Selamat kepada Ibu Afiahayati bersama Vincent Michael Sutanto dan Zaki Indra Sukma dari Gojek Indonesia, yang telah mempublikasikan karyanya berjudul “Predicting Secondary Structure of Protein Using Hybrid of Convolutional Neural Network and Support Vector Machine” yang terbit pada Jurnal Internasional “International Journal of Intelligent Engineering & Systems” (Scopus Q2) di awal 2021 ini.

Paper ini berisikan tentang bagaimana metode CNN dikombinasikan dengan SVM untuk melakukan Sequence Labelling Task. read more

Selamat kepada Ibu Afiahayati bersama Hanifia Dyoniputri dari Klikdokter yang telah mempublikasikan paper berjudul “A Hybrid Convolutional Neural Network and Support Vector Machine for Dysarthria Speech Classification” pada International Journal of Innovative Computing, Information and Control.

Paper ini memberikan hasil bahwa CNN-SVM Hybrid memberikan hasil yang lebih baik daripada CNN biasa dan beberapa temuan lainnya.

Full paper dapat diakses di http://www.ijicic.org/ijicic-170107.pdf read more

Selamat kepada Ibu Afiahayati yang tergabung dalam tim NGS COVID-19 UGM. Tim telah mempublikasikan paper berjudul ”Full-length genome characterization and phylogenetic analysis of SARS-CoV-2 virus strains from Yogyakarta and Central Java, Indonesia ” pada PeerJ Journal (Scopus Q1, Impact Factor:2,8).

Pada paper ini, dipaparkan terkait karakterisktik dan analisis filogenetik Virus Sars-Cov-2 dari sample pasien di Yogyakarta dan Jawa Tengah, juga ditemukan beberapa mutasi diantaranya D614G yang memiliki daya infeksi 10 kali lebih tinggi. Pada penelitian ini, peran bioinformatika sangat penting diantaranya untuk melakukan assembly, alignment, konstruksi dan analisis filogenetik serta menemukan mutasi dari virus. read more

Selamat kepada Bapak Retantyo Wardoyo, Ph.D., telah mempublikasikan paper berjudul “Analysis of Fuzzy Logic Modification for Student Assessment in e-Learning” pada International Journal on Informatics for Development (Sinta S4)

Abstract

The phenomenon of the rapid transfer of learning to online systems, such as e-Learning, has occurred massively. Institutions must ensure that student assessments run well. The characteristics of learning in e-Learning require an appropriate assessment method. The fuzzy logic method can be an option. Research shows that fuzzy logic is capable of providing flexible and objective performance evaluation. Fuzzy logic is a method that can overcome the uncertainty of transparency and objectivity of student assessments. In general, fuzzy logic applications are carried out by standards. Modification is an attempt to reveal the flexibility and to optimize the use of fuzzy logic. This study presents an analysis of fuzzy logic modification for the assessment of Algorithm and Data Structures courses held in e-Learning. These modifications include (i) modification of the parameter score with score compatibility, (ii) consequent modification of the fuzzy rules and (iii) modification of the implication process. The study results show that although the use of fuzzy logic requires more complicated procedures and tools, it can present various kinds of assessment as an option for educators to assess students in e-Learning.

Keywords

student assessment; e-Learning; fuzzy logic; compatibility; fuzzy rule; implication

Artikel lengkap dapat diakses melalui URL

http://ejournal.uin-suka.ac.id/saintek/ijid/article/view/2071

Selamat kepada Ibu Afiahayati yang tergabung dalam tim NGS untuk Cancer Analysis. Tim telah mempublikasikan paper berjudul ”Transcriptome Related to Avoiding Immune Destruction in Nasopharyngeal Cancer in Indonesian Patients Using Next-Generation Sequencing” pada Asian Pacific Journal of Cancer Prevention (Scopus Q2)

Abstract
Objective: This study aims to obtain the transcriptomes profile associated with avoiding immune destruction from nasopharyngeal cancer patients in Indonesia using next-generation sequencing. Methods: The samples are divided into two types of samples; 1) biopsy of nasopharyngeal cancer tissue samples, 2) brushing tissue of people without nasopharyngeal cancer as control samples. The sequencing results were mapped (HISAT2) and quantified (HTSeq) for differential expression analysis using edgeR software. Transcripts data analyzed with Pantherdb and DAVID software to find genes related to the immune system and pathways related to immune destruction by cancer. Results: The differential expression results show that 2,046 genes that have a significant differential expression. The 90 genes expression has down-regulated and 1,956 genes expression up-regulated, there are 20 genes related to the immune system. The 20 genes related to the immune system by analyzing lionproject.net that directly related to hallmark avoiding immune destruction that genes are CXCL9/10/11. The gene expression of CXCL9/10/11 regulates PD-L1 expressions via the Jak/STAT signaling pathway. The interaction between the extracellular domain PD-1 and PD-L1 in cancer cells have avoiding immune destruction. Conclusion: The results of this study suggest that the gene expression of CXCL9/10/11 have up-regulated is related to avoiding immune destruction that can use as an early detection biomarker of nasopharyngeal cancer in Indonesian patients. read more

