Dataset analysis: first_experimental_validation

Run id 20260515_data_first_experimental_validation_seed0 · 2026-05-17T20:58:42+00:00 · championsnet

TL;DR

Basic

rows1,974
columns80
unique_seq_hash1,974
duplicate_rows0

source_dataset distribution

sourcerowsfraction
first_experimental_validation1,974100.00%

label_source distribution

label_sourcerowsfraction
observed1,974100.00%

Label coverage

Labels per row

labels per rowrowsfractiondistribution
021310.79%██████████░░░░░░░░░░░░░░░░░░░░░░
131616.01%███████████████░░░░░░░░░░░░░░░░░
221911.09%██████████░░░░░░░░░░░░░░░░░░░░░░
31497.55%███████░░░░░░░░░░░░░░░░░░░░░░░░░
41035.22%█████░░░░░░░░░░░░░░░░░░░░░░░░░░░
5974.91%████░░░░░░░░░░░░░░░░░░░░░░░░░░░░
61005.07%████░░░░░░░░░░░░░░░░░░░░░░░░░░░░
71196.03%█████░░░░░░░░░░░░░░░░░░░░░░░░░░░
865833.33%████████████████████████████████

Per-receptor balance

Receptorbindersnon-bindersmissingmissing %bind % (of called)
R119691786143.62%17.61%
FcRn622293082241.64%19.27%
R2AH12498786343.72%11.16%
R2AR20684892046.61%19.54%
R2B17994185443.26%15.98%
R3AF13588395648.43%13.26%
R3AV19194184242.65%16.87%
R3B651,03087944.53%5.94%

Profile strings

283 unique profile strings; 658 rows (33.33%) have all 8 receptors labelled.

Top 20 most common profiles

profilerowsfraction
0000000024912.61%
--------21310.79%
010000001638.26%
10111111572.89%
-0------522.63%
0-------452.28%
------0-422.13%
10111110412.08%
-------0402.03%
--0-----371.87%
----0---371.87%
10000000351.77%
-----0--341.72%
00000-00291.47%
10011010251.27%
---0----221.11%
0000000-201.01%
0-000000160.81%
-0-----0160.81%
0000-000140.71%

Sequence features

wt_length_rate1.00
canonical_aa_rate1.00
n_glyco_motif_rate0.0000
in_variable_region_only_rate1.00

Edit distance to WT

mean = 8.49, std = 2.13, median = 8, p90 = 12, p99 = 13, max = 13.

edit distancerowshistogram
01░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
10░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
212░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
3-449█░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
5-7544██████████████████░░░░░░░░░░░░
8-9875██████████████████████████████
10-14493████████████████░░░░░░░░░░░░░░
15-190░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
20-290░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
30-490░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
>=500░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░

Mean edit distance, by per-receptor label

Receptorbindersnon-bindersmissing
R1mean=6.62, median=7 (n=196)mean=8.26, median=8 (n=917)mean=9.15, median=9 (n=861)
FcRn6mean=7.46, median=7 (n=222)mean=8.28, median=8 (n=930)mean=9.00, median=9 (n=822)
R2AHmean=6.66, median=7 (n=124)mean=8.15, median=8 (n=987)mean=9.13, median=9 (n=863)
R2ARmean=6.61, median=7 (n=206)mean=8.24, median=8 (n=848)mean=9.13, median=9 (n=920)
R2Bmean=6.50, median=7 (n=179)mean=8.35, median=8 (n=941)mean=9.06, median=9 (n=854)
R3AFmean=6.81, median=7 (n=135)mean=8.16, median=8 (n=883)mean=9.03, median=9 (n=956)
R3AVmean=6.72, median=7 (n=191)mean=8.26, median=8 (n=941)mean=9.14, median=9 (n=842)
R3Bmean=7.09, median=7 (n=65)mean=8.03, median=8 (n=1,030)mean=9.12, median=9 (n=879)

Read counts per receptor

(no count data on this dataset)

Sequence diversity (per-position Shannon entropy)

Overall (sampled): n=1,974, mean entropy = 0.22 bits, max position = 2.12, positions above 1 bit = 17/232, zero-entropy positions = 108.

Sequences with all 8 labels: n=658, mean entropy = 0.19 bits, max position = 2.16, positions above 1 bit = 13/232, zero-entropy positions = 129.

Per receptor (binders vs non-binders)

Receptorbindersnon-binders
R1n=196, mean H = 0.12n=917, mean H = 0.21
FcRn6n=222, mean H = 0.14n=930, mean H = 0.22
R2AHn=124, mean H = 0.12n=987, mean H = 0.21
R2ARn=206, mean H = 0.14n=848, mean H = 0.21
R2Bn=179, mean H = 0.13n=941, mean H = 0.22
R3AFn=135, mean H = 0.12n=883, mean H = 0.21
R3AVn=191, mean H = 0.14n=941, mean H = 0.22
R3Bn=65, mean H = 0.11n=1,030, mean H = 0.21