Evolutionary Information Research Articles

ProB-Site: Protein Binding Site Prediction Using Local Features.

Protein–protein interactions (PPIs) are responsible for various essential biological processes. This information can help develop a new drug against diseases. Various experimental methods have been employed for this purpose; however, their application is limited by their cost and time consumption. Alternatively, computational methods are considered viable means to achieve this crucial task. Various techniques have been explored in the literature using the sequential information of amino acids in a protein sequence, including machine learning and deep learning techniques. The current efficiency of interaction-site prediction still has growth potential. Hence, a deep neural network-based model, ProB-site, is proposed. ProB-site utilizes sequential information of a protein to predict its binding sites. The proposed model uses evolutionary information and predicted structural information extracted from sequential information of proteins, generating three unique feature sets for every amino acid in a protein sequence. Then, these feature sets are fed to their respective sub-CNN architecture to acquire complex features. Finally, the acquired features are concatenated and classified using fully connected layers. This methodology performed better than state-of-the-art techniques because of the selection of the best features and contemplation of local information of each amino acid.

EBP-A: a prediction method of protein backbone torsion angle based on convolutional neural network

Protein backbone torsion angles prediction from sequence is an important sub-problem in protein structure prediction. The prediction of protein backbone torsion angle can help to achieve an accurate prediction of protein structure and its function determination. Therefore, there are many methods for the prediction of protein backbone torsion angle. However, most existing methods are profile-based, and most proteins(more than 90%) have none or very few homologous sequences for generating evolutionary information. In addition, with the development of protein sequencing technology, the number of sequences in the protein sequence library continues to grow rapidly. To this end, this paper proposes a new embeddings-based prediction method, which takes the embedding feature of amino acid sequences as input, and designs a suitable network structure, to prediction protein backbone torsion angles. The experimental results on the Test2018 and Test2016 test datasets show that our method has higher prediction accuracy than existing prediction methods.

Predicting Protein-Protein Interactions Based on Ensemble Learning-Based Model from Protein Sequence.

Simple SummaryDue to most traditional high-throughput experiments are tedious and laborious in identifying potential protein–protein interaction. To better improve accuracy prediction in protein–protein interactions. We proposed a novel computational method that can identify unknown protein–protein interaction efficiently and hope this method can provide a helpful idea and tool for proteomics research.Protein–protein interactions (PPIs) play an essential role in many biological cellular functions. However, it is still tedious and time-consuming to identify protein–protein interactions through traditional experimental methods. For this reason, it is imperative and necessary to develop a computational method for predicting PPIs efficiently. This paper explores a novel computational method for detecting PPIs from protein sequence, the approach which mainly adopts the feature extraction method: Locality Preserving Projections (LPP) and classifier: Rotation Forest (RF). Specifically, we first employ the Position Specific Scoring Matrix (PSSM), which can remain evolutionary information of biological for representing protein sequence efficiently. Then, the LPP descriptor is applied to extract feature vectors from PSSM. The feature vectors are fed into the RF to obtain the final results. The proposed method is applied to two datasets: Yeast and H. pylori, and obtained an average accuracy of 92.81% and 92.56%, respectively. We also compare it with K nearest neighbors (KNN) and support vector machine (SVM) to better evaluate the performance of the proposed method. In summary, all experimental results indicate that the proposed approach is stable and robust for predicting PPIs and promising to be a useful tool for proteomics research.

Теоретичний аналіз проблеми економічного виховання дітей з інтелектуальними порушеннями

The article identifies the theoretical prerequisites for the formation of ideas about the essence of economic education in world pedagogy. The basic evolutionary information is given and the critical analysis of scientific works of foreign and domestic researchers concerning economic education as a psychological and pedagogical category is carried out. The position of researchers on the sources of economic education of children is substantiated. The interrelation of economic education of children with their socialization is proved. The main approaches and guidelines of leading Western researchers on the essence of economic education (cognitive, behavioral and interactionist) are identified. Taking into account the above approaches, the interrelated key components of economic socialization of children are given: 1) subjects (agents) of socialization; 2) the process of socialization through learning; 3) individual variables arising from the peculiarities of social structure (sex, age, social status, etc.); 4) the result of the process of socialization (adequate implementation of the chosen economic role). The foreign experience of formation of elementary economic skills in children within the current educational programs in the leading countries of the world is characterized. Related psychological and pedagogical categories: "economic education", "economic education", "economic competence", "economic training", "economic consciousness", "economic thinking", "economic culture", "economic socialization", etc. The possibilities of their synonymous use in the formation of economic skills in children are emphasized. The approaches of scientists to the definition of the term "economic education" are described. For a deeper understanding of the differences between education and upbringing, the common and distinctive features of these terms are justified. It is emphasized that for the purposes of studying the peculiarities of the acquisition of economic skills by children with intellectual disabilities, it is advisable to use the term "economic education" instead of "economic education". The author's definition of the terms: "economic education", "economic education of children with intellectual disabilities" is given.

