Find the shortcut. Learn the biology.
Automated quality control for genomic machine learning datasets: scores the biases, duplicates and data leakage a classifier could exploit before you train on it.
Searching test set enhancers_test.csv against train set enhancers_train.csv
Data Leakage:!WarningHow a flag is decided →
gb-qc v1.0.0 · run 2026-08-26 23:58:05

Basic Descriptive Statistics

Filename enhancers_test.csv enhancers_train.csv
Number of sequences 600 1200
Minimum length 4 4
Mean length 276.71 274.48
Maximum length 568 568

Every test sequence searched against the train set with MMseqs2, and scored on its best hit. Similarity is min(query coverage, target coverage) × percent identity: how much of the shorter sequence the alignment spans, times how much of that matches. The histogram is the distribution of those best hits.

The flag is the percentage of test sequences at or above the threshold: Pass at 0%, Warning below 2%, Fail at 2% or more. A test sequence that near-duplicates a training one is one the model has already seen, so the accuracy it earns there is not evidence. What to do about it →

The panel under the histogram lists those alignments, up to the first 100; every one of them, listed or not, is exported to mmseqs/mmseqs2_search_result.tsv beside this report. Its columns are:

Query (Q)
Identifier of the test sequence: seq_<i>_test, where i is its 0-based position in the input test file.
Target (T)
Identifier of the train sequence: seq_<i>_train, where i is its 0-based position in the input train file.
Q Cov.
Fraction of the query sequence covered by the alignment (0–1).
T Cov.
Fraction of the target sequence covered by the alignment (0–1).
% Identity
Percent identical aligned positions in the aligned region.
% Similarity
Similarity score used for leakage detection, calculated as min(Q Cov., T Cov.) × % Identity.
E-value
MMseqs2 E-value (lower is more "significant").
Alignment
Click “Show” to expand the alignment visualisation for a row.
Filename enhancers_test.csv enhancers_train.csv
Data Leakage (percentage) 0.67% 0.33%
Data Leakage (count) 4 4
Similarity Histogram
4 high-similarity alignments
Query (Q) Target (T) Q Cov. T Cov. % Identity % Similarity E-value Alignment
seq_162_test seq_617_train 1.00 1.00 100.0 100.00 1.00e-195
seq_455_test seq_468_train 1.00 1.00 100.0 100.00 2.20e-85
seq_42_test seq_1192_train 1.00 1.00 100.0 100.00 4.53e-259
seq_73_test seq_32_train 1.00 1.00 100.0 100.00 1.28e-233