Release week 2023-01-11

Jump to:

structures analysed (5 full · 5.6%)

00.0%

confidently wrong

11.1%

novel sequences

00.0%

novel & wrong

0.975

median TM-score

⭐ This week's notable releases

1 novel sequence, 0 confidently wrong. Highlight: Melanocortin-2 receptor accessory protein.

PDB	Protein	Flags	Why it matters
8GY7_P ↗	Melanocortin-2 receptor accessory protein	novel · 100%	Genuinely unseen sequence (0% identity to anything AlphaFold trained on).

see all 89 structures ↓

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

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: 0 of 89 structures (0.0%) are confidently wrong; median TM-score is 0.975.

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 0.975 — 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

PDB	UniProt	Protein	Method	Å	Deposited	Novelty %	pLDDT	TM	lDDT	GDT_TS	RMSD	FRAUD	Flag
7TZO_G	Q9BPZ7	Target of rapamycin complex 2 subunit MAPK	EM	3.28	2022-02-16	0.00	67.42	0.35	0.72	0.00	25.35	0.66	ok
8BYN_A	P10636	Microtubule-associated protein tau	EM	2.60	2022-12-13	0.00	67.98	0.26	0.46	0.67	24.11	0.65	ok
8BAH_C	O60934	Nibrin	EM	4.13	2022-10-11	48.20	56.23	0.27	0.62	2.59	20.52	0.52	ok
8GY7_P	Q8TCY5	Melanocortin-2 receptor accessory protein	EM	3.30	2022-09-21	100.00 novel	76.18	0.53	0.77	25.00	7.91	0.33	ok
8E40_C	Q13951	Core-binding factor subunit beta	EM	3.57	2022-08-17	0.00	89.41	0.65	0.65	38.78	5.87	0.28	ok
8EFH_O	P09493	Tropomyosin alpha-1 chain	EM	3.30	2022-09-08	—	91.62	0.72	—	—	—	0.26	ok
8HGG_C	Q13219	Pappalysin-1	EM	3.64	2022-11-14	—	79.38	0.72	—	—	—	0.22	ok
8EFD_A	P12883	Beta-cardiac myosin II	EM	3.80	2022-09-08	—	74.25	0.81	—	—	—	0.14	ok
7WJQ_B	Q8TAX9	Isoform 2 of Gasdermin-B	X-ray	2.70	2022-01-07	—	71.56	0.84	—	—	—	0.11	ok
8EFE_A	P12883	Beta-cardiac myosin II	EM	3.80	2022-09-08	—	74.25	0.85	—	—	—	0.11	ok
7TZO_A	P42345	Serine/threonine-protein kinase mTOR	EM	3.28	2022-02-16	—	78.00	0.86	—	—	—	0.11	ok
8EFH_A	P12883	beta-cardiac myosin II	EM	3.30	2022-09-08	—	74.25	0.86	—	—	—	0.10	ok
8ASY_B	P0DTC2	Spike protein S1	X-ray	2.85	2022-08-22	—	67.14	0.86	—	—	—	0.09	ok
8BHT_A	Q9UNQ0	Broad substrate specificity ATP-binding ca	EM	3.10	2022-10-31	—	85.25	0.91	—	—	—	0.07	ok
7TCY_A	Q13470	Non-receptor tyrosine-protein kinase TNK1	X-ray	1.54	2021-12-29	—	72.44	0.91	—	—	—	0.07	ok
8CZF_A	Q16611	Bcl-2 homologous antagonist/killer	X-ray	1.30	2022-05-24	—	81.31	0.92	—	—	—	0.07	ok
8GY7_G	P59768	Guanine nucleotide-binding protein G(I)/G(	EM	3.30	2022-09-21	—	89.56	0.93	—	—	—	0.06	ok
8CZH_A	Q16611	Bcl-2 homologous antagonist/killer	X-ray	1.30	2022-05-24	—	81.31	0.93	—	—	—	0.06	ok
7TZO_C	Q9BVC4	Target of rapamycin complex subunit LST8	EM	3.28	2022-02-16	—	91.62	0.94	—	—	—	0.06	ok
7QO1_Y	P39748	Flap endonuclease 1	EM	4.40	2021-12-23	—	89.62	0.94	—	—	—	0.06	ok
8F9Z_A	A0A0M3KKW8	HIV-1 gp120 core	X-ray	1.94	2022-11-25	—	83.25	0.94	—	—	—	0.05	ok
8D58_B	P57081	tRNA (guanine-N(7)-)-methyltransferase non	X-ray	2.47	2022-06-04	—	86.50	0.95	—	—	—	0.05	ok
8EG0_B	P57081	tRNA (guanine-N(7)-)-methyltransferase non	EM	3.53	2022-09-10	—	86.50	0.95	—	—	—	0.05	ok
7ZTD_A	P60709	actin, cytoplasmic 1	EM	4.60	2022-05-09	—	95.19	0.95	—	—	—	0.05	ok
