MassiveFold Data for CASP16‐CAPRI: A Systematic Massive Sampling Experiment

Protein structure prediction is defined as predicting the tertiary structure from the primary structure of the protein sequence. Because the real protein structure is very complex, it is necessary to adopt the simplified structure model for studying protein 3D space structure. In this paper, we introduce a kind of 3D AB off-lattice model for protein structure prediction, and the amino acids are labeled as two hydrophobic amino acids and hydrophilic amino acids. When the protein model is simplified, the optimization algorithm is also needed to use for searching the lowest energy conformation of the protein sequence based on the hypothesis theory. In this paper, a hybrid algorithm which combines PSO algorithm based on local adjust strategy (LAPSO) and genetic algorithm, was proposed to search the space structure of the protein with AB off-lattice model. Experimental results show that the minimal energy values obtained by the improved LAPSO are lower than those obtained by previous methods. The performance of our improved algorithm is better, and it can effectively solve the search problem of the protein space folding structure.

The rapid evolution of protein structure prediction tools has significantly broadened access to protein structural data. Although predicted structure models have the potential to accelerate and impact fundamental and translational research significantly, it is essential to note that they are not validated and cannot be considered the ground truth. Thus, challenges persist, particularly in capturing protein dynamics, predicting multi-chain structures, interpreting protein function, and assessing model quality. Interdisciplinary collaborations are crucial to overcoming these obstacles. Databases like the AlphaFold Protein Structure Database, the ESM Metagenomic Atlas, and initiatives like the 3D-Beacons Network provide FAIR access to these data, enabling their interpretation and application across a broader scientific community. Whilst substantial advancements have been made in protein structure prediction, further progress is required to address the remaining challenges. Developing training materials, nurturing collaborations, and ensuring open data sharing will be paramount in this pursuit. The continued evolution of these tools and methodologies will deepen our understanding of protein function and accelerate disease pathogenesis and drug development discoveries.

Protein complex structure prediction is an important problem in computational biology. While significant progress has been made for protein monomers, accurate evaluation of protein complexes remains challenging. Existing assessment methods in CASP, lack dedicated metrics for evaluating complexes. DockQ, a widely used metric, has some limitations. In this study, we propose a novel metric called BDM (Based on Distance difference Matrix) for assessing protein complex prediction structures. Our approach utilizes a distance difference matrix derived from comparing real and predicted protein structures, establishing a linear correlation with Root Mean Square Deviation (RMSD). BDM overcomes limitations associated with receptor-ligand differentiation and eliminates the requirement for structure alignment, making it a more effective and efficient metric. Evaluation of BDM using CASP14 and CASP15 test sets demonstrates superior performance compared to the official CASP scoring. BDM provides accurate and reasonable assessments of predicted protein complexes, wide adoption of BDM has the potential to advance protein complex structure prediction and facilitate related researches across scientific domains. Code is available at http://mialab.ruc.edu.cn/BDMServer/ .

Besides economic and welfare aspects, breeding might also reduce environmental impacts, such as use of water or land, or emission of CO2, methane or ammonia Thus, environmental impacts have received increasing attention in the definition of breeding goals. Environmental impacts occur not only at the farm level, but also during the production of farm inputs (upstream processes), such as feed production, or during processing or selling of animal products (downstream processes). A method commonly used to assess the environmental impact of livestock or fish production is life cycle assessment (LCA). LCA is a standardized method that estimates the environmental impacts of a product during the entire life cycle, or in other words, throughout the production chain. LCA links the environmental impacts along the production chain to the main output of that system, i.e. also referred to as the functional unit Functional units in LCAs of food products are, for example, kg of fat-and-protein-corrected milk, kg of grain or meat produced (de Vries and de Boer, 2010) or ton of fresh fish produced Two types of environmental impacts are distinguished in a LCA: the use of natural resources (e.g. land, fossil energy, or water) required for the production of a functional unit and the corresponding emission of pollutants (e.g. ammonia, nitrate or methane) from a given production system. Use of resources or emission of pollutants can contribute to different environmental problems (referred to as impact categories), such as fossil energy use, acidification, eutrophication of or climate change (de Vries and de Boer, 2010). For example, to assess the impact of a production system on climate change, emissions of the main greenhouse gases in food production (i.e. carbon dioxide (CO2), methane (CH4) and nitrous oxide (N2O)) are summed along the chain based on their equivalence factor in terms of CO2 equivalent (CO2-eq, 100-year time horizon). Because of its capacity to include environmental impacts at every step of the production system, LCA has started to be used to investigate the environmental effects of genetic improvement in livestock Similar to economic values, environmental values represent the change in environmental impacts (i.e. climate change) after genetic improvement of one trait, while keeping the other traits constant. The purpose of the bioeconomic model developed by

