Microbiome and Human Health: Current Understanding, Engineering, and Enabling Technologies

Chemical Reviews, Год журнала: 2022, Номер 123(1), С. 31 - 72

Опубликована: Ноя. 1, 2022

The human microbiome is composed of a collection dynamic microbial communities that inhabit various anatomical locations in the body. Accordingly, coevolution with host has resulted these playing profound role promoting health. Consequently, perturbations can cause or exacerbate several diseases. In this Review, we present our current understanding relationship between health and disease development, focusing on microbiomes found across digestive, respiratory, urinary, reproductive systems as well skin. We further discuss strategies by which composition function be modulated to exert therapeutic effect host. Finally, examine technologies such multiomics approaches cellular reprogramming microbes enable significant advancements research engineering.

Язык: Английский

---

Glycoproteomics

Nature Reviews Methods Primers, Год журнала: 2022, Номер 2(1)

Опубликована: Июнь 23, 2022

Язык: Английский

---

The impact of AlphaFold2 one year on

Nature Methods, Год журнала: 2022, Номер 19(1), С. 15 - 20

Опубликована: Янв. 1, 2022

Язык: Английский

---

DNA methylation-based predictors of health: applications and statistical considerations

Nature Reviews Genetics, Год журнала: 2022, Номер 23(6), С. 369 - 383

Опубликована: Март 18, 2022

Язык: Английский

---

PIGNet: a physics-informed deep learning model toward generalized drug–target interaction predictions

Chemical Science, Год журнала: 2022, Номер 13(13), С. 3661 - 3673

Опубликована: Янв. 1, 2022

Recently, deep neural network (DNN)-based drug-target interaction (DTI) models were highlighted for their high accuracy with affordable computational costs. Yet, the models' insufficient generalization remains a challenging problem in practice of

Язык: Английский

---

Engineered Living Materials For Sustainability

Chemical Reviews, Год журнала: 2022, Номер 123(5), С. 2349 - 2419

Опубликована: Дек. 13, 2022

Recent advances in synthetic biology and materials science have given rise to a new form of materials, namely engineered living (ELMs), which are composed matter or cell communities embedded self-regenerating matrices their own artificial scaffolds. Like natural such as bone, wood, skin, ELMs, possess the functional capabilities organisms, can grow, self-organize, self-repair when needed. They also spontaneously perform programmed biological functions upon sensing external cues. Currently, ELMs show promise for green energy production, bioremediation, disease treatment, fabricating advanced smart materials. This review first introduces dynamic features systems potential developing novel We then summarize recent research progress on emerging design strategies from both perspectives. Finally, we discuss positive impacts promoting sustainability key future directions.

Язык: Английский

---

Review on automated condition assessment of pipelines with machine learning

Advanced Engineering Informatics, Год журнала: 2022, Номер 53, С. 101687 - 101687

Опубликована: Июль 5, 2022

Язык: Английский

---

Direct generation of protein conformational ensembles via machine learning

Nature Communications, Год журнала: 2023, Номер 14(1)

Опубликована: Фев. 11, 2023

Abstract Dynamics and conformational sampling are essential for linking protein structure to biological function. While challenging probe experimentally, computer simulations widely used describe dynamics, but at significant computational costs that continue limit the systems can be studied. Here, we demonstrate machine learning trained with simulation data directly generate physically realistic ensembles of proteins without need any negligible cost. As a proof-of-principle train generative adversarial network based on transformer architecture self-attention coarse-grained intrinsically disordered peptides. The resulting model, idpGAN, predict sequence-dependent sequences not present in training set demonstrating transferability achieved beyond limited data. We also retrain idpGAN atomistic show approach extended principle higher-resolution ensemble generation.

Язык: Английский

---

Machine Learning-Guided Protein Engineering

ACS Catalysis, Год журнала: 2023, Номер 13(21), С. 13863 - 13895

Опубликована: Окт. 13, 2023

Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid the discovery annotation of enzymes, as well suggesting beneficial mutations for improving known targets. The field protein is gathering steam, driven by recent success stories notable other areas. It already encompasses ambitious tasks such understanding predicting structure function, catalytic efficiency, enantioselectivity, dynamics, stability, solubility, aggregation, more. Nonetheless, still evolving, with many challenges overcome questions address. In this Perspective, we provide an overview ongoing trends domain, highlight case studies, examine current limitations learning-based We emphasize crucial importance thorough validation emerging models before their use rational design. present our opinions on fundamental problems outline potential directions future research.

Язык: Английский

---

An Unsupervised Machine Learning Algorithms: Comprehensive Review

International Journal of Computing and Digital Systems, Год журнала: 2023, Номер 13(1), С. 911 - 921

Опубликована: Апрель 16, 2023

Machine learning (ML) is a data-driven strategy in which computers learn from data without human intervention.The outstanding ML applications are used variety of areas.In ML, there three types problems: Supervised, Unsupervised, and Semi-Supervised Learning.Examples unsupervised techniques algorithms include Apriori algorithm, ECLAT frequent pattern growth clustering using k-means, principal components analysis.Objects grouped based on their same properties.The divided into two categories: hierarchical partition clustering.Many have been created during the last decade, some them well-known commonly algorithms.Unsupervised approaches seen lot success disciplines including machine vision, speech recognition, creation self-driving cars, natural language processing.Unsupervised eliminates requirement for labeled feature engineering, making standard more flexible automated.Unsupervised topic this survey report.

Язык: Английский

---