SURE-tools 2.1.58__tar.gz → 2.1.59__tar.gz

{sure_tools-2.1.58 → sure_tools-2.1.59}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SURE-tools
-Version: 2.1.58
+Version: 2.1.59
 Summary: Succinct Representation of Single Cells
 Home-page: https://github.com/ZengFLab/SURE
 Author: Feng Zeng

{sure_tools-2.1.58 → sure_tools-2.1.59}/SURE/PerturbFlow.py

@@ -62,7 +62,7 @@ class PerturbFlow(nn.Module):
                  supervised_mode: bool = False,
                  z_dim: int = 10,
                  z_dist: Literal['normal','studentt','laplacian','cauchy','gumbel'] = 'normal',
-                 loss_func: Literal['negbinomial','poisson','multinomial','bernoulli'] = 'negbinomial',
+                 loss_func: Literal['negbinomial','poisson','multinomial','bernoulli'] = 'multinomial',
                  inverse_dispersion: float = 10.0,
                  use_zeroinflate: bool = False,
                  hidden_layers: list = [300],
@@ -317,8 +317,6 @@ class PerturbFlow(nn.Module):
         if self.loss_func=='negbinomial':
             total_count = pyro.param("inverse_dispersion", self.inverse_dispersion *
                                      xs.new_ones(self.input_size), constraint=constraints.positive)
-        elif self.loss_func == 'multinomial':
-            total_count = pyro.param('total_count', int(1e8), constraint=constraints.positive_integer)
             
         if self.use_zeroinflate:
             gate_logits = pyro.param("dropout_rate", xs.new_zeros(self.input_size))
@@ -357,8 +355,9 @@ class PerturbFlow(nn.Module):
                 log_theta = concentrate
             else:
                 rate = concentrate.exp()
-                if self.loss_func != 'poisson':
-                    theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                if self.loss_func == 'poisson':
+                    rate = theta * torch.sum(xs, dim=1, keepdim=True)
 
             if self.loss_func == 'negbinomial':
                 if self.use_zeroinflate:
@@ -371,7 +370,7 @@ class PerturbFlow(nn.Module):
                 else:
                     pyro.sample('x', dist.Poisson(rate=rate).to_event(1), obs=xs.round())
             elif self.loss_func == 'multinomial':
-                pyro.sample('x', dist.Multinomial(total_count=total_count, probs=theta), obs=xs)
+                pyro.sample('x', dist.Multinomial(total_count=int(1e8), probs=theta), obs=xs)
             elif self.loss_func == 'bernoulli':
                 if self.use_zeroinflate:
                     pyro.sample('x', dist.ZeroInflatedDistribution(dist.Bernoulli(logits=log_theta),gate_logits=gate_logits).to_event(1), obs=xs)
@@ -397,8 +396,6 @@ class PerturbFlow(nn.Module):
         if self.loss_func=='negbinomial':
             total_count = pyro.param("inverse_dispersion", self.inverse_dispersion *
                                      xs.new_ones(self.input_size), constraint=constraints.positive)
-        elif self.loss_func == 'multinomial':
-            total_count = pyro.param('total_count', int(1e8), constraint=constraints.positive_integer)
             
         if self.use_zeroinflate:
             gate_logits = pyro.param("dropout_rate", xs.new_zeros(self.input_size))
@@ -432,12 +429,6 @@ class PerturbFlow(nn.Module):
                 zns = pyro.sample('zn', dist.Gumbel(zn_loc, zn_scale).to_event(1))
 
             if self.cell_factor_size>0:
-                #zus = None
-                #for i in np.arange(self.cell_factor_size):
-                #    if i==0:
-                #        zus = self.cell_factor_effect[i]([zns,us[:,i].reshape(-1,1)])
-                #    else:
-                #        zus = zus + self.cell_factor_effect[i]([zns,us[:,i].reshape(-1,1)])
                 zus = self._total_effects(zns, us)
                 zs = zns+zus
             else:
@@ -448,8 +439,9 @@ class PerturbFlow(nn.Module):
                 log_theta = concentrate
             else:
                 rate = concentrate.exp()
-                if self.loss_func != 'poisson':
-                    theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                if self.loss_func == 'poisson':
+                    rate = theta * torch.sum(xs, dim=1, keepdim=True)
 
             if self.loss_func == 'negbinomial':
                 if self.use_zeroinflate:
@@ -462,7 +454,7 @@ class PerturbFlow(nn.Module):
                 else:
                     pyro.sample('x', dist.Poisson(rate=rate).to_event(1), obs=xs.round())
             elif self.loss_func == 'multinomial':
-                pyro.sample('x', dist.Multinomial(total_count=total_count, probs=theta), obs=xs)
+                pyro.sample('x', dist.Multinomial(total_count=int(1e8), probs=theta), obs=xs)
             elif self.loss_func == 'bernoulli':
                 if self.use_zeroinflate:
                     pyro.sample('x', dist.ZeroInflatedDistribution(dist.Bernoulli(logits=log_theta),gate_logits=gate_logits).to_event(1), obs=xs)
@@ -488,8 +480,6 @@ class PerturbFlow(nn.Module):
         if self.loss_func=='negbinomial':
             total_count = pyro.param("inverse_dispersion", self.inverse_dispersion *
                                      xs.new_ones(self.input_size), constraint=constraints.positive)
-        elif self.loss_func == 'multinomial':
-            total_count = pyro.param('total_count', int(1e8), constraint=constraints.positive_integer)
             
