Research & Learning skills

Turn observations or preliminary findings into testable research plans. The skill separates candidate hypotheses from evidence, develops competing explanations and distinguishing predictions, and helps specify measurements and analysis plans for preregistration, a research plan recorded before testing.

• Turn an observation into testable research hypotheses
• Compare competing explanations and distinguishing predictions
• Define measurements and review an analysis plan

Calculate seawater carbonate chemistry from two independent measurements using PyCO2SYS. Produce pH, carbonate species, and mineral saturation results, convert laboratory conditions to ocean conditions, and propagate measurement uncertainty while recording calculation assumptions.

• Calculate carbonate chemistry from paired seawater measurements
• Assess aragonite and calcite saturation
• Convert laboratory results to ocean temperature and pressure

Organize research sources in self-hosted Open Notebook, then search them, ask questions with citations, create notes, transform text, or generate podcasts with multiple speakers. Supports REST API automation and configuration of local or cloud AI providers.

• Collect PDFs and web sources in a research notebook
• Ask questions about selected sources with citations
• Apply custom summaries and text transformations

Plan and write literature reviews using multiple scholarly databases. Document searches, screen papers, synthesize findings, and check citations, then prepare Markdown or PDF reports with transparent selection counts, evidence limitations, and reproducible search records.

• Prepare a literature review for a thesis or research paper
• Record reproducible searches across scholarly databases
• Track screening decisions and exclusion reasons

Plan experiments before collecting data. Helps choose study designs, randomly assign subjects or samples, organize treatment combinations, and generate reproducible schedules while checking for confounding and repeated measurements incorrectly counted as independent samples.

• Create random assignments for subjects or samples
• Screen multiple experimental factors
• Balance conditions across batches, days, or plate positions

Plan and review fluid simulations with FluidSim, from solver selection and resource estimates to output analysis and restart checks. Examine numerical accuracy through grid and time-step comparisons, conservation checks, and explicit limits on computing resources.

• Selecting a solver and reviewing simulation parameters
• Estimating memory, disk space, and runtime needs
• Inspecting spectra and conservation budgets

Retrieve public evidence and linked publications for a supported genetic variant, or look up gene–disease relationships. Preserve sources, conflicting assertions, and explicit search outcomes so qualified professionals can review the findings.

• Review public evidence for a single genetic variant
• Find publications linked to a resolved variant
• Look up gene–disease relationships

Simulate a uniform gas mixture in a closed, insulated reactor at constant volume or pressure. Calculate ignition delay from the peak temperature rise rate, export temperature and species histories, and check conservation and numerical stability.

• Calculate ignition delay at constant volume or pressure
• Inspect temperature and species histories
• Compare ignition delays across reaction mechanisms

Generate candidate positions and orientations for small molecules binding to proteins with DiffDock and DiffDock-L. Prepare single or batch docking runs, organize predicted poses by model confidence, and review validation needs without treating confidence as binding affinity.

• Predicting binding poses for a protein and small molecule
• Preparing and validating batch docking inputs
• Comparing poses across receptor conformations

Plan protein characterization experiments with Adaptyv's cloud laboratory, estimate costs, submit sequences, track progress, and retrieve measured results. Supports binding, thermal stability, expression, fluorescence, and enzyme activity workflows through the API and Python SDK.

• Plan binding screens for candidate protein sequences
• Estimate experiment costs before submission
• Track laboratory progress and retrieve results

Use COBRApy to model metabolic networks and calculate possible reaction flows under defined constraints. Compare gene knockouts, nutrient conditions, and production limits, while checking model validity and keeping computational predictions separate from experimental findings.

• Calculating metabolic reaction flows and their possible ranges
• Comparing predicted effects of gene knockouts
• Exploring minimal media and production limits

Process next-generation sequencing data with deepTools: convert alignment files into coverage tracks, normalize signals, compare samples, and check quality. Create heatmaps and profiles around genes or peak regions for ChIP-seq, RNA-seq, and ATAC-seq experiments.

