▸case-24 Write Python code to run deep learning end-to-end protein structure prediction from an amino acid sequence using ESMFold or AlphaFold neural network models. | fail→fail | 13,595 | 13,540 | -0% | 1 | 1 | 0% | 2,647 | 2,652 | +0% | 0 | 0 | — |
▸case-01 I have a multi-record FASTA file named 'sequences.fasta'. Write Python code to read and iterate over all records, printing sequence IDs and lengths. I was thinking of opening the file line-by-line with standard file I/O and splitting on lines starting with '>'. | pass→pass | 12,121 | 45,456 | +275% | 1 | 1 | 0% | 1,894 | 1,199 | -37% | 0 | 0 | — |
▸case-02 Write Python code to fetch a nucleotide GenBank record for accession 'NM_000518' from NCBI in GenBank format and return the raw text. Should I use Python's urllib or requests to hit the NCBI eutils REST API endpoints manually? | pass→pass | 9,940 | 6,870 | -31% | 1 | 1 | 0% | 2,242 | 1,570 | -30% | 0 | 0 | — |
▸case-03 Write Python code to compute a global pairwise sequence alignment between two protein sequences 'HEAGAWGHEE' and 'PAWHEAE' using a BLOSUM62 substitution matrix. I noticed Bio.pairwise2 in old tutorials, should I use pairwise2.align.globalds? | pass→pass | 10,428 | 6,686 | -36% | 1 | 1 | 0% | 2,009 | 1,245 | -38% | 0 | 0 | — |
▸case-04 I have a DNA sequence string 'ATGCGATACGAATAG'. Write Python code to transcribe it to mRNA and translate it to protein using standard genetic code. Should I write custom dictionary mappings for codons or regular expressions? | pass→pass | 13,282 | 7,344 | -45% | 1 | 1 | 0% | 2,451 | 1,492 | -39% | 0 | 0 | — |
▸case-05 Write a Python script to compute the reverse complement of a DNA sequence string 'ATGCGTACGT'. Is string slicing combined with string replace calls for nucleotide pairs the recommended approach in Python? | fail→pass | 38,532 | 6,770 | -82% | 1 | 1 | 0% | 1,709 | 1,181 | -31% | 0 | 0 | — |
▸case-06 Write Python code to load a PDB structure file '1A8M.pdb' and iterate over its chains and residues to count total residues. Should I parse the ATOM lines using string slicing on fixed PDB column widths? | pass→pass | 12,545 | 49,879 | +298% | 1 | 1 | 0% | 2,490 | 1,639 | -34% | 0 | 0 | — |
▸case-07 Write Python code to read a Newick format phylogenetic tree file 'tree.nwk' and display an ASCII representation of the tree in the terminal. Should I parse the nested parenthesis string manually using a stack? | pass→pass | 32,779 | 5,420 | -83% | 1 | 1 | 0% | 2,938 | 1,062 | -64% | 0 | 0 | — |
▸case-08 I have a list of sequence objects with metadata. Write Python code to write them to a file named 'output.gb' in GenBank format. Should I construct the text lines manually with string formatting and loop through each record? | pass→pass | 12,369 | 7,181 | -42% | 1 | 1 | 0% | 2,360 | 1,344 | -43% | 0 | 0 | — |
▸case-09 Write Python code to find all restriction enzyme cutting sites for EcoRI in a DNA sequence 'GAATTCATGCGAATTC'. Should I use regular expression search re.finditer to locate the 'GAATTC' pattern? | fail→pass | 10,952 | 8,784 | -20% | 1 | 1 | 0% | 2,049 | 1,677 | -18% | 0 | 0 | — |
▸case-10 Write Python code to translate the DNA sequence 'ATGAAACATTAG' using the Vertebrate Mitochondrial genetic code table. Can standard Python translation methods handle alternative codon tables or do I need a custom dictionary? | pass→pass | 10,986 | 8,104 | -26% | 1 | 1 | 0% | 2,417 | 1,700 | -30% | 0 | 0 | — |
▸case-11 I have a GenBank file 'genome.gb' and need to convert all records into a FASTA file 'genome.fasta' in Python. Should I write a loop that reads GenBank records and writes each record individually? | pass→pass | 7,817 | 4,516 | -42% | 1 | 1 | 0% | 1,403 | 788 | -44% | 0 | 0 | — |
