List all resources, or create a new resource.

GET /api/t/?inputDataFormat=%22FASTA%22
HTTP 200 OK
Allow: GET, POST, HEAD, OPTIONS
Content-Type: application/json
Vary: Accept

{
    "count": 596,
    "next": "?page=2",
    "previous": null,
    "list": [
        {
            "name": "HMMER3",
            "description": "This tool is used for searching sequence databases for homologs of protein sequences, and for making protein sequence alignments. It implements methods using probabilistic models called profile hidden Markov models. The new HMMER3 project, HMMER is now as fast as BLAST for protein search.",
            "homepage": "http://hmmer.org/",
            "biotoolsID": "hmmer3",
            "biotoolsCURIE": "biotools:hmmer3",
            "version": [
                "3.1b1"
            ],
            "otherID": [],
            "relation": [],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0335",
                            "term": "Formatting"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0863",
                                "term": "Sequence alignment"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0863",
                                "term": "Sequence alignment"
                            },
                            "format": []
                        }
                    ],
                    "note": "alimask is used to apply a mask line to a multiple sequence alignment, based on provided alignment or model coordinates.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0492",
                            "term": "Multiple sequence alignment"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0850",
                                "term": "Sequence set"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1916",
                                "term": "Alignment"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1961",
                                    "term": "Stockholm format"
                                }
                            ]
                        }
                    ],
                    "note": "Align sequences to a profile HMM The < hmmfile > should contain only a single profile.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0296",
                            "term": "Sequence profile generation"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0863",
                                "term": "Sequence alignment"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "note": "Construct profile HMM(s) from multiple sequence alignment(s).",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0336",
                            "term": "Format validation"
                        },
                        {
                            "uri": "http://edamontology.org/operation_3434",
                            "term": "Conversion"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1370",
                                    "term": "HMMER format"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_3329",
                                    "term": "HMMER3"
                                }
                            ]
                        }
                    ],
                    "note": "The hmmconvert utility converts an input profile file to different HMMER formats.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0230",
                            "term": "Sequence generation"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2044",
                                "term": "Sequence"
                            },
                            "format": []
                        }
                    ],
                    "note": "Sample sequences from a profile HMM.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_2422",
                            "term": "Data retrieval"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0968",
                                "term": "Keyword"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "note": "Retrieve profile HMM(s) from a file.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_2238",
                            "term": "Statistical calculation"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1361",
                                "term": "Position frequency matrix"
                            },
                            "format": []
                        }
                    ],
                    "note": "Given an HMM, produce data required to build an HMM logo.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_2421",
                            "term": "Database search"
                        }
                    ],
                    "input": [],
                    "output": [],
                    "note": "Daemon for searching a protein query against a protein database.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0335",
                            "term": "Formatting"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_3329",
                                    "term": "HMMER3"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2048",
                                "term": "Report"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0955",
                                "term": "Data index"
                            },
                            "format": []
                        }
                    ],
                    "note": "Prepare an HMM database for hmmscan.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_2421",
                            "term": "Database search"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2976",
                                "term": "Protein sequence"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1927",
                                    "term": "EMBL format"
                                },
                                {
                                    "uri": "http://edamontology.org/format_1936",
                                    "term": "GenBank format"
                                },
                                {
                                    "uri": "http://edamontology.org/format_1963",
                                    "term": "UniProtKB format"
                                },
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0957",
                                "term": "Database metadata"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2080",
                                "term": "Database search results"
                            },
                            "format": []
                        }
                    ],
                    "note": "Search protein sequence(s) against a protein profile database. query sequence to search the target database of profiles Needs to have those four auxiliary binary files generated by hmmpress. The output format is designed to be human-readable, but is often so voluminous that reading it is impractical.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_2421",
                            "term": "Database search"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0850",
                                "term": "Sequence set"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2080",
                                "term": "Database search results"
                            },
                            "format": []
                        }
                    ],
                    "note": "Search profile(s) against a sequence database. Query profile to search the target database of sequences. Sequence database. Ranked lists of the sequences with the most significant matches to the profile.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_3481",
                            "term": "Probabilistic sequence generation"
                        },
                        {
                            "uri": "http://edamontology.org/operation_2238",
                            "term": "Statistical calculation"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2048",
                                "term": "Report"
                            },
                            "format": []
                        }
                    ],
                    "note": "Collect score distributions on random sequences. The output is a table of numbers, one row for each model. Four different parametric fits to the score data are tested: (1) maximum likelihood fits to both location (mu/tau) and slope (lambda) parameters; (2) assuming lambda=log 2, maximum likelihood fit to the location parameter only; (3) same but assuming an edge- corrected lambda, using current procedures in H3 [Eddy, 2008]; and (4) using both parameters determined by H3s current procedures.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_2238",
                            "term": "Statistical calculation"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2048",
                                "term": "Report"
                            },
                            "format": []
                        }
                    ],
                    "note": "Display summary statistics for a profile file. Tabular file of summary statistics for each profile.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0338",
                            "term": "Sequence database search"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2976",
                                "term": "Protein sequence"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1233",
                                "term": "Sequence set (protein)"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0857",
                                "term": "Sequence search results"
                            },
                            "format": []
                        }
                    ],
                    "note": "Iteratively search sequence(s) against a protein database. database sequence The output format is designed to be human-readable, but is often so voluminous that reading it is impractical.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0335",
                            "term": "Formatting"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_3494",
                                "term": "DNA sequence"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2044",
                                "term": "Sequence"
                            },
                            "format": []
                        }
                    ],
                    "note": "Build a HMMER binary database file from a sequence file. This binary file may be used as a target database for the DNA search tool nhmmer.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0338",
                            "term": "Sequence database search"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2977",
                                "term": "Nucleic acid sequence"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1234",
                                "term": "Sequence set (nucleic acid)"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0857",
                                "term": "Sequence search results"
                            },
                            "format": []
                        }
                    ],
                    "note": "Search DNA/RNA queries against a DNA/RNA sequence database. nucleic sequence database",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_2421",
                            "term": "Database search"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2977",
                                "term": "Nucleic acid sequence"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1364",
                                "term": "Hidden Markov model"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2080",
                                "term": "Database search results"
                            },
                            "format": []
                        }
                    ],
                    "note": "Search nucleotide sequence(s) against collections of nucleotide profiles. The <hmmdb> needs to be pressed using hmmpress before it can be searched with hmmscan. The output format is designed to be human-readable, but is often so voluminous that reading it is impractical.",
                    "cmd": null
                },
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0338",
