Server definition
- Hash
- sha256:b2e046aba416010cf5d622e59847d6776ee10265901f0e4d013adb007fc2f224
- What it is
- What a remote MCP server returned when asked what it offers: 30 tools
The blob, as servednamed by its sha256
{
"instructions": "askPulse federates pulse and legume data resources: Ensembl Plants gene annotation (pea (three genomes), faba bean,\nnarrow-leafed lupin, common bean, pigeonpea, mungbean, adzuki bean, cowpea, plus soybean, wild soybean, peanut,\nMedicago truncatula and red clover), chickpea and lentil genes and legume gene families from the Legume Information\nSystem (LIS), extra lentil (KnowPulse: CDC Greenstar, Lens ervoides, curated genes, diversity-panel SNPs, GWAS) and\nfaba bean data (Hedin/2 v2 and Tiffany gene sets, QTL compilation, NORFAB SNPs), RNA-seq expression (chickpea and pea\nfrom LIS, soybean and Medicago from Expression Atlas, faba bean quantified by askPulse), QTL and GWAS (soybean, common\nbean, cowpea, peanut from LIS; faba bean, lentil and pulsedb.org), genebank accessions from GBIF and Europe PMC\nliterature.\n- Chickpea (CDC Frontier v3) and lentil (CDC Redberry v2) are not in Ensembl Plants: use legume_gene and\n legume_genes_in_region for them, not find_gene. legume_family links chickpea and lentil genes to pea and soybean\n genes (Ensembl IDs) and Medicago through LIS legume gene families; from there use orthologues or the expression\n tools. Families are broader than orthologue groups, so say 'in the same gene family', and cite LIS.\n- Chickpea has three gene sets: 'chickpea' (kabuli CDC Frontier v3, Ca1g000100 IDs), 'chickpea_kabuli_v1' (the\n original kabuli Ca_00001 IDs used in most papers, on the UWA kabuli v2.6.3 assembly, cicer.info) and 'chickpea_desi'\n (desi ICC 4958, also Ca_ IDs, on the UWA desi v3.0 assembly). Kabuli and desi Ca_ IDs with the same number are\n different genes: if a Ca_ ID matches both, say so and ask which genotype, or use the paper's context. Name the\n assembly with every position. Cite Edwards 2016 (CyVerse doi:10.7946/P2G596 kabuli, doi:10.7946/P2KW2Q desi) for\n the UWA assemblies.\n- legume_pangene converts a gene ID between chickpea assemblies (kabuli v3 Ca1g…, kabuli v1/v2 Ca_, desi ICC 4958 Ca_,\n wild C. reticulatum and C. echinospermum) or pea assemblies (Cameor v1a = Ensembl, Cameor v2, JI2822, ZW6). Use it\n before expression or region lookups when a paper uses an older ID.\n- Expression: chickpea (CDC Frontier v3 Ca1g… IDs) and pea (Cameor Psat… IDs) baseline TPM come from LIS datasets\n (experiment IDs LIS-CHICKPEA-ATLAS, -DROUGHT, -SALT, -PHYTOPHTHORA, -NITROGEN, -HYBRID, LIS-PEA-ATLAS); soybean and\n Medicago from Expression Atlas. Convert a Ca_ ID with legume_pangene first. Cite the study given for each dataset.\n- QTL and GWAS (legume_qtl, legume_qtl_traits): soybean (SoyBase), common bean, cowpea and peanut from LIS; faba bean\n QTL markers of 56 studies (Faba Bean Genome Consortium compilation; Hedin/2 v2 positions, projected to the Ensembl v1\n assembly through gene matches, so v1 positions are approximate); lentil protein and amino acid GWAS on the diversity\n panel (Wright et al. 2025, KnowPulse); chickpea, lentil, pea, faba bean and lupin records from pulsedb.org. QTL are\n intervals on genetic maps; physical positions come from their markers. Use ensembl_region with genes_in_region\n (lis_region with legume_genes_in_region for lentil) to list candidate genes, and say these are genes near the\n markers, not identified causal genes. Cite the study DOI.\n- lupin_markers covers the narrow-leafed lupin 97L380 genetic map (9,972 markers) and its domestication loci (Tardus,\n Lentus pod shattering; Leucospermus; Iucundus low alkaloid; Mollis soft seed; Ku vernalisation; Lanr1 anthracnose),\n with Tanjil positions (= Ensembl lupinus_angustifolius LG01-LG20). Locus intervals are estimated from neighbouring\n anchored markers: genes found there with genes_in_region are candidates, not the cloned gene. Cite Hane et al. 2017\n doi:10.1111/pbi.12615 and the UWA00151 dataset doi:10.26182/xyhy-7y72.\n- arabidopsis_function gives a gene's function through its Arabidopsis orthologue(s) (Ensembl Compara -> UniProtKB\n function, mutant phenotype, GO); say it is inferred and give the orthology type.\n- Use find_gene for any gene name or Ensembl ID, genes_in_region for a genomic interval and orthologues to move between\n legume species (e.g. from soybean or Medicago to pea or lupin). Give the species and relationship for each copy.\n- Every result carries a source URL. Cite those URLs; do not invent IDs, positions or links.\n- A search result with match 'most words' is a partial match; say so.\n- Genesys genebank accessions (database 'Genesys genebank accessions' in search_data / find_germplasm; live details with\n genesys_accession) carry the holding genebank's own passport data; GBIF records of the same holder + accession number\n are dropped. genesys_accession adds availability, Multilateral System (SMTA) status, how to request seed, and the\n WorldClim climate at the collection site (describes the origin, not a phenotype). Cite Genesys.