Skip to content
ULMFiT for Genomic Sequence Data
Branch: master
Clone or download
Latest commit 93c71de Apr 24, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Bacteria embedding tsne notebook Apr 9, 2019
Mammals Update README.md Apr 21, 2019
Methods methods 4 Apr 25, 2019
Model Interpretations
.gitignore mammal enhancer notebooks refactor Mar 18, 2019
README.md Update README.md Apr 24, 2019
utils.py

README.md

Genomic ULMFiT

This is an implementation of ULMFiT for genomics classification using Pytorch and Fastai. The model architecture used is based on the AWD-LSTM model, consisting of an embedding, three LSTM layers, and a final set of linear layers.

The ULMFiT approach uses three training phases to produce a classification model:

  1. Train a language model on a large, unlabeled corpus
  2. Fine tune the language model on the classification corpus
  3. Use the fine tuned language model to initialize a classification model

This method is particularly advantageous for genomic data, where large amounts of unlabeled data is abundant and labeled data is scarce. The ULMFiT approach allows us to train a model on a large, unlabeled genomic corpus in an unsupervised fashion. The pre-trained language model serves as a feature extractor for parsing genomic data.

Typical deep learning approaches to genomics classification are highly restricted to whatever labeled data is available. Models are usually trained from scratch on small datasets, leading to problems with overfitting. When unsupervised pre-training is used, it is typically done only on the classification dataset or on synthetically generated data. The Genomic-ULMFiT approach uses genome scale corpuses for pre-training to produce better feature extractors than we would get by training only on the classification corpus.

For a deep dive into the ULMFiT approach, model architectures, regularization and training strategies, see the Methods Long Form document in the Methods section.

Results

Performance of Genomic-ULMFiT relative to other methods

Promoter Classification

E. coli promoters

The Genomic-ULMFiT method performs well at the task of classifying promoter sequences from random sections of the genome. The process of unsupervised pre-training and fine-tuning has a clear impact on the performance of the classification model

Model Accuracy Precision Recall Correlation Coefficient
Naive 0.834 0.847 0.816 0.670
E. coli Genome Pre-Training 0.919 0.941 0.893 0.839
Genomic Ensemble Pre-Training 0.973 0.980 0.966 0.947

Data generation described in notebook

Notebook Directory

Classification performance on human promoters is competitive with published results

Human Promoters (short)

For the short promoter sequences, using data from Recognition of Prokaryotic and Eukaryotic Promoters using Convolutional Deep Learning Neural Networks:

Model DNA Size kmer/stride Accuracy Precision Recall Correlation Coefficient Specificity
Kh et al. -200/50 - - - 0.9 0.89 0.98
Naive Model -200/50 5/2 0.80 0.74 0.80 0.59 0.80
With Pre-Training -200/50 5/2 0.922 0.963 0.849 0.844 0.976
With Pre-Training and Fine Tuning -200/50 5/2 .977 .959 .989 .955 .969
With Pre-Training and Fine Tuning -200/50 5/1 .990 .983 .995 .981 .987
With Pre-Training and Fine Tuning -200/50 3/1 .995 .992 .996 .991 .994

Data Source

Notebook Directory

Human Promoters (long)

For the long promoter sequences, using data from PromID: Human Promoter Prediction by Deep Learning:

Model DNA Size Models Accuracy Precision Recall Correlation Coefficient
Umarov et al. -1000/500 2 Model Ensemble - 0.636 0.802 0.714
Umarov et al. -200/400 2 Model Ensemble - 0.769 0.755 0.762
Naive Model -500/500 Single Model 0.858 0.877 0.772 0.708
With Pre-Training -500/500 Single Model 0.888 0.90 0.824 0.770
With Pre-Training and Fine Tuning -500/500 Single Model 0.892 0.877 0.865 0.778

Data generation described in notebook

Notebook Directory

Other Bacterial Promoters

This table shows results on data from Recognition of prokaryotic and eukaryotic promoters using convolutional deep learning neural networks. These results show how CNN based methods can sometimes perform better when training on small datasets.

