Skip to content

LooseLab/readfish

Repository files navigation

If you are anything like us (Matt), reading a README is the last thing you do when running code. PLEASE DON'T DO THAT FOR READFISH. This will effect changes to your sequencing and - if you use it incorrectly - cost you money. We have added a list of GOTCHAs at the end of this README. We have almost certainly missed some... so - if something goes wrong, let us know so we can add you to the GOTCHA hall of fame!

Note

We also have more detailed documentation for your perusal at https://looselab.github.io/readfish

Note

Now also see our cool FAQ.

Warning

Breaking for any version of MinKNOW <= 6.0.0 As of readfish >=2024.3.0 we no longer support guppy.

readfish is a Python package that integrates with the Read Until API.

The Read Until API provides a mechanism for an application to connect to a MinKNOW server to obtain read data in real-time. The data can be analysed in the way most fit for purpose, and a return call can be made to the server to unblock the read in progress and so direct sequencing capacity towards reads of interest.

This implementation of readfish requires Dorado server version >= 7.3.9 and MinKNOW version core >= 6.0.0 . It will not work on earlier versions.

To run with earlier versions of MinKNOW please use an earlier version of readfish.

The code here has been tested with Dorado in GPU mode using GridION Mk1 and NVIDIA RTX4090s on live sequencing runs and on MacOSX M2Max using playback on a simulated run (see below for how to test this). This code is run at your own risk as it DOES affect sequencing output. You are strongly advised to test your setup prior to running (see below for example tests).

Supported Sequencing Platforms

The following platforms are supported:

  • PromethION Big Boy
  • P2Solo Smol Big Boy
  • P2i Not so Smol Big Boy
  • GridION Box
  • MinION Smol Boy

Warning

PromethION support is currently only available using the Mappy-rs plugin only. See here for more information.

Supported OS's

The following OSs are supported:

  • Linux yay
  • MacOS boo (Apple Silicon Only)

Note

Note - MacOS supports is on MinKNOW 5.7 and greater using Dorado basecaller on Apple Silicon devices only.

Citation

The paper is available at nature biotechnology and bioRxiv

If you use this software please cite: 10.1038/s41587-020-00746-x

Readfish enables targeted nanopore sequencing of gigabase-sized genomes Alexander Payne, Nadine Holmes, Thomas Clarke, Rory Munro, Bisrat Debebe, Matthew Loose Nat Biotechnol (2020); doi: https://doi.org/10.1038/s41587-020-00746-x

Other works

An update preprint is available at bioRxiv

Barcode aware adaptive sampling for Oxford Nanopore sequencers Alexander Payne, Rory Munro, Nadine Holmes, Christopher Moore, Matt Carlile, Matthew Loose bioRxiv (2021); doi: https://doi.org/10.1101/2021.12.01.470722

Installation

Our preferred installation method is via conda.

The environment is specified as:

name: readfish
channels:
  - bioconda
  - conda-forge
  - defaults
dependencies:
  - python=3.10
  - pip
  - pip:
    - readfish[all]

Saving the snippet above as readfish_env.yml and running the following commands will create the environment.

conda env create -f readfish_env.yml
conda activate readfish

Apple Silicon

Some users may encounter an issue with grpcio on apple silicon. This can be fixed by reinstalling grpcio as follows:

pip uninstall grpcio
GRPC_PYTHON_LDFLAGS=" -framework CoreFoundation" pip install grpcio --no-binary :all:

Installing with development dependencies

A conda yaml file is available for installing with dev dependencies - development.yml

curl -LO https://raw.githubusercontent.com/LooseLab/readfish/e30f1fa8ac7a37bb39e9d8b49251426fe1674c98/docs/development.yml?token=GHSAT0AAAAAACBZL42IS3QVM4ZGPPW4SHB6ZE67V6Q
conda env create -f development.yml
conda activate readfish_dev

‼️ Important !!