\n- GBIF genebank accessions (find_germplasm, search_data with database 'GBIF genebank accessions') are passport\n records only: holding genebank as an FAO WIEWS code (e.g. IND002 = ICRISAT, SYR002/LBN002 = ICARDA), accession number, taxon and sometimes country.\n Most are Svalbard Global Seed Vault safety duplicates; seed requests go to the holding genebank, not Svalbard.\n Country may be the holder's or the origin; do not state it as the origin unless the record says so.\n- FAIDARE germplasm (database 'GnpIS (INRAE, via FAIDARE)') are curated INRAE passport records (pea and faba bean) with\n holding institute, taxon, country of origin, status, pedigree and panels. The same variety can appear in GBIF and\n FAIDARE: match by accession number and holder, not by name alone.\n- Expression tools (gene_expression, expression_genes, expression_experiments) cover chickpea, pea, soybean,\n Medicago and faba bean (Ensembl Hedin/2 v1 IDs: FABA-ISOSEQ-ATLAS, 11 tissues from Iso-Seq with one library each,\n reads per million, no replicates; FABA-COLD-WONJAM1HO and FABA-COLD-PI271634, leaves at 18, 4, 0 and -7 C;\n FABA-SEED-COTYLEDON and FABA-SEED-TESTA, Hedin/2 and Tiffany mid and late seed development). Name the experiment and\n tissue/contrast; compare TPM only within an experiment. For other pulses (faba bean v2 or Tiffany genes: use the\n best_match Ensembl v1 gene from legume_gene), find the orthologue or family member first and say which species the\n expression is from.\n- Extra gene sets (legume_gene, legume_genes_in_region): 'faba_v2' (Hedin/2 v2, Zhang et al. 2026, Vfaba.Hedin2.R2…),\n 'faba_tiffany' (Tiffany), 'lentil_greenstar' (CDC Greenstar, Lcu.1GRN…) and 'lentil_ervoides' (Lens ervoides IG\n 72815, Ler.1DRT…). Each gene has its best protein match (DIAMOND) in Ensembl faba bean v1 or LIS lentil CDC Redberry v2:\n call it the best match, not an orthologue. Lentil CDC Redberry v2 genes carry curated symbols and gene lists\n (KnowPulse curated genes, flowering time genes of Yuan et al. 2021, pigment genes of Cao et al. 2022, resistance gene\n analogues). Cite KnowPulse (Sanderson et al. 2019 doi:10.3389/fpls.2019.00965) and the assembly page given.\n- panel_haplotypes gives SNP haplotypes of a gene in a diversity panel: lentil diversity panel (324 accessions, CDC\n Redberry v2 IDs), lentil diversity panel + ACTIVATE (521, CDC Greenstar IDs) and faba bean NORFAB (196 accessions\n coded Core1..Core197, Ensembl v1 IDs). SNP effects are not annotated; heterozygous calls count as missing.\n- For publications use search_literature (Europe PMC) and get_paper; cite DOIs/PMIDs it returns. Never cite a paper\n that no tool returned.\n- pulse_gene_view draws one gene as an interactive relationship map (orthologues, LIS gene family members, Arabidopsis\n function, expression, papers) with gene-family and expression tabs. Use it when the user asks to see or visualise a\n gene, and give its page link (gene.html) so they can open the full view.\n- Region tools return a genome_browser link (askPulse JBrowse) for the interval: share it so the user can view genes\n in context.\n- gene_pathways and pathway_genes use Plant Reactome (Gramene): pathways are curated in rice and projected to other\n species by orthology, so say a gene's pathway is inferred. Most genes have none (coverage is metabolism, hormone\n signalling and selected processes). Cite Gupta et al. 2024 (doi:10.1093/nar/gkad1052) and link the pathway diagram.\n- trait_hits gives positioned trait features for a chromosome overview: narrow-leafed lupin domestication loci and 97L380 map markers on Tanjil, soybean and common bean QTL (span of their markers) and GWAS markers on the Ensembl assemblies, faba bean QTL markers (Hedin/2 v2 and projected v1) and lentil GWAS SNPs (CDC Redberry v2) (chromosome numbers; say which species). Each feature has a genome_browser\n link where the assembly is loaded; the web page traits.html draws them by chromosome. GWAS hits are statistical\n associations: nearby genes are candidates. Gene pages and gene_map results may include an efp link (BAR eFP browser).\n- blast_sequence searches this site's BLAST databases (genomes, CDS, proteins). Report hits with identity,\n alignment length and e-value, the gene (CDS/protein hits) or genome position with overlapping genes, and the\n genome browser link; a short primer can hit many places. Point people to /blast/ for the interactive page.\n- genes_with_annotation finds genes by GO term, InterPro/Pfam domain or Plant Reactome pathway, optionally within a\n region (e.g. NB-ARC genes under a QTL). Annotation is electronic: say so. Give the counts (facets) and the genes.\n- gene_neighbourhood shows microsynteny: conserved/total neighbours per related genome and the gene's orthologue\n there. Use it to judge whether a candidate sits in a conserved region.\n- gene_papers lists papers mentioning a gene: ID matches are reliable, name matches may be homonyms. Cite DOIs/PMIDs\n as returned. annotate_genes annotates a gene list in one call; the page /genes.html downloads it as TSV.\n",
"tools": [
{