• Converting BAM files to normalized bigWig tracks
• Checking sequencing quality and replicate agreement
• Plotting heatmaps around transcription start sites

Investigate how DNA variants may affect gene activity using precomputed AlphaGenome Atlas results and model predictions. Rank candidate variants, examine tissue-specific effects, and inspect the features behind scores to develop research hypotheses about biological mechanisms.

• Ranking candidate variants from a VCF
• Examining tissue-specific effects on gene activity
• Comparing reference and altered DNA predictions

Find academic papers, verify authors and publication details, and create BibTeX entries, a structured format for references. Use it to organize bibliographies, remove duplicates, and check missing fields or mismatches with a manuscript.

• Find papers across multiple academic databases
• Convert DOIs into BibTeX references
• Remove duplicate bibliography entries

Prepare and check research documents for clinical decision-support evaluation, including evidence profiles, cohort tables, survival plans, and model assessments. Work with aggregate or synthetic inputs, record sources and review status, and keep outputs outside patient care.

• Preparing research model evaluation documents
• Checking evidence profiles and source links
• Reviewing survival analysis plans

Analyze existing evolutionary trees and other hierarchical trees with ETE 4. Edit branches, add annotations, compare branching structures, explore large trees interactively, and render figures for publication using the appropriate optional visualization components.

• Prune selected species and change a tree's root
• Compare branching structures between two trees
• Add NCBI or GTDB taxonomy information

Organize MRI, EEG, and other biomedical research data using BIDS, a shared standard for filenames, folders, and metadata. Query datasets, check compliance, convert DICOM files, and prepare metadata or processed outputs for analysis and sharing.

• Organize MRI and EEG files using BIDS conventions
• Find files by participant, session, or task
• Convert DICOM data and prepare metadata

Automate lab data tasks in Benchling using its Python SDK and REST API. Import and export sequences, inspect sample inventory, and work with electronic lab notebooks and workflow tasks while checking schemas, permissions, and operation results.

• Importing DNA sequences from FASTA files
• Auditing sample inventory at a storage location
• Exporting sequences for a specific schema to CSV

Search scientific papers by topic or DOI, a paper’s identifier, and organize evidence extracted from full text. Connect claims with experiments, reported statistics, limitations, and source locations for literature reviews and evidence tables.

• Find papers relevant to a research question
• Check experimental details beyond abstracts
• Build evidence tables with traceable sources

Search scientific and technical topics with Exa, prioritize scholarly sources using publication and domain filters, and extract text from webpages or PDFs in batches to collect material for research.

• Find papers and primary sources on a research topic
• Search within academic and institutional websites
• Extract article and PDF text from multiple URLs

Retrieve facts from named scientific, regulatory, economic, and other databases through documented APIs. Get results with recorded filters, retrieval dates, and record counts so another person can repeat the lookup and assess its completeness.

• Look up gene or compound records by identifier
• Collect clinical trials matching defined criteria
• Retrieve economic statistics with documented sources

Develop a social science research direction from an initial interest, organize the literature, and assess evidence and feasibility. Structured worksheets help compare research questions, challenge novelty claims, and keep academic wording within what the evidence supports.

• Turn a broad interest into research questions
• Map literature and identify unresolved problems
• Challenge novelty claims from a reviewer's perspective

Read a supplied paper in depth and produce a structured Markdown explanation of its research logic, essential design choices, and evidence limits. Work through key equations with concrete numerical examples and identify missing controls or unreported information.

• Understand a paper before building on its research
• Prepare an explanation for a paper presentation
• Work through key equations with numerical examples

Evaluate scientific manuscripts or excerpts through three independent mock reviewer reports and a combined assessment. Identify strengths, evidence gaps, major concerns, and minor corrections to guide revisions before submission.

• Reviewing a manuscript before submission
• Assessing an abstract or methods excerpt
• Prioritizing major concerns and minor corrections