Prepare scientific figures for papers, reports, and saved deliverables by checking data fidelity, chart choice, labels, axes, and color consistency. Verify exported figures for overlapping text and readability while keeping fonts, palettes, and framing configurable.
Use scGPT to convert single-cell gene expression data into numerical representations of cells and genes. These representations support clustering, data integration, cell-type annotation, and analyses of gene perturbations or regulatory relationships.
Create a multi-panel research figure from a clear claim and fixed data references, or start from an existing figure. Plan the layout, coordinate panel creation, inspect the composite, and revise affected panels through independent review.
Review a paper’s complete figure set against its manuscript and captions. Develop a supported central claim, propose figure ordering and content changes, and pass human-reviewed revisions to figure-composer while preserving figures that need no changes.
Predict structures of complexes containing proteins, DNA, RNA, and ligands with OpenFold3, an AlphaFold3 reproduction with publicly available model weights. Prepare JSON inputs, generate candidate structures, and inspect confidence scores and molecular clashes.
Build a structured research dossier for a defined patient population, covering epidemiology, disease biology, current treatment, regulatory precedents, and major clinical trials. Receive a cited report and structured data to inform therapeutic development and trial planning.
Create and manage focused Specialist agents and Skills through conversation. Draft agent roles, review available Skills and Connectors, configure access, and manage changes, with Skill creation and publishing handled by the application's internal skill-creator.
Convert protein sequences into numerical features with Meta AI's ESM-2 for machine learning. Extract features for individual amino acids or whole sequences, score mutations, and predict which positions in a protein may contact each other.
Turn a recurring task into a reusable Open-Science Skill, or revise an existing one. Guide package creation, optional testing, improvements to when the Skill activates, and publication after the user reviews and accepts the draft.
Predict patterns of gene expression and other genomic measurements from DNA sequences with Borzoi. Compare reference and altered sequences to estimate regulatory effects, generate predicted coverage tracks, and prioritize variants in regions that do not encode proteins.
Design amino acid sequences from a protein backbone stored in a PDB file using ProteinMPNN. Generate multiple candidates, redesign selected chains while preserving specified residues, and vary sampling settings to prepare sequences for downstream structure prediction.
Run demanding scientific work on SSH compute hosts using direct execution or Slurm, a cluster job scheduler. Choose an enabled host, submit background jobs, check progress, collect outputs, and continue with analysis and artifact publication.
Predict structures for single proteins or protein complexes with AlphaFold2 through ColabFold. Use confidence scores and comparisons with a designed structure to assess whether a designed sequence folds as intended.
Predict structures of protein, nucleic acid, and small-molecule complexes with ESMFold2, using single sequences or aligned related sequences. The skill also covers ESMC models for numerical sequence representations, mutation scoring, and predictions of contacts between residues.
Prepare reproducible setup and removal instructions for software environments on Open-Science SSH hosts, including Slurm clusters. Check available tools, define named activation settings, and validate the environment where jobs run after the user installs it.
Design amino acid sequences from a protein backbone using SolubleMPNN, a model trained on soluble protein structures. Generate candidates with a solubility bias for redesigning aggregation-prone proteins or preparing an E. coli expression screen.
Predict how a small molecule may sit within a protein using structural inputs. Generate ranked 3D poses without defining a search region, then use those poses as starting points for further evaluation.
Use Evo 2 to score DNA sequences, turn genomic regions into numerical representations for classification, and generate sequences from a supplied prefix. Compare reference and variant sequences or assess coding and regulatory regions across species.
Design protein sequences while accounting for bound small molecules, nucleic acids, or metals. Use LigandMPNN to redesign binding pockets or metal-coordinating sites, and export sequence files alongside PDB structures with the designed sequences applied.
Inspect available APIs in Open-Science and find files, session status, and agent conversations within the current project. Check which host features are available before using them, and trace the inputs behind generated file versions.
Use Boltz-2 to predict structures of complexes containing proteins, DNA, RNA, and small molecules. Obtain structure files and confidence scores to assess designed binders, with optional predictions of binding strength between a protein and a small molecule.
Manage Python and R packages for notebook work. Resolve missing-package errors, check installed versions, install into the selected runtime, and restart the kernel when needed, with guidance on using separate environments for different dependency requirements.
Analyze single-cell RNA sequencing data with scVI and scANVI. Combine experimental batches while correcting technical differences, produce compact cell features for clustering, assign cell types using reference labels, and assess differences in gene expression between groups.
Predict three-dimensional structures of complexes containing proteins, RNA, DNA, and small molecules with Chai-1. Compare candidate structures using confidence scores and clash indicators, or run repeated predictions from Python to evaluate designed binders.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)