                            "term": "Sequence database search"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2976",
                                "term": "Protein sequence"
                            },
                            "format": []
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1233",
                                "term": "Sequence set (protein)"
                            },
                            "format": []
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0857",
                                "term": "Sequence search results"
                            },
                            "format": []
                        }
                    ],
                    "note": "Search protein sequence(s) against a protein sequence database. database of sequences Ranked lists of the sequences with the most significant matches to the query. The output format is designed to be human-readable, but is often so voluminous that reading it is impractical.",
                    "cmd": null
                }
            ],
            "toolType": [
                "Command-line tool",
                "Web application"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_0080",
                    "term": "Sequence analysis"
                },
                {
                    "uri": "http://edamontology.org/topic_0160",
                    "term": "Sequence sites, features and motifs"
                },
                {
                    "uri": "http://edamontology.org/topic_0623",
                    "term": "Gene and protein families"
                }
            ],
            "operatingSystem": [
                "Linux",
                "Windows",
                "Mac"
            ],
            "language": [
                "Perl",
                "C"
            ],
            "license": "Other",
            "collectionID": [
                "HMMER",
                "Animal and Crop Genomics"
            ],
            "maturity": null,
            "cost": null,
            "accessibility": null,
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [
                {
                    "url": "https://github.com/EddyRivasLab/hmmer",
                    "type": [
                        "Repository"
                    ],
                    "note": null
                },
                {
                    "url": "https://github.com/EddyRivasLab/hmmer/issues",
                    "type": [
                        "Issue tracker"
                    ],
                    "note": null
                }
            ],
            "download": [],
            "documentation": [
                {
                    "url": "http://eddylab.org/software/hmmer3/3.1b2/Userguide.pdf",
                    "type": [
                        "User manual"
                    ],
                    "note": "HMMER User Guide"
                },
                {
                    "url": "http://hmmer.org/documentation.html",
                    "type": [
                        "General"
                    ],
                    "note": null
                }
            ],
            "publication": [
                {
                    "doi": "10.1093/nar/gkr367",
                    "pmid": null,
                    "pmcid": null,
                    "type": [
                        "Primary"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "HMMER web server: Interactive sequence similarity searching",
                        "abstract": "HMMER is a software suite for protein sequence similarity searches using probabilistic methods. Previously, HMMER has mainly been available only as a computationally intensive UNIX command-line tool, restricting its use. Recent advances in the software, HMMER3, have resulted in a 100-fold speed gain relative to previous versions. It is now feasible to make efficient profile hidden Markov model (profile HMM) searches via the web. A HMMER web server (http://hmmer.janelia.org) has been designed and implemented such that most protein database searches return within a few seconds. Methods are available for searching either a single protein sequence, multiple protein sequence alignment or profile HMM against a target sequence database, and for searching a protein sequence against Pfam. The web server is designed to cater to a range of different user expertise and accepts batch uploading of multiple queries at once. All search methods are also available as RESTful web services, thereby allowing them to be readily integrated as remotely executed tasks in locally scripted workflows. We have focused on minimizing search times and the ability to rapidly display tabular results, regardless of the number of matches found, developing graphical summaries of the search results to provide quick, intuitive appraisement of them. © 2011 The Author(s).",
                        "date": "2011-07-01T00:00:00Z",
                        "citationCount": 2484,
                        "authors": [
                            {
                                "name": "Finn R.D."
                            },
                            {
                                "name": "Clements J."
                            },
                            {
                                "name": "Eddy S.R."
                            }
                        ],
                        "journal": "Nucleic Acids Research"
                    }
                },
                {
                    "doi": "10.1371/journal.pcbi.1002195",
                    "pmid": "22039361",
                    "pmcid": "PMC3197634",
                    "type": [
                        "Primary"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "Accelerated profile HMM searches",
                        "abstract": "Profile hidden Markov models (profile HMMs) and probabilistic inference methods have made important contributions to the theory of sequence database homology search. However, practical use of profile HMM methods has been hindered by the computational expense of existing software implementations. Here I describe an acceleration heuristic for profile HMMs, the \"multiple segment Viterbi\" (MSV) algorithm. The MSV algorithm computes an optimal sum of multiple ungapped local alignment segments using a striped vector-parallel approach previously described for fast Smith/Waterman alignment. MSV scores follow the same statistical distribution as gapped optimal local alignment scores, allowing rapid evaluation of significance of an MSV score and thus facilitating its use as a heuristic filter. I also describe a 20-fold acceleration of the standard profile HMM Forward/Backward algorithms using a method I call \"sparse rescaling\". These methods are assembled in a pipeline in which high-scoring MSV hits are passed on for reanalysis with the full HMM Forward/Backward algorithm. This accelerated pipeline is implemented in the freely available HMMER3 software package. Performance benchmarks show that the use of the heuristic MSV filter sacrifices negligible sensitivity compared to unaccelerated profile HMM searches. HMMER3 is substantially more sensitive and 100- to 1000-fold faster than HMMER2. HMMER3 is now about as fast as BLAST for protein searches. © 2011 Sean R. Eddy.",
                        "date": "2011-10-01T00:00:00Z",
                        "citationCount": 2414,
                        "authors": [
                            {
                                "name": "Eddy S.R."
                            }
                        ],
                        "journal": "PLoS Computational Biology"
                    }
                }
            ],
            "credit": [
                {
                    "name": "Sean Eddy",
                    "email": "sean@eddylab.org",
                    "url": null,
                    "orcidid": "http://orcid.org/0000-0001-6676-4706",
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": "Person",
                    "typeRole": [
                        "Primary contact"
                    ],
                    "note": null
                }
            ],
            "community": {
                "biolib": {
                    "app_name": "hmmsearch",
                    "author_name": "HMMER",
                    "author_username": "HMMER"
                }
            },
            "owner": "ELIXIR-FR",
            "additionDate": "2015-04-03T13:17:38Z",
            "lastUpdate": "2021-10-15T14:09:31.104633Z",
            "editPermission": {
                "type": "group",
                "authors": [
                    "animalandcropgenomics",
                    "laurasansc"
                ]
            },
            "validated": 1,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "MAFFT",
            "description": "MAFFT (Multiple Alignment using Fast Fourier Transform) is a high speed multiple sequence alignment program.",
            "homepage": "http://mafft.cbrc.jp/alignment/server/index.html",
            "biotoolsID": "MAFFT",
            "biotoolsCURIE": "biotools:MAFFT",
            "version": [],
            "otherID": [],
            "relation": [],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0492",
                            "term": "Multiple sequence alignment"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0863",
                                "term": "Sequence alignment"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0863",
                                "term": "Sequence alignment"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        }
                    ],
                    "note": null,
                    "cmd": null
                }
            ],
            "toolType": [
                "Command-line tool",
                "Web application"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_0080",
                    "term": "Sequence analysis"
                }
            ],
            "operatingSystem": [
                "Linux",
                "Windows",
                "Mac"
            ],
            "language": [
                "Python"
            ],
            "license": "BSD-Source-Code",
            "collectionID": [
                "galaxyPasteur",
                "MAFFT"
            ],
            "maturity": "Mature",
            "cost": "Free of charge",
            "accessibility": "Open access",
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [
                {
                    "url": "https://galaxy.pasteur.fr/tool_runner?tool_id=toolshed.pasteur.fr/repos/fmareuil/mafft/rbc_mafft/7.273.1",
                    "type": [
                        "Galaxy service"
                    ],
                    "note": null
                }
            ],
            "download": [
                {
                    "url": "https://mafft.cbrc.jp/alignment/software/",
                    "type": "Downloads page",
                    "note": null,
                    "version": null
                }
            ],
            "documentation": [
                {
                    "url": "https://mafft.cbrc.jp/alignment/software/tips0.html",
                    "type": [
                        "FAQ"
                    ],
                    "note": null
                }
            ],
            "publication": [
                {
                    "doi": "10.1007/978-1-62703-646-7_8",
                    "pmid": null,
                    "pmcid": null,
                    "type": [
                        "Primary"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "MAFFT: Iterative refinement and additional methods",
                        "abstract": "This chapter outlines several methods implemented in the MAFFT package. MAFFT is a popular multiple sequence alignment (MSA) program with various options for the progressive method, the iterative refinement method and other methods. We first outline basic usage of MAFFT and then describe recent practical extensions, such as dot plot and adjustment of direction in DNA alignment. We also refer to MUSCLE, another high-performance MSA program. © 2014 Springer Science+Business Media, LLC.",
                        "date": "2014-01-01T00:00:00Z",
                        "citationCount": 232,
                        "authors": [
                            {
                                "name": "Katoh K."
