Filters








11,680 Hits in 5.5 sec

The influence of the inactives subset generation on the performance of machine learning methods

Sabina Smusz, Rafał Kurczab, Andrzej J Bojarski
2013 Journal of Cheminformatics  
It appeared that the process of inactive set formation had a substantial impact on the machine learning methods performance.  ...  All learning methods were tested in two modes: using one test set, the same for each method of inactive molecules generation and using test sets with inactives prepared in an analogous way as for training  ...  Acknowledgements The study was partly supported by a project UDA-POIG.01.03.01-12-100/08-00 co-financed by the European Union from the European Fund of Regional Development (EFRD); http://www.prokog.pl  ... 
doi:10.1186/1758-2946-5-17 pmid:23561266 pmcid:PMC3626618 fatcat:woss6cjjbbefdmu5cxw42i6gwe

QSAR based predictive modeling for anti-malarial molecules

Deepak R. Bharti, Andrew M. Lynn
2017 Bioinformation  
The use of machine learning methods is now commonly available through open source programs.  ...  Multiple model building methods are used including Generalized Linear Models (GLM), Random Forest (RF), C5.0 implementation of a decision tree, Support Vector Machines (SVM), K-Nearest Neighbour and Naive  ...  Hence exploring other machine learning methods with different feature selection and generation may be investigated.  ... 
doi:10.6026/97320630013154 pmid:28690382 pmcid:PMC5498782 fatcat:5a5mq6bxu5gwfbs6aahhhht22y

Cheminformatics models based on machine learning approaches for design of USP1/UAF1 abrogators as anticancer agents

Divya Wahi, Salma Jamal, Sukriti Goyal, Aditi Singh, Ritu Jain, Preeti Rana, Abhinav Grover
2015 Journal of Systems and Synthetic Biology  
A machine learning approach was devised for generation of computational models that could predict for potential anti USP1/UAF1 biological activity of novel anticancer compounds.  ...  The structural fragment analysis was further performed to explore structural properties of the molecules.  ...  Conflict of interest The authors declare that they have no conflict of interest.  ... 
doi:10.1007/s11693-015-9162-1 pmid:25972987 pmcid:PMC4427583 fatcat:622mfrmz5nfmzlmvrojgpqszja

Influence of Varying Training Set Composition and Size on Support Vector Machine-Based Prediction of Active Compounds

Raquel Rodríguez-Pérez, Martin Vogt, Jürgen Bajorath
2017 Journal of Chemical Information and Modeling  
Support vector machine (SVM) modeling is one of the most popular machine learning approaches in chemoinformatics and drug design.  ...  The influence of training set composition and size on predictions currently is an underinvestigated issue in SVM modeling.  ...  and other machine learning methods. 7, 8 Especially the choice of negative training examples is often little considered in machine learning.  ... 
doi:10.1021/acs.jcim.7b00088 pmid:28376613 pmcid:PMC5417594 fatcat:skqugxm7mzecjds6xaige2aj7e

Kinome-wide activity classification of small molecules by deep learning [article]

Bryce K Allen, Nagi G Ayad, Stephan C Schürer
2019 bioRxiv   pre-print
Because such data is not publicly available, we evaluated multiple machine learning methods to predict small molecule inhibition of 342 kinases using over 650K aggregated bioactivity annotations for over  ...  However, the application of deep learning to discriminating features of kinase inhibitors has not been well explored.  ...  Generally, the KA-PI models performed better than the KA-KI classifiers across all machine learning methods.  ... 
doi:10.1101/512459 fatcat:tjxoyyoodne65niucfnv5ay23u

Performance of machine-learning scoring functions in structure-based virtual screening

Maciej Wójcikowski, Pedro J. Ballester, Pawel Siedlecki
2017 Scientific Reports  
Indeed, the degree with which machine-learning  ...  We use the full DUD-E data sets along with three docking tools, five classical and three machine-learning scoring functions for model building and performance assessment.  ...  Acknowledgements This work was supported by the Polish Ministry of Science and Higher Education POIG.02.03.00-00-003/09-00 and POIG.02.02.00-14-024/08-00.  ... 
doi:10.1038/srep46710 pmid:28440302 pmcid:PMC5404222 fatcat:xzylkmmdybdydgkjcgol5xolcu

Prediction of P53 Mutants (Multiple Sites) Transcriptional Activity Based on Structural (2D&3D) Properties

R. Geetha Ramani, Shomona Gracia Jacob, Freddie Salsbury
2013 PLoS ONE  
We expect that our prediction methods and reported results may provide useful insights on p53 functional mechanisms and generate more avenues for utilizing computational techniques in biological data analysis  ...  The optimal MCC obtained by the proposed approach on prediction of one-site, two-site, three-site, four-site and five-site mutants were 0.775,0.341,0.784,0.916 and 0.655 respectively, the highest reported  ...  Acknowledgments The authors wish to thank the Editor and the kind Reviewers for their candid and constructive comments, which was very effective in strengthening the presentation of this research.  ... 
doi:10.1371/journal.pone.0055401 pmid:23468845 pmcid:PMC3572112 fatcat:drh7osbx7reljh7wq5omgyjfqy

Deep Learning-Based Structure-Activity Relationship Modeling for Multi-Category Toxicity Classification: A Case Study of 10K Tox21 Chemicals With High-Throughput Cell-Based Androgen Receptor Bioassay Data