PhyloPGM: boosting regulatory function prediction accuracy using evolutionary information.

MotivationThe computational prediction of regulatory function associated with a genomic sequence is of utter importance in -omics study, which facilitates our understanding of the underlying mechanisms underpinning the vast gene regulatory network. Prominent examples in this area include the binding prediction of transcription factors in DNA regulatory regions, and predicting RNA–protein interaction in the context of post-transcriptional gene expression. However, existing computational methods have suffered from high false-positive rates and have seldom used any evolutionary information, despite the vast amount of available orthologous data across multitudes of extant and ancestral genomes, which readily present an opportunity to improve the accuracy of existing computational methods.ResultsIn this study, we present a novel probabilistic approach called PhyloPGM that leverages previously trained TFBS or RNA–RBP binding predictors by aggregating their predictions from various orthologous regions, in order to boost the overall prediction accuracy on human sequences. Throughout our experiments, PhyloPGM has shown significant improvement over baselines such as the sequence-based RNA–RBP binding predictor RNATracker and the sequence-based TFBS predictor that is known as FactorNet. PhyloPGM is simple in principle, easy to implement and yet, yields impressive results.Availability and implementationThe PhyloPGM package is available at https://github.com/BlanchetteLab/PhyloPGMSupplementary information Supplementary data are available at Bioinformatics online.

Bioinformatics Approaches to Predict Mutation Effects in the Binding Site of the Proangiogenic Molecule CD93.

The transmembrane glycoprotein CD93 has been identified as a potential new target to inhibit tumor angiogenesis. Recently, Multimerin-2 (MMRN2), a pan-endothelial extracellular matrix protein, has been identified as a ligand for CD93, but the interaction mechanism between these two proteins is yet to be studied. In this article, we aim to investigate the structural and functional effects of induced mutations on the binding domain of CD93 to MMRN2. Starting from experimental data, we assessed how specific mutations in the C-type lectin-like domain (CTLD) affect the binding interaction profile. We described a four-step workflow in order to predict the effects of variations on the inter-residue interaction network at the PPI, based on evolutionary information, complex network metrics, and energetic affinity. We showed that the application of computational approaches, combined with experimental data, allowed us to gain more in-depth molecular insights into the CD93-MMRN2 interaction, offering a platform for developing innovative therapeutics able to target these molecules and block their interaction. This comprehensive molecular insight might prove useful in drug design in cancer therapy.

Random neighbor elite guided differential evolution for global numerical optimization

Optimization problems not only become more and more ubiquitous in various fields, but also become more and more difficult to optimize nowadays, which seriously challenge the effectiveness of existing optimizers like different evolution (DE). To effectively solve this kind of problems, this paper proposes a random neighbor elite guided differential evolution (RNEGDE) algorithm. Specifically, to let individuals explore and exploit the solution space properly, a novel random neighbor elite guided mutation strategy named “DE/current-to-rnbest/1” is first proposed to mutate individuals. In this mutation strategy, several individuals randomly selected from the population for each individual to be updated along with the individual itself form a neighbor region, and then the best one in such a region is adopted as the guiding exemplar to mutate the individual. Due to the random selection of neighbors and the directional guidance of elites, this strategy is expected to direct individuals to promising areas fast without serious loss of diversity. Notably, it is found that two popular mutation strategies, namely “DE/current-to-best/1” and “DE/current-to-pbest/1”, are two special cases of the proposed “DE/current-to-rnbest/1”. Further, to alleviate the sensitivity of the proposed algorithm to the involved parameters, this paper utilizes the Gaussian distribution and the Cauchy distribution to adaptively generate parameter values for each individual with the mean value of the Gaussian distribution and the position value of the Cauchy distribution adaptively adjusted based on the evolutionary information of the population. With the above two techniques, the proposed algorithm is expected to effectively search the solution space. At last, extensive experiments conducted on one widely used benchmark function set with three different dimension sizes demonstrate that the proposed algorithm achieves highly competitive or even much better performance than several compared state-of-the-art peer methods.

