Reduction strategies for hierarchical multi-label classification in protein function prediction

SHN: rock image classification and feature visualization using multiple granularity spatial disorder hierarchical residual network

The automated classification of rock images is of paramount importance in geological analysis, as it serves as the foundational criterion for the categorization of rock lithology. Despite recent advancements in leveraging deep learning technologies to enhance the efficiency and precision of image classification, a crucial aspect has been overlooked: these methods face a performance bottleneck when attempting to apply it directly to rock classification methods. To address this limitation, we propose a multiple granularity Spatial disorder Hierarchical residual Network (SHN). This approach involves learning from objects annotated at different levels, thereby facilitating the transfer of hierarchical knowledge across levels. By enabling lower-level classes to inherit pertinent attributes from higher-level superclasses, our method aims to capture the intricate hierarchical relationships among different rock types. Especially, we introduce a multi-granularity spatial disorder module to aid neural networks in discerning discriminative details across various scales. This module enables processed images to exhibit region independence, compelling the network to adeptly identify discriminative local regions at diverse granularity levels and extract pertinent features. Furthermore, in light of the absence of a comprehensive rock dataset, this study amassed 4,227 rock images of diverse compositions from various places, culminating in the creation of a robust rock dataset for classification. Rigorous experimentation on this dataset yielded highly promising results, demonstrating the effectiveness of our proposed method in addressing the challenges of rock image classification.

A Novel Piano Arrangement Timbre Intelligent Recognition System Using Multilabel Classification Technology and KNN Algorithm

In this paper, melody and harmony are regarded as the task of machine learning, and a piano arranger timbre recognition system based on AI (Artificial Intelligence) is constructed by training a series of samples. The short-time Fourier transform spectrum analysis method is used to extract the piano timbre characteristic matrix, and the electronic synthesis of timbre recognition is improved by extracting the envelope function. Using the traditional multilabel classification method and KNN (K-nearest neighbor) algorithm, a combined algorithm of these two algorithms is proposed. The experimental results show that the detection rate increases from 61.3% to 70.2% after using the combined classification algorithm. The correct rate also increased from 40.3% to 48.9%, and the detection rate increased to 74.6% when the K value was set to 6. The experimental results show that, compared with the traditional classification algorithm, this algorithm has a certain improvement in recognition rate. Using this system to recognize the timbre of piano arrangement has a high recognition accuracy, which is worthy of further popularization and application.

Evaluating hierarchical machine learning approaches to classify biological databases

The rate of biological data generation has increased dramatically in recent years, which has driven the importance of databases as a resource to guide innovation and the generation of biological insights. Given the complexity and scale of these databases, automatic data classification is often required. Biological data sets are often hierarchical in nature, with varying degrees of complexity, imposing different challenges to train, test and validate accurate and generalizable classification models. While some approaches to classify hierarchical data have been proposed, no guidelines regarding their utility, applicability and limitations have been explored or implemented. These include ‘Local’ approaches considering the hierarchy, building models per level or node, and ‘Global’ hierarchical classification, using a flat classification approach. To fill this gap, here we have systematically contrasted the performance of ‘Local per Level’ and ‘Local per Node’ approaches with a ‘Global’ approach applied to two different hierarchical datasets: BioLip and CATH. The results show how different components of hierarchical data sets, such as variation coefficient and prediction by depth, can guide the choice of appropriate classification schemes. Finally, we provide guidelines to support this process when embarking on a hierarchical classification task, which will help optimize computational resources and predictive performance.

