Gå til hovedindhold
OpenAI

30. juni 2026

I Genebench-Pro

Et nærmere kig på benchmarken, dens spørgsmål og supplerende materiale

Casestudier

Disse 10 casestudier præsenterer repræsentative spørgsmål fra GeneBench-Pro. Hvert casestudie indeholder den oprindelige prompt, datasæt og understøttende materialer. Der findes en oversigt over benchmarken og de vigtigste resultater i annonceringsbloggen.

Bemærk: Filforhåndsvisninger viser uddrag fra de komplette datasæt.

Casestudie 1

Somatisk onkologi: beslutning om afvejning af fordele og risici ved tumorbehandling baseret på strukturelle varianter

Vurdér, om en syntetisk hæmmer rettet mod TXR1 har positiv klinisk nytteværdi i tumorer, hvor målaktiveringen er drevet af en strukturel variant. TXR1, TXR1i, DLR1 og stjernealleletiketter er syntetiske benchmarketiketter. 

Målundergruppen skal udledes af long-read-, ekspressions-, tumorkvalitets- og farmakogenomisk evidens, før gavn og toksicitet kan fortolkes som en behandlingsbeslutning.

Den frigivne prompt, der vises for modellen

A molecular tumor board registry contains trial-eligible advanced solid-tumor cases considered for a TXR1-directed inhibitor. Estimate, for tumors with SV-driven TXR1 target-mediated activation at time zero, the marginal effect of TXR1i versus non-TXR1 systemic therapy on week-16 clinical benefit as if all patients had an assessable week-16 visit. Also estimate the 8-week treatment-limiting toxicity/discontinuation risk under TXR1i in the same target population. Report net clinical utility = benefit risk difference (percentage points) - 0.35 * toxicity risk (percentage points), and choose therapy_class_code 1 if TXR1i has positive net utility and 0 otherwise. 

Use percentage-point units for all non-code quantities. Positive benefit means TXR1i improves week-16 clinical benefit relative to non-TXR1 systemic therapy.

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "therapy_class_code": <int>,
4
    "benefit_rd_pp": <float>,
5
    "toxicity_dropout_risk_pp": <float>,
6
    "net_clinical_utility_pp": <float>
7
  },
8
  "reasoning": "<description of method and QC>"
9
}

Filer stillet til rådighed for modellen

Casestudie 2

Funktionel genomik: CRISPR-målvalidering: lncRNA-transkript eller genomisk lokus?

Afgør, om en tilsyneladende lncRNA-afhængighed er transkriptspecifik eller drevet af effekter fra nærliggende loci og nabogener.

Transkriptrettet evidens skal kunne bestå kontroller for lokal perturbation af DNA-lokus, repression af nabogener, guideombytninger, GC-toksicitet og pladeeffekter.

Frigivet prompt vist for modellen

You are given pooled CRISPRi screening data, guide-level local expression measurements, transcript-targeting CasRx follow-up data, and single-guide follow-up growth measurements for a nominated lncRNA program (LINC473) and a nearby coding gene (KIN1). The identifiers LINC473, KIN1, and ANKRD42 are synthetic benchmark labels; any resemblance to real human genes is coincidental.

Estimate the requested quantities.

Definitions:

  • lncrna_specific_lfc: the pooled-screen matched-control day-10 log2 growth effect expected at 100% effective knockdown of the dominant LINC473 transcript, not local DNA-locus effects.

  • neighbor_mediated_lfc: the pooled-screen matched-control day-10 log2 growth effect expected at 100% KIN1 repression in the local LINC473-locus model after accounting for concomitant LINC473 transcript knockdown.

  • advance_target: 1 if the evidence supports advancing LINC473 as a transcript-directed target, else 0.

Conventions:

  • all growth effects are log2(day10/day0) competitive-growth effects relative to matched controls;

  • more negative numbers indicate stronger loss of fitness;

  • set advance_target to 1 only if lncrna_specific_lfc <= -0.08 and neighbor_mediated_lfc > -0.25; otherwise 0.

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "advance_target": <int>,
4
    "lncrna_specific_lfc": <float>,
5
    "neighbor_mediated_lfc": <float>
6
  },
7
  "reasoning": "<description of method and QC>"
8
}

Filer stillet til rådighed for modellen

Casestudie 3

Statistisk genetik: Prioritering af proteinlægemiddelmål i et koblet genetisk lokus

Estimér direkte sygdomseffekter for to nærliggende proteiner ved hjælp af cis-multivariabel mendelsk randomisering (cis-MVMR), samtidig med håndtering af assay-skala, allel-orientering, winner's curse, LD og residual lokal pleiotropi.

De to proteiner deler et korreleret loci. Analysen skal bevæge sig fra marginale associationer til betingede, LD-informerede sygdomseffekter på en fælles proteinskala.

Frigivet prompt vist modellen

You are given association summary statistics and metadata for two nearby proteins (PROTA and PROTB), a binary disease outcome, a locus correlation reference, and protein measurement records.

