28 Hits in 2.8 sec

Convex Factorization Machine for Toxicogenomics Prediction

Makoto Yamada, Wenzhao Lian, Amit Goyal, Jianhui Chen, Kishan Wimalawarne, Suleiman A. Khan, Samuel Kaski, Hiroshi Mamitsuka, Yi Chang
2017 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '17  
We introduce the convex factorization machine (CFM), which is a convex variant of the widely used Factorization Machines (FMs).  ...  We then show in a toxicogenomics prediction task that CFM predicts the toxic outcomes of a collection of drugs be er than a state-of-the-art tensor factorization method.  ...  CONCLUSION We proposed the convex factorization machine (CFM), which is a convex variant of factorization machines (FMs).  ... 
doi:10.1145/3097983.3098103 dblp:conf/kdd/YamadaLGCWKKMC17 fatcat:yl4rses5cbcyph5icjqyufmvku

Convex Factorization Machine for Regression [article]

Makoto Yamada, Wenzhao Lian, Amit Goyal, Jianhui Chen, Kishan Wimalawarne, Suleiman A Khan, Samuel Kaski, Hiroshi Mamitsuka, Yi Chang
2016 arXiv   pre-print
We propose the convex factorization machine (CFM), which is a convex variant of the widely used Factorization Machines (FMs).  ...  Furthermore, in a toxicogenomics prediction task, we show that CFM outperforms a state-of-the-art tensor factorization method.  ...  • We propose a simple yet efficient optimization procedure for the semidefinite programming problem using Hazan's algorithm [14] . • We applied the proposed CFM for a toxicogenomics prediction task; it  ... 
arXiv:1507.01073v5 fatcat:awqbv6lvejbytmvcs2p25lb4iy

Online Compact Convexified Factorization Machine [article]

Wenpeng Zhang, Xiao Lin, Peilin Zhao
2018 arXiv   pre-print
To address this subsequent challenge, we follow the general projection-free algorithmic framework of Online Conditional Gradient and propose an Online Compact Convex Factorization Machine (OCCFM) algorithm  ...  Factorization Machine (FM) is a supervised learning approach with a powerful capability of feature engineering.  ...  We believe our work sheds light on the Factorization Machine research, especially for online Factorization Machine.  ... 
arXiv:1802.01379v1 fatcat:pu3bcebbrvem3oohnxptvopnhu

A Toxicogenomic Approach for the Prediction of Murine Hepatocarcinogenesis Using Ensemble Feature Selection

Johannes Eichner, Nadine Kossler, Clemens Wrzodek, Arno Kalkuhl, Dorthe Bach Toft, Nina Ostenfeldt, Virgile Richard, Andreas Zell, Enrique Hernandez-Lemus
2013 PLoS ONE  
Predictive models based on toxicogenomics investigations after short-term exposure have shown their potential for assessing the carcinogenic risk.  ...  In this study, we investigated a novel method for the evaluation of toxicogenomics data based on ensemble feature selection in conjunction with bootstrapping for the purpose to derive reproducible and  ...  Acknowledgments We would like to thank Heidrun Ellinger-Ziegelbauer, Michael Schwarz and Jonathan Moggs for critically reading the manuscript and for helpful suggestions.  ... 
doi:10.1371/journal.pone.0073938 pmid:24040119 pmcid:PMC3769381 fatcat:xfaubvrp3rcpvhcautzf3o3nry

Computational prediction of Drug-Disease association based on Graph-regularized one bit Matrix completion [article]

Aanchal Mongia, Emilie Chouzenoux, Angshul Majumdar
2020 bioRxiv   pre-print
This task of drug re-positioning can be assisted by various kinds of computational methods to predict the best indication for a drug given the open-source biological datasets.  ...  The usage of the method is also evaluated through a case study where top 5 indications are predicted for novel drugs and diseases, which then are verified with the CTD database.  ...  There have also been several machine learning and deep learning techniques used for association prediction apart from the ones (clustering and classification methods) used in few of the works mentioned  ... 
doi:10.1101/2020.04.02.020891 fatcat:ser73gkzt5c5daksaf6bjcd2ru

Multiple Similarity Drug-Target Interaction Prediction with Random Walks and Matrix Factorization [article]

Bin Liu, Dimitrios Papadopoulos, Fragkiskos D. Malliaros, Grigorios Tsoumakas, Apostolos N. Papadopoulos
2022 arXiv   pre-print
In this work, we leverage random walks and matrix factorization techniques towards DTI prediction.  ...  To fully take advantage of topology information captured in multiple views, we develop an optimization framework, called MDMF, for DTI prediction.  ...  Matrix Factorization for DTI Prediction In DTI prediction, MF methods typically learn two vectorized representations of drugs and targets that approximate the interaction matrix Y by minimizing the following  ... 
arXiv:2201.09508v1 fatcat:nvbbtymxbba6bigjicz47au6um

Big-data and machine learning to revamp computational toxicology and its use in risk assessment

Thomas Luechtefeld, Craig Rowlands, Thomas Hartung
2018 Toxicology Research  
The creation of large toxicological databases and advances in machine-learning techniques have empowered computational approaches in toxicology.  ...  For example, chemi-cal tonnage and production environment are factors that determine testing requirements for a given compound.  ...  Some approaches to estimate parameters for these distributions include expectation maximization and the concave convex procedure.  ... 
doi:10.1039/c8tx00051d pmid:30310652 pmcid:PMC6116175 fatcat:ms7njv5sbnh6dfbv5lhospcowi

iDrug: Integration of drug repositioning and drug-target prediction via cross-network embedding

