sincFold: end-to-end learning of short- and long-range interactions in RNA secondary structure.

MOTIVATION: Coding and noncoding RNA molecules participate in many important biological processes. Noncoding RNAs fold into well-defined secondary structures to exert their functions. However, the computational prediction of the secondary structure from a raw RNA sequence is a long-standing unsolved problem, which after decades of almost unchanged performance has now re-emerged due to deep learning. Traditional RNA secondary structure prediction algorithms have been mostly based on thermodynamic models and dynamic programming for free energy minimization. More recently deep learning methods have shown competitive performance compared with the classical ones, but there is still a wide margin for improvement. RESULTS: In this work we present sincFold, an end-to-end deep learning approach, that predicts the nucleotides contact matrix using only the RNA sequence as input. The model is based on 1D and 2D residual neural networks that can learn short- and long-range interaction patterns. We show that structures can be accurately predicted with minimal physical assumptions. Extensive experiments were conducted on several benchmark datasets, considering sequence homology and cross-family validation. sincFold was compared with classical methods and recent deep learning models, showing that it can outperform the state-of-the-art methods.

PhDSeeker: Pheromone-Directed Seeker for metabolic pathways.

Manually finding relationship networks among compounds can be a hard and time-consuming task. However, this process is fundamental when looking for a metabolic pathway that explains how multiple compounds are related, to identify relevant pathways in organisms, filling gaps on metabolic networks, or when new mechanisms for the synthesis of important compounds are sought. Here, we present PhDSeeker, a new tool for the automatic search of metabolic pathways. This tool is able to relate simultaneously several compounds. Furthermore, its flexibility allows it to be easily configured for addressing a wide range of situations. Solutions found are provided not only in plain text but also as interactive representations that can be analyzed in a web browser. Source code is available at https://github.com/sinc-lab/phdseeker. A web service is also available at https://sinc.unl.edu.ar/web-demo/phds/. Several fully documented study cases, including their settings and solutions files, are also provided as Supplementary Material.

Predicting novel microRNA: a comprehensive comparison of machine learning approaches.

MOTIVATION: The importance of microRNAs (miRNAs) is widely recognized in the community nowadays because these short segments of RNA can play several roles in almost all biological processes. The computational prediction of novel miRNAs involves training a classifier for identifying sequences having the highest chance of being precursors of miRNAs (pre-miRNAs). The big issue with this task is that well-known pre-miRNAs are usually few in comparison with the hundreds of thousands of candidate sequences in a genome, which results in high class imbalance. This imbalance has a strong influence on most standard classifiers, and if not properly addressed in the model and the experiments, not only performance reported can be completely unrealistic but also the classifier will not be able to work properly for pre-miRNA prediction. Besides, another important issue is that for most of the machine learning (ML) approaches already used (supervised methods), it is necessary to have both positive and negative examples. The selection of positive examples is straightforward (well-known pre-miRNAs). However, it is difficult to build a representative set of negative examples because they should be sequences with hairpin structure that do not contain a pre-miRNA. RESULTS: This review provides a comprehensive study and comparative assessment of methods from these two ML approaches for dealing with the prediction of novel pre-miRNAs: supervised and unsupervised training. We present and analyze the ML proposals that have appeared during the past 10 years in literature. They have been compared in several prediction tasks involving two model genomes and increasing imbalance levels. This work provides a review of existing ML approaches for pre-miRNA prediction and fair comparisons of the classifiers with same features and data sets, instead of just a revision of published software tools. The results and the discussion can help the community to select the most adequate bioinformatics approach according to the prediction task at hand. The comparative results obtained suggest that from low to mid-imbalance levels between classes, supervised methods can be the best. However, at very high imbalance levels, closer to real case scenarios, models including unsupervised and deep learning can provide better performance.

Metabolic pathways synthesis based on ant colony optimization.

One of the current challenges in bioinformatics is to discover new ways to transform a set of compounds into specific products. The usual approach is finding the reactions to synthesize a particular product, from a given substrate, by means of classical searching algorithms. However, they have three main limitations: difficulty in handling large amounts of reactions and compounds; absence of a step that verifies the availability of substrates; and inability to find branched pathways. We present here a novel bio-inspired algorithm for synthesizing linear and branched metabolic pathways. It allows relating several compounds simultaneously, ensuring the availability of substrates for every reaction in the solution. Comparisons with classical searching algorithms and other recent metaheuristic approaches show clear advantages of this proposal, fully recovering well-known pathways. Furthermore, solutions found can be analyzed in a simple way through graphical representations on the web.

Evolutionary algorithm for metabolic pathways synthesis.

Metabolic pathway building is an active field of research, necessary to understand and manipulate the metabolism of organisms. There are different approaches, mainly based on classical search methods, to find linear sequences of reactions linking two compounds. However, an important limitation of these methods is the exponential increase of search trees when a large number of compounds and reactions is considered. Besides, such models do not take into account all substrates for each reaction during the search, leading to solutions that lack biological feasibility in many cases. This work proposes a new evolutionary algorithm that allows searching not only linear, but also branched metabolic pathways, formed by feasible reactions that relate multiple compounds simultaneously. Tests performed using several sets of reactions show that this algorithm is able to find feasible linear and branched metabolic pathways.

EvoMS: An evolutionary tool to find de novo metabolic pathways.

The evolutionary metabolic synthesizer (EvoMS) is an evolutionary tool capable of finding novel metabolic pathways linking several compounds through feasible reactions. It allows system biologists to explore different alternatives for relating specific metabolites, offering the possibility of indicating the initial compound or allowing the algorithm to automatically select it. Searching process can be followed graphically through several plots of the evolutionary process. Metabolic pathways found are displayed in a web browser as directed graphs. In all cases, solutions are networks of reactions that produce linear or branched metabolic pathways which are feasible from the specified set of available compounds. Source code of EvoMS is available at http://sourceforge.net/projects/sourcesinc/files/evoms/. Subsets of reactions are provided, as well as four examples for searching metabolic pathways among several compounds. Available as a web service at http://fich.unl.edu.ar/sinc/web-demo/evoms/.

An evolutionary approach for searching metabolic pathways.

Searching metabolic pathways that relate two compounds is a common task in bioinformatics. This is of particular interest when trying, for example, to discover metabolic relations among compounds clustered with a data mining technique. Search strategies find sequences to relate two or more states (compounds) using an appropriate set of transitions (reactions). Evolutionary algorithms carry out the search guided by a fitness function and explore multiple candidate solutions using stochastic operators. In this work we propose an evolutionary algorithm for searching metabolic pathways between two compounds. The operators and fitness function employed are described and the effect of mutation rate is studied. Performance of this algorithm is compared with two classical search strategies. Source code and dataset are available at http://sourceforge.net/projects/sourcesinc/files/eamp/