ArticlePLoS computational biology2017
Maximum entropy methods for extracting the learned features of deep neural networks.
Article in PLoS computational biology, 2017. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 24 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
24 citing papers in PubMed, 46 citations in OpenAlex.
- The immortality mechanism of TERT promoter mutant cancers is self-reinforcing and reversible.Molecular cell · 2025Article
- Applications of Entropy in Data Analysis and Machine Learning: A Review.Entropy (Basel, Switzerland) · 2024Review
- An interpretable deep learning framework identifies proteomic drivers of Alzheimer's disease.Frontiers in cell and developmental biology · 2024Article
- Chromatin structure and context-dependent sequence features control prime editing efficiency.bioRxiv : the preprint server for biology · 2023Article
- Chromatin structure and context-dependent sequence features control prime editing efficiency.Frontiers in genetics · 2023Article
- On the Solutions of a Quadratic Integral Equation of the Urysohn Type of Fractional Variable Order.Entropy (Basel, Switzerland) · 2022Article
- Artificial intelligence in cancer target identification and drug discovery.Signal transduction and targeted therapy · 2022Review
- Machine Learning in Drug Discovery: A Review.Artificial intelligence review · 2022Article
- Evaluation of machine learning classifiers for predicting essential genes inBioinformation · 2022Article
- Global importance analysis: An interpretability method to quantify importance of genomic features in deep neural networks.PLoS computational biology · 2021Article
- Predicting TCR-Epitope Binding Specificity Using Deep Metric Learning and Multimodal Learning.Genes · 2021Article
- Functional analysis of low-grade glioma genetic variants predicts key target genes and transcription factors.Neuro-oncology · 2021Article
- Studying the Evolution of Neural Activation Patterns During Training of Feed-Forward ReLU Networks.Frontiers in artificial intelligence · 2021Article
- Intelligent Health Care: Applications of Deep Learning in Computational Medicine.Frontiers in genetics · 2021Review
- DeeplyEssential: a deep neural network for predicting essential genes in microbes.BMC bioinformatics · 2020Article
- Fractional Lotka-Volterra-Type Cooperation Models: Impulsive Control on Their Stability Behavior.Entropy (Basel, Switzerland) · 2020Article
- Epigenetic engineering of yeast reveals dynamic molecular adaptation to methylation stress and genetic modulators of specific DNMT3 family members.Nucleic acids research · 2020Article
- Deep learning for inferring transcription factor binding sites.Current opinion in systems biology · 2020Article
- Deep neural networks in psychiatry.Molecular psychiatry · 2019Review
- Visualizing complex feature interactions and feature sharing in genomic deep neural networks.BMC bioinformatics · 2019Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors at 1 institution in 1 country.
Funding
Abstract
New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.