Huiyuan Chen, Feixiong Cheng, Jing Li, Avner Schlessinger
2020 PLoS Computational Biology  
In particular, we provide a principled way to transfer knowledge from these two domains and to enhance prediction performance for both tasks.  ...  Computational drug repositioning and drug-target prediction have become essential tasks in the early stage of drug discovery.  ...  For drug-target prediction, Bleakley et al. applied support vector machine to predict novel targets based on a bipartite local model [16] .  ... 
doi:10.1371/journal.pcbi.1008040 pmid:32667925 fatcat:cijsb6z4oradrotstce7kthesq

Automated literature mining and hypothesis generation through a network of Medical Subject Headings [article]

Stephen Wilson, Angela Dawn Wilkins, Matthew V. Holt, Byung Kwon Choi, Daniel Konecki, Chih-Hsu Lin, Amanda Koire, Yue Chen, Seon-Young Kim, Yi Wang, Brigitta Dewi Wastuwidyaningtyas, Jun Qin (+2 others)
2018 bioRxiv   pre-print
We also show that many predictions based on the literature prior to 2014 were published subsequently.  ...  In a practical application, we validated experimentally a surprising new association found by MeTeOR between novel Epidermal Growth Factor Receptor (EGFR) associations and CDK2.  ...  Toxicogenomic Database (CTD) [20] and DisGeNET [76], and these databases were broken 485 down into their component pieces and mapped to Entrez IDs for genes and MeSH terms for 486 diseases.  ... 
doi:10.1101/403667 fatcat:dcjcg4jbtba4xf3roeeskhhuce

Network-Guided Biomarker Discovery [chapter]

Chloé-Agathe Azencott
2016 Lecture Notes in Computer Science  
In machine learning terms, biomarker discovery can be framed as a feature selection problem on whole-genome data sets.  ...  We review here three families of methods for feature selection that integrate prior knowledge in the form of networks.  ...  [79] propose to use set covering machines [80] to learn conjunctions of disjunctions of short genomic sequences to predict bacterial resistance to antibiotics.  ... 
doi:10.1007/978-3-319-50478-0_16 fatcat:na4p4yse4bfi7abmpbcifijf2y

Kernel methods in genomics and computational biology [article]

Jean-Philippe Vert
2005 arXiv   pre-print
Support vector machines and kernel methods are increasingly popular in genomics and computational biology, due to their good performance in real-world applications and strong modularity that makes them  ...  This is particularly appealing for the sparse encoding, because a product of d binary factors is a binary variable equal to 1 if and only if all factors are 1, meaning that the features created by the  ...  machine learning algorithms to sequence processing.  ... 
arXiv:q-bio/0510032v1 fatcat:edpwkefqrnfkjk5eyfzjddwuqe

Optimizing Area Under the Curve Measures via Matrix Factorization for Predicting Drug-Target Interaction with Multiple Similarities [article]

Bin Liu, Grigorios Tsoumakas
2022 arXiv   pre-print
neighbour entities which is more crucial for the DTI prediction model.  ...  This paper first proposes two matrix factorization (MF) methods that optimize AUPR and AUC using convex surrogate losses respectively, and then develops an ensemble MF approach takes advantage of the two  ...  The prevalent chemogenomic computational methods usually rely on machine learning techniques, such as matrix factorization (MF) [5] , kernel machines [6] , network mining [7] , and deep learning [8  ... 
arXiv:2105.01545v2 fatcat:ja2fcyiyajc2bgj46bridbhuw4

WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models [article]

Marine Le Morvan
2018 arXiv   pre-print
Here we present WHInter, a working set algorithm to solve large l1-regularised problems with two-way interactions for binary design matrices.  ...  In section 4, we evaluate WHInter on simulated datasets and finally in Section 5, we report results on a toxicogenomics prediction task.  ...  Figure 4 - 4 Predictive performance on the test set. The y-axis reports the pearson correlation between the true and predicted response.  ... 
arXiv:1802.05980v1 fatcat:aen22eydyzcxbjkq75hm5frfk4

Systems biology approaches for advancing the discovery of effective drug combinations

Karen A Ryall, Aik Tan
2015 Journal of Cheminformatics  
In this review, we focus on the use of computational modeling, bioinformatics and high-throughput experimental methods for discovery of drug combinations.  ...  Acknowledgements We thank the Tan lab members for useful comments on this manuscript. Funding This work is partly supported by the National Institutes of Health under Ruth L.  ...  ) were used to develop a statistical approach for predicting drug combinations (DCPred) Drug-drug interactions Drug-drug interaction network Applied five machine learning models to a data set of drug-drug  ... 
doi:10.1186/s13321-015-0055-9 pmid:25741385 pmcid:PMC4348553 fatcat:wu2dx5zzmjcdnkz3jiawehblnm

Applications of Support Vector Machines in Chemistry [chapter]

Ovidiu Ivanciuc
2007 Reviews in computational chemistry  
Equation [38] is a convex programming problem for any positive integer k, which for k ¼ 1 and k ¼ 2 is also a quadratic programming problem.  ...  Using 10 principal factors, LS-SVMR models were more predictive than was PLS, with q 2 ¼ 0:83 and R 2 ¼ 0:86.  ... 
doi:10.1002/9780470116449.ch6 fatcat:aumcn53nvfhhhocxvav32rhwzm
« Previous Showing results 1 — 15 out of 28 results