AUC Comparison.
<div><p>An important issue in biotechnology is predicting whether a piRNA and an mRNA will or will not bind. Research and treatment of diseases, drug discovery, and the silencing and regulation of genes, transposons, and genomic stability may all benefit from accurate binding predictions...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| منشور في: |
2025
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852019014188924928 |
|---|---|
| author | Ahmet Gürhanlı (21602042) |
| author_facet | Ahmet Gürhanlı (21602042) |
| author_role | author |
| dc.creator.none.fl_str_mv | Ahmet Gürhanlı (21602042) |
| dc.date.none.fl_str_mv | 2025-06-25T18:19:41Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0324462.t011 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/dataset/AUC_Comparison_/29408735 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Microbiology Genetics Molecular Biology Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified model &# 8217 genomic stability may effective transformer model briefly introduces transformers accurate binding predictions important design alternatives mrna binding prediction important issue design affects xlink "> use self results show proper adjustment paper summarizes optimization algorithm mrna sequences models available mer size learning models including k good candidate evaluated thoroughly drug discovery core modules auc value 38 %. |
| dc.title.none.fl_str_mv | AUC Comparison. |
| dc.type.none.fl_str_mv | Dataset info:eu-repo/semantics/publishedVersion dataset |
| description | <div><p>An important issue in biotechnology is predicting whether a piRNA and an mRNA will or will not bind. Research and treatment of diseases, drug discovery, and the silencing and regulation of genes, transposons, and genomic stability may all benefit from accurate binding predictions. The literature offers numerous deep-learning models for piRNA and mRNA binding prediction. However, a proper adjustment of the effective transformer model and the impact of important design alternatives has not been evaluated thoroughly. This paper summarizes the models available in the literature, briefly introduces transformers, then offers a novel deep learning model and evaluates various design alternatives, including k-mer size, number of core modules, choice of optimization algorithm, and whether to use self-attention. The results show that rbpTransformer can be a good candidate for building deep AI models to predict the binding of piRNA and mRNA sequences with an AUC value of 94.38%. The test results also reveal how the design affects the model’s accuracy.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_0cfaf638d63cce65ba47b4e1e81e6d39 |
| identifier_str_mv | 10.1371/journal.pone.0324462.t011 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/29408735 |
| publishDate | 2025 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | AUC Comparison.Ahmet Gürhanlı (21602042)MicrobiologyGeneticsMolecular BiologyBiological Sciences not elsewhere classifiedChemical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedmodel &# 8217genomic stability mayeffective transformer modelbriefly introduces transformersaccurate binding predictionsimportant design alternativesmrna binding predictionimportant issuedesign affectsxlink ">use selfresults showproper adjustmentpaper summarizesoptimization algorithmmrna sequencesmodels availablemer sizelearning modelsincluding kgood candidateevaluated thoroughlydrug discoverycore modulesauc value38 %.<div><p>An important issue in biotechnology is predicting whether a piRNA and an mRNA will or will not bind. Research and treatment of diseases, drug discovery, and the silencing and regulation of genes, transposons, and genomic stability may all benefit from accurate binding predictions. The literature offers numerous deep-learning models for piRNA and mRNA binding prediction. However, a proper adjustment of the effective transformer model and the impact of important design alternatives has not been evaluated thoroughly. This paper summarizes the models available in the literature, briefly introduces transformers, then offers a novel deep learning model and evaluates various design alternatives, including k-mer size, number of core modules, choice of optimization algorithm, and whether to use self-attention. The results show that rbpTransformer can be a good candidate for building deep AI models to predict the binding of piRNA and mRNA sequences with an AUC value of 94.38%. The test results also reveal how the design affects the model’s accuracy.</p></div>2025-06-25T18:19:41ZDatasetinfo:eu-repo/semantics/publishedVersiondataset10.1371/journal.pone.0324462.t011https://figshare.com/articles/dataset/AUC_Comparison_/29408735CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/294087352025-06-25T18:19:41Z |
| spellingShingle | AUC Comparison. Ahmet Gürhanlı (21602042) Microbiology Genetics Molecular Biology Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified model &# 8217 genomic stability may effective transformer model briefly introduces transformers accurate binding predictions important design alternatives mrna binding prediction important issue design affects xlink "> use self results show proper adjustment paper summarizes optimization algorithm mrna sequences models available mer size learning models including k good candidate evaluated thoroughly drug discovery core modules auc value 38 %. |
| status_str | publishedVersion |
| title | AUC Comparison. |
| title_full | AUC Comparison. |
| title_fullStr | AUC Comparison. |
| title_full_unstemmed | AUC Comparison. |
| title_short | AUC Comparison. |
| title_sort | AUC Comparison. |
| topic | Microbiology Genetics Molecular Biology Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified model &# 8217 genomic stability may effective transformer model briefly introduces transformers accurate binding predictions important design alternatives mrna binding prediction important issue design affects xlink "> use self results show proper adjustment paper summarizes optimization algorithm mrna sequences models available mer size learning models including k good candidate evaluated thoroughly drug discovery core modules auc value 38 %. |