Deep Learning applications for COVID-19

Journal Of Big Data, Journal Year: 2021, Volume and Issue: 8(1)

Published: Jan. 11, 2021

This survey explores how Deep Learning has battled the COVID-19 pandemic and provides directions for future research on COVID-19. We cover applications in Natural Language Processing, Computer Vision, Life Sciences, Epidemiology. describe each of these vary with availability big data learning tasks are constructed. begin by evaluating current state conclude key limitations applications. These include Interpretability, Generalization Metrics, from Limited Labeled Data, Data Privacy. Processing mining Information Retrieval Question Answering, as well Misinformation Detection, Public Sentiment Analysis. Vision Medical Image Analysis, Ambient Intelligence, Vision-based Robotics. Within our looks at can be applied to Precision Diagnostics, Protein Structure Prediction, Drug Repurposing. additionally been utilized Spread Forecasting Our literature review found many examples systems fight hope that this will help accelerate use research.

Language: Английский

---

AlphaFold2 and its applications in the fields of biology and medicine

Signal Transduction and Targeted Therapy, Journal Year: 2023, Volume and Issue: 8(1)

Published: March 14, 2023

Abstract AlphaFold2 (AF2) is an artificial intelligence (AI) system developed by DeepMind that can predict three-dimensional (3D) structures of proteins from amino acid sequences with atomic-level accuracy. Protein structure prediction one the most challenging problems in computational biology and chemistry, has puzzled scientists for 50 years. The advent AF2 presents unprecedented progress protein attracted much attention. Subsequent release more than 200 million predicted further aroused great enthusiasm science community, especially fields medicine. thought to have a significant impact on structural research areas need information, such as drug discovery, design, function, et al. Though time not long since was developed, there are already quite few application studies medicine, many them having preliminarily proved potential AF2. To better understand promote its applications, we will this article summarize principle architecture well recipe success, particularly focus reviewing applications Limitations current also be discussed.

Language: Английский

---

Deep learning-based prediction of the T cell receptor–antigen binding specificity

Nature Machine Intelligence, Journal Year: 2021, Volume and Issue: 3(10), P. 864 - 875

Published: Sept. 23, 2021

Language: Английский

---

Antibody structure prediction using interpretable deep learning

Patterns, Journal Year: 2021, Volume and Issue: 3(2), P. 100406 - 100406

Published: Dec. 9, 2021

Therapeutic antibodies make up a rapidly growing segment of the biologics market. However, rational design is hindered by reliance on experimental methods for determining antibody structures. Here, we present DeepAb, deep learning method predicting accurate FV structures from sequence. We evaluate DeepAb set structurally diverse, therapeutically relevant and find that our consistently outperforms leading alternatives. Previous have operated as "black boxes" offered few insights into their predictions. By introducing directly interpretable attention mechanism, show network attends to physically important residue pairs (e.g., proximal aromatics key hydrogen bonding interactions). Finally, novel mutant scoring metric derived confidence particular antibody, all eight top-ranked mutations improve binding affinity. This model will be useful broad range prediction tasks.

Language: Английский

---

AlphaFold, Artificial Intelligence (AI), and Allostery

The Journal of Physical Chemistry B, Journal Year: 2022, Volume and Issue: 126(34), P. 6372 - 6383

Published: Aug. 17, 2022

AlphaFold has burst into our lives. A powerful algorithm that underscores the strength of biological sequence data and artificial intelligence (AI). appended projects research directions. The database it been creating promises an untold number applications with vast potential impacts are still difficult to surmise. AI approaches can revolutionize personalized treatments usher in better-informed clinical trials. They promise make giant leaps toward reshaping revamping drug discovery strategies, selecting prioritizing combinations targets. Here, we briefly overview structural biology, including molecular dynamics simulations prediction microbiota-human protein-protein interactions. We highlight advancements accomplished by deep-learning-powered protein structure their impact on life sciences. At same time, does not resolve decades-long folding challenge, nor identify pathways. models provides do capture conformational mechanisms like frustration allostery, which rooted ensembles, controlled dynamic distributions. Allostery signaling properties populations. also generate ensembles intrinsically disordered proteins regions, instead describing them low probabilities. Since generates single ranked structures, rather than cannot elucidate allosteric activating driver hotspot mutations resistance. However, capturing key features, deep learning techniques use predicted conformation as basis for generating a diverse ensemble.