PFmulDL: a novel strategy enabling multi-class and multi-label protein function annotation by integrating diverse deep learning methods

Bioinformatic annotation of protein function is essential but extremely sophisticated, which asks for extensive efforts to develop effective prediction method. However, the existing methods tend to amplify the representativeness of the families with large number of proteins by misclassifying the proteins in the families with small number of proteins. That is to say, the ability of the existing methods to annotate proteins in the 'rare classes' remains limited. Herein, a new protein function annotation strategy, PFmulDL, integrating multiple deep learning methods, was thus constructed. First, the recurrent neural network was integrated, for the first time, with the convolutional neural network to facilitate the function annotation. Second, a transfer learning method was introduced to the model construction for further improving the prediction performances. Third, based on the latest data of Gene Ontology, the newly constructed model could annotate the largest number of protein families comparing with the existing methods. Finally, this newly constructed model was found capable of significantly elevating the prediction performance for the 'rare classes' without sacrificing that for the 'major classes'. All in all, due to the emerging requirements on improving the prediction performance for the proteins in 'rare classes', this new strategy would become an essential complement to the existing methods for protein function prediction. All the models and source codes are freely available and open to all users at: https://github.com/idrblab/PFmulDL.

HEMDAG: a family of modular and scalable hierarchical ensemble methods to improve Gene Ontology term prediction

MOTIVATION

Automated protein function prediction is a complex multi-class, multi-label, structured classification problem in which protein functions are organized in a controlled vocabulary, according to the Gene Ontology (GO). "Hierarchy-unaware" classifiers, also known as "flat" methods, predict GO terms without exploiting the inherent structure of the ontology, potentially violating the True-Path-Rule (TPR) that governs the GO, while "hierarchy-aware" approaches, even if they obey the TPR, do not always show clear improvements with respect to flat methods, or do not scale well when applied to the full GO.

RESULTS

To overcome these limitations, we propose Hierarchical Ensemble Methods for Directed Acyclic Graphs (HEMDAG), a family of highly modular hierarchical ensembles of classifiers, able to build upon any flat method and to provide "TPR-safe" predictions, by leveraging a combination of isotonic regression and TPR learning strategies. Extensive experiments on synthetic and real data across several organisms firstly show that HEMDAG can be used as a general tool to improve the predictions of flat classifiers, and secondly that HEMDAG is competitive versus state-of-the-art hierarchy-aware learning methods proposed in the last CAFA international challenges.

AVAILABILITY

Fully-tested R code freely available at https://anaconda.org/bioconda/r-hemdag. Tutorial and documentation at https://hemdag.readthedocs.io.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

ClassifyTE: A stacking based prediction of hierarchical classification of transposable elements

MOTIVATION

Transposable Elements (TEs) or jumping genes are DNA sequences that have an intrinsic capability to move within a host genome from one genomic location to another. Studies show that the presence of a TE within or adjacent to a functional gene may alter its expression. TEs can also cause an increase in the rate of mutation and can even mediate duplications and large insertions and deletions in the genome, promoting gross genetic rearrangements. The proper classification of identified jumping genes is important for analyzing their genetic and evolutionary effects. An effective classifier, which can explain the role of TEs in germline and somatic evolution more accurately, is needed. In this study, we examine the performance of a variety of machine learning (ML) techniques and propose a robust method, ClassifyTE, for the hierarchical classification of TEs with high accuracy, using a stacking-based ML method.

RESULTS

We propose a stacking-based approach for the hierarchical classification of TEs. When trained on three different benchmark datasets, our proposed system achieved 4%, 10.68%, and 10.13% average percentage improvement (using the hF measure) compared to several state-of-the-art methods. We developed an end-to-end automated hierarchical classification tool based on the proposed approach, ClassifyTE, to classify TEs up to the super-family level. We further evaluated our method on a new TE library generated by a homology-based classification method and found relatively high concordance at higher taxonomic levels. Thus, ClassifyTE paves the way for a more accurate analysis of the role of TEs.

AVAILABILITY

The source code and data are available at https://github.com/manisa/ClassifyTE.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Prediction of Ion Channels and their Types from Protein Sequences: Comprehensive Review and Comparative Assessment

BACKGROUND

Ion channels are a large and growing protein family. Many of them are associated with diseases, and consequently, they are targets for over 700 drugs. Discovery of new ion channels is facilitated with computational methods that predict ion channels and their types from protein sequences. However, these methods were never comprehensively compared and evaluated.

