Apply a Convolutional Neural Net to filter annotated variants

Category Variant Filtering

---

Overview

Annotate a VCF with scores from a Convolutional Neural Network (CNN). This tool streams variants and their reference context to a python program, which evaluates a pre-trained neural network on each variant. The default models were trained on single-sample VCFs. The default model should not be used on VCFs with annotations from joint call-sets. The neural network performs convolutions over the reference sequence surrounding the variant and combines those features with a multilayer perceptron on the variant annotations. 2D models convolve over aligned reads as well as the reference sequence, and variant annotations. 2D models require a SAM/BAM file as input and for the --tensor-type argument to be set to a tensor type which requires reads, as in the example below. Pre-trained 1D and 2D models are included in the distribution. It is possible to train your own models with the tools: {@link CNNVariantWriteTensors} and {@link CNNVariantTrain}. CNNVariantTrain will create a json architecture file and an hd5 weights file, which you can use with this tool. The advanced argument `info-annotation-keys` is available for models trained with different sets info field annotations. In order to do this you must first train your own model with the tools {@link CNNVariantWriteTensors} and {@link CNNVariantTrain}. Otherwise, providing this argument with anything but the standard set of annotations will result in an error.

1D Model with pre-trained architecture

 gatk CNNScoreVariants \
   -V vcf_to_annotate.vcf.gz \
   -R reference.fasta \
   -O annotated.vcf
 

2D Model with pre-trained architecture

 gatk CNNScoreVariants \
   -I aligned_reads.bam \
   -V vcf_to_annotate.vcf.gz \
   -R reference.fasta \
   -O annotated.vcf \
   -tensor-type read-tensor
 

1D Model with user-supplied architecture and weights:

 gatk CNNScoreVariants \
   -V vcf_to_annotate.vcf.gz \
   -R reference.fasta \
   -O annotated.vcf \
   -architecture path/to/my_model_folder/1dmodel.json
   -weights path/to/my_model_folder/1dmodel.hd5
 

2D Model with user-supplied model architecture and weights:

 gatk CNNScoreVariants \
   -I aligned_reads.bam \
   -V vcf_to_annotate.vcf.gz \
   -R reference.fasta \
   -O annotated.vcf \
   -tensor-type read-tensor \
   -architecture path/to/my_model_folder/2dmodel.json
   -weights path/to/my_model_folder/2dmodel.hd5
 

---

Additional Information

Read filters

These Read Filters are automatically applied to the data by the Engine before processing by CNNScoreVariants.

• ReadGroupBlackListReadFilter
• WellformedReadFilter

CNNScoreVariants specific arguments

This table summarizes the command-line arguments that are specific to this tool. For more details on each argument, see the list further down below the table or click on an argument name to jump directly to that entry in the list.

