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 transcription_factor_prediction_human_4_test.csv.gz against train set transcription_factor_prediction_human_4_train.csv.gz
Data Leakage:✖FailHow a flag is decided →
gb-qc v1.0.0 · run 2026-09-15 22:30:51

Basic Descriptive Statistics

Filename transcription_factor_prediction_human_4_test.csv.gz transcription_factor_prediction_human_4_train.csv.gz
Number of sequences 1000 19000
Minimum length 101 101
Mean length 101.00 101.00
Maximum length 101 101
✖

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 transcription_factor_prediction_human_4_test.csv.gz transcription_factor_prediction_human_4_train.csv.gz
Data Leakage (percentage) 3.20% 0.56%
Data Leakage (count) 32 106
Similarity Histogram
124 high-similarity alignments (first 100 shown)
Query (Q) Target (T) Q Cov. T Cov. % Identity % Similarity E-value Alignment
seq_906_test seq_1367_train 0.99 0.99 100.0 99.00 1.19e-51
seq_594_test seq_13465_train 0.99 0.99 100.0 99.00 1.19e-51
seq_558_test seq_8556_train 0.99 0.99 99.0 98.01 6.04e-50
seq_906_test seq_1060_train 0.98 0.98 100.0 98.00 5.74e-51
seq_767_test seq_7106_train 0.98 0.98 100.0 98.00 5.74e-51
seq_548_test seq_352_train 1.00 1.00 97.0 97.00 3.07e-47
seq_908_test seq_12949_train 0.98 0.98 98.9 96.92 2.89e-49
seq_558_test seq_18589_train 0.99 0.99 97.0 96.03 1.44e-46
seq_594_test seq_7487_train 0.96 0.96 100.0 96.00 1.32e-49
seq_513_test seq_6007_train 0.96 0.96 100.0 96.00 1.32e-49
seq_899_test seq_10048_train 0.99 0.99 96.0 95.04 6.73e-45
seq_899_test seq_9667_train 0.99 0.99 96.0 95.04 6.73e-45
seq_548_test seq_14890_train 1.00 1.00 95.0 95.00 6.65e-44
seq_899_test seq_3737_train 1.00 1.00 95.0 95.00 6.65e-44
seq_548_test seq_10048_train 0.97 0.97 97.9 94.96 6.65e-47
seq_899_test seq_1918_train 0.98 0.98 96.9 94.96 6.72e-46
seq_767_test seq_2218_train 0.94 0.94 100.0 94.10 2.99e-48
seq_813_test seq_6462_train 0.99 0.99 95.0 94.05 3.04e-43
seq_891_test seq_10850_train 0.99 0.99 95.0 94.05 3.04e-43
seq_549_test seq_18589_train 0.99 0.99 95.0 94.05 3.04e-43
seq_548_test seq_9667_train 0.97 0.97 96.9 93.99 3.12e-45
seq_899_test seq_7606_train 0.97 0.97 96.9 93.99 3.12e-45
seq_908_test seq_17462_train 0.93 0.93 100.0 93.10 1.41e-47
seq_510_test seq_11289_train 0.99 1.00 94.0 93.06 5.99e-41
seq_742_test seq_13390_train 1.00 0.99 94.0 93.06 5.99e-41
seq_549_test seq_15923_train 0.99 0.99 94.0 93.06 1.33e-41
seq_525_test seq_10799_train 0.99 0.99 94.0 93.06 1.33e-41
seq_548_test seq_5760_train 0.96 0.96 96.9 93.02 1.45e-44
seq_548_test seq_3737_train 0.96 0.96 96.9 93.02 1.45e-44
seq_899_test seq_352_train 0.96 0.96 96.9 93.02 1.45e-44
seq_762_test seq_12666_train 0.96 0.96 96.9 93.02 1.45e-44
seq_549_test seq_8556_train 0.97 0.97 95.9 93.02 1.42e-43
seq_558_test seq_15923_train 0.97 0.97 95.9 93.02 1.42e-43
seq_908_test seq_12338_train 0.95 0.95 97.9 93.00 1.45e-45
seq_899_test seq_8214_train 0.98 0.98 94.9 93.00 1.39e-42
seq_732_test seq_1001_train 0.98 0.98 94.9 93.00 1.39e-42
seq_558_test seq_17153_train 1.00 1.00 93.0 93.00 1.27e-40
seq_852_test seq_3812_train 0.92 0.92 100.0 92.10 6.65e-47
seq_732_test seq_9152_train 0.99 0.99 93.0 92.07 5.64e-40
seq_915_test seq_5034_train 0.99 0.99 93.0 92.07 5.64e-40
seq_987_test seq_9531_train 0.99 0.99 93.0 92.07 5.64e-40
seq_932_test seq_7714_train 0.95 0.96 96.9 92.06 3.04e-43