OBJECTIVE

We offer first-of-its-kind comprehensive survey of the sequence-based predictors of ion channels. We describe eight predictors that include five methods that predict ion channels, their types, and four classes of the voltage-gated channels. We also develop and use a new benchmark dataset to perform comparative empirical analysis of the three currently available predictors.

RESULTS

While several methods that rely on different designs were published, only a few of them are currently available and offer a broad scope of predictions. Support and availability after publication should be required when new methods are considered for publication. Empirical analysis shows strong performance for the prediction of ion channels and modest performance for the prediction of ion channel types and voltage-gated channel classes. We identify a substantial weakness of current methods that cannot accurately predict ion channels that are categorized into multiple classes/types.

CONCLUSION

Several predictors of ion channels are available to the end users. They offer practical levels of predictive quality. Methods that rely on a larger and more diverse set of predictive inputs (such as PSIONplus) are more accurate. New tools that address multi-label prediction of ion channels should be developed.

PSIONplusm Server for Accurate Multi-Label Prediction of Ion Channels and Their Types

Computational prediction of ion channels facilitates the identification of putative ion channels from protein sequences. Several predictors of ion channels and their types were developed in the last quindecennial. While they offer reasonably accurate predictions, they also suffer a few shortcomings including lack of availability, parallel prediction mode, single-label prediction (inability to predict multiple channel subtypes), and incomplete scope (inability to predict subtypes of the voltage-gated channels). We developed a first-of-its-kind PSIONplus^m method that performs sequential multi-label prediction of ion channels and their subtypes for both voltage-gated and ligand-gated channels. PSIONplus^m sequentially combines the outputs produced by three support vector machine-based models from the PSIONplus predictor and is available as a webserver. Empirical tests show that PSIONplus^m outperforms current methods for the multi-label prediction of the ion channel subtypes. This includes the existing single-label methods that are available to the users, a naïve multi-label predictor that combines results produced by multiple single-label methods, and methods that make predictions based on sequence alignment and domain annotations. We also found that the current methods (including PSIONplus^m) fail to accurately predict a few of the least frequently occurring ion channel subtypes. Thus, new predictors should be developed when a larger quantity of annotated ion channels will be available to train predictive models.

CHEER: HierarCHical taxonomic classification for viral mEtagEnomic data via deep leaRning

The fast accumulation of viral metagenomic data has contributed significantly to new RNA virus discovery. However, the short read size, complex composition, and large data size can all make taxonomic analysis difficult. In particular, commonly used alignment-based methods are not ideal choices for detecting new viral species. In this work, we present a novel hierarchical classification model named CHEER, which can conduct read-level taxonomic classification from order to genus for new species. By combining k-mer embedding-based encoding, hierarchically organized CNNs, and carefully trained rejection layer, CHEER is able to assign correct taxonomic labels for reads from new species. We tested CHEER on both simulated and real sequencing data. The results show that CHEER can achieve higher accuracy than popular alignment-based and alignment-free taxonomic assignment tools. The source code, scripts, and pre-trained parameters for CHEER are available via GitHub:https://github.com/KennthShang/CHEER.

Improving protein function prediction using protein sequence and GO-term similarities

MOTIVATION

Most automatic functional annotation methods assign Gene Ontology (GO) terms to proteins based on annotations of highly similar proteins. We advocate that proteins that are less similar are still informative. Also, despite their simplicity and structure, GO terms seem to be hard for computers to learn, in particular the Biological Process ontology, which has the most terms (>29 000). We propose to use Label-Space Dimensionality Reduction (LSDR) techniques to exploit the redundancy of GO terms and transform them into a more compact latent representation that is easier to predict.

RESULTS

We compare proteins using a sequence similarity profile (SSP) to a set of annotated training proteins. We introduce two new LSDR methods, one based on the structure of the GO, and one based on semantic similarity of terms. We show that these LSDR methods, as well as three existing ones, improve the Critical Assessment of Functional Annotation performance of several function prediction algorithms. Cross-validation experiments on Arabidopsis thaliana proteins pinpoint the superiority of our GO-aware LSDR over generic LSDR. Our experiments on A.thaliana proteins show that the SSP representation in combination with a kNN classifier outperforms state-of-the-art and baseline methods in terms of cross-validated F-measure.