The prediction of a minimum energy protein structure from its amino acid sequence represents an important and challenging problem in computational biology. In this paper, we propose a novel heuristic approach for protein structure prediction (PSP) based on the concept of optimal hydrophobic core formation. Using 2D HP model, a well-known set of sub-structures analogous to the secondary structures are obtained. Some sub-conformations are appropriately classified and then incorporated as prior knowledge. Unlike most of the popular PSP approaches which are stochastic in nature, the proposed method is deterministic. The effectiveness of the proposed algorithm is evaluated by well-known benchmark as well as non-benchmark sequences commonly used with 2D HP model. Maintaining similar accuracy as other core based and population based algorithms our method is significantly faster and reduces the computation time as it avoids blind search within the hydrophobic core (H-Core).

More than sixty years have passed since it has disclosed that protein can be developed from amino acid sequence. Structures of protein have proven to be a key piece of information for designing a drug, synthetic biology, and diagnosis of diseases. By knowing the protein structure, one can predict its function, find out how molecules or drugs skillfully bind with proteins and structural behavior of protein can help us to diagnose diseases and to invent new drugs. Due to the fast growth of protein sequence from the amino acid, it finds to be much more difficult with experimental techniques to obtain three-dimensional protein structures. Hence protein structure prediction (PSP) is still seen to be more important. Here in this paper, we are presenting a review about the formation of protein, different protein structure, factors affecting the tertiary structure, the importance of protein structure prediction, structural database, experimental and recent computational approaches for PSP, and similarity measures.

Understanding a protein’s 3D structure, which is linked to its function, is essential for biological processes, identifying disease mechanisms, and drug development. Traditional experimental techniques like X-ray crystallography, nuclear magnetic resonance (NMR), and cryogenic electron microscopy (Cryo-EM) have been used to determine precise protein structures. However, these methods are resource-intensive, resulting in only a few thousand structures being deciphered every year. This is in stark contrast to the extensive number of sequences in the UniProt database. To this end, numerous studies have investigated the possibility of integrating template-based and template-free structure prediction approaches. The most notable advancement was through the use of a hybrid approach in 2021 when DeepMind’s AlphaFold2 (AF2) introduced a protein structure prediction model with unprecedented accuracy using an end-to-end deep learning algorithm. Despite its widespread impact, AF2 continues to face architectural challenges and struggles with limited available data, preventing it from generating structures consistent with those that result from experimental methods. Recently, several techniques, such as smart sampling methods, and hybrid experimental approaches that enhance Cryo-EM maps with AF2 structures have been developed to address these limitations, surpassing AF2 and traditional methods in many instances. As developments of novel core algorithms allow AF2 to model a wider range of proteins with higher accuracy and hybrid AF2-experimental approaches expedite experimental data collection for AF2, a pure computation based solution to protein structure prediction seems increasingly likely. This review will provide an overview of AF2 and identify promising advancements in protein structure prediction since its introduction.

GRAPHICAL MODELS FOR PROTEIN FUNCTION AND STRUCTURE PREDICTION MINGJIE TANG,1,† KEAN MING TAN,2,† XIN LU TAN,2 LEE SAEL,1,3 MEGHANA CHITALE,1 JUAN ESQUIVEL-RODRIGUEZ,1 and DAISUKE KIHARA1,3 1Department of Computer Science, Purdue University, West Lafayette, Indiana 2Department of Statistics, Purdue University, West Lafayette, Indiana 3Department of Biological Sciences, Purdue University, West Lafayette, Indiana

Protein structure prediction is an important research field in life sciences and medicine, and it is also a key application scenario of artificial intelligence in scientific research. AlphaFold2 is a protein structure prediction system developed by DeepMind based on deep learning, capable of efficiently generating the atomic-scale spatial structure of a protein from the amino acid sequence. It has demonstrated superior performance in the prediction of protein structures since its inception, thus attracting much attention and research. This paper introduces the model architecture, highlights, limitations, and application progress of AlphaFold2. Furthermore, it briefs the capabilities, highlights, and limitations of several other types of protein structure prediction models and prospects the future development direction in this field.

