SPRoBERTa: protein embedding learning with local fragment modeling.

As one of the recalcitrant challenges in life sciences and biomedicine, protein function prediction suffers from a deluge of AI-designed proteins, particularly having to face multi-modal information in the era of big data. Importing the high-throughput neural-network-based prediction framework to replace the low-throughput biological experiments, a universal multi-modal method is straightforward in addressing the growing gap between known sequences and predicting functions. To bridge the gap, we propose ProtGO, a three-step framework for predicting protein function, which leverages the credible Gene Ontology (GO) knowledge base and integrates four common modalities. Specifically, we first introduce frontier pre-trained protein language models (PLMs) for representation learning of mainstay functional protein sequences. For the remaining multi-modal data, we design a text alignment module for explainable text descriptions, a taxonomy encoding module for species-specific taxonomy, and a GO graph embedding module for biological GO relations. Each module is independent and adaptive for the referenced modalities. By harnessing these four knowledge representations, ProtGO maximizes the potential of GO resources, enhancing the performance of vanilla PLMs and biological language models (LMs) in downstream GO prediction tasks. Extensive experiments demonstrate that ProtGO significantly advances the abilities of state-of-the-art PLMs to predict protein functions: approximately 8% to 27% increase in the maximum F1 measure (Fmax) compared to base models. These comprehensive studies confirm ProtGO's capability to deliver outstanding performance in protein function prediction by utilizing a rich blend of functional and evolutionary knowledge. Our source code and all the data are available at https://github.com/sunyatawang/ProtGO.

The prediction of protein function is a difficult and important problem in computational biology. In this study, an efficient method is presented to predict protein function with sequence composition information. Four kinds of basic building blocks of protein sequences are investigated, including N-grams, binary profiles, PFAM domains and InterPro domains. The protein sequences are mapped into high-dimensional vectors by using the occurrence frequencies of each kind of building blocks. The resulting vectors are then taken as input to support vector machine to predict their function based on gene ontology. Experiments are conducted over the subset of GOA database. The experimental results show that the protein function can be predicted from primary sequence information. The method based on InterPro domains outperforms the other building blocks, and gets an overall accuracy of 0.87 and ROC score is 0.93. We also demonstrate that the use of feature extraction algorithms such as latent semantic analysis and nonnegative matrix factorization, can efficiently remove noise and improve the prediction efficiency without significantly degrading the performance. The results obtained here are helpful for the prediction of protein function by using only sequence information.

Protein secondary structure predictions and amino acid long range contact map predictions from primary sequence of proteins have been explored to aid in modelling protein tertiary structures. In order to evaluate the usefulness of secondary structure and 3D-residue contact prediction methods to model protein structures we have used the known Q3 (alpha-helix,beta-strands and irregular turns/loops) secondary structure information, along with residue-residue contact information as restraints for MODELLER. We present here results of our modelling studies on 30 best resolved single domain protein structures of varied lengths. The results shows that it is very difficult to obtain useful models even with 100% accurate secondary structure predictions and accurate residue contact predictions for up to 30% of residues in a sequence. The best models that we obtained for proteins of lengths 37, 70, 118, 136 and 193 amino acid residues are of RMSDs 4.17, 5.27, 9.12, 7.89 and 9.69,respectively. The results show that one can obtain better models for the proteins which have high percent of alpha-helix content. This analysis further shows that MODELLER restrain optimization program can be useful only if we have truly homologous structure(s) as a template where it derives numerous restraints, almost identical to the templates used. This analysis also clearly indicates that even if we satisfy several true residue-residue contact distances, up to 30%of their sequence length with fully known secondary structural information, we end up predicting model structures much distant from their corresponding native structures.