Argument name(s)	Default value	Summary
Required Arguments
--output  -O		Output file
--reference  -R		Reference sequence file
--variant  -V		A VCF file containing variants
Optional Tool Arguments
--architecture		Neural Net architecture configuration json file
--arguments_file		read one or more arguments files and add them to the command line
--cloud-index-prefetch-buffer  -CIPB	-1	Size of the cloud-only prefetch buffer (in MB; 0 to disable). Defaults to cloudPrefetchBuffer if unset.
--cloud-prefetch-buffer  -CPB	40	Size of the cloud-only prefetch buffer (in MB; 0 to disable).
--disable-bam-index-caching  -DBIC	false	If true, don't cache bam indexes, this will reduce memory requirements but may harm performance if many intervals are specified. Caching is automatically disabled if there are no intervals specified.
--disable-sequence-dictionary-validation	false	If specified, do not check the sequence dictionaries from our inputs for compatibility. Use at your own risk!
--filter-symbolic-and-sv	false	If set will filter symbolic and and structural variants from the input VCF
--gcs-max-retries  -gcs-retries	20	If the GCS bucket channel errors out, how many times it will attempt to re-initiate the connection
--gcs-project-for-requester-pays		Project to bill when accessing "requester pays" buckets. If unset, these buckets cannot be accessed. User must have storage.buckets.get permission on the bucket being accessed.
--help  -h	false	display the help message
--interval-merging-rule  -imr	ALL	Interval merging rule for abutting intervals
--intervals  -L		One or more genomic intervals over which to operate
--read-limit	128	Maximum number of reads to encode in a tensor, for 2D models only.
--sites-only-vcf-output	false	If true, don't emit genotype fields when writing vcf file output.
--tensor-type	reference	Name of the tensors to generate, reference for 1D reference tensors and read_tensor for 2D tensors.
--version	false	display the version number for this tool
--weights		Keras model HD5 file with neural net weights.
--window-size	128	Neural Net input window size
Optional Common Arguments
--add-output-sam-program-record	true	If true, adds a PG tag to created SAM/BAM/CRAM files.
--add-output-vcf-command-line	true	If true, adds a command line header line to created VCF files.
--create-output-bam-index  -OBI	true	If true, create a BAM/CRAM index when writing a coordinate-sorted BAM/CRAM file.
--create-output-bam-md5  -OBM	false	If true, create a MD5 digest for any BAM/SAM/CRAM file created
--create-output-variant-index  -OVI	true	If true, create a VCF index when writing a coordinate-sorted VCF file.
--create-output-variant-md5  -OVM	false	If true, create a a MD5 digest any VCF file created.
--disable-read-filter  -DF		Read filters to be disabled before analysis
--disable-tool-default-read-filters	false	Disable all tool default read filters (WARNING: many tools will not function correctly without their default read filters on)
--exclude-intervals  -XL		One or more genomic intervals to exclude from processing
--gatk-config-file		A configuration file to use with the GATK.
--input  -I		BAM/SAM/CRAM file containing reads
--interval-exclusion-padding  -ixp	0	Amount of padding (in bp) to add to each interval you are excluding.
--interval-padding  -ip	0	Amount of padding (in bp) to add to each interval you are including.
--interval-set-rule  -isr	UNION	Set merging approach to use for combining interval inputs
--inverted-read-filter  -XRF		Inverted (with flipped acceptance/failure conditions) read filters applied before analysis (after regular read filters).
--lenient  -LE	false	Lenient processing of VCF files
--max-variants-per-shard	0	If non-zero, partitions VCF output into shards, each containing up to the given number of records.
--QUIET	false	Whether to suppress job-summary info on System.err.
--read-filter  -RF		Read filters to be applied before analysis
--read-index		Indices to use for the read inputs. If specified, an index must be provided for every read input and in the same order as the read inputs. If this argument is not specified, the path to the index for each input will be inferred automatically.
--read-validation-stringency  -VS	SILENT	Validation stringency for all SAM/BAM/CRAM/SRA files read by this program. The default stringency value SILENT can improve performance when processing a BAM file in which variable-length data (read, qualities, tags) do not otherwise need to be decoded.
--seconds-between-progress-updates	10.0	Output traversal statistics every time this many seconds elapse
--sequence-dictionary		Use the given sequence dictionary as the master/canonical sequence dictionary. Must be a .dict file.
--tmp-dir		Temp directory to use.
--use-jdk-deflater  -jdk-deflater	false	Whether to use the JdkDeflater (as opposed to IntelDeflater)
--use-jdk-inflater  -jdk-inflater	false	Whether to use the JdkInflater (as opposed to IntelInflater)
--verbosity	INFO	Control verbosity of logging.
Advanced Arguments
--disable-avx-check	false	If set, no check will be made for AVX support. Use only if you have installed a pre-1.6 TensorFlow build.
--inference-batch-size	256	Size of batches for python to do inference on.
--info-annotation-keys	[MQ, DP, SOR, FS, QD, MQRankSum, ReadPosRankSum]	The VCF info fields to send to python. This should only be changed if a new model has been trained which expects the annotations provided here.
--inter-op-threads	0	Number of inter-op parallelism threads to use for Tensorflow
--intra-op-threads	0	Number of intra-op parallelism threads to use for Tensorflow
--output-tensor-dir		Optional directory where tensors can be saved for debugging or visualization.
--showHidden	false	display hidden arguments
--transfer-batch-size	512	Size of data to queue for python streaming.

Argument details

Arguments in this list are specific to this tool. Keep in mind that other arguments are available that are shared with other tools (e.g. command-line GATK arguments); see Inherited arguments above.

---

--add-output-sam-program-record / -add-output-sam-program-record

If true, adds a PG tag to created SAM/BAM/CRAM files.

boolean  true

---

--add-output-vcf-command-line / -add-output-vcf-command-line

If true, adds a command line header line to created VCF files.

boolean  true

---

--architecture / -architecture

Neural Net architecture configuration json file

String  null

---

--arguments_file

read one or more arguments files and add them to the command line

List[File]  []

---

--cloud-index-prefetch-buffer / -CIPB

Size of the cloud-only prefetch buffer (in MB; 0 to disable). Defaults to cloudPrefetchBuffer if unset.

int  -1  [ [ -∞  ∞ ] ]

---

--cloud-prefetch-buffer / -CPB

Size of the cloud-only prefetch buffer (in MB; 0 to disable).