MinKNOW has now transitioned from Guppy to Dorado. Until MinKNOW version 5.9 both Guppy and Dorado used ont-pyguppy-client-lib.
As of MinKNOW version 5.9 and Dorado server version 7.3.9 and greater Dorado required an alternate library, ont-pybasecall-client-lib, but guppy could still be used.
As of MinKNOW 6.0 Guppy support has been deprecated and only Dorado support is provided. It is important to ensure the correct library is installed for your specific configuration and the listed ont-pyguppy-client-lib or ont-pybasecaller-client-lib version may not match the versions installed on your system. To fix this, Please see this issue, using the appropriate library.

ONT's Dorado Basecall Server GPU should be installed and running as a server.

Alternatively, install readfish into a python virtual-environment
# Make a virtual environment
python3 -m venv readfish
. ./readfish/bin/activate
pip install --upgrade pip

# Install our readfish Software
pip install readfish[all]

# Install ont_pybasecall_client that matches your dorado basecall server version. E.G.
pip install ont_pybasecall_client_lib==7.1.2

Usage

usage: readfish [-h] [--version]  ...

positional arguments:
                   Sub-commands
    targets        Run targeted sequencing
    barcode-targets
                   Run targeted sequencing
    unblock-all    Unblock all reads
    validate       readfish TOML Validator

options:
  -h, --help       show this help message and exit
  --version        show program's version number and exit

See '<command> --help' to read about a specific sub-command.

TOML File

For information on the TOML files see TOML.md. There are several example TOMLS, with comments explaining what each field does, as well as the overall purpose of the TOML file here .

Testing

To test readfish on your configuration we recommend first running a playback experiment to test unblock speed and then selection.

The following steps should all happen with a configuration (test) flow cell inserted into the target device. A simulated device can also be created within MinKNOW, following these instructions. This assumes that you are runnning MinKNOW locally, using default ports. If this is not the case a developer API token is required on the commands as well, as well as setting the correct port.

If no test flow cell is available, a simulated device can be created within MinKNOW, following the below instructions.

Adding a simulated position for testing

  1. Linux

    In the readfish virtual environment we created earlier:

    • See help
    python -m minknow_api.examples.manage_simulated_devices --help
    • Add Minion position
    python -m minknow_api.examples.manage_simulated_devices --add MS00000
    • Add PromethION position
    python -m minknow_api.examples.manage_simulated_devices --prom --add S0
  2. Mac

    In the readfish virtual environment we created earlier:

    • See help
    python -m minknow_api.examples.manage_simulated_devices --help
    • Add Minion position
    python -m minknow_api.examples.manage_simulated_devices --add MS00000
    • Add PromethION position
    python -m minknow_api.examples.manage_simulated_devices --prom --add S0

As a back up it is possible to restart MinKNOW with a simulated device. This is done as follows:

  1. Stop minknow

    On Linux:

    cd /opt/ont/minknow/bin
    sudo systemctl stop minknow
  2. Start MinKNOW with a simulated device

    On Linux

    sudo ./mk_manager_svc -c /opt/ont/minknow/conf --simulated-minion-devices=1 &

You may need to add the host 127.0.0.1 in the MinKNOW UI.

Configuring bulk FAST5 file Playback

Download an open access bulk FAST5 file, either R9.4.1 4khz or R10 (5khz). This file is 21Gb so make sure you have sufficient space. A promethION bulkfile is also available but please note this is R10.4 4khz and so will give slightly unexpected results on MinKNOW which assumes 5khz. This file is approx 35Gb in size.

Previously to set up Playback using a pre-recorded bulk FAST5 file, it was necessary to edit the sequencing configuration file that MinKNOW uses. This is currently no longer the case. The "old method" steps are left after this section for reference only or if the direct playback from a bulk file option is removed in future.

To start sequencing using playback, simply begin setting up the run in the MinKNOW UI as you would usually. Under Run Options you can select Simulated Playback and browse to the downloaded Bulk Fast5 file.

Run Options Screenshot

[!NOTE]
Note - The below instructions, whilst they will still work, are no longer required. They are left here for reference only. As of Minknow 5.7, it is possible to select a bulk FAST5 file for playback in the MinKNOW UI.

Old method Configuring bulk FAST5 file Playback

To setup a simulation the sequencing configuration file that MinKNOW uses must be edited. Steps:
  1. Download an open access bulkfile - either R9.4.1 or R10 (5khz). These files are approximately 21Gb so make sure you have plenty of space. The files are from NA12878 sequencing data using either R9.4.1 or R10.4 pores. Data is not barcoded and the libraries were ligation preps from DNA extracted from cell lines.

  2. A promethION bulkfile is also available but please note this is R10.4, 4khz, and so will give slightly unexpected results on MinKNOW which assumes 5khz.

  3. Copy a sequencing TOML file to the user_scripts folder:

    On Mac if your MinKNOW output directory is the default:

    mkdir -p /Library/MinKNOW/data/user_scripts/simulations
    cp /Applications/MinKNOW.app/Contents/Resources/conf/package/sequencing/sequencing_MIN106_DNA.toml /Library/MinKNOW/data/user_scripts/simulations/sequencing_MIN106_DNA_sim.toml

    On Linux:

    sudo mkdir -p /opt/ont/minknow/conf/package/sequencing/simulations
    cp /opt/ont/minknow/conf/package/sequencing/sequencing_MIN106_DNA.toml /opt/ont/minknow/conf/package/sequencing/simulations/sequencing_MIN106_DNA_sim.toml
  4. Edit the copied file to add the following line under the line that reads "[custom_settings]":

    simulation = "/full/path/to/your_bulk.FAST5"
    

    Change the text between the quotes to point to your downloaded bulk FAST5 file.

  5. Optional, If running Dorado in GPU mode, you can set the parameter break_reads_after_seconds = 1.0 to break_reads_after_seconds = 0.4. This results in a smaller read chunk. For R10.4 this is not required but can be tried. For adaptive sampling on PromethION, this should be left at 1 second.

  6. In MinKNOW >= 6.0.0 this value defaults to 0.8 which is a reasonable balance.

  7. In the MinKNOW GUI, right click on a sequencing position and select Reload Scripts. Your version of MinKNOW will now playback the bulkfile rather than live sequencing.

  8. Start a sequencing run as you would normally, selecting the corresponding flow cell type to the edited script (here FLO-MIN106) as the flow cell type.

Whichever instructions you followed, the run should start and immediately begin a mux scan. Let it run for around five minutes after which your read length histogram should look as below: Control Image Screenshot

Testing unblock response

Now we shall test unblocking by running readfish unblock-all which will simply eject every single read on the flow cell.

  1. To do this run:
    readfish unblock-all --device <YOUR_DEVICE_ID> --experiment-name "Testing readfish Unblock All"
  2. Leave the run for a further 5 minutes and observe the read length histogram. If unblocks are happening correctly you will see something like the below: Unblock All Screenshot A closeup of the unblock peak shows reads being unblocked quickly: Closeup Unblock Image

If you are happy with the unblock response, move on to testing base-calling.

Note: The plots here are generated from running readfish unblock-all on an Apple Silicon laptop. The unblock response may be faster on a GPU server.

Testing base-calling and mapping

To test selective sequencing you must have access to a dorado basecall server.

and a readfish TOML configuration file.

  1. First make a local copy of the example TOML file:

    curl -O https://raw.githubusercontent.com/LooseLab/readfish/master/docs/_static/example_tomls/human_chr_selection.toml
  2. If on PromethION, edit the mapper_settings.mappy section to read:

    [mapper_settings.mappy-rs]
  3. If on MinKNOW core>=5.9.0 and Dorado server version >=7.3.9, edit the basecaller section to read:

    [caller_settings.dorado]
  4. Modify the fn_idx_in field in the file to be the full path to a minimap2 index of the human genome.

  5. Modify the targets fields for each condition to reflect the naming convention used in your index. This is the sequence name only, up to but not including any whitespace. e.g. >chr1 human chromosome 1 would become chr1. If these names do not match, then target matching will fail.

We can now validate this TOML file to see if it will be loaded correctly.

readfish validate human_chr_selection.toml

Errors with the configuration will be written to the terminal along with a text description of the conditions for the experiment as below.

