Live Stats, next update: Wed 02 Sep
Human PDBs Analysed
Confidently Wrong
Novel + Confidently Wrong
DB size
Visitors
Full statistics →
New PDB Depositions vs. Their Blind AlphaFold Predictions — A Running Test of “Is Folding Solved?”

Release week 2021-07-14

109
structures analysed (7 full · 6.4%)
10.9%
confidently wrong
00.0%
novel sequences
00.0%
novel & wrong
0.96
median TM-score

Zoomed into the red "confidently wrong" box above (pLDDT ≥ 70, TM < 0.5) — the structures AlphaFold got confidently wrong.

The worst offenders ranked, one row per protein (AlphaFold has one model per sequence, so repeat depositions are collapsed — “×N” marks how many structures of that protein exist; the worst is shown). Each row joins what AlphaFold claimed (blue, pLDDT/100) to what the experiment showed (red, TM-score) — the longer the bar, the bigger the miss. Hover a dot to preview its Cα-deviation ribbon; click to open the full entry.

How to read this

Every point is one experimental protein structure. The horizontal axis is AlphaFold's own confidence in its prediction (mean pLDDT, 0–100). The vertical axis is how well that blind prediction actually matches the experiment (TM-score, 0–1; above 0.5 means the same fold, above 0.9 near-identical). Marker size grows with the FRAUD score (confidence-weighted error).

Cutoff: the shaded red box is the "confidently wrong" zone — AlphaFold was confident (mean pLDDT above 70) yet the fold is wrong (TM-score below 0.5). A predictor that had truly solved folding would leave that box empty.

Take-home: 1 of 109 structures (0.9%) are confidently wrong; median TM-score is 0.96.

Read moreShow less — how each metric is calculated

TM-score: how similar the two 3D shapes are overall, 0–1 (a random pair scores ~0.17, an identical fold ~1). Length-normalised so large and small proteins compare fairly. TM = (1/L) Σᵢ 1/(1 + (dᵢ/d₀)²) — dᵢ is the gap between the i-th aligned Cα atoms after best-fit superposition, and d₀ = 1.24(L−15)^⅓ − 1.8 sets the distance scale for length L. Ref: Zhang & Skolnick, Proteins 2004 doi:10.1002/prot.20264; computed with TM-align, doi:10.1093/nar/gki524.

pLDDT: AlphaFold's own confidence in each residue, 0–100 (higher = surer). It is the model predicting its own accuracy before ever seeing the experiment. We plot the per-structure mean. pLDDT = (1/N) Σᵢ pLDDTᵢ, where pLDDTᵢ is the network's confidence output for residue i.

FRAUD score: the headline number — how wrong the prediction was, weighted by how confident AlphaFold was, so a big error it was sure about counts most. FRAUD = (1/N) Σᵢ (pLDDTᵢ/100) · min(Δᵢ,15)/15, where Δᵢ is residue i's Cα distance from the experiment (Å) after superposition, capped at 15 Å. Runs 0 (perfect) to 1.

Novelty: how little AlphaFold had to go on — 100 minus the highest sequence identity between this protein and any structure released before the 2018-04-30 training cutoff. High = genuinely unseen (100% = nothing similar was ever in the training set). novelty = 100 − maxₚ identity(s, p) over pre-cutoff PDB chains p, with identity = 100 × (matching aligned residues)/(alignment length), from an MMseqs2 search.

Homology: the point colour. High novelty (above 70%) flags the sequence as novel (amber) — AlphaFold had no close template; otherwise a pre-cutoff homolog existed (blue) it could have learned the fold from. novel ⇔ novelty > 70%.

What the metrics mean

TM-score (0–1): overall fold match — above 0.5 is the same fold, above 0.9 near-identical. Cα-RMSD (Å): average backbone distance after best-fit superposition — lower is better (under 2 Å is excellent). lDDT (0–1): local accuracy measured without superposition — above 0.8 is good. Each bar counts how many structures fall in that range.

Take-home: median TM-score 0.96 — most predictions match the experimental fold well, with a long tail that do not.

Read moreShow less — how each metric is calculated

TM-score: overall shape match, 0–1 (above 0.5 = same fold, above 0.9 near-identical), length-normalised. TM = (1/L) Σᵢ 1/(1 + (dᵢ/d₀)²) with dᵢ the aligned-Cα gap after superposition and d₀ = 1.24(L−15)^⅓ − 1.8. Ref: Zhang & Skolnick, Proteins 2004 doi:10.1002/prot.20264.

