Batch Effect Screen

Screen batch-level mean shifts relative to within-batch variation.

Description

A standardized batch mean shift compares between-batch difference with within-batch spread.

A standardized batch mean shift compares between-batch difference with within-batch spread. The denominator here gives the two batch variances equal weight, regardless of sample counts.^[1]

Screen batch-level mean shifts relative to within-batch variation.

When to use Batch Effect Screen

Use this tool to screen batch-level mean shifts relative to within-batch variation.

Prepare the upstream counts, expression values, sequences or record lists requested by this tool. Keep corresponding features in the same order and confirm count units, transformations and caller-selected criteria.

How to use Batch Effect Screen and understand its results

Prepare the upstream counts, expression values, sequences or record lists requested by this tool. Keep corresponding features in the same order and confirm count units, transformations and caller-selected criteria.
Enter batchOneValues, batchTwoValues, maximumAbsoluteStandardizedShift using the field table and calculation rules, then run the tool.
Read batchMeanDifference, pooledWithinBatchStdDev, standardizedShift, batchEffectFlag. The explanation below defines the units, signs, ordering and any flags or placeholder values.
If the tool reports an input issue, correct the values and run it again. Apply the stated assumptions when interpreting a successfully returned result.

Input field	Meaning	Value type; see rules below	Requirement
batchOneValues	Batch one values	list of number	Required
batchTwoValues	Batch two values	list of number	Required
maximumAbsoluteStandardizedShift	Maximum absolute standardized shift	number	Required

Enter at least two finite observations in each batch and a finite absolute-shift criterion. Require positive combined within-batch spread, then return signed mean difference, pooled SD, standardized shift and an inclusive absolute-shift flag. Batch lengths may differ.

pooledSD=sqrt((populationVariance(batch1)+populationVariance(batch2))/2); shift=(mean2−mean1)/pooledSD

Units, indexing, boundary conditions and exceptional cases are defined in the calculation rules above.

Output field	Meaning	Value type
batchMeanDifference	Batch mean difference	number
pooledWithinBatchStdDev	Pooled within batch std dev	number
standardizedShift	Standardized shift	number
batchEffectFlag	Batch effect flag	boolean

json

{
  "input": {
    "batchOneValues": [
      1,
      2,
      3
    ],
    "batchTwoValues": [
      5,
      6,
      7
    ],
    "maximumAbsoluteStandardizedShift": 1
  },
  "output": {
    "batchMeanDifference": 4,
    "pooledWithinBatchStdDev": 0.816496580927726,
    "standardizedShift": 4.898979485566356,
    "batchEffectFlag": true
  }
}

Limitations and assumptions

This is not a hypothesis test or a sample-size-weighted pooled variance estimate. Biological confounding and covariates are not separated from batch effects.

Numeric inputs must be finite. Follow the calculation-specific rules for overflow, underflow and exceptional cases. Lists are limited to 100,000 entries; the rules above may require smaller limits. Missing required fields, extra fields, wrong value types and violations of the calculation rules are input errors. A successfully returned false flag is an evaluated outcome; its meaning is explained above.

Alternative or Complementary methods

Use Combat Location Scale: Recenter and rescale batch samples using caller-estimated location and scale parameters. For a complementary task, use Wilcoxon Rank Sum: Calculate a two-group Wilcoxon rank-sum statistic with averaged tied ranks.

References

Batch Effect Screen — tool.io

Similar or alternative tools

Combat Location Scale
Recenter and rescale batch samples using caller-estimated location and scale parameters.
Wilcoxon Rank Sum
Calculate a two-group Wilcoxon rank-sum statistic with averaged tied ranks.