Guiding questions to avoid data leakage in biological machine learning applications

Machine learning methods for extracting patterns from high-dimensional data are very important in the biological sciences. However, in certain cases, real-world applications cannot confirm the reported prediction performance. One of the main reasons for this is data leakage, which can be seen as the illicit sharing of information between the training data and the test data, resulting in performance estimates that are far better than the performance observed in the intended application scenario. Data leakage can be difficult to detect in biological datasets due to their complex dependencies. With this in mind, we present seven questions that should be asked to prevent data leakage when constructing machine learning models in biological domains. We illustrate the usefulness of our questions by applying them to nontrivial examples. Our goal is to raise awareness of potential data leakage problems and to promote robust and reproducible machine learning-based research in biology.

SENSE-PPI reconstructs interactomes within, across, and between species at the genome scale

Ab initio computational reconstructions of protein-protein interaction (PPI) networks will provide invaluable insights into cellular systems, enabling the discovery of novel molecular interactions and elucidating biological mechanisms within and between organisms. Leveraging the latest generation protein language models and recurrent neural networks, we present SENSE-PPI, a sequence-based deep learning model that efficiently reconstructs ab initio PPIs, distinguishing partners among tens of thousands of proteins and identifying specific interactions within functionally similar proteins. SENSE-PPI demonstrates high accuracy, limited training requirements, and versatility in cross-species predictions, even with non-model organisms and human-virus interactions. Its performance decreases for phylogenetically more distant model and non-model organisms, but signal alteration is very slow. In this regard, it demonstrates the important role of parameters in protein language models. SENSE-PPI is very fast and can test 10,000 proteins against themselves in a matter of hours, enabling the reconstruction of genome-wide proteomes.

Leveraging machine learning models for peptide-protein interaction prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as docking and molecular dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

Computational Approaches to Predict Protein-Protein Interactions in Crowded Cellular Environments

Investigating protein-protein interactions is crucial for understanding cellular biological processes because proteins often function within molecular complexes rather than in isolation. While experimental and computational methods have provided valuable insights into these interactions, they often overlook a critical factor: the crowded cellular environment. This environment significantly impacts protein behavior, including structural stability, diffusion, and ultimately the nature of binding. In this review, we discuss theoretical and computational approaches that allow the modeling of biological systems to guide and complement experiments and can thus significantly advance the investigation, and possibly the predictions, of protein-protein interactions in the crowded environment of cell cytoplasm. We explore topics such as statistical mechanics for lattice simulations, hydrodynamic interactions, diffusion processes in high-viscosity environments, and several methods based on molecular dynamics simulations. By synergistically leveraging methods from biophysics and computational biology, we review the state of the art of computational methods to study the impact of molecular crowding on protein-protein interactions and discuss its potential revolutionizing effects on the characterization of the human interactome.

Cracking the black box of deep sequence-based protein-protein interaction prediction

Identifying protein-protein interactions (PPIs) is crucial for deciphering biological pathways. Numerous prediction methods have been developed as cheap alternatives to biological experiments, reporting surprisingly high accuracy estimates. We systematically investigated how much reproducible deep learning models depend on data leakage, sequence similarities and node degree information, and compared them with basic machine learning models. We found that overlaps between training and test sets resulting from random splitting lead to strongly overestimated performances. In this setting, models learn solely from sequence similarities and node degrees. When data leakage is avoided by minimizing sequence similarities between training and test set, performances become random. Moreover, baseline models directly leveraging sequence similarity and network topology show good performances at a fraction of the computational cost. Thus, we advocate that any improvements should be reported relative to baseline methods in the future. Our findings suggest that predicting PPIs remains an unsolved task for proteins showing little sequence similarity to previously studied proteins, highlighting that further experimental research into the 'dark' protein interactome and better computational methods are needed.

Multi-modal features-based human-herpesvirus protein-protein interaction prediction by using LightGBM

The identification of human-herpesvirus protein-protein interactions (PPIs) is an essential and important entry point to understand the mechanisms of viral infection, especially in malignant tumor patients with common herpesvirus infection. While natural language processing (NLP)-based embedding techniques have emerged as powerful approaches, the application of multi-modal embedding feature fusion to predict human-herpesvirus PPIs is still limited. Here, we established a multi-modal embedding feature fusion-based LightGBM method to predict human-herpesvirus PPIs. In particular, we applied document and graph embedding approaches to represent sequence, network and function modal features of human and herpesviral proteins. Training our LightGBM models through our compiled non-rigorous and rigorous benchmarking datasets, we obtained significantly better performance compared to individual-modal features. Furthermore, our model outperformed traditional feature encodings-based machine learning methods and state-of-the-art deep learning-based methods using various benchmarking datasets. In a transfer learning step, we show that our model that was trained on human-herpesvirus PPI dataset without cytomegalovirus data can reliably predict human-cytomegalovirus PPIs, indicating that our method can comprehensively capture multi-modal fusion features of protein interactions across various herpesvirus subtypes. The implementation of our method is available at https://github.com/XiaodiYangpku/MultimodalPPI/.

State-of-the-art computational methods to predict protein-protein interactions with high accuracy and coverage

Prediction of protein-protein interactions (PPIs) commonly involves a significant computational component. Rapid recent advances in the power of computational methods for protein interaction prediction motivate a review of the state-of-the-art. We review the major approaches, organized according to the primary source of data utilized: protein sequence, protein structure, and protein co-abundance. The advent of deep learning (DL) has brought with it significant advances in interaction prediction, and we show how DL is used for each source data type. We review the literature taxonomically, present example case studies in each category, and conclude with observations about the strengths and weaknesses of machine learning methods in the context of the principal sources of data for protein interaction prediction.

Prediction of the interaction between Calloselasma rhodostoma venom-derived peptides and cancer-associated hub proteins: A computational study

The use of peptide drugs to treat cancer is gaining popularity because of their efficacy, fewer side effects, and several advantages over other properties. Identifying the peptides that interact with cancer proteins is crucial in drug discovery. Several approaches related to predicting peptide-protein interactions have been conducted. However, problems arise due to the high costs of resources and time and the smaller number of studies. This study predicts peptide-protein interactions using Random Forest, XGBoost, and SAE-DNN. Feature extraction is also performed on proteins and peptides using intrinsic disorder, amino acid sequences, physicochemical properties, position-specific assessment matrices, amino acid composition, and dipeptide composition. Results show that all algorithms perform equally well in predicting interactions between peptides derived from venoms and target proteins associated with cancer. However, XGBoost produces the best results with accuracy, precision, and area under the receiver operating characteristic curve of 0.859, 0.663, and 0.697, respectively. The enrichment analysis revealed that peptides from the Calloselasma rhodostoma venom targeted several proteins (ESR1, GOPC, and BRD4) related to cancer.

