khushi singh.in

Tools · AlphaFold

AlphaFold explorer

Open any protein’s predicted structure from AlphaFold, check how confident the prediction is, and save figures for a paper or poster.

1 Choose a protein

Data load live from AlphaFold DB and UniProt (EMBL-EBI) in your browser. Nothing is contacted until you pick or search. What is shared

  • Related story
  • Related story
  • Related story
  • Related story
  • Related story
  • Related story
  • Related story
  • Related story
  • Related story
  • Related story

Pick a protein above to open its dashboard.

↔ Compare two proteins

Fly and human cousins

Most human disease genes have a fly counterpart. Align two proteins, lay one AlphaFold model on top of the other and see how much of the shape has survived since their lineages split. Everything is computed on this device.

A not chosen

B not chosen

3 Try the API yourself

The same public endpoints this page uses. Send a request, inspect the answer, then copy the code into your own notebook.

Model metadata for one UniProt accession: confidence summary, sequence and links to the model, PAE and confidence files.

GET Enter a valid value to build the URL

Use it in your own code

import requests

r = requests.get("https://alphafold.ebi.ac.uk/api/prediction/P42212", timeout=30)
r.raise_for_status()
data = r.json()
entry = data[0]
print(entry["uniprotDescription"], "mean pLDDT", entry["globalMetricValue"])

Recipe: confidence table for any protein (Python)

# Per-residue confidence for P42212 from AlphaFold DB, saved as CSV
import csv, requests

acc = "P42212"
meta = requests.get(f"https://alphafold.ebi.ac.uk/api/prediction/{acc}", timeout=30).json()[0]
pdb = requests.get(meta["pdbUrl"], timeout=60).text

rows = [(int(l[22:26]), l[17:20], float(l[60:66]))           # residue number, name, pLDDT (B-factor)
        for l in pdb.splitlines() if l.startswith("ATOM") and l[12:16].strip() == "CA"]
with open(f"{acc}_plddt.csv", "w", newline="") as f:
    csv.writer(f).writerows([("residue", "name", "plddt"), *rows])

mean = sum(p for *_, p in rows) / len(rows)
print(f"{meta['uniprotDescription']}: {len(rows)} residues, mean pLDDT {mean:.1f}")

How to read it

  • pLDDT (0–100) is AlphaFold’s confidence for each residue. Above 90 is very confident; below 50 often marks a floppy, disordered region (Jumper et al. 2021; Ruff & Pappu 2021). Established
  • PAE shows how sure AlphaFold is about where two parts sit relative to each other. Dark blocks on the diagonal are domains; pale squares between them are flexible hinges.
  • Mutation scan: a protein language model (ESM-2) running on your device guesses which single changes the protein would tolerate (Lin et al. 2023). For human proteins it can be compared with AlphaMissense and reported variants (Cheng et al. 2023). Predictions only, never clinical advice.
  • Against experiment: lay a measured structure from the PDB over the prediction and see where they differ, residue by residue (TM-score; Zhang & Skolnick 2004).
  • Figures: every chart saves as editable SVG or 300/600 dpi PNG, and charts can be combined into one labelled figure. Methods and caveats for each chart are under “In detail”.
Methods and references (39)