2023-10-05 15:29:18,934 readfish /home/adoni5/mambaforge/envs/readfish_dev/bin/readfish validate human_chr_selection.toml
2023-10-05 15:29:18,934 readfish command='validate'
2023-10-05 15:29:18,934 readfish log_file=None
2023-10-05 15:29:18,934 readfish log_format='%(asctime)s %(name)s %(message)s'
2023-10-05 15:29:18,934 readfish log_level='info'
2023-10-05 15:29:18,934 readfish no_check_plugins=False
2023-10-05 15:29:18,934 readfish no_describe=False
2023-10-05 15:29:18,934 readfish prom=False
2023-10-05 15:29:18,934 readfish toml='human_chr_selection.toml'
2023-10-05 15:29:18,934 readfish.validate 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
2023-10-05 15:29:18,937 readfish.validate Loaded TOML config without error
2023-10-05 15:29:18,937 readfish.validate Initialising Caller
2023-10-05 15:29:18,945 readfish.validate Caller initialised
2023-10-05 15:29:18,945 readfish.validate Initialising Aligner
2023-10-05 15:29:18,947 readfish.validate Aligner initialised
2023-10-05 15:29:18,948 readfish.validate Configuration description:
Region hum_test (control=False).
Region applies to section of flow cell (# = applied, . = not applied):

    ################################
    ################################
    ################################
    ################################
    ################################
    ################################
    ################################
    ################################

2023-10-05 15:29:18,948 readfish.validate Using the mappy plugin. Using reference: /home/adoni5/Documents/Bioinformatics/refs/hg38_no_alts.fa.gz.split/hg38_chr_M.mmi.

Region hum_test has targets on 1 contig, with 1 found in the provided reference.
This region has 2 total targets (+ve and -ve strands), covering approximately 100.00% of the genome.
  1. If your toml file validates then run the following command:

  2. readfish targets --toml <PATH_TO_TOML> --device <YOUR_DEVICE_ID> --log-file test.log --experiment-name human_select_test
  3. In the terminal window you should see messages reporting the speed of mapping of the form:

    2023-10-05 15:24:03,910 readfish.targets MinKNOW is reporting PHASE_MUX_SCAN, waiting for PHASE_SEQUENCING to begin.
    2023-10-05 15:25:48,150 readfish._read_until_client Protocol phase changed to PHASE_SEQUENCING
    2023-10-05 15:25:48,724 readfish.targets 0494R/0.5713s; Avg: 0494R/0.5713s; Seq:0; Unb:494; Pro:0; Slow batches (>1.00s): 0/1
    2023-10-05 15:25:52,132 readfish.targets 0004R/0.1831s; Avg: 0249R/0.3772s; Seq:0; Unb:498; Pro:0; Slow batches (>1.00s): 0/2
    2023-10-05 15:25:52,600 readfish.targets 0122R/0.2494s; Avg: 0206R/0.3346s; Seq:0; Unb:620; Pro:0; Slow batches (>1.00s): 0/3
    2023-10-05 15:25:52,967 readfish.targets 0072R/0.2144s; Avg: 0173R/0.3046s; Seq:0; Unb:692; Pro:0; Slow batches (>1.00s): 0/4
    2023-10-05 15:25:53,349 readfish.targets 0043R/0.1932s; Avg: 0147R/0.2823s; Seq:0; Unb:735; Pro:0; Slow batches (>1.00s): 0/5
    2023-10-05 15:25:53,759 readfish.targets 0048R/0.2011s; Avg: 0130R/0.2688s; Seq:0; Unb:783; Pro:0; Slow batches (>1.00s): 0/6
    2023-10-05 15:25:54,206 readfish.targets 0126R/0.2458s; Avg: 0129R/0.2655s; Seq:0; Unb:909; Pro:0; Slow batches (>1.00s): 0/7
    2023-10-05 15:25:54,580 readfish.targets 0082R/0.2180s; Avg: 0123R/0.2595s; Seq:0; Unb:991; Pro:0; Slow batches (>1.00s): 0/8
    2023-10-05 15:25:54,975 readfish.targets 0053R/0.2110s; Avg: 0116R/0.2542s; Seq:0; Unb:1,044; Pro:0; Slow batches (>1.00s): 0/9
    2023-10-05 15:25:55,372 readfish.targets 0057R/0.2051s; Avg: 0110R/0.2492s; Seq:0; Unb:1,101; Pro:0; Slow batches (>1.00s): 0/10
    2023-10-05 15:25:55,817 readfish.targets 0135R/0.2467s; Avg: 0112R/0.2490s; Seq:0; Unb:1,236; Pro:0; Slow batches (>1.00s): 0/11
    2023-10-05 15:25:56,192 readfish.targets 0086R/0.2206s; Avg: 0110R/0.2466s; Seq:0; Unb:1,322; Pro:0; Slow batches (>1.00s): 0/12
    2023-10-05 15:25:56,588 readfish.targets 0060R/0.2138s; Avg: 0106R/0.2441s; Seq:0; Unb:1,382; Pro:0; Slow batches (>1.00s): 0/13
    2023-10-05 15:25:56,989 readfish.targets 0060R/0.2123s; Avg: 0103R/0.2418s; Seq:0; Unb:1,442; Pro:0; Slow batches (>1.00s): 0/14
    2023-10-05 15:25:57,429 readfish.targets 0133R/0.2502s; Avg: 0105R/0.2424s; Seq:0; Unb:1,575; Pro:0; Slow batches (>1.00s): 0/15
    2023-10-05 15:25:57,809 readfish.targets 0089R/0.2280s; Avg: 0104R/0.2415s; Seq:0; Unb:1,664; Pro:0; Slow batches (>1.00s): 0/16
    2023-10-05 15:25:58,210 readfish.targets 0059R/0.2247s; Avg: 0101R/0.2405s; Seq:0; Unb:1,723; Pro:0; Slow batches (>1.00s): 0/17
    ^C2023-10-05 15:25:58,238 readfish.targets Keyboard interrupt received, stopping readfish
    
