Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of medaka

medaka - v2.1.1

Added

  • Python 3.12 support ### Fixed
  • Issue with checking for the presence of dwell information in fastq files. ### Changed
  • Behaviour of medaka_consensus with --bacteria option: if the basecaller model cannot be parsed or is not compatible with the bacterial polishing model, exit with an error instead of falling back to default model.
  • Replaced pkg_resources with importlib ### Removed
  • Python 3.8 support (EOL).

- Python
Published by ontresearch 11 months ago

medaka - v2.1.0

Fixed

  • Updated documentation with inference and sequence command renaming.
  • Changed default model resolved from bam file from variant to consensus.
  • Fixed issue with initializing inference in Medaka tandem model.
  • Fixed a memory leak in the Medaka C library and removed redundant memory objects to reduce the footprint. ### Changed
  • Fully refactored and redesigned medaka tandem code and optimised CPU-based execution.
  • Read-level models cannot be used with medaka tandem.
  • gettrimmedreads now also returns the phase-set, hap and read ids. ### Added
  • Consensus models for v5.2.0 basecaller models.
  • Added support for read-level consensus models for v5.0.0 and v5.2.0 basecaller models.
  • Models dna_r10.4.1_e8.2_5khz_400bps_sup and dna_r10.4.1_e8.2_5khz_400bps_hac added as aliases to those without _5kz_ in their names.
  • Added -B option to medaka_consensus to allow passing a bed file or region to polish via medaka inference --regions.
  • Added --cpu option to medaka inference to force CPU and avoid searching for GPUs.
  • New output format for medaka tandem tailored for population studies.
  • New fields to medaka tandem output: depth, read lengths, read names, phase sets, and MAD of read lengths.
  • Read length–based outlier detection in medaka tandem.

- Python
Published by ontresearch about 1 year ago

medaka - v2.0.1

Fixed

  • medaka smolecule was broken by change from medaka consensus to medaka inference. ### Changed
  • Improved error message when model is not found.

- Python
Published by ontresearch almost 2 years ago

medaka - v2.0.0

Switched from tensorflow to pytorch.

Existing models for recent basecallers have been converted to the new format. Pytorch format models contain a _pt suffix in the filename.

Changed

  • Inference is now performed using PyTorch instead of TensorFlow.
  • The medaka consensus command has been renamed to medaka inference to reflect its function in running an arbitrary model and avoid confusion with medaka_consensus.
  • The medaka stitch command has been renamed to medaka sequence to reflect its function in creating a consensus sequence.
  • The medaka variant command has been renamed to medaka vcf to reflect its function in consolidating variants and avoid confusion with medaka_variant.
  • Order of arguments to medaka vcf has been changed to be more consistent with medaka sequence.
  • The helper script medaka_haploid_variant has been renamed medaka_variant to save typing.
  • Make --ignore_read_groups option available to more medaka subcommands including inference. ### Removed
  • The medaka snp command has been removed. This was long defunct as diploid SNP calling had been deprecated, and medaka variant is used to create VCFs for current models.
  • Loading models in hdf format has been deprecated.
  • Deleted minimap2 and racon wrappers in medaka/wrapper.py. ### Added
  • Release conda packages for Linux (x86 and aarch64) and macOS (arm64).
  • Option --lr_schedule allows using cosine learning rate schedule in training.
  • Option --max_valid_samples to set number of samples in a training validation batch. ### Fixed
  • Training models with DiploidLabelScheme uses categorical cross-entropy loss instead of binary cross-entropy.

- Python
Published by ontresearch almost 2 years ago

medaka - v1.12.1

(Probably) final version of medaka using tensorflow. Future versions will use pytorch instead.

Fixed

  • medaka_consensus: only keep bam tags if input file matches joint polishing pipeline.
  • Pin numpy to <2.0.0. ### Added
  • Consensus and variant models lookup for v3.5.1 Dorado models.

- Python
Published by ontresearch about 2 years ago

medaka - v1.12.0

Fixed

  • tandem: Use haplotag 0 in unphased mode.
  • tandem: Don't run consensus if regions set is empty. ### Added
  • Models for version 5 basecaller models.
  • Expose sym_indels option for training.
  • Expose --min_mapq minimum mapping quality alignment fitering option for medaka consensus.
  • tandem: Option --ignore_read_groups to ignore read groups present in input file.
  • Wrapper script medaka_consensus_joint and convenience tools (prepare_tagged_bam, get_model_dtypes) to facilitate joint polishing with multiple datatypes.

