Search

Background: Recently, drug repositioning has received considerable attention for its advantage to pharmaceutical industries in drug development. Artificial intelligence techniques have greatly enhanced drug reproduction by discovering therapeutic drug profiles, side effects, and new target proteins. However, as the number of drugs increases, their targets and enormous interactions produce imbalanced data that might not be preferable as an input to a prediction model immediately. Methods: This paper proposes a novel scheme for predicting drug–target interactions (DTIs) based on drug chemical structures and protein sequences. The drug Morgan fingerprint, drug constitutional descriptors, protein amino acid composition, and protein dipeptide composition were employed to extract the drugs and protein's characteristics. Then, the proposed approach for extracting negative samples using a support vector machine one-class classifier was developed to tackle the imbalanced data problem feature sets from the drug–target dataset. Negative and positive samplings were constructed and fed into different prediction algorithms to identify DTIs. A 10-fold CV validation test procedure was applied to assess the predictability of the proposed method, in addition to the study of the effectiveness of the chemical and physical features in the evaluation and discovery of the drug–target interactions. Results: Our experimental model outperformed existing techniques concerning the curve for receiver operating characteristic (AUC), accuracy, precision, recall F-score, mean square error, and MCC. The results obtained by the AdaBoost classifier enhanced prediction accuracy by 2.74%, precision by 1.98%, AUC by 1.14%, F-score by 3.53%, and MCC by 4.54% over existing methods. [ABSTRACT FROM AUTHOR]

Predicting which proteins interact together from amino acid sequences is an important task. We develop a method to pair interacting protein sequences which leverages the power of protein language models trained on multiple sequence alignments (MSAs), such as MSA Transformer and the EvoFormer module of AlphaFold. We formulate the problem of pairing interacting partners among the paralogs of two protein families in a differentiable way. We introduce a method called Differentiable Pairing using Alignment-based Language Models (DiffPALM) that solves it by exploiting the ability of MSA Transformer to fill in masked amino acids in multiple sequence alignments using the surrounding context. MSA Transformer encodes coevolution between functionally or structurally coupled amino acids within protein chains. It also captures inter-chain coevolution, despite being trained on single-chain data. Relying on MSA Transformer without fine-tuning, DiffPALM outperforms existing coevolutionbased pairing methods on difficult benchmarks of shallow multiple sequence alignments extracted from ubiquitous prokaryotic protein datasets. It also outperforms an alternative method based on a state-of-the-art protein language model trained on single sequences. Paired alignments of interacting protein sequences are a crucial ingredient of supervised deep learning methods to predict the three-dimensional structure of protein complexes. Starting from sequences paired by DiffPALM substantially improves the structure prediction of some eukaryotic protein complexes by AlphaFold-Multimer. It also achieves competitive performance with using orthology-based pairing. [ABSTRACT FROM AUTHOR]

Descriptors play a pivotal role in enzyme design for the greener synthesis of biochemicals, as they could characterize enzymes and chemicals from the physicochemical and evolutionary perspective. This study examined the effects of various descriptors on the performance of Random Forest model used for enzyme-chemical relationships prediction. We curated activity data of seven specific enzyme families from the literature and developed the pipeline for evaluation the machine learning model performance using 10-fold cross-validation. The influence of protein and chemical descriptors was assessed in three scenarios, which were predicting the activity of unknown relations between known enzymes and known chemicals (new relationship evaluation), predicting the activity of novel enzymes on known chemicals (new enzyme evaluation), and predicting the activity of new chemicals on known enzymes (new chemical evaluation). The results showed that protein descriptors significantly enhanced the classification performance of model on new enzyme evaluation in three out of the seven datasets with the greatest number of enzymes, whereas chemical descriptors appear no effect. A variety of sequence-based and structure-based protein descriptors were constructed, among which the esm-2 descriptor achieved the best results. Using enzyme families as labels showed that descriptors could cluster proteins well, which could explain the contributions of descriptors to the machine learning model. As a counterpart, in the new chemical evaluation, chemical descriptors made significant improvement in four out of the seven datasets, while protein descriptors appear no effect. We attempted to evaluate the generalization ability of the model by correlating the statistics of the datasets with the performance of the models. The results showed that datasets with higher sequence similarity were more likely to get better results in the new enzyme evaluation and datasets with more enzymes were more likely beneficial from the protein descriptor strategy. This work provides guidance for the development of machine learning models for specific enzyme families. [ABSTRACT FROM AUTHOR]

