Dataset Information

Prioritizing bona fide bacterial small RNAs with machine learning classifiers.

ABSTRACT: Bacterial small (sRNAs) are involved in the control of several cellular processes. Hundreds of putative sRNAs have been identified in many bacterial species through RNA sequencing. The existence of putative sRNAs is usually validated by Northern blot analysis. However, the large amount of novel putative sRNAs reported in the literature makes it impractical to validate each of them in the wet lab. In this work, we applied five machine learning approaches to construct twenty models to discriminate bona fide sRNAs from random genomic sequences in five bacterial species. Sequences were represented using seven features including free energy of their predicted secondary structure, their distances to the closest predicted promoter site and Rho-independent terminator, and their distance to the closest open reading frames (ORFs). To automatically calculate these features, we developed an sRNA Characterization Pipeline (sRNACharP). All seven features used in the classification task contributed positively to the performance of the predictive models. The best performing model obtained a median precision of 100% at 10% recall and of 64% at 40% recall across all five bacterial species, and it outperformed previous published approaches on two benchmark datasets in terms of precision and recall. Our results indicate that even though there is limited sRNA sequence conservation across different bacterial species, there are intrinsic features in the genomic context of sRNAs that are conserved across taxa. We show that these features are utilized by machine learning approaches to learn a species-independent model to prioritize bona fide bacterial sRNAs.

SUBMITTER: Eppenhof EJJ

PROVIDER: S-EPMC6348098 | biostudies-literature | 2019

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Prioritizing bona fide bacterial small RNAs with machine learning classifiers.

Eppenhof Erik J J EJJ Peña-Castillo Lourdes L

PeerJ 20190124

Bacterial small (sRNAs) are involved in the control of several cellular processes. Hundreds of putative sRNAs have been identified in many bacterial species through RNA sequencing. The existence of putative sRNAs is usually validated by Northern blot analysis. However, the large amount of novel putative sRNAs reported in the literature makes it impractical to validate each of them in the wet lab. In this work, we applied five machine learning approaches to construct twenty models to discriminate ...[more]

PMID: 30697489

Similar Datasets

Project description:UnlabelledMammalian prions are PrP proteins with altered structures causing transmissible fatal neurodegenerative diseases. They are self-perpetuating through formation of beta-sheet-rich assemblies that seed conformational change of cellular PrP. Pathological PrP usually forms an insoluble protease-resistant core exhibiting beta-sheet structures but no more alpha-helical content, loosing the three alpha-helices contained in the correctly folded PrP. The lack of a high-resolution prion structure makes it difficult to understand the dynamics of conversion and to identify elements of the protein involved in this process. To determine whether completeness of residues within the protease-resistant domain is required for prions, we performed serial deletions in the helix H2 C terminus of ovine PrP, since this region has previously shown some tolerance to sequence changes without preventing prion replication. Deletions of either four or five residues essentially preserved the overall PrP structure and mutant PrP expressed in RK13 cells were efficiently converted into bona fide prions upon challenge by three different prion strains. Remarkably, deletions in PrP facilitated the replication of two strains that otherwise do not replicate in this cellular context. Prions with internal deletion were self-propagating and de novo infectious for naive homologous and wild-type PrP-expressing cells. Moreover, they caused transmissible spongiform encephalopathies in mice, with similar biochemical signatures and neuropathologies other than the original strains. Prion convertibility and transfer of strain-specific information are thus preserved despite shortening of an alpha-helix in PrP and removal of residues within prions. These findings provide new insights into sequence/structure/infectivity relationship for prions.ImportancePrions are misfolded PrP proteins that convert the normal protein into a replicate of their own abnormal form. They are responsible for invariably fatal neurodegenerative disorders. Other aggregation-prone proteins appear to have a prion-like mode of expansion in brains, such as in Alzheimer's or Parkinson's diseases. To date, the resolution of prion structure remains elusive. Thus, to genetically define the landscape of regions critical for prion conversion, we tested the effect of short deletions. We found that, surprisingly, removal of a portion of PrP, the C terminus of alpha-helix H2, did not hamper prion formation but generated infectious agents with an internal deletion that showed characteristics essentially similar to those of original infecting strains. Thus, we demonstrate that completeness of the residues inside prions is not necessary for maintaining infectivity and the main strain-specific information, while reporting one of the few if not the only bona fide prions with an internal deletion.

Project description:BackgroundTwitter presents a valuable and relevant social media platform to study the prevalence of information and sentiment on vaping that may be useful for public health surveillance. Machine learning classifiers that identify vaping-relevant tweets and characterize sentiments in them can underpin a Twitter-based vaping surveillance system. Compared with traditional machine learning classifiers that are reliant on annotations that are expensive to obtain, deep learning classifiers offer the advantage of requiring fewer annotated tweets by leveraging the large numbers of readily available unannotated tweets.ObjectiveThis study aims to derive and evaluate traditional and deep learning classifiers that can identify tweets relevant to vaping, tweets of a commercial nature, and tweets with provape sentiments.MethodsWe continuously collected tweets that matched vaping-related keywords over 2 months from August 2018 to October 2018. From this data set of tweets, a set of 4000 tweets was selected, and each tweet was manually annotated for relevance (vape relevant or not), commercial nature (commercial or not), and sentiment (provape or not). Using the annotated data, we derived traditional classifiers that included logistic regression, random forest, linear support vector machine, and multinomial naive Bayes. In addition, using the annotated data set and a larger unannotated data set of tweets, we derived deep learning classifiers that included a convolutional neural network (CNN), long short-term memory (LSTM) network, LSTM-CNN network, and bidirectional LSTM (BiLSTM) network. The unannotated tweet data were used to derive word vectors that deep learning classifiers can leverage to improve performance.ResultsLSTM-CNN performed the best with the highest area under the receiver operating characteristic curve (AUC) of 0.96 (95% CI 0.93-0.98) for relevance, all deep learning classifiers including LSTM-CNN performed better than the traditional classifiers with an AUC of 0.99 (95% CI 0.98-0.99) for distinguishing commercial from noncommercial tweets, and BiLSTM performed the best with an AUC of 0.83 (95% CI 0.78-0.89) for provape sentiment. Overall, LSTM-CNN performed the best across all 3 classification tasks.ConclusionsWe derived and evaluated traditional machine learning and deep learning classifiers to identify vaping-related relevant, commercial, and provape tweets. Overall, deep learning classifiers such as LSTM-CNN had superior performance and had the added advantage of requiring no preprocessing. The performance of these classifiers supports the development of a vaping surveillance system.

Dataset Information

Prioritizing bona fide bacterial small RNAs with machine learning classifiers.

Publications

Prioritizing bona fide bacterial small RNAs with machine learning classifiers.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets