accept list of string representations of genetic sequence

Author: lucidrains

README.md

@@ -24,7 +24,7 @@ model = Enformer(
     target_length = 896,
 )
 
-seq = torch.randint(0, 5, (1, 196_608)) # for ACGTN, in that order
+seq = torch.randint(0, 5, (1, 196_608)) # for ACGTN, in that order (-1 for padding)
 output = model(seq)
 
 output['human'] # (1, 896, 5313)

enformer_pytorch/enformer_pytorch.py

@@ -413,6 +413,9 @@ def forward(
         return_only_embeddings = False,
         head = None
     ):
+        if isinstance(x, list):
+            x = str_to_seq_indices(x)
+
         dtype = x.dtype
 
         if x.dtype == torch.long:

setup.py

@@ -4,7 +4,7 @@
   name = 'enformer-pytorch',
   packages = find_packages(exclude=[]),
   include_package_data = True,
-  version = '0.1.28',
+  version = '0.1.29',
   license='MIT',
   description = 'Enformer - Pytorch',
   author = 'Phil Wang',