References

  1. Jumper J, et al. 2021. Highly accurate protein structure prediction with AlphaFold. Nature 596:583–589. doi:10.1038/s41586-021-03819-2
  2. Varadi M, et al. 2024. AlphaFold Protein Structure Database in 2024: providing structure coverage for over 214 million protein sequences. Nucleic Acids Research 52:D368–D375. doi:10.1093/nar/gkad1011
  3. Tunyasuvunakool K, et al. 2021. Highly accurate protein structure prediction for the human proteome. Nature 596:590–596. doi:10.1038/s41586-021-03828-1
  4. Ruff KM, Pappu RV. 2021. AlphaFold and implications for intrinsically disordered proteins. Journal of Molecular Biology 433:167208. doi:10.1016/j.jmb.2021.167208
  5. The UniProt Consortium. 2025. UniProt: the Universal Protein Knowledgebase in 2025. Nucleic Acids Research 53:D609–D617. doi:10.1093/nar/gkae1010
  6. Kyte J, Doolittle RF. 1982. A simple method for displaying the hydropathic character of a protein. Journal of Molecular Biology 157:105–132. doi:10.1016/0022-2836(82)90515-0
  7. Pace CN, et al. 1995. How to measure and predict the molar absorption coefficient of a protein. Protein Science 4:2411–2423. doi:10.1002/pro.5560041120
  8. Ikai A. 1980. Thermostability and aliphatic index of globular proteins. Journal of Biochemistry 88:1895–1898. doi:10.1093/oxfordjournals.jbchem.a133168
  9. Lin Z, et al. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model (ESM-2). Science 379:1123–1130. doi:10.1126/science.ade2574
  10. Meier J, et al. 2021. Language models enable zero-shot prediction of the effects of mutations on protein function. bioRxiv (NeurIPS 2021). doi:10.1101/2021.07.09.450648
  11. Needleman SB, Wunsch CD. 1970. A general method applicable to the search for similarities in the amino acid sequence of two proteins. Journal of Molecular Biology 48:443–453. doi:10.1016/0022-2836(70)90057-4
  12. Gotoh O. 1982. An improved algorithm for matching biological sequences. Journal of Molecular Biology 162:705–708. doi:10.1016/0022-2836(82)90398-9
  13. Henikoff S, Henikoff JG. 1992. Amino acid substitution matrices from protein blocks (BLOSUM). PNAS 89:10915–10919. doi:10.1073/pnas.89.22.10915
  14. Kabsch W. 1976. A solution for the best rotation to relate two sets of vectors. Acta Crystallographica A 32:922–923. doi:10.1107/S0567739476001873
  15. Horn BKP. 1987. Closed-form solution of absolute orientation using unit quaternions. Journal of the Optical Society of America A 4:629–642. doi:10.1364/JOSAA.4.000629
  16. Zhang Y, Skolnick J. 2004. Scoring function for automated assessment of protein structure template quality (TM-score). Proteins 57:702–710. doi:10.1002/prot.20264
  17. Xu J, Zhang Y. 2010. How significant is a protein structure similarity with TM-score = 0.5? Bioinformatics 26:889–895. doi:10.1093/bioinformatics/btq066
  18. Abramson J, et al. 2024. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630:493–500. doi:10.1038/s41586-024-07487-w
  19. Evans R, et al. 2021. Protein complex prediction with AlphaFold-Multimer. bioRxiv. doi:10.1101/2021.10.04.463034
  20. Mirdita M, et al. 2022. ColabFold: making protein folding accessible to all. Nature Methods 19:679–682. doi:10.1038/s41592-022-01488-1
  21. Ahdritz G, et al. 2024. OpenFold: retraining AlphaFold2 yields new insights into its learning mechanisms and capacity for generalization. Nature Methods 21:1514–1524. doi:10.1038/s41592-024-02272-z
  22. Bryant P, Pozzati G, Elofsson A. 2022. Improved prediction of protein–protein interactions using AlphaFold2 (pDockQ). Nature Communications 13:1265. doi:10.1038/s41467-022-28865-w
  23. Zhu W, et al. 2023. Evaluation of AlphaFold-Multimer prediction on multi-chain protein complexes (pDockQ2). Bioinformatics 39:btad424. doi:10.1093/bioinformatics/btad424
  24. Dunbrack RL. 2025. Rēs ipSAE loquuntur: what’s wrong with AlphaFold’s ipTM score and how to fix it. bioRxiv. doi:10.1101/2025.02.10.637595
  25. Kim AR, et al. 2024. Enhanced protein–protein interaction discovery via AlphaFold-Multimer (LIS). bioRxiv. doi:10.1101/2024.02.19.580970
  26. Blondel VD, et al. 2008. Fast unfolding of communities in large networks (the Louvain method). Journal of Statistical Mechanics P10008. doi:10.1088/1742-5468/2008/10/P10008
  27. Shrake A, Rupley JA. 1973. Environment and exposure to solvent of protein atoms. Lysozyme and insulin. Journal of Molecular Biology 79:351–371. doi:10.1016/0022-2836(73)90011-9
  28. Tien MZ, et al. 2013. Maximum allowed solvent accessibilites of residues in proteins. PLoS ONE 8:e80635. doi:10.1371/journal.pone.0080635
  29. Ramachandran GN, Ramakrishnan C, Sasisekharan V. 1963. Stereochemistry of polypeptide chain configurations. Journal of Molecular Biology 7:95–99. doi:10.1016/S0022-2836(63)80023-6
  30. Lovell SC, et al. 2003. Structure validation by Cα geometry: ϕ, ψ and Cβ deviation. Proteins 50:437–450. doi:10.1002/prot.10286
  31. Armstrong DR, et al. 2020. PDBe: improved findability of macromolecular structure data in the PDB. Nucleic Acids Research 48:D335–D343. doi:10.1093/nar/gkz990
  32. Dana JM, et al. 2019. SIFTS: updated Structure Integration with Function, Taxonomy and Sequences resource. Nucleic Acids Research 47:D482–D489. doi:10.1093/nar/gky1114
  33. Cheng J, et al. 2023. Accurate proteome-wide missense variant effect prediction with AlphaMissense. Science 381:eadg7492. doi:10.1126/science.adg7492
  34. Nightingale A, et al. 2017. The Proteins API: accessing key integrated protein and genome information. Nucleic Acids Research 45:W539–W544. doi:10.1093/nar/gkx237
  35. Landrum MJ, et al. 2018. ClinVar: improving access to variant interpretations and supporting evidence. Nucleic Acids Research 46:D1062–D1067. doi:10.1093/nar/gkx1153
  36. Uversky VN, Gillespie JR, Fink AL. 2000. Why are “natively unfolded” proteins unstructured under physiologic conditions? Proteins 41:415–427. doi:10.1002/1097-0134(20001115)41:3<415::AID-PROT130>3.0.CO;2-7
  37. Das RK, Pappu RV. 2013. Conformations of intrinsically disordered proteins are influenced by linear sequence distributions of oppositely charged residues. PNAS 110:13392–13397. doi:10.1073/pnas.1304749110
  38. Wootton JC, Federhen S. 1993. Statistics of local complexity in amino acid sequences and sequence databases. Computers & Chemistry 17:149–163. doi:10.1016/0097-8485(93)85006-X
  39. Martin EW, et al. 2020. Valence and patterning of aromatic residues determine the phase behavior of prion-like domains. Science 367:694–699. doi:10.1126/science.aaw8653