7,619 Hits in 9.4 sec

Exact and efficient top-K inference for multi-target prediction by querying separable linear relational models

Michiel Stock, Krzysztof Dembczyński, Bernard De Baets, Willem Waegeman
2016 Data mining and knowledge discovery  
Many complex multi-target prediction problems that concern large target spaces are characterised by a need for efficient prediction strategies that avoid the computation of predictions for all targets  ...  Examples of such problems emerge in several subfields of machine learning, such as collaborative filtering, multi-label classification, dyadic prediction and biological network inference.  ...  To this end we use a large multi-label classification dataset related to protein function.  ... 
doi:10.1007/s10618-016-0456-z fatcat:qvr2uryyx5gmzdpp3tntjlxnne

DeepTox: Toxicity prediction using deep learning

Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter
2017 Toxicology Letters  
Then it computes a large number of chemical descriptors that are used as input to machine learning methods.  ...  We found that Deep Learning excelled in toxicity prediction and outperformed many other computational approaches like naive Bayes, support vector machines, and random forests.  ...  Typically, the crossentropy is used as an error function for multi-class classification.  ... 
doi:10.1016/j.toxlet.2017.07.175 fatcat:rajiojv6fjeornjxgdjmf5e5iu

DeepTox: Toxicity Prediction using Deep Learning

Andreas Mayr, Günter Klambauer, Thomas Unterthiner, Sepp Hochreiter
2016 Frontiers in Environmental Science  
Then it computes a large number of chemical descriptors that are used as input to machine learning methods.  ...  We found that Deep Learning excelled in toxicity prediction and outperformed many other computational approaches like naive Bayes, support vector machines, and random forests.  ...  Typically, the crossentropy is used as an error function for multi-class classification.  ... 
doi:10.3389/fenvs.2015.00080 fatcat:f3uxqnexobf43jg5q2z6rn7pqq

Predictive Systems Toxicology [chapter]

Narsis A. Kiani, Ming-Mei Shang, Hector Zenil, Jesper Tegner
2018 Msphere  
These systems approaches employ advanced statistical analytical data processing complemented with machine learning techniques and use both pharmacokinetic and omics data.  ...  laid the foundation for in silico toxicity prediction [7].  ...  In a more recent effort, machine-learning approaches have been used for larger-scale predictions of drug-target interactions.  ... 
doi:10.1007/978-1-4939-7899-1_25 pmid:29934910 fatcat:67btyybpxrc7dgu2d74fav7inq

Microbial Forensics: Predicting Phenotypic Characteristics and Environmental Conditions from Large-Scale Gene Expression Profiles

Minseung Kim, Violeta Zorraquino, Ilias Tagkopoulos, Olga G. Troyanskaya
2015 PLoS Computational Biology  
Results show that gene expression is an excellent predictor of environmental structure, with multi-class ensemble models achieving balanced accuracy between 70.0% (±3.5%) to 98.3% (±2.3%) for the various  ...  This work demonstrates the degree at which genome-scale transcriptional information can be predictive of latent, heterogeneous and seemingly disparate phenotypic and environmental characteristics, with  ...  Acknowledgments We thank the Tagkopoulos lab for the helpful discussions. Author Contributions  ... 
doi:10.1371/journal.pcbi.1004127 pmid:25774498 pmcid:PMC4361189 fatcat:4ay45uxx6fgoja3t6bejkn4mka

Unsupervised machine learning in atomistic simulations, between predictions and understanding [article]

Michele Ceriotti
2019 arXiv   pre-print
Supervised machine-learning techniques, that explicitly attempt to predict the properties of a material given its structure, are less susceptible to such biases.  ...  of a coherent toolbox of data-driven approaches.  ...  learning schemes which also use the labels and make predictions on the relations between inputs and some target properties.  ... 
arXiv:1902.05158v2 fatcat:witrszp3brazlgnfa75ivdgqym

A Fast Machine Learning Workflow for Rapid Phenotype Prediction from Whole Shotgun Metagenomes

Anna Paola Carrieri, Will PM Rowe, Martyn Winn, Edward O. Pyzer-Knapp
time diagnostics and a potential for cloud applications.  ...  Current machine learning workflows that predict traits of host organisms from their commensal microbiome do not take into account the whole genetic material constituting the microbiome, instead basing  ...  Multi-class and binary classification In this paper, we focus on machine learning approaches for multi-class and binary classification of microbiome samples Figure 1 : ML workflow for phenotype prediction  ... 
doi:10.1609/aaai.v33i01.33019434 fatcat:za2xw6d5bvfw5ndhgi5vngyitq

Efficient iterative virtual screening with Apache Spark and conformal prediction

Laeeq Ahmed, Valentin Georgiev, Marco Capuccini, Salman Toor, Wesley Schaal, Erwin Laure, Ola Spjuth
2018 Journal of Cheminformatics  
Docking and scoring large libraries of ligands against target proteins forms the basis of structure-based virtual screening.  ...  Contribution: In this study we propose a strategy that is based on iteratively docking a set of ligands to form a training set, training a ligand-based model on this set, and predicting the remainder of  ...  HPC computations were performed on resources provided by SNIC through Uppsala Multidisciplinary Center for Advanced Computational Science (UPPMAX) [40] under Project b2015245.  ... 
doi:10.1186/s13321-018-0265-z pmid:29492726 pmcid:PMC5833896 fatcat:jk3vh6ha2rbsppvmuqjgrxjvuy

