|
Dataset
|
update: {"publication_state"=>["version candidate under curator review", "released"], "release_date"=>[nil, Tue, 17 Sep 2024]}
|
2024-09-17T12:53:35Z
|
|
RelatedMaterial
|
update: {"note"=>[nil, ""]}
|
2024-09-13T15:28:23Z
|
|
Dataset
|
update: {"title"=>["Datasets for \"Phylogeny, Biogeography and Morphological Evolution of the Treehopper-Like Leafhoppers (Hemiptera: Cicadellidae) Megophthalminae and Ulopinae\"", "Dataset title: Datasets, scripts and main output files for \"Phylogeny, Biogeography and Morphological Evolution of the Treehopper-Like Leafhoppers (Hemiptera: Cicadellidae) Megophthalminae and Ulopinae\""], "description"=>["The following 6 files were used to reconstruct the phylogeny of the Megophthalminae and Ulopinae.\r\n1. Taxon_sampling.csv: contains the sample IDs (1st column) which were used in the alignments and the taxonomic information (2nd to 6th columns).\r\n2. concatenated_aa_partition.nex: the partitioning schemes for the maximum likelihood analysis using concatenated_aa.phy. This file partitions the 52,024 amino acid positions into 427 character sets.\r\n3. concatenated_aa_.phy: a concatenated amino acid dataset with 52,024 amino acid positions. This dataset was used for the maximum likelihood analysis by IQ-TREE v1.6.12. Hyphens are used to represent gaps.\r\n4. concatenated_nt_partition.nex: the partitioning schemes for the maximum likelihood analysis using concatenated_nt.phy. This file partitions the 156,072 nucleotide positions into 427 character sets.\r\n5. concatenated_nt_.phy: a concatenated nucleotide dataset with 156,072 nucleotide positions. This dataset was used for the maximum likelihood analysis by IQ-TREE v1.6.12. Hyphens are used to represent gaps.\r\n6. Individual_gene_alignment.zip: contains 427 FASTA files, each one represents the nucleotide alignment for a gene. Hyphens are used to represent gaps. These files were used to construct gene trees using IQ-TREE v1.6.12, followed by multispecies coalescent analysis using ASTRAL v 4.10.5 based the maximum likelihood trees with the average SH-aLRT and ultrafast bootstrap values of ≥ 70.\r\n\r\n", "The following seven zip files are compressed folders containing the input datasets/trees, main output files and the scripts of the related analyses performed in this study.\r\n\r\nI. ancestral_microhabitat_reconstruction.zip: contains four files, including two input files (microhabitats.csv, timetree.tre) and a script (simmap_microhabitat.R) for ancestral states reconstruction of microhabitat by make.simmap implemented in the R package phytools v1.5, as well as the main output file (ancestral_microhabitats.csv).\r\n\r\n\t1. ancestral_microhabitats.csv: reconstructed ancestral microhabitats for each node.\r\n\r\n\t2. microhabitats.csv: microhabitats of the studies species.\r\n\t\r\n\t3. simmap_microhabitat.R: the R script of make.simmap for ancestral microhabitat reconstruction\r\n\t\r\n\t4. timetree.tre: dated tree used for ancestral state reconstruction for microhabitat and morphological characters\r\n\t\r\nII. ancestral_morphology_reconstruction.zip: contains six files, including an input file (morphology.csv) and a script (simmap_morphology.R) for ancestral states reconstruction of morphology by make.simmap implemented in the R package phytools v1.5, as well as four main output files(forewing_ancestral_state.csv, frontal_sutures_ancestral_state.csv, hind_wing_ancestral_state.csv, ocellus_ancestral_state.csv).\r\n\r\n\t1. forewing_ancestral_state.csv: reconstructed ancestral states of the development of the forewing for each node.\r\n\t\r\n\t2. frontal_sutures_ancestral_state.csv: reconstructed ancestral states of the development of frontal sutures for each node.\r\n\t\r\n\t3. hind_wing_ancestral_state.csv: reconstructed ancestral states of the development of the hind wing for each node.\r\n\t\r\n\t4. morphology.csv: the states of the development of ocellus, forewing, hing wing and frontal sutures for each studies species.\r\n\t\r\n\t5. ocellus_ancestral_state.csv: reconstructed ancestral states of the development of the ocellus for each node.\r\n\t\r\n\t6. simmap_morphology.R: the R script of make.simmap for ancestral state reconstruction of morphology\r\n\t\r\nIII. biogeographic_reconstruction.zip: contains four files, including three input files (dispersal_probablity.txt, distributions.csv, timetree_noOutgroup.tre) used for a stratified biogeographic analysis by BioGeoBEARS in RASP v4.2 and the main output file (DIVELIKE_result.txt).