Detection of m6A from direct RNA sequencing using a Multiple Instance Learning framework

RNA modifications such as m6A methylation form an additional layer of complexity in the transcriptome. Nanopore direct RNA sequencing captures this information in the raw current signal for each RNA molecule, enabling the detection of RNA modifications using supervised machine learning. However, experimental approaches provide only site-level training data, whereas the modification status for each single RNA molecule is missing. Here we present m6Anet, a neural network-based method that leverages the Multiple Instance Learning framework to specifically handle missing read-level modification labels in site-level training data. m6Anet outperforms existing computational methods, shows similar accuracy as experimental approaches, and generalises to different cell lines with almost identical accuracy. We demonstrate that m6Anet captures the underlying read-level stoichiometry that can be used to approximate differences in modification rates. m6Anet achieves this without retraining model parameters, enabling the transcriptome-wide identification and quantification of m6A from a single run of direct RNA sequencing.

Download Full-text

Lost in Space: Geolocation in Event Data

Political Science Research and Methods ◽

10.1017/psrm.2018.23 ◽

2018 ◽

Vol 7 (04) ◽

pp. 871-888 ◽

Cited By ~ 6

Author(s):

Sophie J. Lee ◽

Howard Liu ◽

Michael D. Ward

Keyword(s):

Learning Algorithm ◽

Text Processing ◽

Contextual Information ◽

Training Data ◽

Supervised Machine Learning ◽

Model Parameters ◽

Event Data ◽

Data Set ◽

N Gram ◽

Automated Text Processing

Improving geolocation accuracy in text data has long been a goal of automated text processing. We depart from the conventional method and introduce a two-stage supervised machine-learning algorithm that evaluates each location mention to be either correct or incorrect. We extract contextual information from texts, i.e., N-gram patterns for location words, mention frequency, and the context of sentences containing location words. We then estimate model parameters using a training data set and use this model to predict whether a location word in the test data set accurately represents the location of an event. We demonstrate these steps by constructing customized geolocation event data at the subnational level using news articles collected from around the world. The results show that the proposed algorithm outperforms existing geocoders even in a case added post hoc to test the generality of the developed algorithm.

Download Full-text

RNA modifications detection by comparative Nanopore direct RNA sequencing

Nature Communications ◽

10.1038/s41467-021-27393-3 ◽

2021 ◽

Vol 12 (1) ◽

Author(s):

Adrien Leger ◽

Paulo P. Amaral ◽

Luca Pandolfini ◽

Charlotte Capitanchik ◽

Federica Capraro ◽

...

Keyword(s):

Rna Sequencing ◽

High Throughput Sequencing ◽

Control Sample ◽

Analytical Framework ◽

Rna Modifications ◽

Rna Molecules ◽

Oxford Nanopore ◽

Experimental Approaches

AbstractRNA molecules undergo a vast array of chemical post-transcriptional modifications (PTMs) that can affect their structure and interaction properties. In recent years, a growing number of PTMs have been successfully mapped to the transcriptome using experimental approaches relying on high-throughput sequencing. Oxford Nanopore direct-RNA sequencing has been shown to be sensitive to RNA modifications. We developed and validated Nanocompore, a robust analytical framework that identifies modifications from these data. Our strategy compares an RNA sample of interest against a non-modified control sample, not requiring a training set and allowing the use of replicates. We show that Nanocompore can detect different RNA modifications with position accuracy in vitro, and we apply it to profile m6A in vivo in yeast and human RNAs, as well as in targeted non-coding RNAs. We confirm our results with orthogonal methods and provide novel insights on the co-occurrence of multiple modified residues on individual RNA molecules.

Download Full-text

Deep Model Poisoning Attack on Federated Learning

Future Internet ◽

10.3390/fi13030073 ◽

2021 ◽

Vol 13 (3) ◽

pp. 73

Author(s):

Xingchen Zhou ◽

Ming Xu ◽

Yiming Wu ◽

Ning Zheng

Keyword(s):

Deep Learning ◽

Numerical Experiments ◽

Distributed Learning ◽

Systematic Investigation ◽

Training Data ◽

Model Parameters ◽

Learning Framework ◽

Deep Model ◽

Shared Information ◽

Deep Learning Model

Federated learning is a novel distributed learning framework, which enables thousands of participants to collaboratively construct a deep learning model. In order to protect confidentiality of the training data, the shared information between server and participants are only limited to model parameters. However, this setting is vulnerable to model poisoning attack, since the participants have permission to modify the model parameters. In this paper, we perform systematic investigation for such threats in federated learning and propose a novel optimization-based model poisoning attack. Different from existing methods, we primarily focus on the effectiveness, persistence and stealth of attacks. Numerical experiments demonstrate that the proposed method can not only achieve high attack success rate, but it is also stealthy enough to bypass two existing defense methods.