Most of the protein structure prediction methods use a multi-step process, which often includes secondary structure prediction, contact prediction, fragment generation, clustering, etc. For many years, secondary structure prediction has been the workhorse for numerous methods aimed at predicting protein structure and function. This paper presents a new mixed integer linear optimization (MILP)-based consensus method: a Consensus scheme based On a mixed integer liNear optimization method for seCOndary stRucture preDiction (CONCORD). Based on seven secondary structure prediction methods, SSpro, DSC, PROF, PROFphd, PSIPRED, Predator and GorIV, the MILP-based consensus method combines the strengths of different methods, maximizes the number of correctly predicted amino acids and achieves a better prediction accuracy. The method is shown to perform well compared with the seven individual methods when tested on the PDBselect25 training protein set using sixfold cross validation. It also performs well compared with another set of 10 online secondary structure prediction servers (including several recent ones) when tested on the CASP9 targets ( http://predictioncenter.org/casp9/ ). The average Q3 prediction accuracy is 83.04 per cent for the sixfold cross validation of the PDBselect25 set and 82.3 per cent for the CASP9 targets. We have developed a MILP-based consensus method for protein secondary structure prediction. A web server, CONCORD, is available to the scientific community at http://helios.princeton.edu/CONCORD .

Protein sequences are symbols generally different characters representing the 20 amino acids used in human proteins those sequences can range from the very sort to the very long. There are many proteins database for the sequences are known but the function and functional annotation is not. Protein function prediction (PFP) as well as functional annotation (FA) from its structure or sequence is a major field of bioinformatics at the same time how to judge how well perform these algorithms. We proposed the novel method that converts the protein function problem into a language translation problem by a new proposed protein sequence language encoded to the protein function language decoded and build a recurrent neural machine encoding decoding translator (RNNEDT) based on the recurrent neural networks model. The excellent acting on training, testing datasets exhibits the proposed system as an improving direction for PFP. The proposed system alters the PFP matter to a language translation issue as well as applies a recurrent neural network machine version model for PFP, and visualizes the annotation of biological process (BP), molecular function (MF), as well as cellular component (CP).

Protein function, which is determined by sequence, structure, and other characteristics, plays a crucial role in an organism’s performance. Existing protein function prediction methods mainly rely on sequence data and often ignore structural properties that are crucial for accurate prediction. Protein structure provides richer spatial and functional insights, which can significantly improve prediction accuracy. In this work, we propose a multi-modal protein function prediction model (MMPFP) that integrates protein sequence and structure information through the use of GCN, CNN, and Transformer models. We validate the model using the PDBest dataset, demonstrating that MMPFP outperforms traditional single-modal models in the molecular function (MF), biological process (BP), and cellular component (CC) prediction tasks. Specifically, MMPFP achieved AUPR scores of 0.693, 0.355, and 0.478; scores of 0.752, 0.629, and 0.691; and scores of 0.336, 0.488, and 0.459, showing a 3–5% improvement over single-modal models. Additionally, ablation studies confirm the effectiveness of the Transformer module within the GCN branch, further validating MMPFP’s superior performance over existing methods. This multi-modal approach offers a more accurate and comprehensive framework for protein function prediction, addressing key limitations of current models.

Protein function prediction is a crucial task in bioinformatics and computational biology, as it enables the understanding of disease mechanisms, development of new therapeutics, and improvement of crop yields. Despite significant advances, the majority of protein functions remain unknown or poorly annotated, hindering our understanding of biological systems. This review provides a comprehensive overview of the available methods for protein function prediction, categorizing them into eight classes based on the sources of information they use. We examine over 35 methods, including traditional sequence-based approaches and recent advances in machine learning and natural language processing. We also discuss the incorporation of background knowledge in Gene Ontology and zero-shot predictions. To improve protein function prediction, we highlight the need for developing more accurate and robust methods that integrate multiple sources of information. We provide several practical notes for choosing and interpreting the results of protein function prediction methods.

The prediction of protein function as well as the reconstruction of evolutionary genesis employing sequence comparison at large is still the most powerful tool in sequence analysis. Due to the exponential growth of the number of known protein sequences and the subsequent quadratic growth of the similarity matrix, the computation of the Similarity Matrix of Proteins (SIMAP) becomes a computational intensive task. The SIMAP database provides a comprehensive and up-to-date pre-calculation of the protein sequence similarity matrix, sequence-based features and sequence clusters. As of September 2009, SIMAP covers 48 million proteins and more than 23 million non-redundant sequences. Novel features of SIMAP include the expansion of the sequence space by including databases such as ENSEMBL as well as the integration of metagenomes based on their consistent processing and annotation. Furthermore, protein function predictions by Blast2GO are pre-calculated for all sequences in SIMAP and the data access and query functions have been improved. SIMAP assists biologists to query the up-to-date sequence space systematically and facilitates large-scale downstream projects in computational biology. Access to SIMAP is freely provided through the web portal for individuals (http://mips.gsf.de/simap/) and for programmatic access through DAS (http://webclu.bio.wzw.tum.de/das/) and Web-Service (http://mips.gsf.de/webservices/services/SimapService2.0?wsdl).