Most intracellular activities of living organisms are performed by proteins that have unique and complex 3-Dimensional (3D) structures, playing very important roles in their operations. Due to importance and challenges of predicting 3D structures for proteins, laboratory methods with limitations such as time consuming and high cost have been developed. Computational methods use a sequence of amino acids to obtain the 3D structure. They encounter with a nondeterministic problem having polynomial completion time (NP-Complete problem); with a chain of amino acids as input, and a protein, with 3D structure, as output. In this paper, a new population-based algorithm, under Predatory Search Strategy-Particle Swarm Optimization (PSS-PSO) framework, is presented for predicting the 3D structure; using Hydrophobic-Polar (HP) model on Face-Centered Cubic (FCC) lattice. In this approach, name TRL-PSSPSO, two new moves are proposed to direct each solution toward the native structure: Local Move for reaching a dense hydrophobic core and large H-H contacts and Meta Move for reaching optimal structure, by using Transfer learning. Two datasets are considered for evaluating and the results on some set of standard protein benchmarks show outperforming the state-of-the-art approaches. They show that the proposed approach can improve the accuracy of template-free prediction in an acceptable manner. [ABSTRACT FROM AUTHOR]

Protein structure analysis is essential in various bioinformatics domains such as drug discovery, disease diagnosis, and evolutionary studies. Within structural biology, the classification of protein structures is pivotal, employing machine learning algorithms to categorize structures based on data from databases like the Protein Data Bank (PDB). To predict protein functions, embeddings based on protein sequences have been employed. Creating numerical embeddings that preserve vital information while considering protein structure and sequence presents several challenges. The existing literature lacks a comprehensive and effective approach that combines structural and sequence-based features to achieve efficient protein classification. While large language models (LLMs) have exhibited promising outcomes for protein function prediction, their focus primarily lies on protein sequences, disregarding the 3D structures of proteins. The quality of embeddings heavily relies on how well the geometry of the embedding space aligns with the underlying data structure, posing a critical research question. Traditionally, Euclidean space has served as a widely utilized framework for embeddings. In this study, we propose a novel method for designing numerical embeddings in Euclidean space for proteins by leveraging 3D structure information, specifically employing the concept of contact maps. These embeddings are synergistically combined with features extracted from LLMs and traditional feature engineering techniques to enhance the performance of embeddings in supervised protein analysis. Experimental results on benchmark datasets, including PDB Bind and STCRDAB, demonstrate the superior performance of the proposed method for protein function prediction. [ABSTRACT FROM AUTHOR]

Missense variation in genomes can affect protein structure stability and, in turn, the cell physiology behavior. Predicting the impact of those variations is relevant, and the best-performing computational tools exploit the protein structure information. However, most of the current protein sequence variants are unresolved, and comparative or ab initio tools can provide a structure. Here, we evaluate the impact of model structures, compared to experimental structures, on the predictors of protein stability changes upon single-point mutations, where no significant changes are expected between the original and the mutated structures. We show that there are substantial differences among the computational tools. Methods that rely on coarse-grained representation are less sensitive to the underlying protein structures. In contrast, tools that exploit more detailed molecular representations are sensible to structures generated from comparative modeling, even on single-residue substitutions. [ABSTRACT FROM AUTHOR]

Simple Summary: This study aimed to create an intelligent computer model called TAFPred to predict how proteins move and twist by looking at their sequences. By analyzing different features of the protein sequences, the model can accurately estimate the degree of flexibility of protein structures per residue. The investigators used an advanced machine learning technique called LightGBM to make these predictions even better. Compared to existing methods, TAFPred significantly improved in accurately predicting how proteins bend and twist within the individual and collective residual degree of freedom. This study is vital because understanding protein flexibility helps us know how they function in our bodies. By improving our ability to predict protein movements, this study brings us closer to unlocking the secrets of how proteins work and the role of protein flexibility in cellular functions, which can have critical applications in medicine and biology. Protein molecules show varying degrees of flexibility throughout their three-dimensional structures. The flexibility is determined by the fluctuations in torsion angles, specifically phi (φ) and psi (ψ), which define the protein backbone. These angle fluctuations are derived from variations in backbone torsion angles observed in different models. By analyzing the fluctuations in Cartesian coordinate space, we can understand the structural flexibility of proteins. Predicting torsion angle fluctuations is valuable for determining protein function and structure when these angles act as constraints. In this study, a machine learning method called TAFPred is developed to predict torsion angle fluctuations using protein sequences directly. The method incorporates various features, such as disorder probability, position-specific scoring matrix profiles, secondary structure probabilities, and more. TAFPred, employing an optimized Light Gradient Boosting Machine Regressor (LightGBM), achieved high accuracy with correlation coefficients of 0.746 and 0.737 and mean absolute errors of 0.114 and 0.123 for the φ and ψ angles, respectively. Compared to the state-of-the-art method, TAFPred demonstrated significant improvements of 10.08% in MAE and 24.83% in PCC for the phi angle and 9.93% in MAE, and 22.37% in PCC for the psi angle. [ABSTRACT FROM AUTHOR]

