chiron - Bug fix for better RNA basecall performance

Add the description in the README about the dependent package.

Add tf version Remove unused package

Change the signal normalization to MEAN for better performance.

- Python
Published by haotianteng over 6 years ago

chiron - Faster RNA+DNA model with high accuracy

Release v0.6

Improvement

A new RNA model with overall >85% accuracy.

Obtain >60% successful short RNA reads basecall pass rate when using BoostNano for preprocess. (from <20% successful short RNA reads pass rate of other basecallers).

- Python
Published by haotianteng over 6 years ago

chiron - Bug fix and remake the DNA model.

This is a new version with a faster DNA model(10X faster and same accuracy) and pipeline optimization.

- Python
Published by haotianteng about 7 years ago

chiron - Chiron-v0.5

Update a new RNA model. 10X faster RNA inferencing.

- Python
Published by haotianteng over 7 years ago

chiron - Bug fix and human benchmark result update

Fix a bug that could cause the CTC decoding pipline stuck, replace tqdm module in chironeval.py with a self-written progress bar which is more stable(and almost equally fancy). Improvement of the new model(DNAdefault) on NA12878-WGS(human) benchmark dataset:

SUMMARY

Total reads:6080 Unaligned reads:3303 -> 1553 Deletion rate : 0.0930 -> 0.0847 Insertion rate : 0.0562 -> 0.0538 Mismatch rate : 0.0933 -> 0.0670 Identity rate : 0.8283 -> 0.8483

- Python
Published by haotianteng almost 8 years ago

chiron - tqdm bug fix, and chiron_label added

Remove the tqdm process bar inside the worker, which cause Chiron collapsed. And fix the description of the process bar.

New feature released: chiron_label.py Enable label(re-squiggle) the DNA/RNA reads with a high success rate, label reads can be used to train new Chiron model.

- Python
Published by haotianteng almost 8 years ago

chiron - Chiron-0.4

Enable different model configuration specified by the config Json file. Added a pre-trained RNN model (-200 mV, test version) ~3X faster basecalling when using GPU. Enable cloud training using Google Cloud ML Engine. Enable distributed training process, support multiple GPU training.

- Python
Published by haotianteng about 8 years ago

chiron - Chiron 0.3

New option added --beam Default now using a beam search decoder with a beam width 50, set beam_width to 0 to use the previous greedy decoder. Beam search decoder greatly reduced the deletion rate.

- Python
Published by haotianteng over 8 years ago

chiron - Chiron 0.2

- Python
Published by haotianteng almost 9 years ago

chiron - Chiron 0.1.4

Add fastq output, and provide the quality score output.

- Python
Published by haotianteng almost 9 years ago