Cα-RMSD: the average straight-line distance between matching backbone Cα atoms once the two structures are best-fit superposed (Å; lower is better, under ~2 Å excellent). RMSD = √( (1/N) Σᵢ |Pᵢ − (R·Qᵢ + t)|² ), with Pᵢ/Qᵢ the experimental/model Cα coordinates and R,t the rotation and translation from Kabsch superposition.

lDDT: local accuracy with no superposition — the fraction of short-range inter-residue distances the model reproduces, so it is not fooled by a single wrongly-placed domain. lDDT = (1/N) Σᵢ ¼ Σ_t 1[ |d_exp − d_model| < t ] over thresholds t ∈ {0.5, 1, 2, 4} Å and all residue pairs within 15 Å.

Trend over time

The blue line is the mean TM-score of the structures by their deposit month; the red bars count how many were confidently wrong. Binning by deposit date (rather than by when we processed them) gives an even timeline, tracking whether AlphaFold's accuracy on newly-deposited structures is holding steady, improving, or slipping as the PDB keeps growing. Months with fewer than 5 structures are omitted so each point is a meaningful average. A dashed trend line is drawn only if the change over time is statistically significant.

Read moreShow less — how each metric is calculated

Mean TM-score: the month's average shape-match score. TM̄ = (1/M) Σ TM over the M structures deposited that month.

Trend line: a monotonic-trend test over the monthly means — Mann-Kendall (Kendall's τ) for significance, with a robust Theil-Sen slope for the line. Rank-based, so it tolerates the skewed TM distribution and noisy low-count months. Shown only when p < 0.05; otherwise a note reports that no significant trend was found.

Confidently wrong: the count that were both confident and wrong. count( mean pLDDT > 70 AND TM < 0.5 ).

