Benchmarking of protein descriptor sets in proteochemometric modeling (part 2): modeling performance of 13 amino acid descriptor sets

Uncovering substrate specificity determinants of class IIb aminoacyl-tRNA synthetases with machine learning

Specific amino acid (AA) binding by aminoacyl-tRNA synthetases (aaRSs) is necessary for correct translation of the genetic code. Sequence and structure analyses have revealed the main specificity determinants and allowed a partitioning of aaRSs into two classes and several subclasses. However, the information contributed by each determinant has not been precisely quantified, and other, minor determinants may still be unidentified. Growth of genomic data and development of machine learning classification methods allow us to revisit these questions. This work considered the subclass IIb, formed by the three enzymes aspartyl-, asparaginyl-, and lysyl-tRNA synthetase (LysRS). Over 35,000 sequences from the Pfam database were considered, and used to train a machine-learning model based on ensembles of decision trees. The model was trained to reproduce the existing classification of each sequence as AspRS, AsnRS, or LysRS, and to identify which sequence positions were most important for the classification. A few positions (5-8 depending on the AA substrate) sufficed for accurate classification. Most but not all of them were well-known specificity determinants. The machine learning models thus identified sets of mutations that distinguish the three subclass members, which might be targeted in engineering efforts to alter or swap the AA specificities for biotechnology applications.

ProteoMutaMetrics: machine learning approaches for solute carrier family 6 mutation pathogenicity prediction

The solute carrier transporter family 6 (SLC6) is of key interest for their critical role in the transport of small amino acids or amino acid-like molecules. Their dysfunction is strongly associated with human diseases such as including schizophrenia, depression, and Parkinson's disease. Linking single point mutations to disease may support insights into the structure-function relationship of these transporters. This work aimed to develop a computational model for predicting the potential pathogenic effect of single point mutations in the SLC6 family. Missense mutation data was retrieved from UniProt, LitVar, and ClinVar, covering multiple protein-coding transcripts. As encoding approach, amino acid descriptors were used to calculate the average sequence properties for both original and mutated sequences. In addition to the full-sequence calculation, the sequences were cut into twelve domains. The domains are defined according to the transmembrane domains of the SLC6 transporters to analyse the regions' contributions to the pathogenicity prediction. Subsequently, several classification models, namely Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) with the hyperparameters optimized through grid search were built. For estimation of model performance, repeated stratified k-fold cross-validation was used. The accuracy values of the generated models are in the range of 0.72 to 0.80. Analysis of feature importance indicates that mutations in distinct regions of SLC6 transporters are associated with an increased risk for pathogenicity. When applying the model on an independent validation set, the performance in accuracy dropped to averagely 0.6 with high precision but low sensitivity scores.

Intelligent Protein Design and Molecular Characterization Techniques: A Comprehensive Review

In recent years, the widespread application of artificial intelligence algorithms in protein structure, function prediction, and de novo protein design has significantly accelerated the process of intelligent protein design and led to many noteworthy achievements. This advancement in protein intelligent design holds great potential to accelerate the development of new drugs, enhance the efficiency of biocatalysts, and even create entirely new biomaterials. Protein characterization is the key to the performance of intelligent protein design. However, there is no consensus on the most suitable characterization method for intelligent protein design tasks. This review describes the methods, characteristics, and representative applications of traditional descriptors, sequence-based and structure-based protein characterization. It discusses their advantages, disadvantages, and scope of application. It is hoped that this could help researchers to better understand the limitations and application scenarios of these methods, and provide valuable references for choosing appropriate protein characterization techniques for related research in the field, so as to better carry out protein research.

3DDPDs: describing protein dynamics for proteochemometric bioactivity prediction. A case for (mutant) G protein-coupled receptors

Proteochemometric (PCM) modelling is a powerful computational drug discovery tool used in bioactivity prediction of potential drug candidates relying on both chemical and protein information. In PCM features are computed to describe small molecules and proteins, which directly impact the quality of the predictive models. State-of-the-art protein descriptors, however, are calculated from the protein sequence and neglect the dynamic nature of proteins. This dynamic nature can be computationally simulated with molecular dynamics (MD). Here, novel 3D dynamic protein descriptors (3DDPDs) were designed to be applied in bioactivity prediction tasks with PCM models. As a test case, publicly available G protein-coupled receptor (GPCR) MD data from GPCRmd was used. GPCRs are membrane-bound proteins, which are activated by hormones and neurotransmitters, and constitute an important target family for drug discovery. GPCRs exist in different conformational states that allow the transmission of diverse signals and that can be modified by ligand interactions, among other factors. To translate the MD-encoded protein dynamics two types of 3DDPDs were considered: one-hot encoded residue-specific (rs) and embedding-like protein-specific (ps) 3DDPDs. The descriptors were developed by calculating distributions of trajectory coordinates and partial charges, applying dimensionality reduction, and subsequently condensing them into vectors per residue or protein, respectively. 3DDPDs were benchmarked on several PCM tasks against state-of-the-art non-dynamic protein descriptors. Our rs- and ps3DDPDs outperformed non-dynamic descriptors in regression tasks using a temporal split and showed comparable performance with a random split and in all classification tasks. Combinations of non-dynamic descriptors with 3DDPDs did not result in increased performance. Finally, the power of 3DDPDs to capture dynamic fluctuations in mutant GPCRs was explored. The results presented here show the potential of including protein dynamic information on machine learning tasks, specifically bioactivity prediction, and open opportunities for applications in drug discovery, including oncology.

Accelerating the Screening of Small Peptide Ligands by Combining Peptide-Protein Docking and Machine Learning

This research introduces a novel pipeline that couples machine learning (ML), and molecular docking for accelerating the process of small peptide ligand screening through the prediction of peptide-protein docking. Eight ML algorithms were analyzed for their potential. Notably, Light Gradient Boosting Machine (LightGBM), despite having comparable F1-score and accuracy to its counterparts, showcased superior computational efficiency. LightGBM was used to classify peptide-protein docking performance of the entire tetrapeptide library of 160,000 peptide ligands against four viral envelope proteins. The library was classified into two groups, 'better performers' and 'worse performers'. By training the LightGBM algorithm on just 1% of the tetrapeptide library, we successfully classified the remaining 99%with an accuracy range of 0.81-0.85 and an F1-score between 0.58-0.67. Three different molecular docking software were used to prove that the process is not software dependent. With an adjustable probability threshold (from 0.5 to 0.95), the process could be accelerated by a factor of at least 10-fold and still get 90-95% concurrence with the method without ML. This study validates the efficiency of machine learning coupled to molecular docking in rapidly identifying top peptides without relying on high-performance computing power, making it an effective tool for screening potential bioactive compounds.