                            },
                            {
                                "name": "Standley D.M."
                            }
                        ],
                        "journal": "Methods in Molecular Biology"
                    }
                },
                {
                    "doi": "10.7490/f1000research.1114334.1",
                    "pmid": null,
                    "pmcid": null,
                    "type": [
                        "Other"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": null
                },
                {
                    "doi": "10.1093/bioinformatics/bty121",
                    "pmid": null,
                    "pmcid": null,
                    "type": [
                        "Other"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "Parallelization of MAFFT for large-scale multiple sequence alignments",
                        "abstract": "© The Author(s) 2018. Published by Oxford University Press.Summary: We report an update for the MAFFT multiple sequence alignment program to enable parallel calculation of large numbers of sequences. The G-INS-1 option of MAFFT was recently reported to have higher accuracy than other methods for large data, but this method has been impractical for most large-scale analyses, due to the requirement of large computational resources. We introduce a scalable variant, G-large-INS-1, which has equivalent accuracy to G-INS-1 and is applicable to 50 000 or more sequences.",
                        "date": "2018-07-15T00:00:00Z",
                        "citationCount": 238,
                        "authors": [
                            {
                                "name": "Nakamura T."
                            },
                            {
                                "name": "Yamada K.D."
                            },
                            {
                                "name": "Tomii K."
                            },
                            {
                                "name": "Katoh K."
                            }
                        ],
                        "journal": "Bioinformatics"
                    }
                },
                {
                    "doi": "10.1093/bib/bbx108",
                    "pmid": null,
                    "pmcid": null,
                    "type": [
                        "Other"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "MAFFT online service: Multiple sequence alignment, interactive sequence choice and visualization",
                        "abstract": "© 2017 The Author. Published by Oxford University Press.This article describes several features in the MAFFT online service for multiple sequence alignment (MSA). As a result of recent advances in sequencing technologies, huge numbers of biological sequences are available and the need for MSAs with large numbers of sequences is increasing. To extract biologically relevant information from such data, sophistication of algorithms is necessary but not sufficient. Intuitive and interactive tools for experimental biologists to semiautomatically handle large data are becoming important. We are working on development of MAFFT toward these two directions. Here, we explain (i) the Web interface for recently developed options for large data and (ii) interactive usage to refine sequence data sets and MSAs.",
                        "date": "2018-03-27T00:00:00Z",
                        "citationCount": 1615,
                        "authors": [
                            {
                                "name": "Katoh K."
                            },
                            {
                                "name": "Rozewicki J."
                            },
                            {
                                "name": "Yamada K.D."
                            }
                        ],
                        "journal": "Briefings in Bioinformatics"
                    }
                }
            ],
            "credit": [
                {
                    "name": "Contact Form",
                    "email": null,
                    "url": "https://mafft.cbrc.jp/alignment/software/mailform.html",
                    "orcidid": null,
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": "Person",
                    "typeRole": [
                        "Primary contact"
                    ],
                    "note": null
                }
            ],
            "community": {
                "biolib": {
                    "app_name": "MAFFT",
                    "author_name": "bio-utils",
                    "author_username": "bio-utils"
                }
            },
            "owner": "jison",
            "additionDate": "2017-12-06T18:14:39Z",
            "lastUpdate": "2021-10-15T13:58:17.883534Z",
            "editPermission": {
                "type": "group",
                "authors": [
                    "laurasansc"
                ]
            },
            "validated": 1,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "VarGenius-HZD",
            "description": "VarGenius-HZD allows accurate detection of rare homozygous or hemizygous deletions in targeted sequencing leveraging breadth of coverage.",
            "homepage": "https://github.com/frankMusacchia/VarGenius-HZD",
            "biotoolsID": "vargenius-hzd",
            "biotoolsCURIE": "biotools:vargenius-hzd",
            "version": [],
            "otherID": [],
            "relation": [
                {
                    "biotoolsID": "vargenius",
                    "type": "includedIn"
                }
            ],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_3962",
                            "term": "Deletion detection"
                        },
                        {
                            "uri": "http://edamontology.org/operation_0452",
                            "term": "Indel detection"
                        },
                        {
                            "uri": "http://edamontology.org/operation_3226",
                            "term": "Variant prioritisation"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2534",
                                "term": "Sequence attribute"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        }
                    ],
                    "output": [],
                    "note": null,
                    "cmd": null
                }
            ],
            "toolType": [
                "Plug-in",
                "Command-line tool"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_3676",
                    "term": "Exome sequencing"
                },
                {
                    "uri": "http://edamontology.org/topic_0622",
                    "term": "Genomics"
                },
                {
                    "uri": "http://edamontology.org/topic_3325",
                    "term": "Rare diseases"
                },
                {
                    "uri": "http://edamontology.org/topic_3958",
                    "term": "Copy number variation"
                }
            ],
            "operatingSystem": [
                "Mac",
                "Linux",
                "Windows"
            ],
            "language": [
                "Perl",
                "R"
            ],
            "license": "GPL-3.0",
            "collectionID": [],
            "maturity": null,
            "cost": "Free of charge",
            "accessibility": null,
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [],
            "download": [
                {
                    "url": "https://github.com/frankMusacchia/VarGenius-HZD",
                    "type": "Downloads page",
                    "note": null,
                    "version": null
                }
            ],
            "documentation": [
                {
                    "url": "https://www.biorxiv.org/content/10.1101/2021.06.21.449209v1.full",
                    "type": [
                        "General"
                    ],
                    "note": null
                }
            ],
            "publication": [
                {
                    "doi": "10.1101/2021.06.21.449209",
                    "pmid": null,
                    "pmcid": null,
                    "type": [],
                    "version": null,
                    "note": null,
                    "metadata": null
                }
            ],
            "credit": [
                {
                    "name": "Francesco Musacchia",
                    "email": "francesco.musacchia@iit.it",
                    "url": null,
                    "orcidid": "https://orcid.org/0000-0001-9440-1080",
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": "Person",
                    "typeRole": [],
                    "note": null
                }
            ],
            "community": null,
            "owner": "Jennifer",
            "additionDate": "2021-10-07T17:25:10.116881Z",
            "lastUpdate": "2021-10-08T08:48:51.354364Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 0,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": "tool"
        },
        {
            "name": "Nerpa",
            "description": "Nerpa is a tool for linking biosynthetic gene clusters (BGCs) to known nonribosomal peptides (NRPs). BGCs are predicted in genome sequences (FASTA or GBK) with antiSMASH. Known NRPs are accepted in the SMILES format and processed with rBAN.",
            "homepage": "https://cab.spbu.ru/software/nerpa/",
            "biotoolsID": "nerpa",
            "biotoolsCURIE": "biotools:nerpa",
            "version": [
                "1.0.0"
            ],
            "otherID": [],
            "relation": [
                {
                    "biotoolsID": "antismash",
                    "type": "uses"
                },
                {
                    "biotoolsID": "nrpspredictor2",
                    "type": "uses"
                }
            ],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0361",
