Summary

Basic Descriptive Statistics
! Data Leakage
Documentation GitHub
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 core_promoter_detection_all_val.csv.gz against train set core_promoter_detection_all_train.csv.gz
Data Leakage:!WarningHow a flag is decided →
gb-qc v1.0.0 · run 2026-09-15 22:30:51

Basic Descriptive Statistics

Filename core_promoter_detection_all_val.csv.gz core_promoter_detection_all_train.csv.gz
Number of sequences 5920 47356
Minimum length 70 70
Mean length 70.00 70.00
Maximum length 70 70
!

Data Leakage

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 core_promoter_detection_all_val.csv.gz core_promoter_detection_all_train.csv.gz
Data Leakage (percentage) 1.74% 0.24%
Data Leakage (count) 103 114
Similarity Histogram
117 high-similarity alignments (first 100 shown)
Query (Q) Target (T) Q Cov. T Cov. % Identity % Similarity E-value Alignment
seq_3340_test seq_709_train 1.00 1.00 100.0 100.00 1.57e-34
seq_1727_test seq_45771_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5559_test seq_27491_train 1.00 1.00 100.0 100.00 1.57e-34
seq_993_test seq_37318_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5124_test seq_12737_train 1.00 1.00 100.0 100.00 1.57e-34
seq_2575_test seq_38581_train 1.00 1.00 100.0 100.00 1.57e-34
seq_3584_test seq_14033_train 1.00 1.00 100.0 100.00 1.57e-34
seq_568_test seq_7525_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4688_test seq_2811_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4651_test seq_12739_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4939_test seq_2006_train 1.00 1.00 100.0 100.00 1.57e-34
seq_1977_test seq_20343_train 1.00 1.00 100.0 100.00 1.57e-34
seq_3979_test seq_15949_train 1.00 1.00 100.0 100.00 1.57e-34
seq_1972_test seq_370_train 1.00 1.00 100.0 100.00 1.57e-34
seq_2100_test seq_7223_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5206_test seq_7531_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4453_test seq_12333_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4997_test seq_42584_train 1.00 1.00 100.0 100.00 1.57e-34
seq_1298_test seq_28363_train 1.00 1.00 100.0 100.00 1.57e-34
seq_3554_test seq_18253_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4998_test seq_28319_train 1.00 1.00 100.0 100.00 1.57e-34
seq_795_test seq_21851_train 1.00 1.00 100.0 100.00 1.57e-34
seq_2249_test seq_38848_train 1.00 1.00 100.0 100.00 1.57e-34
seq_1978_test seq_17025_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5901_test seq_1841_train 1.00 1.00 100.0 100.00 1.57e-34
seq_975_test seq_27721_train 1.00 1.00 100.0 100.00 1.57e-34
seq_442_test seq_32406_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4642_test seq_35554_train 1.00 1.00 100.0 100.00 1.57e-34
seq_711_test seq_47254_train 1.00 1.00 100.0 100.00 1.57e-34
seq_2675_test seq_10788_train 1.00 1.00 100.0 100.00 1.57e-34
seq_2967_test seq_25684_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4051_test seq_20473_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4234_test seq_39599_train 1.00 1.00 100.0 100.00 1.57e-34
seq_2902_test seq_20760_train 1.00 1.00 100.0 100.00 1.57e-34
seq_3516_test seq_11493_train 1.00 1.00 100.0 100.00 1.57e-34
seq_3268_test seq_36511_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5673_test seq_11070_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4712_test seq_28170_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4669_test seq_3440_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5555_test seq_24526_train 1.00 1.00 100.0 100.00 1.57e-34