WARNING
Note: if these times are longer than the number of seconds specified in the break read chunk in the sequencing TOML, you will have performance issues. Contact us via github issues for support.

This log is a little dense at first. Moving from left to right, we have:

[Date Time] [Logger Name] [Batch Stats]; [Average Batch Stats]; [Count commands sent]; [Slow Batch Info]

Using the provided log as an example:

On 2023-10-05 at 15:25:56,989, the Readfish targets command logged a batch of read signal:

- It saw 60 reads in the current batch.
- The batch took 0.2123 seconds.
- On average, batches are 103 reads, which are processed in 0.2418 seconds.
- Since the start, 0 reads were sequenced, 1,442 reads were unblocked, and 0 reads were asked to proceed.
- Out of 14 total batches processed, 0 were considered slow (took more than 1 second).

The important thing to note here is that the average batch time is less than the break read chunk time in the sequencing TOML. The slow batch section will show the number of batches that were slower than break reads. If the average is lower, or the slow batch count is high, you will have performance issues. Contact us via github issues for support.

If you are happy with the speed of mapping, move on to testing a selection.

Testing expected results from a selection experiment.

The only way to test readfish on a playback run is to look at changes in read length for rejected vs accepted reads. To do this:

  1. Start a fresh simulation run using the bulkfile provided above.
  2. Restart the readfish command (as above):
    readfish targets --toml <PATH_TO_TOML> --device <YOUR_DEVICE_ID> --log-file test.log --experiment-name human_select_test
  3. Allow the run to proceed for at least 15 minutes (making sure you are writing out read data!).
  4. After 15 minutes it should look something like this: Playback Unblock Image If one zooms in on the unblock peak: Closeup Playback Unblock Image And if one zooms to exclude the unblock peak: Closeup Playback On Target Image NOTE: These simulations are also run on Apple Silicon - GPU platform performance may vary - please contact us via github issues for support.

Analysing results with readfish stats

Once a run is complete, it can be analysed with the readfish stats command.

HTML file output is optional.

readfish stats --toml <path/to/toml/file.toml> --fastq-directory  <path/to/run/folder> --html <filename>

Readfish stats will use the initial experiment configuration to analyse the final sequence data and output a formatted table to the screen. The table is broken into two sections. For clarity these are shown individually below.