Deep learning tools to accelerate antibiotic discovery

INTRODUCTION

As machine learning (ML) and artificial intelligence (AI) expand to many segments of our society, they are increasingly being used for drug discovery. Recent deep learning models offer an efficient way to explore high-dimensional data and design compounds with desired properties, including those with antibacterial activity.

AREAS COVERED

This review covers key frameworks in antibiotic discovery, highlighting physicochemical features and addressing dataset limitations. The deep learning approaches here described include discriminative models such as convolutional neural networks, recurrent neural networks, graph neural networks, and generative models like neural language models, variational autoencoders, generative adversarial networks, normalizing flow, and diffusion models. As the integration of these approaches in drug discovery continues to evolve, this review aims to provide insights into promising prospects and challenges that lie ahead in harnessing such technologies for the development of antibiotics.

EXPERT OPINION

Accurate antimicrobial prediction using deep learning faces challenges such as imbalanced data, limited datasets, experimental validation, target strains, and structure. The integration of deep generative models with bioinformatics, molecular dynamics, and data augmentation holds the potential to overcome these challenges, enhance model performance, and utlimately accelerate antimicrobial discovery.

CalcAMP: A New Machine Learning Model for the Accurate Prediction of Antimicrobial Activity of Peptides

To combat infection by microorganisms host organisms possess a primary arsenal via the innate immune system. Among them are defense peptides with the ability to target a wide range of pathogenic organisms, including bacteria, viruses, parasites, and fungi. Here, we present the development of a novel machine learning model capable of predicting the activity of antimicrobial peptides (AMPs), CalcAMP. AMPs, in particular short ones (<35 amino acids), can become an effective solution to face the multi-drug resistance issue arising worldwide. Whereas finding potent AMPs through classical wet-lab techniques is still a long and expensive process, a machine learning model can be useful to help researchers to rapidly identify whether peptides present potential or not. Our prediction model is based on a new data set constructed from the available public data on AMPs and experimental antimicrobial activities. CalcAMP can predict activity against both Gram-positive and Gram-negative bacteria. Different features either concerning general physicochemical properties or sequence composition have been assessed to retrieve higher prediction accuracy. CalcAMP can be used as an promising prediction asset to identify short AMPs among given peptide sequences.

Proteochemometric Modeling Identifies Chemically Diverse Norepinephrine Transporter Inhibitors

Solute carriers (SLCs) are relatively underexplored compared to other prominent protein families such as kinases and G protein-coupled receptors. However, proteins from the SLC family play an essential role in various diseases. One such SLC is the high-affinity norepinephrine transporter (NET/SLC6A2). In contrast to most other SLCs, the NET has been relatively well studied. However, the chemical space of known ligands has a low chemical diversity, making it challenging to identify chemically novel ligands. Here, a computational screening pipeline was developed to find new NET inhibitors. The approach increases the chemical space to model for NETs using the chemical space of related proteins that were selected utilizing similarity networks. Prior proteochemometric models added data from related proteins, but here we use a data-driven approach to select the optimal proteins to add to the modeled data set. After optimizing the data set, the proteochemometric model was optimized using stepwise feature selection. The final model was created using a two-step approach combining several proteochemometric machine learning models through stacking. This model was applied to the extensive virtual compound database of Enamine, from which the top predicted 22,000 of the 600 million virtual compounds were clustered to end up with 46 chemically diverse candidates. A subselection of 32 candidates was synthesized and subsequently tested using an impedance-based assay. There were five hit compounds identified (hit rate 16%) with sub-micromolar inhibitory potencies toward NET, which are promising for follow-up experimental research. This study demonstrates a data-driven approach to diversify known chemical space to identify novel ligands and is to our knowledge the first to select this set based on the sequence similarity of related targets.

PSnpBind-ML: predicting the effect of binding site mutations on protein-ligand binding affinity

Protein mutations, especially those which occur in the binding site, play an important role in inter-individual drug response and may alter binding affinity and thus impact the drug's efficacy and side effects. Unfortunately, large-scale experimental screening of ligand-binding against protein variants is still time-consuming and expensive. Alternatively, in silico approaches can play a role in guiding those experiments. Methods ranging from computationally cheaper machine learning (ML) to the more expensive molecular dynamics have been applied to accurately predict the mutation effects. However, these effects have been mostly studied on limited and small datasets, while ideally a large dataset of binding affinity changes due to binding site mutations is needed. In this work, we used the PSnpBind database with six hundred thousand docking experiments to train a machine learning model predicting protein-ligand binding affinity for both wild-type proteins and their variants with a single-point mutation in the binding site. A numerical representation of the protein, binding site, mutation, and ligand information was encoded using 256 features, half of them were manually selected based on domain knowledge. A machine learning approach composed of two regression models is proposed, the first predicting wild-type protein-ligand binding affinity while the second predicting the mutated protein-ligand binding affinity. The best performing models reported an RMSE value within 0.5 [Formula: see text] 0.6 kcal/mol^-1 on an independent test set with an R² value of 0.87 [Formula: see text] 0.90. We report an improvement in the prediction performance compared to several reported models developed for protein-ligand binding affinity prediction. The obtained models can be used as a complementary method in early-stage drug discovery. They can be applied to rapidly obtain a better overview of the ligand binding affinity changes across protein variants carried by people in the population and narrow down the search space where more time-demanding methods can be used to identify potential leads that achieve a better affinity for all protein variants.

Engineering the Substrate Specificity of Toluene Degrading Enzyme XylM Using Biosensor XylS and Machine Learning

Enzyme engineering using machine learning has been developed in recent years. However, to obtain a large amount of data on enzyme activities for training data, it is necessary to develop a high-throughput and accurate method for evaluating enzyme activities. Here, we examined whether a biosensor-based enzyme engineering method can be applied to machine learning. As a model experiment, we aimed to modify the substrate specificity of XylM, a rate-determining enzyme in a multistep oxidation reaction catalyzed by XylMABC in Pseudomonas putida. XylMABC naturally converts toluene and xylene to benzoic acid and toluic acid, respectively. We aimed to engineer XylM to improve its conversion efficiency to a non-native substrate, 2,6-xylenol. Wild-type XylMABC slightly converted 2,6-xylenol to 3-methylsalicylic acid, which is the ligand of the transcriptional regulator XylS in P. putida. By locating a fluorescent protein gene under the control of the Pm promoter to which XylS binds, a XylS-producing Escherichia coli strain showed higher fluorescence intensity in a 3-methylsalicylic acid concentration-dependent manner. We evaluated the 3-methylsalicylic acid productivity of XylM variants using the fluorescence intensity of the sensor strain as an indicator. The obtained data provided the training data for machine learning for the directed evolution of XylM. Two cycles of machine learning-assisted directed evolution resulted in the acquisition of XylM-D140E-V144K-F243L-N244S with 15 times higher productivity than wild-type XylM. These results demonstrate that an indirect enzyme activity evaluation method using biosensors is sufficiently quantitative and high-throughput to be used as training data for machine learning. The findings expand the versatility of machine learning in enzyme engineering.