- Python
Published by ontresearch about 2 years ago

medaka - v1.11.3

Added

  • Consensus and variant models for v4.3.0 dorado models.

- Python
Published by ontresearch over 2 years ago

medaka - v1.11.2

Added

  • Parsing model information from fastq headers output by Guppy and MinKNOW. ### Changed
  • Additional explanatory information in VCF INFO fields concerning depth calculations.

- Python
Published by ontresearch over 2 years ago

medaka - v1.11.1

Fixed

  • Do not exit if model cannot be interpreted, use the default instead.
  • An issue with co-ordinate handling in computing variants from alignments. ### Added
  • Ability to use basecaller model name as --model argument.
  • Better handling or errors when running abpoa.

- Python
Published by ontresearch over 2 years ago

medaka - v1.11.0

Fixed

  • Correct suffix of consensus file when medaka_consensus outputs a fastq. ### Added
  • Choice of model file can be introspected from input files. For BAM files the read group (RG) headers are searched according to the dorado specification, whilst for .fastq files the comment section of a number of reads are checked for corresponding read group information. In the latter case see README for information on correctly converting basecaller output to .fastq whilst maintaining the relevant meta information.
  • medaka tools resolve_model can display the model that would automatically be used for a given input file. ### Changed
  • If no model is provided on command-line interface (medaka consensus, medakaconsensus, and medakahaploid_variant) automatic attempts will be made to choose the appropriate model.

- Python
Published by ontresearch over 2 years ago

medaka - v1.10.0

Changed

  • Tensorflow logging level no longer set from Python.
  • spoa and parasail are now strict requirements. ### Fixed
  • Sort VCF before annotating in medaka_haploid_variant.
  • Ignore errors when deleting temporary files.
  • The output of the first POA run not being used in the second iteration in smolecule command. ### Added
  • Support for Python 3.11.
  • --spoa_min_coverage option to smolecule command. ### Removed
  • Support for Python 3.7.

- Python
Published by ontresearch over 2 years ago

medaka - v1.9.1

Fixed

  • A long-standing bug in pileup_counts that manifests for single-position pileups on ARM64.

- Python
Published by ontresearch almost 3 years ago

medaka - v1.9.0

Added

  • Added medaka tandem targeted tandem repeat variant calling.

- Python
Published by ontresearch almost 3 years ago

medaka - v1.8.2

Added

  • Updated features related to fetching of trimmed reads. ### Changed
  • Refactored smolecule module.
  • Faster inference and stitching of many short contigs.
  • Tensorflow version 2.10 (allows for aarch64 wheels).

- Python
Published by ontresearch almost 3 years ago

medaka - v1.8.1

Added

  • Expose qualities parameter in medaka_consensus script with -q parameter.

- Python
Published by ontresearch about 3 years ago

medaka - v1.8.0

Added

  • Consensus and variant models for v4.1 and v4.2 basecallers. ### Changed
  • Changed default models to be r1041e8.2400bps_v4.2 models
  • Clip probabilities in _phred() rather than adding smallest float.

- Python
Published by ontresearch about 3 years ago

medaka - v1.7.3

Added

  • Consensus polishing models for Version 4 basecallers.
  • Wheel builds for newer Python versions. ### Fixed
  • Deprecated numpy.unicode use. ### Changed
  • Set minimum Python version to 3.7.
  • Updated tensorflow requirement to 2.8.
  • Put lower bound on numpy requirement. ### Removed
  • Dropped support for Python 3.6. Security support for Python 3.6 was ended on 23 Dec 2021; as such we have removed support for Python 3.6 and suggest users update their Python version.

- Python
Published by ontresearch over 3 years ago

medaka - v1.7.2

Added

  • New models for R10.4.1 E8.2 260bps based sequencing chemistries. ### Changed
  • Updated Hac and Fast models for R10.4.1 E8.2 400bps based sequencing chemistries.
  • Removed models for Fast basecallers from pypi package

- Python
Published by ontresearch almost 4 years ago

medaka - v1.7.1

Fixed

  • medaka variant IndexError on long insertion

- Python
Published by ontresearch almost 4 years ago

medaka - v1.7.0

Added

  • capability to fill gaps in consensus sequence with a designated character (e.g. 'N') instead of content from a reference sequence.
  • option -r in medaka_consensus to set the designated fill character.
  • option --fill_char in medaka stitch to set the designated fill character. ### Fixed
  • CUDA initialization errors during medaka smolecules stitch phase.

- Python
Published by ontresearch almost 4 years ago

medaka - v1.6.1

Added

  • New models for R10.4.1 E8.2 400bps based sequencing chemistries.

Fixed

  • DiploidZygosityLabelScheme renaming.

- Python
Published by ontresearch about 4 years ago

medaka - v1.6.0

Changed

  • Updated to tensorflow~=2.7.0.
  • Do not always force recreation of minimap2 index in helper scripts.
  • PyPI wheel releases now built with libdeflate for faster BAM reading. ### Fixed
  • Inclusion of inserted bases immediately after deletion in pileup counts. ### Added
  • Makefile can now build environment for macOS M1.
  • Publish ARMv8 wheels compatible with NVIDIA's Jetpack 4.6.1 binary.
  • --qualities option for smolecule and stitch to output consensus fastq.

- Python
Published by ontresearch over 4 years ago

medaka - v1.5.0

Changed

  • Updated tensorflow requirement to ~=2.5.2.
  • Spruced-up documentation. ### Added
  • Light testing of Docker build. ### Removed
  • Remove medaka_variant in deference of clair3.

- Python
Published by ontresearch over 4 years ago

medaka - v1.4.4

Changed

  • tensorflow requirement to ~=2.2.2 ### Added
  • R10.4 E8.1 consensus models for Guppy version 5.0.15.

- Python
Published by ontresearch almost 5 years ago

medaka - v1.4.3

Fixed

  • medaka tools now displays its help rather than an error. ### Added
  • `medaka tools download_models can download specific models.

- Python
Published by ontresearch about 5 years ago

medaka - v1.4.2

Fixed

  • Missing sites in gVCF output. ### Changed
  • Rewrittern algorithm for determining VCF records from RNN outputs for clarity and speed.

- Python
Published by ontresearch about 5 years ago

medaka - v1.4.1

Fixed

  • Inclusion of select models in distributions.

- Python
Published by ontresearch about 5 years ago

medaka - v1.4.0

Added

  • Models for Guppy version 5.0.7.

- Python
Published by ontresearch about 5 years ago

medaka - v1.3.4

Fixed

  • Issue whereby tensorflow would spawn many threads that do not exit.

- Python
Published by ontresearch about 5 years ago

medaka - v1.3.3

Fixed

  • Added missing default option to arparse instance in smolecule command.
  • Copy across contigs with no aligned reads during medaka stitch.
  • Quote strings in bash scripts to allow filenames with spaces.

- Python
Published by ontresearch about 5 years ago

medaka - v1.3.2

Fixed

  • Typo in medaka_consensus causing a syntax error.

- Python
Published by ontresearch over 5 years ago

medaka - v1.3.1

Added

  • Option to output VCF record for all reference positions from medaka variant.

- Python
Published by ontresearch over 5 years ago

medaka - v1.3.0

Changed

  • Haploid variant calling reverted to old-style methodology. ### Fixed
  • Early exits on error in medaka_consensus and medaka_variant.
  • INFO field of VCFs is now correctly . when empty.

- Python
Published by ontresearch over 5 years ago

medaka - v1.2.6

Changed

  • Rewrote inference data loading code for clarity.
  • Removed pinned BioPython pin.
  • Formally update htslib program requirements to 1.11. ### Removed
  • Support for Python 3.5. ### Fixed
  • Corner case in consensus stitching.

- Python
Published by ontresearch over 5 years ago

medaka - v1.2.3

Fixed

  • Off-by-one error during stitching of consensus chunks.

- Python
Published by ontresearch over 5 years ago

medaka - v1.2.2

Minor release

Fixed

  • Fixed incorrect read depth annotations in VCFs.
  • Fixed missing files in PyPI source distribution.
  • Fix StopIteration issues in newer Pythons. ## Added
  • Added -n option to medaka_variant to add a sample field to outputs.
  • Set HDF5_USE_FILE_LOCKING=FALSE, which some users report as useful.
  • Set OMP_NUM_THREADS=1 required to make Tensorflow anaconda use CPU resource sensibly.

- Python
Published by ontresearch over 5 years ago

medaka - v1.2.0

Performance release

  • Improve inference performance by 30%.
  • Add efficient multiprocessing to medaka stitch.
  • Fix long-standing issue where genome regions could be unprocessed.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 over 5 years ago

medaka - v1.1.3

Bugfix release

  • Work around tensorflow threading issue.
  • Fix iteration error in retrieving trimmed reads.
  • Add ability to haploid2diploid tool on VCFs generated by medaka_haploid_variant

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 over 5 years ago

medaka - v1.1.2

Bug fix and feature release

  • Fix issues in command-line argument parsing.
  • Add true ploidy-1 variant caller.
  • Do not break contigs at unpolished regions (fill with input instead).
  • Add multi-nucleotide variant decomposition to be compatible with DeepVariant.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 almost 6 years ago

medaka - v1.1.1

Bux fix release.

  • Remove pythong version check preventing Python >3.6 builds from running

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 almost 6 years ago

medaka - v1.1.0

Update with new models and features.

  • Upgrade to Tensorflow 2.2.
  • Add ARM builds to PyPI release.
  • Add Python 3.7 and 3.8 builds for x86-64.
  • Add PromethION model for Guppy 4.0.11.
  • Option to split MNPs to independent SNPs (for compatibility with DeepVariant).
  • Fix a few bugs in variant annotation program.
  • Single molecule consensus program now uses pyspoa.
  • Remove methylation aggregation functionality.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 almost 6 years ago

medaka - v1.0.3

v1.0.3

Minor fixes release.

  • Fix occasional mangled sam output in guppy2sam.
  • Update htslib ecosystem to 1.10 to fix conda installation issue.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by mwykes about 6 years ago

medaka - v1.0.2

Minor fixes and models release.

  • R9.4.1 variant calling models for Guppy 3.6.0 and updated benchmarks.
  • Made r941minhigh_g360 the default consensus model.
  • VCF GQ is now an integer in line with VCF spec.
  • Fixed issue requiring a previous model for training.
  • Fixed issue causing -p option of medaka_variant to crash.
  • Fixed issue preventing installation in a virtualenv with python <3.6.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by mwykes about 6 years ago

medaka - v1.0.1

Minor fixes release, resolving issues introduced in v1.0.0.

  • Fix default model for SNP calling.
  • Fix issue causing medaka_consensus to crash.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by mwykes about 6 years ago

medaka - v1.0.0

Models, features and fixes release

  • Consensus models for Guppy 3.6.0.
  • Add functionality for auto-download of older models.
  • Fix to methylation aggregation.
  • VCF annotation tool.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by mwykes about 6 years ago

medaka - v0.12.1

Minor release harmonising versions of htslib/samtools dependencies.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by mwykes over 6 years ago

medaka - v0.12.0

Models, features and fixes release

  • Variant calling models for R10.3 and R9.4.1 and updated benchmarks.
  • Consensus models for Guppy 3.5.1.
  • Add read group (RG) tag filtering.
  • Add option to create consensus sequence via intermediate .vcf file.
  • Update to methylation calling documentation.
  • Addition of all-context modified-base aggregation.
  • Minor speed improvement.
  • Fix bug where force overwrite of output was always enabled.
  • Fix bug where variant calling of a region crashed if the region began with a deletion.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by mwykes over 6 years ago

medaka - v0.11.5

R10.3 model and small fixes

  • Add model for R10.3 on MinION.
  • Fix index/compression issue with RLE workflow
  • Write an empty vcf when no variants are found in medaka_variant.
  • Fix a rare memory error during feature generation caused by very long indels.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 over 6 years ago

medaka - v0.11.4

Bugfix

  • Fix invalid specification of variant calling model.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by javierblasco over 6 years ago

medaka - v0.11.3

Model release

  • Models for guppy 3.4.4.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by javierblasco over 6 years ago

medaka - v0.11.2

Minor fix release

  • Fix a memory error in pileup calculation.
  • Update variant calling models (improved indel performance) and benchmarks.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 over 6 years ago

medaka - v0.11.1

Minor Release

  • Preliminary hard-RLE model for R9.4.1
  • --regions argument can now be a .bed file.
  • Detect NaNs during training and halt early.
  • Workaround pysam interface changes (for conda package).
  • Support soft-RLE network training.