"description": "Annotate a list of genes (up to 500 IDs or names) in one call: resolved ID, species, location, name, top\nInterPro/Pfam domains, GO terms, Plant Reactome pathways and orthologues in the main related genomes\n(['pisum_sativum', 'vicia_faba', 'medicago_truncatula', 'glycine_max', 'phaseolus_vulgaris', 'lupinus_angustifolius']). For gene-list follow-up after an experiment (DE genes, GWAS candidates); the web\npage genes.html (gene-list tab) runs this and downloads a TSV.",
"inputSchema": {
"properties": {
"genes": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "string"
}
],
"title": "Genes"
},
"targets": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Targets"
}
},
"required": [
"genes"
],
"title": "annotate_genesArguments",
"type": "object"
},
"name": "annotate_genes",
"outputSchema": null
},
{
"description": "Function of a gene through its Arabidopsis thaliana orthologue(s): Ensembl Plants Compara orthologues, then\nUniProtKB curated function, protein and gene names, mutant (disruption) phenotype, subcellular location and GO\nterms. gene: an Ensembl gene ID or name of any crop genome here, or an AGI (AT5G10140) / Arabidopsis name (FLC);\nin askBrassica also a B. napus pangenome gene (BnaA01g00010.1D2, BnaPanG...).\none2many / many2many orthologues are all listed; the crop gene's own function is inferred, not shown.",
"inputSchema": {
"properties": {
"gene": {
"title": "Gene",
"type": "string"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
}
},
"required": [
"gene"
],
"title": "arabidopsis_functionArguments",
"type": "object"
},
"name": "arabidopsis_function",
"outputSchema": null
},
{
"description": "BLAST a DNA or protein sequence (raw or FASTA; up to 20 kb DNA or 5,000 aa) against this site's databases:\npea, narrow-leafed lupin, faba bean, soybean, common bean, chickpea and lentil genomes, CDS and proteins. The program is chosen from the query and database types (blastn, or blastn-short under 50 nt;\nblastx; blastp; tblastn against CDS only). databases: ids from the list this tool returns (default: DNA query ->\nreference genome + all CDS sets; protein -> all protein sets). Hits give gene ID (CDS/protein) or genome position\nwith overlapping genes, identity, alignment length, e-value and a genome browser link. People can use the\nSequenceServer page at /blast/ for the same databases.",
"inputSchema": {
"properties": {
"databases": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Databases"
},
"evalue": {
"default": 1e-10,
"title": "Evalue",
"type": "number"
},
"max_hits": {
"default": 20,
"title": "Max Hits",
"type": "integer"
},
"sequence": {
"title": "Sequence",
"type": "string"
}
},
"required": [
"sequence"
],
"title": "blast_sequenceArguments",
"type": "object"
},
"name": "blast_sequence",
"outputSchema": null
},
{
"description": "What askPulse currently indexes: record counts per database and data type, and data versions; plus the live\nendpoints it queries or offers (BrAPI nodes, the CropSNPdb genotype API, its own MCP server and JSON API).",
"inputSchema": {
"properties": {},
"title": "data_sourcesArguments",
"type": "object"
},
"name": "data_sources",
"outputSchema": null
},
{
"description": "Soybean, Medicago, chickpea, pea and faba bean RNA-seq experiments held by askPulse (Expression Atlas, the Legume Information System for chickpea and pea, and faba bean studies quantified by askPulse): baseline (TPM by\ntissue / developmental stage / treatment) and differential (stress, pathogen, genotype contrasts). query filters descriptions/labels (e.g. 'drought',\n'grain', 'Fusarium'). Gives each experiment's assay groups (baseline) or contrasts (differential).",
"inputSchema": {
"properties": {
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query"
}
},
"title": "expression_experimentsArguments",
"type": "object"
},
"name": "expression_experiments",
"outputSchema": null
},
{
"description": "Genes characteristic of a tissue/stage or responsive to a treatment in one Expression Atlas experiment.\nBaseline experiment + group (text matched to group labels, e.g. 'root', 'grain'): genes with TPM >= min_tpm in a\nmatching group ranked by specificity = (max TPM in matching groups + 1) / (max TPM in other groups + 1).\nDifferential experiment + contrast (text matched to contrast names or IDs): significant genes, direction 'up' or\n'down', ranked by |log2FC|. Use expression_experiments() for group and contrast names.",
"inputSchema": {
"properties": {
"contrast": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Contrast"
},
"direction": {
"default": "up",
"title": "Direction",
"type": "string"
},
"experiment": {
"title": "Experiment",
"type": "string"
},
"group": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Group"
},
"limit": {
"default": 50,
"title": "Limit",
"type": "integer"
},
"min_tpm": {
"default": 5,
"title": "Min Tpm",
"type": "number"
}
},
"required": [
"experiment"
],
"title": "expression_genesArguments",
"type": "object"
},
"name": "expression_genes",
"outputSchema": null
},
{