Evolution of the DEHYDRATION-RESPONSIVE ELEMENT-BINDING PROTEIN subfamily in green plants.

Adapting to unfavorable environments is a necessary step in plant terrestrialization and radiation. The dehydration-responsive element-binding (DREB) protein subfamily plays a pivotal role in plant abiotic stress regulation. However, relationships between the origin and expansion of the DREB subfamily and adaptive evolution of land plants are still being elucidated. Here, we constructed the evolutionary history of the DREB subfamily by compiling APETALA2/ethylene-responsive element-binding protein superfamily genes from 169 representative species of green plants. Through extensive phylogenetic analyses and comparative genomic analysis, our results revealed that the DREB subfamily diverged from the ethylene-responsive factor (ERF) subfamily in the common ancestor of Zygnemophyceae and Embryophyta during the colonization of land by plants, followed by expansions to form three different ancient archetypal genes in Zygnemophyceae species, designated as groups archetype-I, archetype-II/III, and archetype-IV. Four large-scale expansions paralleling the evolution of land plants led to the nine-subgroup divergence of group archetype-II/III in angiosperms, and five whole-genome duplications during Brassicaceae and Poaceae radiation shaped the diversity of subgroup IIb-1. We identified a Poaceae-specific gene in subgroup IIb-1, ERF014, remaining in a Poaceae-specific microsynteny block and co-evolving with a small heat shock protein cluster. Expression analyses demonstrated that heat acclimation may have driven the neofunctionalization of ERF014s in Pooideae by engaging in the conserved heat-responsive module in Poaceae. This study provides insights into lineage-specific expansion and neofunctionalization in the DREB subfamily, together with evolutionary information valuable for future functional studies of plant stress biology.

Pep-Whisperer: Inhibitory peptide design.

Designing peptides for protein-protein interaction inhibition is of significant interest in computer-aided drug design. Such inhibitory peptides could mimic and compete with the binding of the partner protein to the inhibition target. Experimental peptide design is a laborious, time consuming, and expensive multi-step process. Therefore, in silico peptide design can be beneficial for achieving this task. We present a novel algorithm, Pep-Whisperer, which aims to design inhibitory peptides for protein-protein interaction. The desirable peptides would have a relatively high predicted binding affinity to the target protein in a given protein-protein complex. The algorithm outputs linear peptides which are based on an initial template. The template could either be a peptide which is retrieved from the interaction site, or a patch of nonconsecutive amino acids from the protein-protein interface which is completed to a linear peptide by short polyalanine linkers. In addition, the algorithm takes into consideration the conservation of the amino acids in the ligand-protein binding site by using evolutionary information for choosing the preferred amino acids in each position of the designed peptide. Our algorithm was able to design peptides with high predicted binding affinity to the target protein. The method is fully automated and available as a web server at http://bioinfo3d.cs.tau.ac.il/PepWhisperer/.

Research on DNA-Binding Protein Identification Method Based on LSTM-CNN Feature Fusion.

Protein is closely related to life activities. As a kind of protein, DNA-binding protein plays an irreplaceable role in life activities. Therefore, it is very important to study DNA-binding protein, which is a subject worthy of study. Although traditional biotechnology has high precision, its cost and efficiency are increasingly unable to meet the needs of modern society. Machine learning methods can make up for the deficiencies of biological experimental techniques to a certain extent, but they are not as simple and fast as deep learning for data processing. In this paper, a deep learning framework based on parallel long and short-term memory(LSTM) and convolutional neural networks(CNN) was proposed to identify DNA-binding protein. This model can not only further extract the information and features of protein sequences, but also the features of evolutionary information. Finally, the two features are combined for training and testing. On the PDB2272 dataset, compared with PDBP_Fusion model, Accuracy(ACC) and Matthew's Correlation Coefficient (MCC) increased by 3.82% and 7.98% respectively. The experimental results of this model have certain advantages.