8BI0_A	Q9UNQ0	Broad substrate specificity ATP-binding ca	EM	3.20	2022-11-01	—	85.25	0.95	—	—	—	0.04	ok
8B8T_A	P18858	DNA ligase 1	EM	4.20	2022-10-05	—	76.75	0.94	—	—	—	0.04	ok
8HGG_A	P13727	Bone marrow proteoglycan	EM	3.64	2022-11-14	—	75.94	0.94	—	—	—	0.04	ok
7Y5Q_C	O76061	Stanniocalcin-2	EM	3.80	2022-06-17	—	73.00	0.94	—	—	—	0.04	ok
8HGH_C	O76061	Stanniocalcin-2	EM	4.16	2022-11-14	—	73.00	0.94	—	—	—	0.04	ok
8DKB_A	O95619	YEATS domain-containing protein 4	X-ray	2.58	2022-07-05	—	91.56	0.95	—	—	—	0.04	ok
8FA0_A	A0A0M3KKW8	HIV-1 gp120 core	X-ray	2.09	2022-11-25	—	83.25	0.95	—	—	—	0.04	ok
8CZG_A	Q16611	Bcl-2 homologous antagonist/killer	X-ray	1.99	2022-05-24	—	81.31	0.95	—	—	—	0.04	ok
7ZTC_A	P60709	actin, cytoplasmic 1	EM	3.90	2022-05-09	—	95.19	0.96	—	—	—	0.04	ok
7Y5N_A	P13727	Bone marrow proteoglycan	EM	3.45	2022-06-17	—	75.94	0.95	—	—	—	0.04	ok
7TZO_E	Q6R327	Rapamycin-insensitive companion of mTOR	EM	3.28	2022-02-16	—	65.94	0.94	—	—	—	0.04	ok
7UW0_A	Q16740	ATP-dependent Clp protease proteolytic sub	X-ray	2.80	2022-05-02	—	82.31	0.96	—	—	—	0.04	ok
7XBH_A	Q9BYF1	Processed angiotensin-converting enzyme 2	X-ray	3.02	2022-03-21	—	90.69	0.96	—	—	—	0.03	ok
8D9K_A	Q9UBP6	tRNA (guanine-N(7)-)-methyltransferase	EM	3.72	2022-06-10	—	88.06	0.96	—	—	—	0.03	ok
7UVN_A	Q16740	ATP-dependent Clp protease proteolytic sub	X-ray	3.11	2022-05-02	—	82.31	0.97	—	—	—	0.03	ok
7Y5N_C	Q13219	Pappalysin-1	EM	3.45	2022-06-17	—	79.38	0.97	—	—	—	0.03	ok
8D9L_A	Q9UBP6	tRNA (guanine-N(7)-)-methyltransferase	EM	4.04	2022-06-10	—	88.06	0.97	—	—	—	0.03	ok
8D58_A	Q9UBP6	tRNA (guanine-N(7)-)-methyltransferase	X-ray	2.47	2022-06-04	—	88.06	0.97	—	—	—	0.03	ok
7QO1_B	P12004	Proliferating cell nuclear antigen	EM	4.40	2021-12-23	—	94.31	0.98	—	—	—	0.02	ok
8ASY_A	Q9BYF1	Processed angiotensin-converting enzyme 2	X-ray	2.85	2022-08-22	—	90.69	0.97	—	—	—	0.02	ok
7RB3_A	Q147X3	N-alpha-acetyltransferase 30	EM	3.10	2021-07-05	—	63.22	0.96	—	—	—	0.02	ok
7UVU_A	Q16740	ATP-dependent Clp protease proteolytic sub	X-ray	3.24	2022-05-02	—	82.31	0.97	—	—	—	0.02	ok
7XBG_A	Q9BYF1	Processed angiotensin-converting enzyme 2	X-ray	3.37	2022-03-21	—	90.69	0.98	—	—	—	0.02	ok
8B8T_E	P12004	Proliferating cell nuclear antigen	EM	4.20	2022-10-05	—	94.31	0.98	—	—	—	0.02	ok
7UVR_A	Q16740	ATP-dependent Clp protease proteolytic sub	X-ray	2.86	2022-05-02	—	82.31	0.97	—	—	—	0.02	ok
8D9L_B	P57081	tRNA (guanine-N(7)-)-methyltransferase non	EM	4.04	2022-06-10	—	86.50	0.98	—	—	—	0.02	ok
7XBF_A	Q9BYF1	Processed angiotensin-converting enzyme 2	X-ray	3.51	2022-03-21	—	90.69	0.98	—	—	—	0.02	ok
7UVM_A	Q16740	ATP-dependent Clp protease proteolytic sub	X-ray	2.19	2022-05-02	—	82.31	0.98	—	—	—	0.02	ok
7QO1_A	P18858	DNA ligase 1	EM	4.40	2021-12-23	—	76.75	0.98	—	—	—	0.02	ok
7QNZ_B	P12004	Proliferating cell nuclear antigen	EM	4.58	2021-12-23	—	94.31	0.98	—	—	—	0.02	ok
7XAC_A	P47929	Galectin-7	X-ray	1.80	2022-03-17	—	96.62	0.98	—	—	—	0.02	ok
8BAH_A	P49959	Double-strand break repair protein MRE11	EM	4.13	2022-10-11	—	75.38	0.98	—	—	—	0.02	ok
8D9K_B	P57081	tRNA (guanine-N(7)-)-methyltransferase non	EM	3.72	2022-06-10	—	86.50	0.98	—	—	—	0.02	ok