                            "term": "Sequence annotation"
                        },
                        {
                            "uri": "http://edamontology.org/operation_0292",
                            "term": "Sequence alignment"
                        },
                        {
                            "uri": "http://edamontology.org/operation_3929",
                            "term": "Metabolic pathway prediction"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1463",
                                "term": "Small molecule structure"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1196",
                                    "term": "SMILES"
                                }
                            ]
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0925",
                                "term": "Sequence assembly"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                },
                                {
                                    "uri": "http://edamontology.org/format_1936",
                                    "term": "GenBank format"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0893",
                                "term": "Sequence-structure alignment"
                            },
                            "format": []
                        }
                    ],
                    "note": "Run Nerpa on antiSMASH-generated genome predictions (initially in FASTA or GenBank format) and structures of nonribosomal peptides (NRPs) written in the SMILES format in a single tab-separated file. Nerpa will report the most likely matches of the antiSMASH-predicted NRP biosynthetic gene clusters against NRP structures.",
                    "cmd": "nerpa -a genome_predictions --smiles-tsv structures_info.tsv"
                }
            ],
            "toolType": [
                "Command-line tool"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_0154",
                    "term": "Small molecules"
                },
                {
                    "uri": "http://edamontology.org/topic_3172",
                    "term": "Metabolomics"
                },
                {
                    "uri": "http://edamontology.org/topic_0622",
                    "term": "Genomics"
                },
                {
                    "uri": "http://edamontology.org/topic_0091",
                    "term": "Bioinformatics"
                }
            ],
            "operatingSystem": [
                "Linux",
                "Mac"
            ],
            "language": [
                "C++",
                "Python"
            ],
            "license": "Other",
            "collectionID": [],
            "maturity": "Emerging",
            "cost": "Free of charge",
            "accessibility": "Open access",
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [
                {
                    "url": "https://github.com/ablab/nerpa",
                    "type": [
                        "Repository",
                        "Issue tracker"
                    ],
                    "note": null
                },
                {
                    "url": "https://cab.spbu.ru/software/nerpa/",
                    "type": [
                        "Other"
                    ],
                    "note": "The main tool page at the maintainer's website."
                }
            ],
            "download": [
                {
                    "url": "https://github.com/ablab/nerpa/releases/tag/v1.0.0",
                    "type": "Source code",
                    "note": null,
                    "version": "1.0.0"
                }
            ],
            "documentation": [
                {
                    "url": "https://github.com/ablab/nerpa/blob/master/README.md",
                    "type": [
                        "Command-line options"
                    ],
                    "note": null
                }
            ],
            "publication": [],
            "credit": [
                {
                    "name": "Alexey Gurevich",
                    "email": "aleksey.gurevich@spbu.ru",
                    "url": "https://cab.spbu.ru/employees/alexey-gurevich/",
                    "orcidid": "http://orcid.org/0000-0002-5855-3519",
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": "Person",
                    "typeRole": [
                        "Primary contact",
                        "Maintainer",
                        "Developer"
                    ],
                    "note": "Senior Research Scientist at Center for Algorithmic Biotechnology, St. Petersburg State University, Russia"
                }
            ],
            "community": null,
            "owner": "alexeigurevich",
            "additionDate": "2021-10-02T09:03:46.462279Z",
            "lastUpdate": "2021-10-02T09:05:04.307995Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 0,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "Bwa-mem2",
            "description": "Bwa-mem2 is the next version of the bwa-mem algorithm in bwa. It produces alignment identical to bwa and is ~1.3-3.1x faster depending on the use-case,  dataset and the running machine.",
            "homepage": "https://github.com/bwa-mem2/bwa-mem2",
            "biotoolsID": "bwa-mem2",
            "biotoolsCURIE": "biotools:bwa-mem2",
            "version": [
                "2.2.1"
            ],
            "otherID": [],
            "relation": [],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0292",
                            "term": "Sequence alignment"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1383",
                                "term": "Nucleic acid sequence alignment"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        }
                    ],
                    "output": [],
                    "note": null,
                    "cmd": null
                }
            ],
            "toolType": [
                "Command-line tool"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_0102",
                    "term": "Mapping"
                }
            ],
            "operatingSystem": [],
            "language": [
                "C++",
                "C"
            ],
            "license": "MIT",
            "collectionID": [],
            "maturity": null,
            "cost": null,
            "accessibility": null,
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [],
            "download": [
                {
                    "url": "https://github.com/bwa-mem2/bwa-mem2/releases/tag/v2.2.1",
                    "type": "Source code",
                    "note": null,
                    "version": "2.2.1"
                }
            ],
            "documentation": [
                {
                    "url": "https://github.com/bwa-mem2/bwa-mem2",
                    "type": [
                        "Command-line options"
                    ],
                    "note": null
                }
            ],
            "publication": [
                {
                    "doi": "10.1109/IPDPS.2019.00041",
                    "pmid": null,
                    "pmcid": null,
                    "type": [
                        "Primary"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "Efficient architecture-aware acceleration of BWA-MEM for multicore systems",
                        "abstract": "© 2019 IEEEInnovations in Next-Generation Sequencing are enabling generation of DNA sequence data at ever faster rates and at very low cost. For example, the Illumina NovaSeq 6000 sequencer can generate 6 Terabases of data in less than two days, sequencing nearly 20 Billion short DNA fragments called reads at the low cost of $1000 per human genome. Large sequencing centers typically employ hundreds of such systems. Such high-throughput and low-cost generation of data underscores the need for commensurate acceleration in downstream computational analysis of the sequencing data. A fundamental step in downstream analysis is mapping of the reads to a long reference DNA sequence, such as a reference human genome. Sequence mapping is a compute-intensive step that accounts for more than 30% of the overall time of the GATK (Genome Analysis ToolKit) best practices workflow. BWA-MEM is one of the most widely used tools for sequence mapping and has tens of thousands of users. In this work, we focus on accelerating BWA-MEM through an efficient architecture aware implementation, while maintaining identical output. The volume of data requires distributed computing and is usually processed on clusters or cloud deployments with multicore processors usually being the platform of choice. Since the application can be easily parallelized across multiple sockets (even across distributed memory systems) by simply distributing the reads equally, we focus on performance improvements on a single socket multicore processor. BWA-MEM run time is dominated by three kernels, collectively responsible for more than 85% of the overall compute time. We improved the performance of the three kernels by 1) using techniques to improve cache reuse, 2) simplifying the algorithms, 3) replacing many small memory allocations with a few large contiguous ones to improve hardware prefetching of data, 4) software prefetching of data, and 5) utilization of SIMD wherever applicable and massive reorganization of the source code to enable these improvements. As a result, we achieved nearly 2×, 183×, and 8× speedups on the three kernels, respectively, resulting in up to 3.5× and 2.4× speedups on end-to-end compute time over the original BWA-MEM on single thread and single socket of Intel Xeon Skylake processor. To the best of our knowledge, this is the highest reported speedup over BWA-MEM (running on a single CPU) while using a single CPU or a single CPU-single GPGPU/FPGA combination.",
                        "date": "2019-05-01T00:00:00Z",
                        "citationCount": 18,
                        "authors": [
                            {
                                "name": "Md V."