Protein language-model embeddings for fast, accurate, and alignment-free protein structure prediction

Advanced protein structure prediction requires evolutionary information from multiple sequence alignments (MSAs) from evolutionary couplings that are not always available. Artificial intelligence (AI)-based predictions inputting only single sequences are faster but so inaccurate as to render speed irrelevant. Here, we described a competitive prediction of inter-residue distances (2D structure) exclusively inputting embeddings from pre-trained protein language models (pLMs), namely ProtT5, from single sequences into a convolutional neural network (CNN) with relatively few layers. The major advance used the ProtT5 attention heads. Our new method, EMBER2, which never requires any MSAs, performed similarly to other methods that fully rely on co-evolution. Although clearly not reaching AlphaFold2, our leaner solution came somehow close at substantially lower costs. By generating protein-specific rather than family-averaged predictions, EMBER2 might better capture some features of particular protein structures. Results from using protein engineering and deep mutational scanning (DMS) experiments provided at least a proof of principle for such a speculation.

MSPEDTI: Prediction of Drug-Target Interactions via Molecular Structure with Protein Evolutionary Information.

Simple SummaryDrug discovery is the process of identifying potential new compounds through biological, chemical, and pharmacological means. Billions of dollars are spent each year on research aimed at discovering, designing, and developing new drugs for a wide range of diseases. However, the research and development of new drugs remain time-consuming and sometimes difficult to complete. With the development of new experimental techniques, huge amounts of data are generated at different stages of drug development. Biomedical research, especially in the field of drug discovery, is currently undergoing a major shift towards “big data” applications of artificial intelligence technologies. Therefore, a key challenge for future drug discovery research is the development of robust artificial-intelligence-based predictive tools for drug–target interactions (DTIs) that can study biomedical problems from multiple perspectives. In this study, a deep-learning-based prediction model for DTIs was designed by combining information on drug structure and protein evolution to provide theoretical support for drug research.The key to new drug discovery and development is first and foremost the search for molecular targets of drugs, thus advancing drug discovery and drug repositioning. However, traditional drug–target interactions (DTIs) is a costly, lengthy, high-risk, and low-success-rate system project. Therefore, more and more pharmaceutical companies are trying to use computational technologies to screen existing drug molecules and mine new drugs, leading to accelerating new drug development. In the current study, we designed a deep learning computational model MSPEDTI based on Molecular Structure and Protein Evolutionary to predict the potential DTIs. The model first fuses protein evolutionary information and drug structure information, then a deep learning convolutional neural network (CNN) to mine its hidden features, and finally accurately predicts the associated DTIs by extreme learning machine (ELM). In cross-validation experiments, MSPEDTI achieved 94.19%, 90.95%, 87.95%, and 86.11% prediction accuracy in the gold-standard datasets enzymes, ion channels, G-protein-coupled receptors (GPCRs), and nuclear receptors, respectively. MSPEDTI showed its competitive ability in ablation experiments and comparison with previous excellent methods. Additionally, 7 of 10 potential DTIs predicted by MSPEDTI were substantiated by the classical database. These excellent outcomes demonstrate the ability of MSPEDTI to provide reliable drug candidate targets and strongly facilitate the development of drug repositioning and drug development.

Alpha and beta phylogenetic diversities jointly reveal ant community assembly mechanisms along a tropical elevational gradient

Despite the long-standing interest in the organization of ant communities across elevational gradients, few studies have incorporated the evolutionary information to understand the historical processes that underlay such patterns. Through the evaluation of phylogenetic α and β-diversity, we analyzed the structure of leaf-litter ant communities along the Cofre de Perote mountain in Mexico and evaluated whether deterministic- (i.e., habitat filtering, interspecific competition) or stochastic-driven processes (i.e., dispersal limitation) were driving the observed patterns. Lowland and some highland sites showed phylogenetic clustering, whereas intermediate elevations and the highest site presented phylogenetic overdispersion. We infer that strong environmental constraints found at the bottom and the top elevations are favoring closely-related species to prevail at those elevations. Conversely, less stressful climatic conditions at intermediate elevations suggest interspecific interactions are more important in these environments. Total phylogenetic dissimilarity was driven by the turnover component, indicating that the turnover of ant species along the mountain is actually shifts of lineages adapted to particular locations resembling their ancestral niche. The greater phylogenetic dissimilarity between communities was related to greater temperature differences probably due to narrow thermal tolerances inherent to several ant lineages that evolved in more stable conditions. Our results suggest that the interplay between environmental filtering, interspecific competition and habitat specialization plays an important role in the assembly of leaf-litter ant communities along elevational gradients.