How to approach machine learning-based prediction of drug/compound-target interactions

The identification of drug/compound-target interactions (DTIs) constitutes the basis of drug discovery, for which computational predictive approaches have been developed. As a relatively new data-driven paradigm, proteochemometric (PCM) modeling utilizes both protein and compound properties as a pair at the input level and processes them via statistical/machine learning. The representation of input samples (i.e., proteins and their ligands) in the form of quantitative feature vectors is crucial for the extraction of interaction-related properties during the artificial learning and subsequent prediction of DTIs. Lately, the representation learning approach, in which input samples are automatically featurized via training and applying a machine/deep learning model, has been utilized in biomedical sciences. In this study, we performed a comprehensive investigation of different computational approaches/techniques for protein featurization (including both conventional approaches and the novel learned embeddings), data preparation and exploration, machine learning-based modeling, and performance evaluation with the aim of achieving better data representations and more successful learning in DTI prediction. For this, we first constructed realistic and challenging benchmark datasets on small, medium, and large scales to be used as reliable gold standards for specific DTI modeling tasks. We developed and applied a network analysis-based splitting strategy to divide datasets into structurally different training and test folds. Using these datasets together with various featurization methods, we trained and tested DTI prediction models and evaluated their performance from different angles. Our main findings can be summarized under 3 items: (i) random splitting of datasets into train and test folds leads to near-complete data memorization and produce highly over-optimistic results, as a result, should be avoided, (ii) learned protein sequence embeddings work well in DTI prediction and offer high potential, despite interaction-related properties (e.g., structures) of proteins are unused during their self-supervised model training, and (iii) during the learning process, PCM models tend to rely heavily on compound features while partially ignoring protein features, primarily due to the inherent bias in DTI data, indicating the requirement for new and unbiased datasets. We hope this study will aid researchers in designing robust and high-performing data-driven DTI prediction systems that have real-world translational value in drug discovery.

Machine learning and comparative genomics approaches for the discovery of xylose transporters in yeast

Background

The need to mitigate and substitute the use of fossil fuels as the main energy matrix has led to the study and development of biofuels as an alternative. Second-generation (2G) ethanol arises as one biofuel with great potential, due to not only maintaining food security, but also as a product from economically interesting crops such as energy-cane. One of the main challenges of 2G ethanol is the inefficient uptake of pentose sugars by industrial yeast Saccharomyces cerevisiae, the main organism used for ethanol production. Understanding the main drivers for xylose assimilation and identify novel and efficient transporters is a key step to make the 2G process economically viable.

Results

By implementing a strategy of searching for present motifs that may be responsible for xylose transport and past adaptations of sugar transporters in xylose fermenting species, we obtained a classifying model which was successfully used to select four different candidate transporters for evaluation in the S. cerevisiae hxt-null strain, EBY.VW4000, harbouring the xylose consumption pathway. Yeast cells expressing the transporters SpX, SpH and SpG showed a superior uptake performance in xylose compared to traditional literature control Gxf1.

Conclusions

Modelling xylose transport with the small data available for yeast and bacteria proved a challenge that was overcome through different statistical strategies. Through this strategy, we present four novel xylose transporters which expands the repertoire of candidates targeting yeast genetic engineering for industrial fermentation. The repeated use of the model for characterizing new transporters will be useful both into finding the best candidates for industrial utilization and to increase the model’s predictive capabilities.

Graphical Abstract

Supplementary Information

The online version contains supplementary material available at 10.1186/s13068-022-02153-7.

Molecular Mingling: Multimodal Predictions of Ligand Promiscuity in Pentameric Ligand-Gated Ion Channels

Background: Human pentameric ligand-gated ion channels (pLGICs) comprise nicotinic acetylcholine receptors (nAChRs), 5-hydroxytryptamine type 3 receptors (5-HT3Rs), zinc-activated channels (ZAC), γ-aminobutyric acid type A receptors (GABAARs) and glycine receptors (GlyRs). They are recognized therapeutic targets of some of the most prescribed drugs like general anesthetics, anxiolytics, smoking cessation aids, antiemetics and many more. Currently, approximately 100 experimental structures of pLGICs with ligands bound exist in the protein data bank (PDB). These atomic-level 3D structures enable the generation of a comprehensive binding site inventory for the superfamily and the in silico prediction of binding site properties. Methods: A panel of high throughput in silico methods including pharmacophore screening, conformation analysis and descriptor calculation was applied to a selection of allosteric binding sites for which in vitro screens are lacking. Variant abundance near binding site forming regions and computational docking complement the approach. Results: The structural data reflects known and novel binding sites, some of which may be unique to individual receptors, while others are broadly conserved. The membrane spanning domain, comprising four highly conserved segments, contains ligand interaction sites for which in vitro assays suitable for high throughput screenings are critically lacking. This is also the case for structurally more variable novel sites in the extracellular domain. Our computational results suggest that the phytocannabinoid Δ9-tetrahydrocannabinol (Δ9-THC) can utilize multiple pockets which are likely to exist on most superfamily members. Conclusion: With this study, we explore the potential for polypharmacology among pLGICs. Our data suggest that ligands can display two forms of promiscuity to an extent greater than what has been realized: 1) Ligands can interact with homologous sites in many members of the superfamily, which bears toxicological relevance. 2) Multiple pockets in distinct localizations of individual receptor subtypes share common ligands, which counteracts efforts to develop selective agents. Moreover, conformational states need to be considered for in silico drug screening, as certain binding sites display considerable flexibility. In total, this work contributes to a better understanding of polypharmacology across pLGICs and provides a basis for improved structure guided in silico drug development and drug derisking.

GNIFdb: a neoantigen intrinsic feature database for glioma

ABSTRACT

Neoantigens are mutation-containing immunogenic peptides from tumor cells. Neoantigen intrinsic features are neoantigens' sequence-associated features characterized by different amino acid descriptors and physical-chemical properties, which have a crucial function in prioritization of neoantigens with immunogenic potentials and predicting patients with better survival. Different intrinsic features might have functions to varying degrees in evaluating neoantigens' potentials of immunogenicity. Identification and comparison of intrinsic features among neoantigens are particularly important for developing neoantigen-based personalized immunotherapy. However, there is still no public repository to host the intrinsic features of neoantigens. Therefore, we developed GNIFdb, a glioma neoantigen intrinsic feature database specifically designed for hosting, exploring and visualizing neoantigen and intrinsic features. The database provides a comprehensive repository of computationally predicted Human leukocyte antigen class I (HLA-I) restricted neoantigens and their intrinsic features; a systematic annotation of neoantigens including sequence, neoantigen-associated mutation, gene expression, glioma prognosis, HLA-I subtype and binding affinity between neoantigens and HLA-I; and a genome browser to visualize them in an interactive manner. It represents a valuable resource for the neoantigen research community and is publicly available at http://www.oncoimmunobank.cn/index.php.

