Plasmid maps, cloning & primers
Design constructs, simulate cloning and design primers.
20 project-authored proposals · taxonomy v1.1 · 0 new benchmark runs. Verifiers and partial-credit rules below are designs, not executed results.
- Typical applications
- SnapGene · Benchling · Geneious
- Class GUI-need label
G2· GUI-essential
Task proposals · 20
Expand to inspect the complete original wording and proposed checks. Original proposal text remains English in both interfaces.
R08.06.01.01-T01 Clone a GFP CDS into pUC19 between EcoRI and BamHI in SnapGene
Original instruction
In SnapGene open input/pUC19.dna and input/gfp_insert.dna. Simulate restriction cloning: cut the vector with EcoRI and BamHI, cut the insert with the same enzymes, ligate, keep the GFP reading frame in frame with the lacZα start codon, annotate the insert as a CDS named 'GFP', and save output/pUC19-GFP.dna plus output/pUC19-GFP.gb.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G3· GUI-only- Interaction primitives
click· Point & clickdrag· Drag & dropvis· Visual judgment- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
GenBank sequence must equal gold (circular, rotation-invariant) and carry a CDS feature named GFP at the gold coordinates in frame. The .dna file must hold a SnapGene cloning history with the two-enzyme ligation; a Biopython-built record without history scores 0. Biopython and SnapGene Server are not installed on the VM, and a file-system audit log flags output files not written by SnapGene.
Proposed partial credit
40% final sequence correct; 25% junctions seamless and in frame; 20% GFP feature annotated; 15% cloning history present.
R08.06.01.01-T02 Design Gibson primers to join two fragments into a linearized vector in SnapGene
Original instruction
In SnapGene use Gibson Assembly with input/vector.dna (linearized at the MCS), input/fragA.dna and input/fragB.dna in the order vector-A-B-vector. Set 25-bp overlaps, primer Tm 58–62 °C and annealing length 20 bp, save output/assembly.dna and export the primer list to output/primers.csv.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G3· GUI-only- Interaction primitives
click· Point & clicktype· Text & formsvis· Visual judgment- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
In-silico assembly of the exported primers and fragments (Biopython check) must reproduce the gold construct; every primer's annealing Tm 58–62 °C, overlaps 25±2 bp, no primer self-dimer ΔG below −9 kcal/mol. Primer files without a SnapGene Gibson-assembly history in the .dna are rejected. Primer3 and SnapGene Server are not installed, and a file-system audit log flags files not written by SnapGene.
Proposed partial credit
35% assembled sequence; 30% overlap lengths; 25% Tm window; 10% primer CSV exported.
R08.06.01.01-T03 Simulate a double digest of a plasmid and report band sizes in SnapGene
Original instruction
Open input/plasmid_X.dna in SnapGene and simulate an EcoRI + HindIII digest on a 1% agarose gel view. Write all expected fragment sizes in bp, descending, to output/answer.json and export the gel image to output/gel.png.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
CL· CLI-sufficient- Interaction primitives
click· Point & clickvis· Visual judgment- Work product
WP12· Answer/decision- Conditions
licensed· Licensed pro app- Proposed difficulty
- 2 / 5
Proposed verifier
Fragment list must equal gold exactly (circular plasmid, both enzymes, ±0 bp); gel.png must be a SnapGene gel export showing the same number of bands.
Proposed partial credit
70% fragment sizes exact; 30% gel image exported.
R08.06.01.01-T04 Build a Golden Gate level-1 assembly with four BsaI parts in Benchling
Original instruction
In the Benchling test workspace open the sequences in folder 'GG_parts' (promoter, RBS-CDS, terminator, backbone). Use the Golden Gate assembly wizard with BsaI to assemble them in that order, name the product 'L1_RFP_cassette', and verify no internal BsaI sites remain. Export the product as output/L1_RFP_cassette.gb.
- Platforms
web· Any OS (web)- Applications
- Benchling
- Interfaces
brow· Browser- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clickdrag· Drag & droptype· Text & forms- Work product
WP02· Records/table- Conditions
- None declared
- Proposed difficulty
- 4 / 5
Proposed verifier
Exported sequence equals gold (rotation-invariant, circular), zero BsaI sites, fusion-site scars at the four junctions equal the gold 4-bp overhangs. Benchling workspace must contain the assembly record with the four input parts linked. The test workspace issues no Benchling API token, so the assembly record must be created in a browser session.