DDGun: an untrained predictor of protein stability changes upon amino acid variants.

Estimating the functional effect of single amino acid variants in proteins is fundamental for predicting the change in the thermodynamic stability, measured as the difference in the Gibbs free energy of unfolding, between the wild-type and the variant protein (ΔΔG). Here, we present the web-server of the DDGun method, which was previously developed for the ΔΔG prediction upon amino acid variants. DDGun is an untrained method based on basic features derived from evolutionary information. It is antisymmetric, as it predicts opposite ΔΔG values for direct (A → B) and reverse (B → A) single and multiple site variants. DDGun is available in two versions, one based on only sequence information and the other one based on sequence and structure information. Despite being untrained, DDGun reaches prediction performances comparable to those of trained methods. Here we make DDGun available as a web server. For the web server version, we updated the protein sequence database used for the computation of the evolutionary features, and we compiled two new data sets of protein variants to do a blind test of its performances. On these blind data sets of single and multiple site variants, DDGun confirms its prediction performance, reaching an average correlation coefficient between experimental and predicted ΔΔG of 0.45 and 0.49 for the sequence-based and structure-based versions, respectively. Besides being used for the prediction of ΔΔG, we suggest that DDGun should be adopted as a benchmark method to assess the predictive capabilities of newly developed methods. Releasing DDGun as a web-server, stand-alone program and docker image will facilitate the necessary process of method comparison to improve ΔΔG prediction.

KnotAli: informed energy minimization through the use of evolutionary information

BackgroundImproving the prediction of structures, especially those containing pseudoknots (structures with crossing base pairs) is an ongoing challenge. Homology-based methods utilize structural similarities within a family to predict the structure. However, their prediction is limited to the consensus structure, and by the quality of the alignment. Minimum free energy (MFE) based methods, on the other hand, do not rely on familial information and can predict structures of novel RNA molecules. Their prediction normally suffers from inaccuracies due to their underlying energy parameters.ResultsWe present a new method for prediction of RNA pseudoknotted secondary structures that combines the strengths of MFE prediction and alignment-based methods. KnotAli takes a multiple RNA sequence alignment as input and uses covariation and thermodynamic energy minimization to predict possibly pseudoknotted secondary structures for each individual sequence in the alignment. We compared KnotAli’s performance to that of three other alignment-based programs, two that can handle pseudoknotted structures and one control, on a large data set of 3034 RNA sequences with varying lengths and levels of sequence conservation from 10 families with pseudoknotted and pseudoknot-free reference structures. We produced sequence alignments for each family using two well-known sequence aligners (MUSCLE and MAFFT).ConclusionsWe found KnotAli’s performance to be superior in 6 of the 10 families for MUSCLE and 7 of the 10 for MAFFT. While both KnotAli and Cacofold use background noise correction strategies, we found KnotAli’s predictions to be less dependent on the alignment quality. KnotAli can be found online at the Zenodo image: https://doi.org/10.5281/zenodo.5794719

Evaluation Model of English Diagnostic Intelligence Based on Organizational Evolutionary Information Entropy

We show how to optimize English diagnostic Q matrix based on cognitive diagnostic model fitting method. Firstly, attribute annotation verifies the reliability of existing Q matrix and fitting analysis, as researchers found that they still have the original Q matrix optimization space; secondly, this paper proposes a classification algorithm based on organization evolution and the information entropy of English in the diagnosis of intelligent evaluation algorithm, the running mechanism of the existing evolutionary algorithm, and the evolution of its direct effects on operation data rather than the rule. After the end of evolution, rules can be extracted from each organization to avoid meaningless rules in the process of evolution. According to the characteristics of the classification problem, we put forward three kinds of evolutionary operators and a selection mechanism, which is presented based on the information office of the evolution of the way of attribute importance. Based on this definition, the organizational fitness function, and finally the algorithm used in six test data sets and compared with the existing two classification methods, the experimental results show that the method obtained the higher forecast accuracy, and smaller rule sets are produced. Finally, a matching combination and quantitative fitting screening based on G-DINA measurement model were decomposed and analyzed, and a better fitting model was optimized based on the original Q matrix model. The results show that, first, the optimized new model is better than the original model in relative data fitting value and interpretation and diagnosis of fractional variation; second, the new model has a higher correlation with the results of self-evaluation, indicating that the probability of the new model is closer to the results of self-evaluation.

