FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4378473350> ?p ?o ?g. }

• W4378473350 endingPage "e1011175" @default.
• W4378473350 startingPage "e1011175" @default.
• W4378473350 abstract "Machine learning tools have proven useful across biological disciplines, allowing researchers to draw conclusions from large datasets, and opening up new opportunities for interpreting complex and heterogeneous biological data. Alongside the rapid growth of machine learning, there have also been growing pains: some models that appear to perform well have later been revealed to rely on features of the data that are artifactual or biased; this feeds into the general criticism that machine learning models are designed to optimize model performance over the creation of new biological insights. A natural question arises: how do we develop machine learning models that are inherently interpretable or explainable? In this manuscript, we describe the SWIF(r) reliability score (SRS), a method building on the SWIF(r) generative framework that reflects the trustworthiness of the classification of a specific instance. The concept of the reliability score has the potential to generalize to other machine learning methods. We demonstrate the utility of the SRS when faced with common challenges in machine learning including: 1) an unknown class present in testing data that was not present in training data, 2) systemic mismatch between training and testing data, and 3) instances of testing data that have missing values for some attributes. We explore these applications of the SRS using a range of biological datasets, from agricultural data on seed morphology, to 22 quantitative traits in the UK Biobank, and population genetic simulations and 1000 Genomes Project data. With each of these examples, we demonstrate how the SRS can allow researchers to interrogate their data and training approach thoroughly, and to pair their domain-specific knowledge with powerful machine-learning frameworks. We also compare the SRS to related tools for outlier and novelty detection, and find that it has comparable performance, with the advantage of being able to operate when some data are missing. The SRS, and the broader discussion of interpretable scientific machine learning, will aid researchers in the biological machine learning space as they seek to harness the power of machine learning without sacrificing rigor and biological insight." @default.
• W4378473350 created "2023-05-27" @default.
• W4378473350 creator A5009372230 @default.
• W4378473350 creator A5020442033 @default.
• W4378473350 creator A5023549081 @default.
• W4378473350 date "2023-05-26" @default.
• W4378473350 modified "2023-09-27" @default.
• W4378473350 title "Enabling interpretable machine learning for biological data with reliability scores" @default.
• W4378473350 cites W1964547306 @default.
• W4378473350 cites W1995443851 @default.
• W4378473350 cites W2009494639 @default.
• W4378473350 cites W2025253353 @default.
• W4378473350 cites W2025979859 @default.
• W4378473350 cites W2026905436 @default.
• W4378473350 cites W2065974896 @default.
• W4378473350 cites W2103286878 @default.
• W4378473350 cites W2104549677 @default.
• W4378473350 cites W2111574971 @default.
• W4378473350 cites W2115627867 @default.
• W4378473350 cites W2126022166 @default.
• W4378473350 cites W2133298050 @default.
• W4378473350 cites W2136557734 @default.
• W4378473350 cites W2140449543 @default.
• W4378473350 cites W2140784970 @default.
• W4378473350 cites W2144182447 @default.
• W4378473350 cites W2152381343 @default.
• W4378473350 cites W2152799443 @default.
• W4378473350 cites W2156866331 @default.
• W4378473350 cites W2162506329 @default.
• W4378473350 cites W2476376090 @default.
• W4378473350 cites W2531014594 @default.
• W4378473350 cites W2748151855 @default.
• W4378473350 cites W2752747624 @default.
• W4378473350 cites W2773279226 @default.
• W4378473350 cites W2810986024 @default.
• W4378473350 cites W2889321024 @default.
• W4378473350 cites W2900471700 @default.
• W4378473350 cites W2915168078 @default.
• W4378473350 cites W2920529430 @default.
• W4378473350 cites W2932881901 @default.
• W4378473350 cites W2945976633 @default.
• W4378473350 cites W2949832836 @default.
• W4378473350 cites W2950732129 @default.
• W4378473350 cites W2950836897 @default.
• W4378473350 cites W2951448613 @default.
• W4378473350 cites W2963521553 @default.
• W4378473350 cites W2975578922 @default.
• W4378473350 cites W3004083863 @default.
• W4378473350 cites W3008695158 @default.
• W4378473350 cites W3013574460 @default.
• W4378473350 cites W3032942004 @default.
• W4378473350 cites W3046630804 @default.
• W4378473350 cites W3116286104 @default.
• W4378473350 cites W3119985211 @default.
• W4378473350 cites W3126829124 @default.
• W4378473350 cites W3137125108 @default.
• W4378473350 cites W3138819813 @default.
• W4378473350 cites W3155215330 @default.
• W4378473350 cites W3186118520 @default.
• W4378473350 cites W3197433610 @default.
• W4378473350 cites W3200707343 @default.
• W4378473350 cites W3211282104 @default.
• W4378473350 cites W4220988604 @default.
• W4378473350 cites W4239873714 @default.
• W4378473350 cites W4375184042 @default.
• W4378473350 doi "https://doi.org/10.1371/journal.pcbi.1011175" @default.
• W4378473350 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37235578" @default.
• W4378473350 hasPublicationYear "2023" @default.
• W4378473350 type Work @default.
• W4378473350 citedByCount "0" @default.
• W4378473350 crossrefType "journal-article" @default.
• W4378473350 hasAuthorship W4378473350A5009372230 @default.
• W4378473350 hasAuthorship W4378473350A5020442033 @default.
• W4378473350 hasAuthorship W4378473350A5023549081 @default.
• W4378473350 hasBestOaLocation W43784733501 @default.
• W4378473350 hasConcept C116567970 @default.
• W4378473350 hasConcept C119857082 @default.
• W4378473350 hasConcept C121332964 @default.
• W4378473350 hasConcept C154945302 @default.
• W4378473350 hasConcept C163258240 @default.
• W4378473350 hasConcept C201797286 @default.
• W4378473350 hasConcept C39890363 @default.
• W4378473350 hasConcept C41008148 @default.
• W4378473350 hasConcept C43214815 @default.
• W4378473350 hasConcept C60644358 @default.
• W4378473350 hasConcept C62520636 @default.
• W4378473350 hasConcept C86803240 @default.
• W4378473350 hasConceptScore W4378473350C116567970 @default.
• W4378473350 hasConceptScore W4378473350C119857082 @default.
• W4378473350 hasConceptScore W4378473350C121332964 @default.
• W4378473350 hasConceptScore W4378473350C154945302 @default.
• W4378473350 hasConceptScore W4378473350C163258240 @default.
• W4378473350 hasConceptScore W4378473350C201797286 @default.
• W4378473350 hasConceptScore W4378473350C39890363 @default.
• W4378473350 hasConceptScore W4378473350C41008148 @default.
• W4378473350 hasConceptScore W4378473350C43214815 @default.
• W4378473350 hasConceptScore W4378473350C60644358 @default.
• W4378473350 hasConceptScore W4378473350C62520636 @default.

• next