Accurate prediction of protein enzymatic class by N-to-1 Neural Networks

Machine Learning-Guided Protein Engineering

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.

Predicting enzymatic function of protein sequences with attention

MOTIVATION

There is a growing number of available protein sequences, but only a limited amount has been manually annotated. For example, only 0.25% of all entries of UniProtKB are reviewed by human annotators. Further developing automatic tools to infer protein function from sequence alone can alleviate part of this gap. In this article, we investigate the potential of Transformer deep neural networks on a specific case of functional sequence annotation: the prediction of enzymatic classes.

RESULTS

We show that our EnzBert transformer models, trained to predict Enzyme Commission (EC) numbers by specialization of a protein language model, outperforms state-of-the-art tools for monofunctional enzyme class prediction based on sequences only. Accuracy is improved from 84% to 95% on the prediction of EC numbers at level two on the EC40 benchmark. To evaluate the prediction quality at level four, the most detailed level of EC numbers, we built two new time-based benchmarks for comparison with state-of-the-art methods ECPred and DeepEC: the macro-F1 score is respectively improved from 41% to 54% and from 20% to 26%. Finally, we also show that using a simple combination of attention maps is on par with, or better than, other classical interpretability methods on the EC prediction task. More specifically, important residues identified by attention maps tend to correspond to known catalytic sites. Quantitatively, we report a max F-Gain score of 96.05%, while classical interpretability methods reach 91.44% at best.

AVAILABILITY AND IMPLEMENTATION

Source code and datasets are respectively available at https://gitlab.inria.fr/nbuton/tfpc and https://doi.org/10.5281/zenodo.7253910.

Enzyme Substrate Prediction from Three-Dimensional Feature Representations Using Space-Filling Curves

Compact and interpretable structural feature representations are required for accurately predicting properties and function of proteins. In this work, we construct and evaluate three-dimensional feature representations of protein structures based on space-filling curves (SFCs). We focus on the problem of enzyme substrate prediction, using two ubiquitous enzyme families as case studies: the short-chain dehydrogenase/reductases (SDRs) and the S-adenosylmethionine-dependent methyltransferases (SAM-MTases). Space-filling curves such as the Hilbert curve and the Morton curve generate a reversible mapping from discretized three-dimensional to one-dimensional representations and thus help to encode three-dimensional molecular structures in a system-independent way and with only a few adjustable parameters. Using three-dimensional structures of SDRs and SAM-MTases generated using AlphaFold2, we assess the performance of the SFC-based feature representations in predictions on a new benchmark database of enzyme classification tasks including their cofactor and substrate selectivity. Gradient-boosted tree classifiers yield binary prediction accuracy of 0.77-0.91 and area under curve (AUC) characteristics of 0.83-0.92 for the classification tasks. We investigate the effects of amino acid encoding, spatial orientation, and (the few) parameters of SFC-based encodings on the accuracy of the predictions. Our results suggest that geometry-based approaches such as SFCs are promising for generating protein structural representations and are complementary to the existing protein feature representations such as evolutionary scale modeling (ESM) sequence embeddings.

Improving automatic GO annotation with semantic similarity

BACKGROUND

Automatic functional annotation of proteins is an open research problem in bioinformatics. The growing number of protein entries in public databases, for example in UniProtKB, poses challenges in manual functional annotation. Manual annotation requires expert human curators to search and read related research articles, interpret the results, and assign the annotations to the proteins. Thus, it is a time-consuming and expensive process. Therefore, designing computational tools to perform automatic annotation leveraging the high quality manual annotations that already exist in UniProtKB/SwissProt is an important research problem RESULTS: In this paper, we extend and adapt the GrAPFI (graph-based automatic protein function inference) (Sarker et al. in BMC Bioinform 21, 2020; Sarker et al., in: Proceedings of 7th international conference on complex networks and their applications, Cambridge, 2018) method for automatic annotation of proteins with gene ontology (GO) terms renaming it as GrAPFI-GO. The original GrAPFI method uses label propagation in a similarity graph where proteins are linked through the domains, families, and superfamilies that they share. Here, we also explore various types of similarity measures based on common neighbors in the graph. Moreover, GO terms are arranged in a hierarchical manner according to semantic parent-child relations. Therefore, we propose an efficient pruning and post-processing technique that integrates both semantic similarity and hierarchical relations between the GO terms. We produce experimental results comparing the GrAPFI-GO method with and without considering common neighbors similarity. We also test the performance of GrAPFI-GO and other annotation tools for GO annotation on a benchmark of proteins with and without the proposed pruning and post-processing procedure.

