FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3211676052> ?p ?o ?g. }

• W3211676052 endingPage "9483" @default.
• W3211676052 startingPage "9465" @default.
• W3211676052 abstract "Recent advances in molecular machine learning, especially deep neural networks such as graph neural networks (GNNs), for predicting structure-activity relationships (SAR) have shown tremendous potential in computer-aided drug discovery. However, the applicability of such deep neural networks is limited by the requirement of large amounts of training data. In order to cope with limited training data for a target task, transfer learning for SAR modeling has been recently adopted to leverage information from data of related tasks. In this work, in contrast to the popular parameter-based transfer learning such as pretraining, we develop novel deep transfer learning methods TAc and TAc-fc to leverage source domain data and transfer useful information to the target domain. TAc learns to generate effective molecular features that can generalize well from one domain to another and increase the classification performance in the target domain. Additionally, TAc-fc extends TAc by incorporating novel components to selectively learn feature-wise and compound-wise transferability. We used the bioassay screening data from PubChem and identified 120 pairs of bioassays such that the active compounds in each pair are more similar to each other compared to their inactive compounds. Overall, TAc achieves the best performance with an average ROC-AUC of 0.801; it significantly improves the ROC-AUC of 83% of target tasks with an average task-wise performance improvement of 7.102%, compared to the best baseline dmpna. Our experiments clearly demonstrate that TAc achieves significant improvement over all baselines across a large number of target tasks. Furthermore, although TAc-fc achieves slightly worse ROC-AUC on average compared to TAc (0.798 vs 0.801), TAc-fc still achieves the best performance on more tasks in terms of PR-AUC and F1 compared to other methods. In summary, TAc-fc is also found to be a strong model with competitive or even better performance than TAc on a notable number of target tasks." @default.
• W3211676052 created "2021-11-22" @default.
• W3211676052 creator A5002832419 @default.
• W3211676052 creator A5028997621 @default.
• W3211676052 creator A5047987659 @default.
• W3211676052 date "2022-03-11" @default.
• W3211676052 modified "2023-10-16" @default.
• W3211676052 title "Improving Compound Activity Classification via Deep Transfer and Representation Learning" @default.
• W3211676052 cites W1971327393 @default.
• W3211676052 cites W1978253274 @default.
• W3211676052 cites W1988037271 @default.
• W3211676052 cites W1988195734 @default.
• W3211676052 cites W1999798000 @default.
• W3211676052 cites W2006286139 @default.
• W3211676052 cites W2017398555 @default.
• W3211676052 cites W2056562706 @default.
• W3211676052 cites W2060851522 @default.
• W3211676052 cites W2064675550 @default.
• W3211676052 cites W2074176940 @default.
• W3211676052 cites W2075665815 @default.
• W3211676052 cites W2085074871 @default.
• W3211676052 cites W2085145070 @default.
• W3211676052 cites W2085411747 @default.
• W3211676052 cites W2086098969 @default.
• W3211676052 cites W2096729078 @default.
• W3211676052 cites W2096943734 @default.
• W3211676052 cites W2112411768 @default.
• W3211676052 cites W2115403315 @default.
• W3211676052 cites W2116341502 @default.
• W3211676052 cites W2121175754 @default.
• W3211676052 cites W2146211839 @default.
• W3211676052 cites W2152681556 @default.
• W3211676052 cites W2154117231 @default.
• W3211676052 cites W2163204906 @default.
• W3211676052 cites W2163646378 @default.
• W3211676052 cites W2165698076 @default.
• W3211676052 cites W2200017991 @default.
• W3211676052 cites W2213443318 @default.
• W3211676052 cites W2221269644 @default.
• W3211676052 cites W2279949369 @default.
• W3211676052 cites W2290847742 @default.
• W3211676052 cites W2493157521 @default.
• W3211676052 cites W2558217333 @default.
• W3211676052 cites W2565684601 @default.
• W3211676052 cites W2589279470 @default.
• W3211676052 cites W2593768305 @default.
• W3211676052 cites W2594183968 @default.
• W3211676052 cites W2605488490 @default.
• W3211676052 cites W2734982589 @default.
• W3211676052 cites W2751756351 @default.
• W3211676052 cites W2753588101 @default.
• W3211676052 cites W2767147442 @default.
• W3211676052 cites W2770942678 @default.
• W3211676052 cites W2786808285 @default.
• W3211676052 cites W2788768841 @default.
• W3211676052 cites W2789796452 @default.
• W3211676052 cites W2790808809 @default.
• W3211676052 cites W2801991413 @default.
• W3211676052 cites W2805404971 @default.
• W3211676052 cites W2887280559 @default.
• W3211676052 cites W2894566366 @default.
• W3211676052 cites W2899070097 @default.
• W3211676052 cites W2903198840 @default.
• W3211676052 cites W2911107164 @default.
• W3211676052 cites W2914757825 @default.
• W3211676052 cites W2915792373 @default.
• W3211676052 cites W2948035163 @default.
• W3211676052 cites W2956769933 @default.
• W3211676052 cites W2962764460 @default.
• W3211676052 cites W2966357564 @default.
• W3211676052 cites W2969849947 @default.
• W3211676052 cites W2980113592 @default.
• W3211676052 cites W2982197252 @default.
• W3211676052 cites W2982691277 @default.
• W3211676052 cites W3000478925 @default.
• W3211676052 cites W3030978062 @default.
• W3211676052 cites W3032781902 @default.
• W3211676052 cites W3041133507 @default.
• W3211676052 cites W3042826782 @default.
• W3211676052 cites W3097145107 @default.
• W3211676052 cites W3101498208 @default.
• W3211676052 cites W3112376646 @default.
• W3211676052 cites W3130274530 @default.
• W3211676052 doi "https://doi.org/10.1021/acsomega.1c06805" @default.
• W3211676052 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35350358" @default.
• W3211676052 hasPublicationYear "2022" @default.
• W3211676052 type Work @default.
• W3211676052 sameAs 3211676052 @default.
• W3211676052 citedByCount "3" @default.
• W3211676052 countsByYear W32116760522022 @default.
• W3211676052 countsByYear W32116760522023 @default.
• W3211676052 crossrefType "journal-article" @default.
• W3211676052 hasAuthorship W3211676052A5002832419 @default.
• W3211676052 hasAuthorship W3211676052A5028997621 @default.
• W3211676052 hasAuthorship W3211676052A5047987659 @default.
• W3211676052 hasBestOaLocation W32116760522 @default.
• W3211676052 hasConcept C107908354 @default.
• W3211676052 hasConcept C108583219 @default.

• next