\r\n\r\n\t1. dispersal_probablity.txt: relative dispersal probabilities among biogeographical regions at different geological epochs.\r\n\t\r\n\t2. distributions.csv: current distributions of the studied species.\r\n\t\r\n\t3. DIVELIKE_result.txt: BioGeoBEARS result of ancestral areas based on the DIVELIKE model.\r\n\t\r\n\t4. timetree_noOutgroup.tre: the dated tree with the outgroup lineage (Eurymelinae) excluded.\r\n\t\r\nIV. coalescent_analysis.zip: contains a folder and two files, including a folder (individual_gene_alignment) of input files used to construct gene trees, an input file (MLtree_BS70.tre) used for the multi-species coalescent analysis by ASTRAL v 4.10.5 and the main output file (coalescent_species_tree.tre).\r\n\r\n\t1. coalescent_species_tree.tre: the species tree generated by the multi-species coalescent analysis with the quartet support, effective number of genes and the local posterior probability indicated.\r\n\t\r\n\t2. individual_gene_alignment: a folder containing 427 FASTA files, each one represents the nucleotide alignment for a gene. Hyphens are used to represent gaps. These files were used to construct gene trees using IQ-TREE v1.6.12.\r\n\r\n\t3. MLtree_BS70.tre: 165 gene trees with the average SH-aLRT and ultrafast bootstrap values of ≥ 70%. This file was used to estimate the species tree by ASTRAL v 4.10.5.\r\n\t\r\nV. divergence_time_estimation.zip: contains five files, including two input files (treefile_rooted_noBranchLength.tre, treefile_rooted.tre) and two control files (baseml.ctl, mcmctree.ctl) used for divergence time estimation by BASEML and MCMCTREE in PAML v4.9, as well as the main output file (timetree_with95%HPD.tre).\r\n\r\n\t1. baseml.ctl: the control file used for the estimation of substitution rates by BASEML in PAML v4.9.\r\n\t\r\n\t2. mcmctree.ctl: the control file used for the estimation of divergence times by MCMCTREE in PAML v4.9.\r\n\t\r\n\t3. timetree_with95%HPD.tre: dated tree with the 95% highest posterior density confidence intervals indicated.\r\n\r\n\t4. treefile_rooted_noBranchLength.tre: the maximum likelihood tree based on the concatenated nucleotide dataset with calibrations for the crown and internal nodes. Branch length and support values were not indicated.\r\n\r\n\t5. treefile_rooted.tre: the maximum likelihood tree based on the concatenated nucleotide dataset with a secondary calibration on the root age. Branch support values were not indicated.\r\n\t\r\nVI. maximum_likelihood_analysis_aa.zip: contains three files, including two input files (concatenated_aa_partition.nex, concatenated_aa.phy) used for the maximum likelihood analysis by IQ-TREE v1.6.12 and the main output file (MLtree_aa.tre).\r\n\r\n\t1. concatenated_aa_partition.nex: the partitioning schemes for the maximum likelihood analysis using concatenated_aa.phy. This file partitions the 52,024 amino acid positions into 427 character sets.\r\n\r\n\t2. concatenated_aa.phy: a concatenated amino acid dataset with 52,024 amino acid positions. Hyphens are used to represent gaps. This dataset was used for the maximum likelihood analysis. \r\n\r\n\t3. MLtree_aa.tre: the maximum likelihood tree based on the concatenated amino acid dataset, with SH-aLRT values and ultrafast bootstrap values indicated.\r\n\r\nVII. maximum_likelihood_analysis_nt.zip: contains three files, including two input files (concatenated_nt_partition.nex, concatenated_nt.phy) used for the maximum likelihood analysis by IQ-TREE v1.6.12 and the main output file (MLtree_nt.tre).\r\n\r\n\t1. concatenated_nt_partition.nex: the partitioning schemes for the maximum likelihood analysis using concatenated_nt.phy. This file partitions the 156,072 nucleotide positions into 427 character sets.\r\n\r\n\t2. concatenated_nt.phy: a concatenated nucleotide dataset with 156,072 nucleotide positions. Hyphens are used to represent gaps. This dataset was used for the maximum likelihood analysis as well as divergence time estimation.\r\n\r\n\t3. MLtree_nt.tre: the maximum likelihood tree based on the concatenated nucleotide dataset, with SH-aLRT values and ultrafast bootstrap values indicated.\r\n\r\nVIII. Taxon_sampling.csv: contains the sample IDs (1st column) which were used in the alignments and the taxonomic information (2nd to 6th columns).\r\n"], "keywords"=>["Cicadellidae; Classification; Phylogenomics; Megophthalminae; Ulopinae", "Anchored Hybrid Enrichment, Biogeography, Cicadellidae, Phylogenomics, Treehoppers"]}