Matched structures

PDBUniProtProteinMethodÅDeposited Novelty %pLDDTTMlDDTGDT_TSRMSDFRAUDFlag
7LB1_A P21675 Transcription initiation factor TFIID subu X-ray 1.35 2021-01-07 0.00 89.54 0.55 0.90 3.61 16.55 0.72 ok
7LB2_A P21675 Transcription initiation factor TFIID subu X-ray 1.70 2021-01-07 0.00 89.60 0.54 0.90 3.74 16.51 0.72 ok
7LB0_A P21675 Transcription initiation factor TFIID subu X-ray 2.33 2021-01-07 0.00 89.54 0.55 0.90 3.53 16.50 0.72 ok
7OKY_Z O00267 Transcription elongation factor SPT5 EM 4.14 2021-05-18 0.00 90.27 0.64 0.88 11.16 13.70 0.58 ok
7EPU_B Q86WJ1 Chromodomain-helicase-DNA-binding protein X-ray 3.50 2021-04-27 55.20 79.15 0.63 0.72 15.51 11.91 0.48 ok
7D4B_A Q07011 Tumor necrosis factor receptor superfamily X-ray 3.14 2020-09-23 35.80 94.01 0.68 0.92 38.67 6.27 0.30 ok
7CJB_D Q13546 THR-LEU-TYR-TYR-MET-ALA-PRO-GLU-HIS-LEU-AS X-ray 2.80 2020-07-09 92.88 0.39 0.61 50.00 4.06 0.21 wrong
7F1Q_A P63096 Guanine nucleotide-binding protein G(i) su EM 2.90 2021-06-09 93.75 0.81 0.18 ok
7F1R_A P63096 Guanine nucleotide-binding protein G(i) su EM 3.00 2021-06-09 93.75 0.82 0.17 ok
7F1S_A P63096 Guanine nucleotide-binding protein G(i) su EM 2.80 2021-06-09 93.75 0.82 0.16 ok
7OKY_M O00472 RNA polymerase II elongation factor ELL2 EM 4.14 2021-05-18 65.62 0.76 0.16 ok
7OKX_M O00472 RNA polymerase II elongation factor ELL2 EM 3.30 2021-05-18 65.62 0.76 0.16 ok
7DUQ_R P43220 Glucagon-like peptide 1 receptor EM 2.50 2021-01-11 81.50 0.81 0.16 ok
7DRT_A P56704 Protein Wnt-3a EM 2.20 2020-12-29 88.31 0.82 0.16 ok
7DUQ_P P01275 Glucagon-like peptide 1 EM 2.50 2021-01-11 68.94 0.79 0.14 ok
7DUQ_A P63092 Guanine nucleotide-binding protein G(s) su EM 2.50 2021-01-11 91.31 0.86 0.13 ok
7F1Q_C P59768 Guanine nucleotide-binding protein G(I)/G( EM 2.90 2021-06-09 89.56 0.87 0.12 ok
7LJ1_A Q06830 Peroxiredoxin-1 X-ray 2.97 2021-01-28 97.19 0.88 0.11 ok
7F1S_C P59768 Guanine nucleotide-binding protein G(I)/G( EM 2.80 2021-06-09 89.56 0.89 0.10 ok
7F1R_C P59768 Guanine nucleotide-binding protein G(I)/G( EM 3.00 2021-06-09 89.56 0.89 0.10 ok
6XCP_C O19707 Hybrid insulin peptide, MHC class II HLA-D X-ray 3.30 2020-06-08 89.31 0.89 0.10 ok
6XCO_B O19707 Hybrid Insulin Peptide, MHC class II HLA-D X-ray 2.90 2020-06-08 89.31 0.89 0.09 ok
7F1S_R P51681 C-C chemokine receptor type 5 EM 2.80 2021-06-09 85.38 0.89 0.09 ok
6XC9_C O19707 Hybrid Insulin Peptide, MHC class II HLA-D X-ray 2.40 2020-06-08 89.31 0.90 0.09 ok
7ENN_K Q86WJ1 Chromodomain-helicase-DNA-binding protein EM 2.80 2021-04-18 73.19 0.88 0.09 ok
7DRT_B Q5T9L3 Protein wntless homolog EM 2.20 2020-12-29 82.56 0.90 0.08 ok
7OKX_O Q96JC9 ELL-associated factor 1 EM 3.30 2021-05-18 70.75 0.89 0.08 ok
7OKY_O Q96JC9 ELL-associated factor 1 EM 4.14 2021-05-18 70.75 0.89 0.08 ok
7LEJ_A Q58F21 Bromodomain testis-specific protein X-ray 1.73 2021-01-14 62.44 0.88 0.07 ok
7EP2_A Q9C0D3 Protein zyg-11 homolog B X-ray 2.38 2021-04-26 92.31 0.93 0.06 ok
7E25_A O15540 Fatty acid-binding protein, brain X-ray 1.60 2021-02-04 96.31 0.94 0.06 ok
7E7E_A Q9BYF1 Processed angiotensin-converting enzyme 2 X-ray 3.80 2021-02-26 90.69 0.94 0.06 ok
7EA8_C P20671 Histone H2A type 1-D EM 3.10 2021-03-06 90.94 0.94 0.06 ok
7BV7_C Q9UL03 Integrator complex subunit 6 X-ray 2.40 2020-04-09 72.50 0.92 0.06 ok