DATABASE URL

http://www.oncoimmunobank.cn/index.php.

Sequence-based prediction of protein binding regions and drug-target interactions

Identifying drug-target interactions (DTIs) is important for drug discovery. However, searching all drug-target spaces poses a major bottleneck. Therefore, recently many deep learning models have been proposed to address this problem. However, the developers of these deep learning models have neglected interpretability in model construction, which is closely related to a model's performance. We hypothesized that training a model to predict important regions on a protein sequence would increase DTI prediction performance and provide a more interpretable model. Consequently, we constructed a deep learning model, named Highlights on Target Sequences (HoTS), which predicts binding regions (BRs) between a protein sequence and a drug ligand, as well as DTIs between them. To train the model, we collected complexes of protein-ligand interactions and protein sequences of binding sites and pretrained the model to predict BRs for a given protein sequence-ligand pair via object detection employing transformers. After pretraining the BR prediction, we trained the model to predict DTIs from a compound token designed to assign attention to BRs. We confirmed that training the BRs prediction model indeed improved the DTI prediction performance. The proposed HoTS model showed good performance in BR prediction on independent test datasets even though it does not use 3D structure information in its prediction. Furthermore, the HoTS model achieved the best performance in DTI prediction on test datasets. Additional analysis confirmed the appropriate attention for BRs and the importance of transformers in BR and DTI prediction. The source code is available on GitHub ( https://github.com/GIST-CSBL/HoTS ).

Applications of Artificial Intelligence in Drug Design: Opportunities and Challenges

Artificial intelligence (AI) has undergone rapid development in recent years and has been successfully applied to real-world problems such as drug design. In this chapter, we review recent applications of AI to problems in drug design including virtual screening, computer-aided synthesis planning, and de novo molecule generation, with a focus on the limitations of the application of AI therein and opportunities for improvement. Furthermore, we discuss the broader challenges imposed by AI in translating theoretical practice to real-world drug design; including quantifying prediction uncertainty and explaining model behavior.

Antigenicity prediction and vaccine recommendation of human influenza virus A (H3N2) using convolutional neural networks

The rapid evolution of influenza A viruses poses a great challenge to vaccine development. Analytical and machine learning models have been applied to facilitate the process of antigenicity determination. In this study, we designed deep convolutional neural networks (CNNs) to predict Influenza antigenicity. Our model is the first that systematically analyzed 566 amino acid properties and 141 amino acid substitution matrices for their predictability. We then optimized the structure of the CNNs using particle swarm optimization. The optimal neural networks outperform other predictive models with a blind validation accuracy of 95.8%. Further, we applied our model to vaccine recommendations in the period 1997 to 2011 and contrasted the performance of previous vaccine recommendations using traditional experimental approaches. The results show that our model outperforms the WHO recommendation and other existing models and could potentially improve the vaccine recommendation process. Our results show that WHO often selects virus strains with small variation from year to year and learns slowly and recovers once coverage dips very low. In contrast, the influenza strains selected via our CNN model can differ quite drastically from year to year and exhibit consistently good coverage. In summary, we have designed a comprehensive computational pipeline for optimizing a CNN in the modeling of Influenza A antigenicity and vaccine recommendation. It is more cost and time-effective when compared to traditional hemagglutination inhibition assay analysis. The modeling framework is flexible and can be adopted to study other type of viruses.

Successive Statistical and Structure-Based Modeling to Identify Chemically Novel Kinase Inhibitors

Kinases are frequently studied in the context of anticancer drugs. Their involvement in cell responses, such as proliferation, differentiation, and apoptosis, makes them interesting subjects in multitarget drug design. In this study, a workflow is presented that models the bioactivity spectra for two panels of kinases: (1) inhibition of RET, BRAF, SRC, and S6K, while avoiding inhibition of MKNK1, TTK, ERK8, PDK1, and PAK3, and (2) inhibition of AURKA, PAK1, FGFR1, and LKB1, while avoiding inhibition of PAK3, TAK1, and PIK3CA. Both statistical and structure-based models were included, which were thoroughly benchmarked and optimized. A virtual screening was performed to test the workflow for one of the main targets, RET kinase. This resulted in 5 novel and chemically dissimilar RET inhibitors with remaining RET activity of <60% (at a concentration of 10 μM) and similarities with known RET inhibitors from 0.18 to 0.29 (Tanimoto, ECFP6). The four more potent inhibitors were assessed in a concentration range and proved to be modestly active with a pIC₅₀ value of 5.1 for the most active compound. The experimental validation of inhibitors for RET strongly indicates that the multitarget workflow is able to detect novel inhibitors for kinases, and hence, this workflow can potentially be applied in polypharmacology modeling. We conclude that this approach can identify new chemical matter for existing targets. Moreover, this workflow can easily be applied to other targets as well.

Evidence Supporting an Antimicrobial Origin of Targeting Peptides to Endosymbiotic Organelles

Mitochondria and chloroplasts emerged from primary endosymbiosis. Most proteins of the endosymbiont were subsequently expressed in the nucleo-cytosol of the host and organelle-targeted via the acquisition of N-terminal presequences, whose evolutionary origin remains enigmatic. Using a quantitative assessment of their physico-chemical properties, we show that organelle targeting peptides, which are distinct from signal peptides targeting other subcellular compartments, group with a subset of antimicrobial peptides. We demonstrate that extant antimicrobial peptides target a fluorescent reporter to either the mitochondria or the chloroplast in the green alga Chlamydomonas reinhardtii and, conversely, that extant targeting peptides still display antimicrobial activity. Thus, we provide strong computational and functional evidence for an evolutionary link between organelle-targeting and antimicrobial peptides. Our results support the view that resistance of bacterial progenitors of organelles to the attack of host antimicrobial peptides has been instrumental in eukaryogenesis and in the emergence of photosynthetic eukaryotes.