CONCLUSION

Our results show that the proposed semantic hierarchical post-processing potentially improves the performance of GrAPFI-GO and of other annotation tools as well. Thus, GrAPFI-GO exposes an original efficient and reusable procedure, to exploit the semantic relations among the GO terms in order to improve the automatic annotation of protein functions.

Protein Science Meets Artificial Intelligence: A Systematic Review and a Biochemical Meta-Analysis of an Inter-Field

Proteins are some of the most fascinating and challenging molecules in the universe, and they pose a big challenge for artificial intelligence. The implementation of machine learning/AI in protein science gives rise to a world of knowledge adventures in the workhorse of the cell and proteome homeostasis, which are essential for making life possible. This opens up epistemic horizons thanks to a coupling of human tacit–explicit knowledge with machine learning power, the benefits of which are already tangible, such as important advances in protein structure prediction. Moreover, the driving force behind the protein processes of self-organization, adjustment, and fitness requires a space corresponding to gigabytes of life data in its order of magnitude. There are many tasks such as novel protein design, protein folding pathways, and synthetic metabolic routes, as well as protein-aggregation mechanisms, pathogenesis of protein misfolding and disease, and proteostasis networks that are currently unexplored or unrevealed. In this systematic review and biochemical meta-analysis, we aim to contribute to bridging the gap between what we call binomial artificial intelligence (AI) and protein science (PS), a growing research enterprise with exciting and promising biotechnological and biomedical applications. We undertake our task by exploring “the state of the art” in AI and machine learning (ML) applications to protein science in the scientific literature to address some critical research questions in this domain, including What kind of tasks are already explored by ML approaches to protein sciences? What are the most common ML algorithms and databases used? What is the situational diagnostic of the AI–PS inter-field? What do ML processing steps have in common? We also formulate novel questions such as Is it possible to discover what the rules of protein evolution are with the binomial AI–PS? How do protein folding pathways evolve? What are the rules that dictate the folds? What are the minimal nuclear protein structures? How do protein aggregates form and why do they exhibit different toxicities? What are the structural properties of amyloid proteins? How can we design an effective proteostasis network to deal with misfolded proteins? We are a cross-functional group of scientists from several academic disciplines, and we have conducted the systematic review using a variant of the PICO and PRISMA approaches. The search was carried out in four databases (PubMed, Bireme, OVID, and EBSCO Web of Science), resulting in 144 research articles. After three rounds of quality screening, 93 articles were finally selected for further analysis. A summary of our findings is as follows: regarding AI applications, there are mainly four types: 1) genomics, 2) protein structure and function, 3) protein design and evolution, and 4) drug design. In terms of the ML algorithms and databases used, supervised learning was the most common approach (85%). As for the databases used for the ML models, PDB and UniprotKB/Swissprot were the most common ones (21 and 8%, respectively). Moreover, we identified that approximately 63% of the articles organized their results into three steps, which we labeled pre-process, process, and post-process. A few studies combined data from several databases or created their own databases after the pre-process. Our main finding is that, as of today, there are no research road maps serving as guides to address gaps in our knowledge of the AI–PS binomial. All research efforts to collect, integrate multidimensional data features, and then analyze and validate them are, so far, uncoordinated and scattered throughout the scientific literature without a clear epistemic goal or connection between the studies. Therefore, our main contribution to the scientific literature is to offer a road map to help solve problems in drug design, protein structures, design, and function prediction while also presenting the “state of the art” on research in the AI–PS binomial until February 2021. Thus, we pave the way toward future advances in the synthetic redesign of novel proteins and protein networks and artificial metabolic pathways, learning lessons from nature for the welfare of humankind. Many of the novel proteins and metabolic pathways are currently non-existent in nature, nor are they used in the chemical industry or biomedical field.

deepNEC: a novel alignment-free tool for the identification and classification of nitrogen biochemical network-related enzymes using deep learning