Proteins are the main undertakers of life activities, and accurately predicting their biological functions can help human better understand life mechanism and promote the development of themselves. With the rapid development of high-throughput technologies, an abundance of proteins are discovered. However, the gap between proteins and function annotations is still huge. To accelerate the process of protein function prediction, some computational methods taking advantage of multiple data have been proposed. Among these methods, the deep-learning-based methods are currently the most popular for their capability of learning information automatically from raw data. However, due to the diversity and scale difference between data, it is challenging for existing deep learning methods to capture related information from different data effectively. In this paper, we introduce a deep learning method that can adaptively learn information from protein sequences and biomedical literature, namely DeepAF. DeepAF first extracts the two kinds of information by using different extractors, which are built based on pre-trained language models and can capture rudimentary biological knowledge. Then, to integrate those information, it performs an adaptive fusion layer based on a Cross-attention mechanism that considers the knowledge of mutual interactions between two information. Finally, based on the mixed information, DeepAF utilizes logistic regression to obtain prediction scores. The experimental results on the datasets of two species (i.e., Human and Yeast) show that DeepAF outperforms other state-of-the-art approaches.

The exploitation of fundamental invariants is among the most elegant solutions to many computational problems in a wide variety of domains. One of the more powerful approaches to exploit invariants is the principle of by association. In particular, the principle of guilt by association is the foundation of remote homolog detection, protein function prediction, disease subtype diagnosis, treatment plan prognosis, and other challenges in computational biology. The principle suggests that two entities are in a specific relationship if they exhibit invariant properties underlying that relationship. For example, a protein is predicted to have a particular biological function if it exhibits the underlying invariant properties of that functional group---viz., guilty by association to other members of that functional group through the shared invariant properties.In my talk, I plan to present several facets of guilt by association in the computational prediction of protein function and draw parallels of these facets in information retrieval. Specifically, I plan to touch on the following facets: (a) the issue of chance associations; (b) novel generalizable forms of association; (c) fusion of multiple heterogeneous sources of evidence; (d) the dichotomy of knowing to a high degree of reliability that two entities are in some relationship and yet not knowing what that relationship is. I hope this talk will be, for the informational retrieval community, a window to the opportunities in computational biology that may benefit from the depth and variety of solutions information retrieval has to offer.

MotivationProtein function prediction is important for drug development and disease treatment. Recently, deep learning methods have leveraged protein sequence and structural information, achieving remarkable progress in the field of protein function prediction. However, existing methods ignore the complex multimodal interaction information between sequence and structural features. Since protein sequence and structural information reveal the functional characteristics of proteins from different perspectives, it is challenging to effectively fuse the information from these two modalities to portray protein functions more comprehensively. In addition, current methods have difficulty in effectively capturing long-range dependencies and global contextual information in protein sequences during feature extraction, thus limiting the ability of the model to recognize critical functional residues.ResultsIn this study, we propose a novel framework termed Multi-stage Attention-based Extraction and Fusion model for GO prediction (MAEF-GO) based on a multistage attention mechanism to predict protein functions. MAEF-GO innovatively integrates the graph convolutional network and the graph attention network to extract protein structural features. To address the issue of modeling long-range dependencies within protein sequences, we introduce a frequency-domain attention mechanism capable of extracting global contextual relationships. Additionally, a cross-attention module is implemented to facilitate interactive fusion between protein sequence and structural modalities. Experimental evaluations demonstrate that MAEF-GO achieves superior performance compared to several state-of-the-art baseline models across standard benchmarks. Furthermore, analysis of the cross-attention weight distributions demonstrates MAEF-GO’s interpretability. It can effectively identify critical functional residues of proteins.Availability and implementationThe MAEF-GO source code can be found at https://github.com/nebstudio/MAEF-GO, an archived snapshot of the code used in this study is also available via Zenodo at https://doi.org/10.5281/zenodo.15422392.

