Journal of Thrombosis and Thrombolysis, 2013, 35 : 304 - 311
  • [47] The Role of Automation in Engineering Target-specific Disease Models and Reporter Cell Lines
    Patterson, E.
    IN VITRO CELLULAR & DEVELOPMENTAL BIOLOGY-ANIMAL, 2018, 54 : S10 - S10
  • [48] Incorporating Target-Specific Pharmacophoric Information into Deep Generative Models for Fragment Elaboration
    Hadfield, Thomas E.
    Imrie, Fergus
    Merritt, Andy
    Birchall, Kristian
    Deane, Charlotte M.
    JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2022, 62 (10) : 2280 - 2292
  • [49] A Machine Learning Approach to Enhance Scoring Performance in Docking-Based Virtual Screening Experiments: COX-1 as a Case Study
    Silva, Candida G.
    Carreiras, Pedro
    Henriques, Elsa S.
    Simoes, Carlos J. V.
    Brito, Rui M. M.
    PROCEEDINGS IWBBIO 2014: INTERNATIONAL WORK-CONFERENCE ON BIOINFORMATICS AND BIOMEDICAL ENGINEERING, VOLS 1 AND 2, 2014, : 406 - 414
  • [50] Target-Specific Drug Design Method Combining Deep Learning and Water Pharmacophore
    Kim, Minsup
    Park, Kichul
    Kim, Wonsang
    Jung, Sangwon
    Cho, Art E.
    JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2021, 61 (01) : 36 - 45