Frequently asked questions
Can't find an answer? Email hello@foldfunc.xyz.
What sequence format is accepted?+
Single-letter amino acid format (e.g. MKTIIALSYIFCLVFA...). For batch mode, you can paste multiple sequences in FASTA format — each entry starts with a >Name header followed by the sequence on the next line. Spaces, newlines, and carriage returns inside a sequence are stripped automatically.
Which amino acids are valid?+
The 20 standard amino acids: A C D E F G H I K L M N P Q R S T V W Y. Non-standard residues (B, J, O, U, X, Z) will return a validation error. Selenocysteine (U) and pyrrolysine (O) are not supported.
What are the sequence length limits?+
Minimum 10 residues, maximum 2000 residues. Sequences above 800 residues may take longer to process — a warning is shown when this applies.
How does batch mode work?+
Switch to Batch in the analyzer, then paste up to 20 sequences in FASTA format (>Name on one line, sequence on the next). You can also upload a .fasta or .txt file. Results are ranked by pLDDT confidence — highest-confidence structures appear first.
How do I specify mutation positions?+
Enter a comma-separated list of integers using 1-based indexing — the first residue is position 1. Example: 14, 35, 52, 101. If left blank, foldfunc selects positions automatically across the sequence.
How accurate is the structure prediction?+
Our models can struggle with intrinsically disordered regions and multi-domain assemblies. The pLDDT score is your primary guide to per-region reliability.
What do negative mutation scores mean?+
Mutation scores are log-probabilities. A score near 0 means the wild-type amino acid is highly expected at that position. Increasingly negative scores indicate the residue is evolutionarily unusual — a signal the position is conserved and likely functionally critical. Click any position in the heatmap to expand all 20 amino acid scores and the top 5 suggested substitutions.
Why is my analysis taking a long time?+
Repeat analyses for known sequences return in 1–2 seconds from cache. For new sequences above 800 residues, or when the GPU inference server cold-starts, it can take 30–90 seconds. If analysis takes more than 3 minutes, try a shorter sequence or retry shortly after.
Are my sequences stored?+
Your raw sequence is never stored. We store a one-way SHA-256 hash of the sequence (which cannot be reversed to recover the original), along with the predicted structure, mutation scores, and AI interpretation in our prediction cache. This cache is what makes repeat analyses nearly instant. See the Privacy Policy for full details.
Can I use foldfunc for clinical or medical decisions?+
No. foldfunc is a research tool. Outputs are probabilistic and generated by machine learning models. They are not validated for clinical use and must not be used to inform medical, diagnostic, or therapeutic decisions.
What is the free tier limit?+
The free tier includes 20 analyses per month with no account required. Paid plans with higher limits are coming soon — see the Pricing page for details.
Something went wrong. What should I do?+
Check that your sequence contains only valid amino acids and is within the length limits. For batch mode, make sure each entry follows FASTA format (>Name then sequence). For persistent issues, contact us at hello@foldfunc.xyz with a description of what you submitted.