Download Full-text

RNA modifications detection by comparative Nanopore direct RNA sequencing

10.1101/843136 ◽

2019 ◽

Cited By ~ 16

Author(s):

Adrien Leger ◽

Paulo P. Amaral ◽

Luca Pandolfini ◽

Charlotte Capitanchik ◽

Federica Capraro ◽

...

Keyword(s):

Rna Sequencing ◽

Single Molecule ◽

High Throughput Sequencing ◽

Control Sample ◽

Analytical Framework ◽

Rna Modifications ◽

Rna Molecules ◽

Naturally Occurring ◽

Oxford Nanopore ◽

Experimental Approaches

AbstractRNA molecules undergo a vast array of chemical post-transcriptional modifications (PTMs) that can affect their structure and interaction properties. To date, over 150 naturally occurring PTMs have been identified, however the overwhelming majority of their functions remain elusive. In recent years, a small number of PTMs have been successfully mapped to the transcriptome using experimental approaches relying on high-throughput sequencing. Oxford Nanopore direct-RNA sequencing (DRS) technology has been shown to be sensitive to RNA modifications. We developed and validated Nanocompore, a robust analytical framework to evaluate the presence of modifications in DRS data. To do so, we compare an RNA sample of interest against a non-modified control sample. Our strategy does not require a training set and allows the use of replicates to model biological variability. Here, we demonstrate the ability of Nanocompore to detect RNA modifications at single-molecule resolution in human polyA+ RNAs, as well as in targeted non-coding RNAs. Our results correlate well with orthogonal methods, confirm previous observations on the distribution of N6-methyladenosine sites and provide novel insights into the distribution of RNA modifications in the coding and non-coding transcriptomes. The latest version of Nanocompore can be obtained at https://github.com/tleonardi/nanocompore.

Download Full-text

SCOUR: a stepwise machine learning framework for predicting metabolite-dependent regulatory interactions

BMC Bioinformatics ◽

10.1186/s12859-021-04281-7 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Justin Y. Lee ◽

Britney Nguyen ◽

Carlos Orosco ◽

Mark P. Styczynski

Keyword(s):

Machine Learning ◽

Metabolic Networks ◽

Sampling Frequency ◽

Low Noise ◽

Training Data ◽

High Noise ◽

Regulatory Interactions ◽

Learning Framework ◽

Metabolic Systems ◽

Noise Data

Abstract Background The topology of metabolic networks is both well-studied and remarkably well-conserved across many species. The regulation of these networks, however, is much more poorly characterized, though it is known to be divergent across organisms—two characteristics that make it difficult to model metabolic networks accurately. While many computational methods have been built to unravel transcriptional regulation, there have been few approaches developed for systems-scale analysis and study of metabolic regulation. Here, we present a stepwise machine learning framework that applies established algorithms to identify regulatory interactions in metabolic systems based on metabolic data: stepwise classification of unknown regulation, or SCOUR. Results We evaluated our framework on both noiseless and noisy data, using several models of varying sizes and topologies to show that our approach is generalizable. We found that, when testing on data under the most realistic conditions (low sampling frequency and high noise), SCOUR could identify reaction fluxes controlled only by the concentration of a single metabolite (its primary substrate) with high accuracy. The positive predictive value (PPV) for identifying reactions controlled by the concentration of two metabolites ranged from 32 to 88% for noiseless data, 9.2 to 49% for either low sampling frequency/low noise or high sampling frequency/high noise data, and 6.6–27% for low sampling frequency/high noise data, with results typically sufficiently high for lab validation to be a practical endeavor. While the PPVs for reactions controlled by three metabolites were lower, they were still in most cases significantly better than random classification. Conclusions SCOUR uses a novel approach to synthetically generate the training data needed to identify regulators of reaction fluxes in a given metabolic system, enabling metabolomics and fluxomics data to be leveraged for regulatory structure inference. By identifying and triaging the most likely candidate regulatory interactions, SCOUR can drastically reduce the amount of time needed to identify and experimentally validate metabolic regulatory interactions. As high-throughput experimental methods for testing these interactions are further developed, SCOUR will provide critical impact in the development of predictive metabolic models in new organisms and pathways.