HNSPPI: a hybrid computational model combing network and sequence information for predicting protein-protein interaction

Most life activities in organisms are regulated through protein complexes, which are mainly controlled via Protein-Protein Interactions (PPIs). Discovering new interactions between proteins and revealing their biological functions are of great significance for understanding the molecular mechanisms of biological processes and identifying the potential targets in drug discovery. Current experimental methods only capture stable protein interactions, which lead to limited coverage. In addition, expensive cost and time consuming are also the obvious shortcomings. In recent years, various computational methods have been successfully developed for predicting PPIs based only on protein homology, primary sequences of protein or gene ontology information. Computational efficiency and data complexity are still the main bottlenecks for the algorithm generalization. In this study, we proposed a novel computational framework, HNSPPI, to predict PPIs. As a hybrid supervised learning model, HNSPPI comprehensively characterizes the intrinsic relationship between two proteins by integrating amino acid sequence information and connection properties of PPI network. The experimental results show that HNSPPI works very well on six benchmark datasets. Moreover, the comparison analysis proved that our model significantly outperforms other five existing algorithms. Finally, we used the HNSPPI model to explore the SARS-CoV-2-Human interaction system and found several potential regulations. In summary, HNSPPI is a promising model for predicting new protein interactions from known PPI data.

SGPPI: structure-aware prediction of protein-protein interactions in rigorous conditions with graph convolutional network

While deep learning (DL)-based models have emerged as powerful approaches to predict protein-protein interactions (PPIs), the reliance on explicit similarity measures (e.g. sequence similarity and network neighborhood) to known interacting proteins makes these methods ineffective in dealing with novel proteins. The advent of AlphaFold2 presents a significant opportunity and also a challenge to predict PPIs in a straightforward way based on monomer structures while controlling bias from protein sequences. In this work, we established Structure and Graph-based Predictions of Protein Interactions (SGPPI), a structure-based DL framework for predicting PPIs, using the graph convolutional network. In particular, SGPPI focused on protein patches on the protein-protein binding interfaces and extracted the structural, geometric and evolutionary features from the residue contact map to predict PPIs. We demonstrated that our model outperforms traditional machine learning methods and state-of-the-art DL-based methods using non-representation-bias benchmark datasets. Moreover, our model trained on human dataset can be reliably transferred to predict yeast PPIs, indicating that SGPPI can capture converging structural features of protein interactions across various species. The implementation of SGPPI is available at https://github.com/emerson106/SGPPI.

MM-StackEns: A new deep multimodal stacked generalization approach for protein-protein interaction prediction

Accurate in-silico identification of protein-protein interactions (PPIs) is a long-standing problem in biology, with important implications in protein function prediction and drug design. Current computational approaches predominantly use a single data modality for describing protein pairs, which may not fully capture the characteristics relevant for identifying PPIs. Another limitation of existing methods is their poor generalization to proteins outside the training graph. In this paper, we aim to address these shortcomings by proposing a new ensemble approach for PPI prediction, which learns information from two modalities, corresponding to pairs of sequences and to the graph formed by the training proteins and their interactions. Our approach uses a siamese neural network to process sequence information, while graph attention networks are employed for the network view. For capturing the relationships between the proteins in a pair, we design a new feature fusion module, based on computing the distance between the distributions corresponding to the two proteins. The prediction is made using a stacked generalization procedure, in which the final classifier is represented by a Logistic Regression model trained on the scores predicted by the sequence and graph models. Additionally, we show that protein sequence embeddings obtained using pretrained language models can significantly improve the generalization of PPI methods. The experimental results demonstrate the good performance of our approach, which surpasses all the related work on two Yeast data sets, while outperforming the majority of literature approaches on two Human data sets and on independent multi-species data sets.

Growing ecosystem of deep learning methods for modeling protein-protein interactions

Numerous cellular functions rely on protein-protein interactions. Efforts to comprehensively characterize them remain challenged however by the diversity of molecular recognition mechanisms employed within the proteome. Deep learning has emerged as a promising approach for tackling this problem by exploiting both experimental data and basic biophysical knowledge about protein interactions. Here, we review the growing ecosystem of deep learning methods for modeling protein interactions, highlighting the diversity of these biophysically informed models and their respective trade-offs. We discuss recent successes in using representation learning to capture complex features pertinent to predicting protein interactions and interaction sites, geometric deep learning to reason over protein structures and predict complex structures, and generative modeling to design de novo protein assemblies. We also outline some of the outstanding challenges and promising new directions. Opportunities abound to discover novel interactions, elucidate their physical mechanisms, and engineer binders to modulate their functions using deep learning and, ultimately, unravel how protein interactions orchestrate complex cellular behaviors.

MARPPI: boosting prediction of protein-protein interactions with multi-scale architecture residual network

Protein-protein interactions (PPIs) are a major component of the cellular biochemical reaction network. Rich sequence information and machine learning techniques reduce the dependence of exploring PPIs on wet experiments, which are costly and time-consuming. This paper proposes a PPI prediction model, multi-scale architecture residual network for PPIs (MARPPI), based on dual-channel and multi-feature. Multi-feature leverages Res2vec to obtain the association information between residues, and utilizes pseudo amino acid composition, autocorrelation descriptors and multivariate mutual information to achieve the amino acid composition and order information, physicochemical properties and information entropy, respectively. Dual channel utilizes multi-scale architecture improved ResNet network which extracts protein sequence features to reduce protein feature loss. Compared with other advanced methods, MARPPI achieves 96.03%, 99.01% and 91.80% accuracy in the intraspecific datasets of Saccharomyces cerevisiae, Human and Helicobacter pylori, respectively. The accuracy on the two interspecific datasets of Human-Bacillus anthracis and Human-Yersinia pestis is 97.29%, and 95.30%, respectively. In addition, results on specific datasets of disease (neurodegenerative and metabolic disorders) demonstrate the ability to detect hidden interactions. To better illustrate the performance of MARPPI, evaluations on independent datasets and PPIs network suggest that MARPPI can be used to predict cross-species interactions. The above shows that MARPPI can be regarded as a concise, efficient and accurate tool for PPI datasets.

