Tasks

Six tasks, each a single endpoint: POST /v1/tasks/{task}/predict (and the same six tools over MCP). Each accepts a DNA sequence (and a sequence_name label) and returns task-specific fields under data; meta is uniform across tasks. Request and response schemas — with copyable examples — are in ReDoc; per-task length caps and latency are in Limits.

Task	Input (bp)	Strand-sensitive	Output	Default model
Promoter	1–500,000	Yes (coding strand)	Promoter-region probabilities	g0-promoter-2000bp
Splice	1–500,000	No	Donor / acceptor sites	g0-splice-bigbird
Enhancer	50–500,000	Yes (dev/hk channels)	dev + hk activity scores	g0-deepstarr
Chromatin	1–500,000	No	919 features in 8 track groups	g0-deepsea
Expression	9,198 (TSS-centered)	Yes (coding strand)	Expression in log(TPM+1)	g0-expression
Annotation	1–500,000	Plus-strand input	Transcripts with type + exon/intron/CDS structure (GFF3); async	g0-annotation

Where a task is marked strand-sensitive, submit DNA 5'→3' on the gene's coding (sense) strand; for annotation, submit the plus-strand region.

Model selection

Each task has a default_model and may offer alternatives. List them with GET /v1/tasks/{task}/models (a flat object, not the {data, meta} envelope); pass a model's name in options.model to pick one. Beyond the default human models, promoter offers species-specific variants (Drosophila, yeast, Arabidopsis), and DNABERT k-mer variants exist for promoter, enhancer, and chromatin. The model-list endpoint is authoritative for what each task currently serves.

Promoter

Binary classification that detects promoter regions. The default g0-promoter-2000bp is a G0 BERT-Large encoder trained on human promoters from EPDnew. Inputs above 2,000 bp are scanned in windows automatically.

• options.threshold (0–1, default 0.5): probability cutoff for calling a window a promoter.
• Strand-sensitive — submit the coding (sense) strand.

Output: per-window promoter probabilities. Also BED and bedGraph (see output formats).

MCP: "Fetch a 100 kb window around human TP53 and scan it for promoter regions."

Splice

Token-level classification labeling each position as a splice acceptor (3' site), donor (5' site), or neither. The default g0-splice-bigbird is a G0 BigBird encoder trained on human splice sites from SpliceAI. Long inputs are scanned in a 15,000 bp sliding window; predictions are most reliable in the central region of each window.

• options.threshold (0–1, default 0.5): score cutoff for emitting a site.
• options.site_types: subset of ["donor", "acceptor"] (default both).

Output: detected acceptor and donor sites with scores. Also BED and GFF3 (see output formats).

MCP: "Fetch the human HBB gene sequence and predict its splice sites."

Enhancer

Regression predicting two scores per window: developmental (dev) and housekeeping (hk). The default g0-deepstarr is a G0 BERT-Base encoder trained on Drosophila enhancers from DeepSTARR. The sequence is split into consecutive, non-overlapping 249 bp windows, each scored independently.

The model is Drosophila-trained and strand-sensitive for the dev/hk channels — use a fly sequence on the gene's coding (sense) strand.

Output: per-window dev and hk scores, embedding bedGraph renderings of each track. bedGraph is also available directly (see output formats).

MCP: "Fetch the Drosophila ftz gene and predict enhancer activity."

Chromatin

Multi-label classification predicting 919 mammalian chromatin features (DeepSEA-style), grouped into eight categories (DNase, CTCF, Pol2, c-Myc, H3K27ac, H3K27me3, H3K4me1, Other). The default g0-deepsea is a G0 BERT-Base encoder trained on ENCODE data. The sequence is tiled into 1,000 bp windows stepping every 200 bp.

• options.threshold (0–1, default 0.5): only features scoring above this are returned.

Output: per-feature probabilities (above the threshold), grouped by category. Also BED (see output formats).

MCP: "Fetch the human HBB promoter region and predict its chromatin features."

Expression

Predicts gene expression from a DNA sequence plus an experimental-context description, on a log(TPM+1) scale. The default g0-expression is trained on ENCODE RNA-seq across cell types.

• sequence: DNA centered on the transcription start site. The model was trained on a 9,198 bp window (4,599 bp each side of the TSS); supply that for in-distribution results. 500–500,000 bp is accepted but truncated to the first ~1,024 tokens. Pre-center on the TSS on the gene's coding (sense) strand.
• options.description (required): free-text experimental context (cell type, assay, conditions). Omitting it returns 422 validation_failed.

Output: data.prediction = {expression, expression_log_tpm, expression_tpm, unit} — expression/expression_log_tpm are log(TPM+1); expression_tpm is the back-transformed linear value. JSON only (no text-track formats).

MCP: "Predict HBB expression in K562 cells."

Annotation

Gene finding over long DNA: detects transcripts and returns their intervals. The g0-annotation model (multispecies) predicts transcript boundaries, transcript type (mRNA / lnc_RNA), and full internal exon/intron/CDS structure, and emits a browser-ready GFF3 track. Submit the plus-strand genomic region; the model finds transcripts on both strands. This is the longest-running task — run it asynchronously (see Asynchronous jobs).

• model (optional): g0-annotation — the only annotation model, selected by default.
• options.batch_size (1–128): windows processed per batch.
• options.shift_coordinates: "UCSC": rebase output coordinates from a UCSC-style sequence_name (e.g. chr8:127,680,000-127,800,000).

Output: transcript intervals, each carrying its own strand (+/-) plus tss_position and polya_position. Each transcript additionally carries transcript_type, transcript_type_score, and 0-based half-open exons/introns/cds arrays, and data.formats.gff3 holds a full GFF3 track (also via Accept: text/x-gff3). BED is also available. See output formats.

MCP: "Find the genes in chr8:127,680,000-127,800,000."

---

Next: Limits for caps and latency, or the REST API guide for the call walkthrough.