7LW7_A Q9H790 Exonuclease V X-ray 2.50 2021-02-27 80.00 0.94 0.05 ok
7EP5_A Q7Z7L7 Protein zer-1 homolog X-ray 2.02 2021-04-26 90.81 0.94 0.05 ok
7EA8_A Q6PI79 Histone H3.3 EM 3.10 2021-03-06 85.81 0.95 0.05 ok
7LJ1_a Q9BYN0 Sulfiredoxin-1 X-ray 2.97 2021-01-28 83.69 0.95 0.05 ok
6XQ8_A Q15109 Advanced glycosylation end product-specifi X-ray 1.82 2020-07-09 82.81 0.95 0.04 ok
7EP1_A Q9C0D3 Protein zyg-11 homolog B X-ray 1.85 2021-04-26 92.31 0.95 0.04 ok
7EA8_L Q9BYW2 Histone-lysine N-methyltransferase SETD2 EM 3.10 2021-03-06 43.34 0.90 0.04 ok
7OL0_Z O00267 Transcription elongation factor SPT5 EM 3.00 2021-05-18 68.56 0.94 0.04 ok
7CJX_A P54855 UDP-glucuronosyltransferase 2B15 X-ray 1.99 2020-07-14 93.38 0.95 0.04 ok
7P1L_A P27448 MAP/microtubule affinity-regulating kinase X-ray 1.95 2021-07-01 68.25 0.94 0.04 ok
6XQ9_A Q15109 Advanced glycosylation end product-specifi X-ray 2.30 2020-07-09 82.81 0.96 0.04 ok
6XQ6_A Q15109 Advanced glycosylation end product-specifi X-ray 1.90 2020-07-09 82.81 0.96 0.04 ok
7DCU_A Q03933 Heat shock factor protein 2 X-ray 1.75 2020-10-27 59.47 0.94 0.03 ok
6XQ3_A Q15109 Advanced glycosylation end product-specifi X-ray 1.71 2020-07-09 82.81 0.96 0.03 ok
7KMF_J Q9NR50 Translation initiation factor eIF-2B subun EM 2.91 2020-11-02 72.56 0.95 0.03 ok
6XQ5_A Q15109 Advanced glycosylation end product-specifi X-ray 1.80 2020-07-09 82.81 0.96 0.03 ok
7EP0_A Q9C0D3 Protein zyg-11 homolog B X-ray 2.16 2021-04-26 92.31 0.96 0.03 ok
6ZLX_A Q9Y2S7 Polymerase delta-interacting protein 2 X-ray 3.39 2020-07-01 79.75 0.96 0.03 ok
6XQ1_A Q15109 Advanced glycosylation end product-specifi X-ray 1.51 2020-07-09 82.81 0.96 0.03 ok
6XQ7_A Q15109 Advanced glycosylation end product-specifi X-ray 1.80 2020-07-09 82.81 0.96 0.03 ok
7LEL_A Q58F21 Bromodomain testis-specific protein X-ray 2.15 2021-01-14 62.44 0.95 0.03 ok
7OKX_Z O00267 Transcription elongation factor SPT5 EM 3.30 2021-05-18 68.56 0.95 0.03 ok
7LEK_A Q58F21 Bromodomain testis-specific protein X-ray 2.75 2021-01-14 62.44 0.95 0.03 ok
7LAK_A P25440 Bromodomain-containing protein 2 X-ray 1.83 2021-01-06 64.06 0.95 0.03 ok
6XCP_A Q30069 MHC class II HLA-DQ-alpha chain X-ray 3.30 2020-06-08 91.56 0.97 0.03 ok
7JYQ_A O60674 Tyrosine-protein kinase JAK2 X-ray 1.86 2020-08-31 86.88 0.97 0.03 ok
7JYO_A O60674 Tyrosine-protein kinase JAK2 X-ray 2.16 2020-08-31 86.88 0.97 0.03 ok
7LWA_A Q9H790 Exonuclease V X-ray 2.85 2021-02-28 80.00 0.97 0.03 ok
6XS5_A Q9UBQ0 Vacuolar protein sorting-associated protei X-ray 2.01 2020-07-15 96.62 0.98 0.02 ok
7LBT_A Q15059 Bromodomain-containing protein 3 X-ray 2.70 2021-01-08 66.88 0.97 0.02 ok
7KMF_C P49770 Translation initiation factor eIF-2B subun EM 2.91 2020-11-02 86.56 0.97 0.02 ok
7MEZ_A P48736 Phosphatidylinositol 4,5-bisphosphate 3-ki EM 2.89 2021-04-08 87.81 0.98 0.02 ok
7CJB_C Q15369 Elongin-C X-ray 2.80 2020-07-09 89.81 0.98 0.02 ok
7EA8_D P06899 Histone H2B type 2-E EM 3.10 2021-03-06 85.50 0.98 0.02 ok
7LW8_A Q9H790 Exonuclease V X-ray 2.88 2021-02-28 80.00 0.97 0.02 ok
7OKY_Y P63272 Transcription elongation factor SPT4 EM 4.14 2021-05-18 96.50 0.98 0.02 ok
7EA8_B P62799 Histone H4 EM 3.10 2021-03-06 89.44 0.98 0.02 ok
7LAY_A Q15059 Bromodomain-containing protein 3 X-ray 1.45 2021-01-07 66.88 0.97 0.02 ok
