{"id":"https://openalex.org/W7212008100","doi":"https://doi.org/10.26434/chemrxiv.15008524/v1","title":"Chainable DataFrame Framework for Interactive Chemical Data Processing with pdChemChain","display_name":"Chainable DataFrame Framework for Interactive Chemical Data Processing with pdChemChain","publication_year":2026,"publication_date":"2026-09-08","ids":{"openalex":"https://openalex.org/W7212008100","doi":"https://doi.org/10.26434/chemrxiv.15008524/v1"},"language":"en","primary_location":{"id":"doi:10.26434/chemrxiv.15008524/v1","doi":"https://doi.org/10.26434/chemrxiv.15008524/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008524/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008524/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008524/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046421751","display_name":"Esben Jannik Bjerrum","orcid":"https://orcid.org/0000-0003-1614-7376","observed_orcids":["https://orcid.org/0000-0003-1614-7376"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Esben Jannik Bjerrum","raw_affiliation_strings":["AbbVie, Hagaplan 4, Stockholm, Sweden, SE-113 68"],"raw_orcid":"https://orcid.org/0000-0003-1614-7376","affiliations":[{"raw_affiliation_string":"AbbVie, Hagaplan 4, Stockholm, Sweden, SE-113 68","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5046421751"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8300999999046326,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.8300999999046326,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.11339999735355377,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.03799999877810478,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pandas-dataframes","display_name":"pandas DataFrames","score":0.7979999780654907},{"id":"https://openalex.org/keywords/jupyter-notebooks","display_name":"Jupyter notebooks","score":0.7940000295639038},{"id":"https://openalex.org/keywords/rdkit","display_name":"RDKit","score":0.675000011920929},{"id":"https://openalex.org/keywords/open-source-python-framework","display_name":"open-source Python framework","score":0.6949999928474426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198000192642212},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7494999766349792},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7318000197410583},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5253999829292297},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.48330000042915344},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4399000108242035},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40230000019073486},{"id":"https://openalex.org/C81147070","wikidata":"https://www.wikidata.org/wiki/Q1172449","display_name":"Encapsulation (networking)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3230000138282776},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C109701466","wikidata":"https://www.wikidata.org/wiki/Q460584","display_name":"Scala","level":3,"score":0.27239999175071716},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C2780977526","wikidata":"https://www.wikidata.org/wiki/Q42417149","display_name":"Data exploration","level":3,"score":0.2637999951839447},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.26434/chemrxiv.15008524/v1","doi":"https://doi.org/10.26434/chemrxiv.15008524/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008524/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008524/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.26434/chemrxiv.15008524/v1","doi":"https://doi.org/10.26434/chemrxiv.15008524/v1","is_oa":true,"landing_page_url":"https://doi.org/10.26434/chemrxiv.15008524/v1","pdf_url":"https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15008524/v1","source":{"id":"https://openalex.org/S4393918830","display_name":"ChemRxiv","issn_l":"2573-2293","issn":["2573-2293"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212008100.pdf","grobid_xml":"https://content.openalex.org/works/W7212008100.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1979900513","https://openalex.org/W2011301426","https://openalex.org/W2034549041","https://openalex.org/W2113364934","https://openalex.org/W2605897695","https://openalex.org/W3082081167","https://openalex.org/W3122109253","https://openalex.org/W3128261063","https://openalex.org/W4292362226","https://openalex.org/W4389396422","https://openalex.org/W4392015344","https://openalex.org/W4397037994","https://openalex.org/W4402555999","https://openalex.org/W4403814244","https://openalex.org/W4403947974"],"related_works":["https://openalex.org/W4384933406","https://openalex.org/W4285591076","https://openalex.org/W2069585443","https://openalex.org/W7100051716","https://openalex.org/W2796410048","https://openalex.org/W4396887306","https://openalex.org/W2624695942","https://openalex.org/W4366090395","https://openalex.org/W2104817357","https://openalex.org/W7208724206"],"abstract_inverted_index":{"Computational":[0],"chemists":[1],"frequently":[2],"build":[3],"data":[4,59],"processing":[5,60],"workflows":[6,34],"as":[7,62,131],"ad-hoc":[8],"scripts":[9],"that":[10,46,95],"are":[11,96,103,116],"difficult":[12],"to":[13,107],"reuse,":[14],"share,":[15],"or":[16,29,130],"deploy.":[17],"Yet,":[18],"many":[19],"of":[20,38],"the":[21,90,172],"alternative":[22],"workflow":[23],"platforms":[24],"demand":[25],"significant":[26],"complexity":[27],"overhead":[28],"create":[30],"manual":[31],"breaks":[32],"in":[33,50,119,134],"involving":[35],"different":[36],"pieces":[37],"software.":[39],"pdChemChain":[40,145,166],"is":[41,70,167],"an":[42],"open-source":[43],"Python":[44],"framework":[45,69],"bridges":[47],"interactive":[48],"use":[49],"python":[51],"with":[52,121],"reuse":[53],"and":[54,82,99,143,155],"deployment,":[55],"by":[56],"treating":[57],"chemical":[58],"chains":[61,94,102],"composable,":[63],"self-serializing":[64],"pandas":[65],"DataFrame":[66,81],"operations.":[67],"The":[68],"built":[71,117],"around":[72],"three":[73],"design":[74,136],"principles:":[75],"(1)":[76],"every":[77],"operation":[78],"takes":[79],"a":[80,84,162],"returns":[83],"DataFrame,":[85],"(2)":[86],"operations":[87],"compose":[88],"via":[89,128],"+":[91],"operator":[92],"into":[93],"themselves":[97],"operations,":[98],"(3)":[100],"all":[101],"self-configuring,":[104],"i.e.":[105],"serializable":[106],"YAML":[108],"for":[109,148],"command-line":[110],"deployment":[111],"without":[112],"code":[113],"changes.":[114],"Chains":[115],"interactively":[118],"notebooks":[120],"immediate":[122],"visual":[123],"feedback,":[124],"then":[125],"deployed":[126],"as-is":[127],"CLI":[129],"scoring":[132],"components":[133],"generative":[135],"frameworks.":[137],"Built":[138],"on":[139],"widely":[140],"used":[141],"RDKit":[142],"pandas,":[144],"provides":[146],"links":[147],"molecular":[149],"processing,":[150],"property":[151],"calculation,":[152],"score":[153],"transformation,":[154],"multi-parameter":[156],"aggregation,":[157],"while":[158],"remaining":[159],"extensible":[160],"through":[161],"minimal":[163],"dataclass-based":[164],"API.":[165],"available":[168],"at":[169],"https://github.com/EBjerrum/pdchemchain":[170],"under":[171],"LGPL-3.0":[173],"license.":[174]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-10T00:00:00"}