Proposed partial credit
35% correct assembled sequence; 25% junction overhangs; 20% no BsaI sites; 20% assembly record saved.
R08.06.01.01-T05 Align three Sanger reads to a construct and locate the single mismatch
Original instruction
In SnapGene align input/read1.ab1, read2.ab1 and read3.ab1 to input/construct.dna. One read contains a real single-base substitution in the CDS; the others only have low-quality ends. Report the construct position, the base change and the resulting amino-acid change in output/answer.json and save output/alignment.dna.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clickvis· Visual judgmentnav· Pan/zoom/scroll- Work product
WP12· Answer/decision- Conditions
licensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
Position, base change and protein consequence must equal gold exactly; low-quality end discrepancies must not be reported. alignment.dna must contain all three traces aligned. The .dna must carry SnapGene trace alignment objects; Biopython-built records are rejected. Biopython and SnapGene Server are not installed; a file-system audit log flags a .dna not written by SnapGene.
Proposed partial credit
40% position; 25% base change; 25% amino-acid change; 10% alignment saved.
R08.06.01.01-T06 Design site-directed mutagenesis primers for a point mutation in SnapGene
Original instruction
In SnapGene open input/kinase_plasmid.dna and design QuikChange-style primers introducing D166A in the CDS, using a silent restriction site for screening if possible. Keep length 25–45 bp, Tm ≥78 °C, mismatch centred, and export output/sdm_primers.csv plus the mutated plasmid output/D166A.dna.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & formsvis· Visual judgment- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
Translated CDS of D166A.dna differs from input only at residue 166 (Asp→Ala). Primers: complementary pair, length 25–45, Tm ≥78 °C by the SnapGene formula, mutation within the central third, and in-silico PCR reproduces the mutant plasmid. Biopython and primer3 are not installed on the VM; the .dna must hold SnapGene's primer objects.
Proposed partial credit
35% mutant plasmid correct; 35% primer design constraints; 20% in-silico PCR reproduces; 10% CSV exported.
R08.06.01.01-T07 Annotate an unannotated plasmid map and export GenBank in SnapGene
Original instruction
input/unknown.dna is a 5.4 kb plasmid with no features. In SnapGene detect common features, then manually add and name the missing ones listed in input/expected_features.txt (origin, resistance marker, promoter, CDS, terminator) with correct strands and exact boundaries. Save output/annotated.gb.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
CL· CLI-sufficient- Interaction primitives
click· Point & clickdrag· Drag & dropvis· Visual judgment- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
Each expected feature must be present with correct type, name, strand and boundaries within ±3 bp of gold; no duplicate overlapping features of the same name. Biopython is not installed, and a file-system audit log flags an annotated.gb not written by SnapGene's export (script or text-editor writes score 0).
Proposed partial credit
80% scaled by features correct (16 pts each of 5); 20% strands and types all correct.
R08.06.01.01-T08 Design a CRISPR knock-in donor with homology arms and silent PAM blocking
Original instruction
In Benchling open 'HDR_project': the target locus, the guide (listed in guides.csv) and the HA-tag insert. Design a dsDNA donor with 500-bp homology arms placing the tag in frame at the C-terminus, mutate the PAM silently to block re-cutting, and export output/donor.gb with annotated arms, tag and the silent change.
- Platforms
web· Any OS (web)- Applications
- Benchling
- Interfaces
brow· Browser- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & formsvis· Visual judgment- Work product
WP02· Records/table- Conditions
long· Long-horizon- Proposed difficulty
- 4 / 5
Proposed verifier
Donor equals gold: arms 500±5 bp matching the genome, tag in frame directly before the stop, PAM altered with a synonymous codon (translation unchanged), guide protospacer no longer a perfect match. Features annotated. The Benchling workspace must hold the design record; API tokens are not available to the agent.
Proposed partial credit
25% homology arms; 25% in-frame tag; 30% silent PAM block; 20% annotation and export.