int  40  [ [ -∞  ∞ ] ]

---

--create-output-bam-index / -OBI

If true, create a BAM/CRAM index when writing a coordinate-sorted BAM/CRAM file.

boolean  true

---

--create-output-bam-md5 / -OBM

If true, create a MD5 digest for any BAM/SAM/CRAM file created

boolean  false

---

--create-output-variant-index / -OVI

If true, create a VCF index when writing a coordinate-sorted VCF file.

boolean  true

---

--create-output-variant-md5 / -OVM

If true, create a a MD5 digest any VCF file created.

boolean  false

---

--disable-avx-check / -disable-avx-check

If set, no check will be made for AVX support. Use only if you have installed a pre-1.6 TensorFlow build.

boolean  false

---

--disable-bam-index-caching / -DBIC

If true, don't cache bam indexes, this will reduce memory requirements but may harm performance if many intervals are specified. Caching is automatically disabled if there are no intervals specified.

boolean  false

---

--disable-read-filter / -DF

Read filters to be disabled before analysis

List[String]  []

---

--disable-sequence-dictionary-validation / -disable-sequence-dictionary-validation

If specified, do not check the sequence dictionaries from our inputs for compatibility. Use at your own risk!

boolean  false

---

--disable-tool-default-read-filters / -disable-tool-default-read-filters

Disable all tool default read filters (WARNING: many tools will not function correctly without their default read filters on)

boolean  false

---

--exclude-intervals / -XL

One or more genomic intervals to exclude from processing
Use this argument to exclude certain parts of the genome from the analysis (like -L, but the opposite). This argument can be specified multiple times. You can use samtools-style intervals either explicitly on the command line (e.g. -XL 1 or -XL 1:100-200) or by loading in a file containing a list of intervals (e.g. -XL myFile.intervals). strings gathered from the command line -XL argument to be parsed into intervals to exclude

List[String]  []

---

--filter-symbolic-and-sv / -filter-symbolic-and-sv

If set will filter symbolic and and structural variants from the input VCF

boolean  false

---

--gatk-config-file

A configuration file to use with the GATK.

String  null

---

--gcs-max-retries / -gcs-retries

If the GCS bucket channel errors out, how many times it will attempt to re-initiate the connection

int  20  [ [ -∞  ∞ ] ]

---

--gcs-project-for-requester-pays

Project to bill when accessing "requester pays" buckets. If unset, these buckets cannot be accessed. User must have storage.buckets.get permission on the bucket being accessed.

String  ""

---

--help / -h

display the help message

boolean  false

---

--inference-batch-size / -inference-batch-size

Size of batches for python to do inference on.

int  256  [ [ 1  4,096 ] ]

---

--info-annotation-keys / -info-annotation-keys

The VCF info fields to send to python. This should only be changed if a new model has been trained which expects the annotations provided here.

List[String]  [MQ, DP, SOR, FS, QD, MQRankSum, ReadPosRankSum]

---

--input / -I

BAM/SAM/CRAM file containing reads

List[GATKPath]  []

---

--inter-op-threads / -inter-op-threads

Number of inter-op parallelism threads to use for Tensorflow

int  0  [ [ 0  4,096 ] ]

---

--interval-exclusion-padding / -ixp

Amount of padding (in bp) to add to each interval you are excluding.
Use this to add padding to the intervals specified using -XL. For example, '-XL 1:100' with a padding value of 20 would turn into '-XL 1:80-120'. This is typically used to add padding around targets when analyzing exomes.

int  0  [ [ -∞  ∞ ] ]

---

--interval-merging-rule / -imr

Interval merging rule for abutting intervals
By default, the program merges abutting intervals (i.e. intervals that are directly side-by-side but do not actually overlap) into a single continuous interval. However you can change this behavior if you want them to be treated as separate intervals instead.

The --interval-merging-rule argument is an enumerated type (IntervalMergingRule), which can have one of the following values:

ALL

OVERLAPPING_ONLY

IntervalMergingRule  ALL

---

--interval-padding / -ip

Amount of padding (in bp) to add to each interval you are including.
Use this to add padding to the intervals specified using -L. For example, '-L 1:100' with a padding value of 20 would turn into '-L 1:80-120'. This is typically used to add padding around targets when analyzing exomes.

int  0  [ [ -∞  ∞ ] ]

---

--interval-set-rule / -isr

Set merging approach to use for combining interval inputs
By default, the program will take the UNION of all intervals specified using -L and/or -XL. However, you can change this setting for -L, for example if you want to take the INTERSECTION of the sets instead. E.g. to perform the analysis only on chromosome 1 exomes, you could specify -L exomes.intervals -L 1 --interval-set-rule INTERSECTION. However, it is not possible to modify the merging approach for intervals passed using -XL (they will always be merged using UNION). Note that if you specify both -L and -XL, the -XL interval set will be subtracted from the -L interval set.