                            },
                            {
                                "name": "Misra S."
                            },
                            {
                                "name": "Li H."
                            },
                            {
                                "name": "Aluru S."
                            }
                        ],
                        "journal": "Proceedings - 2019 IEEE 33rd International Parallel and Distributed Processing Symposium, IPDPS 2019"
                    }
                }
            ],
            "credit": [],
            "community": null,
            "owner": "gallardoalba",
            "additionDate": "2021-10-01T13:13:53.151274Z",
            "lastUpdate": "2021-10-01T13:13:53.154131Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 0,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "SPOT-RNA2",
            "description": "Improved RNA Secondary Secondary Structure Prediction using Evolutionary Profile, Mutational Coupling and Two-dimensional Transfer Learning",
            "homepage": "https://sparks-lab.org/server/spot-rna2/",
            "biotoolsID": "spot-rna2",
            "biotoolsCURIE": "biotools:spot-rna2",
            "version": [],
            "otherID": [],
            "relation": [],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0278",
                            "term": "RNA secondary structure prediction"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_3495",
                                "term": "RNA sequence"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        }
                    ],
                    "output": [],
                    "note": null,
                    "cmd": null
                }
            ],
            "toolType": [],
            "topic": [],
            "operatingSystem": [],
            "language": [],
            "license": null,
            "collectionID": [],
            "maturity": null,
            "cost": null,
            "accessibility": null,
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [
                {
                    "url": "https://github.com/jaswindersingh2/SPOT-RNA2",
                    "type": [
                        "Repository"
                    ],
                    "note": null
                }
            ],
            "download": [
                {
                    "url": "https://github.com/jaswindersingh2/SPOT-RNA2",
                    "type": "Software package",
                    "note": null,
                    "version": null
                }
            ],
            "documentation": [
                {
                    "url": "https://github.com/jaswindersingh2/SPOT-RNA2",
                    "type": [
                        "User manual"
                    ],
                    "note": null
                }
            ],
            "publication": [
                {
                    "doi": "10.1093/bioinformatics/btab165",
                    "pmid": "33704363",
                    "pmcid": null,
                    "type": [
                        "Primary"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": null
                }
            ],
            "credit": [
                {
                    "name": "Jaswinder Singh",
                    "email": "jaswinder.singh3@griffithuni.edu.au",
                    "url": null,
                    "orcidid": "https://orcid.org/0000-0003-4974-5188",
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": null,
                    "typeRole": [],
                    "note": null
                }
            ],
            "community": null,
            "owner": "jaswinder_singh",
            "additionDate": "2021-09-28T10:58:05.452983Z",
            "lastUpdate": "2021-09-28T10:58:05.455389Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 0,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "SPOT-RNA",
            "description": "RNA secondary structure predictor",
            "homepage": "http://sparks-lab.org/jaswinder/server/SPOT-RNA/",
            "biotoolsID": "SPOT-RNA",
            "biotoolsCURIE": "biotools:SPOT-RNA",
            "version": [],
            "otherID": [
                {
                    "value": "doi:10.1038/s41467-019-13395-9",
                    "type": "doi",
                    "version": null
                }
            ],
            "relation": [],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0278",
                            "term": "RNA secondary structure prediction"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_3495",
                                "term": "RNA sequence"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0880",
                                "term": "RNA secondary structure"
                            },
                            "format": []
                        }
                    ],
                    "note": null,
                    "cmd": null
                }
            ],
            "toolType": [
                "Command-line tool"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_0097",
                    "term": "Nucleic acid structure analysis"
                }
            ],
            "operatingSystem": [
                "Linux"
            ],
            "language": [
                "Python"
            ],
            "license": null,
            "collectionID": [],
            "maturity": "Mature",
            "cost": "Free of charge",
            "accessibility": null,
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [
                {
                    "url": "http://sparks-lab.org/jaswinder/server/SPOT-RNA/",
                    "type": [
                        "Service"
                    ],
                    "note": null
                }
            ],
            "download": [
                {
                    "url": "https://github.com/jaswindersingh2/SPOT-RNA",
                    "type": "Downloads page",
                    "note": null,
                    "version": null
                }
            ],
            "documentation": [
                {
                    "url": "https://github.com/jaswindersingh2/SPOT-RNA/blob/master/README.md",
                    "type": [
                        "User manual"
                    ],
                    "note": null
                }
            ],
            "publication": [
                {
                    "doi": "10.1038/s41467-019-13395-9",
                    "pmid": "31776342",
                    "pmcid": "PMC6881452",
                    "type": [
                        "Primary"
                    ],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "RNA secondary structure prediction using an ensemble of two-dimensional deep neural networks and transfer learning",
                        "abstract": "© 2019, The Author(s).The majority of our human genome transcribes into noncoding RNAs with unknown structures and functions. Obtaining functional clues for noncoding RNAs requires accurate base-pairing or secondary-structure prediction. However, the performance of such predictions by current folding-based algorithms has been stagnated for more than a decade. Here, we propose the use of deep contextual learning for base-pair prediction including those noncanonical and non-nested (pseudoknot) base pairs stabilized by tertiary interactions. Since only < 250 nonredundant, high-resolution RNA structures are available for model training, we utilize transfer learning from a model initially trained with a recent high-quality bpRNA dataset of > 10,000 nonredundant RNAs made available through comparative analysis. The resulting method achieves large, statistically significant improvement in predicting all base pairs, noncanonical and non-nested base pairs in particular. The proposed method (SPOT-RNA), with a freely available server and standalone software, should be useful for improving RNA structure modeling, sequence alignment, and functional annotations.",
                        "date": "2019-12-01T00:00:00Z",
                        "citationCount": 38,
                        "authors": [
                            {
                                "name": "Singh J."