7EP4_A Q7Z7L7 Protein zer-1 homolog X-ray 2.07 2021-04-26 90.81 0.98 0.02 ok
7CZD_B Q9NZQ7 Programmed cell death 1 ligand 1 X-ray 1.64 2020-09-08 88.25 0.98 0.02 ok
7LW9_A Q9H790 Exonuclease V X-ray 2.71 2021-02-28 80.00 0.98 0.02 ok
6XS7_A Q9UBQ0 Vacuolar protein sorting-associated protei X-ray 1.58 2020-07-15 96.62 0.98 0.02 ok
7EP3_A Q7Z7L7 Protein zer-1 homolog X-ray 1.51 2021-04-26 90.81 0.98 0.02 ok
7KMF_G Q14232 Translation initiation factor eIF-2B subun EM 2.91 2020-11-02 91.81 0.98 0.02 ok
6XCO_A Q30069 MHC class II HLA-DQ-alpha chain X-ray 2.90 2020-06-08 91.56 0.98 0.02 ok
7DCJ_A Q00613 Heat shock factor protein 1 X-ray 2.00 2020-10-26 61.31 0.97 0.02 ok
7DZD_U P00749 Urokinase-type plasminogen activator X-ray 2.00 2021-01-25 82.12 0.98 0.02 ok
7KMF_E Q9UI10 Translation initiation factor eIF-2B subun EM 2.91 2020-11-02 76.50 0.98 0.02 ok
7CJB_B Q15370 Elongin-B X-ray 2.80 2020-07-09 92.50 0.98 0.02 ok
6XC9_A Q30069 MHC class II HLA-DQ-alpha chain X-ray 2.40 2020-06-08 91.56 0.98 0.01 ok
7M2N_A P00338 L-lactate dehydrogenase A chain X-ray 2.50 2021-03-17 96.19 0.99 0.01 ok
7KMF_B Q13144 Translation initiation factor eIF-2B subun EM 2.91 2020-11-02 78.75 0.98 0.01 ok
6XSA_A Q9UBQ0 Vacuolar protein sorting-associated protei X-ray 1.83 2020-07-15 96.62 0.99 0.01 ok
7LAZ_A Q15059 Bromodomain-containing protein 3 X-ray 2.30 2021-01-07 66.88 0.98 0.01 ok
7LEM_A Q58F21 Bromodomain testis-specific protein X-ray 1.89 2021-01-14 62.44 0.98 0.01 ok
7DCI_A Q03933 Heat shock factor protein 2 X-ray 1.70 2020-10-26 59.47 0.98 0.01 ok
7F1R_B P62873 Guanine nucleotide-binding protein G(I)/G( EM 3.00 2021-06-09 97.06 0.99 0.01 ok
7F1Q_B P62873 Guanine nucleotide-binding protein G(I)/G( EM 2.90 2021-06-09 97.06 0.99 0.01 ok
7BV7_A Q68E01 Integrator complex subunit 3 X-ray 2.40 2020-04-09 83.06 0.99 0.01 ok
7F1S_B P62873 Guanine nucleotide-binding protein G(I)/G( EM 2.80 2021-06-09 97.06 0.99 0.01 ok
7M2O_A Q9UJM8 Hydroxyacid oxidase 1 X-ray 2.07 2021-03-17 94.56 0.99 0.01 ok
7LB4_A Q15059 Bromodomain-containing protein 3 X-ray 2.00 2021-01-07 66.88 0.99 0.01 ok
7DCT_A Q00613 Heat shock factor protein 1 X-ray 2.36 2020-10-27 61.31 0.99 0.01 ok
7DCS_A Q00613 Heat shock factor protein 1 X-ray 2.40 2020-10-27 61.31 0.99 0.01 ok
7OBP_A Q8NI08 NCOA7-AS X-ray 1.80 2021-04-23 55.62 0.99 0.01 ok
7OZ7_A Q6V1X1 Dipeptidyl peptidase 8 X-ray 2.60 2021-06-26 90.44 0.99 0.01 ok
7CJ2_A P36222 Chitinase 3-like 1 (Cartilage glycoprotein X-ray 2.70 2020-07-09 94.69 0.99 0.01 ok
7CJB_A P40337 von Hippel-Lindau disease tumor suppressor X-ray 2.80 2020-07-09 84.44 0.99 0.01 ok
7NC4_A P43166 Carbonic anhydrase 7 X-ray 1.60 2021-01-28 97.00 1.00 0.00 ok
7MYR_A P56817 Beta-secretase 1 X-ray 1.72 2021-05-21 87.50 1.00 0.00 ok
7MOT_A Q92769 Histone deacetylase 2 X-ray 1.54 2021-05-03 85.56 1.00 0.00 ok
7MOZ_A Q92769 Histone deacetylase 2 X-ray 1.54 2021-05-03 85.56 1.00 0.00 ok
7MOY_A Q92769 Histone deacetylase 2 X-ray 1.78 2021-05-03 85.56 1.00 0.00 ok
7MOX_A Q92769 Histone deacetylase 2 X-ray 1.69 2021-05-03 85.56 1.00 0.00 ok
7MOS_A Q92769 Histone deacetylase 2 X-ray 1.70 2021-05-03 85.56 1.00 0.00 ok

Click a column header to sort. FRAUD = confidence-weighted error; a structure is flagged confidently wrong when mean pLDDT > 70 yet TM-score < 0.5.