Self-supervised pretraining on protein sequences has led to state-of-the art performance on protein function and fitness prediction. However, sequence-only methods ignore the rich information contained in experimental and predicted protein structures. Meanwhile, inverse folding methods reconstruct a protein's amino-acid sequence given its structure, but do not take advantage of sequences that do not have known structures. In this study, we train a masked inverse folding protein masked language model parameterized as a structured graph neural network. During pretraining, this model learns to reconstruct corrupted sequences conditioned on the backbone structure. We then show that using the outputs from a pretrained sequence-only protein masked language model as input to the inverse folding model further improves pretraining perplexity. We evaluate both of these models on downstream protein engineering tasks and analyze the effect of using information from experimental or predicted structures on performance. [ABSTRACT FROM AUTHOR]

Aegerolysins are remarkable proteins. They are distributed over the tree of life, being relatively widespread in bacteria and fungi, but also present in some insects, plants, protozoa, and viruses. Despite their abundance in cells of certain developmental stages and their presence in secretomes, only a few aegerolysins have been studied in detail. Their function, in particular, is intriguing. Here, we summarize previously published findings on the distribution, molecular interactions, and function of these versatile aegerolysins. They have very diverse protein sequences but a common fold. The machine learning approach of the AlphaFold2 algorithm, which incorporates physical and biological knowledge of protein structures and multisequence alignments, provides us new insights into the aegerolysins and their pore-forming partners, complemented by additional genomic support. We hypothesize that aegerolysins are involved in the mechanisms of competitive exclusion in the niche. [ABSTRACT FROM AUTHOR]

Background: Optimization of DNA and protein sequences based on Machine Learning models is becoming a powerful tool for molecular design. Activation maximization offers a simple design strategy for differentiable models: one-hot coded sequences are first approximated by a continuous representation, which is then iteratively optimized with respect to the predictor oracle by gradient ascent. While elegant, the current version of the method suffers from vanishing gradients and may cause predictor pathologies leading to poor convergence. Results: Here, we introduce Fast SeqProp, an improved activation maximization method that combines straight-through approximation with normalization across the parameters of the input sequence distribution. Fast SeqProp overcomes bottlenecks in earlier methods arising from input parameters becoming skewed during optimization. Compared to prior methods, Fast SeqProp results in up to 100-fold faster convergence while also finding improved fitness optima for many applications. We demonstrate Fast SeqProp's capabilities by designing DNA and protein sequences for six deep learning predictors, including a protein structure predictor. Conclusions: Fast SeqProp offers a reliable and efficient method for general-purpose sequence optimization through a differentiable fitness predictor. As demonstrated on a variety of deep learning models, the method is widely applicable, and can incorporate various regularization techniques to maintain confidence in the sequence designs. As a design tool, Fast SeqProp may aid in the development of novel molecules, drug therapies and vaccines. [ABSTRACT FROM AUTHOR]

Protein secondary structures are important in many biological processes and applications. Due to advances in sequencing methods, there are many proteins sequenced, but fewer proteins with secondary structures defined by laboratory methods. With the development of computer technology, computational methods have (started to) become the most important methodologies for predicting secondary structures. We evaluated two different approaches to this problem—driven by the recent results obtained by computational methods in this task—(i) template-free classifiers, based on machine learning techniques; and (ii) template-based classifiers, based on searching tools. Both approaches are formed by different sub-classifiers—six for template-free and two for template-based, each with a specific view of the protein. Our results show that these ensembles improve the results of each approach individually. [ABSTRACT FROM AUTHOR]

The subcellular locations of proteins are closely related to their functions. In the past few decades, the application of machine learning algorithms to predict protein subcellular locations has been an important topic in proteomics. However, most studies in this field used only amino acid sequences as the data source. Only a few works focused on other protein data types. For example, three-dimensional structures, which contain far more functional protein information than sequences, remain to be explored. In this work, we extracted various handcrafted features to describe the protein structures from physical, chemical, and topological aspects, as well as the learned features obtained by deep neural networks. We then used these features to classify the protein subcellular locations. Our experimental results demonstrated that some of these structural features have a certain effect on the protein location classification, and can help improve the performance of sequence-based location predictors. Our method provides a new view for the analysis of protein spatial distribution, and is anticipated to be used in revealing the relationships between protein structures and functions. [ABSTRACT FROM AUTHOR]