                            },
                            {
                                "name": "Hanson J."
                            },
                            {
                                "name": "Paliwal K."
                            },
                            {
                                "name": "Zhou Y."
                            }
                        ],
                        "journal": "Nature Communications"
                    }
                }
            ],
            "credit": [
                {
                    "name": "Jaswinder Singh",
                    "email": "jaswinder.singh3@griffithuni.edu.au",
                    "url": "http://sparks-lab.org",
                    "orcidid": "https://orcid.org/0000-0002-0478-5533",
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": "Person",
                    "typeRole": [
                        "Primary contact"
                    ],
                    "note": "PhD Candidate at Signal Processing Lab, Griffith University"
                }
            ],
            "community": null,
            "owner": "jaswinder_singh",
            "additionDate": "2019-12-25T03:46:00Z",
            "lastUpdate": "2021-09-28T10:47:18.113882Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 1,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "IPC 2.0",
            "description": "Isoelectric Point Calculator 2.0 is a web service and a standalone program for the estimation of protein and peptide isoelectric point (pI) and dissociation constant (pKa) values using a mixture of deep learning and support vector regression models.\n\n\nIsoelectric point, the pH at which a particular molecule carries no net electrical charge, is a critical parameter for many analytical biochemistry and proteomics techniques, especially for 2D gel electrophoresis (2D-PAGE), capillary isoelectric focusing (cIEF), X-ray crystallography, and liquid chromatography–mass spectrometry (LC-MS).\n\nAccording to the benchmarks, the prediction accuracy (RMSD) of IPC 2.0 for proteins and peptides outperforms previous algorithms: 0.848 versus 0.868 and 0.222 versus 0.405, respectively. Moreover, the IPC 2.0 prediction of pKa using sequence information alone was better than the prediction from structure-based methods (0.576 versus 0.826) and a few folds faster.",
            "homepage": "http://ipc2-isoelectric-point.org/",
            "biotoolsID": "ipc_2.0",
            "biotoolsCURIE": "biotools:ipc_2.0",
            "version": [
                "2.0"
            ],
            "otherID": [],
            "relation": [
                {
                    "biotoolsID": "ipc",
                    "type": "isNewVersionOf"
                },
                {
                    "biotoolsID": "proteome-pi_2.0",
                    "type": "usedBy"
                }
            ],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_3092",
                            "term": "Protein feature detection"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2886",
                                "term": "Protein sequence record"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                },
                                {
                                    "uri": "http://edamontology.org/format_1964",
                                    "term": "plain text format (unformatted)"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2884",
                                "term": "Plot"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_3752",
                                    "term": "CSV"
                                }
                            ]
                        }
                    ],
                    "note": null,
                    "cmd": null
                }
            ],
            "toolType": [
                "Web service",
                "Command-line tool"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_3047",
                    "term": "Molecular biology"
                },
                {
                    "uri": "http://edamontology.org/topic_0121",
                    "term": "Proteomics"
                },
                {
                    "uri": "http://edamontology.org/topic_0123",
                    "term": "Protein properties"
                },
                {
                    "uri": "http://edamontology.org/topic_3292",
                    "term": "Biochemistry"
                }
            ],
            "operatingSystem": [
                "Mac",
                "Linux",
                "Windows"
            ],
            "language": [
                "Python"
            ],
            "license": "Freeware",
            "collectionID": [],
            "maturity": "Mature",
            "cost": "Free of charge (with restrictions)",
            "accessibility": "Open access",
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [
                {
                    "url": "http://ipc2.mimuw.edu.pl",
                    "type": [
                        "Mirror"
                    ],
                    "note": null
                }
            ],
            "download": [
                {
                    "url": "https://doi.org/10.18150/QLPZDQ",
                    "type": "Downloads page",
                    "note": "The file contains the protein, peptide, and pKa datasets used for the training and testing of IPC 2.0. The files *_25.txt contain randomly selected test sets. The files *_75.txt contain randomly selected training sets. The files *_100.txt denote complete sets.",
                    "version": null
                },
                {
                    "url": "https://doi.org/10.18150/34GBOB",
                    "type": "Downloads page",
                    "note": "The file contains the ML models (PICKLE files for SVR from Sklearn and HDF5 and JSON files for DL from Keras and Tensorflow)",
                    "version": null
                },
                {
                    "url": "https://doi.org/10.18150/CAG3QJ",
                    "type": "Downloads page",
                    "note": "The file contains the protein, peptide, and pKa predictions for all methods",
                    "version": null
                },
                {
                    "url": "https://doi.org/10.18150/7LDND3",
                    "type": "Downloads page",
                    "note": "The file contains IPC2 standalone version",
                    "version": null
                }
            ],
            "documentation": [
                {
                    "url": "http://www.ipc2-isoelectric-point.org/help.html",
                    "type": [
                        "User manual"
                    ],
                    "note": "Help for webservise (help for the standalone version is included in CLI)"
                }
            ],
            "publication": [
                {
                    "doi": "10.1093/nar/gkab295",
                    "pmid": "33905510",
                    "pmcid": null,
                    "type": [],
                    "version": null,
                    "note": null,
                    "metadata": {
                        "title": "IPC 2.0: Prediction of isoelectric point and pKadissociation constants",
                        "abstract": "© 2021 The Author(s) 2021. Published by Oxford University Press on behalf of Nucleic Acids Research.The isoelectric point is the pH at which a particular molecule is electrically neutral due to the equilibrium of positive and negative charges. In proteins and peptides, this depends on the dissociation constant (pKa) of charged groups of seven amino acids and NH+ and COO- groups at polypeptide termini. Information regarding isoelectric point and pKa is extensively used in two-dimensional gel electrophoresis (2D-PAGE), capillary isoelectric focusing (cIEF), crystallisation, and mass spectrometry. Therefore, there is a strong need for the in silico prediction of isoelectric point and pKa values. In this paper, I present Isoelectric Point Calculator 2.0 (IPC 2.0), a web server for the prediction of isoelectric points and pKa values using a mixture of deep learning and support vector regression models. The prediction accuracy (RMSD) of IPC 2.0 for proteins and peptides outperforms previous algorithms: 0.848 versus 0.868 and 0.222 versus 0.405, respectively. Moreover, the IPC 2.0 prediction of pKa using sequence information alone was better than the prediction from structure-based methods (0.576 versus 0.826) and a few folds faster. The IPC 2.0 webserver is freely available at www.ipc2-isoelectric-point.org.",
                        "date": "2021-07-02T00:00:00Z",
                        "citationCount": 2,
                        "authors": [
                            {
                                "name": "Kozlowski L.P."