"description": "Look up a gene by Ensembl gene ID or gene name/symbol in Ensembl Plants: species, location, assembly, biotype,\ndescription and link. Names are searched in all of: pisum_sativum (Cameor v1a), pisum_sativum_gca024323335v2gb (pea ZW6), pisum_sativum_gca964186695v1gb (pea JI2822), vicia_faba, lupinus_angustifolius, phaseolus_vulgaris, cajanus_cajan_gca000340665v2gb (pigeonpea), vigna_unguiculata_gca004118075v2rs (cowpea), vigna_radiata, vigna_angularis, glycine_max, glycine_soja, arachis_hypogaea, medicago_truncatula, trifolium_pratense (red clover) (or only in species, if given).\ne.g. 'GLYMA_01G000600', 'Psat1g000360'.",
"inputSchema": {
"properties": {
"gene": {
"title": "Gene",
"type": "string"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
}
},
"required": [
"gene"
],
"title": "find_geneArguments",
"type": "object"
},
"name": "find_gene",
"outputSchema": null
},
{
"description": "Find pulse and legume genebank accessions by accession number or name (e.g. 'ICC 4958' for chickpea at\nICRISAT): chickpea, lentil, pea, faba bean, lupin, grass pea, Phaseolus, Vigna, pigeonpea, soybean, peanut and\nMedicago accessions from GBIF, with the holding genebank (FAO WIEWS code, e.g. IND002 = ICRISAT, SYR002/LBN002 =\nICARDA) and accession number; mostly Svalbard safety duplicates. Passport data are minimal (no traits).\nAlso INRAE GnpIS pea and faba bean collections via FAIDARE, with taxon, holding institute, country of origin,\nstatus, pedigree and panels.",
"inputSchema": {
"properties": {
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"name": {
"title": "Name",
"type": "string"
}
},
"required": [
"name"
],
"title": "find_germplasmArguments",
"type": "object"
},
"name": "find_germplasm",
"outputSchema": null
},
{
"description": "Where and when a pulse and legume gene is expressed, and under which treatments it changes, from Expression Atlas, the Legume Information System for chickpea and pea, and faba bean studies quantified by askPulse.\ngene: Ensembl gene ID (e.g. GLYMA_01G000600, pea Psat1g000360), a chickpea CDC Frontier v3 ID (Ca1g000100) or a gene name find_gene resolves. Baseline: TPM (median over replicates,\nwith range) for the top_groups highest-expressed tissues/stages per experiment. Differential: every contrast where\nthe gene is significant (adjusted p < 0.05, |log2FC| >= 1). experiment restricts to one accession; otherwise the\nmax_experiments baseline experiments with the highest TPM are detailed and the rest listed with their maximum.",
"inputSchema": {
"properties": {
"experiment": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Experiment"
},
"gene": {
"title": "Gene",
"type": "string"
},
"max_experiments": {
"default": 20,
"title": "Max Experiments",
"type": "integer"
},
"top_groups": {
"default": 10,
"title": "Top Groups",
"type": "integer"
}
},
"required": [
"gene"
],
"title": "gene_expressionArguments",
"type": "object"
},
"name": "gene_expression",
"outputSchema": null
},
{
"description": "Gene neighbourhood (microsynteny): the gene and its flanking genes, with their orthologues in related genomes\n(pea, faba bean, Medicago, soybean, common bean, lupin) from Ensembl Compara. For each target genome, the collinear block holding most\northologues of the neighbourhood is reported with how many neighbours are conserved there, so a candidate gene can\nbe checked for a conserved genomic context. flank: genes each side (default 8, max 25). targets: Ensembl genome\nnames (default ['pisum_sativum', 'vicia_faba', 'medicago_truncatula', 'glycine_max', 'phaseolus_vulgaris', 'lupinus_angustifolius']).",
"inputSchema": {
"properties": {
"flank": {
"default": 8,
"title": "Flank",
"type": "integer"
},
"gene": {
"title": "Gene",
"type": "string"
},
"targets": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Targets"
}
},
"required": [
"gene"
],
"title": "gene_neighbourhoodArguments",
"type": "object"
},
"name": "gene_neighbourhood",
"outputSchema": null
},
{
"description": "Papers mentioning a gene: Europe PMC search for its gene IDs (all versions, in open-access full text) and its\nname/symbols (in title or abstract, with a legume crop or genus name). Each paper says whether it matched an ID or a\nname. Name matches can be another gene with the same symbol: check the abstract.",
"inputSchema": {
"properties": {
"gene": {
"title": "Gene",
"type": "string"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
}
},
"required": [
"gene"
],
"title": "gene_papersArguments",
"type": "object"
},
"name": "gene_papers",
"outputSchema": null
},
{
"description": "Plant Reactome metabolic and signalling pathways of a gene (Gramene), with the top-level category and a link\nto the pathway diagram. gene: an Ensembl Plants gene ID or a gene name/symbol. Pathways are projected from rice\nby orthology, so say they are inferred. Use pathway_genes for the reverse (all genes of a pathway).",
"inputSchema": {
"properties": {
"gene": {
"title": "Gene",
"type": "string"
}
},
"required": [
"gene"
],
"title": "gene_pathwaysArguments",
"type": "object"
},
"name": "gene_pathways",
"outputSchema": null
},
{