Nitrogen is essential for life and its transformations are an important part of the global biogeochemical cycle. Being an essential nutrient, nitrogen exists in a range of oxidation states from +5 (nitrate) to -3 (ammonium and amino-nitrogen), and its oxidation and reduction reactions catalyzed by microbial enzymes determine its environmental fate. The functional annotation of the genes encoding the core nitrogen network enzymes has a broad range of applications in metagenomics, agriculture, wastewater treatment and industrial biotechnology. This study developed an alignment-free computational approach to determine the predicted nitrogen biochemical network-related enzymes from the sequence itself. We propose deepNEC, a novel end-to-end feature selection and classification model training approach for nitrogen biochemical network-related enzyme prediction. The algorithm was developed using Deep Learning, a class of machine learning algorithms that uses multiple layers to extract higher-level features from the raw input data. The derived protein sequence is used as an input, extracting sequential and convolutional features from raw encoded protein sequences based on classification rather than traditional alignment-based methods for enzyme prediction. Two large datasets of protein sequences, enzymes and non-enzymes were used to train the models with protein sequence features like amino acid composition, dipeptide composition (DPC), conformation transition and distribution, normalized Moreau-Broto (NMBroto), conjoint and quasi order, etc. The k-fold cross-validation and independent testing were performed to validate our model training. deepNEC uses a four-tier approach for prediction; in the first phase, it will predict a query sequence as enzyme or non-enzyme; in the second phase, it will further predict and classify enzymes into nitrogen biochemical network-related enzymes or non-nitrogen metabolism enzymes; in the third phase, it classifies predicted enzymes into nine nitrogen metabolism classes; and in the fourth phase, it predicts the enzyme commission number out of 20 classes for nitrogen metabolism. Among all, the DPC + NMBroto hybrid feature gave the best prediction performance (accuracy of 96.15% in k-fold training and 93.43% in independent testing) with an Matthews correlation coefficient (0.92 training and 0.87 independent testing) in phase I; phase II (accuracy of 99.71% in k-fold training and 98.30% in independent testing); phase III (overall accuracy of 99.03% in k-fold training and 98.98% in independent testing); phase IV (overall accuracy of 99.05% in k-fold training and 98.18% in independent testing), the DPC feature gave the best prediction performance. We have also implemented a homology-based method to remove false negatives. All the models have been implemented on a web server (prediction tool), which is freely available at http://bioinfo.usu.edu/deepNEC/.

IHEC_RAAC: a online platform for identifying human enzyme classes via reduced amino acid cluster strategy

Enzymes have been proven to play considerable roles in disease diagnosis and biological functions. The feature extraction that truly reflects the intrinsic properties of protein is the most critical step for the automatic identification of enzymes. Although lots of feature extraction methods have been proposed, some challenges remain. In this study, we developed a predictor called IHEC_RAAC, which has the capability to identify whether a protein is a human enzyme and distinguish the function of the human enzyme. To improve the feature representation ability, protein sequences were encoded by a new feature-vector called 'reduced amino acid cluster'. We calculated 673 amino acid reduction alphabets to determine the optimal feature representative scheme. The tenfold cross-validation test showed that the accuracy of IHEC_RAAC to identify human enzymes was 74.66% and further discriminate the human enzyme classes with an accuracy of 54.78%, which was 2.06% and 8.68% higher than the state-of-the-art predictors, respectively. Additionally, the results from the independent dataset indicated that IHEC_RAAC can effectively predict human enzymes and human enzyme classes to further provide guidance for protein research. A user-friendly web server, IHEC_RAAC, is freely accessible at http://bioinfor.imu.edu.cn/ihecraac .

A Survey for Predicting Enzyme Family Classes Using Machine Learning Methods

Enzymes are proteins that act as biological catalysts to speed up cellular biochemical processes. According to their main Enzyme Commission (EC) numbers, enzymes are divided into six categories: EC-1: oxidoreductase; EC-2: transferase; EC-3: hydrolase; EC-4: lyase; EC-5: isomerase and EC-6: synthetase. Different enzymes have different biological functions and acting objects. Therefore, knowing which family an enzyme belongs to can help infer its catalytic mechanism and provide information about the relevant biological function. With the large amount of protein sequences influxing into databanks in the post-genomics age, the annotation of the family for an enzyme is very important. Since the experimental methods are cost ineffective, bioinformatics tool will be a great help for accurately classifying the family of the enzymes. In this review, we summarized the application of machine learning methods in the prediction of enzyme family from different aspects. We hope that this review will provide insights and inspirations for the researches on enzyme family classification.