Download Full-text

MULFE: Multi-Label Learning via Label-Specific Feature Space Ensemble

ACM Transactions on Knowledge Discovery from Data ◽

10.1145/3451392 ◽

2021 ◽

Vol 16 (1) ◽

pp. 1-24

Author(s):

Yaojin Lin ◽

Qinghua Hu ◽

Jinghua Liu ◽

Xingquan Zhu ◽

Xindong Wu

Keyword(s):

Empirical Studies ◽

Feature Space ◽

Training Data ◽

Data Sets ◽

Learning Framework ◽

Feature Spaces ◽

Public Data ◽

Margin Distribution ◽

Label Correlations ◽

Label Correlation

In multi-label learning, label correlations commonly exist in the data. Such correlation not only provides useful information, but also imposes significant challenges for multi-label learning. Recently, label-specific feature embedding has been proposed to explore label-specific features from the training data, and uses feature highly customized to the multi-label set for learning. While such feature embedding methods have demonstrated good performance, the creation of the feature embedding space is only based on a single label, without considering label correlations in the data. In this article, we propose to combine multiple label-specific feature spaces, using label correlation, for multi-label learning. The proposed algorithm, mu lti- l abel-specific f eature space e nsemble (MULFE), takes consideration label-specific features, label correlation, and weighted ensemble principle to form a learning framework. By conducting clustering analysis on each label’s negative and positive instances, MULFE first creates features customized to each label. After that, MULFE utilizes the label correlation to optimize the margin distribution of the base classifiers which are induced by the related label-specific feature spaces. By combining multiple label-specific features, label correlation based weighting, and ensemble learning, MULFE achieves maximum margin multi-label classification goal through the underlying optimization framework. Empirical studies on 10 public data sets manifest the effectiveness of MULFE.

Download Full-text

A Reinforcement Learning Framework for Spiking Networks with Dynamic Synapses

Computational Intelligence and Neuroscience ◽

10.1155/2011/869348 ◽

2011 ◽

Vol 2011 ◽

pp. 1-12 ◽

Cited By ~ 3

Author(s):

Karim El-Laithy ◽

Martin Bogdan

Keyword(s):

Reinforcement Learning ◽

Spike Timing ◽

Neural Representation ◽

Model Parameters ◽

Learning Framework ◽

Reference Target ◽

Wide Range ◽

Spiking Network ◽

Dynamic Synapses ◽

Exclusive Or

An integration of both the Hebbian-based and reinforcement learning (RL) rules is presented for dynamic synapses. The proposed framework permits the Hebbian rule to update the hidden synaptic model parameters regulating the synaptic response rather than the synaptic weights. This is performed using both the value and the sign of the temporal difference in the reward signal after each trial. Applying this framework, a spiking network with spike-timing-dependent synapses is tested to learn the exclusive-OR computation on a temporally coded basis. Reward values are calculated with the distance between the output spike train of the network and a reference target one. Results show that the network is able to capture the required dynamics and that the proposed framework can reveal indeed an integrated version of Hebbian and RL. The proposed framework is tractable and less computationally expensive. The framework is applicable to a wide class of synaptic models and is not restricted to the used neural representation. This generality, along with the reported results, supports adopting the introduced approach to benefit from the biologically plausible synaptic models in a wide range of intuitive signal processing.

Download Full-text

Effects of Training Set Size on Supervised Machine-Learning Land-Cover Classification of Large-Area High-Resolution Remotely Sensed Data

Remote Sensing ◽

10.3390/rs13030368 ◽

2021 ◽

Vol 13 (3) ◽

pp. 368

Author(s):

Christopher A. Ramezan ◽

Timothy A. Warner ◽

Aaron E. Maxwell ◽

Bradley S. Price

Keyword(s):

Machine Learning ◽

Sample Size ◽

Remotely Sensed ◽

Training Data ◽

Supervised Machine Learning ◽

Sample Sizes ◽

Remotely Sensed Data ◽

Large Area ◽

Training Set ◽

Set Size

The size of the training data set is a major determinant of classification accuracy. Nevertheless, the collection of a large training data set for supervised classifiers can be a challenge, especially for studies covering a large area, which may be typical of many real-world applied projects. This work investigates how variations in training set size, ranging from a large sample size (n = 10,000) to a very small sample size (n = 40), affect the performance of six supervised machine-learning algorithms applied to classify large-area high-spatial-resolution (HR) (1–5 m) remotely sensed data within the context of a geographic object-based image analysis (GEOBIA) approach. GEOBIA, in which adjacent similar pixels are grouped into image-objects that form the unit of the classification, offers the potential benefit of allowing multiple additional variables, such as measures of object geometry and texture, thus increasing the dimensionality of the classification input data. The six supervised machine-learning algorithms are support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), single-layer perceptron neural networks (NEU), learning vector quantization (LVQ), and gradient-boosted trees (GBM). RF, the algorithm with the highest overall accuracy, was notable for its negligible decrease in overall accuracy, 1.0%, when training sample size decreased from 10,000 to 315 samples. GBM provided similar overall accuracy to RF; however, the algorithm was very expensive in terms of training time and computational resources, especially with large training sets. In contrast to RF and GBM, NEU, and SVM were particularly sensitive to decreasing sample size, with NEU classifications generally producing overall accuracies that were on average slightly higher than SVM classifications for larger sample sizes, but lower than SVM for the smallest sample sizes. NEU however required a longer processing time. The k-NN classifier saw less of a drop in overall accuracy than NEU and SVM as training set size decreased; however, the overall accuracies of k-NN were typically less than RF, NEU, and SVM classifiers. LVQ generally had the lowest overall accuracy of all six methods, but was relatively insensitive to sample size, down to the smallest sample sizes. Overall, due to its relatively high accuracy with small training sample sets, and minimal variations in overall accuracy between very large and small sample sets, as well as relatively short processing time, RF was a good classifier for large-area land-cover classifications of HR remotely sensed data, especially when training data are scarce. However, as performance of different supervised classifiers varies in response to training set size, investigating multiple classification algorithms is recommended to achieve optimal accuracy for a project.