"description": "Genes overlapping a region of one Ensembl Plants genome (max 5 Mb). species is an Ensembl name, e.g.\n'pisum_sativum', 'vicia_faba', 'glycine_max' or 'lupinus_angustifolius'; chromosome names as in that assembly. Chromosome names differ by assembly: pea 1LG6..7LG7, narrow-leafed lupin LG01..LG20, soybean 1..20; faba bean uses ENA sequence accessions (e.g. OX451735.1).",
"inputSchema": {
"properties": {
"chromosome": {
"title": "Chromosome",
"type": "string"
},
"end": {
"title": "End",
"type": "integer"
},
"limit": {
"default": 200,
"title": "Limit",
"type": "integer"
},
"species": {
"title": "Species",
"type": "string"
},
"start": {
"title": "Start",
"type": "integer"
}
},
"required": [
"species",
"chromosome",
"start",
"end"
],
"title": "genes_in_regionArguments",
"type": "object"
},
"name": "genes_in_region",
"outputSchema": null
},
{
"description": "Find genes by function: GO term, InterPro or Pfam domain (accession or words, e.g. 'NB-ARC', 'IPR002182',\n'GO:0009414', 'disease resistance', 'MADS-box') or Plant Reactome pathway ('gibberellin biosynthesis',\nR-TAE-...; kind='pathway'). kind: GO, InterPro, Pfam or pathway (default: GO + InterPro + Pfam). Optional species\n(Ensembl name) and region (chromosome, start, end in bp on the Ensembl/RefSeq v1.0 assembly) filters, e.g. all\nNLR genes in a QTL interval. Returns matching genes with location, matched terms and genome browser link, plus\nfacet counts by species, chromosome and term. Annotations are electronic (InterProScan, GO from InterPro2GO).",
"inputSchema": {
"properties": {
"chromosome": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Chromosome"
},
"end": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "End"
},
"kind": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Kind"
},
"limit": {
"default": 200,
"title": "Limit",
"type": "integer"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
},
"start": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Start"
},
"term": {
"title": "Term",
"type": "string"
}
},
"required": [
"term"
],
"title": "genes_with_annotationArguments",
"type": "object"
},
"name": "genes_with_annotation",
"outputSchema": null
},
{
"description": "Genebank accessions from Genesys (Crop Trust), live: full passport data (holder, accession number and names,\ntaxon, biological status, country and site of origin, coordinates, pedigree), whether the accession is available,\nin the Multilateral System (SMTA) and safety-duplicated in Svalbard, whether the holder takes requests through\nGenesys, a DOI where assigned, and the climate at the collection site (WorldClim: mean temperature, temperature\nextremes, precipitation). accession: accession number (e.g. 'PI 591780', 'IG 32990'); holder: FAO WIEWS code\n(e.g. USA029, LBN002, AUS165) to make it unique; name: free text (e.g. 'Chinese Spring') when the number is not\nknown; crop: Genesys crop code (wheat, barley, chickpea, lentil, pea ...) to narrow a name search.",
"inputSchema": {
"properties": {
"accession": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Accession"
},
"crop": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Crop"
},
"holder": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Holder"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Name"
}
},
"title": "genesys_accessionArguments",
"type": "object"
},
"name": "genesys_accession",
"outputSchema": null
},
{
"description": "Full record for one paper: DOI (10.xxxx/..), PMID (digits) or PMCID (PMC...). Returns the abstract,\nopen-access status and full-text links.",
"inputSchema": {
"properties": {
"identifier": {
"title": "Identifier",
"type": "string"
}
},
"required": [
"identifier"
],
"title": "get_paperArguments",
"type": "object"
},
"name": "get_paper",
"outputSchema": null
},
{
"description": "Members of an LIS legume gene family across chickpea, lentil, pea, soybean and Medicago truncatula. gene: a\nchickpea/lentil/pea/Medicago gene ID, a soybean Ensembl ID (GLYMA_01G000600) or LIS name (Glyma.01G000600), or a\nfamily ID (Legume.fam3.00142). Use it to go from a soybean or pea gene (e.g. from orthologues or expression\nresults) to its chickpea and lentil relatives, or back. Families are broader than orthologue groups. dataset\n(e.g. 'chickpea_desi' or 'chickpea_kabuli_v1') picks one when a Ca_ ID exists in several annotations.",
"inputSchema": {
"properties": {
"dataset": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Dataset"
},
"gene": {
"title": "Gene",
"type": "string"
},
"per_species": {
"default": 25,
"title": "Per Species",
"type": "integer"
}
},
"required": [
"gene"
],
"title": "legume_familyArguments",
"type": "object"
},
"name": "legume_family",
"outputSchema": null
},
{
