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 enhancer_promoter_interaction_K562_val.csv.gz against train set enhancer_promoter_interaction_K562_train.csv.gz
Data Leakage:!WarningHow a flag is decided →
gb-qc v1.0.0 · run 2026-09-15 22:31:15

Basic Descriptive Statistics

Filename enhancer_promoter_interaction_K562_val.csv.gz enhancer_promoter_interaction_K562_train.csv.gz
Number of sequences 2000 10000
Minimum length 5000 5000
Mean length 5000.00 5000.00
Maximum length 5000 5000

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 enhancer_promoter_interaction_K562_val.csv.gz enhancer_promoter_interaction_K562_train.csv.gz
Data Leakage (percentage) 1.80% 0.37%
Data Leakage (count) 36 37
Similarity Histogram
37 high-similarity alignments
Query (Q) Target (T) Q Cov. T Cov. % Identity % Similarity E-value Alignment
seq_1827_test seq_1671_train 0.99 0.99 99.5 98.50 0.00e+00
seq_1936_test seq_2376_train 0.99 0.99 99.5 98.50 0.00e+00
seq_1302_test seq_8121_train 0.99 0.99 99.5 98.50 0.00e+00
seq_110_test seq_4582_train 0.99 0.99 99.5 98.50 0.00e+00
seq_1330_test seq_5321_train 0.99 0.99 99.4 98.41 0.00e+00
seq_1294_test seq_6641_train 0.99 0.99 99.4 98.41 0.00e+00
seq_1347_test seq_3616_train 0.99 0.99 99.4 98.41 0.00e+00
seq_1629_test seq_761_train 0.99 0.99 99.4 98.41 0.00e+00
seq_1391_test seq_9524_train 0.99 0.99 99.4 98.41 0.00e+00
seq_856_test seq_4685_train 0.99 0.99 99.4 98.41 0.00e+00
seq_602_test seq_6746_train 0.99 0.99 99.4 98.41 0.00e+00
seq_835_test seq_1219_train 0.99 0.99 99.4 98.41 0.00e+00
seq_23_test seq_184_train 0.99 0.99 99.4 98.41 0.00e+00
seq_1281_test seq_3877_train 0.99 0.99 99.4 98.41 0.00e+00
seq_462_test seq_6851_train 0.99 0.99 99.4 98.41 0.00e+00
seq_1546_test seq_3195_train 0.99 0.99 99.4 98.41 0.00e+00
seq_1153_test seq_6273_train 0.99 0.99 99.4 98.41 0.00e+00
seq_947_test seq_2667_train 0.99 0.99 99.3 98.31 0.00e+00
seq_1106_test seq_5687_train 0.99 0.99 99.3 98.31 0.00e+00
seq_1055_test seq_1845_train 0.99 0.99 99.3 98.31 0.00e+00
seq_1825_test seq_2145_train 0.99 0.99 99.3 98.31 0.00e+00
seq_289_test seq_6552_train 0.99 0.99 99.3 98.31 0.00e+00
seq_43_test seq_9483_train 0.99 0.99 99.3 98.31 0.00e+00
seq_1514_test seq_1131_train 0.99 0.99 99.3 98.31 0.00e+00
seq_1997_test seq_4546_train 0.99 0.99 99.3 98.31 0.00e+00
seq_1082_test seq_6372_train 0.99 0.99 99.3 98.31 0.00e+00
seq_9_test seq_5641_train 0.99 0.99 99.3 98.31 0.00e+00
seq_966_test seq_9404_train 0.99 0.99 99.3 98.31 0.00e+00
seq_779_test seq_160_train 0.99 0.99 99.2 98.21 0.00e+00
seq_1331_test seq_921_train 0.99 0.99 99.1 98.11 0.00e+00
seq_1013_test seq_5091_train 1.00 0.99 99.0 98.11 0.00e+00
seq_1772_test seq_5059_train 1.00 0.99 99.0 98.11 0.00e+00
seq_762_test seq_9542_train 0.98 0.98 99.2 97.22 0.00e+00
seq_1713_test seq_4512_train 0.97 0.97 99.2 96.22 0.00e+00
seq_118_test seq_9080_train 0.97 0.97 99.2 96.22 0.00e+00
seq_805_test seq_6395_train 0.97 0.97 98.1 95.16 0.00e+00
seq_118_test seq_9015_train 0.92 0.92 98.4 90.53 0.00e+00