Transformer Neural Networks for Protein Family and Interaction Prediction Tasks

The scientific community is rapidly generating protein sequence information, but only a fraction of these proteins can be experimentally characterized. While promising deep learning approaches for protein prediction tasks have emerged, they have computational limitations or are designed to solve a specific task. We present a Transformer neural network that pre-trains task-agnostic sequence representations. This model is fine-tuned to solve two different protein prediction tasks: protein family classification and protein interaction prediction. Our method is comparable to existing state-of-the-art approaches for protein family classification while being much more general than other architectures. Further, our method outperforms other approaches for protein interaction prediction for two out of three different scenarios that we generated. These results offer a promising framework for fine-tuning the pre-trained sequence representations for other protein prediction tasks.

A correlation coefficient-based feature selection approach for virus-host protein-protein interaction prediction

Prediction of virus-host protein-protein interactions (PPI) is a broad research area where various machine-learning-based classifiers are developed. Transforming biological data into machine-usable features is a preliminary step in constructing these virus-host PPI prediction tools. In this study, we have adopted a virus-host PPI dataset and a reduced amino acids alphabet to create tripeptide features and introduced a correlation coefficient-based feature selection. We applied feature selection across several correlation coefficient metrics and statistically tested their relevance in a structural context. We compared the performance of feature-selection models against that of the baseline virus-host PPI prediction models created using different classification algorithms without the feature selection. We also tested the performance of these baseline models against the previously available tools to ensure their predictive power is acceptable. Here, the Pearson coefficient provides the best performance with respect to the baseline model as measured by AUPR; a drop of 0.003 in AUPR while achieving a 73.3% (from 686 to 183) reduction in the number of tripeptides features for random forest. The results suggest our correlation coefficient-based feature selection approach, while decreasing the computation time and space complexity, has a limited impact on the prediction performance of virus-host PPI prediction tools.

Machine Learning Methods for Virus-Host Protein-Protein Interaction Prediction

The attachment of a virion to a respective cellular receptor on the host organism occurring through the virus-host protein-protein interactions (PPIs) is a decisive step for viral pathogenicity and infectivity. Therefore, a vast number of wet-lab experimental techniques are used to study virus-host PPIs. Taking the great number and enormous variety of virus-host PPIs and the cost as well as labor of laboratory work, however, computational approaches toward analyzing the available interaction data and predicting previously unidentified interactions have been on the rise. Among them, machine-learning-based models are getting increasingly more attention with a great body of resources and tools proposed recently.In this chapter, we first provide the methodology with major steps toward the development of a virus-host PPI prediction tool. Next, we discuss the challenges involved and evaluate several existing machine-learning-based virus-host PPI prediction tools. Finally, we describe our experience with several ensemble techniques as utilized on available prediction results retrieved from individual PPI prediction tools. Overall, based on our experience, we recognize there is still room for the development of new individual and/or ensemble virus-host PPI prediction tools that leverage existing tools.

Recent developments of sequence-based prediction of protein-protein interactions

The identification of protein-protein interactions (PPIs) can lead to a better understanding of cellular functions and biological processes of proteins and contribute to the design of drugs to target disease-causing PPIs. In addition, targeting host-pathogen PPIs is useful for elucidating infection mechanisms. Although several experimental methods have been used to identify PPIs, these methods can yet to draw complete PPI networks. Hence, computational techniques are increasingly required for the prediction of potential PPIs, which have never been seen experimentally. Recent high-performance sequence-based methods have contributed to the construction of PPI networks and the elucidation of pathogenetic mechanisms in specific diseases. However, the usefulness of these methods depends on the quality and quantity of training data of PPIs. In this brief review, we introduce currently available PPI databases and recent sequence-based methods for predicting PPIs. Also, we discuss key issues in this field and present future perspectives of the sequence-based PPI predictions.

On the choice of negative examples for prediction of host-pathogen protein interactions

As practitioners of machine learning in the area of bioinformatics we know that the quality of the results crucially depends on the quality of our labeled data. While there is a tendency to focus on the quality of positive examples, the negative examples are equally as important. In this opinion paper we revisit the problem of choosing negative examples for the task of predicting protein-protein interactions, either among proteins of a given species or for host-pathogen interactions and describe important issues that are prevalent in the current literature. The challenge in creating datasets for this task is the noisy nature of the experimentally derived interactions and the lack of information on non-interacting proteins. A standard approach is to choose random pairs of non-interacting proteins as negative examples. Since the interactomes of all species are only partially known, this leads to a very small percentage of false negatives. This is especially true for host-pathogen interactions. To address this perceived issue, some researchers have chosen to select negative examples as pairs of proteins whose sequence similarity to the positive examples is sufficiently low. This clearly reduces the chance for false negatives, but also makes the problem much easier than it really is, leading to over-optimistic accuracy estimates. We demonstrate the effect of this form of bias using a selection of recent protein interaction prediction methods of varying complexity, and urge researchers to pay attention to the details of generating their datasets for potential biases like this.

PPI-Miner: A Structure and Sequence Motif Co-Driven Protein-Protein Interaction Mining and Modeling Computational Method

Protein-protein interactions (PPIs) play important roles in biological processes of life, and predicting PPIs becomes a critical scientific issue of concern. Most PPIs occur through small domains or motifs (fragments), which are challenging and laborious to map by standard biochemical approaches because they generally require the cloning of several truncation mutants. Here, we present a computational method, named as PPI-Miner, to fish potential protein interacting partners utilizing protein motifs as queries. In brief, this work first developed a motif-matching algorithm designed to identify the proteins that contain sequential or structural similar motifs with the given query motif. Being aligned to the query motif, the binding mode of the discovered motif and its receptor protein will be initially determined to be used to build PPI complexes accordingly. Eventually, a PPI complex structure could be built and optimized with a designed automatic protocol. Besides discovering PPIs, PPI-Miner can also be applied to other areas, i.e., the rational design of molecular glues and protein vaccines. In this work, PPI-Miner was employed to mine the potential cereblon (CRBN) substrates from human proteome. As a result, 1,739 candidates were predicted, and 16 of them have been experimentally validated in previous studies. The source code of PPI-Miner can be obtained from the GitHub repository (https://github.com/Wang-Lin-boop/PPI-Miner), the webserver is freely available for users (https://bailab.siais.shanghaitech.edu.cn/services/ppi-miner), and the database of predicted CRBN substrates is accessible at https://bailab.siais.shanghaitech.edu.cn/services/crbn-subslib.