Towards Structured Prediction in Bioinformatics with Deep Learning [article]

Yu Li
2020 arXiv   pre-print
Using machine learning, especially deep learning, to facilitate biological research is a fascinating research direction.  ...  Due to the properties of those structured prediction problems, such as having problem-specific constraints and dependency within the labeling space, the straightforward application of existing deep learning  ...  We used a level-by-level prediction strategy, hierarchical transfer learning, and a novel multi-label loss function to incorporate the hierarchical labeling structure and the multi-class information into  ... 
arXiv:2008.11546v1 fatcat:5in2a642b5cj3lweuynl7sniaa

Learning to Make Predictions on Graphs with Autoencoders

Phi Vu Tran
2018 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA)  
We present a novel autoencoder architecture capable of learning a joint representation of both local graph structure and available node features for the multi-task learning of link prediction and node  ...  We provide a comprehensive empirical evaluation of our models on nine benchmark graph-structured datasets and demonstrate significant improvement over related methods for graph representation learning.  ...  Acknowledgment The author thanks Edward Raff and Jared Sylvester for insightful discussions, and gracious reviewers for constructive feedback on the paper.  ... 
doi:10.1109/dsaa.2018.00034 dblp:conf/dsaa/Tran18 fatcat:5esavcggqve27fk2szcyq5q3wq

Novel prediction methods for virtual drug screening [article]

Josip Mesarić
2022 arXiv   pre-print
As these methods are known to demand huge amounts of computational power to get accurate results, prediction models based on machine learning techniques became a popular solution requiring less computational  ...  One of key parts of the early drug discovery process has become virtual drug screening -- a method used to narrow down search for potential drugs by running computer simulations of drug-target interactions  ...  and compounds and finally feeding those vectors to machine learning models to train it for prediction of target interactions.  ... 
arXiv:2202.06635v1 fatcat:cab5pvnvw5httnuksmb4ke2piy

Retention Time Prediction Using Neural Networks Increases Identifications in Crosslinking Mass Spectrometry [article]

Sven H. Giese, Ludwig R Sinn, Fritz Wegner, Juri Rappsilber
2021 bioRxiv   pre-print
Our Siamese machine learning model xiRT achieved highly accurate RT predictions of crosslinked peptides in a multi-dimensional separation of crosslinked E. coli lysate.  ...  We also demonstrate the value of this approach for the more routine analysis of a crosslinked multiprotein complexes.  ...  For the RP prediction, a linear activation function was 181 used and mean squared error (MSE) as loss function. For the prediction of SCX and hSAX fractions we 182 followed a different approach.  ... 
doi:10.1101/2021.03.08.432999 fatcat:nc3dedhifzfohihvgy3aja5zai

Recent Applications of Deep Learning Methods on Evolution- and Contact-Based Protein Structure Prediction

Donghyuk Suh, Jai Woo Lee, Sun Choi, Yoonji Lee
2021 International Journal of Molecular Sciences  
We also look at the potential opportunities for deep learning methods to identify unknown protein structures and functions to be discovered and help guide drug–target interactions.  ...  The prediction of proteins' 3D structural components is now heavily dependent on machine learning techniques that interpret how protein sequences and their homology govern the inter-residue contacts and  ...  Deep learning a class of machine learning approach that uses artificial neural networks (ANNs) with many layers of nonlinear processing units for learning data representation.  ... 
doi:10.3390/ijms22116032 pmid:34199677 pmcid:PMC8199773 fatcat:7znk2khhhfgj7err5roqnygz6i

Specificity Enhancement in microRNA Target Prediction through Knowledge Discovery [chapter]

Yanju Zhang, Jeroen S. de Bruin, Fons J.
2010 Machine Learning  
Erno Vreugdenhil for discussing some biological implications of the results and Peter van de Putten for suggestions on the use of WEKA.  ...  ., 2004) was the first method which integrated powerful statistical models for large-scale target prediction.  ...  As machine learning methods become more popular, this database provides a valuable resource to train and test for machine learning based target prediction algorithms.  ... 
doi:10.5772/9140 fatcat:gedflwuorjdvtgrcmhgs2534lq

Neural Architecture Search for Joint Optimization of Predictive Power and Biological Knowledge [article]

Zijun Zhang, Linqi Zhou, Liangke Gou, Ying Nian Wu
2019 arXiv   pre-print
BioNAS provides a useful tool for domain experts to inject their prior belief into automated machine learning and therefore making deep learning easily accessible to practitioners.  ...  The introduction of knowledge dissimilarity functions in BioNAS enables the joint optimization of predictive power and biological knowledge through searching architectures in a model space.  ...  More concretely, for any given RNA sequence, we predict a list of multi-class binary label of whether there are protein binding sites corresponding to a list of proteins of interests.  ... 
arXiv:1909.00337v1 fatcat:j6h7iaudzzcpbfvyfkxu2oxvcu
« Previous Showing results 1 — 15 out of 7,619 results