In the first table, the data is summarised by condition as defined in the TOML file. In this example we have a single Region - "hum_test". The total number of reads is shown, along with the number of alignments broken down into On-Target and Off-Target. In addition, we show yield, median read length and a summary of the number of targets.

ConditionReadsAlignmentsYieldMedian read lengthsNumber of targetsPercent targetEstimated coverage
On-TargetOff-TargetTotalOn-TargetOff-TargetTotalRatioOn-targetOff-targetCombined
hum_test112,058819 (0.73%)111,239 (99.27%)112,0589.27 Mb (5.49%)159.43 Mb (94.51%)168.69 Mb1:17.200 b896 b896 b23.60%0.08 X
On-TargetOff-TargetTotalOn-TargetOff-TargetTotalRatioOn-targetOff-targetCombined
ConditionReadsAlignmentsYieldMedian read lengthsNumber of targetsPercent targetEstimated coverage

The lower portion of the table shows the data broken down by contig in the reference (and so can be very long if using a complex reference!). Again data are broken down by On and Off target. Read counts, yield, median and N50 read lengths are presented. Finally we estimate the proportion of reads on target and an estimate of coverage.

In this experiment, we were targeting chromosomes 20 and 21. As this is a playback run there is no effect on yield but you can see a clear effect on read length. The read length N50 and Median is higher for chromosomes 20 and 21 as expected. If running on more performant systems, the anticipated difference would be higher.