Protein-protein interaction prediction with deep learning: A comprehensive review

Most proteins perform their biological function by interacting with themselves or other molecules. Thus, one may obtain biological insights into protein functions, disease prevalence, and therapy development by identifying protein-protein interactions (PPI). However, finding the interacting and non-interacting protein pairs through experimental approaches is labour-intensive and time-consuming, owing to the variety of proteins. Hence, protein-protein interaction and protein-ligand binding problems have drawn attention in the fields of bioinformatics and computer-aided drug discovery. Deep learning methods paved the way for scientists to predict the 3-D structure of proteins from genomes, predict the functions and attributes of a protein, and modify and design new proteins to provide desired functions. This review focuses on recent deep learning methods applied to problems including predicting protein functions, protein-protein interaction and their sites, protein-ligand binding, and protein design.

ProteinPrompt: a webserver for predicting protein-protein interactions

Motivation

Protein-protein interactions (PPIs) play an essential role in a great variety of cellular processes and are therefore of significant interest for the design of new therapeutic compounds as well as the identification of side effects due to unexpected binding. Here, we present ProteinPrompt, a webserver that uses machine learning algorithms to calculate specific, currently unknown PPIs. Our tool is designed to quickly and reliably predict contact propensities based on an input sequence in order to scan large sequence libraries for potential binding partners, with the goal to accelerate and assure the quality of the laborious process of drug target identification.

Results

We collected and thoroughly filtered a comprehensive database of known binders from several sources, which is available as download. ProteinPrompt provides two complementary search methods of similar accuracy for comparison and consensus building. The default method is a random forest (RF) algorithm that uses the auto-correlations of seven amino acid scales. Alternatively, a graph neural network (GNN) implementation can be selected. Additionally, a consensus prediction is available. For each query sequence, potential binding partners are identified from a protein sequence database. The proteom of several organisms are available and can be searched for binders. To evaluate the predictive power of the algorithms, we prepared a test dataset that was rigorously filtered for redundancy. No sequence pairs similar to the ones used for training were included in this dataset. With this challenging dataset, the RF method achieved an accuracy rate of 0.88 and an area under the curve of 0.95. The GNN achieved an accuracy rate of 0.86 using the same dataset. Since the underlying learning approaches are unrelated, comparing the results of RF and GNNs reduces the likelihood of errors. The consensus reached an accuracy of 0.89.

Availability and implementation

ProteinPrompt is available online at: http://proteinformatics.org/ProteinPrompt, where training and test data used to optimize the methods are also available. The server makes it possible to scan the human proteome for potential binding partners of an input sequence within minutes. For local offline usage, we furthermore created a ProteinPrompt Docker image which allows for batch submission: https://gitlab.hzdr.de/proteinprompt/ProteinPrompt. In conclusion, we offer a fast, accurate, easy-to-use online service for predicting binding partners from an input sequence.

Protein-protein interaction and non-interaction predictions using gene sequence natural vector

Predicting protein–protein interaction and non-interaction are two important different aspects of multi-body structure predictions, which provide vital information about protein function. Some computational methods have recently been developed to complement experimental methods, but still cannot effectively detect real non-interacting protein pairs. We proposed a gene sequence-based method, named NVDT (Natural Vector combine with Dinucleotide and Triplet nucleotide), for the prediction of interaction and non-interaction. For protein–protein non-interactions (PPNIs), the proposed method obtained accuracies of 86.23% for Homo sapiens and 85.34% for Mus musculus, and it performed well on three types of non-interaction networks. For protein-protein interactions (PPIs), we obtained accuracies of 99.20, 94.94, 98.56, 95.41, and 94.83% for Saccharomyces cerevisiae, Drosophila melanogaster, Helicobacter pylori, Homo sapiens, and Mus musculus, respectively. Furthermore, NVDT outperformed established sequence-based methods and demonstrated high prediction results for cross-species interactions. NVDT is expected to be an effective approach for predicting PPIs and PPNIs.

Protein-protein non-interactions and interactions are distinguished and predicted by gene sequence using single nucleotide and contiguous nucleotides combined with machine learning models.

A Survey on Deep Networks Approaches in Prediction of Sequence-Based Protein–Protein Interactions

The prominence of protein–protein interactions (PPIs) in system biology with diverse biological procedures has become the topic to discuss because it acts as a fundamental part in predicting the protein function of the target protein and drug ability of molecules. Numerous researches have been published to predict PPIs computationally because they provide an alternative solution to laboratory trials and a cost-effective way of predicting the most likely set of interactions at the entire proteome scale. In recent computational methods, deep learning has become a buzzword with numerous scientific researches. This paper presents, for the first time, a comprehensive survey of sequence-based PPI prediction by three popular deep learning architectures i.e. deep neural networks, convolutional neural networks and recurrent neural networks and its variants. The thorough survey discussed herein carefully mined every possible information, can help the researchers to further explore the success in this area.

JUPPI: A Multi-Level Feature Based Method for PPI Prediction and a Refined Strategy for Performance Assessment

Over the years, several methods have been proposed for the computational PPI prediction with different performance evaluation strategies. While attempting to benchmark performance scores, most of these methods often suffer with ill-treated cross-validation strategies, adhoc selection of positive/negative samples etc. To address these issues, in our proposed multi-level feature based PPI prediction approach (JUPPI), using sequence, domain and GO information as features, a refined evaluation strategy has been introduced. During the evaluation process, we first extract high quality negative data using three-stage filtering, and then introduce a pair-input based cross validation strategy with three difficulty levels for test-set predictions. Our proposed evaluation strategy reduces the component-level overlapping issue in test sets. Performance of JUPPI is compared with those of the state-of-the-art approaches in this domain and tested on six independent PPI datasets. In almost all the datasets, JUPPI outperforms the state-of-the-art not only at human proteome level for PPI prediction, but also for prediction of interactors for intrinsic disordered human proteins. https://figshare.com/projects/JUPPI_A_Multi-level_Feature_Based_Method_for_PPI_Prediction_and_a_Refined_Strategy_for_Performance_Assessment/81656 JUPPI tool and the developed datasets (JUPPId) are available in public domain for academic use along with supplementary materials, which can be found on the Computer Society Digital Library at http://doi.ieeecomputersociety.org/10.1109/TCBB.2020.3004970.