seq_3406_test seq_47039_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5154_test seq_9545_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5513_test seq_93_train 1.00 1.00 100.0 100.00 1.57e-34
seq_786_test seq_23156_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4156_test seq_27797_train 1.00 1.00 100.0 100.00 1.57e-34
seq_2095_test seq_23010_train 1.00 1.00 100.0 100.00 1.57e-34
seq_1271_test seq_40171_train 1.00 1.00 100.0 100.00 1.57e-34
seq_1390_test seq_30860_train 1.00 1.00 100.0 100.00 1.57e-34
seq_5261_test seq_3232_train 1.00 1.00 100.0 100.00 1.57e-34
seq_273_test seq_5901_train 1.00 1.00 100.0 100.00 1.57e-34
seq_3222_test seq_20531_train 1.00 1.00 100.0 100.00 1.57e-34
seq_4475_test seq_18231_train 1.00 1.00 100.0 100.00 1.57e-34
seq_261_test seq_5848_train 1.00 1.00 100.0 100.00 1.57e-34
seq_301_test seq_43134_train 1.00 1.00 100.0 100.00 1.57e-34
seq_271_test seq_45821_train 0.99 0.99 100.0 98.60 7.71e-34
seq_412_test seq_37534_train 0.99 0.99 100.0 98.60 7.71e-34
seq_1785_test seq_41469_train 0.99 0.99 100.0 98.60 7.71e-34
seq_1405_test seq_8108_train 0.99 0.99 100.0 98.60 7.71e-34
seq_4613_test seq_8930_train 0.99 0.99 100.0 98.60 7.71e-34
seq_1861_test seq_28602_train 0.99 0.99 100.0 98.60 7.71e-34
seq_2249_test seq_9120_train 0.99 0.99 100.0 98.60 7.71e-34
seq_3236_test seq_24004_train 0.99 0.99 100.0 98.60 7.71e-34
seq_3236_test seq_36433_train 0.99 0.99 100.0 98.60 7.71e-34
seq_3534_test seq_13340_train 1.00 1.00 98.5 98.50 8.30e-33
seq_5245_test seq_7867_train 1.00 1.00 98.5 98.50 8.30e-33
seq_411_test seq_19120_train 1.00 1.00 98.5 98.50 8.30e-33
seq_5653_test seq_38827_train 0.97 0.97 100.0 97.10 3.76e-33
seq_3942_test seq_27741_train 1.00 1.00 97.1 97.10 4.23e-31
seq_3730_test seq_36600_train 0.97 0.97 100.0 97.10 3.76e-33
seq_975_test seq_30521_train 1.00 1.00 97.1 97.10 4.23e-31
seq_4260_test seq_22856_train 1.00 1.00 97.1 97.10 4.23e-31
seq_2630_test seq_7173_train 0.96 0.96 100.0 95.70 1.83e-32
seq_4491_test seq_31769_train 0.96 0.96 100.0 95.70 1.83e-32
seq_1588_test seq_4605_train 0.96 0.96 100.0 95.70 1.83e-32
seq_1772_test seq_44874_train 0.96 0.96 100.0 95.70 1.83e-32
seq_4260_test seq_19375_train 0.96 0.96 100.0 95.70 1.83e-32
seq_628_test seq_24155_train 0.97 0.97 98.5 95.64 1.93e-31
seq_1552_test seq_1559_train 1.00 0.99 95.7 94.36 4.54e-28
seq_1564_test seq_572_train 0.94 0.94 100.0 94.30 8.82e-32
seq_620_test seq_31320_train 0.94 0.94 100.0 94.30 8.82e-32
seq_1362_test seq_2006_train 1.00 1.00 94.2 94.20 9.79e-28
seq_1491_test seq_24456_train 1.00 1.00 94.2 94.20 9.79e-28
seq_410_test seq_2248_train 1.00 1.00 94.2 94.20 9.79e-28
seq_3311_test seq_44353_train 1.00 1.00 94.2 94.20 9.79e-28
seq_4340_test seq_43273_train 0.97 0.97 97.0 94.19 9.57e-30
seq_1889_test seq_39032_train 0.93 0.93 100.0 92.90 4.23e-31
seq_1193_test seq_38662_train 0.93 0.93 100.0 92.90 4.23e-31
seq_3311_test seq_12960_train 0.99 1.00 94.2 92.88 2.07e-26
seq_5231_test seq_43917_train 0.99 0.99 94.2 92.88 4.51e-27
seq_2112_test seq_14434_train 0.96 0.96 97.0 92.83 4.50e-29
seq_2318_test seq_24672_train 1.00 1.00 92.8 92.80 4.41e-26
seq_410_test seq_35981_train 1.00 1.00 92.8 92.80 4.41e-26
seq_3311_test seq_3746_train 1.00 1.00 92.8 92.80 4.41e-26
seq_2628_test seq_7894_train 1.00 0.96 95.7 91.58 9.75e-29
seq_4526_test seq_42159_train 0.96 0.94 97.0 91.47 9.79e-28
seq_2113_test seq_27149_train 0.93 0.93 98.4 91.41 2.08e-29
seq_2719_test seq_7529_train 0.91 0.91 100.0 91.40 2.02e-30
seq_2790_test seq_19478_train 0.91 0.91 100.0 91.40 2.02e-30
seq_3581_test seq_1559_train 1.00 1.00 91.4 91.40 1.89e-24
seq_123_test seq_339_train 1.00 1.00 91.4 91.40 1.89e-24