DEEPScreen: high performance drug-target interaction prediction with convolutional neural networks using 2-D structural compound representations

The identification of physical interactions between drug candidate compounds and target biomolecules is an important process in drug discovery. Since conventional screening procedures are expensive and time consuming, computational approaches are employed to provide aid by automatically predicting novel drug-target interactions (DTIs). In this study, we propose a large-scale DTI prediction system, DEEPScreen, for early stage drug discovery, using deep convolutional neural networks. One of the main advantages of DEEPScreen is employing readily available 2-D structural representations of compounds at the input level instead of conventional descriptors that display limited performance. DEEPScreen learns complex features inherently from the 2-D representations, thus producing highly accurate predictions. The DEEPScreen system was trained for 704 target proteins (using curated bioactivity data) and finalized with rigorous hyper-parameter optimization tests. We compared the performance of DEEPScreen against the state-of-the-art on multiple benchmark datasets to indicate the effectiveness of the proposed approach and verified selected novel predictions through molecular docking analysis and literature-based validation. Finally, JAK proteins that were predicted by DEEPScreen as new targets of a well-known drug cladribine were experimentally demonstrated in vitro on cancer cells through STAT3 phosphorylation, which is the downstream effector protein. The DEEPScreen system can be exploited in the fields of drug discovery and repurposing for in silico screening of the chemogenomic space, to provide novel DTIs which can be experimentally pursued. The source code, trained "ready-to-use" prediction models, all datasets and the results of this study are available at ; https://github.com/cansyl/DEEPscreen.

Evaluation of deep and shallow learning methods in chemogenomics for the prediction of drugs specificity

Chemogenomics, also called proteochemometrics, covers a range of computational methods that can be used to predict protein–ligand interactions at large scales in the protein and chemical spaces. They differ from more classical ligand-based methods (also called QSAR) that predict ligands for a given protein receptor. In the context of drug discovery process, chemogenomics allows to tackle the question of predicting off-target proteins for drug candidates, one of the main causes of undesirable side-effects and failure within drugs development processes. The present study compares shallow and deep machine-learning approaches for chemogenomics, and explores data augmentation techniques for deep learning algorithms in chemogenomics. Shallow machine-learning algorithms rely on expert-based chemical and protein descriptors, while recent developments in deep learning algorithms enable to learn abstract numerical representations of molecular graphs and protein sequences, in order to optimise the performance of the prediction task. We first propose a formulation of chemogenomics with deep learning, called the chemogenomic neural network (CN), as a feed-forward neural network taking as input the combination of molecule and protein representations learnt by molecular graph and protein sequence encoders. We show that, on large datasets, the deep learning CN model outperforms state-of-the-art shallow methods, and competes with deep methods with expert-based descriptors. However, on small datasets, shallow methods present better prediction performance than deep learning methods. Then, we evaluate data augmentation techniques, namely multi-view and transfer learning, to improve the prediction performance of the chemogenomic neural network. We conclude that a promising research direction is to integrate heterogeneous sources of data such as auxiliary tasks for which large datasets are available, or independently, multiple molecule and protein attribute views.

Proteochemometrics - recent developments in bioactivity and selectivity modeling

Proteochemometrics is a machine learning based modeling approach relying on a combination of ligand and protein descriptors. With ongoing developments in machine learning and increases in public data the technique is more frequently applied in early drug discovery, typically in ligand-target binding prediction. Common applications include improvements to single target quantitative structure-activity relationship models, protein selectivity and promiscuity modeling, and large-scale deep learning approaches. The increase in predictive power using proteochemometrics is observed in multi-target bioactivity modeling, opening the door to more extensive studies covering whole protein families. On top of that, with deep learning fueling more complex and larger scale models, proteochemometrics allows faster and higher quality computational models supporting the design, make, test cycle.

Current computational methods for predicting protein interactions of natural products

Natural products (NPs) are an indispensable source of drugs and they have a better coverage of the pharmacological space than synthetic compounds, owing to their high structural diversity. The prediction of their interaction profiles with druggable protein targets remains a major challenge in modern drug discovery. Experimental (off-)target predictions of NPs are cost- and time-consuming, whereas computational methods, on the other hand, are much faster and cheaper. As a result, computational predictions are preferentially used in the first instance for NP profiling, prior to experimental validations. This review covers recent advances in computational approaches which have been developed to aid the annotation of unknown drug-target interactions (DTIs), by focusing on three broad classes, namely: ligand-based, target-based, and target-ligand-based (hybrid) approaches. Computational DTI prediction methods have the potential to significantly advance the discovery and development of novel selective drugs exhibiting minimal side effects. We highlight some inherent caveats of these methods which must be overcome to enable them to realize their full potential, and a future outlook is given.

An Optimized Screen Reduces the Number of GA Transporters and Provides Insights Into Nitrate Transporter 1/Peptide Transporter Family Substrate Determinants

Based on recent in vitro data, a relatively large number of the plant nitrate transporter 1/peptide transporter family (NPF) proteins have been suggested to function as gibberellic acid (GA) transporters. Most GA transporting NPF proteins also appear to transport other structurally unrelated phytohormones or metabolites. Several of the GAs used in previous in vitro assays are membrane permeable weak organic acids whose movement across membranes are influenced by the pH-sensitive ion-trap mechanism. Moreover, a large proportion of in vitro GA transport activities have been demonstrated indirectly via long-term yeast-based GA-dependent growth assays that are limited to detecting transport of bioactive GAs. Thus, there is a need for an optimized transport assay for identifying and characterizing GA transport. Here, we develop an improved transport assay in Xenopus laevis oocytes, wherein we directly measure movement of six different GAs across oocyte membranes over short time. We show that membrane permeability of GAs in oocytes can be predicted based on number of oxygen atoms and that several GAs do not diffuse over membranes regardless of changes in pH values. In addition, we show that small changes in internal cellular pH can result in strongly altered distribution of membrane permeable phytohormones. This prompts caution when interpreting heterologous transport activities. We use our transport assay to screen all Arabidopsis thaliana NPF proteins for transport activity towards six GAs (two membrane permeable and four non-permeable). The results presented here, significantly reduce the number of bona fide NPF GA transporters in Arabidopsis and narrow the activity to fewer subclades within the family. Furthermore, to gain first insight into the molecular determinants of substrate specificities toward organic molecules transported in the NPF, we charted all surface exposed amino acid residues in the substrate-binding cavity and correlated them to GA transport. This analysis suggests distinct residues within the substrate-binding cavity that are shared between GA transporting NPF proteins; the potential roles of these residues in determining substrate specificity are discussed.