Machine learning-guided protein engineering is a new paradigm that enables the optimization of complex protein functions. Machine-learning methods use data to predict protein function without requiring a detailed model of the underlying physics or biological pathways. They accelerate protein engineering by learning from information contained in all measured variants and using it to select variants that are likely to be improved. We begin with a review of the basics of machine learning with a focus on applications to protein engineering and protein sequence-function datasets (Chapter 1). We used the entire machine-learning guided engineering paradigm to engineer the algal-derived light-gated channel channelrhodopsin (ChR), which can be used to modulate neuronal activity with light. We build models that discover ChRs with strong plasma membrane localization in mammalian cells (Chapter 2) and unprecedented light sensitivity and photocurrents for optogenetic applications (Chapter 3). Machine learning-guided evolution requires a machine-learning model that learns the relationship between sequence and function. For machine-learning models to learn about protein sequences, protein sequences must be represented as vectors or matrices of numbers. How each protein sequence is represented determines what can be learned. We learn continuous vector encodings of sequences from patterns in unlabeled sequences (Chapter 4). Learned encodings are low-dimensional, do not require alignments, and may improve performance by transferring information in unlabeled sequences to specific prediction tasks. Alternately, we demonstrate an interpretable Gaussian process kernel tailored to biological sequences (Chapter 6). In addition to a model to predict function from sequence, engineering requires a method to use the model to choose sequences for the next round of evolution. Most machine-learning guided engineering strategies assume that selected sequences can be queried directly. However, in directed evolution it is common to design a library of sequences and then sample stochastic batches from that library. We propose a batched stochastic Bayesian optimization algorithm for iteratively designing and screening site-saturation mutagenesis libraries (Chapter 5).

Nature often brings several domains together to form multidomain and multifunctional proteins with a vast number of possibilities. In our previous study, we disclosed that the protein function prediction problem is naturally and inherently Multi-Instance Multilabel (MIML) learning tasks. Automated protein function prediction is typically implemented under the assumption that the functions of labeled proteins are complete; that is, there are no missing labels. In contrast, in practice just a subset of the functions of a protein are known, and whether this protein has other functions is unknown. It is evident that protein function prediction tasks suffer from weak-label problem; thus protein function prediction with incomplete annotation matches well with the MIML with weak-label learning framework. In this paper, we have applied the state-of-the-art MIML with weak-label learning algorithm MIMLwel for predicting protein functions in two typical real-world electricigens organisms which have been widely used in microbial fuel cells (MFCs) researches. Our experimental results validate the effectiveness of MIMLwel algorithm in predicting protein functions with incomplete annotation.

Deep learning has revolutionized difficult tasks in chemistry and biology, yet existing language models often treat these domains separately, relying on concatenated architectures and independently pretrained weights. These approaches fail to fully exploit the shared atomic foundations of molecular and protein sequences. Here, we introduce T5ProtChem, a unified model based on the T5 architecture, designed to simultaneously process molecular and protein sequences. Using a new pretraining objective, ProtiSMILES, T5ProtChem bridges the molecular and protein domains, enabling efficient, generalizable protein-chemical modeling. The model achieves a state-of-the-art performance in tasks such as binding affinity prediction and reaction prediction, while having a strong performance in protein function prediction. Additionally, it supports novel applications, including covalent binder classification and sequence-level adduct prediction. These results demonstrate the versatility of unified language models for drug discovery, protein engineering, and other interdisciplinary efforts in computational biology and chemistry.

Motivation: The development of effective methods for the prediction of ontological annotations is an important goal in computational biology, with protein function prediction and disease gene prioritization gaining wide recognition. Although various algorithms have been proposed for these tasks, evaluating their performance is difficult owing to problems caused both by the structure of biomedical ontologies and biased or incomplete experimental annotations of genes and gene products.Results: We propose an information-theoretic framework to evaluate the performance of computational protein function prediction. We use a Bayesian network, structured according to the underlying ontology, to model the prior probability of a protein’s function. We then define two concepts, misinformation and remaining uncertainty, that can be seen as information-theoretic analogs of precision and recall. Finally, we propose a single statistic, referred to as semantic distance, that can be used to rank classification models. We evaluate our approach by analyzing the performance of three protein function predictors of Gene Ontology terms and provide evidence that it addresses several weaknesses of currently used metrics. We believe this framework provides useful insights into the performance of protein function prediction tools.Contact:predrag@indiana.eduSupplementary information:Supplementary data are available at Bioinformatics online.