"description": "Chickpea or lentil gene from the Legume Information System (these genomes are not in Ensembl Plants), or a gene\nof the extra faba bean and lentil gene sets: location, functional description, LIS legume gene family, curated\nlentil symbols and gene lists (flowering, pigment, resistance gene analogues), best protein match to the reference\ngene set, and link. gene: a gene ID (e.g. 'Ca1g000100', 'Lcu.2RBY.1g000010', 'Vfaba.Hedin2.R2.1g000001'), a\ncurated lentil symbol (e.g. 'LcFIE'), an Ensembl faba bean v1 ID (lists its v2/Tiffany counterparts) or words from\nthe description (e.g. 'flowering locus T'). Datasets: 'chickpea' = Cicer arietinum CDC Frontier (kabuli) assembly v3 (gene IDs like Ca1g000100, chromosomes chr1-chr8); 'chickpea_kabuli_v1' = the original kabuli CDC Frontier genes (Ca_00001 IDs used in most chickpea papers) placed on the UWA kabuli v2.6.3 assembly (Ca1-Ca8); 'chickpea_desi' = desi ICC 4958 genes (also Ca_ IDs, but different genes from the kabuli Ca_ IDs) on the UWA desi v3.0 assembly (Ca1-Ca8); 'lentil' = Lens culinaris CDC Redberry assembly v2 (IDs like Lcu.2RBY.1g000010, chromosomes Chr1-Chr7); extra gene sets (no LIS families; best protein match given): 'faba_v2' = faba bean Hedin/2 v2 (Vfaba.Hedin2.R2.1g000001, chr1_partA/B, chr2-chr6; matched to Ensembl Hedin/2 v1), 'faba_tiffany' = faba bean Tiffany (Vfaba.Tiffany.R1..., matched to Ensembl v1), 'lentil_greenstar' = lentil CDC Greenstar (Lcu.1GRN.1g000010) and 'lentil_ervoides' = Lens ervoides IG 72815 (Ler.1DRT.1g000010), both matched to LIS CDC Redberry v2. Gene families (LIS legume.fam3) also cover pea (Cameor, Psat... = Ensembl Plants pisum_sativum IDs), soybean (Wm82.a2, Glyma.01G000600 = Ensembl GLYMA_01G000600) and Medicago truncatula (A17 v5, MtrunA17Chr...).",
"inputSchema": {
"properties": {
"dataset": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Dataset"
},
"gene": {
"title": "Gene",
"type": "string"
},
"limit": {
"default": 20,
"title": "Limit",
"type": "integer"
}
},
"required": [
"gene"
],
"title": "legume_geneArguments",
"type": "object"
},
"name": "legume_gene",
"outputSchema": null
},
{
"description": "Chickpea, lentil or extra faba bean genes in a region (max 5 Mb) with descriptions, gene families, curated lentil\ngene lists and best matches. dataset 'chickpea' (CDC Frontier v3, chromosomes chr1-chr8), 'chickpea_kabuli_v1'\n(UWA kabuli v2.6.3, Ca1-Ca8), 'chickpea_desi' (UWA desi v3.0, Ca1-Ca8), 'lentil' (CDC Redberry v2, Chr1-Chr7),\n'lentil_greenstar' (Lcu.1GRN.Chr1-7), 'lentil_ervoides' (Ler.1DRT.Chr1-7), 'faba_v2' (Hedin/2 v2, chr1_partA,\nchr1_partB, chr2-chr6) or 'faba_tiffany' (chr1S, chr1L, chr2-chr6). Chromosome numbers alone (e.g. '4') are\naccepted for chickpea and lentil.",
"inputSchema": {
"properties": {
"chromosome": {
"title": "Chromosome",
"type": "string"
},
"dataset": {
"title": "Dataset",
"type": "string"
},
"end": {
"title": "End",
"type": "integer"
},
"limit": {
"default": 300,
"title": "Limit",
"type": "integer"
},
"start": {
"title": "Start",
"type": "integer"
}
},
"required": [
"dataset",
"chromosome",
"start",
"end"
],
"title": "legume_genes_in_regionArguments",
"type": "object"
},
"name": "legume_genes_in_region",
"outputSchema": null
},
{
"description": "The same gene across chickpea or pea assemblies and annotation versions, from LIS pangene sets (synteny-aware\nclustering). Chickpea (Cicer.pan3): kabuli CDC Frontier v3 (Ca1g000200), v1/v2 (Ca_00003), desi ICC 4958 (Ca_) and\nwild C. reticulatum (Cr1g…) and C. echinospermum (Ce…). Pea (Pisum.pan1): Cameor v1a (Psat1g000360 = Ensembl\npisum_sativum), Cameor v2 (Psat.1g…), JI2822 (PSAT_LOCUS… = Ensembl JI2822) and ZW6 (Psat01G…). gene: any of these\nIDs or a pangene ID. Use it to convert IDs between assemblies (e.g. a kabuli Ca_ ID from a paper to the v3 gene\nwith expression data). dataset ('chickpea_desi', 'chickpea_kabuli_v1', ...) disambiguates a shared Ca_ ID.",
"inputSchema": {
"properties": {
"dataset": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Dataset"
},
"gene": {
"title": "Gene",
"type": "string"
}
},
"required": [
"gene"
],
"title": "legume_pangeneArguments",
"type": "object"
},
"name": "legume_pangene",
"outputSchema": null
},
{
"description": "QTL and GWAS results for legumes: soybean (SoyBase QTL on genetic maps plus GWAS; marker positions on Wm82.a2 = Ensembl glycine_max), common bean (G19833 v1 = Ensembl phaseolus_vulgaris; some GWAS on G19833 v2), cowpea (IT97K-499-35 v1) and peanut (Tifrunner v2) from LIS; faba bean QTL markers from 56 studies (Faba Bean Genome Consortium compilation, positions on Hedin/2 v2 and projected to the Ensembl Hedin/2 v1 assembly); lentil protein and amino acid GWAS on the diversity panel (KnowPulse, CDC Redberry v2 = LIS lentil genes); chickpea, lentil, pea, faba bean, lupin, grass pea and pigeonpea QTL and GWAS from pulsedb.org (Cool Season Food Legume Database). Search by trait words (e.g.\n'seed oil', 'pod dehiscence', 'chocolate spot', 'lysine'; soybean traits use SoyBase names such as 'SCN', 'SDS',\n'Sclero', so check legume_qtl_traits) and/or a physical region (species + chromosome as in the\nmarker assembly or the Ensembl name, start, end). Returns each QTL (genetic map, linkage group, cM interval,\nmarkers) or marker-trait association (marker, p-value where reported) with study, DOI and marker positions;\nensembl_region gives genes_in_region arguments where the markers are on the Ensembl assembly (faba bean: positions\nprojected from Hedin/2 v2 to v1 through gene matches, approximate), lis_region gives legume_genes_in_region\narguments (lentil).",
"inputSchema": {
"properties": {