Using Material Flow Analysis for Sustainable Materials Management

Plants employ self-incompatibility (SI) to promote cross-fertilization. In Brassicaceae, this process is regulated by the formation of a complex between the pistil determinant S receptor kinase (SRK) and the pollen determinant S-locus protein 11 (SP11, also known as S-locus cysteine-rich protein, SCR). In our previous study, we used the crystal structures of two eSRK–SP11 complexes in Brassica rapa S8 and S9 haplotypes and nine computationally predicted complex models to demonstrate that only the SRK ectodomain (eSRK) and SP11 pairs derived from the same S haplotype exhibit high binding free energy. However, predicting the eSRK–SP11 complex structures for the other 100 + S haplotypes and genera remains difficult because of SP11 polymorphism in sequence and structure. Although protein structure prediction using AlphaFold2 exhibits considerably high accuracy for most protein monomers and complexes, 46% of the predicted SP11 structures that we tested showed < 75 mean per-residue confidence score (pLDDT). Here, we demonstrate that the use of curated multiple sequence alignment (MSA) for cysteine-rich proteins significantly improved model accuracy for SP11 and eSRK–SP11 complexes. Additionally, we calculated the binding free energies of the predicted eSRK–SP11 complexes using molecular dynamics (MD) simulations and observed that some Arabidopsis haplotypes formed a binding mode that was critically different from that of B. rapa S8 and S9. Thus, our computational results provide insights into the haplotype-specific eSRK–SP11 binding modes in Brassicaceae at the residue level. The predicted models are freely available at Zenodo, https://doi.org/10.5281/zenodo.8047768.

The protein is not just a simple word. It is a backbone of every living organism from small to big. Protein monomer units consist of structures which are constructed by some definite process which is called protein folding. Protein folding process gives brief idea about the sequence’s structural occurrence from primary to quaternary state. In this process one important aspect is protein structure prediction which helps predicting the structural formation from a previous structural state. In bioinformatics field most researchers concentrate on protein structure prediction for better drug discovery. In this paper, we studied the protein secondary structure prediction using different algorithms like simple Artificial Neural Network (ANN), Machine Learning (ML) with multiple ANN (ML-ANN), and Deep Neural Network (DNN) in Restricted Boltzman Machine(RBM) on one dataset called Protein Data Bank (PDB). We compare the accuracy result of these three techniques with the same dataset.

Comparative environmental impact assessment of aquafeed production: Sustainability implications of forage fish meal and oil free diets

The knowledge of the protein structural class is one of the most important sources of information in many biological fields, such as function analysis, protein structure, drug design, and protein folding. However, the protein structural class prediction is still a challenge when dealing with low similarity sequences. Therefore, the accuracy of the top-performing prediction methods remains unsatisfying, especially for proteins from the + ß class. This paper proposes a novel approach for Protein Structural Class Prediction using a Convolutional Neural Network (PSCP-CNN). Our approach consists of two stages. The first is the preprocessing stage which allows the preparation of the data. The second stage is a CNN classifier that automatically extracts the needed features for the classification. To evaluate the performance of our approach, we performed the jackknife test on four low similarity benchmark datasets: 25PDB, 640, 1189, and FC699. The experimental results show that PSCP-CNN achieved high prediction accuracy, where the overall accuracy on datasets 25PDB, 640, 1189, and FC699 is 93.8%, 94.5%, 94.0%, and 98.0%, respectively. Furthermore, comparing the results obtained with existing methods shows that PSCP-CNN outperforms state-of-the-art techniques and confirms that using a convolutional neural network allows a better prediction of protein structural classes.

Chapter 26 - Machine learning in bioinformatics