Method Organism Training Examples Accuracy Precision Recall Correlation Coefficient Specificity
Kh et al. E. coli 2936 - - 0.90 0.84 0.96
Genomic-ULMFiT E. coli 2936 0.956 0.917 0.880 0.871 0.977
Kh et al. B. subtilis 1050 - - 0.91 0.86 0.95
Genomic-ULMFiT B. subtilis 1050 0.905 0.857 0.789 0.759 0.95

Data Source

Notebook Directory

Metaganomics Classification

Genomic-ULMFiT shows improved performance on the metagenomics taxonomic dataset from Deep learning models for bacteria taxonomic classification of metagenomic data.

Method Data Source Accuracy Precision Recall F1
Fiannaca et al. Amplicon .9137 .9162 .9137 .9126
Genomic-ULMFiT Amplicon .9239 .9402 .9332 .9306
Fiannaca et al. Shotgun .8550 .8570 .8520 .8511
Genomic-ULMFiT Shotgun .8797 .8824 .8769 .8758

Data Source

Notebook Directory

Enhancer Classification

When trained on a dataset of mammalian enhancer sequences from Enhancer Identification using Transfer and Adversarial Deep Learning of DNA Sequences, Genomic_ULMFiT improves on results from Cohn et al.

Model/ROC-AUC Human Mouse Dog Opossum
Cohn et al. 0.80 0.78 0.77 0.72
Genomic-ULMFiT 5-mer Stride 2 0.812 0.871 0.773 0.787
Genomic-ULMFiT 4-mer Stride 2 0.804 0.876 0.771 0.786
Genomic-ULMFiT 3-mer Stride 1 0.819 0.875 0.788 0.798

Data Source

Notebook Directory

mRNA/lncRNA Classification

This table shows results for training a classification model on a dataset of coding mRNA sequences and long noncoding RNA (lncRNA) sequences. The dataset comes from A deep recurrent neural network discovers complex biological rules to decipher RNA protein-coding potential by Hill et al. The dataset contains two test sets - a standard test set and a challenge test set.

Model Test Set Accuracy Specificity Sensitivity Precision MCC
GRU Ensemble (Hill et al.)* Standard Test Set 0.96 0.97 0.95 0.97 0.92
Genomic ULMFiT (3mer stride 1) Standard Test Set 0.963 0.952 0.974 0.953 0.926
GRU Ensemble (Hill et al.)* Challenge Test Set 0.875 0.95 0.80 0.95 0.75
Genomic ULMFiT (3mer stride 1) Challenge Test Set 0.90 0.944 0.871 0.939 0.817

(*) Hill et al. presented their results as a plot rather than as a data table. Values in the above table are estimated by reading off the plot

Data Source

Notebook Directory

Interpreting Results

One way to gain insight into how the classification model makes decisions is to perturb regions of a given input sequence to see how changing different regions of the sequence impact the classification result. This allows us to create plots like the one below, highlighting important sequence regions for classification. In the plot below, the red line corresponds to a true transcripotion start site. The plot shows how prediction results are sensitive to changes around that location. More detail on interpretations can be found in the Model Interpretations directory.

Long Sequence Inference

Inference on long, unlabeled sequences can be done by breaking the input sequence into chunks and plotting prediction results as a function of length. The image below shows a sample prediction of promoter locations on a 40,000 bp region of the E. coli genome. True promoter locations are shown in red. More detail can be found in this notebook

Upcoming Experiments

There are a number of other genomic classification domains I intend to explore when time permits.

  • Classification from raw NGS data

Relevant Literature

I'm planning on doing a more structured literature review of deep learning for genomic classification and how they compare to Genomic_ULMFiT. For now, here are links to relevant papers.

DeepCRISPR: optimized CRISPR guide RNA design by deep learning

Recognition of prokaryotic and eukaryotic promoters using convolutional deep learning neural networks

PromID: human promoter prediction by deep learning

Deep Learning for Genomics: A Concise Overview

Prediction of deleterious mutations in coding regions of mammals with transfer learning

Enhancer Identification using Transfer and Adversarial Deep Learning of DNA Sequences

PEDLA: predicting enhancers with a deep learning-based algorithmic framework

Predicting enhancers with deep convolutional neural networks

BiRen: predicting enhancers with a deep-learning-based model using the DNA sequence alone

Deep learning models for bacteria taxonomic classification of metagenomic data

Prediction of enhancer-promoter interactions via natural language processing

A deep recurrent neural network discovers complex biological rules to decipher RNA protein-coding potential

Recurrent Neural Network for Predicting Transcription Factor Binding Sites

Learning the Language of the Genome using RNNs

You can’t perform that action at this time.