"chromosome": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Chromosome"
},
"end": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "End"
},
"limit": {
"default": 30,
"title": "Limit",
"type": "integer"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
},
"start": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Start"
},
"trait": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Trait"
}
},
"title": "legume_qtlArguments",
"type": "object"
},
"name": "legume_qtl",
"outputSchema": null
},
{
"description": "Traits with QTL or GWAS results, with counts per species (soybean (SoyBase QTL on genetic maps plus GWAS; marker positions on Wm82.a2 = Ensembl glycine_max), common bean (G19833 v1 = Ensembl phaseolus_vulgaris; some GWAS on G19833 v2), cowpea (IT97K-499-35 v1) and peanut (Tifrunner v2) from LIS; faba bean QTL markers from 56 studies (Faba Bean Genome Consortium compilation, positions on Hedin/2 v2 and projected to the Ensembl Hedin/2 v1 assembly); lentil protein and amino acid GWAS on the diversity panel (KnowPulse, CDC Redberry v2 = LIS lentil genes); chickpea, lentil, pea, faba bean, lupin, grass pea and pigeonpea QTL and GWAS from pulsedb.org (Cool Season Food Legume Database)).\nquery filters trait names (e.g. 'seed', 'rust').",
"inputSchema": {
"properties": {
"query": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Query"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
}
},
"title": "legume_qtl_traitsArguments",
"type": "object"
},
"name": "legume_qtl_traits",
"outputSchema": null
},
{
"description": "Narrow-leafed lupin (Lupinus angustifolius) genetic map: 9,972 markers (DArTseq SNP/PAV, Fluidigm SNP, indel,\nSSR, gene-based) and domestication loci (Tardus and Lentus pod shattering, Leucospermus white flower/seed,\nIucundus low alkaloid, Mollis soft seed, Ku vernalisation independence, Lanr1 anthracnose resistance) on the\n97L380 RIL map (83A:476 x P27255), with positions on the Tanjil reference (= Ensembl Plants lupinus_angustifolius,\nLG01-LG20) and Medicago Mt4.0 hits. Search by marker name (exact or prefix), trait words (e.g. 'alkaloid',\n'pod shattering'), Tanjil region (chromosome LGxx + start/end) or map interval (chromosome + cm_start/cm_end).\nFor trait loci and unplaced markers the physical interval comes from the nearest anchored map neighbours, with\ngenes_in_region arguments.",
"inputSchema": {
"properties": {
"chromosome": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Chromosome"
},
"cm_end": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Cm End"
},
"cm_start": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Cm Start"
},
"end": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "End"
},
"limit": {
"default": 50,
"title": "Limit",
"type": "integer"
},
"marker": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Marker"
},
"start": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "Start"
},
"trait": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Trait"
}
},
"title": "lupin_markersArguments",
"type": "object"
},
"name": "lupin_markers",
"outputSchema": null
},
{
"description": "Orthologues of a gene from Ensembl Plants Compara (gene trees across plant genomes), e.g. the Brassica copies\nof an Arabidopsis gene. gene: Ensembl ID or name; target_species: Ensembl name to restrict to (e.g.\n'medicago_truncatula' or 'pisum_sativum'). Returns orthologue IDs, species, relationship (one2one, one2many, many2many).",
"inputSchema": {
"properties": {
"gene": {
"title": "Gene",
"type": "string"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
},
"target_species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Target Species"
}
},
"required": [
"gene"
],
"title": "orthologuesArguments",
"type": "object"
},
"name": "orthologues",
"outputSchema": null
},
{
"description": "SNP haplotypes of a gene across a pulse diversity panel: accessions grouped by their SNP alleles in the gene\n+-2 kb (MAF >= 0.02, <= 20% missing), each haplotype with size, number of alternative alleles, whether it is\nreference-like and its accessions, plus the SNPs (position, alleles, frequency). Panels: 'lentil_ldp' = lentil diversity panel, 324 accessions, exome capture, CDC Redberry v2 (= LIS lentil gene IDs; KnowPulse); 'lentil_activate' = lentil diversity panel + ACTIVATE lines, 521 accessions, CDC Greenstar (Lcu.1GRN IDs; KnowPulse); 'faba_norfab' = NORFAB faba bean panel, 196 accessions shown as 'name, origin country (Core code)' from Skovbjerg et al. 2023 Supplementary File 1 where listed, SPET, Ensembl Hedin/2 v1 (Aarhus University).\ngene: a lentil CDC Redberry v2 ID (Lcu.2RBY.1g000010), a CDC Greenstar ID (Lcu.1GRN.1g000010, for the\nLDP + ACTIVATE panel), a curated lentil symbol (e.g. LcFIE), or an Ensembl faba bean v1 ID\n(Vfaba.Hedin2.R1.1g000010, NORFAB). Matching genes in the other lentil assembly are tried too.",
"inputSchema": {
"properties": {
"gene": {
"title": "Gene",
"type": "string"
},
"members": {
"default": 30,
"title": "Members",
"type": "integer"
},
"panel": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Panel"
}
},
"required": [
"gene"
],
