Automated assembly of molecular mechanisms at scale from text mining and curated databases
Abstract The analysis of omic data depends on machine‐readable information about protein interactions, modifications, and activities as found in protein interaction networks, databases of post‐translational modifications, and curated models of gene and protein function. These resources typically dep...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2023-05-01
|
| Series: | Molecular Systems Biology |
| Subjects: | |
| Online Access: | https://doi.org/10.15252/msb.202211325 |
| _version_ | 1797281316788502528 |
|---|---|
| author | John A Bachman Benjamin M Gyori Peter K Sorger |
| author_facet | John A Bachman Benjamin M Gyori Peter K Sorger |
| author_sort | John A Bachman |
| collection | DOAJ |
| description | Abstract The analysis of omic data depends on machine‐readable information about protein interactions, modifications, and activities as found in protein interaction networks, databases of post‐translational modifications, and curated models of gene and protein function. These resources typically depend heavily on human curation. Natural language processing systems that read the primary literature have the potential to substantially extend knowledge resources while reducing the burden on human curators. However, machine‐reading systems are limited by high error rates and commonly generate fragmentary and redundant information. Here, we describe an approach to precisely assemble molecular mechanisms at scale using multiple natural language processing systems and the Integrated Network and Dynamical Reasoning Assembler (INDRA). INDRA identifies full and partial overlaps in information extracted from published papers and pathway databases, uses predictive models to improve the reliability of machine reading, and thereby assembles individual pieces of information into non‐redundant and broadly usable mechanistic knowledge. Using INDRA to create high‐quality corpora of causal knowledge we show it is possible to extend protein–protein interaction databases and explain co‐dependencies in the Cancer Dependency Map. |
| first_indexed | 2024-03-07T16:55:45Z |
| format | Article |
| id | doaj.art-346465df4b12472ab556eaf2ee519332 |
| institution | Directory Open Access Journal |
| issn | 1744-4292 |
| language | English |
| last_indexed | 2024-03-07T16:55:45Z |
| publishDate | 2023-05-01 |
| publisher | Springer Nature |
| record_format | Article |
| series | Molecular Systems Biology |
| spelling | doaj.art-346465df4b12472ab556eaf2ee5193322024-03-03T04:04:55ZengSpringer NatureMolecular Systems Biology1744-42922023-05-01195n/an/a10.15252/msb.202211325Automated assembly of molecular mechanisms at scale from text mining and curated databasesJohn A Bachman0Benjamin M Gyori1Peter K Sorger2Laboratory of Systems Pharmacology Harvard Medical School Boston MA USALaboratory of Systems Pharmacology Harvard Medical School Boston MA USALaboratory of Systems Pharmacology Harvard Medical School Boston MA USAAbstract The analysis of omic data depends on machine‐readable information about protein interactions, modifications, and activities as found in protein interaction networks, databases of post‐translational modifications, and curated models of gene and protein function. These resources typically depend heavily on human curation. Natural language processing systems that read the primary literature have the potential to substantially extend knowledge resources while reducing the burden on human curators. However, machine‐reading systems are limited by high error rates and commonly generate fragmentary and redundant information. Here, we describe an approach to precisely assemble molecular mechanisms at scale using multiple natural language processing systems and the Integrated Network and Dynamical Reasoning Assembler (INDRA). INDRA identifies full and partial overlaps in information extracted from published papers and pathway databases, uses predictive models to improve the reliability of machine reading, and thereby assembles individual pieces of information into non‐redundant and broadly usable mechanistic knowledge. Using INDRA to create high‐quality corpora of causal knowledge we show it is possible to extend protein–protein interaction databases and explain co‐dependencies in the Cancer Dependency Map.https://doi.org/10.15252/msb.202211325curationdatabasesmodelingnetworkstext mining |
| spellingShingle | John A Bachman Benjamin M Gyori Peter K Sorger Automated assembly of molecular mechanisms at scale from text mining and curated databases Molecular Systems Biology curation databases modeling networks text mining |
| title | Automated assembly of molecular mechanisms at scale from text mining and curated databases |
| title_full | Automated assembly of molecular mechanisms at scale from text mining and curated databases |
| title_fullStr | Automated assembly of molecular mechanisms at scale from text mining and curated databases |
| title_full_unstemmed | Automated assembly of molecular mechanisms at scale from text mining and curated databases |
| title_short | Automated assembly of molecular mechanisms at scale from text mining and curated databases |
| title_sort | automated assembly of molecular mechanisms at scale from text mining and curated databases |
| topic | curation databases modeling networks text mining |
| url | https://doi.org/10.15252/msb.202211325 |
| work_keys_str_mv | AT johnabachman automatedassemblyofmolecularmechanismsatscalefromtextminingandcurateddatabases AT benjaminmgyori automatedassemblyofmolecularmechanismsatscalefromtextminingandcurateddatabases AT peterksorger automatedassemblyofmolecularmechanismsatscalefromtextminingandcurateddatabases |