Identification of novel small molecule inhibitors for solute carrier SGLT1 using proteochemometric modeling

Sodium-dependent glucose co-transporter 1 (SGLT1) is a solute carrier responsible for active glucose absorption. SGLT1 is present in both the renal tubules and small intestine. In contrast, the closely related sodium-dependent glucose co-transporter 2 (SGLT2), a protein that is targeted in the treatment of diabetes type II, is only expressed in the renal tubules. Although dual inhibitors for both SGLT1 and SGLT2 have been developed, no drugs on the market are targeted at decreasing dietary glucose uptake by SGLT1 in the gastrointestinal tract. Here we aim at identifying SGLT1 inhibitors in silico by applying a machine learning approach that does not require structural information, which is absent for SGLT1. We applied proteochemometrics by implementation of compound- and protein-based information into random forest models. We obtained a predictive model with a sensitivity of 0.64 ± 0.06, specificity of 0.93 ± 0.01, positive predictive value of 0.47 ± 0.07, negative predictive value of 0.96 ± 0.01, and Matthews correlation coefficient of 0.49 ± 0.05. Subsequent to model training, we applied our model in virtual screening to identify novel SGLT1 inhibitors. Of the 77 tested compounds, 30 were experimentally confirmed for SGLT1-inhibiting activity in vitro, leading to a hit rate of 39% with activities in the low micromolar range. Moreover, the hit compounds included novel molecules, which is reflected by the low similarity of these compounds with the training set (< 0.3). Conclusively, proteochemometric modeling of SGLT1 is a viable strategy for identifying active small molecules. Therefore, this method may also be applied in detection of novel small molecules for other transporter proteins.

The Future of Computational Chemogenomics

Following the elucidation of the human genome, chemogenomics emerged in the beginning of the twenty-first century as an interdisciplinary research field with the aim to accelerate target and drug discovery by making best usage of the genomic data and the data linkable to it. What started as a systematization approach within protein target families now encompasses all types of chemical compounds and gene products. A key objective of chemogenomics is the establishment, extension, analysis, and prediction of a comprehensive SAR matrix which by application will enable further systematization in drug discovery. Herein we outline future perspectives of chemogenomics including the extension to new molecular modalities, or the potential extension beyond the pharma to the agro and nutrition sectors, and the importance for environmental protection. The focus is on computational sciences with potential applications for compound library design, virtual screening, hit assessment, analysis of phenotypic screens, lead finding and optimization, and systems biology-based prediction of toxicology and translational research.

Identification of Allosteric Modulators of Metabotropic Glutamate 7 Receptor Using Proteochemometric Modeling

Proteochemometric modeling (PCM) is a computational approach that can be considered an extension of quantitative structure-activity relationship (QSAR) modeling, where a single model incorporates information for a family of targets and all the associated ligands instead of modeling activity versus one target. This is especially useful for situations where bioactivity data exists for similar proteins but is scarce for the protein of interest. Here we demonstrate the application of PCM to identify allosteric modulators of metabotropic glutamate (mGlu) receptors. Given our long-running interest in modulating mGlu receptor function we compiled a matrix of compound-target bioactivity data. Some members of the mGlu family are well explored both internally and in the public domain, while there are much fewer examples of ligands for other targets such as the mGlu7 receptor. Using a PCM approach mGlu7 receptor hits were found. In comparison to conventional single target modeling the identified hits were more diverse, had a better confirmation rate, and provide starting points for further exploration. We conclude that the robust structure-activity relationship from well explored target family members translated to better quality hits for PCM compared to virtual screening (VS) based on a single target.

Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method ('DNN_PCM') performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized 'DNN_PCM'). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi-task learning is offered by providing the data and the protocols. Graphical Abstract .

Proteochemometrics-Based Prediction of Peptide Binding to HLA-DP Proteins

Human leukocyte antigens (HLA) class II proteins are involved in the antigen processing in the antigen presenting cells. They form complexes with antigen peptide fragments. The peptide-HLA protein complexes are presented on the cell surface where they are recognized by helper T cells (Th cells). HLA-DP is one of the three HLA class II loci. The HLA-DP proteins are associated with a significant number of autoimmune diseases, as well as with a susceptibility or resistance to a number of infectious agents. In the present study, we apply proteochemometrics-a method for bioactivity modeling of multiple ligands binding to multiple target proteins-to derive and validate a robust model for peptide binding prediction to the 7 most frequent HLA-DP proteins. The model is able to identify 86% of the binders in the top 10% of the best predicted nonamers generated from one protein.

Kinome-Wide Profiling Prediction of Small Molecules

Extensive kinase profiling data, covering more than half of the human kinome, are available nowadays and allow the construction of activity prediction models of high practical utility. Proteochemometric (PCM) approaches use compound and protein descriptors, which enables the extrapolation of bioactivity values to thus far unexplored kinases. In this study, the potential of PCM to make large-scale predictions on the entire kinome is explored, considering the applicability on novel compounds and kinases, including clinically relevant mutants. A rigorous validation indicates high predictive power on left-out kinases and superiority over individual kinase QSAR models for new compounds. Furthermore, external validation on clinically relevant mutant kinases reveals an excellent predictive power for mutations spread across the ATP binding site.

Proteochemometric Modeling of the Interaction Space of Carbonic Anhydrase and its Inhibitors: An Assessment of Structure-based and Sequence-based Descriptors

Due to its physiological and clinical roles, carbonic anhydrase (CA) is one of the most interesting case studies. There are different classes of CAinhibitors including sulfonamides, polyamines, coumarins and dithiocarbamates (DTCs). However, many of them hardly act as a selective inhibitor against a specific isoform. Therefore, finding highly selective inhibitors for different isoforms of CA is still an ongoing project. Proteochemometrics modeling (PCM) is able to model the bioactivity of multiple compounds against different isoforms of a protein. Therefore, it would be extremely applicable when investigating the selectivity of different ligands towards different receptors. Given the facts, we applied PCM to investigate the interaction space and structural properties that lead to the selective inhibition of CA isoforms by some dithiocarbamates. Our models have provided interesting structural information that can be considered to design compounds capable of inhibiting different isoforms of CA in an improved selective manner. Validity and predictivity of the models were confirmed by both internal and external validation methods; while Y-scrambling approach was applied to assess the robustness of the models. To prove the reliability and the applicability of our findings, we showed how ligands-receptors selectivity can be affected by removing any of these critical findings from the modeling process.