Download Full-text

Semi-Supervised Aspect-Based Sentiment Analysis for Case-Related Microblog Reviews Using Case Knowledge Graph Embedding

International Journal of Asian Language Processing ◽

10.1142/s2717554520500125 ◽

2021 ◽

pp. 2050012

Author(s):

Peilian Zhao ◽

Cunli Mao ◽

Zhengtao Yu

Keyword(s):

Sentiment Analysis ◽

Domain Knowledge ◽

Opinion Mining ◽

Data Augmentation ◽

Training Data ◽

Knowledge Graph ◽

Fine Grained ◽

Learning Framework ◽

Proposed Model ◽

Real World Applications

Aspect-Based Sentiment Analysis (ABSA), a fine-grained task of opinion mining, which aims to extract sentiment of specific target from text, is an important task in many real-world applications, especially in the legal field. Therefore, in this paper, we study the problem of limitation of labeled training data required and ignorance of in-domain knowledge representation for End-to-End Aspect-Based Sentiment Analysis (E2E-ABSA) in legal field. We proposed a new method under deep learning framework, named Semi-ETEKGs, which applied E2E framework using knowledge graph (KG) embedding in legal field after data augmentation (DA). Specifically, we pre-trained the BERT embedding and in-domain KG embedding for unlabeled data and labeled data with case elements after DA, and then we put two embeddings into the E2E framework to classify the polarity of target-entity. Finally, we built a case-related dataset based on a popular benchmark for ABSA to prove the efficiency of Semi-ETEKGs, and experiments on case-related dataset from microblog comments show that our proposed model outperforms the other compared methods significantly.

Download Full-text

DeepIsoFun: a deep domain adaptation approach to predict isoform functions

Bioinformatics ◽

10.1093/bioinformatics/bty1017 ◽

2018 ◽

Vol 35 (15) ◽

pp. 2535-2544 ◽

Cited By ~ 4

Author(s):

Dipan Shaw ◽

Hao Chen ◽

Tao Jiang

Keyword(s):

Network Architecture ◽

Domain Adaptation ◽

Multiple Instance Learning ◽

Training Data ◽

Supplementary Information ◽

Operating Characteristics ◽

Neural Network Architecture ◽

Receiver Operating Characteristics Curve ◽

Gene Functions ◽

Better Than

AbstractMotivationIsoforms are mRNAs produced from the same gene locus by alternative splicing and may have different functions. Although gene functions have been studied extensively, little is known about the specific functions of isoforms. Recently, some computational approaches based on multiple instance learning have been proposed to predict isoform functions from annotated gene functions and expression data, but their performance is far from being desirable primarily due to the lack of labeled training data. To improve the performance on this problem, we propose a novel deep learning method, DeepIsoFun, that combines multiple instance learning with domain adaptation. The latter technique helps to transfer the knowledge of gene functions to the prediction of isoform functions and provides additional labeled training data. Our model is trained on a deep neural network architecture so that it can adapt to different expression distributions associated with different gene ontology terms.ResultsWe evaluated the performance of DeepIsoFun on three expression datasets of human and mouse collected from SRA studies at different times. On each dataset, DeepIsoFun performed significantly better than the existing methods. In terms of area under the receiver operating characteristics curve, our method acquired at least 26% improvement and in terms of area under the precision-recall curve, it acquired at least 10% improvement over the state-of-the-art methods. In addition, we also study the divergence of the functions predicted by our method for isoforms from the same gene and the overall correlation between expression similarity and the similarity of predicted functions.Availability and implementationhttps://github.com/dls03/DeepIsoFun/Supplementary informationSupplementary data are available at Bioinformatics online.

Download Full-text