Filters








3,108 Hits in 8.8 sec

Generating Explainable and Effective Data Descriptors Using Relational Learning: Application to Cancer Biology [chapter]

Oghenejokpeme I. Orhobor, Joseph French, Larisa N. Soldatova, Ross D. King
2020 Lecture Notes in Computer Science  
Here we demonstrate the use of relational learning to generate new data descriptors in such semantically complex background knowledge.  ...  The key to success in machine learning is the use of effective data representations.  ...  A more general approach to encoding known structure in data is to use logic programs [21] to represent the data -relational learning (RL) [24] .  ... 
doi:10.1007/978-3-030-61527-7_25 fatcat:57l4nemeqrdbrc6av7fl2pdlxq

Machine learning for predicting lifespan-extending chemical compounds

Diogo G. Barardo, Danielle Newby, Daniel Thornton, Taravat Ghafourian, João Pedro de Magalhães, Alex A. Freitas
2017 Aging  
The top 20 most important GO terms include those related to mitochondrial processes, to enzymatic and immunological processes, and terms related to metabolic and transport processes.  ...  In this work we analyse data from the DrugAge database, which contains chemical compounds and their effect on the lifespan of model organisms.  ...  ACKNOWLEDGEMENTS DN would like to thank the Medway School of Pharmacy, Universities of Kent and Greenwich, for the use of software to calculate molecular descriptors.  ... 
doi:10.18632/aging.101264 pmid:28783714 pmcid:PMC5559175 fatcat:bqnqbtoltjexxhusoqpxfd7al4

Machine learning approaches for drug combination therapies

Betül Güvenç Paltun, Samuel Kaski, Hiroshi Mamitsuka
2021 Briefings in Bioinformatics  
Therefore, building computational approaches, particularly machine learning methods, could provide an effective strategy to overcome drug resistance and improve therapeutic efficacy.  ...  Drug combination therapy is a promising strategy to treat complex diseases such as cancer and infectious diseases.  ...  Systems biology approaches for advancing the discovery of effective drug combinations [3] Modeling of compound combination effects and applications to efficacy and toxicity: state-of-the-art, challenges  ... 
doi:10.1093/bib/bbab293 pmid:34368832 pmcid:PMC8574999 fatcat:lam5d6lmonfinmqs32umlgzc3m

Machine learning methods in chemoinformatics

John B. O. Mitchell
2014 Wiley Interdisciplinary Reviews. Computational Molecular Science  
This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive.  ...  Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion.  ...  It is not sufficient simply to fit known data, a useful model must be able to generalize to unknown data, and thus must be validated. 99 The traditional way of doing this is to have the total dataset  ... 
doi:10.1002/wcms.1183 pmid:25285160 pmcid:PMC4180928 fatcat:rt6652htybbodod7va3t4vrvh4

Radiomics at a Glance: A Few Lessons Learned from Learning Approaches

Enrico Capobianco, Jun Deng
2020 Cancers  
Various types of hybrid learning can be considered when building complex integrative approaches aimed to deliver gains in accuracy for both classification and prediction tasks.  ...  The advent of radiomics has assigned a central role to quantitative data analytics targeting medical image features algorithmically extracted from large volumes of images.  ...  The authors want to thank three anonymous reviewers for questions and comments that led to an improved final paper. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/cancers12092453 pmid:32872466 fatcat:qgdgcwzfmnakhpnfdm3pdub22a

A review on Machine Learning approaches and trends in drug discovery

Paula Carracedo-Reboredo, Jose Linares-Blanco, Nereida Rodriguez-Fernandez, Francisco Cedron, Francisco J. Novoa, Adrian Carballal, Victor Maojo, Alejandro Pazos, Carlos Fernandez-Lozano
2021 Computational and Structural Biotechnology Journal  
This review will focus mainly on the methods used to model the molecular data, as well as the biological problems addressed and the Machine Learning algorithms used for drug discovery in recent years.  ...  With the objectives set by the Precision Medicine initiative and the new challenges generated, it is necessary to establish robust, standard and reproducible computational methodologies to achieve the  ...  A promising approach to drug repositioning is to take advantage of machine learning algorithms to learn patterns in available drug-related biological data and link them to specific diseases to be treated  ... 
doi:10.1016/j.csbj.2021.08.011 pmid:34471498 pmcid:PMC8387781 fatcat:s5pwhypudfehbotkrofqgbq33m

Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification

Ahsan Habib Polash, Takumi Nakano, Shunichi Takeda, J.B. Brown
2019 Molecules  
prior chemogenomic active learning studies despite the increased difficulty from chemical biology experimental settings used here.  ...  The active learning virtual screening method has demonstrated the ability to efficiently converge on predictive models with reduced datasets, though its applicability domain to probe identification has  ...  Acknowledgments: J.B.B. and S.T. wish to express thanks to Jurgen Bajorath of the University of Bonn for related discussions.  ... 
doi:10.3390/molecules24152716 pmid:31357419 pmcid:PMC6696588 fatcat:amhkvm4wwzekhkdyipn5naeat4

The use of data mining and machine learning in nanomedicine: a survey

Andrea Dimitri, Maurizio Talamo
2018 Frontiers in Nanoscience and Nanotechnology  
Quantitative methods based on data mining and machine learning techniques have to strengthen this new branch of medicine.  ...  In this paper we analyze applications of supervised and unsupervised learning technique to better understand hot issues in nanomedicine regarding nanoparticles, molecules and cells behaviours and relationships  ...  Next step is to understand the effective clustering profile and use it to learn. In pattern recognition, the k-nearest neighbours algorithm (k-NN) is a non-parametric method used for classification.  ... 
doi:10.15761/fnn.1000s1004 fatcat:pprdkv2b3fhcdg2cdww3eflsam

