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 promoter_all_test.csv.gz against train set promoter_all_train.csv.gz
Data Leakage:!WarningHow a flag is decided →
gb-qc v1.0.0 · run 2026-09-15 22:31:08

Basic Descriptive Statistics

Filename promoter_all_test.csv.gz promoter_all_train.csv.gz
Number of sequences 1584 30000
Minimum length 300 300
Mean length 300.00 300.00
Maximum length 300 300
!

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 promoter_all_test.csv.gz promoter_all_train.csv.gz
Data Leakage (percentage) 0.88% 0.05%
Data Leakage (count) 14 16
Similarity Histogram
16 high-similarity alignments
Query (Q) Target (T) Q Cov. T Cov. % Identity % Similarity E-value Alignment
seq_1008_test seq_21913_train 1.00 1.00 98.3 98.01 3.08e-155
seq_1195_test seq_20817_train 0.98 0.98 96.6 94.96 2.44e-144
seq_1398_test seq_15576_train 0.96 0.96 97.2 93.60 1.10e-143
seq_1008_test seq_12421_train 0.96 0.96 97.5 93.31 5.18e-144
seq_1220_test seq_6349_train 0.99 0.99 93.9 93.24 2.36e-133
seq_1406_test seq_7418_train 0.99 1.00 93.9 93.24 1.02e-132
seq_1004_test seq_13620_train 0.96 0.96 96.5 92.64 8.77e-140
seq_1246_test seq_351_train 0.96 0.96 96.1 91.97 7.05e-137
seq_1145_test seq_14215_train 0.94 0.94 97.8 91.93 2.21e-142
seq_1157_test seq_12130_train 0.99 0.99 91.9 91.26 6.72e-124
seq_1195_test seq_761_train 0.97 0.97 94.1 90.99 6.53e-129
seq_1041_test seq_15920_train 0.99 0.99 91.6 90.96 2.40e-122
seq_1519_test seq_20374_train 0.99 1.00 91.0 90.36 4.86e-118
seq_1165_test seq_17962_train 0.95 0.95 95.1 90.34 8.27e-131
seq_1542_test seq_19998_train 0.96 0.96 94.4 90.34 6.53e-129
seq_884_test seq_3937_train 1.00 1.00 90.3 90.30 1.98e-117