R08.06.01.01-T09 Simulate colony PCR screening and report insert-positive clones
Original instruction
In SnapGene open input/parent_vector.dna, input/correct_clone.dna and input/empty_clone.dna. Design a primer pair flanking the insertion site (Tm within 2 °C of each other, product <1.2 kb), run in-silico PCR on all three, and report expected product sizes per template in output/answer.json with the primers in output/primers.csv.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
CL· CLI-sufficient- Interaction primitives
click· Point & clicktype· Text & forms- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 2 / 5
Proposed verifier
Primers bind both constructs with ≤1 mismatch; reported sizes equal in-silico PCR gold (±0 bp) and differ between clones by the insert length; Tm difference ≤2 °C; product <1.2 kb. The .dna must contain SnapGene primer-binding objects for the pair. Primer3, Biopython and SnapGene Server are not installed, and a file-system audit log flags a .dna not written by SnapGene.
Proposed partial credit
35% primer design; 45% three product sizes; 20% files exported.
R08.06.01.01-T10 Codon-optimize a CDS for E. coli in Geneious and check for forbidden sites
Original instruction
In Geneious Prime open input/gene_native.fasta and codon-optimize the CDS for E. coli K-12 using the supplied usage table, keeping the protein identical, GC 45–55%, and removing all BsaI and BsmBI sites. Save output/optimized.fasta and report the CAI and GC in output/answer.json.
- Platforms
mac· macOSwin· Windows- Applications
- Geneious Prime
- Interfaces
desk· Desktop GUI- GUI need · task setting
HY· Hybrid- GUI need · ordinary access
CL· CLI-sufficient- Interaction primitives
click· Point & clicktype· Text & forms- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
Translation identical to input; zero BsaI/BsmBI sites; GC 45–55%; CAI ≥0.75 recomputed from the table and matching the reported value within 0.01; no homopolymer run >8.
Proposed partial credit
25% protein preserved; 25% CAI; 25% sites removed; 25% GC and reported values.
R08.06.01.01-T11 Design a four-fragment Gibson assembly of a plasmid in Benchling
Original instruction
In the Benchling test workspace, assemble the backbone plus three inserts in folder 'Gibson4' into a circular plasmid in the stated order using the Gibson/assembly wizard with 30-bp overlaps and Tm 60±3 °C. Name the product 'pFC_4frag', verify the junctions keep each CDS in frame, and export output/pFC_4frag.gb and output/primers.csv.
- Platforms
web· Any OS (web)- Applications
- Benchling
- Interfaces
brow· Browser- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clickdrag· Drag & droptype· Text & forms- Work product
WP02· Records/table- Conditions
long· Long-horizon- Proposed difficulty
- 4 / 5
Proposed verifier
In-silico assembly from the exported primers reproduces gold; all four junctions in frame with no stop codons introduced; overlaps 30±3 bp and Tm in window; Benchling assembly record present. Benchling must hold the assembly record; no API credentials are provided.
Proposed partial credit
30% assembled sequence; 25% frames at junctions; 25% primer parameters; 20% record and export.
R08.06.01.01-T12 Build a six-part MoClo transcription unit and verify fusion-site compatibility
Original instruction
In SnapGene use Golden Gate cloning with BsaI on the six MoClo parts in input/moclo/ (promoter, 5'UTR, CDS, CDS-tag, 3'UTR, terminator) and the level-1 acceptor. Verify the fusion sites are compatible in the intended order, assemble, and save output/TU1.dna plus a compatibility note in output/check.txt.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G3· GUI-only- Interaction primitives
click· Point & clickdrag· Drag & dropvis· Visual judgment- Work product
WP02· Records/table- Conditions
licensed· Licensed pro apptutorial· Follow docs/tutorial- Proposed difficulty
- 4 / 5
Proposed verifier
TU1 sequence equals gold with the six parts in order; all seven junction overhangs match the MoClo standard; no internal BsaI remains; check.txt names the one part pair whose sites would mis-assemble if swapped (keyword check). The .dna must carry SnapGene's Golden Gate cloning history. Biopython and SnapGene Server are not installed, and a file-system audit log flags a .dna not written by SnapGene.
Proposed partial credit
40% assembled sequence; 25% overhangs; 20% no BsaI; 15% compatibility note.
R08.06.01.01-T13 Design qPCR primers and probe spanning an exon junction in Geneious
Original instruction
In Geneious Prime open input/transcript.gb (annotated exons) and design a qPCR assay spanning the exon 3–exon 4 junction: amplicon 80–150 bp, primer Tm 59–61 °C, GC 40–60%, probe Tm 68–70 °C inside the amplicon. Export output/qpcr_assay.csv and annotate them on the transcript as output/transcript_assay.gb.