AVAILABILITY AND IMPLEMENTATION

Source code for the experiments is available at https://github.com/stamakro/SSP-LSDR.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Incremental Class Learning for Hierarchical Classification

Objects can be described in hierarchical semantics, and people also perceive them this way. It leads to the need for hierarchical classification in machine learning. On the other hand, when a new data that belongs to a new class is given, the existing classification methods should be retrained for all data including the new data. To deal with these issues, we propose an adaptive resonance theory-supervised predictive mapping for hierarchical classification (ARTMAP-HC) network that allows incremental class learning for raw data without normalization in advance. Our proposed ARTMAP-HC is composed of hierarchically stacked modules, and each module incorporates two fuzzy ARTMAP networks. Regardless of the level of the class hierarchy and the number of classes for each level, ARTMAP-HC is able to incrementally learn sequentially added input data belonging to new classes. By using a novel online normalization process, ARTMAP-HC can classify the new data without prior knowledge of the maximum value of the dataset. By adopting the prior labels appending process, the class dependency between class hierarchy levels is reflected in ARTMAP-HC. The effectiveness of the proposed ARTMAP-HC is validated through experiments on hierarchical classification datasets. To demonstrate the applicability, ARTMAP-HC is applied to a multimedia recommendation system for digital storytelling.

Learning important features from multi-view data to predict drug side effects

The problem of drug side effects is one of the most crucial issues in pharmacological development. As there are many limitations in current experimental and clinical methods for detecting side effects, a lot of computational algorithms have been developed to predict side effects with different types of drug information. However, there is still a lack of methods which could integrate heterogeneous data to predict side effects and select important features at the same time. Here, we propose a novel computational framework based on multi-view and multi-label learning for side effect prediction. Four different types of drug features are collected and graph model is constructed from each feature profile. After that, all the single view graphs are combined to regularize the linear regression functions which describe the relationships between drug features and side effect labels. L1 penalties are imposed on the regression coefficient matrices in order to select features relevant to side effects. Additionally, the correlations between side effect labels are also incorporated into the model by graph Laplacian regularization. The experimental results show that the proposed method could not only provide more accurate prediction for side effects but also select drug features related to side effects from heterogeneous data. Some case studies are also supplied to illustrate the utility of our method for prediction of drug side effects.

Machine learning techniques for protein function prediction

Proteins play important roles in living organisms, and their function is directly linked with their structure. Due to the growing gap between the number of proteins being discovered and their functional characterization (in particular as a result of experimental limitations), reliable prediction of protein function through computational means has become crucial. This paper reviews the machine learning techniques used in the literature, following their evolution from simple algorithms such as logistic regression to more advanced methods like support vector machines and modern deep neural networks. Hyperparameter optimization methods adopted to boost prediction performance are presented. In parallel, the metamorphosis in the features used by these algorithms from classical physicochemical properties and amino acid composition, up to text-derived features from biomedical literature and learned feature representations using autoencoders, together with feature selection and dimensionality reduction techniques, are also reviewed. The success stories in the application of these techniques to both general and specific protein function prediction are discussed.

Machine learning for discovering missing or wrong protein function annotations : A comparison using updated benchmark datasets

BACKGROUND

A massive amount of proteomic data is generated on a daily basis, nonetheless annotating all sequences is costly and often unfeasible. As a countermeasure, machine learning methods have been used to automatically annotate new protein functions. More specifically, many studies have investigated hierarchical multi-label classification (HMC) methods to predict annotations, using the Functional Catalogue (FunCat) or Gene Ontology (GO) label hierarchies. Most of these studies employed benchmark datasets created more than a decade ago, and thus train their models on outdated information. In this work, we provide an updated version of these datasets. By querying recent versions of FunCat and GO yeast annotations, we provide 24 new datasets in total. We compare four HMC methods, providing baseline results for the new datasets. Furthermore, we also evaluate whether the predictive models are able to discover new or wrong annotations, by training them on the old data and evaluating their results against the most recent information.

