Opportunities and obstacles for deep learning in biology and medicine

  title={Opportunities and obstacles for deep learning in biology and medicine},
  author={Travers Ching and Daniel S. Himmelstein and Brett K. Beaulieu-Jones and Alexandr A Kalinin and Brian T Do and Gregory P. Way and Enrico Ferrero and Paul-Michael Agapow and Michael Zietz and Michael M. Hoffman and Wei Xie and Gail L. Rosen and Benjamin J. Lengerich and Johnny Israeli and Jack Lanchantin and Stephen Woloszynek and Anne E Carpenter and Avanti Shrikumar and Jinbo Xu and Evan M. Cofer and Christopher A. Lavender and Srinivas C. Turaga and Amr M. Alexandari and Zhiyong Lu and David J Harris and David DeCaprio and Yanjun Qi and Anshul Kundaje and Yifan Peng and Laura K. Wiley and Marwin H. S. Segler and Simina Maria Boca and S. Joshua Joshua Swamidass and Austin Huang and Anthony Gitter and Casey S. Greene},
  journal={Journal of the Royal Society Interface},
Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. [] Key Result Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress…
Current methods and challenges for deep learning in drug discovery.
  • S. Schroedl
  • Computer Science, Biology
    Drug discovery today. Technologies
  • 2019
Deep learning in biomedicine
This work argues that challenges in guaranteeing the performance of deployed systems and in establishing trust with stakeholders, clinicians and regulators will be overcome using the same flexibility that created them; for example, by training deep models so that they can output a rationale for their predictions.
Applications of deep learning for the analysis of medical data
The basic learning algorithms underlying deep learning are explored and the procedures for building deep learning-based classifiers for seizure electroencephalograms and gastric tissue slides are described as examples to demonstrate the simplicity and effectiveness of deep learning applications.
Deep learning in bioinformatics and biomedicine
The aim of this special issue is to provide the readers with a set of reviews that describe the latest concepts, innovations, approaches and technologies in the area of deep learning in bioinformatics, computational biology and systems medicine.
Deep Learning Methods for Predicting Disease Status Using Genomic Data
Four articles first used auto-encoders to project high-dimensional genomic data to a low dimensional space and then applied the state-of-the-art machine learning algorithms to predict disease status based on the low-dimensional representations, which outperformed existing prediction methods.
An overview of deep learning in medical imaging focusing on MRI
A guide to machine learning for biologists
This Review provides a gentle introduction to a few key machine learning techniques, including the most recently developed and widely used techniques involving deep neural networks.
Better Application of Bayesian Deep Learning to Diagnose Disease
  • P. Singh
  • Computer Science
    2021 5th International Conference on Computing Methodologies and Communication (ICCMC)
  • 2021
Bayesian Deep Learning's proposed approach has outperformed current methods of diagnosis & prediction and demonstrates high precision and great potential to develop clinical tools.


Deep learning for healthcare: review, opportunities and challenges
It is suggested that deep learning approaches could be the vehicle for translating big biomedical data into improved human health and develop holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability.
Applications of Deep Learning in Biomedicine.
Key features of deep learning that may give this approach an edge over other machine learning methods are discussed and a number of applications ofdeep learning in biomedical studies demonstrating proof of concept and practical utility are reviewed.
Deep learning in bioinformatics
This review will provide valuable insights and serve as a starting point for researchers to apply deep learning approaches in their bioinformatics studies and suggest future research directions.
Low Data Drug Discovery with One-Shot Learning
This work demonstrates how one-shot learning can be used to significantly lower the amounts of data required to make meaningful predictions in drug discovery applications and introduces a new architecture, the iterative refinement long short-term memory, that significantly improves learning of meaningful distance metrics over small-molecules.
Deep learning for computational biology
This review discusses applications of this new breed of analysis approaches in regulatory genomics and cellular imaging, and provides background of what deep learning is, and the settings in which it can be successfully applied to derive biological insights.
Distilling Knowledge from Deep Networks with Applications to Healthcare Domain
A novel knowledge-distillation approach called Interpretable Mimic Learning is introduced, to learn interpretable phenotype features for making robust prediction while mimicking the performance of deep learning models.
Computational Phenotype Discovery Using Unsupervised Feature Learning over Noisy, Sparse, and Irregular Clinical Data
From episodic, longitudinal sequences of serum uric acid measurements in 4368 individuals, this work produced continuous phenotypic features that suggest multiple population subtypes, and that accurately distinguished the uric-acid signatures of gout vs. acute leukemia despite not being optimized for the task.
Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules
A brief overview of deep learning methods is presented and in particular how recursive neural network approaches can be applied to the problem of predicting molecular properties, by considering an ensemble of recursive neural networks associated with all possible vertex-centered acyclic orientations of the molecular graph.
Diet Networks: Thin Parameters for Fat Genomics
A novel neural network parametrization is proposed which considerably reduces the number of parameters and the error rate of the classifier on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms, yielding millions of ternary inputs.
Multi-Layer and Recursive Neural Networks for Metagenomic Classification
Traditional neural networks can be quite powerful classifiers on metagenomic data compared to baseline methods, such as random forests, and deep learning approaches did not result in improvements to the classification accuracy, but they do provide the ability to learn hierarchical representations of a data set that standard classification methods do not allow.