GrAPFI: predicting enzymatic function of proteins from domain similarity graphs

An amendment to this paper has been published and can be accessed via the original article.

DeEPn: a deep neural network based tool for enzyme functional annotation

With the advancement of high throughput techniques, the discovery rate of enzyme sequences has increased significantly in the recent past. All of these raw sequences are required to be precisely mapped to their respective functional attributes, which helps in deciphering their biological role. In the recent past, various prediction models have been proposed to predict the enzyme functional class; however, all of these models were able to quantify at most six functional enzyme classes (EC1 to EC6) out of existing seven functional classes, making these approaches inappropriate for handling enzymes corresponding to the seventh functional class (EC7). In this study, a Deep Neural Network-based approach, DeEPn, has been proposed, which can quantify enzymes corresponding to all seven functional classes with high precision and accuracy. The proposed model was compared with two recently developed tools, ECPred and SVM-Prot. The result demonstrated that DeEPn outperformed ECPred and SVM-Prot in terms of predictive quality. The DeEPn tool has been hosted as a web-based tool at https://bioserver.iiita.ac.in/DeEPn/.Communicated by Ramaswamy H. Sarma.

DEEPre: sequence-based enzyme EC number prediction by deep learning

Motivation

Annotation of enzyme function has a broad range of applications, such as metagenomics, industrial biotechnology, and diagnosis of enzyme deficiency-caused diseases. However, the time and resource required make it prohibitively expensive to experimentally determine the function of every enzyme. Therefore, computational enzyme function prediction has become increasingly important. In this paper, we develop such an approach, determining the enzyme function by predicting the Enzyme Commission number.

Results

We propose an end-to-end feature selection and classification model training approach, as well as an automatic and robust feature dimensionality uniformization method, DEEPre, in the field of enzyme function prediction. Instead of extracting manually crafted features from enzyme sequences, our model takes the raw sequence encoding as inputs, extracting convolutional and sequential features from the raw encoding based on the classification result to directly improve the prediction performance. The thorough cross-fold validation experiments conducted on two large-scale datasets show that DEEPre improves the prediction performance over the previous state-of-the-art methods. In addition, our server outperforms five other servers in determining the main class of enzymes on a separate low-homology dataset. Two case studies demonstrate DEEPre’s ability to capture the functional difference of enzyme isoforms.

Availability and implementation

The server could be accessed freely at http://www.cbrc.kaust.edu.sa/DEEPre.

Supplementary information

Supplementary data are available at Bioinformatics online.

ECPred: a tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature

BACKGROUND

The automated prediction of the enzymatic functions of uncharacterized proteins is a crucial topic in bioinformatics. Although several methods and tools have been proposed to classify enzymes, most of these studies are limited to specific functional classes and levels of the Enzyme Commission (EC) number hierarchy. Besides, most of the previous methods incorporated only a single input feature type, which limits the applicability to the wide functional space. Here, we proposed a novel enzymatic function prediction tool, ECPred, based on ensemble of machine learning classifiers.

RESULTS

In ECPred, each EC number constituted an individual class and therefore, had an independent learning model. Enzyme vs. non-enzyme classification is incorporated into ECPred along with a hierarchical prediction approach exploiting the tree structure of the EC nomenclature. ECPred provides predictions for 858 EC numbers in total including 6 main classes, 55 subclass classes, 163 sub-subclass classes and 634 substrate classes. The proposed method is tested and compared with the state-of-the-art enzyme function prediction tools by using independent temporal hold-out and no-Pfam datasets constructed during this study.

CONCLUSIONS

ECPred is presented both as a stand-alone and a web based tool to provide probabilistic enzymatic function predictions (at all five levels of EC) for uncharacterized protein sequences. Also, the datasets of this study will be a valuable resource for future benchmarking studies. ECPred is available for download, together with all of the datasets used in this study, at: https://github.com/cansyl/ECPred . ECPred webserver can be accessed through http://cansyl.metu.edu.tr/ECPred.html .