Goal: estimate the direct log-odds effect of each protein on the disease outcome per +1 SD increase in log10 concentration, conditional on the other protein.

Interpretation: theta_PROTA and theta_PROTB use the same log-odds per-SD scale defined in the goal.

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "theta_PROTA": <float>,
4
    "theta_PROTB": <float>
5
  },
6
  "reasoning": "<description of method and QC>"
7
}

Filer stillet til rådighed for modellen

Casestudie 4

Klinisk genomik/bærerscreening: residualrisiko ved DRX1-bærerscreening ved CNV- og pseudogenkalibrering

Estimér afstamningsspecifikke bærerfrekvenser, resterende risiko efter en negativ screening, partnerens bærerfrekvens og risiko for påvirket konceptus baseret på data fra bærerscreeningsanalyser.

Estimatet af restrisiko afhænger af pseudogenbevidste bærerkald, kollaps af grundlægger-haplotype, kalibrering af det afstamningsspecifikke assay og standardisering fra testede partnere tilbage til den fulde partnerliste.

Frigivet prompt vist til modellen

Using cohort_roster.tsv.gz, partner_roster.tsv.gz, calibration_controls.tsv.gz, target_metadata.tsv.gz, and assay_observations.tsv.gz, estimate residual reproductive risk for an autosomal recessive DRX1 condition. Report all quantities on the probability scale, not as percentages: carrier_frequency_afr and carrier_frequency_eur among screening-roster adults; residual_carrier_risk_afr_negative for an AFR screening-roster adult with a negative DRX1 screen; partner_carrier_frequency_full_roster for a uniformly sampled partner_roster.tsv.gz row; and couple_reproductive_risk for an affected conceptus when the index person is AFR and screen-negative and the partner is drawn from partner_roster.tsv.gz. Assume autosomal recessive inheritance with a 1/4 affected-conceptus risk conditional on both biological parents being carriers. 

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "carrier_frequency_afr": <float>,
4
    "carrier_frequency_eur": <float>,
5
    "residual_carrier_risk_afr_negative": <float>,
6
    "partner_carrier_frequency_full_roster": <float>,
7
    "couple_reproductive_risk": <float>
8
  },
9
  "reasoning": "<description of method and QC>"
10
}

Filer stillet til rådighed for modellen

Casestudie 5

Enkeltcellegenomik: Aktiveret monocyt eQTL efter korrektion af ambient RNA

Estimer genotypeeffekten på ekspressionen i aktiverede-monocytter efter fjernelse af omgivende RNA og teknisk kontaminering fra enkeltcelle-RNA-seq-data.

Omgivende RNA påvirker både målekspression og det markørpanel, der anvendes til at fastslå aktiveringstilstanden, så korrektionen skal foretages før eQTL-modellen.

Den frigivne prompt, som vises for modellen

Estimate the per-allele log rate ratio for CXCL10 expression in the activated monocyte subpopulation from the provided single-cell RNA-seq data. 

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "beta_activated": <float>
4
  },
5
  "reasoning": "<description of method and QC>"
6
}

Filer stillet til rådighed for modellen

Casestudie 6

Strukturel genetik: Indlejret strukturel variant: ekspressionsstøtte og klinisk sammenhæng

Vurdér, om en indlejret strukturel subhaplotype i et anonymt inversionslignende locus har en kalibreret klinisk association og troværdig ekspressionsstøtte.

Et indlejret kopi-doseringssignal kan forstyrres af den bredere inversionsorientering, så doseringskalibrering, ekspressionsunderstøttelse og klinisk modellering skal forblive adskilte.

Den frigivne prompt vist for modellen

Analyze the released files for anonymous Locus Q. Estimate the full-cohort source-population clinical association and molecular expression support for the calibrated nested segment-B structural copy dosage, separating the nested segment-B dosage from the broader outer-orientation dosage. Report subhap_log_or as the natural-log source-population total-effect odds ratio for case status per additional calibrated segment-B copy. Report expression_log_fc as the natural-log expression fold-change per calibrated segment-B copy for the expression-supported gene. Report target_support_code as 1 if the supported gene has a positive expression_log_fc and the clinical association is protective (subhap_log_or < 0), otherwise 0. Report n_calibrated_carriers as the number of reliable breakpoint-panel samples carrying at least one segment-B copy. 

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "n_calibrated_carriers": <int>,
4
    "target_support_code": <int>,
5
    "expression_log_fc": <float>,
6
    "subhap_log_or": <float>
7
  },
8
  "reasoning": "<description of method and QC>"
9
}

Filer stillet til rådighed for modellen

Casestudie 7

Regulatorisk genomik: Måling af styrken af kromatinløkker efter maskering af strukturelle varianter og kortlægningsartefakter

Kvantificér en fokal forskel i Hi-C-loopstyrke mellem case og kontrol efter at have fjernet artefakter, der er forårsaget af lav kortlægningsbarhed og strukturelle varianter fra baggrunden for forventede kontakter.