|
2024-09-13T01:21:38Z
|
|
Dataset
|
update: {"hold_state"=>["version candidate under curator review", "none"]}
|
2024-09-12T14:50:33Z
|
|
Dataset
|
update: {"version_comment"=>[nil, "I would like to upload more files to this dataset, including more input files of our analyses and related scripts, as well as the main outputs."]}
|
2024-09-12T11:51:06Z
|
|
RelatedMaterial
|
create: {"material_type"=>"Dataset", "availability"=>nil, "link"=>"https://doi.org/10.13012/B2IDB-1475719_V2", "uri"=>"10.13012/B2IDB-1475719_V2", "uri_type"=>"DOI", "citation"=>"Cao, Yanghui; Dietrich, Christopher H.; Dmitriev, Dmitry A.; Kits, Joel H.; Xue, Qingquan; Zhang, Yalin (2024): Datasets for \"Phylogeny, Biogeography and Morphological Evolution of the Treehopper-Like Leafhoppers (Hemiptera: Cicadellidae) Megophthalminae and Ulopinae\". University of Illinois at Urbana-Champaign. https://doi.org/10.13012/B2IDB-1475719_V2", "dataset_id"=>2785, "selected_type"=>"Dataset", "datacite_list"=>"IsNewVersionOf", "note"=>nil, "feature"=>nil}
|
2024-09-12T11:48:35Z
|
|
RelatedMaterial
|
create: {"material_type"=>"Dataset", "availability"=>nil, "link"=>"https://doi.org/10.13012/B2IDB-8842653_V2", "uri"=>"", "uri_type"=>"", "citation"=>"Cao, Y., Dietrich, C.H., Zahniser, J.N. & Dmitriev, D.A. (2022) Dense sampling of taxa and characters improves phylogenetic resolution among deltocephaline leafhoppers (Hemiptera: Cicadellidae: Deltocephalinae). Systematic Entomology, 47: 430–444.", "dataset_id"=>2785, "selected_type"=>"Dataset", "datacite_list"=>"", "note"=>"", "feature"=>nil}
|
2024-09-12T11:48:35Z
|
|
RelatedMaterial
|
create: {"material_type"=>"Dataset", "availability"=>nil, "link"=>"https://doi.org/10.13012/B2IDB-8636195_V1", "uri"=>"", "uri_type"=>"", "citation"=>"Cao, Y., Dietrich, C.H., Kits, J.H., Dmitriev, D.A., Richter, R., Eyres, J., Dettman, J.R., Xu, Y. & Huang, M. (2023). Phylogenomics of microleafhoppers (Hemiptera: Cicadellidae: Typhlocybinae): morphological evolution, divergence times and biogeography. Insect Systematics and Diversity, 7(4): 1–19.", "dataset_id"=>2785, "selected_type"=>"Dataset", "datacite_list"=>"", "note"=>"", "feature"=>nil}
|
2024-09-12T11:48:35Z
|
|
Funder
|
create: {"name"=>"Agriculture and Agri- Food Canada", "identifier"=>"", "identifier_scheme"=>"", "grant"=>"J-001564, J-002279", "dataset_id"=>2785, "code"=>"other"}
|
2024-09-12T11:48:35Z
|
|
Funder
|
create: {"name"=>"National Natural Science Foundation of China", "identifier"=>"", "identifier_scheme"=>"", "grant"=>"32370493, 32370495, 32170472", "dataset_id"=>2785, "code"=>"other"}
|
2024-09-12T11:48:35Z
|
|
Funder
|
create: {"name"=>"U.S. National Science Foundation (NSF)", "identifier"=>"10.13039/100000001", "identifier_scheme"=>"DOI", "grant"=>"DEB-1639601", "dataset_id"=>2785, "code"=>"NSF"}
|
2024-09-12T11:48:35Z
|
|
Creator
|
create: {"family_name"=>"Zhang", "given_name"=>"Yalin", "identifier"=>"", "email"=>"yalinzh@nwsuaf.edu.cn", "is_contact"=>false, "row_position"=>6}
|
2024-09-12T11:48:35Z
|
|
Creator
|
create: {"family_name"=>"Xue", "given_name"=>"Qingquan", "identifier"=>"", "email"=>"xueqingquan_123@nwsuaf.edu.cn", "is_contact"=>false, "row_position"=>5}
|
2024-09-12T11:48:35Z
|
|
Creator
|
create: {"family_name"=>"Kits", "given_name"=>"Joel H.", "identifier"=>"", "email"=>"joel.kits@AGR.GC.CA", "is_contact"=>false, "row_position"=>4}
|
2024-09-12T11:48:35Z
|
|
Creator
|
create: {"family_name"=>"Dmitriev", "given_name"=>"Dmitry A.", "identifier"=>"", "email"=>"arboridia@gmail.com", "is_contact"=>false, "row_position"=>3}
|
2024-09-12T11:48:35Z
|
|
Creator
|
create: {"family_name"=>"Dietrich", "given_name"=>"Christopher H.", "identifier"=>"", "email"=>"chdietri@illinois.edu", "is_contact"=>false, "row_position"=>2}
|
2024-09-12T11:48:35Z
|
|
Creator
|
create: {"family_name"=>"Cao", "given_name"=>"Yanghui", "identifier"=>"", "email"=>"caoyh@illinois.edu", "is_contact"=>true, "row_position"=>1}
|
2024-09-12T11:48:35Z
|
|
Dataset
|
update: {"corresponding_creator_name"=>[nil, "Yanghui Cao"], "corresponding_creator_email"=>[nil, "caoyh@illinois.edu"]}
|
2024-09-12T11:48:35Z
|
