New strategy for Turbo Similarity Searching: Implementation and testing

Nurul Malim, Yong Pei-Chia, Shereena M. Arif

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    3 Citations (Scopus)

    Abstract

    Virtual screening is one of the most vital methods applied in Chemoinformatics, the field that contributes to drug discovery process. Turbo Similarity Searching (TSS) and data fusion are two of the latest chemical similarity searching strategies, which has evolved from the conventional similarity searching (SS) that apply the concept of multi-target searching instead of just an individual target search. The indirect relationship exists in TSS, with the inclusion of Nearest Neighbours (NN) has been proven to have better performance than the direct relationship (i.e. between query structure and database structures) that exists in similarity searching process. In this paper, we will focus on the implementation and improvement of the existing TSS. By adding in another layer of indirect relationship between the reference compound and the database compounds, along with an additional fusion layer, the performance of the new TSS strategy can be observed. The initial results indicated that there is an obvious increment in the recall value when applying the new strategy. The results are also evaluated with the significance test to show that the result produced by the new strategy is true and does not occurred by chance. Further work on different activity classes and different descriptors on the new strategy are expected to generate a better performance than the existing TSS.

    Original languageEnglish
    Title of host publication2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013
    PublisherIEEE Computer Society
    Pages179-184
    Number of pages6
    DOIs
    Publication statusPublished - 2013
    Event2013 5th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013 - Bali
    Duration: 28 Sep 201329 Sep 2013

    Other

    Other2013 5th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013
    CityBali
    Period28/9/1329/9/13

    Fingerprint

    Data fusion
    Testing
    Screening
    Drug Discovery

    ASJC Scopus subject areas

    • Computer Science (miscellaneous)
    • Information Systems

    Cite this

    Malim, N., Pei-Chia, Y., & Arif, S. M. (2013). New strategy for Turbo Similarity Searching: Implementation and testing. In 2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013 (pp. 179-184). [6761572] IEEE Computer Society. https://doi.org/10.1109/ICACSIS.2013.6761572

    New strategy for Turbo Similarity Searching : Implementation and testing. / Malim, Nurul; Pei-Chia, Yong; Arif, Shereena M.

    2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013. IEEE Computer Society, 2013. p. 179-184 6761572.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Malim, N, Pei-Chia, Y & Arif, SM 2013, New strategy for Turbo Similarity Searching: Implementation and testing. in 2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013., 6761572, IEEE Computer Society, pp. 179-184, 2013 5th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013, Bali, 28/9/13. https://doi.org/10.1109/ICACSIS.2013.6761572
    Malim N, Pei-Chia Y, Arif SM. New strategy for Turbo Similarity Searching: Implementation and testing. In 2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013. IEEE Computer Society. 2013. p. 179-184. 6761572 https://doi.org/10.1109/ICACSIS.2013.6761572
    Malim, Nurul ; Pei-Chia, Yong ; Arif, Shereena M. / New strategy for Turbo Similarity Searching : Implementation and testing. 2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013. IEEE Computer Society, 2013. pp. 179-184
    @inproceedings{8584116a67384d8382c806fff658641a,
    title = "New strategy for Turbo Similarity Searching: Implementation and testing",
    abstract = "Virtual screening is one of the most vital methods applied in Chemoinformatics, the field that contributes to drug discovery process. Turbo Similarity Searching (TSS) and data fusion are two of the latest chemical similarity searching strategies, which has evolved from the conventional similarity searching (SS) that apply the concept of multi-target searching instead of just an individual target search. The indirect relationship exists in TSS, with the inclusion of Nearest Neighbours (NN) has been proven to have better performance than the direct relationship (i.e. between query structure and database structures) that exists in similarity searching process. In this paper, we will focus on the implementation and improvement of the existing TSS. By adding in another layer of indirect relationship between the reference compound and the database compounds, along with an additional fusion layer, the performance of the new TSS strategy can be observed. The initial results indicated that there is an obvious increment in the recall value when applying the new strategy. The results are also evaluated with the significance test to show that the result produced by the new strategy is true and does not occurred by chance. Further work on different activity classes and different descriptors on the new strategy are expected to generate a better performance than the existing TSS.",
    author = "Nurul Malim and Yong Pei-Chia and Arif, {Shereena M.}",
    year = "2013",
    doi = "10.1109/ICACSIS.2013.6761572",
    language = "English",
    pages = "179--184",
    booktitle = "2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - New strategy for Turbo Similarity Searching

    T2 - Implementation and testing

    AU - Malim, Nurul

    AU - Pei-Chia, Yong

    AU - Arif, Shereena M.

    PY - 2013

    Y1 - 2013

    N2 - Virtual screening is one of the most vital methods applied in Chemoinformatics, the field that contributes to drug discovery process. Turbo Similarity Searching (TSS) and data fusion are two of the latest chemical similarity searching strategies, which has evolved from the conventional similarity searching (SS) that apply the concept of multi-target searching instead of just an individual target search. The indirect relationship exists in TSS, with the inclusion of Nearest Neighbours (NN) has been proven to have better performance than the direct relationship (i.e. between query structure and database structures) that exists in similarity searching process. In this paper, we will focus on the implementation and improvement of the existing TSS. By adding in another layer of indirect relationship between the reference compound and the database compounds, along with an additional fusion layer, the performance of the new TSS strategy can be observed. The initial results indicated that there is an obvious increment in the recall value when applying the new strategy. The results are also evaluated with the significance test to show that the result produced by the new strategy is true and does not occurred by chance. Further work on different activity classes and different descriptors on the new strategy are expected to generate a better performance than the existing TSS.

    AB - Virtual screening is one of the most vital methods applied in Chemoinformatics, the field that contributes to drug discovery process. Turbo Similarity Searching (TSS) and data fusion are two of the latest chemical similarity searching strategies, which has evolved from the conventional similarity searching (SS) that apply the concept of multi-target searching instead of just an individual target search. The indirect relationship exists in TSS, with the inclusion of Nearest Neighbours (NN) has been proven to have better performance than the direct relationship (i.e. between query structure and database structures) that exists in similarity searching process. In this paper, we will focus on the implementation and improvement of the existing TSS. By adding in another layer of indirect relationship between the reference compound and the database compounds, along with an additional fusion layer, the performance of the new TSS strategy can be observed. The initial results indicated that there is an obvious increment in the recall value when applying the new strategy. The results are also evaluated with the significance test to show that the result produced by the new strategy is true and does not occurred by chance. Further work on different activity classes and different descriptors on the new strategy are expected to generate a better performance than the existing TSS.

    UR - http://www.scopus.com/inward/record.url?scp=84898774142&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84898774142&partnerID=8YFLogxK

    U2 - 10.1109/ICACSIS.2013.6761572

    DO - 10.1109/ICACSIS.2013.6761572

    M3 - Conference contribution

    AN - SCOPUS:84898774142

    SP - 179

    EP - 184

    BT - 2013 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2013

    PB - IEEE Computer Society

    ER -