seq_548_test seq_1918_train 0.94 0.94 97.8 92.03 6.73e-45
seq_548_test seq_12107_train 0.98 0.98 93.9 92.02 5.99e-41
seq_548_test seq_8214_train 0.98 0.98 93.9 92.02 5.99e-41
seq_899_test seq_1162_train 0.98 0.98 93.9 92.02 5.99e-41
seq_899_test seq_12107_train 0.98 0.98 93.9 92.02 5.99e-41
seq_542_test seq_11989_train 0.98 0.98 93.9 92.02 5.99e-41
seq_558_test seq_17575_train 0.98 0.98 93.9 92.02 5.99e-41
seq_768_test seq_15698_train 1.00 1.00 92.0 92.00 5.23e-39
seq_805_test seq_3815_train 0.96 0.96 95.8 91.97 6.50e-43
seq_908_test seq_2805_train 0.96 0.96 95.8 91.97 6.50e-43
seq_908_test seq_2201_train 0.96 0.96 95.8 91.97 6.50e-43
seq_525_test seq_11857_train 0.96 0.96 95.8 91.97 6.50e-43
seq_813_test seq_8186_train 0.97 0.97 94.8 91.96 6.28e-42
seq_548_test seq_8985_train 0.97 0.97 94.8 91.96 6.28e-42
seq_558_test seq_18843_train 0.97 0.97 94.8 91.96 6.28e-42
seq_908_test seq_5553_train 0.99 0.98 93.0 91.14 1.10e-38
seq_819_test seq_5511_train 0.91 0.91 100.0 91.10 3.11e-46
seq_548_test seq_2805_train 0.94 0.94 96.8 91.09 3.04e-43
seq_732_test seq_12666_train 0.94 0.94 96.8 91.09 3.04e-43
seq_762_test seq_12170_train 0.94 0.94 96.8 91.09 3.04e-43
seq_894_test seq_15439_train 0.94 0.94 96.8 91.09 3.04e-43
seq_548_test seq_8374_train 0.99 0.99 92.0 91.08 2.29e-38
seq_899_test seq_11462_train 0.99 0.99 92.0 91.08 2.29e-38
seq_899_test seq_18515_train 0.99 0.99 92.0 91.08 2.29e-38
seq_681_test seq_18557_train 0.99 0.99 92.0 91.08 2.29e-38
seq_768_test seq_14117_train 0.99 0.99 92.0 91.08 2.29e-38
seq_768_test seq_16803_train 0.99 1.00 92.0 91.08 1.00e-37
seq_762_test seq_9152_train 0.99 0.99 92.0 91.08 2.29e-38
seq_548_test seq_7606_train 0.93 0.93 97.8 91.05 3.10e-44
seq_548_test seq_13379_train 0.98 0.98 92.9 91.04 2.49e-39
seq_548_test seq_1162_train 0.98 0.98 92.9 91.04 2.49e-39
seq_548_test seq_14485_train 0.98 0.98 92.9 91.04 2.49e-39
seq_681_test seq_9211_train 0.98 0.98 92.9 91.04 2.49e-39
seq_768_test seq_10009_train 0.98 0.98 92.9 91.04 2.49e-39
seq_570_test seq_18230_train 0.98 0.98 92.9 91.04 2.49e-39
seq_549_test seq_1952_train 0.98 0.98 92.9 91.04 2.49e-39
seq_549_test seq_4587_train 0.98 0.98 92.9 91.04 2.49e-39
seq_988_test seq_11229_train 0.98 0.98 92.9 91.04 2.49e-39
seq_805_test seq_6195_train 0.95 0.95 95.8 91.01 2.95e-42
seq_932_test seq_16234_train 0.95 0.96 95.8 91.01 1.33e-41
seq_681_test seq_1593_train 0.96 0.96 94.8 91.01 2.83e-41
seq_987_test seq_11740_train 0.96 0.96 94.8 91.01 2.83e-41
seq_908_test seq_10983_train 0.96 0.96 94.8 91.01 2.83e-41
seq_762_test seq_9792_train 0.96 0.96 94.8 91.01 2.83e-41
seq_762_test seq_1001_train 0.96 0.96 94.8 91.01 2.83e-41
seq_558_test seq_1952_train 0.96 0.96 94.8 91.01 2.83e-41
seq_548_test seq_3248_train 1.00 1.00 91.0 91.00 2.08e-37
seq_548_test seq_12714_train 0.97 0.97 93.8 90.99 2.67e-40
seq_732_test seq_14913_train 0.97 0.97 93.8 90.99 2.67e-40
seq_768_test seq_2907_train 0.97 0.97 93.8 90.99 2.67e-40
seq_908_test seq_2797_train 0.97 0.97 93.8 90.99 2.67e-40
seq_762_test seq_15145_train 0.97 0.97 93.8 90.99 2.67e-40
seq_908_test seq_2183_train 0.95 0.94 95.8 90.15 5.99e-41
seq_762_test seq_6819_train 0.93 0.93 96.8 90.12 1.39e-42
seq_819_test seq_14000_train 0.90 0.90 100.0 90.10 1.45e-45
seq_594_test seq_17428_train 0.90 0.90 100.0 90.10 1.45e-45
seq_899_test seq_14177_train 0.99 1.00 91.0 90.09 3.85e-36
seq_915_test seq_8741_train 0.99 0.99 91.0 90.09 8.98e-37