The --interval-set-rule argument is an enumerated type (IntervalSetRule), which can have one of the following values:

UNION

Take the union of all intervals

INTERSECTION

Take the intersection of intervals (the subset that overlaps all intervals specified)

IntervalSetRule  UNION

---

--intervals / -L

One or more genomic intervals over which to operate

List[String]  []

---

--intra-op-threads / -intra-op-threads

Number of intra-op parallelism threads to use for Tensorflow

int  0  [ [ 0  4,096 ] ]

---

--inverted-read-filter / -XRF

Inverted (with flipped acceptance/failure conditions) read filters applied before analysis (after regular read filters).

List[String]  []

---

--lenient / -LE

Lenient processing of VCF files

boolean  false

---

--max-variants-per-shard

If non-zero, partitions VCF output into shards, each containing up to the given number of records.

int  0  [ [ 0  ∞ ] ]

---

--output / -O

Output file

R GATKPath  null

---

--output-tensor-dir / -output-tensor-dir

Optional directory where tensors can be saved for debugging or visualization.

String  ""

---

--QUIET

Whether to suppress job-summary info on System.err.

Boolean  false

---

--read-filter / -RF

Read filters to be applied before analysis

List[String]  []

---

--read-index / -read-index

Indices to use for the read inputs. If specified, an index must be provided for every read input and in the same order as the read inputs. If this argument is not specified, the path to the index for each input will be inferred automatically.

List[GATKPath]  []

---

--read-limit / -read-limit

Maximum number of reads to encode in a tensor, for 2D models only.

int  128  [ [ 0  ∞ ] ]

---

--read-validation-stringency / -VS

Validation stringency for all SAM/BAM/CRAM/SRA files read by this program. The default stringency value SILENT can improve performance when processing a BAM file in which variable-length data (read, qualities, tags) do not otherwise need to be decoded.

The --read-validation-stringency argument is an enumerated type (ValidationStringency), which can have one of the following values:

STRICT

LENIENT

SILENT

ValidationStringency  SILENT

---

--reference / -R

Reference sequence file

R GATKPath  null

---

--seconds-between-progress-updates / -seconds-between-progress-updates

Output traversal statistics every time this many seconds elapse

double  10.0  [ [ -∞  ∞ ] ]

---

--sequence-dictionary / -sequence-dictionary

Use the given sequence dictionary as the master/canonical sequence dictionary. Must be a .dict file.

GATKPath  null

---

--showHidden / -showHidden

display hidden arguments

boolean  false

---

--sites-only-vcf-output

If true, don't emit genotype fields when writing vcf file output.

boolean  false

---

--tensor-type / -tensor-type

Name of the tensors to generate, reference for 1D reference tensors and read_tensor for 2D tensors.

The --tensor-type argument is an enumerated type (TensorType), which can have one of the following values:

reference

1 Hot encoding of a reference sequence.

read_tensor

Read tensor are 3D tensors spanning aligned reads, sites and channels. The maximum number of reads is a hyper-parameter typically set to 128. There are 15 channels in the read tensor. They correspond to the reference sequence data (4), read sequence data (4), insertions and deletions (2) read flags (4) and mapping quality (1).

TensorType  reference

---

--tmp-dir

Temp directory to use.

GATKPath  null

---

--transfer-batch-size / -transfer-batch-size

Size of data to queue for python streaming.

int  512  [ [ 1  8,192 ] ]

---

--use-jdk-deflater / -jdk-deflater

Whether to use the JdkDeflater (as opposed to IntelDeflater)

boolean  false

---

--use-jdk-inflater / -jdk-inflater

Whether to use the JdkInflater (as opposed to IntelInflater)

boolean  false

---

--variant / -V

A VCF file containing variants

R GATKPath  null

---

--verbosity / -verbosity

Control verbosity of logging.

The --verbosity argument is an enumerated type (LogLevel), which can have one of the following values:

ERROR

WARNING

INFO

DEBUG

LogLevel  INFO

---

--version

display the version number for this tool

boolean  false

---

--weights / -weights

Keras model HD5 file with neural net weights.

String  null

---

--window-size / -window-size

Neural Net input window size

int  128  [ [ 0  ∞ ] ]

---

Return to top

---

GATK version 4.6.0.0 built at Sat, 29 Jun 2024 20:47:29 -0400.