Deep Learning in Biomedical Data Science

Since the 1980s, deep learning and biomedical data have been coevolving and feeding each other. The breadth, complexity, and rapidly expanding size of biomedical data have stimulated the development of novel deep learning methods, and application of these methods to biomedical data have led to scientific discoveries and practical solutions. This overview provides technical and historical pointers to the field, and surveys current applications of deep learning to biomedical data organized around five subareas, roughly of increasing spatial scale: chemoinformatics, proteomics, genomics and transcriptomics, biomedical imaging, and health care. The black box problem of deep learning methods is also briefly discussed.

Automatic single- and multi-label enzymatic function prediction by machine learning

The number of protein structures in the PDB database has been increasing more than 15-fold since 1999. The creation of computational models predicting enzymatic function is of major importance since such models provide the means to better understand the behavior of newly discovered enzymes when catalyzing chemical reactions. Until now, single-label classification has been widely performed for predicting enzymatic function limiting the application to enzymes performing unique reactions and introducing errors when multi-functional enzymes are examined. Indeed, some enzymes may be performing different reactions and can hence be directly associated with multiple enzymatic functions. In the present work, we propose a multi-label enzymatic function classification scheme that combines structural and amino acid sequence information. We investigate two fusion approaches (in the feature level and decision level) and assess the methodology for general enzymatic function prediction indicated by the first digit of the enzyme commission (EC) code (six main classes) on 40,034 enzymes from the PDB database. The proposed single-label and multi-label models predict correctly the actual functional activities in 97.8% and 95.5% (based on Hamming-loss) of the cases, respectively. Also the multi-label model predicts all possible enzymatic reactions in 85.4% of the multi-labeled enzymes when the number of reactions is unknown. Code and datasets are available at https://figshare.com/s/a63e0bafa9b71fc7cbd7.

Accurate Ab Initio and Template-Based Prediction of Short Intrinsically-Disordered Regions by Bidirectional Recurrent Neural Networks Trained on Large-Scale Datasets

Intrinsically-disordered regions lack a well-defined 3D structure, but play key roles in determining the function of many proteins. Although predictors of disorder have been shown to achieve relatively high rates of correct classification of these segments, improvements over the the years have been slow, and accurate methods are needed that are capable of accommodating the ever-increasing amount of structurally-determined protein sequences to try to boost predictive performances. In this paper, we propose a predictor for short disordered regions based on bidirectional recurrent neural networks and tested by rigorous five-fold cross-validation on a large, non-redundant dataset collected from MobiDB, a new comprehensive source of protein disorder annotations. The system exploits sequence and structural information in the forms of frequency profiles, predicted secondary structure and solvent accessibility and direct disorder annotations from homologous protein structures (templates) deposited in the Protein Data Bank. The contributions of sequence, structure and homology information result in large improvements in predictive accuracy. Additionally, the large scale of the training set leads to low false positive rates, making our systems a robust and efficient way to address high-throughput disorder prediction.

Modeling evolution of spatially distributed bacterial communities: a simulation with the haploid evolutionary constructor

Background

Multiscale approaches for integrating submodels of various levels of biological organization into a single model became the major tool of systems biology. In this paper, we have constructed and simulated a set of multiscale models of spatially distributed microbial communities and study an influence of unevenly distributed environmental factors on the genetic diversity and evolution of the community members.

Results

Haploid Evolutionary Constructor software http://evol-constructor.bionet.nsc.ru/ was expanded by adding the tool for the spatial modeling of a microbial community (1D, 2D and 3D versions). A set of the models of spatially distributed communities was built to demonstrate that the spatial distribution of cells affects both intensity of selection and evolution rate.

Conclusion

In spatially heterogeneous communities, the change in the direction of the environmental flow might be reflected in local irregular population dynamics, while the genetic structure of populations (frequencies of the alleles) remains stable. Furthermore, in spatially heterogeneous communities, the chemotaxis might dramatically affect the evolution of community members.

A survey of computational intelligence techniques in protein function prediction

During the past, there was a massive growth of knowledge of unknown proteins with the advancement of high throughput microarray technologies. Protein function prediction is the most challenging problem in bioinformatics. In the past, the homology based approaches were used to predict the protein function, but they failed when a new protein was different from the previous one. Therefore, to alleviate the problems associated with homology based traditional approaches, numerous computational intelligence techniques have been proposed in the recent past. This paper presents a state-of-the-art comprehensive review of various computational intelligence techniques for protein function predictions using sequence, structure, protein-protein interaction network, and gene expression data used in wide areas of applications such as prediction of DNA and RNA binding sites, subcellular localization, enzyme functions, signal peptides, catalytic residues, nuclear/G-protein coupled receptors, membrane proteins, and pathway analysis from gene expression datasets. This paper also summarizes the result obtained by many researchers to solve these problems by using computational intelligence techniques with appropriate datasets to improve the prediction performance. The summary shows that ensemble classifiers and integration of multiple heterogeneous data are useful for protein function prediction.

