China 
Africa 
Explore chapters and articles related to this topic
Reliable Biomedical Applications Using AI Models
Published in Punit Gupta, Dinesh Kumar Saini, Rohit Verma, Healthcare Solutions Using Machine Learning and Informatics, 2023
Shambhavi Mishra, Tanveer Ahmed, Vipul Mishra
Studies based on genomics sequencing and gene expression directed towards protein structure prediction fall under the biomedical sector. Several studies show omics work on genomics, but other applications such as biomedicine and bioinformatics can also be found. Omics covers genetic data such as protein, metabol, gen, transcript, and epigen. It also concerns protein–protein interactions (PPIs). The authors of [39] studied different statistical learning framework methods that are integrated with different multidisciplinary areas including biology, machine learning, and AI. In the literature, PCA, clustering methods, regularization-based methods, regression methods, and knowledge enhancement learning have all been investigated and analyzed. The limitations and strengths of multiple standard ML methods are also discussed. According to [40]’s research, image data alone is insufficient for analyzing complicated disorders and obtaining an appropriate diagnosis. In parallel with large, high-quality data sets, domain knowledge and the requirement for multiple networks is also important. While high-dimensional data will always yield better results, all three components are crucial for providing robust ML model training and validation. The authors of one of the studies[41] looked at various AI-based approaches to analyzing different types of cancer.
Approaches for Identification and Validation of Antimicrobial Compounds of Plant Origin: A Long Way from the Field to the Market
Published in Mahendra Rai, Chistiane M. Feitosa, Eco-Friendly Biobased Products Used in Microbial Diseases, 2022
Lívia Maria Batista Vilela, Carlos André dos Santos-Silva, Ricardo Salas Roldan-Filho, Pollyanna Michelle da Silva, Marx de Oliveira Lima, José Rafael da Silva Araújo, Wilson Dias de Oliveira, Suyane de Deus e Melo, Madson Allan de Luna Aragão, Thiago Henrique Napoleão, Patrícia Maria Guedes Paiva, Ana Christina Brasileiro-Vidal, Ana Maria Benko-Iseppon
Another valuable technique is the computational analysis of plant protein evolution and its conserved functions (Shafee et al. 2020). These findings constitute the basic assumption behind most of the available bioinformatics algorithms for alignment and protein structure prediction (Campos et al. 2018; Shafee et al. 2020). Among the more used available prediction methods (e.g., template-based, threading and ab initio modeling), those based on comparative modeling provide more accurate structures that can be used in a large variety of applications, including ligand binding sites prediction and virtual screening (Ehrt et al. 2016).
An Efficient Protein Structure Prediction Using Genetic Algorithm
Published in Abdel-Badeeh M. Salem, Innovative Smart Healthcare and Bio-Medical Systems, 2020
Mohamad Yousef, Tamer Abdelkader, Khaled El-Bahnasy
I-TASSER is a web-based protein structure prediction tool that employs profile–profile threading alignment (PPA) [16] and Threading ASSEmbly Refinement (TASSER) program [17]. The query sequence is aligned to a selected library of PDB structures to search for the potential structures by four methods: PPA, HMM [18], PSI-BLAST profiles, and the Needleman–Wunsch and Smith–Waterman alignment algorithms. The unaligned regions (e.g., loops) are built by ab initio modeling, while the aligned regions after threading are used to build the main structure [19, 20].
Challenges in antibody structure prediction
Published in mAbs, 2023
Monica L. Fernández-Quintero, Janik Kokot, Franz Waibl, Anna-Lena M. Fischer, Patrick K. Quoika, Charlotte M. Deane, Klaus R. Liedl
Predicting the three-dimensional (3D) structure of a protein based solely on the amino-acid sequence is one of the grand challenges in the field of protein structure prediction.1 Accurate prediction of the 3D structure of a protein is critical to understand its function, as the shape of the protein determines its properties and ultimately its function. To determine the state-of-the-art methods in protein structure prediction, the biennial community-based benchmarking experiment “Critical Assessment of methods in protein Structure Prediction (CASP)” was established.2–4 In CASP14 (2020), DeepMind showcased AlphaFold2, a program based on artificial intelligence (AI) that directly processes multiple sequence alignments.5 Comparable accuracies in predicting protein structures can also be achieved with other methods including RoseTTAFold,6 and specialized tools for antibodies which incorporate the recent advances.7–9 Those tools are highly accurate based on global measures, often with root mean square deviations (RMSDs) to the crystal structure of less than 1 Å. However, there are often higher inaccuracies in specific parts of the protein that should be carefully reviewed.10,11 Post-translational modifications are omitted, but can sometimes be added afterwards.12 Furthermore, the accuracy for multimers, such as antibodies, is still lower.13 Additional challenges can arise for antibodies since VDJ recombination events do not follow the classical pathway of evolution.14
Promiscuity in drug discovery on the verge of the structural revolution: recent advances and future chances
Published in Expert Opinion on Drug Discovery, 2023
Sarah Naomi Bolz, Michael Schroeder
For these reasons, unraveling the structure of proteins holds immense value. Yet, experimentally determined structures deposited in the RCSB Protein Data Bank (PDB) [1] cover only a limited proportion of known amino acid sequences. Notably, for half of the protein families defined by sequence, no structural information is available in the PDB [2]. Computational protein structure prediction from amino acid sequences has the potential to close this gap. Recently, the artificial intelligence system AlphaFold has been demonstrated to predict protein structure with unprecedentedly high accuracy [3], and further structure prediction methods reaching comparable levels of accuracy have already followed [4,5]. Structure predictions via AlphaFold for over 200 million proteins are now publicly and freely available [6,7]. The magnitude and accuracy of these structure predictions may represent the beginning of a structural revolution affecting all areas of the life sciences.
Recent advances in automated protein design and its future challenges
Published in Expert Opinion on Drug Discovery, 2018
Dani Setiawan, Jeffrey Brender, Yang Zhang
The first question gave rise to the field of protein structure prediction [9,10], while the second gave rise to the field of protein design, both of which emerged concurrently (Figure 1). In protein structure prediction, the aim is to deduce the three-dimensional structure of an amino acid sequence; while, in protein design, having a specific, known function or protein structure as a target, the aim is to figure out which amino acid sequences will lead to successful, correct folding, and biological activity. One may think of the protein design problem as the inverse of the protein structure prediction problem [11], or as an inverted-folding problem [12].