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 AGO2_eCLIP_Manakov2022_test_leftout.csv.gz against train set AGO2_eCLIP_Manakov2022_train.csv.gz
Data Leakage:!WarningHow a flag is decided →
gb-qc v1.0.0 · run 2026-09-15 22:32:00

Basic Descriptive Statistics

Filename AGO2_eCLIP_Manakov2022_test_leftout.csv.gz AGO2_eCLIP_Manakov2022_train.csv.gz
Number of sequences 20054 2495535
Minimum length 67 66
Mean length 71.87 72.38
Maximum length 77 78

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 AGO2_eCLIP_Manakov2022_test_leftout.csv.gz AGO2_eCLIP_Manakov2022_train.csv.gz
Data Leakage (percentage) 1.30% 0.02%
Data Leakage (count) 261 403
Similarity Histogram
423 high-similarity alignments (first 100 shown)
Query (Q) Target (T) Q Cov. T Cov. % Identity % Similarity E-value Alignment
seq_18707_test seq_2220402_train 0.99 0.97 98.5 95.84 1.60e-31
seq_18708_test seq_2224339_train 0.99 1.00 97.1 95.74 8.05e-30
seq_9218_test seq_1002171_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9080_test seq_1027469_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8479_test seq_1021251_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8641_test seq_1056154_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8705_test seq_1072409_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9334_test seq_1074380_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8610_test seq_1068802_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8674_test seq_1020636_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8915_test seq_999594_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8979_test seq_1027369_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9043_test seq_1033313_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8621_test seq_1022204_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8749_test seq_1032196_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8708_test seq_1043662_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8863_test seq_1032864_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8927_test seq_1033794_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9840_test seq_1089113_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8864_test seq_1077285_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8636_test seq_1020628_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8557_test seq_1001175_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8570_test seq_1066334_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8698_test seq_1027902_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8757_test seq_1033324_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9144_test seq_1032741_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9240_test seq_1015799_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9328_test seq_1018314_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9328_test seq_1060512_train 0.99 0.99 94.3 92.98 3.05e-25
seq_8668_test seq_1089526_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8668_test seq_1023324_train 0.99 0.99 94.3 92.98 3.05e-25
seq_9537_test seq_1058513_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8983_test seq_1032202_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9079_test seq_1079069_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9143_test seq_1001954_train 0.99 0.99 94.3 92.98 3.05e-25
seq_9239_test seq_1055699_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9212_test seq_1058103_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8485_test seq_1066164_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8623_test seq_998522_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8751_test seq_1023535_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8701_test seq_1001971_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8765_test seq_1032736_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8940_test seq_1028169_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9124_test seq_1020568_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9316_test seq_1063045_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8954_test seq_1029728_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8886_test seq_1041693_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9110_test seq_1056444_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8487_test seq_1015678_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8898_test seq_1029398_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8962_test seq_1043792_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9122_test seq_998515_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8637_test seq_1040296_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8797_test seq_1032199_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8893_test seq_1032212_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8957_test seq_1027800_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8606_test seq_1058704_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8670_test seq_1056382_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8766_test seq_1057745_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8508_test seq_998667_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8691_test seq_1055804_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8755_test seq_1016860_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8787_test seq_1008577_train 0.99 0.99 94.3 92.98 3.05e-25
seq_8966_test seq_1091752_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8931_test seq_1036232_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9123_test seq_1066282_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8603_test seq_1086490_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8667_test seq_1027273_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9321_test seq_1029601_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8776_test seq_1040194_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8904_test seq_1033580_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8904_test seq_1066494_train 0.99 0.99 94.3 92.98 3.05e-25
seq_8814_test seq_1033439_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8974_test seq_1056425_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8458_test seq_1033806_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8490_test seq_1073113_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8592_test seq_1023050_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8656_test seq_1035717_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8720_test seq_1061024_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8752_test seq_1027743_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9164_test seq_1032951_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9075_test seq_1008263_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8566_test seq_1090597_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8726_test seq_1040004_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9009_test seq_1063482_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9201_test seq_1090474_train 0.99 0.99 94.3 92.98 3.05e-25
seq_8650_test seq_1020594_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8714_test seq_1029158_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8746_test seq_1027982_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8778_test seq_1061319_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8810_test seq_1027271_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8891_test seq_1085934_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8923_test seq_1016670_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9051_test seq_1018483_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8818_test seq_1027851_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8914_test seq_1032735_train 1.00 0.99 94.3 92.98 1.44e-26
seq_9074_test seq_1058635_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8965_test seq_1040184_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8997_test seq_1020463_train 1.00 0.99 94.3 92.98 1.44e-26
seq_8690_test seq_1020482_train 1.00 0.99 94.3 92.98 1.44e-26