v1.4a

• add a function, which could use enhancer annotation.
• avoid overflow of float16

v1.31

• add run_visualize subcommand to visualize results.
• correct some typos.

v1.3

• optimize the latent to gene mem usage
• add --no_expression_fraction option

v1.2

Improve:

1. Reduce the Spatial LDSC Step RAM Usage
2. Speed up the Latent to Gene Step
3. Use Sparse Matrix For generate LD score
4. Some Bug fixed