This release includes an experimental consensus mode using run-length encoded alignments. Use of this algorithm can be specified using the new "rle" model:

medaka_consensus -m r941_min_high_g340_rle -i basecalls.fasta -d draft.fa

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 over 6 years ago

medaka - v0.11.0

Feature release

  • Consensus models for guppy 3.3 and 3.4.
  • Aggregation of Guppy modified base probability tables.
  • Multi-thread stitching of inference chunks in medaka_consensus.
  • Optionally run whatshap phase at the end of medaka_variant.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 over 6 years ago

medaka - v0.10.1

Minor fix release

  • Fix bug where feature matrix was misaligned with coordinate system.
  • Add missing arguments from smolecule command.
  • Output contig names are no longer written as samtools-style regions.
  • Fixed issue with medaka_variant failing on zero-coverage regions.
  • Rename incorrectly named diploid SNP calling model.
  • Made variant calling faster by resolving trivial bottleneck in variant classification.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 over 6 years ago

medaka - v0.10.0

Feature release

  • Switched variant calling to an explicitly diploid calling model.
  • Added a -f force overwrite option to medaka_consenses.
  • Refreshed E. coli benchmark to include effect of racon.
  • Refreshed variant calling benchmarks.
  • Added C. elegans assembly benchmarks to documentation.
  • Fixed bug causing larger than requested overlap in inference chunks.
  • Corrected parsing of region strings with multiple : charaters
  • Fixed rare consensus stitching error.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 almost 7 years ago

medaka - v0.9.2

Minor fix release.

  • Additional fix to handling lowercase reference sequences.
  • Fix bug in creation of RLE alignments.
  • Update update_model.py script.
  • Remove option to select labelling scheme during training.
  • Unify how LabelSchemes store training data.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 almost 7 years ago

medaka - v0.9.1

Minor fix release

  • Fix regression in medaka stitch and medaka snp speed.
  • Handle lowercase letters in reference sequences.
  • Remove dill and yaml requirements.

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 almost 7 years ago

medaka - v0.9.0

Bugfix and training refactor release

  • Fix readlink issue on MacOS
  • Fix bug where medaka_variant did not call indels by default
  • Fix bug in determining when to split contigs
  • Drop support for older basecaller models (guppy<3.0.3)
  • Store models in git-lfs
  • Simplify medaka_variant workflow for speed
  • Make network feature generation 2x faster
  • Add smolecule command
  • Log use of GPU and cuDNN, noting workaround for RTX cards
  • Refactor labelling of training data and storing of models
  • Reimplement RLE feature generation

Please do not attempt to use the "Source code" assets attached below for running medaka, they do not include medaka's model files.

- Python
Published by cjw85 almost 7 years ago

medaka - v0.8.2

Documentation release

  • Clarify suggested workflows in documentation.

- Python
Published by cjw85 almost 7 years ago

medaka - v0.8.1

Patch release

  • Patch import of loading of older models

- Python
Published by cjw85 almost 7 years ago

medaka - v0.8.0

v0.8.0

Model release

  • Add support for R10 basecaller
  • Add support for diploid multi-labelling models
  • Upgrade to tensorflow 1.14.0

Note: pypi binaries for the updated tensorflow are linked to CUDA10, previous medaka releases used a tensorflow version that was linked to CUDA9. This only affects users who run medaka on GPU hardware.

- Python
Published by javierblasco about 7 years ago

medaka - v0.7.1

Bug fix release

  • Fix regression in consensus stitching when chunks do not overlap

- Python
Published by cjw85 about 7 years ago

medaka - v0.7.0

Feature release

  • Indel calling for medaka_variant.
  • New models for MinION/GridION and PromethION paired to high accuracy an fast guppy basecallers.
  • Overhaul of chunk handling and overlapping.

- Python
Published by cjw85 about 7 years ago

medaka - v0.6.5

Bug fix release

  • Tidy up some parsing and sorting of regions from strings.
  • Disable by default validation of output HDF during consensus.
  • Refactor variant handling code.
  • Ensure medaka consensus is given absolute path to model.
  • Fix Makefile for parallel build.

- Python
Published by cjw85 about 7 years ago

medaka - v0.6.4

Bug fix

  • Fix for models not specifiying data types.

- Python
Published by mwykes over 7 years ago

medaka - v0.6.3

Bug fix release

  • Split pileup when reads do not span rather than silently deleting region.
  • Refactor handling of short and remainder regions.
  • Drop 3.4 support.
  • Fix error in stitching occuring with a single region.

