Merge pull request #24 from jrm5100/master

Version 0.6.1

docs/release-history.rst

@@ -2,6 +2,11 @@
 Release History
 ===============
 
+v0.6.1 (2021-06-26)
+-------------------
+
+Specify only alternate allele frequencies when generating random genotypes, to avoid float rounding problems
+
 v0.6.0 (2021-06-25)
 -------------------
 

pandas_genomics/sim/random_gt.py

@@ -1,4 +1,4 @@
-from typing import List
+from typing import List, Union
 
 import numpy as np
 
@@ -7,16 +7,19 @@
 
 
 def generate_random_gt(
-    variant: Variant, allele_freq: List[float], n: int = 1000, random_seed: int = 1855
+    variant: Variant,
+    alt_allele_freq: Union[List[float], float],
+    n: int = 1000,
+    random_seed: int = 1855,
 ) -> GenotypeArray:
     """
     Simulate random genotypes according to the provided allele frequencies
 
     Parameters
     ----------
     variant: Variant
-    allele_freq: List[float]
-      Allele frequencies for each allele in the variant
+    alt_allele_freq: float or List[float]
+      Allele frequencies for each alternate allele in the variant (Bialleleic variants may specify a single float value)
     n: int, default 1000
         How many genotypes to simulate
     random_seed: int, default 1855
@@ -27,16 +30,26 @@ def generate_random_gt(
 
     """
     # Validate frequencies
-    if len(allele_freq) != len(variant.alleles):
+    if isinstance(alt_allele_freq, float):
+        # Convert it into a list
+        alt_allele_freq = [
+            alt_allele_freq,
+        ]
+    if len(alt_allele_freq) != len(variant.alleles) - 1:
         raise ValueError(
-            f"The number of provided frequencies ({len(allele_freq)}) doesn't match"
-            f" the number of alleles in the variant ({len(variant.alleles)})."
+            f"The number of provided frequencies ({len(alt_allele_freq)}) doesn't match"
+            f" the number of alternate alleles in the variant ({len(variant.alleles)-1})."
         )
-    if sum(allele_freq) != 1.0:
+    if sum(alt_allele_freq) > 1.0:
         raise ValueError(
-            f"The provided frequencies must add up to 1.0 (sum was {sum(allele_freq):.3f})"
+            f"The provided frequencies must not sum to > 1.0 (sum was {sum(alt_allele_freq):.3e})"
         )
 
+    # Set remaining odds to the reference allele
+    allele_freq = [
+        1 - sum(alt_allele_freq),
+    ] + alt_allele_freq
+
     # Choose gts
     np.random.seed(random_seed)
     genotypes = np.random.choice(

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pandas-genomics"
-version = "0.6.0"
+version = "v0.6.1"
 description = "Pandas ExtensionDtypes and ExtensionArray for working with genomics data"
 license = "BSD-3-Clause"
 authors = ["John McGuigan <jrm5100@psu.edu>"]

tests/simulation/test_random.py

@@ -4,6 +4,6 @@
 
 def test():
     var = Variant(chromosome="1", position=123456, ref="T", alt=["A"])
-    gta = sim.generate_random_gt(var, allele_freq=[0.7, 0.3])
+    gta = sim.generate_random_gt(var, alt_allele_freq=0.3)
     var2 = Variant(chromosome="1", position=223456, ref="T", alt=["A", "C"])
-    gta_2 = sim.generate_random_gt(var2, allele_freq=[0.7, 0.25, 0.05])
+    gta_2 = sim.generate_random_gt(var2, alt_allele_freq=[0.25, 0.05])