                            }
                        ],
                        "journal": "Nucleic Acids Research"
                    }
                }
            ],
            "credit": [
                {
                    "name": "Lukasz P. Kozlowski",
                    "email": "lukaszkozlowski.lpk@gmail.com",
                    "url": "http://bioinformatics.netmark.pl",
                    "orcidid": "https://orcid.org/0000-0001-8187-1980",
                    "gridid": "grid.12847.38",
                    "rorid": "039bjqg32",
                    "fundrefid": "10.13039/501100004281",
                    "typeEntity": "Person",
                    "typeRole": [],
                    "note": "Assistant Professor at University of Warsaw"
                }
            ],
            "community": null,
            "owner": "lukaskoz",
            "additionDate": "2021-05-25T13:54:39Z",
            "lastUpdate": "2021-09-23T10:00:03.623837Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 0,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "CoverM",
            "description": "Read coverage calculator for metagenomics",
            "homepage": "https://github.com/wwood/CoverM",
            "biotoolsID": "coverm",
            "biotoolsCURIE": "biotools:coverm",
            "version": [
                "0.6.1"
            ],
            "otherID": [],
            "relation": [],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0495",
                            "term": "Local alignment"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_3494",
                                "term": "DNA sequence"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1930",
                                    "term": "FASTQ"
                                }
                            ]
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_3494",
                                "term": "DNA sequence"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_2200",
                                    "term": "FASTA-like (text)"
                                }
                            ]
                        },
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1383",
                                "term": "Nucleic acid sequence alignment"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_2572",
                                    "term": "BAM"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_0951",
                                "term": "Statistical estimate score"
                            },
                            "format": []
                        }
                    ],
                    "note": null,
                    "cmd": "coverm genome --coupled read1.fastq.gz read2.fastq.gz --genome-fasta-files genome1.fna genome2.fna -o output.tsv\ncoverm contig --coupled read1.fastq.gz read2.fastq.gz --reference assembly.fna"
                }
            ],
            "toolType": [
                "Command-line tool"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_0091",
                    "term": "Bioinformatics"
                }
            ],
            "operatingSystem": [
                "Mac",
                "Linux"
            ],
            "language": [
                "Other"
            ],
            "license": "GPL-3.0",
            "collectionID": [],
            "maturity": "Emerging",
            "cost": "Free of charge",
            "accessibility": "Open access",
            "elixirPlatform": [],
            "elixirNode": [],
            "elixirCommunity": [],
            "link": [],
            "download": [],
            "documentation": [],
            "publication": [],
            "credit": [],
            "community": null,
            "owner": "benjwoodcroft",
            "additionDate": "2021-09-22T07:04:05.229537Z",
            "lastUpdate": "2021-09-22T07:09:39.139136Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 0,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        },
        {
            "name": "mlplasmids",
            "description": "mlplasmids consists of binary classifiers to predict contigs either as plasmid-derived or chromosome-derived.\nIt currently classifies short-read contigs as chromosomes and plasmids for Enterococcus faecium, Escherichia coli and Klebsiella pneumoniae.",
            "homepage": "https://gitlab.com/sirarredondo/mlplasmids",
            "biotoolsID": "mlplasmids",
            "biotoolsCURIE": "biotools:mlplasmids",
            "version": [
                "V1.0.0",
                "V2.0.0",
                "V2.1.0"
            ],
            "otherID": [],
            "relation": [
                {
                    "biotoolsID": "gplas",
                    "type": "usedBy"
                }
            ],
            "function": [
                {
                    "operation": [
                        {
                            "uri": "http://edamontology.org/operation_0525",
                            "term": "Genome assembly"
                        },
                        {
                            "uri": "http://edamontology.org/operation_2423",
                            "term": "Prediction and recognition"
                        }
                    ],
                    "input": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_2977",
                                "term": "Nucleic acid sequence"
                            },
                            "format": [
                                {
                                    "uri": "http://edamontology.org/format_1929",
                                    "term": "FASTA"
                                }
                            ]
                        }
                    ],
                    "output": [
                        {
                            "data": {
                                "uri": "http://edamontology.org/data_1270",
                                "term": "Feature table"
                            },
                            "format": []
                        }
                    ],
                    "note": null,
                    "cmd": null
                }
            ],
            "toolType": [
                "Command-line tool",
                "Web service"
            ],
            "topic": [
                {
                    "uri": "http://edamontology.org/topic_3673",
                    "term": "Whole genome sequencing"
                },
                {
                    "uri": "http://edamontology.org/topic_0196",
                    "term": "Sequence assembly"
                },
                {
                    "uri": "http://edamontology.org/topic_3305",
                    "term": "Public health and epidemiology"
                }
            ],
            "operatingSystem": [
                "Linux"
            ],
            "language": [
                "R"
            ],
            "license": "GPL-3.0",
            "collectionID": [
                "Genomics"
            ],
            "maturity": "Emerging",
            "cost": "Free of charge",
            "accessibility": "Open access",
            "elixirPlatform": [
                "Tools"
            ],
            "elixirNode": [
                "Netherlands"
            ],
            "elixirCommunity": [
                "Microbial Biotechnology"
            ],
            "link": [
                {
                    "url": "https://gitlab.com/sirarredondo/mlplasmids",
                    "type": [
                        "Repository"
                    ],
                    "note": null
                },
                {
                    "url": "https://gitlab.com/sirarredondo/mlplasmids/-/issues",
                    "type": [
                        "Issue tracker"
                    ],
                    "note": null
                },
                {
                    "url": "https://sarredondo.shinyapps.io/mlplasmids",
                    "type": [
                        "Other"
                    ],
                    "note": "webserver with GUI of mlplasmids"
                }
            ],
            "download": [
                {
                    "url": "https://gitlab.com/sirarredondo/mlplasmids/-/releases/v1.0.0",
                    "type": "Source code",
                    "note": null,
                    "version": "V1.0.0"
                }
            ],
            "documentation": [
                {
                    "url": "https://gitlab.com/sirarredondo/mlplasmids/-/blob/master/README.Rmd",
                    "type": [
                        "Other"
                    ],
                    "note": "README of the repository"
                }
            ],
            "publication": [
                {
                    "doi": "10.1099/mgen.0.000224",
                    "pmid": "30383524",
                    "pmcid": "PMC6321875",
                    "type": [
                        "Method"
                    ],
                    "version": "V1.0.0",
                    "note": null,
                    "metadata": {
                        "title": "mlplasmids: a user-friendly tool to predict plasmid- and chromosome-derived sequences for single species",
                        "abstract": "Assembly of bacterial short-read whole-genome sequencing data frequently results in hundreds of contigs for which the origin, plasmid or chromosome, is unclear. Complete genomes resolved by long-read sequencing can be used to generate and label short-read contigs. These were used to train several popular machine learning methods to classify the origin of contigs from Enterococcus faecium, Klebsiella pneumoniae and Escherichia coli using pentamer frequencies. We selected support-vector machine (SVM) models as the best classifier for all three bacterial species (F1-score E. faecium=0.92, F1-score K. pneumoniae=0.90, F1-score E. coli=0.76), which outperformed other existing plasmid prediction tools using a benchmarking set of isolates. We demonstrated the scalability of our models by accurately predicting the plasmidome of a large collection of 1644 E. faecium isolates and illustrate its applicability by predicting the location of antibiotic-resistance genes in all three species. The SVM classifiers are publicly available as an R package and graphical-user interface called 'mlplasmids'. We anticipate that this tool may significantly facilitate research on the dissemination of plasmids encoding antibiotic resistance and/or contributing to host adaptation.",
                        "date": "2018-11-01T00:00:00Z",
                        "citationCount": 50,
                        "authors": [
                            {
                                "name": "Arredondo-Alonso S."
