Artificial neural network classification of copy number variation, part 1

In this series of posts, I want to describe some work I’ve been doing attempting to apply an artificial neural network model to the problem of classifying copy number variation in a clinically-important gene, CYP2D6.   I will be presenting a poster-paper on this topic at the 2018 ISMB/ISCB meeting in Chicago.

Here is the abstract from the poster:

Pharmacogenomics is a rapidly developing field that aims to deliver on the promise of personalized medicine by guiding pharmacological intervention using an understanding of a patient’s individual genotype for drug metabolism.  By avoiding ineffective or dangerous treatments, patient outcomes could be dramatically improved and hospital costs reduced. We have developed a sequencing-based pharmacogenomics screening panel that uses targeted capture to perform deep sequencing of 200+ critical drug metabolism genes.  Assessing copy-number variation is a critical part of correctly interpreting genotypes in key drug metabolism genes, such as CYP2D6.  Historically, this has been a time-consuming step in our clinical pipeline involving large amounts of expert analyst time and data visualization.  This study presents a novel application of an artificial neural network (ANN) machine learning algorithm to learn the complex patterns in CNV data.  The result is a trained network that can quickly and accurately classify copy number events according to known training categories in the CYP2D6 gene.  We show that a simple, one hidden-layer network is sufficient to achieve the extremely high accuracy and low false-positive rate required in a high-throughput clinical setting.

Motivating factors

Motivating this work is the fact that interpreting copy number variation data from targeted capture sequencing is difficult owing to several factors.  First, the data are noisy owing to biases in capture efficiency and GC content.  Second, the copy number variation events in a gene like CYP2D6 are complex and subtle, but have dramatic impacts on the functional status of the gene.  Third, most copy number variation detection methods are optimized for whole genome sequencing with smooth and even coverage across each chromosome.

The result is that, although most of the variant calling and interpretation is automated, a person still has to sit down with the copy number variation copy-ratio plots and make a manual determination of genotype for the CYP2D6 gene (and other genes if they contain clinically-actionable CNVs).   Below is one such copy-ratio plot that illustrates the problems we face:

copy ratio plot
A copy-ratio plot for 9 clinical samples from our targeted sequencing pipeline at the CYP2D6 gene and CYP2D7 pseudogene.  Note the noise in the data.

You can see from the plot that one sample (red) has what appears to be a deletion (copy ratio ~ 0.5).   We do look at these plots individually, but the problem with noise and complexity remains.  This means that the analyst must be, in effect, a domain expert on each gene with a clinically-actionable copy number variation.   This limits pipeline throughput and is impractical if the goal is to process hundreds or thousands of patient samples per month.

A role for machine learning?

It occurred to me that the copy ratio data fall into distinct patterns that a human (like myself) learns by eye and with experience.  These patterns could be classifiable by machine-learning methods.   I considered applying a convolution neural network (CNN) to the plot above.

However, I only had 175 samples in my test/train set drawn from real patients and CEPH/Coriell depositories.   Therefore, I thought it would be best to start with simple models and go from there.  To establish the ground truth CYP2D6 genotype, the samples had all be processed by our current pipeline methods, with many (but not all) confirmed by Taqman assay.

It began to dawn on me that I first needed a better representation of the training data.   I liked the output of the CNV-kit method (below) better than the method from our pipeline (above):

Visualization of CNV-kit output at CYP2D6. The gray and orange lines are not important to this discussion.

The important part of the plot above are the gray dots, representing copy ratio values across 19 different bins or segments along the CYP2D6/2D7 gene and pseudogene.   CNV-kit also had the advantage of being well-documented, fast to run, and available as open-source software on github.

Tidying the training set

The data plotted above looked like this after I did some wrangling and tidying in python:

Copy ratio data from CNV-kit output at the CYP2D6 and 2D7 gene/pseudogene.  There are five columns to the right (four not shown) that contain “one-hot” encoded ground-truth for model training.

With the data in “tidy” form (each column a variable, each row an observation, thank you Hadley Wickham), I was ready to train some machine learning models to see if I could classify common copy number variation events in CYP2D6 and bypass the time-consuming visualization step.

I had no idea if this would work, given that there are only 175 samples (total) to train on and some of the more rare copy number variation events only have a handful of examples.  In part 2, I will talk more about how I tried a LASSO regression model, which, while performing well, failed to yield the high accuracy needed for an automated clinical pipeline.  I then tried a simple one-layer neural network approach.  I’ll talk about the surprisingly good performance of neural network approach and also future directions for this project.

 

 

Decode SAM files with these handy references

I recently had to inspect some genomic alignments as part of a project.  Usually, I am just working with BAM files and if inspection is needed, I just visualize the pileups to see what is going on.

In this case, I just wanted a quick answer to how the reads were aligning to the reference, and I didn’t want to go through the process of subsetting and copying the BAM files to my local machine.