- Platforms
mac· macOSwin· Windows- Applications
- Geneious Prime
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
CL· CLI-sufficient- Interaction primitives
click· Point & clicktype· Text & formsvis· Visual judgment- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 4 / 5
Proposed verifier
Amplicon crosses the junction (one primer or the probe spans it), length 80–150 bp; Tm and GC within windows (recomputed); probe inside the amplicon; no genomic product in in-silico PCR against input/genomic.fasta. Primer3 and Biopython are not installed; the assay must exist as Geneious primer annotations, and a file-system audit log flags outputs not written by Geneious Prime.
Proposed partial credit
30% junction spanning; 25% primer parameters; 25% probe; 20% genomic specificity.
R08.06.01.01-T14 Resolve a failed cloning design: SnapGene finds no usable restriction sites
Original instruction
input/target.dna and input/insert.dna are to be joined by restriction cloning, but every enzyme pair in the MCS also cuts the insert (check in SnapGene). Write output/report.md stating that restriction cloning is infeasible here, which enzymes conflict, and propose Gibson or Golden Gate with specific overlaps; do not fabricate a cloning file.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
CL· CLI-sufficient- Interaction primitives
click· Point & clickvis· Visual judgment- Work product
WP01· Document- Conditions
clarify· Ask when unclearlicensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
report.md must name the conflicting enzymes exactly (set match against gold), state infeasibility, and give an alternative with overlap coordinates that an in-silico check confirms would assemble. Submitting a cloned .dna file instead scores 0 for the main milestone. Biopython and EMBOSS restriction tools are not installed on the VM, so enzyme conflicts must be checked in SnapGene.
Proposed partial credit
40% correct infeasibility call; 30% conflicting enzymes listed; 30% workable alternative with coordinates.
R08.06.01.01-T15 Reconstruct a plasmid map from a published figure and a digest in ApE
Original instruction
input/figure.png shows a plasmid map with feature positions and input/digest.txt lists observed EcoRV/XbaI band sizes. In ApE build the 4,312-bp plasmid from the parts in input/parts.fasta so that its simulated digest matches the observed bands, annotate the features as shown, and save output/reconstructed.gb.
- Platforms
mac· macOSwin· Windowslin· Linux- Applications
- ApE
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & formsvis· Visual judgment- Work product
WP02· Records/table- Conditions
- None declared
- Proposed difficulty
- 5 / 5
Proposed verifier
Simulated EcoRV/XbaI digest of the saved file must match the observed bands within ±10 bp each; total length 4,312±5 bp; features placed within ±25 bp of the figure positions with correct orientation. Biopython and EMBOSS are not installed, and a file-system audit log flags a reconstructed.gb not written by ApE (scripted or text-editor writes score 0).
Proposed partial credit
40% digest matches; 25% total length; 25% feature placement; 10% valid GenBank.
R08.06.01.01-T16 Build a dual-guide CRISPR deletion plasmid and verify the predicted junction
Original instruction
In Benchling's CRISPR tool pick two guides from 'del_project' that excise exon 5 of the target gene, choosing on-target ≥0.6 and off-target ≥80, clone both into the dual-guide vector with the wizard, and export output/dual_guide.gb plus the predicted deletion junction sequence (50 bp either side) in output/junction.txt.
- Platforms
web· Any OS (web)- Applications
- Benchling
- Interfaces
brow· Browser- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clicktype· Text & formsvis· Visual judgment- Work product
WP02· Records/table- Conditions
long· Long-horizon- Proposed difficulty
- 5 / 5
Proposed verifier
Both guides present in the vector at the correct cassettes with scores meeting thresholds; cut sites flank exon 5 entirely; junction.txt equals the gold blunt-ligation junction; vector sequence equals gold. The Benchling CRISPR design record must exist; no API credentials are provided.
Proposed partial credit
25% guide choice meeting thresholds; 25% both cloned correctly; 30% junction sequence; 20% export.
R08.06.01.01-T17 Control: simulate the GFP restriction cloning with Biopython
Original instruction
Control pair of T01. Without a GUI, use Biopython from the terminal to cut input/pUC19.gb and input/gfp_insert.gb with EcoRI and BamHI, ligate in frame, add a CDS feature named GFP, and write output/pUC19-GFP.gb.