                            },
                            {
                                "name": "Rogers M.R.C."
                            },
                            {
                                "name": "Braat J.C."
                            },
                            {
                                "name": "Verschuuren T.D."
                            },
                            {
                                "name": "Top J."
                            },
                            {
                                "name": "Corander J."
                            },
                            {
                                "name": "Willems R.J.L."
                            },
                            {
                                "name": "Schurch A.C."
                            }
                        ],
                        "journal": "Microbial genomics"
                    }
                },
                {
                    "doi": "10.1128/mBio.03284-19",
                    "pmid": "32047136",
                    "pmcid": "PMC7018651",
                    "type": [
                        "Usage"
                    ],
                    "version": "V1.0.0",
                    "note": null,
                    "metadata": {
                        "title": "Plasmids shaped the recent emergence of the major nosocomial pathogen Enterococcus faecium",
                        "abstract": "© 2020 Arredondo-Alonso et al.Enterococcus faecium is a gut commensal of humans and animals but is also listed on the WHO global priority list of multidrug-resistant pathogens. Many of its antibiotic resistance traits reside on plasmids and have the potential to be disseminated by horizontal gene transfer. Here, we present the first comprehensive population-wide analysis of the pan-plasmidome of a clinically important bacterium, by whole-genome sequence analysis of 1,644 isolates from hospital, commensal, and animal sources of E. faecium. Long-read sequencing on a selection of isolates resulted in the completion of 305 plasmids that exhibited high levels of sequence modularity. We further investigated the entirety of all plasmids of each isolate (plas-midome) using a combination of short-read sequencing and machine-learning classi-fiers. Clustering of the plasmid sequences unraveled different E. faecium populations with a clear association with hospitalized patient isolates, suggesting different optimal configurations of plasmids in the hospital environment. The characterization of these populations allowed us to identify common mechanisms of plasmid stabilization such as toxin-antitoxin systems and genes exclusively present in particular plasmidome populations exemplified by copper resistance, phosphotransferase systems, or bacteriocin genes potentially involved in niche adaptation. Based on the distribution of k-mer distances between isolates, we concluded that plasmidomes rather than chromosomes are most informative for source specificity of E. faecium. IMPORTANCE Enterococcus faecium is one of the most frequent nosocomial pathogens of hospital-acquired infections. E. faecium has gained resistance against most commonly available antibiotics, most notably, against ampicillin, gentamicin, and vancomycin, which renders infections difficult to treat. Many antibiotic resistance traits, in particular, vancomycin resistance, can be encoded in autonomous and extrachromosomal elements called plasmids. These sequences can be disseminated to other isolates by horizontal gene transfer and confer novel mechanisms to source specificity. In our study, we elucidated the total plasmid content, referred to as the plasmidome, of 1,644 E. faecium isolates by using short-and long-read whole-genome technologies with the combination of a machine-learning classifier. This was fundamental to investigate the full collection of plasmid sequences present in our collection (pan-plasmidome) and to observe the potential transfer of plasmid sequences between E. faecium hosts. We observed that E. faecium isolates from hospitalized patients carried a larger number of plasmid sequences compared to that from other sources, and they elucidated different configurations of plasmidome populations in the hospital environment. We assessed the contribution of different genomic components and observed that plasmid sequences have the highest contribution to source specificity. Our study suggests that E. faecium plasmids are regulated by complex ecological constraints rather than physical interaction between hosts.",
                        "date": "2020-01-01T00:00:00Z",
                        "citationCount": 20,
                        "authors": [
                            {
                                "name": "Arredondo-Alonso S."
                            },
                            {
                                "name": "Top J."
                            },
                            {
                                "name": "McNally A."
                            },
                            {
                                "name": "Puranen S."
                            },
                            {
                                "name": "Pesonen M."
                            },
                            {
                                "name": "Pensar J."
                            },
                            {
                                "name": "Marttinen P."
                            },
                            {
                                "name": "Braat J.C."
                            },
                            {
                                "name": "Rogers M.R.C."
                            },
                            {
                                "name": "van Schaik W."
                            },
                            {
                                "name": "Kaski S."
                            },
                            {
                                "name": "Willems R.J.L."
                            },
                            {
                                "name": "Corander J."
                            },
                            {
                                "name": "Schurch A.C."
                            }
                        ],
                        "journal": "mBio"
                    }
                }
            ],
            "credit": [
                {
                    "name": "Sergio Arredondo-Alonso",
                    "email": "a.c.schurch@umcutrecht.nl",
                    "url": null,
                    "orcidid": "https://orcid.org/0000-0002-4445-2442",
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": "Person",
                    "typeRole": [
                        "Developer",
                        "Maintainer"
                    ],
                    "note": null
                },
                {
                    "name": "Anita Schürch",
                    "email": "a.c.schurch@umcutrecht.nl",
                    "url": null,
                    "orcidid": "https://orcid.org/0000-0003-1894-7545",
                    "gridid": null,
                    "rorid": null,
                    "fundrefid": null,
                    "typeEntity": "Person",
                    "typeRole": [
                        "Contributor",
                        "Maintainer"
                    ],
                    "note": null
                }
            ],
            "community": null,
            "owner": "aschuerch",
            "additionDate": "2021-01-07T14:35:00Z",
            "lastUpdate": "2021-09-21T12:35:01.650974Z",
            "editPermission": {
                "type": "private",
                "authors": []
            },
            "validated": 1,
            "homepage_status": 0,
            "elixir_badge": 0,
            "confidence_flag": null
        }
    ]
}