From complete cross-docking to partners identification and binding sites predictions

Proteins ensure their biological functions by interacting with each other. Hence, characterising protein interactions is fundamental for our understanding of the cellular machinery, and for improving medicine and bioengineering. Over the past years, a large body of experimental data has been accumulated on who interacts with whom and in what manner. However, these data are highly heterogeneous and sometimes contradictory, noisy, and biased. Ab initio methods provide a means to a "blind" protein-protein interaction network reconstruction. Here, we report on a molecular cross-docking-based approach for the identification of protein partners. The docking algorithm uses a coarse-grained representation of the protein structures and treats them as rigid bodies. We applied the approach to a few hundred of proteins, in the unbound conformations, and we systematically investigated the influence of several key ingredients, such as the size and quality of the interfaces, and the scoring function. We achieved some significant improvement compared to previous works, and a very high discriminative power on some specific functional classes. We provide a readout of the contributions of shape and physico-chemical complementarity, interface matching, and specificity, in the predictions. In addition, we assessed the ability of the approach to account for protein surface multiple usages, and we compared it with a sequence-based deep learning method. This work may contribute to guiding the exploitation of the large amounts of protein structural models now available toward the discovery of unexpected partners and their complex structure characterisation.

LSTM-PHV: prediction of human-virus protein-protein interactions by LSTM with word2vec

Viral infection involves a large number of protein-protein interactions (PPIs) between human and virus. The PPIs range from the initial binding of viral coat proteins to host membrane receptors to the hijacking of host transcription machinery. However, few interspecies PPIs have been identified, because experimental methods including mass spectrometry are time-consuming and expensive, and molecular dynamic simulation is limited only to the proteins whose 3D structures are solved. Sequence-based machine learning methods are expected to overcome these problems. We have first developed the LSTM model with word2vec to predict PPIs between human and virus, named LSTM-PHV, by using amino acid sequences alone. The LSTM-PHV effectively learnt the training data with a highly imbalanced ratio of positive to negative samples and achieved AUCs of 0.976 and 0.973 and accuracies of 0.984 and 0.985 on the training and independent datasets, respectively. In predicting PPIs between human and unknown or new virus, the LSTM-PHV learned greatly outperformed the existing state-of-the-art PPI predictors. Interestingly, learning of only sequence contexts as words is sufficient for PPI prediction. Use of uniform manifold approximation and projection demonstrated that the LSTM-PHV clearly distinguished the positive PPI samples from the negative ones. We presented the LSTM-PHV online web server and support data that are freely available at http://kurata35.bio.kyutech.ac.jp/LSTM-PHV.

A deep-learning framework for multi-level peptide-protein interaction prediction

Peptide-protein interactions are involved in various fundamental cellular functions and their identification is crucial for designing efficacious peptide therapeutics. Recently, a number of computational methods have been developed to predict peptide-protein interactions. However, most of the existing prediction approaches heavily depend on high-resolution structure data. Here, we present a deep learning framework for multi-level peptide-protein interaction prediction, called CAMP, including binary peptide-protein interaction prediction and corresponding peptide binding residue identification. Comprehensive evaluation demonstrated that CAMP can successfully capture the binary interactions between peptides and proteins and identify the binding residues along the peptides involved in the interactions. In addition, CAMP outperformed other state-of-the-art methods on binary peptide-protein interaction prediction. CAMP can serve as a useful tool in peptide-protein interaction prediction and identification of important binding residues in the peptides, which can thus facilitate the peptide drug discovery process.

Transfer learning via multi-scale convolutional neural layers for human-virus protein-protein interaction prediction

Motivation

To complement experimental efforts, machine learning-based computational methods are playing an increasingly important role to predict human–virus protein–protein interactions (PPIs). Furthermore, transfer learning can effectively apply prior knowledge obtained from a large source dataset/task to a small target dataset/task, improving prediction performance.

Results

To predict interactions between human and viral proteins, we combine evolutionary sequence profile features with a Siamese convolutional neural network (CNN) architecture and a multi-layer perceptron. Our architecture outperforms various feature encodings-based machine learning and state-of-the-art prediction methods. As our main contribution, we introduce two transfer learning methods (i.e. ‘frozen’ type and ‘fine-tuning’ type) that reliably predict interactions in a target human–virus domain based on training in a source human–virus domain, by retraining CNN layers. Finally, we utilize the ‘frozen’ type transfer learning approach to predict human–SARS-CoV-2 PPIs, indicating that our predictions are topologically and functionally similar to experimentally known interactions.

Availability and implementation: The source codes and datasets are available at https://github.com/XiaodiYangCAU/TransPPI/.

Supplementary information

Supplementary data are available at Bioinformatics online.

PredictProtein - Predicting Protein Structure and Function for 29 Years

Since 1992 PredictProtein (https://predictprotein.org) is a one-stop online resource for protein sequence analysis with its main site hosted at the Luxembourg Centre for Systems Biomedicine (LCSB) and queried monthly by over 3,000 users in 2020. PredictProtein was the first Internet server for protein predictions. It pioneered combining evolutionary information and machine learning. Given a protein sequence as input, the server outputs multiple sequence alignments, predictions of protein structure in 1D and 2D (secondary structure, solvent accessibility, transmembrane segments, disordered regions, protein flexibility, and disulfide bridges) and predictions of protein function (functional effects of sequence variation or point mutations, Gene Ontology (GO) terms, subcellular localization, and protein-, RNA-, and DNA binding). PredictProtein's infrastructure has moved to the LCSB increasing throughput; the use of MMseqs2 sequence search reduced runtime five-fold (apparently without lowering performance of prediction methods); user interface elements improved usability, and new prediction methods were added. PredictProtein recently included predictions from deep learning embeddings (GO and secondary structure) and a method for the prediction of proteins and residues binding DNA, RNA, or other proteins. PredictProtein.org aspires to provide reliable predictions to computational and experimental biologists alike. All scripts and methods are freely available for offline execution in high-throughput settings.

Predicting Protein-Protein Interactions via Gated Graph Attention Signed Network

Protein-protein interactions (PPIs) play a key role in signal transduction and pharmacogenomics, and hence, accurate PPI prediction is crucial. Graph structures have received increasing attention owing to their outstanding performance in machine learning. In practice, PPIs can be expressed as a signed network (i.e., graph structure), wherein the nodes in the network represent proteins, and edges represent the interactions (positive or negative effects) of protein nodes. PPI predictions can be realized by predicting the links of the signed network; therefore, the use of gated graph attention for signed networks (SN-GGAT) is proposed herein. First, the concept of graph attention network (GAT) is applied to signed networks, in which "attention" represents the weight of neighbor nodes, and GAT updates the node features through the weighted aggregation of neighbor nodes. Then, the gating mechanism is defined and combined with the balance theory to obtain the high-order relations of protein nodes to improve the attention effect, making the attention mechanism follow the principle of "low-order high attention, high-order low attention, different signs opposite". PPIs are subsequently predicted on the Saccharomyces cerevisiae core dataset and the Human dataset. The test results demonstrate that the proposed method exhibits strong competitiveness.