RESULTS

The results demonstrated that the method based on predictive clustering trees, Clus-Ensemble, proposed in 2008, achieved superior results compared to more recent methods on the standard evaluation task. For the discovery of new knowledge, Clus-Ensemble performed better when discovering new annotations in the FunCat taxonomy, whereas hierarchical multi-label classification with genetic algorithm (HMC-GA), a method based on genetic algorithms, was overall superior when detecting annotations that were removed. In the GO datasets, Clus-Ensemble once again had the upper hand when discovering new annotations, HMC-GA performed better for detecting removed annotations. However, in this evaluation, there were less significant differences among the methods.

CONCLUSIONS

The experiments have showed that protein function prediction is a very challenging task which should be further investigated. We believe that the baseline results associated with the updated datasets provided in this work should be considered as guidelines for future studies, nonetheless the old versions of the datasets should not be disregarded since other tasks in machine learning could benefit from them.

Survey of Image Processing Techniques for Brain Pathology Diagnosis: Challenges and Opportunities

In recent years, a number of new products introduced to the global market combine intelligent robotics, artificial intelligence and smart interfaces to provide powerful tools to support professional decision making. However, while brain disease diagnosis from the brain scan images is supported by imaging robotics, the data analysis to form a medical diagnosis is performed solely by highly trained medical professionals. Recent advances in medical imaging techniques, artificial intelligence, machine learning and computer vision present new opportunities to build intelligent decision support tools to aid the diagnostic process, increase the disease detection accuracy, reduce error, automate the monitoring of patient's recovery, and discover new knowledge about the disease cause and its treatment. This article introduces the topic of medical diagnosis of brain diseases from the MRI based images. We describe existing, multi-modal imaging techniques of the brain's soft tissue and describe in detail how are the resulting images are analyzed by a radiologist to form a diagnosis. Several comparisons between the best results of classifying natural scenes and medical image analysis illustrate the challenges of applying existing image processing techniques to the medical image analysis domain. The survey of medical image processing methods also identified several knowledge gaps, the need for automation of image processing analysis, and the identification of the brain structures in the medical images that differentiate healthy tissue from a pathology. This survey is grounded in the cases of brain tumor analysis and the traumatic brain injury diagnoses, as these two case studies illustrate the vastly different approaches needed to define, extract, and synthesize meaningful information from multiple MRI image sets for a diagnosis. Finally, the article summarizes artificial intelligence frameworks that are built as multi-stage, hybrid, hierarchical information processing work-flows and the benefits of applying these models for medical diagnosis to build intelligent physician's aids with knowledge transparency, expert knowledge embedding, and increased analytical quality.

eccCL: parallelized GPU implementation of Ensemble Classifier Chains

Background

Multi-label classification has recently gained great attention in diverse fields of research, e.g., in biomedical application such as protein function prediction or drug resistance testing in HIV. In this context, the concept of Classifier Chains has been shown to improve prediction accuracy, especially when applied as Ensemble Classifier Chains. However, these techniques lack computational efficiency when applied on large amounts of data, e.g., derived from next-generation sequencing experiments. By adapting algorithms for the use of graphics processing units, computational efficiency can be greatly improved due to parallelization of computations.

Results

Here, we provide a parallelized and optimized graphics processing unit implementation (eccCL) of Classifier Chains and Ensemble Classifier Chains. Additionally to the OpenCL implementation, we provide an R-Package with an easy to use R-interface for parallelized graphics processing unit usage.

Conclusion

eccCL is a handy implementation of Classifier Chains on GPUs, which is able to process up to over 25,000 instances per second, and thus can be used efficiently in high-throughput experiments. The software is available at http://www.heiderlab.de.