A guide to machine learning for biologists

Greener, Joe G; Kandathil, Shaun M.; Moffat, Lewis; Jones, David T.

doi:10.1038/s41580-021-00407-0

Cited by 1,043 publications

(697 citation statements)

References 126 publications

Supporting

Mentioning

684

Contrasting

Unclassified

Order By: Relevance

“…PCA is a linear dimensionality reduction technique to transform data with many dimensions into a lower dimensional space and preserve the different relationships between the data points as much as possible [ 42 ]. PCA was generated from six physicochemical properties (MW, HB, HBA, SlogP, TPSA, and RB).…”

Section: Methodsmentioning

confidence: 99%

Towards the De Novo Design of HIV-1 Protease Inhibitors Based on Natural Products

et al. 2021

View full text Add to dashboard Cite

Acquired immunodeficiency syndrome (AIDS) caused by the human immunodeficiency virus (HIV) continues to be a public health problem. In 2020, 680,000 people died from HIV-related causes, and 1.5 million people were infected. Antiretrovirals are a way to control HIV infection but not to cure AIDS. As such, effective treatment must be developed to control AIDS. Developing a drug is not an easy task, and there is an enormous amount of work and economic resources invested. For this reason, it is highly convenient to employ computer-aided drug design methods, which can help generate and identify novel molecules. Using the de novo design, novel molecules can be developed using fragments as building blocks. In this work, we develop a virtual focused compound library of HIV-1 viral protease inhibitors from natural product fragments. Natural products are characterized by a large diversity of functional groups, many sp3 atoms, and chiral centers. Pseudo-natural products are a combination of natural products fragments that keep the desired structural characteristics from different natural products. An interactive version of chemical space visualization of virtual compounds focused on HIV-1 viral protease inhibitors from natural product fragments is freely available in the supplementary material.

show abstract

Section: Methodsmentioning

confidence: 99%

Towards the De Novo Design of HIV-1 Protease Inhibitors Based on Natural Products

et al. 2021

View full text Add to dashboard Cite

show abstract

“…DL-based methods have demonstrated their prowess in a broad range of single-cell studies 10 , such as understanding the complexity of brain cell types related to perception and complex behaviours, and inferring the high diversity of tumour and immune cell populations to greatly accelerate the discovery of novel pathogenesis and cancer therapeutics. We expect such studies will be greatly expanded to provide unique insights, which likely would not be achievable without combining single-cell data and DL technologies.…”

Section: Prospects Of Deep Learning In Single-cell Data Analysismentioning

confidence: 99%

Deep learning shapes single-cell data analysis

2022

Nat Rev Mol Cell Biol

View full text Add to dashboard Cite

show abstract

“…In DL, Deep Neural Networks can extract and process information from given data. DL mimics the human brain via connecting multiple artificial neurons in deep and densely connected layers [72][73][74]. ML/DL approaches provide an opportunity to move away from interpretive attempts to apply group-level associations and instead predict responses in individual patients, i.e., enabling more personalized medicine.…”

Section: Machine Learning and Deep Learningmentioning

confidence: 99%

“…Semi-supervised learning employs both labelled and unlabeled data for training. In all of these ML approaches, model validation is essential, and the accuracy of ML results is verified using independent test sets [74].…”

Section: Machine Learning and Deep Learningmentioning

confidence: 99%

Computational Models for Clinical Applications in Personalized Medicine—Guidelines and Recommendations for Data Integration and Model Validation

Collin

Gebhardt

Golebiewski

et al. 2022

JPM

View full text Add to dashboard Cite

The future development of personalized medicine depends on a vast exchange of data from different sources, as well as harmonized integrative analysis of large-scale clinical health and sample data. Computational-modelling approaches play a key role in the analysis of the underlying molecular processes and pathways that characterize human biology, but they also lead to a more profound understanding of the mechanisms and factors that drive diseases; hence, they allow personalized treatment strategies that are guided by central clinical questions. However, despite the growing popularity of computational-modelling approaches in different stakeholder communities, there are still many hurdles to overcome for their clinical routine implementation in the future. Especially the integration of heterogeneous data from multiple sources and types are challenging tasks that require clear guidelines that also have to comply with high ethical and legal standards. Here, we discuss the most relevant computational models for personalized medicine in detail that can be considered as best-practice guidelines for application in clinical care. We define specific challenges and provide applicable guidelines and recommendations for study design, data acquisition, and operation as well as for model validation and clinical translation and other research areas.

show abstract

A guide to machine learning for biologists

Cited by 1,043 publications

References 126 publications

Towards the De Novo Design of HIV-1 Protease Inhibitors Based on Natural Products

Towards the De Novo Design of HIV-1 Protease Inhibitors Based on Natural Products

Deep learning shapes single-cell data analysis

Computational Models for Clinical Applications in Personalized Medicine—Guidelines and Recommendations for Data Integration and Model Validation

Contact Info

Product

Resources

About