Applicability of predictive toxicology methods for monoclonal antibody therapeutics: status Quo and scope

Biopharmaceuticals, monoclonal antibody (mAb)-based therapeutics in particular, have positively impacted millions of lives. MAbs and related therapeutics are highly desirable from a biopharmaceutical perspective as they are highly target specific and well tolerated within the human system. Nevertheless, several mAbs have been discontinued or withdrawn based either on their inability to demonstrate efficacy and/or due to adverse effects. Approved monoclonal antibodies and derived therapeutics have been associated with adverse effects such as immunogenicity, cytokine release syndrome, progressive multifocal leukoencephalopathy, intravascular haemolysis, cardiac arrhythmias, abnormal liver function, gastrointestinal perforation, bronchospasm, intraocular inflammation, urticaria, nephritis, neuropathy, birth defects, fever and cough to name a few. The advances made in this field are also impeded by a lack of progress in bioprocess development strategies as well as increasing costs owing to attrition, wherein the lack of efficacy and safety accounts for nearly 60 % of all factors contributing to attrition. This reiterates the need for smarter preclinical development using quality by design-based approaches encompassing carefully designed predictive models during early stages of drug development. Different in vitro and in silico methods are extensively used for predicting biological activity as well as toxicity during small molecule drug development; however, their full potential has not been utilized for biological drug development. The scope of in vitro and in silico tools in early developmental stages of monoclonal antibody-based therapeutics production and how it contributes to lower attrition rates leading to faster development of potential drug candidates has been evaluated. The applicability of computational toxicology approaches in this context as well as the pitfalls and promises of extending such techniques to biopharmaceutical development has been highlighted.

Unprecedently Large-Scale Kinase Inhibitor Set Enabling the Accurate Prediction of Compound-Kinase Activities: A Way toward Selective Promiscuity by Design?

Drug discovery programs frequently target members of the human kinome and try to identify small molecule protein kinase inhibitors, primarily for cancer treatment, additional indications being increasingly investigated. One of the challenges is controlling the inhibitors degree of selectivity, assessed by in vitro profiling against panels of protein kinases. We manually extracted, compiled, and standardized such profiles published in the literature: we collected 356 908 data points corresponding to 482 protein kinases, 2106 inhibitors, and 661 patents. We then analyzed this data set in terms of kinome coverage, results reproducibility, popularity, and degree of selectivity of both kinases and inhibitors. We used the data set to create robust proteochemometric models capable of predicting kinase activity (the ligand-target space was modeled with an externally validated RMSE of 0.41 ± 0.02 log units and R02 0.74 ± 0.03), in order to account for missing or unreliable measurements. The influence on the prediction quality of parameters such as number of measurements, Murcko scaffold frequency or inhibitor type was assessed. Interpretation of the models enabled to highlight inhibitors and kinases properties correlated with higher affinities, and an analysis in the context of kinases crystal structures was performed. Overall, the models quality allows the accurate prediction of kinase-inhibitor activities and their structural interpretation, thus paving the way for the rational design of compounds with a targeted selectivity profile.

Prediction of Cell-Penetrating Peptides

The in silico methods for the prediction of the cell-penetrating peptides are reviewed. Those include the multivariate statistical methods, machine-learning methods such as the artificial neural networks and support vector machines, and molecular modeling techniques including molecular docking and molecular dynamics.The applicability of the methods is demonstrated on the basis of the exemplary cases from the literature.

Pred-binding: large-scale protein-ligand binding affinity prediction

Drug target interactions (DTIs) are crucial in pharmacology and drug discovery. Presently, experimental determination of compound-protein interactions remains challenging because of funding investment and difficulties of purifying proteins. In this study, we proposed two in silico models based on support vector machine (SVM) and random forest (RF), using 1589 molecular descriptors and 1080 protein descriptors in 9948 ligand-protein pairs to predict DTIs that were quantified by Ki values. The cross-validation coefficient of determination of 0.6079 for SVM and 0.6267 for RF were obtained, respectively. In addition, the two-dimensional (2D) autocorrelation, topological charge indices and three-dimensional (3D)-MoRSE descriptors of compounds, the autocorrelation descriptors and the amphiphilic pseudo-amino acid composition of protein are found most important for Ki predictions. These models provide a new opportunity for the prediction of ligand-receptor interactions that will facilitate the target discovery and toxicity evaluation in drug development.

The recent progress in proteochemometric modelling: focusing on target descriptors, cross-term descriptors and application scope

As an extension of the conventional quantitative structure activity relationship models, proteochemometric (PCM) modelling is a computational method that can predict the bioactivity relations between multiple ligands and multiple targets. Traditional PCM modelling includes three essential elements: descriptors (including target descriptors, ligand descriptors and cross-term descriptors), bioactivity data and appropriate learning functions that link the descriptors to the bioactivity data. Since its appearance, PCM modelling has developed rapidly over the past decade by taking advantage of the progress of different descriptors and machine learning techniques, along with the increasing amounts of available bioactivity data. Specifically, the new emerging target descriptors and cross-term descriptors not only significantly increased the performance of PCM modelling but also expanded its application scope from traditional protein-ligand interaction to more abundant interactions, including protein-peptide, protein-DNA and even protein-protein interactions. In this review, target descriptors and cross-term descriptors, as well as the corresponding application scope, are intensively summarized. Additionally, we look forward to seeing PCM modelling extend into new application scopes, such as Target-Catalyst-Ligand systems, with the further development of descriptors, machine learning techniques and increasing amounts of available bioactivity data.

Cheminformatics Research at the Unilever Centre for Molecular Science Informatics Cambridge

The Centre for Molecular Informatics, formerly Unilever Centre for Molecular Science Informatics (UCMSI), at the University of Cambridge is a world-leading driving force in the field of cheminformatics. Since its opening in 2000 more than 300 scientific articles have fundamentally changed the field of molecular informatics. The Centre has been a key player in promoting open chemical data and semantic access. Though mainly focussing on basic research, close collaborations with industrial partners ensured real world feedback and access to high quality molecular data. A variety of tools and standard protocols have been developed and are ubiquitous in the daily practice of cheminformatics. Here, we present a retrospective of cheminformatics research performed at the UCMSI, thereby highlighting historical and recent trends in the field as well as indicating future directions.

Chemically Aware Model Builder (camb): an R package for property and bioactivity modelling of small molecules

BACKGROUND

In silico predictive models have proved to be valuable for the optimisation of compound potency, selectivity and safety profiles in the drug discovery process.

RESULTS

camb is an R package that provides an environment for the rapid generation of quantitative Structure-Property and Structure-Activity models for small molecules (including QSAR, QSPR, QSAM, PCM) and is aimed at both advanced and beginner R users. camb's capabilities include the standardisation of chemical structure representation, computation of 905 one-dimensional and 14 fingerprint type descriptors for small molecules, 8 types of amino acid descriptors, 13 whole protein sequence descriptors, filtering methods for feature selection, generation of predictive models (using an interface to the R package caret), as well as techniques to create model ensembles using techniques from the R package caretEnsemble). Results can be visualised through high-quality, customisable plots (R package ggplot2).