- Platforms
mac· macOSlin· Linux- Applications
- Biopython
- Interfaces
term· Terminal- GUI need · task setting
CL· CLI-sufficient- GUI need · ordinary access
CL· CLI-sufficient- Interaction primitives
code· Code & commands- Work product
WP02· Records/table- Conditions
- None declared
- Proposed difficulty
- 2 / 5
Proposed verifier
Same sequence and feature checks as T01 (rotation-invariant match to gold, GFP CDS in frame); the cloning-history milestone does not apply. Scored as the CLI control of T01.
Proposed partial credit
55% sequence; 25% junctions in frame; 20% GFP feature.
R08.06.01.01-T18 Trim and assemble four Sanger traces into a consensus in Geneious
Original instruction
In Geneious Prime import the four traces in input/traces/ (two forward, two reverse), trim ends with an error probability limit of 0.05, assemble de novo into one contig, resolve the two disagreements by trace quality, and export output/consensus.fasta plus output/contig.geneious.
- Platforms
mac· macOSwin· Windows- Applications
- Geneious Prime
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clickvis· Visual judgmentnav· Pan/zoom/scroll- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 3 / 5
Proposed verifier
Consensus must match the gold reference over its full length with zero mismatches and length within ±5 bp; contig must contain all four reads; both ambiguity positions resolved to the gold base. The .geneious contig must hold the four trimmed traces, not a scripted FASTA consensus. CAP3, phrap and Biopython are not installed on the VM, and a file-system audit log flags outputs not written by Geneious Prime.
Proposed partial credit
25% trimming; 25% single contig with 4 reads; 40% consensus identity; 10% export.
R08.06.01.01-T19 Design a seamless His-tag removal by inverse PCR in SnapGene
Original instruction
In SnapGene open input/pET_tagged.dna and design an inverse-PCR (around-the-horn) primer pair that deletes the N-terminal His6 tag and its linker precisely, keeping the start codon and downstream frame intact. Export output/ipcr_primers.csv and the product output/pET_untagged.dna.
- Platforms
mac· macOSwin· Windows- Applications
- SnapGene
- Interfaces
desk· Desktop GUI- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G3· GUI-only- Interaction primitives
click· Point & clicktype· Text & formsvis· Visual judgment- Work product
WP02· Records/table- Conditions
licensed· Licensed pro app- Proposed difficulty
- 4 / 5
Proposed verifier
Translated CDS equals gold untagged protein with ATG retained and no frameshift; primers are back-to-back, 5'-phosphorylated or with blunt ends, Tm within 3 °C, and in-silico amplification plus circularization reproduces pET_untagged. The .dna must hold SnapGene's inverse-PCR primer objects and product history. Primer3, Biopython and SnapGene Server are not installed; a file-system audit log flags files not written by SnapGene.
Proposed partial credit
35% product sequence; 30% primer placement and frame; 25% in-silico PCR reproduces; 10% export.
R08.06.01.01-T20 Design a two-level MoClo multigene plasmid from a spec sheet in Benchling
Original instruction
In the Benchling workspace 'MoClo3', build three level-1 transcription units from the parts given in spec.pdf, then assemble them into a level-2 plasmid in the stated order with the correct end-linkers. Verify no internal BsaI or BsmBI sites, and export output/L2_multigene.gb and output/assembly_plan.csv (part per step and enzyme).
- Platforms
web· Any OS (web)- Applications
- Benchling
- Interfaces
brow· Browser- GUI need · task setting
G2· GUI-essential- GUI need · ordinary access
G2· GUI-essential- Interaction primitives
click· Point & clickdrag· Drag & droptype· Text & forms- Work product
WP02· Records/table- Conditions
long· Long-horizon- Proposed difficulty
- 5 / 5
Proposed verifier
L2 sequence equals gold (rotation-invariant) with the three TUs in order and correct end-linkers; zero internal BsaI/BsmBI; assembly_plan.csv lists each level with the correct enzyme; Benchling records exist for all four assemblies. No Benchling API token is issued, so the records must be created in a browser session.
Proposed partial credit
20% three level-1 TUs; 35% level-2 sequence; 20% enzyme sites clean; 25% end-linkers and plan file.
Mapped research references
Existing benchmark-to-class links from the research catalog. They are not record-level annotations, executions or product endorsements.