The SAM file is the uncompressed record of the read alignments produced by an aligner method (STAR, TopHat, BWA, etc….).   This file can get very large, and so is usually compressed into BAM (faster for machine parsing, but not human readable) and the SAM file is discarded.

In my case, I still had the SAM files around to inspect.  If you find yourself needing to read a SAM file, here are three helpful reference tools to make the process less painful:

1)  This page has an enormous amount of detail about SAM files including this helpful chart that enumerates all of the fields that you can expect to find specified within each alignment:

SAM file structure explained in this handy chart.

 

2) This post from the blog “zenfractal.com” contains a great exposition on CIGAR strings and how to decode them:

3)  And finally, if you’re trying to decode the SAM bitwise flags, you can calculate them using this tool from the Broad Institute:

Decode SAM flags with this handy online tool from the Broad Institute.

 

 

Get hands-on with t-SNE plots

With the growing popularity of single-cell RNA-Seq analysis, the t-SNE projection of multi-dimensional data is appearing more often in publications and online.  If you’ve ever wanted to develop a better intuitive feel for what exactly t-SNE does and where it can go wrong, this interactive tutorial (by Martin Wattenberg and Fernanda Viegas) is extremely compelling and useful.

A screen capture of the interactive t-SNE interface.

In addition to providing a wonderful, interactive plotting function, the authors go on to provide an informative tutorial explains the pitfalls and challenges of the optimization and hyper-parameter tuning of t-SNE projections and how to get the most from the plots.  Here is an example:

An example of how hyperparameter tuning affects the final plot.

In the example above, tuning the “perplexity” of the t-SNE projection causes the correct reconstruction of the data when values are between 30-50, but the same method fails when the parameter falls outside those ranges (i.e., too small or too large).

Go check out this distill.pub site.  It’s worth your time.

Breakthrough advances in 2018 so far: flu, germs, and cancer

2018 medicine breakthrough review!

So far this year has seen some pretty important research breakthrough advances in several key areas of health and medicine.  I want to briefly describe some of what we’ve seen in just the first few months of 2018.

Flu

A pharmaceutical company in Japan has released phase 3 trial results showing that its drug, Xofluza, can effectively kill the virus in just 24 hours in infected humans.  And it can do this with just one single dose, compared to a 10-dose, three day regimen of Tamiflu. The drug works by inhibiting an endonuclease needed for replication of the virus.

Germs

It is common knowledge that antibiotics are over-prescribed and over-used.  This fact has led to the rise of MRSA and other resistant bacteria which threaten human health.  Although it is thought that bacteria could be a source of novel antibiotics since they are in constant chemical warfare with each other, most bacteria aren’t culture-friendly in the lab and so researchers haven’t been looking at them for leads.  Until now.

Malacidin drugs kill multi-drug resistant S. Aureus in tests on rats.

By adopting whole genome sequencing approaches to soil bacterial diversity, researchers were able to screen for gene clusters associated with calcium-binding motifs known for antibiotic activity.   The result was the discovery of a novel class of lipo-peptides, called malacidins A and B.  They showed potent activity against MRSA in skin infection models in rats.

The researchers estimate that 99% of bacterial natural-product antibiotic compounds remain unexplored at present.

Cancer

2017 and 2018 have seen some major advances with cancer treatment.   It seems that the field is moving away from the focus on small-molecule drugs towards harnessing the patient’s own immune system to attack cancer.  The CAR-T therapies for pediatric leukemia appear extremely promising.  These kinds of therapies are now in trials for a wide range of blood and solid tumors.

A great summary of the advances being made is available here from the Fred Hutchinson Cancer Research Center.   Here is how Dr. Gilliland, President of Fred Hutch, begins his review of the advances:

I’ve gone on record to say that by 2025, cancer researchers will have developed curative therapeutic approaches for most if not all cancers.

I took some flak for putting that stake in the ground. But we in the cancer research field are making incredible strides toward better and safer, potentially curative treatments for cancer, and I’m excited for what’s next. I believe that we must set a high bar, execute and implement — that there should be no excuses for not advancing the field at that pace.

This is a stunning statement on its own;  but made even more so because it is usually the scientists in the day-to-day trenches of research who are themselves the most pessimistic about the possibility of rapid advances.

Additionally, an important paper came out recently proposing a novel paradigm for understanding and modeling cancer incidence with age.  For a long time the dominant model has been the “two-hit” hypothesis which predicts that clinically-observable cancers arise when a cell acquires sufficient mutations in tumor-suppressor genes to become a tumor.

This paper challenges that notion and shows that a model of thymic function decline (the thymus produces T-cells) over time better describes the incidence of cancers with age.   This model better fits the data and leads to the conclusion that cancers are continually arising in our bodies, but it is our properly functioning immune system that roots them out and prevents clinical disease from emerging.  This model also helps explain why novel cancer immunotherapies are so potent and why focus has shifted to supporting and activating T-cells.

Declining T cell production leads to increasing disease incidence with age.