- Python
Published by cjw85 over 7 years ago

medaka - v0.6.2

Bug fix release

  • Enhanced verification of training feature samples
  • Pin pyyaml version

- Python
Published by cjw85 over 7 years ago

medaka - v0.6.1

Bug fix release

  • Fixed bug in medaka_consensus and medaka_variant incorrectly calling python

- Python
Published by cjw85 over 7 years ago

medaka - v0.6.0

SNP calling, model, and bugfix release release

  • Prototype SNP calling and phasing, benchmarks
  • Add model for improved Flip-flop model in Guppy 2.3.5
  • Rename models to be more logical
  • Update to htslib version 1.9 for long cigars
  • Workaround short-contig/no-coverage corner case during pileup.

- Python
Published by cjw85 over 7 years ago

medaka - v0.6.0-alpha.3

Variant calling pre-release

  • added medaka_variant pipeline for diploid variant calling
  • add whatshap 0.18 dependency
  • update to htslib v1.9, handling long cigar strings. (#26)

- Python
Published by cjw85 over 7 years ago

medaka - v0.6.0-alpha.2

Variant calling pre-release

  • added medaka_variant pipeline for diploid variant calling
  • add whatshap 0.18 dependency

- Python
Published by cjw85 over 7 years ago

medaka - v0.6.0-alpha.1

Variant calling pre-release

  • added medaka_variant pipeline for diploid variant calling

- Python
Published by cjw85 over 7 years ago

medaka - v0.5.2

Bug fix release

  • Fix bug leading to dropping of pileup chunks during loading

- Python
Published by cjw85 over 7 years ago

medaka - v0.5.1

Development and performance release

  • Refactor batch queuing in preparation to using keras Sequence
  • Asynchrounous feature loading during inference
  • Pin version of h5py to work around intermittent errors in saving models

- Python
Published by cjw85 over 7 years ago

medaka - v0.5.0

  • Large refactor of training code
    • Resolve hanging at the end of training #15
    • Switch to CuDNN for GRU layers
    • Improved storage and retrieval of features for better IO
    • Training speed improved >10X
  • Resolve issue with contained chunks during stitching #20
  • Changes to medaka_consensus
    • checks presence of minimap2 and samtools
    • provides more feedback on error #16

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.3

  • Add support for R9.4.1 flip-flop basecaller

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.1

Development release * Adds build infrastructure for source distributions and manylinux wheels.

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.0

  • Large refactoring of feature and sample generation (https://github.com/nanoporetech/medaka/issues/10) Fixes many small bugs and edge cases
  • Resize models for small contigs (https://github.com/nanoporetech/medaka/issues/9)
  • Faster Generation of inference features
  • Model updates
  • Remove redundant samtools tview code
  • Ability to handle multiple read types
  • Limit CPU usage when running without a GPU

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.0 Release Candidate 4

  • Fix bug in medaka stitch when --region is specified.

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.0 Release Candidate 5

  • Accelerate multi-datatype pileup creation.
  • Fix some bugs in training.

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.0 Release Candidate 3

  • Large refactoring of feature and sample generation
  • Resize models for small contigs

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.0 Release Candidate 2

  • Fix import error after switching to local imports of keras/tensorflow

- Python
Published by cjw85 over 7 years ago

medaka - v0.4.0 Release Candidate 1

  • Faster Generation of inference features
  • Remove redundant samtools tview code
  • Ability to handle multiple read types

- Python
Published by cjw85 over 7 years ago

medaka - v0.3.0

  • New non-RLE model
  • Updated documentation and benchmarks
  • Bug fixes
  • medaka_consensus no longer needs a pomoxis installation to run
  • Dockerfile to build a medaka Docker image

- Python
Published by mwykes almost 8 years ago

medaka - v0.2.0

  • Release with pre-trained model.
  • Updated walkthrough and benchmarks.

- Python
Published by cjw85 over 8 years ago

medaka - v0.1.0

  • Overhaul API
  • Add walkthrough

- Python
Published by cjw85 over 8 years ago

medaka - v0.0.2

  • Generate pileup using samtools tview.
  • Updated default model architecture.
  • Extensive package restructuring.
  • New features.py with two example feature functions, making it easier for developers to experiment with their own features.

- Python
Published by mwykes almost 9 years ago

medaka - v0.0.1

First prerelease. Simple consensus network using pileup counts.

- Python
Published by cjw85 almost 9 years ago