Condition Namehum_test
ConditionContigContig LengthReadsAlignmentsYieldMedian read lengthsN50Number of targetsPercent targetEstimated coverage
MappedUnmappedTotalOn-TargetOff-TargetTotalOn-TargetOff-TargetTotalRatioOn-targetOff-targetCombinedOn-TargetOff-TargetTotal
hum_testchr1248,956,42210,015010,0156 (0.06%)10,009 (99.94%)10,01548.65 Kb (0.37%)13.03 Mb (99.63%)13.08 Mb1:267.870 b891 b891 b0 b1.35 Kb1.35 Kb00.00%0.00 X
hum_testchr2242,193,5298,82508,8259 (0.10%)8,816 (99.90%)8,82547.36 Kb (0.36%)13.05 Mb (99.64%)13.09 Mb1:275.510 b894 b894 b0 b1.49 Kb1.49 Kb00.00%0.00 X
hum_testchr3198,295,5598,00508,0056 (0.07%)7,999 (99.93%)8,005193.03 Kb (1.73%)10.98 Mb (98.27%)11.17 Mb1:56.860 b893 b893 b0 b1.42 Kb1.42 Kb00.00%0.00 X
hum_testchr4190,214,5557,38107,38130 (0.41%)7,351 (99.59%)7,381861.07 Kb (7.29%)10.95 Mb (92.71%)11.81 Mb1:12.720 b917 b917 b0 b1.60 Kb1.60 Kb00.00%0.00 X
hum_testchr5181,538,2597,54507,5455 (0.07%)7,540 (99.93%)7,54550.70 Kb (0.50%)10.18 Mb (99.50%)10.23 Mb1:200.680 b896 b896 b0 b1.40 Kb1.40 Kb00.00%0.00 X
hum_testchr6170,805,9795,80805,8089 (0.15%)5,799 (99.85%)5,808116.44 Kb (1.35%)8.53 Mb (98.65%)8.65 Mb1:73.280 b905 b905 b0 b1.49 Kb1.49 Kb00.00%0.00 X
hum_testchr7159,345,9736,38306,3832 (0.03%)6,381 (99.97%)6,38326.06 Kb (0.29%)9.11 Mb (99.71%)9.14 Mb1:349.590 b895 b895 b0 b1.44 Kb1.44 Kb00.00%0.00 X
hum_testchr8145,138,6365,20805,2081 (0.02%)5,207 (99.98%)5,208285 b (0.00%)7.43 Mb (100.00%)7.43 Mb1:26061.600 b892 b892 b0 b1.44 Kb1.44 Kb00.00%0.00 X
hum_testchr9138,394,7174,25304,25323 (0.54%)4,230 (99.46%)4,25391.15 Kb (1.50%)6.00 Mb (98.50%)6.09 Mb1:65.850 b899 b899 b0 b1.46 Kb1.46 Kb00.00%0.00 X
hum_testchr10133,797,4224,42404,42415 (0.34%)4,409 (99.66%)4,42495.02 Kb (1.37%)6.86 Mb (98.63%)6.95 Mb1:72.160 b915 b915 b0 b1.56 Kb1.56 Kb00.00%0.00 X
hum_testchr11135,086,6225,34905,3491 (0.02%)5,348 (99.98%)5,349287 b (0.00%)6.89 Mb (100.00%)6.89 Mb1:23997.500 b896 b896 b0 b1.35 Kb1.35 Kb00.00%0.00 X
hum_testchr12133,275,3095,50805,5083 (0.05%)5,505 (99.95%)5,5082.63 Kb (0.03%)7.59 Mb (99.97%)7.59 Mb1:2888.960 b893 b893 b0 b1.40 Kb1.40 Kb00.00%0.00 X
hum_testchr13114,364,3283,41403,4148 (0.23%)3,406 (99.77%)3,41485.71 Kb (1.80%)4.69 Mb (98.20%)4.77 Mb1:54.670 b900 b900 b0 b1.43 Kb1.43 Kb00.00%0.00 X
hum_testchr14107,043,7183,54103,54112 (0.34%)3,529 (99.66%)3,541244.18 Kb (4.79%)4.86 Mb (95.21%)5.10 Mb1:19.900 b892 b892 b0 b1.42 Kb1.42 Kb00.00%0.00 X
hum_testchr15101,991,1893,03303,0333 (0.10%)3,030 (99.90%)3,0334.29 Kb (0.11%)3.79 Mb (99.89%)3.80 Mb1:883.070 b867 b867 b0 b1.31 Kb1.31 Kb00.00%0.00 X
hum_testchr1690,338,3453,27603,2761 (0.03%)3,275 (99.97%)3,2761.97 Kb (0.04%)4.51 Mb (99.96%)4.51 Mb1:2294.280 b900 b900 b0 b1.41 Kb1.41 Kb00.00%0.00 X
hum_testchr1783,257,4413,37803,37810 (0.30%)3,368 (99.70%)3,37816.81 Kb (0.36%)4.72 Mb (99.64%)4.73 Mb1:280.520 b907 b907 b0 b1.43 Kb1.43 Kb00.00%0.00 X
hum_testchr1880,373,2853,15803,1583 (0.09%)3,155 (99.91%)3,158186.59 Kb (4.06%)4.41 Mb (95.94%)4.59 Mb1:23.610 b899 b899 b0 b1.47 Kb1.47 Kb00.00%0.00 X
hum_testchr1958,617,6162,11002,1100 (0.00%)2,110 (100.00%)2,1100 b (0.00%)2.53 Mb (100.00%)2.53 Mb0:0.000 b857 b857 b0 b1.27 Kb1.27 Kb00.00%0.00 X
hum_testchr2064,444,1673700370370 (100.00%)0 (0.00%)3703.60 Mb (100.00%)0 b (0.00%)3.60 Mb1:0.000 b2.88 Kb2.88 Kb0 b32.28 Kb32.28 Kb1100.00%0.06 X
hum_testchr2146,709,9832650265265 (100.00%)0 (0.00%)2653.06 Mb (100.00%)0 b (0.00%)3.06 Mb1:0.000 b2.63 Kb2.63 Kb0 b33.54 Kb33.54 Kb1100.00%0.07 X
hum_testchr2250,818,4681,74101,74128 (1.61%)1,713 (98.39%)1,741421.99 Kb (14.61%)2.47 Mb (85.39%)2.89 Mb1:5.850 b922 b922 b0 b1.63 Kb1.63 Kb00.00%0.00 X
hum_testchrM16,569190190 (0.00%)19 (100.00%)190 b (0.00%)16.82 Kb (100.00%)16.82 Kb0:0.000 b774 b774 b0 b1.11 Kb1.11 Kb00.00%0.00 X
hum_testchrX156,040,8955,63605,6365 (0.09%)5,631 (99.91%)5,6363.19 Kb (0.04%)7.46 Mb (99.96%)7.46 Mb1:2336.710 b905 b905 b0 b1.38 Kb1.38 Kb00.00%0.00 X
hum_testchrY57,227,41511601164 (3.45%)112 (96.55%)116117.28 Kb (27.65%)306.90 Kb (72.35%)424.19 Kb1:2.620 b989 b989 b0 b28.59 Kb28.59 Kb00.00%0.00 X
hum_testunmapped003,2973,2970 (0.00%)3,297 (100.00%)3,2970 b (0.00%)9.10 Mb (100.00%)9.10 Mb0:0.000 b508 b508 b0 b16.81 Kb16.81 Kb00.00%0.00 X