An analysis of protein language model embeddings for fold prediction.

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models, which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the long short-term memory-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT and ProtT5; as well as three neural networks: Multi-Layer Perceptron, ResCNN-BGRU (RBG) and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

Monogenean body size, but not reproduction, increases with infracommunity density

Body size reveals a plethora of life-history, ecological, and evolutionary information about a species. It plays a critical role in success or failure during competitive, reproductive, or predator–prey interactions. Typically, there is a negative relationship between body size and population density in natural populations and communities. I analysed this relationship within and among multiple populations of two prominent monogenean parasites (>90% prevalence) on Lepomis macrochirus in three lakes in New Jersey (USA), using multiple regression models. To elucidate the causes and benefits of this relationship, I also measured host body condition via a regression index, and reproductive output of the parasite community by measuring parasite eggs shed from the host. The relationship between body size and density of infrapopulations (parasites of a single species on a single host) was positive, and the strength of this relationship for both species depended on which lake they occupied, indicating the potential for Allee effects. This relationship persists at the infracommunity level, where there was a similar positive relationship between a community weighted mean body size and density. However, this relationship did not result in greater reproductive success as measured by infracommunity egg production per individual per 24 h or egg size. The cause of this relationship also remains elusive; it was not explained by host condition or age. The results suggest that there is either no reproductive advantage to this increase in body size or the advantage conferred was not related to these measured fitness components. These findings indicate that researchers should be cautious using body size as a proxy for fitness or reproduction, while also raising further questions about the nature of the relationship between parasites on a host and that between those parasites and the host.

MFPS_CNN: Multi‐filter Pattern Scanning from Position‐specific Scoring Matrix with Convolutional Neural Network for Efficient Prediction of Ion Transporters

In cellular transportation mechanisms, the movement of ions across the cell membrane and its proper control are important for cells, especially for life processes. Ion transporters/pumps and ion channel proteins work as border guards controlling the incessant traffic of ions across cell membranes. We revisited the study of classification of transporters and ion channels from membrane proteins with a more efficient deep learning approach. Specifically, we applied multi-window scanning filters of convolutional neural networks on almost full-length position-specific scoring matrices for extracting useful information. In this way, we were able to retain important evolutionary information of the proteins. Our experiment results show that a convolutional neural network with a minimum number of convolutional layers can be enough to extract the conserved information of proteins which leads to higher performance. Our best prediction models were obtained after examining different data imbalanced handling techniques, and different protein encoding methods. We also showed that our models were superior to traditional deep learning approaches on the same datasets as well as other machine learning classification algorithms.

Multiple Profile Models Extract Features from Protein Sequence Data and Resolve Functional Diversity of Very Different Protein Families.

Functional classification of proteins from sequences alone has become a critical bottleneck in understanding the myriad of protein sequences that accumulate in our databases. The great diversity of homologous sequences hides, in many cases, a variety of functional activities that cannot be anticipated. Their identification appears critical for a fundamental understanding of the evolution of living organisms and for biotechnological applications. ProfileView is a sequence-based computational method, designed to functionally classify sets of homologous sequences. It relies on two main ideas: the use of multiple profile models whose construction explores evolutionary information in available databases, and a novel definition of a representation space in which to analyze sequences with multiple profile models combined together. ProfileView classifies protein families by enriching known functional groups with new sequences and discovering new groups and subgroups. We validate ProfileView on seven classes of widespread proteins involved in the interaction with nucleic acids, amino acids and small molecules, and in a large variety of functions and enzymatic reactions. ProfileView agrees with the large set of functional data collected for these proteins from the literature regarding the organization into functional subgroups and residues that characterize the functions. In addition, ProfileView resolves undefined functional classifications and extracts the molecular determinants underlying protein functional diversity, showing its potential to select sequences towards accurate experimental design and discovery of novel biological functions. On protein families with complex domain architecture, ProfileView functional classification reconciles domain combinations, unlike phylogenetic reconstruction. ProfileView proves to outperform the functional classification approach PANTHER, the two k-mer-based methods CUPP and eCAMI and a neural network approach based on Restricted Boltzmann Machines. It overcomes time complexity limitations of the latter.