Målløkken er defineret ved en opløsning på 20 kb, men modellen med forventet kontakt bliver forvrænget, medmindre kontakter med lav kortlægningsevne og en SV-stribe kun for case maskeres først.

Udgivet prompt vist til modellen

You are given Hi-C contact matrices at 20 kb and 40 kb resolution plus bin annotations. Estimate the loop enrichment at the 20 kb interaction between `bin_id = 8` and `bin_id = 17` in `bins_20kb.tsv.gz`. Report three quantities: `case_loop_strength` (mean log2(observed/expected) across case replicates), `control_loop_strength` (mean log2(observed/expected) across control replicates), and `delta_loop_strength` (case minus control).

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "case_loop_strength": <float>,
4
    "control_loop_strength": <float>,
5
    "delta_loop_strength": <float>
6
  },
7
  "reasoning": "<description of method and QC>"
8
}

Filer stillet til rådighed for modellen

Casestudie 8

Statistisk genetik: Multi-Parent QTL Mapping med Founder Rekonstruktion

Kortlæg et kvantitativt egenskabslokus på kromosom 1 i en rekombinant population med otte grundlæggere ved at rekonstruere grundlæggernes afstamning, før fænotypeassociationen testes.

De observerbare markørdata er bialleliske, men det biologiske signal er afstamning fra grundlæggerpopulationer. En holdbar analyse skal derfor rekonstruere foundertilstanden, kontrollere markørorienteringen og adskille QTL'et fra en batchjusteret forstyrrende top.

Frigivet prompt vist for modellen

Map the chromosome 1 QTL in an 8-founder multi-parent population. Report the position (cM) and which founder carries the high-effect allele.

Report high_founder as "F1".."F8".

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
"answer": {
3
"high_founder": "<string>",
4
"qtl_pos_cM": <float>
5
},
6
"reasoning": "<description of method and QC>"
7
}

Data files:

  • markers.tsv.gz: marker metadata

  • founders.tsv.gz: founder alleles at each marker

  • ril_genotypes.npz: observed RIL genotypes (biallelic)

  • phenotypes.tsv.gz: phenotype and covariates

Filer stillet til rådighed for modellen

Casestudie 9

Populationsgenetik: forældrespecifik afstamning og tidspunkt for nylig genetisk blanding

Infér forælderspecifikke afstamningsproportioner og tidspunktet for nylig opblanding ud fra fasede lokale afstamningsstræk efter korrektion af reciprokke artefakter og en kromosomspecifik etiketinversion.

Både afstamningsandele og pulstidspunkter ændrer sig, hvis reciprokke traktartefakter, inversion af kromosomlokale etiketter eller kortnævnere håndteres forkert.

Frigivet prompt vist til modellen

You are given phased local-ancestry tracts for one admixed individual. Estimate, for each transmitted parental haplotype, the fraction of ancestry A across the called tract span and the number of generations since a single recent admixture pulse. Label parent1 as the haplotype with the smaller ancestry-A fraction and parent2 as the haplotype with the larger ancestry-A fraction. 

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
  "answer": {
3
    "parent1_A_fraction": <float>,
4
    "parent1_t": <float>,
5
    "parent2_A_fraction": <float>,
6
    "parent2_t": <float>
7
  },
8
  "reasoning": "<description of method and QC>"
9
}

Filer stillet til rådighed for modellen

Casestudie 10

Populationsgenetik: Estimering af udvælgelse fra støjende tidsserier for gammelt DNA

Udled, hvilket af to haploide loci der er under stærkere positiv selektion ud fra tidsserier over allelfrekvenser fra fortiden, under hensyntagen til allelorientering, retningsbestemt fejl, genetisk drift og varierende populationsstørrelse.

Dominerende tidligere trajektorier er ikke direkte sammenlignelige, før begge loci er placeret på den samme skala for afledte alleler, og de angivne sekventeringsfejlværdier på prøveniveau modelleres direkte.

You are given allele-frequency time series data from two haploid loci sampled over multiple generations.

One locus is under stronger positive selection than the other. Estimate the selection coefficient s for the more strongly selected locus, where s > 0 means the derived allele is favored.

Assume instrument-driven sequencing error is ~1%. The seq_error column is the average of the two directional allele-miscall rates for that locus and sample.

The selected_locus value must be "A" or "B".

These data came from a real experiment; you will be graded not just on numerical correctness but the quality of analytical reasoning you exhibit; do not attempt to take any shortcuts.

Return your final answer as exactly one JSON object.
Do not wrap the JSON in markdown.
Do not add prose before or after the JSON.
Do not omit any keys shown in the example.
Return the JSON object in your final answer:

JSON

1
{
2
"answer": {
3
"selected_locus": "<string>",
4
"s": <float>
5
},
6
"reasoning": "<description of method and QC>"
7
}

Filer stillet til rådighed for modellen