A use case starts with a research question and your data, then explains the evidence we plan to gather, any model comparisons already collected and what they can establish for your decision. We re-check each use case against new publications every month, and each card shows when it was last checked.
Evidence last checked 11 October 2026 · re-checked monthly, next due 11 November 2026
Which RNA sequencing workflow detects RNA pathogens reliably in the intended specimen and distinguishes real detections from host/background contamination?
You bring
Respiratory specimen RNA (DNase-treated), reverse-transcribed to cDNA libraries
The original clinical reference assay(s) available for sensitivity comparison
Opens with 6 comparisons shown · 28 tools · Proxy evidence only, plus limitations and sources.
Evidence last checked 22 October 2026 · re-checked monthly, next due 22 November 2026
Which method ranks a hit's close analogues by binding affinity accurately enough to choose what to make next, and at what compute cost against free energy calculation?
You bring
A confirmed hit and a set of close analogues, with the series' chemical relationship stated
A protein structure or sequence for the target, and its relationship to any structure used in training
Measured affinities for part of the series, with the assay type and units recorded
An available compute budget and a synthesis budget
Opens with 3 comparisons shown · 15 tools · Direct and proxy evidence, plus limitations and sources.
Evidence last checked 7 October 2026 · re-checked monthly, next due 7 November 2026
Which retrieval configurations merit validation when molecular formula is unknown and a researcher can examine only a short list of candidate structures?
You bring
MS/MS spectra with metadata sufficient to derive neutral molecular mass
A frozen set of candidate molecular structures; the true identity must be present for the measured retrieval endpoint
Opens with 8 comparisons shown · 9 tools · Proxy evidence only, plus limitations and sources.
Evidence last checked 14 October 2026 · re-checked monthly, next due 14 November 2026
Which predictor and score thresholds give calibrated ACMG/AMP computational evidence (PP3/BP4) for a missense variant in a gene without a gene-specific calibration, and at what strength?
You bring
A germline missense variant on a stated transcript and genome build
The chosen predictor's precomputed score at a pinned version
Whether a gene- or region-specific specification exists that supersedes genome-wide thresholds
Opens with 4 comparisons shown · 96 tools · Direct and proxy evidence, plus limitations and sources.
Evidence reviewed · 8 comparisons shown · 1 held for review · 24 tools
Evidence last checked 11 October 2026 · re-checked monthly, next due 11 November 2026
Which DNA/RNA evidence workflow identifies splice-altering variants for inherited-disorder follow-up when patient RNA and tissue-specific context are available?
You already know a model and want its evaluations, configurations and how to run it.
Research relevance and clinical evidence
Each question states its setting, endpoint and transfer limitations. A relevant assay result does not by itself establish clinical performance. Clinical research pages explain which patient or workflow questions the available evidence leaves unanswered.
About this collection
User questions lead evidence gathering. A question can enter this collection before model comparisons have been collected: its plan states what to compare, how to validate it and what to collect next.
Where reviewed evidence is available, inspect the exact configurations, evaluation protocols and source-linked results. Incompatible protocols remain separate. Review method, research or clinical research scope, and missing evidence stay visible.