Gabriel Idakwo, Sundar Thangapandian, Joseph Luttrell, Zhaoxian Zhou, Chaoyang Zhang, Ping Gong
2019 Frontiers in Physiology  
To further explore the advantages of DL over shallow learning, we conducted this case study using two cell-based androgen receptor (AR) activity datasets with 10K chemicals generated from the Tox21 program  ...  inconclusive) at the same distribution rates amongst the training, validation and test subsets.  ...  Machine Learning Methods Machine Learning-Based SAR Modeling Approach The overall workflow of our machine learning-based SAR modeling approach is illustrated in Figure 1 .  ... 
doi:10.3389/fphys.2019.01044 pmid:31456700 pmcid:PMC6700714 fatcat:pn3nyjktt5cgpncsqewogbfqgm

Dibenzoylhydrazines as Insect Growth Modulators: Topology-Based QSAR Modelling

J.P. Doucet, A. Doucet-Panaye
2020 Advances in Sciences and Engineering  
Various Machine Learning approaches (Partial Least Squares Regression, Projection Pursuit Regression, Linear Support Vector Machine or Three Layer Perceptron Artificial Neural Network) confirm the validity  ...  Robustness and quality of the model were carefully examined at various levels: data-fitting (recall), leave-one (or some) - out, internal and external validation (including random splitting), points not  ...  They will be then applied to various Machine Learning methods using different representations of the descriptor space.  ... 
doi:10.32732/ase.2020.12.1.28 fatcat:hlwbgfwrd5aezkf24cy5pygkxm

Multiple conformational states in retrospective virtual screening – homology models vs. crystal structures: beta-2 adrenergic receptor case study

Stefan Mordalski, Jagna Witek, Sabina Smusz, Krzysztof Rataj, Andrzej J Bojarski
2015 Journal of Cheminformatics  
The results also showed that increasing the number of receptors considered improves the effectiveness of identifying active compounds by machine learning methods.  ...  Distinguishing active from inactive compounds is one of the crucial problems of molecular docking, especially in the context of virtual screening experiments.  ...  Acknowledgements The study was partially supported by the project "Diamentowy Grant" DI 2011 0046 41 financed by the Polish Ministry of Science and Higher Education and by a grant PRELUDIUM 2013/09/N/NZ2  ... 
doi:10.1186/s13321-015-0062-x pmid:25949744 pmcid:PMC4420846 fatcat:rchlj7rpt5catlpbcveb2tbagu

Prediction of orthosteric and allosteric regulations on cannabinoid receptors using supervised machine learning classifiers

Yuemin Bian, Yankang Jing, Lirong Wang, Shifan Ma, Jaden Jungho Jun, Xiang-Qun (Sean) Xie
2019 Molecular Pharmaceutics  
Their performances on the classification with different types of features were compared and discussed.  ...  This study can be of value to the application of machine learning in the area of drug discovery and compound development.  ...  ACKNOWLEDGMENTS The authors would like to acknowledge the funding support to the Xie laboratory from the NIH NIDA (P30 DA035778A1) and DOD (W81XWH-16-1-0490).  ... 
doi:10.1021/acs.molpharmaceut.9b00182 pmid:31013097 pmcid:PMC6732211 fatcat:zlguz4sayfdjroyzimd27v4fci

Traditional machine learning and big data analytics in virtual screening: a comparative study

Sahar K. Hussin, Yasser M. Omar, Salah M. Abdelmageid, Mahmoud I. Marie
2020 International Journal of Advanced Computer Research  
Conflicts of interest The authors have no conflicts of interest to declare.  ...  Support vector machine (SVM), wrapper method (WM) and subset selection subset (SS) have been used to classify ligand as drug-like and non-drug-like [21] .  ...  In [32] , authors offered a pretty new method that is based on Apache Spark and the ensemble learning model to upgrade the performance of largescale VS processes.  ... 
doi:10.19101/ijacr.2019.940150 fatcat:zzdudmniuvaytcqwhvicn4kg64

Drug-induced QT prolongation prediction using co-regularized multi-view learning

Jintao Zhang, Jun Huan
2012 2012 IEEE International Conference on Bioinformatics and Biomedicine  
Multi-view learning (MVL) has been applied to many challenging machine learning and data mining problems, especially when complex data from diverse domains are involved and only limited labeled examples  ...  Comprehensive experimental comparisons between our proposed method and previous MVL and singleview learning methods demonstrate that our method significantly outperforms those baseline methods. ©  ...  We tested these five methods at various experimental settings to investigate the contribution and influence of the related factors on prediction performance. Table II .  ... 
doi:10.1109/bibm.2012.6392630 dblp:conf/bibm/ZhangH12 fatcat:fymb6kafobawxckdkyswgxrkqe

MoleculeNet: A Benchmark for Molecular Machine Learning [article]

Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S. Pappu, Karl Leswing, Vijay Pande
2018 arXiv   pre-print
Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties.  ...  to gauge the quality of proposed methods.  ...  We investigated how the performance of machine learning methods on FreeSolv changes with the volume of training data.  ... 
arXiv:1703.00564v3 fatcat:pmhnvly7qfhrxkel5a6tctowv4

A genetic algorithm approach for predicting ribonucleic acid sequencing data classification using KNN and decision tree

Micheal Olaolu Arowolo, Marion Olubunmi Adebiyi, Adebiyi Ayodele Ariyo, Olatunji Julius Okesola
2021 TELKOMNIKA (Telecommunication Computing Electronics and Control)  
In this study, RNA-Seq data uses a mosquito anopheles gambiae dataset [28] , to test the machine learning method performance.  ...  The efficiency of machine learning approach in genes are shown in the results to confirm the method, the outcomes are revealed and related in Table 2 showing GA-decision tree outperforms GA-KNN terms  ... 
doi:10.12928/telkomnika.v19i1.16381 fatcat:lwdhlxkqufd3fcgsdcd3y2glca
« Previous Showing results 1 — 15 out of 11,680 results