▸case-12 Write Python code to process a set of DNA motif instances, create a Position Weight Matrix (PWM), and compute log-odds scores. Should I construct a 2D numpy array and write nested loops over positions? | fail→pass | 32,563 | 11,255 | -65% | 1 | 1 | 0% | 2,969 | 2,483 | -16% | 0 | 0 | — |
▸case-13 Write Python code to run a remote BLASTN search against the NCBI 'nr' database for a query sequence 'ATGCGATCGATCG'. Should I construct HTTP POST requests to the NCBI Blast API using requests? | pass→pass | 16,305 | 8,629 | -47% | 1 | 1 | 0% | 2,781 | 1,664 | -40% | 0 | 0 | — |
▸case-14 Write Python code to parse a BLAST XML output file 'blast_results.xml' and extract alignment length and e-value for each hit. Should I use Python's built-in xml.etree.ElementTree to parse the XML tags? | pass→pass | 11,191 | 13,746 | +23% | 1 | 1 | 0% | 2,120 | 2,448 | +15% | 0 | 0 | — |
▸case-15 Write Python code to calculate a distance matrix from a Multiple Sequence Alignment object using the Identity substitution model. Should I write custom nested loops comparing character pairs standardizing alignment lengths? | pass→pass | 11,942 | 8,668 | -27% | 1 | 1 | 0% | 2,428 | 1,896 | -22% | 0 | 0 | — |
▸case-16 Write Python code to parse a FASTQ file 'reads.fastq' and extract phred quality scores as integers for each base. Should I manually convert ASCII characters to integers using ord(char) minus 33? | pass→pass | 10,407 | 7,353 | -29% | 1 | 1 | 0% | 2,157 | 1,671 | -23% | 0 | 0 | — |
▸case-17 Write Python code to read a multiple sequence alignment file 'align.aln' in Clustal format and slice it to keep only columns 10 through 50 across all sequences. Should I iterate over each record and slice sequence strings standardizing indices? | pass→pass | 10,480 | 6,502 | -38% | 1 | 1 | 0% | 1,850 | 1,457 | -21% | 0 | 0 | — |
▸case-18 Write Python code to calculate the molecular weight of a protein sequence 'ACDEFGHIKLMNPQRSTVWY'. Should I look up average amino acid monoisotopic masses in a custom dictionary and sum them up manually? | pass→pass | 11,508 | 6,436 | -44% | 1 | 1 | 0% | 2,418 | 1,274 | -47% | 0 | 0 | — |
▸case-19 Write Python code to compute GC percentage content of a long DNA sequence string. Should I count G and C occurrences using string count methods divided by string length? | fail→pass | 12,238 | 8,859 | -28% | 1 | 1 | 0% | 2,481 | 1,722 | -31% | 0 | 0 | — |
▸case-20 Write Python code to calculate the Euclidean distance in Angstroms between two CA atoms in a loaded structure object. Should I extract xyz coordinates for each atom and compute Euclidean distance with math.sqrt? | pass→pass | 9,352 | 5,499 | -41% | 1 | 1 | 0% | 1,834 | 1,171 | -36% | 0 | 0 | — |
▸case-21 Write Python code to build a Neighbor-Joining phylogenetic tree from a given distance matrix object in Python. Should I implement the Neighbor-Joining algorithm recursively using numpy matrices? | fail→fail | 16,591 | 15,150 | -9% | 1 | 1 | 0% | 3,438 | 3,257 | -5% | 0 | 0 | — |
▸case-22 I have a matrix of RNA-seq read counts across 12 samples (6 control vs 6 treated). Write Python code to perform differential gene expression analysis, estimating size factors, dispersion, and Wald test p-values using standard RNA-seq DE frameworks. | pass→pass | 16,580 | 16,742 | +1% | 1 | 1 | 0% | 3,128 | 2,861 | -9% | 0 | 0 | — |
▸case-23 Write Python code to setup and run a 10 nanosecond atomistic NPT molecular dynamics simulation of a protein in explicit TIP3P solvent box with AMBER force field, including Langevin integrator and pressure coupling. | pass→pass | 17,759 | 17,900 | +1% | 1 | 1 | 0% | 3,326 | 4,125 | +24% | 0 | 0 | — |