Common Gotcha's

These may or may not (!) be mistakes we have made already...

  1. If the previous run has not fully completed - i.e is still base-calling or processing raw data,you may connect to the wrong instance and see nothing happening. Always check the previous run has finished completely.
  2. If you have forgotten to remove your simulation line from your sequencing toml you will forever be trapped in an inception like resequencing of old data... Don't do this!
  3. If base-calling doesn't seem to be working check:
    • Check your base-calling server is running.
    • Check the ip of your server is correct.
    • Check the port of your server is correct.
  4. If you are expecting reads to unblock but they do not - check that you have set control=false in your readfish toml file. control=true will prevent any unblocks but does otherwise run the full analysis pipeline.
  5. Oh no - every single read is being unblocked - I have nothing on target!
    • Double check your reference file is in the correct location.
    • Double check your targets exist in that reference file.
    • Double check your targets are correctly formatted with contig name matching the record names in your reference (Exclude description - i.e the contig name up to the first whitespace).

Happy readfish-ing!

Acknowledgements

We're really grateful to lots of people for help and support. Here's a few of them...

From the lab: Teri Evans, Sam Holt, Lewis Gallagher, Chris Alder, Thomas Clarke

From ONT: Stu Reid, Chris Wright, Rosemary Dokos, Chris Seymour, Clive Brown, George Pimm, Jon Pugh

From the Nanopore World: Nick Loman, Josh Quick, John Tyson, Jared Simpson, Ewan Birney, Alexander Senf, Nick Goldman, Miten Jain, Lukas Weilguny

And for our Awesome Logo please checkout out @tim_bassford from @TurbineCreative!

Changelog

2024.3.0

This release is breaking for ALL versions of MinKNOW <= 6 and no longer supports Guppy.

  1. Introducing support for MinKNOW >=6.0.0 and deprecating support for earlier versions.
  2. Removing support for legacy guppy base caller and only supporting Dorado in future.
  3. Optimising batch sending to the base caller through the use of pass_reads rather than pass_read
  4. Adding the new strand classifications as used by MinKNOW, including strand2 and short.

2024.2.0

  1. Add a dorado base-caller which addressed issue #347 - chiefly in Dorado 7.3.9 ONT have moved to ont-pybasecall-client-lib, and connections from ont_pyguppy_client_lib raise Connection error. ... LOAD_CONFIG. Reply: INVALID_PROTOCOL (#344)
  2. Adds version checking for MinKNOW and Guppy/Dorado, logs if not compatibile (#351)

2024.1.0

  1. bug fix type for --wait-on-ready type and actual function (#327), (#323)
  2. mutiple suffix .mmi support (#330)
  3. Change the default unblock_duration on the Analysis class to use DEFAULT_UNBLOCK value defined in _cli_args.py. Change type on the Argparser for --unblock-duration to float. (#313)
  4. Big dog Duplex feature - adds ability to select duplex reads that cover a target region. See pull request for details (#324)

2023.1.1

  1. Fix Readme Logo link 🥳 (#296)
  2. Fix bug where we had accidentally started requiring barcoded TOMLs to specify a region. Thanks to @jamesemery for catching this. (#299)
  3. Correctly handle overriding a decision in internal statistics tracking. (#299)