Application of supervised Kohonen map and counter propagation neural network for classification of nucleic acid structures based on their circular dichroism spectra

One of the most popular instrumental methods to detect the DNA structure is circular dichroism. Specific experimental conditions are required to form different structures of DNA. However, there is the possibility of different structures establishing in the similar circumstance. So, methods development to improve the classification and prediction of structures using their spectra information are needed. To this end, we applied unsupervised (PCA) and supervised (PLS-DA, SKN, and CPNN) approaches to classify CD spectra dataset of different DNA sequences (random coil (ss-DNA), duplex, hairpin, reversed and normal triplex, parallel and antiparallel G-quadruplex, and i-motif). The main part of this work concentrates on the application of artificial neural networks and weight analysis to obtain more classification and prediction accuracy. For this purpose, the trained network was run 10 times, and the average weights were taken. Also, weight analysis was done for the prediction of mixture samples include different structures. The results prove that new method of weights analysis based on SKN and CPNN is useful for classification of complicated data such as different types of DNA structures.

SCLpredT: Ab initio and homology-based prediction of subcellular localization by N-to-1 neural networks

Abstract

The prediction of protein subcellular localization is a important step towards the prediction of protein function, and considerable effort has gone over the last decade into the development of computational predictors of protein localization. In this article we design a new predictor of protein subcellular localization, based on a Machine Learning model (N-to-1 Neural Networks) which we have recently developed. This system, in three versions specialised, respectively, on Plants, Fungi and Animals, has a rich output which incorporates the class “organelle” alongside cytoplasm, nucleus, mitochondria and extracellular, and, additionally, chloroplast in the case of Plants. We investigate the information gain of introducing additional inputs, including predicted secondary structure, and localization information from homologous sequences. To accommodate the latter we design a new algorithm which we present here for the first time. While we do not observe any improvement when including predicted secondary structure, we measure significant overall gains when adding homology information. The final predictor including homology information correctly predicts 74%, 79% and 60% of all proteins in the case of Fungi, Animals and Plants, respectively, and outperforms our previous, state-of-the-art predictor SCLpred, and the popular predictor BaCelLo. We also observe that the contribution of homology information becomes dominant over sequence information for sequence identity values exceeding 50% for Animals and Fungi, and 60% for Plants, confirming that subcellular localization is less conserved than structure.

SCLpredT is publicly available at http://distillf.ucd.ie/sclpredt/. Sequence- or template-based predictions can be obtained, and up to 32kbytes of input can be processed in a single submission.

SCL-Epred: a generalised de novo eukaryotic protein subcellular localisation predictor

Knowledge of the subcellular location of a protein provides valuable information about its function, possible interaction with other proteins and drug targetability, among other things. The experimental determination of a protein's location in the cell is expensive, time consuming and open to human error. Fast and accurate predictors of subcellular location have an important role to play if the abundance of sequence data which is now available is to be fully exploited. In the post-genomic era, genomes in many diverse organisms are available. Many of these organisms are important in human and veterinary disease and fall outside of the well-studied plant, animal and fungi groups. We have developed a general eukaryotic subcellular localisation predictor (SCL-Epred) which predicts the location of eukaryotic proteins into three classes which are important, in particular, for determining the drug targetability of a protein-secreted proteins, membrane proteins and proteins that are neither secreted nor membrane. The algorithm powering SCL-Epred is a N-to-1 neural network and is trained on very large non-redundant sets of protein sequences. SCL-Epred performs well on training data achieving a Q of 86 % and a generalised correlation of 0.75 when tested in tenfold cross-validation on a set of 15,202 redundancy reduced protein sequences. The three class accuracy of SCL-Epred and LocTree2, and in particular a consensus predictor comprising both methods, surpasses that of other widely used predictors when benchmarked using a large redundancy reduced independent test set of 562 proteins. SCL-Epred is publicly available at http://distillf.ucd.ie/distill/ .