Active learning for computational chemogenomics

Daniel Reker, Petra Schneider, Gisbert Schneider, JB Brown
2017 Future Medicinal Chemistry  
In another application, deorphanization of natural products used in cancer therapy [90, 91] can provide the starting CPIs to initiate an actively learned chemogenomic model which generates testable hypotheses  ...  In this article, random forests are employed to evaluate subsets of the compound and protein descriptors, and to identify statistical patterns (decisions) that explain strong bioactivity or lack of bioactivity  ... 
doi:10.4155/fmc-2016-0197 pmid:28263088 fatcat:pnzwd3jfsjcu3gpnnxmidq7tge

Predicting tumor cell line response to drug pairs with deep learning

Fangfang Xia, Maulik Shukla, Thomas Brettin, Cristina Garcia-Cardona, Judith Cohn, Jonathan E. Allen, Sergei Maslov, Susan L. Holbeck, James H. Doroshow, Yvonne A. Evrard, Eric A. Stahlberg, Rick L. Stevens
2018 BMC Bioinformatics  
Our feature analysis indicates screening data involving more cell lines are needed for the models to make better use of molecular features.  ...  To further demonstrate value in detecting anticancer therapy, we rank the drug pairs for each cell line based on model predicted combination effect and recover 80% of the top pairs with enhanced activity  ...  Jason Gans for advice on proteome data and helpful comments on the manuscript. Funding This work has been supported in part by the Joint Design of Advanced 1  ... 
doi:10.1186/s12859-018-2509-3 fatcat:inq24w5lq5er7g4hlxd5o7njru

Learning Relational Descriptions of Differentially Expressed Gene Groups

I. Trajkovski, F. Zelezny, N. Lavrac, J. Tolar
2008 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
We believe that the presented approach will significantly contribute to the application of relational machine learning to gene expression analysis, given the expected increase in both the quality and quantity  ...  This paper presents a method that uses gene ontologies, together with the paradigm of relational subgroup discovery, to find compactly described groups of genes differentially expressed in specific cancers  ...  Another recent paper [10] also uses relational logic for learning from genomic, proteomic and related data sources, including gene ontologies.  ... 
doi:10.1109/tsmcc.2007.906059 fatcat:tpydbrqgqjdudduatpsotov2cm

Multiparameter Persistence Image for Topological Machine Learning

Mathieu Carrière, Andrew J. Blumberg
2020 Neural Information Processing Systems  
In the last decade, there has been increasing interest in topological data analysis, a new methodology for using geometric structures in data for inference and learning.  ...  However, in many applications there are several different parameters one might wish to vary: for example, scale and density.  ...  The authors would like to thank Mike Lesnick for helpful discussion of the algorithm and in particular the issue of Vineyard stability.  ... 
dblp:conf/nips/CarriereB20 fatcat:sq4dsfavuzdupm3lklhbncsqfa

APPLICATIONS OF DEEP LEARNING TO IMPROVE THE QUALITY OF HEALTHCARE OUTCOMES

Abdulrhman Samman Al-Asmari
2022 International Journal for Quality Research  
The aim of this paper is only to provide a systematic review of important research undertaken thus far in Deep Learning (DL) applications in healthcare and biomedicine.  ...  The primary implication of this research for health practitioners is that there is a plethora of substantial research that is currently available and accessible regarding the applications of DL to cancer  ...  Cancer A specific case of cancer prediction using DL was reported by . Gene expression can be the basis of efficient cancer prediction leading to precise and effective treatment decisions.  ... 
doi:10.24874/ijqr16.01-05 fatcat:36wdbarv7jebphq7wv57pxwrpq

Improvement of Heterogeneous Transfer Learning Efficiency by Using Hebbian Learning Principle

Arjun Magotra, Juntae Kim
2020 Applied Sciences  
In this article, we propose a way of improving transfer learning efficiency, in case of a heterogeneous source and target, by using the Hebbian learning principle, called Hebbian transfer learning (HTL  ...  We apply the Hebbian principle as synaptic plasticity in transfer learning for classification of images using a heterogeneous source-target dataset, and compare results with the standard transfer learning  ...  These data plots are very significant and helps to easily understand the effectiveness of plasticity influenced HTL algorithm.  ... 
doi:10.3390/app10165631 fatcat:76hkgddlpbgk7jctrwai44vzvq

Machine Learning for Drug-Target Interaction Prediction

Ruolan Chen, Xiangrong Liu, Shuting Jin, Jiawei Lin, Juan Liu
2018 Molecules  
In this review, our goal is to focus on machine learning approaches and provide a comprehensive overview. First, we summarize a brief list of databases frequently used in drug discovery.  ...  This article may provide a reference and tutorial insights on machine learning-based DTI prediction for future researchers.  ...  Acknowledgments: We would like to thank all authors of the cited references. Conflicts of Interest: The authors declare no conflicts of interest.  ... 
doi:10.3390/molecules23092208 pmid:30200333 pmcid:PMC6225477 fatcat:gcijck47irhqvlttntb43r63fu
« Previous Showing results 1 — 15 out of 3,108 results