         if self.use_zeroinflate:
             gate_logits = pyro.param("dropout_rate", xs.new_zeros(self.input_size))
@@ -545,8 +535,9 @@ class PerturbFlow(nn.Module):
                 log_theta = concentrate
             else:
                 rate = concentrate.exp()
-                if self.loss_func != 'poisson':
-                    theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                if self.loss_func == 'poisson':
+                    rate = theta * torch.sum(xs, dim=1, keepdim=True)
 
             if self.loss_func == 'negbinomial':
                 if self.use_zeroinflate:
@@ -559,7 +550,7 @@ class PerturbFlow(nn.Module):
                 else:
                     pyro.sample('x', dist.Poisson(rate=rate).to_event(1), obs=xs.round())
             elif self.loss_func == 'multinomial':
-                pyro.sample('x', dist.Multinomial(total_count=total_count, probs=theta), obs=xs)
+                pyro.sample('x', dist.Multinomial(total_count=int(1e8), probs=theta), obs=xs)
             elif self.loss_func == 'bernoulli':
                 if self.use_zeroinflate:
                     pyro.sample('x', dist.ZeroInflatedDistribution(dist.Bernoulli(logits=log_theta),gate_logits=gate_logits).to_event(1), obs=xs)
@@ -585,8 +576,6 @@ class PerturbFlow(nn.Module):
         if self.loss_func=='negbinomial':
             total_count = pyro.param("inverse_dispersion", self.inverse_dispersion *
                                      xs.new_ones(self.input_size), constraint=constraints.positive)
-        elif self.loss_func == 'multinomial':
-            total_count = pyro.param('total_count', int(1e8), constraint=constraints.positive_integer)
             
         if self.use_zeroinflate:
             gate_logits = pyro.param("dropout_rate", xs.new_zeros(self.input_size))
@@ -652,8 +641,9 @@ class PerturbFlow(nn.Module):
                 log_theta = concentrate
             else:
                 rate = concentrate.exp()
-                if self.loss_func != 'poisson':
-                    theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+                if self.loss_func == 'poisson':
+                    rate = theta * torch.sum(xs, dim=1, keepdim=True)
 
             if self.loss_func == 'negbinomial':
                 if self.use_zeroinflate:
@@ -666,7 +656,7 @@ class PerturbFlow(nn.Module):
                 else:
                     pyro.sample('x', dist.Poisson(rate=rate).to_event(1), obs=xs.round())
             elif self.loss_func == 'multinomial':
-                pyro.sample('x', dist.Multinomial(total_count=total_count, probs=theta), obs=xs)
+                pyro.sample('x', dist.Multinomial(total_count=int(1e8), probs=theta), obs=xs)
             elif self.loss_func == 'bernoulli':
                 if self.use_zeroinflate:
                     pyro.sample('x', dist.ZeroInflatedDistribution(dist.Bernoulli(logits=log_theta),gate_logits=gate_logits).to_event(1), obs=xs)
@@ -895,6 +885,8 @@ class PerturbFlow(nn.Module):
             counts = dist.NegativeBinomial(total_count=total_count, logits=concentrate).to_event(1).mean
         elif self.loss_func == 'poisson':
             rate = concentrate.exp()
+            theta = dist.DirichletMultinomial(total_count=1, concentration=rate).mean
+            rate = theta * library_size
             counts = dist.Poisson(rate=rate).to_event(1).mean
         elif self.loss_func == 'multinomial':
             rate = concentrate.exp()
@@ -919,7 +911,7 @@ class PerturbFlow(nn.Module):
         zs = convert_to_tensor(zs, device=self.get_device())
         ls = zs 
         
-        if self.loss_func == 'multinomial':
+        if self.loss_func in ['multinomial','poisson']:
             assert library_sizes!=None, 'Library sizes are required for multinomial!'
             
             if type(library_sizes) == list:

{sure_tools-2.1.58 → sure_tools-2.1.59}/SURE_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: SURE-tools
-Version: 2.1.58
+Version: 2.1.59
 Summary: Succinct Representation of Single Cells
 Home-page: https://github.com/ZengFLab/SURE
 Author: Feng Zeng

{sure_tools-2.1.58 → sure_tools-2.1.59}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:
 
 setup(
     name='SURE-tools',
-    version='2.1.58',
+    version='2.1.59',
     description='Succinct Representation of Single Cells',
     long_description=long_description,
     long_description_content_type="text/markdown",