8B5B_A	O60885	Bromodomain-containing protein 4	X-ray	1.92	2022-09-22	—	55.31	0.97	—	—	—	0.01	ok
8D59_A	Q9UBP6	tRNA (guanine-N(7)-)-methyltransferase	X-ray	2.26	2022-06-04	—	88.06	0.98	—	—	—	0.01	ok
8EG0_A	Q9UBP6	tRNA (guanine-N(7)-)-methyltransferase	EM	3.53	2022-09-10	—	88.06	0.98	—	—	—	0.01	ok
7QNZ_A	P18858	DNA ligase 1	EM	4.58	2021-12-23	—	76.75	0.98	—	—	—	0.01	ok
8HMQ_A	P14618	Pyruvate kinase PKM	X-ray	2.50	2022-12-05	—	96.81	0.99	—	—	—	0.01	ok
8B5C_A	O60885	Bromodomain-containing protein 4	X-ray	1.58	2022-09-22	—	55.31	0.98	—	—	—	0.01	ok
8D5B_A	Q9UBP6	tRNA (guanine-N(7)-)-methyltransferase	X-ray	1.93	2022-06-04	—	88.06	0.99	—	—	—	0.01	ok
8GZC_A	Q09472	Histone acetyltransferase p300	X-ray	2.00	2022-09-26	—	53.25	0.98	—	—	—	0.01	ok
8GY7_B	P62873	Guanine nucleotide-binding protein G(I)/G(	EM	3.30	2022-09-21	—	97.06	0.99	—	—	—	0.01	ok
7XBL_A	P47929	Galectin-7	X-ray	2.00	2022-03-21	—	96.62	0.99	—	—	—	0.01	ok
7UIH_A	Q13200	26S proteasome non-ATPase regulatory subun	EM	3.10	2022-03-29	—	65.06	0.99	—	—	—	0.01	ok
7UJD_A	Q13200	26S proteasome non-ATPase regulatory subun	EM	2.50	2022-03-30	—	65.06	0.99	—	—	—	0.01	ok
7RB3_B	Q5VZE5	N-alpha-acetyltransferase 35, NatC auxilia	EM	3.10	2021-07-05	—	89.75	0.99	—	—	—	0.01	ok
8HMS_A	P14618	Pyruvate kinase PKM	X-ray	2.10	2022-12-05	—	96.81	0.99	—	—	—	0.01	ok
8B5A_A	Q15059	Bromodomain-containing protein 3	X-ray	1.92	2022-09-22	—	66.88	0.99	—	—	—	0.01	ok
7SKD_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.71	2021-10-20	—	78.94	0.99	—	—	—	0.01	ok
7SJW_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.38	2021-10-19	—	78.94	0.99	—	—	—	0.01	ok
7SJT_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.54	2021-10-19	—	78.94	0.99	—	—	—	0.01	ok
7SIB_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.78	2021-10-13	—	78.94	0.99	—	—	—	0.01	ok
7S3P_A	Q15059	Bromodomain-containing protein 3	X-ray	2.89	2021-09-07	—	66.88	0.99	—	—	—	0.00	ok
7SJV_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.39	2021-10-19	—	78.94	0.99	—	—	—	0.00	ok
7T8D_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.38	2021-12-16	—	78.94	0.99	—	—	—	0.00	ok
7SKG_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.33	2021-10-20	—	78.94	0.99	—	—	—	0.00	ok
7SKF_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.28	2021-10-20	—	78.94	0.99	—	—	—	0.00	ok
7SJU_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.39	2021-10-19	—	78.94	0.99	—	—	—	0.00	ok
7SIJ_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.54	2021-10-14	—	78.94	0.99	—	—	—	0.00	ok
7SKE_A	Q99972	Myocilin, C-terminal fragment	X-ray	1.24	2021-10-20	—	78.94	0.99	—	—	—	0.00	ok
8HMU_A	P14618	Pyruvate kinase PKM	X-ray	2.50	2022-12-05	—	96.81	1.00	—	—	—	0.00	ok
8F49_A	P02794	Ferritin heavy chain	EM	1.80	2022-11-10	—	95.31	1.00	—	—	—	0.00	ok
8HMR_A	P14618	Pyruvate kinase PKM	X-ray	2.60	2022-12-05	—	96.81	1.00	—	—	—	0.00	ok
8F1G_A	P61964	WD repeat-containing protein 5	X-ray	2.14	2022-11-05	—	93.31	1.00	—	—	—	0.00	ok
8E9F_A	P61964	WD repeat-containing protein 5	X-ray	1.55	2022-08-26	—	93.31	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.