Josh Meehl

Same here!

Maybe one could hack a training file with a bunch of neutral mutations ``` mutation score M1M 1.0 F12F;L30L 1.0 G89G 1.0 ```

Looks like it worked. Tested with separate test file with random mutations. Need to still validate with experimental data. Prediction from Training File with neutral mutations: > mutation score prediction...

Ignore my previous naive attempt. I re-read the paper and recalled @luoyunan used homologous sequences to train a bidirectional model on masked amino acid residues. I reviewed the ECNet and...