Predicting Protein-Protein Interactions Using Symmetric Logistic Matrix Factorization

Accurate assessment of protein-protein interactions (PPIs) is critical to deciphering disease mechanisms and developing novel drugs, and with rapidly growing PPI data, the need for more efficient predictive methods is emerging. We propose here a symmetric logistic matrix factorization (symLMF)-based approach to predict PPIs, especially useful for large PPI networks. Benchmarked against two widely used datasets (Saccharomyces cerevisiae and Homo sapiens benchmarks) and their extended versions, the symLMF-based method proves to outperform most of the state-of-the-art data-driven methods applied to human PPIs, and it shows a performance comparable to those of deep learning methods despite its conceptual and technical simplicity and efficiency. Tests performed on humans, yeast, and tissue (brain and liver)- and disease (neurodegenerative and metabolic disorders)-specific datasets further demonstrate the high capability to capture the hidden interactions. Notably, many "de novo predictions" made by symLMF are verified to exist in PPI databases other than those used for training/testing the method, indicating that the method could be of broad utility as a simple, yet efficient and accurate, tool applicable to PPI datasets.

Systematic auditing is essential to debiasing machine learning in biology

Biases in data used to train machine learning (ML) models can inflate their prediction performance and confound our understanding of how and what they learn. Although biases are common in biological data, systematic auditing of ML models to identify and eliminate these biases is not a common practice when applying ML in the life sciences. Here we devise a systematic, principled, and general approach to audit ML models in the life sciences. We use this auditing framework to examine biases in three ML applications of therapeutic interest and identify unrecognized biases that hinder the ML process and result in substantially reduced model performance on new datasets. Ultimately, we show that ML models tend to learn primarily from data biases when there is insufficient signal in the data to learn from. We provide detailed protocols, guidelines, and examples of code to enable tailoring of the auditing framework to other biomedical applications.

Fatma-Elzahraa Eid et al. illustrate a principled approach for identifying biases that can inflate the performance of biological machine learning models. When applied to three biomedical prediction problems, they identify previously unrecognized biases and ultimately show that models are likely to learn primarily from data biases when there is insufficient learnable signal in the data.

Delayed Comparison and Apriori Algorithm (DCAA): A Tool for Discovering Protein-Protein Interactions From Time-Series Phosphoproteomic Data

Analysis of high-throughput omics data is one of the most important approaches for obtaining information regarding interactions between proteins/genes. Time-series omics data are a series of omics data points indexed in time order and normally contain more abundant information about the interactions between biological macromolecules than static omics data. In addition, phosphorylation is a key posttranslational modification (PTM) that is indicative of possible protein function changes in cellular processes. Analysis of time-series phosphoproteomic data should provide more meaningful information about protein interactions. However, although many algorithms, databases, and websites have been developed to analyze omics data, the tools dedicated to discovering molecular interactions from time-series omics data, especially from time-series phosphoproteomic data, are still scarce. Moreover, most reported tools ignore the lag between functional alterations and the corresponding changes in protein synthesis/PTM and are highly dependent on previous knowledge, resulting in high false-positive rates and difficulties in finding newly discovered protein–protein interactions (PPIs). Therefore, in the present study, we developed a new method to discover protein–protein interactions with the delayed comparison and Apriori algorithm (DCAA) to address the aforementioned problems. DCAA is based on the idea that there is a lag between functional alterations and the corresponding changes in protein synthesis/PTM. The Apriori algorithm was used to mine association rules from the relationships between items in a dataset and find PPIs based on time-series phosphoproteomic data. The advantage of DCAA is that it does not rely on previous knowledge and the PPI database. The analysis of actual time-series phosphoproteomic data showed that more than 68% of the protein interactions/regulatory relationships predicted by DCAA were accurate. As an analytical tool for PPIs that does not rely on a priori knowledge, DCAA should be useful to predict PPIs from time-series omics data, and this approach is not limited to phosphoproteomic data.

Combining sequence and network information to enhance protein-protein interaction prediction

Background

Protein–protein interactions (PPIs) are of great importance in cellular systems of organisms, since they are the basis of cellular structure and function and many essential cellular processes are related to that. Most proteins perform their functions by interacting with other proteins, so predicting PPIs accurately is crucial for understanding cell physiology.

Results

Recently, graph convolutional networks (GCNs) have been proposed to capture the graph structure information and generate representations for nodes in the graph. In our paper, we use GCNs to learn the position information of proteins in the PPIs networks graph, which can reflect the properties of proteins to some extent. Combining amino acid sequence information and position information makes a stronger representation for protein, which improves the accuracy of PPIs prediction.

Conclusion

In previous research methods, most of them only used protein amino acid sequence as input information to make predictions, without considering the structural information of PPIs networks graph. We first time combine amino acid sequence information and position information to make representations for proteins. The experimental results indicate that our method has strong competitiveness compared with several sequence-based methods.

Analysis of Protein-Protein Interaction Networks through Computational Approaches

The interactions among proteins and genes are extremely important for cellular functions. Molecular interactions at protein or gene levels can be used to construct interaction networks in which the interacting species are categorized based on direct interactions or functional similarities. Compared with the limited experimental techniques, various computational tools make it possible to analyze, filter, and combine the interaction data to get comprehensive information about the biological pathways. By the efficient way of integrating experimental findings in discovering PPIs and computational techniques for prediction, the researchers have been able to gain many valuable data on PPIs, including some advanced databases. Moreover, many useful tools and visualization programs enable the researchers to establish, annotate, and analyze biological networks. We here review and list the computational methods, databases, and tools for protein-protein interaction prediction.

Evolution of Sequence-based Bioinformatics Tools for Protein-protein Interaction Prediction

Protein-protein interactions (PPIs) are the physical connections between two or more proteins via electrostatic forces or hydrophobic effects. Identification of the PPIs is pivotal, which contributes to many biological processes including protein function, disease incidence, and therapy design. The experimental identification of PPIs via high-throughput technology is time-consuming and expensive. Bioinformatics approaches are expected to solve such restrictions. In this review, our main goal is to provide an inclusive view of the existing sequence-based computational prediction of PPIs. Initially, we briefly introduce the currently available PPI databases and then review the state-of-the-art bioinformatics approaches, working principles, and their performances. Finally, we discuss the caveats and future perspective of the next generation algorithms for the prediction of PPIs.