CONCLUSIONS

Overall, camb constitutes an open-source framework to perform the following steps: (1) compound standardisation, (2) molecular and protein descriptor calculation, (3) descriptor pre-processing and model training, visualisation and validation, and (4) bioactivity/property prediction for new molecules. camb aims to speed model generation, in order to provide reproducibility and tests of robustness. QSPR and proteochemometric case studies are included which demonstrate camb's application.Graphical abstractFrom compounds and data to models: a complete model building workflow in one package.

Modelling ligand selectivity of serine proteases using integrative proteochemometric approaches improves model performance and allows the multi-target dependent interpretation of features

Serine proteases, implicated in important physiological functions, have a high intra-family similarity, which leads to unwanted off-target effects of inhibitors with insufficient selectivity. However, the availability of sequence and structure data has now made it possible to develop approaches to design pharmacological agents that can discriminate successfully between their related binding sites. In this study, we have quantified the relationship between 12,625 distinct protease inhibitors and their bioactivity against 67 targets of the serine protease family (20,213 data points) in an integrative manner, using proteochemometric modelling (PCM). The benchmarking of 21 different target descriptors motivated the usage of specific binding pocket amino acid descriptors, which helped in the identification of active site residues and selective compound chemotypes affecting compound affinity and selectivity. PCM models performed better than alternative approaches (models trained using exclusively compound descriptors on all available data, QSAR) employed for comparison with R(2)/RMSE values of 0.64 ± 0.23/0.66 ± 0.20 vs. 0.35 ± 0.27/1.05 ± 0.27 log units, respectively. Moreover, the interpretation of the PCM model singled out various chemical substructures responsible for bioactivity and selectivity towards particular proteases (thrombin, trypsin and coagulation factor 10) in agreement with the literature. For instance, absence of a tertiary sulphonamide was identified to be responsible for decreased selective activity (by on average 0.27 ± 0.65 pChEMBL units) on FA10. Among the binding pocket residues, the amino acids (arginine, leucine and tyrosine) at positions 35, 39, 60, 93, 140 and 207 were observed as key contributing residues for selective affinity on these three targets.

ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins

BACKGROUND

The exponential growth of protein structural and sequence databases is enabling multifaceted approaches to understanding the long sought sequence-structure-function relationship. Advances in computation now make it possible to apply well-established data mining and pattern recognition techniques to these data to learn models that effectively relate structure and function. However, extracting meaningful numerical descriptors of protein sequence and structure is a key issue that requires an efficient and widely available solution.

RESULTS

We here introduce ProtDCal, a new computational software suite capable of generating tens of thousands of features considering both sequence-based and 3D-structural descriptors. We demonstrate, by means of principle component analysis and Shannon entropy tests, how ProtDCal's sequence-based descriptors provide new and more relevant information not encoded by currently available servers for sequence-based protein feature generation. The wide diversity of the 3D-structure-based features generated by ProtDCal is shown to provide additional complementary information and effectively completes its general protein encoding capability. As demonstration of the utility of ProtDCal's features, prediction models of N-linked glycosylation sites are trained and evaluated. Classification performance compares favourably with that of contemporary predictors of N-linked glycosylation sites, in spite of not using domain-specific features as input information.

CONCLUSIONS

ProtDCal provides a friendly and cross-platform graphical user interface, developed in the Java programming language and is freely available at: http://bioinf.sce.carleton.ca/ProtDCal/ . ProtDCal introduces local and group-based encoding which enhances the diversity of the information captured by the computed features. Furthermore, we have shown that adding structure-based descriptors contributes non-redundant additional information to the features-based characterization of polypeptide systems. This software is intended to provide a useful tool for general-purpose encoding of protein sequences and structures for applications is protein classification, similarity analyses and function prediction.

Proteochemometric modelling coupled to in silico target prediction: an integrated approach for the simultaneous prediction of polypharmacology and binding affinity/potency of small molecules

The rampant increase of public bioactivity databases has fostered the development of computational chemogenomics methodologies to evaluate potential ligand-target interactions (polypharmacology) both in a qualitative and quantitative way. Bayesian target prediction algorithms predict the probability of an interaction between a compound and a panel of targets, thus assessing compound polypharmacology qualitatively, whereas structure-activity relationship techniques are able to provide quantitative bioactivity predictions. We propose an integrated drug discovery pipeline combining in silico target prediction and proteochemometric modelling (PCM) for the respective prediction of compound polypharmacology and potency/affinity. The proposed pipeline was evaluated on the retrospective discovery of Plasmodium falciparum DHFR inhibitors. The qualitative in silico target prediction model comprised 553,084 ligand-target associations (a total of 262,174 compounds), covering 3,481 protein targets and used protein domain annotations to extrapolate predictions across species. The prediction of bioactivities for plasmodial DHFR led to a recall value of 79% and a precision of 100%, where the latter high value arises from the structural similarity of plasmodial DHFR inhibitors and T. gondii DHFR inhibitors in the training set. Quantitative PCM models were then trained on a dataset comprising 20 eukaryotic, protozoan and bacterial DHFR sequences, and 1,505 distinct compounds (in total 3,099 data points). The most predictive PCM model exhibited R²_0test and RMSE_test values of 0.79 and 0.59 pIC₅₀ units respectively, which was shown to outperform models based exclusively on compound (R²_0test/RMSE_test = 0.63/0.78) and target information (R²_0test/RMSE_test = 0.09/1.22), as well as inductive transfer knowledge between targets, with respective R²_0test and RMSE_test values of 0.76 and 0.63 pIC₅₀ units. Finally, both methods were integrated to predict the protein targets and the potency on plasmodial DHFR for the GSK TCAMS dataset, which comprises 13,533 compounds displaying strong anti-malarial activity. 534 of those compounds were identified as DHFR inhibitors by the target prediction algorithm, while the PCM algorithm identified 25 compounds, and 23 compounds (predicted pIC₅₀ > 7) were identified by both methods. Overall, this integrated approach simultaneously provides target and potency/affinity predictions for small molecules.

Graphical abstract

A statistical physics perspective on alignment-independent protein sequence comparison

Motivation: Within bioinformatics, the textual alignment of amino acid sequences has long dominated the determination of similarity between proteins, with all that implies for shared structure, function and evolutionary descent. Despite the relative success of modern-day sequence alignment algorithms, so-called alignment-free approaches offer a complementary means of determining and expressing similarity, with potential benefits in certain key applications, such as regression analysis of protein structure-function studies, where alignment-base similarity has performed poorly.

Results: Here, we offer a fresh, statistical physics-based perspective focusing on the question of alignment-free comparison, in the process adapting results from ‘first passage probability distribution’ to summarize statistics of ensemble averaged amino acid propensity values. In this article, we introduce and elaborate this approach.

Contact: d.r.flower@aston.ac.uk