v1.2.0: robustness improve on the LoRa finetuning

Multiple bug fixes:

• the error where seq2print_tfbs might ended up using only the last model, instead of averaging over five folds

Multiple improvement:

• support custom region names, if there is a column "region_names" in the region provided, those would be used to name results instead of the standard chr1:0-10000 etc.
• better verbose
• chromvar also chunk over TF axis for larger datasets
• More robust LoRA training with better coverage warming stages

v1.1.2

Add support for custom genome (seq2PRINT & create bias bigwig for custom genome)
this release also replaces the Tn5 bias model and dispersion mode used in the paper l with a newer version. See tutorials for more details: https://ruochiz.com/scprinter_doc/tutorials/custom_genome_tutorial.html

Full Changelog: v1.1.0...v1.1.2