vimalinx/bio-agent - Page 6

jackhmmer

Use when running iterative sequence-to-sequence HMMER searches to expand a protein family from one or a few seed sequences against a sequence database.

join-into-groups-of

Use when batching newline-separated IDs into fixed-size comma-separated groups for EDirect calls or other list-limited APIs.

json2xml

Use when converting JSON documents into XML for downstream EDirect or XML-based processing.

jsonl2xml

Use when converting JSON Lines streams into XML fragments for downstream EDirect or XML-based processing.

just-top-hits

Use when keeping only the first N query groups from a first-column-grouped tabular hit table.

kinfold

Use when simulating stochastic folding kinetics of single-stranded nucleic acids, computing first passage times between structures, or analyzing RNA/DNA folding trajectories.

kinwalker

Use when simulating RNA folding kinetics during transcription to predict cotranscriptional folding pathways and transient intermediate structures.

legacy-blast-pl

Use when converting NCBI C toolkit BLAST command lines to NCBI C++ toolkit equivalents.

links-bed

Use when you need to generate HTML links to UCSC Genome Browser from BED, GFF, or VCF feature files.

mafft

Use when performing multiple sequence alignment on nucleotide or protein sequences, such as preparing alignments for phylogenetic analysis or comparative genomics.

makeblastdb

Use when creating BLAST databases from FASTA sequence files for use with blastn, blastp, blastx, or other BLAST search tools.

makehmmerdb

Use when building HMMER binary-formatted sequence databases from plain sequence files, especially for hmmpgmd-style serving or specialized accelerated workflows.

makembindex

Use when you need to create a BLAST database index for faster search operations on BLAST databases.

makeprofiledb

Use when creating PSSM databases for rpsblast, cobalt, or deltablast searches. Formats position-specific scoring matrices into BLAST-compatible profile databases.

map-bed

Use when you need to apply aggregation functions (sum, mean, count, etc.) to values from overlapping intervals in one file and map them onto intervals from another file.

maq2sam-long

Use when converting legacy MAQ long-map files into SAM for downstream SAMtools-compatible processing.

maq2sam-short

Use when converting legacy MAQ short-map files into SAM for downstream SAMtools-compatible processing.

mask-fasta-from-bed

Use when you need to hard-mask or soft-mask regions in a FASTA file using BED, GFF, or VCF coordinates, such as repetitive elements, blacklist regions, or loci to exclude from sequence analysis.

md5fa

Use when hashing FASTA records and comparing ordered versus order-insensitive sequence digests instead of taking a single whole-file MD5.

md5sum-lite

Use when computing plain MD5 digests for files or stdin in lightweight HTSlib-based workflows without GNU md5sum features.

merge-bed

Use when merging overlapping or book-ended intervals in BED/GFF/VCF files into single intervals.

multi-bam-cov

Use when you need to count read coverage from multiple BAM files across specific genomic regions defined in a BED, GFF, or VCF file.

multi-intersect-bed

Use when you need to identify overlapping genomic regions across multiple BED files simultaneously.

multiqc

Use when you need to aggregate quality control reports from multiple bioinformatics tools into a single HTML report

muscle

Use when performing multiple sequence alignment of FASTA inputs, generating alignment ensembles, or calculating alignment confidence metrics.

nhance-sh

Use when trying the `nhance.sh` shortcut wrapper around `nquire` for pathway, gene-to-pathway, LitVar, or citation-match lookups against NCBI-related endpoints.

nhmmer

Use when searching DNA or RNA queries against nucleotide sequence databases with HMMER's nucleotide homology search engine.

nhmmscan

Use when scanning DNA or RNA sequences against a nucleotide profile HMM database such as Dfam to identify annotated families or repeated elements.

novo2sam-pl

Use when converting legacy Novoalign text output into SAM, especially for unique alignments and optional paired-end interpretation.

nquire

Use when making raw HTTP, E-utilities, PubChem, datasets, or FTP requests through the low-level EDirect transport wrapper.

nuc-bed

Use when profiling nucleotide content (AT/GC percentages, base counts) of genomic intervals against a FASTA reference.

candidate-plan-generator

Use when generating multiple candidate plans from a normalized request before the user approves execution.

execution-guard

Use when deciding whether a plan stage should continue automatically, pause for confirmation, or escalate because of risk.

plan-comparator

Use when comparing candidate plans and explaining trade-offs so the user can select or modify a plan.

plan-editor

Use when incorporating user changes into a selected plan while preserving execution structure and validation semantics.

request-normalizer

Use when turning a natural-language biology request into a structured request object before planning.

run-resumer

Use when resuming a paused or interrupted run from saved run state instead of regenerating the plan from scratch.

skill-router

Use when expanding an approved plan into stage-by-stage candidate skills drawn from the local skill registry.

stage-reviewer

Use when checking whether a completed stage produced the artifacts and validation evidence required by the approved plan.

pair-at-a-time

Use when turning a plain-text stream into adjacent lowercase word pairs for EDirect-style text mining, token-neighbor extraction, or lightweight bigram generation.