Identification of novel candidate genes in heterotaxy syndrome patients with congenital heart diseases by whole exome sequencing

Heterotaxy syndrome (HS) involves dysfunction of multiple systems resulting from abnormal left-right (LR) body patterning. Most HS patients present with complex congenital heart diseases (CHD), the disability and mortality of HS patients are extremely high. HS has great heterogeneity in phenotypes and genotypes, which have rendered gene discovery challenging. The aim of this study was to identify novel genes that underlie pathogenesis of HS patients with CHD. Whole exome sequencing was performed in 25 unrelated HS cases and 100 healthy controls; 19 nonsynonymous variants in 6 novel candidate genes (FLNA, ITGA1, PCNT, KIF7, GLI1, KMT2D) were identified. The functions of candidate genes were further analyzed in zebrafish model by CRISPR/Cas9 technique. Genome-editing was successfully introduced into the gene loci of flna, kmt2d and kif7, but the phenotypes were heterogenous. Disruption of each gene disturbed normal cardiac looping while kif7 knockout had a more prominent effect on liver budding and pitx2 expression. Our results revealed three potential HS pathogenic genes with probably different molecular mechanisms.

Advancing from protein interactomes and gene co-expression networks towards multi-omics-based composite networks: approaches for predicting and extracting biological knowledge

Prediction of biological interaction networks from single-omics data has been extensively implemented to understand various aspects of biological systems. However, more recently, there is a growing interest in integrating multi-omics datasets for the prediction of interactomes that provide a global view of biological systems with higher descriptive capability, as compared to single omics. In this review, we have discussed various computational approaches implemented to infer and analyze two of the most important and well studied interactomes: protein-protein interaction networks and gene co-expression networks. We have explicitly focused on recent methods and pipelines implemented to infer and extract biologically important information from these interactomes, starting from utilizing single-omics data and then progressing towards multi-omics data. Accordingly, recent examples and case studies are also briefly discussed. Overall, this review will provide a proper understanding of the latest developments in protein and gene network modelling and will also help in extracting practical knowledge from them.

ProNA2020 predicts protein-DNA, protein-RNA, and protein-protein binding proteins and residues from sequence

The intricate details of how proteins bind to proteins, DNA, and RNA are crucial for the understanding of almost all biological processes. Disease-causing sequence variants often affect binding residues. Here, we described a new, comprehensive system of in silico methods that take only protein sequence as input to predict binding of protein to DNA, RNA, and other proteins. Firstly, we needed to develop several new methods to predict whether or not proteins bind (per-protein prediction). Secondly, we developed independent methods that predict which residues bind (per-residue). Not requiring three-dimensional information, the system can predict the actual binding residue. The system combined homology-based inference with machine learning and motif-based profile-kernel approaches with word-based (ProtVec) solutions to machine learning protein level predictions. This achieved an overall non-exclusive three-state accuracy of 77% ± 1% (±one standard error) corresponding to a 1.8 fold improvement over random (best classification for protein-protein with F1 = 91 ± 0.8%). Standard neural networks for per-residue binding residue predictions appeared best for DNA-binding (Q2 = 81 ± 0.9%) followed by RNA-binding (Q2 = 80 ± 1%) and worst for protein-protein binding (Q2 = 69 ± 0.8%). The new method, dubbed ProNA2020, is available as code through github (https://github.com/Rostlab/ProNA2020.git) and through PredictProtein (www.predictprotein.org).

Predicting Protein-Protein Interactions Using SPRINT

Understanding protein-protein interactions (PPIs) is vital to reveal the function mechanisms in cells. Thus, predicting and identifying PPIs is one of the fundamental problems in system biology. Various high-throughput experimental and computation methods have been developed to predict PPIs. Here, we provide a straightforward guide of using the program "SPRINT" to predict the PPIs on an interactome level in an organism. First, some installation guides and input file formats are described. Then, the commands and options to run SPRINT are discussed with examples. In addition, some notes on possible extended installation and usage of SPRINT are given.

Identification of self-interacting proteins by integrating random projection classifier and finite impulse response filter

Background

Identification of protein-protein interactions (PPIs) is crucial for understanding biological processes and investigating the cellular functions of genes. Self-interacting proteins (SIPs) are those in which more than two identical proteins can interact with each other and they are the specific type of PPIs. More and more researchers draw attention to the SIPs detection, and several prediction model have been proposed, but there are still some problems. Hence, there is an urgent need to explore a efficient computational model for SIPs prediction.

Results

In this study, we developed an effective model to predict SIPs, called RP-FIRF, which merges the Random Projection (RP) classifier and Finite Impulse Response Filter (FIRF) together. More specifically, each protein sequence was firstly transformed into the Position Specific Scoring Matrix (PSSM) by exploiting Position Specific Iterated BLAST (PSI-BLAST). Then, to effectively extract the discriminary SIPs feature to improve the performance of SIPs prediction, a FIRF method was used on PSSM. The R’classifier was proposed to execute the classification and predict novel SIPs. We evaluated the performance of the proposed RP-FIRF model and compared it with the state-of-the-art support vector machine (SVM) on human and yeast datasets, respectively. The proposed model can achieve high average accuracies of 97.89 and 97.35% using five-fold cross-validation. To further evaluate the high performance of the proposed method, we also compared it with other six exiting methods, the experimental results demonstrated that the capacity of our model surpass that of the other previous approaches.

Conclusion

Experimental results show that self-interacting proteins are accurately well-predicted by the proposed model on human and yeast datasets, respectively. It fully show that the proposed model can predict the SIPs effectively and sufficiently. Thus, RP-FIRF model is an automatic decision support method which should provide useful insights into the recognition of SIPs.

Modeling aspects of the language of life through transfer-learning protein sequences

BACKGROUND

Predicting protein function and structure from sequence is one important challenge for computational biology. For 26 years, most state-of-the-art approaches combined machine learning and evolutionary information. However, for some applications retrieving related proteins is becoming too time-consuming. Additionally, evolutionary information is less powerful for small families, e.g. for proteins from the Dark Proteome. Both these problems are addressed by the new methodology introduced here.