Language: Английский

---

Protein–protein interaction prediction with deep learning: A comprehensive review

Computational and Structural Biotechnology Journal, Journal Year: 2022, Volume and Issue: 20, P. 5316 - 5341

Published: Jan. 1, 2022

Most proteins perform their biological function by interacting with themselves or other molecules. Thus, one may obtain insights into protein functions, disease prevalence, and therapy development identifying protein–protein interactions (PPI). However, finding the non-interacting pairs through experimental approaches is labour-intensive time-consuming, owing to variety of proteins. Hence, interaction protein–ligand binding problems have drawn attention in fields bioinformatics computer-aided drug discovery. Deep learning methods paved way for scientists predict 3-D structure from genomes, functions attributes a protein, modify design new provide desired functions. This review focuses on recent deep applied including predicting sites, binding, design.

Language: Английский

---

Synthetic Biology: Bottom-Up Assembly of Molecular Systems

Chemical Reviews, Journal Year: 2022, Volume and Issue: 122(21), P. 16294 - 16328

Published: Sept. 30, 2022

The bottom-up assembly of biological and chemical components opens exciting opportunities to engineer artificial vesicular systems for applications with previously unmet requirements. modular combination scaffolds functional building blocks enables the engineering complex biomimetic or new-to-nature functionalities. Inspired by compartmentalized organization cells organelles, lipid polymer vesicles are widely used as model membrane investigate translocation solutes transduction signals proteins. functionalization such compartments full control over their composition can thus provide specifically optimized environments synthetic processes. This review aims inspire future endeavors providing a diverse toolbox molecular modules, methodologies, different approaches assemble systems. Important technical practical aspects addressed selected presented, highlighting particular achievements limitations approach. Complementing cutting-edge technological achievements, fundamental also discussed cater inherently background target audience, which results from interdisciplinary nature biology. proteins modules use lipids block copolymers scaffold functionalized explored in detail. Particular emphasis is placed on ensuring controlled these into increasingly Finally, all descriptions presented greater context valuable biocatalysis, biosensing, bioremediation, targeted drug delivery.

Language: Английский

---

In silico proof of principle of machine learning-based antibody design at unconstrained scale

mAbs, Journal Year: 2022, Volume and Issue: 14(1)

Published: April 4, 2022

Generative machine learning (ML) has been postulated to become a major driver in the computational design of antigen-specific monoclonal antibodies (mAb). However, efforts confirm this hypothesis have hindered by infeasibility testing arbitrarily large numbers antibody sequences for their most critical parameters: paratope, epitope, affinity, and developability. To address challenge, we leveraged lattice-based antibody-antigen binding simulation framework, which incorporates wide range physiological antibody-binding parameters. The framework enables computation synthetic 3D-structures, it functions as an oracle unrestricted prospective evaluation benchmarking parameters ML-generated sequences. We found that deep generative model, trained exclusively on sequence (one dimensional: 1D) data can be used conformational (three 3D) epitope-specific antibodies, matching, or exceeding training dataset affinity developability parameter value variety. Furthermore, established lower threshold diversity necessary high-accuracy ML demonstrated also holds experimental real-world data. Finally, show transfer generation high-affinity from low-N Our work establishes priori feasibility theoretical foundation high-throughput ML-based mAb design.

Language: Английский

---

ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning

Digital Discovery, Journal Year: 2024, Volume and Issue: 3(7), P. 1389 - 1409

Published: Jan. 1, 2024

ProtAgents is a de novo protein design platform based on multimodal LLMs, where distinct AI agents with expertise in knowledge retrieval, structure analysis, physics-based simulations, and results analysis tackle tasks dynamic setting.

Language: Английский

---

Experimental methods to study the structure and dynamics of intrinsically disordered regions in proteins

Current Research in Structural Biology, Journal Year: 2024, Volume and Issue: 7, P. 100138 - 100138

Published: Jan. 1, 2024

Eukaryotic proteins often feature long stretches of amino acids that lack a well-defined three-dimensional structure and are referred to as intrinsically disordered (IDPs) or regions (IDRs). Although these challenge conventional structure-function paradigms, they play vital roles in cellular processes. Recent progress experimental techniques, such NMR spectroscopy, single molecule FRET, high speed AFM SAXS, have provided valuable insights into the biophysical basis IDP function. This review discusses advancements made techniques particularly for study proteins. In spectroscopy new strategies 13C detection, non-uniform sampling, segmental isotope labeling, rapid data acquisition methods address challenges posed by spectral overcrowding low stability IDPs. The importance various parameters, including chemical shifts, hydrogen exchange rates, relaxation measurements, reveal transient secondary structures within IDRs IDPs presented. Given flexibility IDPs, outlines assessing their dynamics at both fast (ps-ns) slow (μs-ms) timescales. exert functions through interactions with other molecules proteins, DNA, RNA. NMR-based titration experiments yield thermodynamics kinetics interactions. Detailed requires multiple thus, several described studying highlighting respective advantages limitations. potential integrating complementary each offering unique perspectives, is explored achieve comprehensive understanding

Language: Английский

---