"title": "panel_haplotypesArguments",
"type": "object"
},
"name": "panel_haplotypes",
"outputSchema": null
},
{
"description": "Genes in a Plant Reactome pathway: pathway is a name or words from it ('jasmonic acid biosynthesis',\n'gibberellin', 'flavonoid') or a stable ID (R-TAE-1119332). species: a species name as Plant Reactome writes it\n('Triticum aestivum', 'Brassica napus', 'Glycine max'); default all species loaded for this site. Matching pathways\nare listed with their genes per species. Membership is projected from rice by orthology.",
"inputSchema": {
"properties": {
"limit": {
"default": 200,
"title": "Limit",
"type": "integer"
},
"pathway": {
"title": "Pathway",
"type": "string"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
}
},
"required": [
"pathway"
],
"title": "pathway_genesArguments",
"type": "object"
},
"name": "pathway_genes",
"outputSchema": null
},
{
"description": "Interactive gene view for one pulse and legume gene: a relationship map of its orthologues across legumes (Ensembl Compara), members of its LIS legume gene family (chickpea, lentil, pea, soybean, Medicago), Arabidopsis function, expression contrasts and recent papers, with tabs for the gene family by species and baseline expression (LIS chickpea and pea atlases, Expression Atlas). Clients that support MCP Apps show it in the chat; the result also lists the nodes, the panel data and the gene page link (page) to share. gene: gene name or Ensembl/LIS ID.",
"inputSchema": {
"properties": {
"gene": {
"title": "Gene",
"type": "string"
}
},
"required": [
"gene"
],
"title": "pulse_gene_viewArguments",
"type": "object"
},
"name": "pulse_gene_view",
"outputSchema": null
},
{
"description": "Full-text search across all askPulse resources (genes, germplasm, genotyping datasets, files).\n\nFilters (exact values): database e.g. 'Ensembl Plants', 'Legume Information System', 'GBIF genebank accessions';\nentry_type e.g. 'Gene annotation', 'Germplasm', 'Genotyping Experiment', 'File';\nspecies e.g. 'Pisum sativum', 'Vicia faba', 'Glycine max'. Returns total count, facet counts and the top hits with source URLs.",
"inputSchema": {
"properties": {
"database": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Database"
},
"entry_type": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Entry Type"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"query": {
"title": "Query",
"type": "string"
},
"species": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Species"
}
},
"required": [
"query"
],
"title": "search_dataArguments",
"type": "object"
},
"name": "search_data",
"outputSchema": null
},
{
"description": "Search publications and preprints in Europe PMC (PubMed, PMC, bioRxiv and others).\n\nquery: free text or Europe PMC syntax (e.g. 'grain size QTL 6A', 'TITLE:\"pan-genome\"').\ngene: optional gene name or Ensembl ID; its curated synonyms and RefSeq IDs are OR-ed into the query\n(e.g. gene='GLYMA_01G000600').\nWords are matched in title and abstract; full_text=True also searches open-access full text.\ncrop_only requires a legume crop or genus name in title or abstract. sort: 'relevance', 'date' (newest first) or 'cited'.\nReturns hit count and papers with DOI/PMID, year, journal, open-access flag, citations and a short abstract.",
"inputSchema": {
"properties": {
"crop_only": {
"default": true,
"title": "Crop Only",
"type": "boolean"
},
"from_year": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": null,
"title": "From Year"
},
"full_text": {
"default": false,
"title": "Full Text",
"type": "boolean"
},
"gene": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Gene"
},
"limit": {
"default": 10,
"title": "Limit",
"type": "integer"
},
"open_access_only": {
"default": false,
"title": "Open Access Only",
"type": "boolean"
},
"query": {
"title": "Query",
"type": "string"
},
"sort": {
"default": "relevance",
"title": "Sort",
"type": "string"
}
},
"required": [
"query"
],
"title": "search_literatureArguments",
"type": "object"
},
"name": "search_literature",
"outputSchema": null
},
{
"description": "Trait-associated positions across the genome for a chromosome overview: GWAS marker-trait associations and\npeaks, named trait genes and mapped trait loci held by this site, with chromosome sizes, each with a genome browser\nlink where the assembly is loaded. trait: words to match (e.g. 'height', 'oil', 'alkaloid'); chromosome filters\none chromosome. Map marker tracks are left out unless a chromosome is given. Tracks with karyotype false are on\nanother assembly than chromosome_sizes (pulse: soybean and common bean, Ensembl chromosome numbers; faba bean on\nHedin/2 v2 and projected v1; lentil CDC Redberry v2).",
"inputSchema": {
"properties": {
"chromosome": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Chromosome"
},
"limit": {
"default": 300,
"title": "Limit",
"type": "integer"
},
"trait": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Trait"
}
},
"title": "trait_hitsArguments",
"type": "object"
},
"name": "trait_hits",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:b2e046aba416010cf5d622e59847d6776ee10265901f0e4d013adb007fc2f224 | sha256sum