RESULTS

We introduced a novel way to represent protein sequences as continuous vectors (embeddings) by using the language model ELMo taken from natural language processing. By modeling protein sequences, ELMo effectively captured the biophysical properties of the language of life from unlabeled big data (UniRef50). We refer to these new embeddings as SeqVec (Sequence-to-Vector) and demonstrate their effectiveness by training simple neural networks for two different tasks. At the per-residue level, secondary structure (Q3 = 79% ± 1, Q8 = 68% ± 1) and regions with intrinsic disorder (MCC = 0.59 ± 0.03) were predicted significantly better than through one-hot encoding or through Word2vec-like approaches. At the per-protein level, subcellular localization was predicted in ten classes (Q10 = 68% ± 1) and membrane-bound were distinguished from water-soluble proteins (Q2 = 87% ± 1). Although SeqVec embeddings generated the best predictions from single sequences, no solution improved over the best existing method using evolutionary information. Nevertheless, our approach improved over some popular methods using evolutionary information and for some proteins even did beat the best. Thus, they prove to condense the underlying principles of protein sequences. Overall, the important novelty is speed: where the lightning-fast HHblits needed on average about two minutes to generate the evolutionary information for a target protein, SeqVec created embeddings on average in 0.03 s. As this speed-up is independent of the size of growing sequence databases, SeqVec provides a highly scalable approach for the analysis of big data in proteomics, i.e. microbiome or metaproteome analysis.

CONCLUSION

Transfer-learning succeeded to extract information from unlabeled sequence databases relevant for various protein prediction tasks. SeqVec modeled the language of life, namely the principles underlying protein sequences better than any features suggested by textbooks and prediction methods. The exception is evolutionary information, however, that information is not available on the level of a single sequence.

Predicting protein-protein interactions through sequence-based deep learning

Motivation

High-throughput experimental techniques have produced a large amount of protein-protein interaction (PPI) data, but their coverage is still low and the PPI data is also very noisy. Computational prediction of PPIs can be used to discover new PPIs and identify errors in the experimental PPI data.

Results

We present a novel deep learning framework, DPPI, to model and predict PPIs from sequence information alone. Our model efficiently applies a deep, Siamese-like convolutional neural network combined with random projection and data augmentation to predict PPIs, leveraging existing high-quality experimental PPI data and evolutionary information of a protein pair under prediction. Our experimental results show that DPPI outperforms the state-of-the-art methods on several benchmarks in terms of area under precision-recall curve (auPR), and computationally is more efficient. We also show that DPPI is able to predict homodimeric interactions where other methods fail to work accurately, and the effectiveness of DPPI in specific applications such as predicting cytokine-receptor binding affinities.

Availability and implementation

Predicting protein-protein interactions through sequence-based deep learning): https://github.com/hashemifar/DPPI/.

Supplementary information

Supplementary data are available at Bioinformatics online.

Algebraic shortcuts for leave-one-out cross-validation in supervised network inference

Supervised machine learning techniques have traditionally been very successful at reconstructing biological networks, such as protein-ligand interaction, protein-protein interaction and gene regulatory networks. Many supervised techniques for network prediction use linear models on a possibly nonlinear pairwise feature representation of edges. Recently, much emphasis has been placed on the correct evaluation of such supervised models. It is vital to distinguish between using a model to either predict new interactions in a given network or to predict interactions for a new vertex not present in the original network. This distinction matters because (i) the performance might dramatically differ between the prediction settings and (ii) tuning the model hyperparameters to obtain the best possible model depends on the setting of interest. Specific cross-validation schemes need to be used to assess the performance in such different prediction settings.In this work we discuss a state-of-the-art kernel-based network inference technique called two-step kernel ridge regression. We show that this regression model can be trained efficiently, with a time complexity scaling with the number of vertices rather than the number of edges. Furthermore, this framework leads to a series of cross-validation shortcuts that allow one to rapidly estimate the model performance for any relevant network prediction setting. This allows computational biologists to fully assess the capabilities of their models. The machine learning techniques with the algebraic shortcuts are implemented in the RLScore software package: https://github.com/aatapa/RLScore.

Reciprocal Perspective for Improved Protein-Protein Interaction Prediction

All protein-protein interaction (PPI) predictors require the determination of an operational decision threshold when differentiating positive PPIs from negatives. Historically, a single global threshold, typically optimized via cross-validation testing, is applied to all protein pairs. However, we here use data visualization techniques to show that no single decision threshold is suitable for all protein pairs, given the inherent diversity of protein interaction profiles. The recent development of high throughput PPI predictors has enabled the comprehensive scoring of all possible protein-protein pairs. This, in turn, has given rise to context, enabling us now to evaluate a PPI within the context of all possible predictions. Leveraging this context, we introduce a novel modeling framework called Reciprocal Perspective (RP), which estimates a localized threshold on a per-protein basis using several rank order metrics. By considering a putative PPI from the perspective of each of the proteins within the pair, RP rescores the predicted PPI and applies a cascaded Random Forest classifier leading to improvements in recall and precision. We here validate RP using two state-of-the-art PPI predictors, the Protein-protein Interaction Prediction Engine and the Scoring PRotein INTeractions methods, over five organisms: Homo sapiens, Saccharomyces cerevisiae, Arabidopsis thaliana, Caenorhabditis elegans, and Mus musculus. Results demonstrate the application of a post hoc RP rescoring layer significantly improves classification (p < 0.001) in all cases over all organisms and this new rescoring approach can apply to any PPI prediction method.

ProfPPIdb: Pairs of physical protein-protein interactions predicted for entire proteomes

MOTIVATION

Protein-protein interactions (PPIs) play a key role in many cellular processes. Most annotations of PPIs mix experimental and computational data. The mix optimizes coverage, but obfuscates the annotation origin. Some resources excel at focusing on reliable experimental data. Here, we focused on new pairs of interacting proteins for several model organisms based solely on sequence-based prediction methods.

RESULTS

We extracted reliable experimental data about which proteins interact (binary) for eight diverse model organisms from public databases, namely from Escherichia coli, Schizosaccharomyces pombe, Plasmodium falciparum, Drosophila melanogaster, Caenorhabditis elegans, Mus musculus, Rattus norvegicus, Arabidopsis thaliana, and for the previously used Homo sapiens and Saccharomyces cerevisiae. Those data were the base to develop a PPI prediction method for each model organism. The method used evolutionary information through a profile-kernel Support Vector Machine (SVM). With the resulting eight models, we predicted all possible protein pairs in each organism and made the top predictions available through a web application. Almost all of the PPIs made available were predicted between proteins that have not been observed in any interaction, in particular for less well-studied organisms. Thus, our work complements existing resources and is particularly helpful for designing experiments because of its uniqueness. Experimental annotations and computational predictions are strongly influenced by the fact that some proteins have many partners and others few. To optimize machine learning, recent methods explicitly ignored such a network-structure and rely either on domain knowledge or sequence-only methods. Our approach is independent of domain-knowledge and leverages evolutionary information. The database interface representing our results is accessible from https://rostlab.org/services/ppipair/. The data can also be downloaded from https://figshare.com/collections/ProfPPI-DB/4141784.