Selamat kepada Ibu Afiahayati yang tergabung dalam tim NGS untuk Cancer Analysis. Tim telah mempublikasikan paper berjudul ”Transcriptome Profile of Next Generation Sequence Data Related to Inflammation on Nasopharyngeal Carcinoma Cases in Indonesia” pada Asian Pacific Journal of Cancer Prevention (Scopus Q2)

Abstract
Objective: Transcriptomic Profile Analysis Related to Inflammation in Nasopharyngeal Carcinoma Cases. Methods: This study used 2 control samples taken using the brushing technique and 7 cancer samples with tissue biopsy. Isolate total RNA using Rneasy® RNA Extraction Mini Kit. Measurement of total RNA concentration and purity using a fluorometer and nanodrop Qubit. Synthesis of cDNA library uses TruSeq® RNA Library Preparation Kit V2 and concentration is measured using qPCR. Sequencing samples using NGS Illumina NextSeq 550 platform engine. Quality control results of sequencing using FASTQC, and raw data processing using HISAT2. Differential analysis of gene expression (DEGs) using edgeR and pathway analysis using DAVID and PANTHER. Results: From the 25,493 genes that experienced a significant change in expression level (P <0.05) from DEG analysis there were 13 genes that play a role in the inflammatory process. Based on DAVID pathway analysis software, there are 8 genes detected based on the KEGG pathway database found in 2 pathways, namely Inflammatory Mediator Regulation of TRP Channels pathway with genes that play HTR2A, NGF, TRPA1, PRKCG, and ADCY8. CXCL9, CXCL10, and CXCL11 genes are found in the Toll-Like Receptor Signaling pathway. Based on PANTHER pathway analysis software, 6 genes were found, namely CXCL10, MYLK2, COL20A1, MYH2, ACTC1, and ALOX15 in the Inflammation Mediated by Chemokine and Cytokine Signaling pathways. Almost all genes found from DEGs are upregulated, except the ALOX15 gene that is downregulated. Conclusion: There are 13 genes that play a role in the inflammatory process in Nasopharyngeal Carcinomafrom a sample of the Indonesian population. Genes CXCL9, CXCL10, CXCL11, MYLK2, COL20A1, MYH2, ACTC1, HTR2A, NGF, TRPA1, PRKCG, and ADCY8 have been upregulated and ALOX15 has been downregulated. These genes play a role in the Inflammation Mediated by Chemokine and Cytokine Signaling pathways, Inflammatory Mediator Regulation of TRP Channels, and Toll-Like Receptor Signaling. read more

Selamat kepada Ibu Afiahayati yang bergabung dalam tim NGS untuk Cancer Analysis. Tim telah mempublikasikan paper berjudul “Transcriptome Profile of Next-Generation Sequencing Data Relate to Proliferation Aberration of Nasopharyngeal Carcinoma Patients in Indonesia (Scopus Q2)

Abstract
Objective: Nasopharyngeal carcinoma (NPC) is the most common cancer arising from epithelial cells of the nasopharynx in  Indonesia. This study aims to determine the differential level of gene expression in NPC patients when compared with normal individuals. Transcriptome profiling analysis was performed using RNA-Seq technology to determine the differential gene expression relate to proliferation aberration that occurs in NPC patients compared with normal individuals. So we get the transcriptomic profile of Indonesia NPC patients. Methods: In this study, we used 9 samples, 7 NPC samples and 2 normal samples as control.  Fresh tissue of tumor samples was collected from biopsy, and normal samples were collected brushing technique. The total RNA was isolated from fresh tissue samples and brushing samples using the Rneasy® RNA Extraction Mini Kit. The cDNA library was generated using TruSeq® RNA Library Preparation Kit V2, and its concentration was determined using qPCR. The library was sequenced using the Next-Generation Sequencing (NGS) Illumina Next Seq 550 platform. The raw sequence data quality was analyzed using FastQC and interpreted using HISAT2, HTSeq, edgeR, and PANTHER. Results: From the analysis, 25493 gene transcripts were expressed, with 1956 genes were significantly upregulated, 90 genes were significantly downregulated in NPC samples, and 23897 genes didn’t change the expression level significantly (p <0.05), 10 of which genes were associated with cell proliferation. These genes are involved in the regulation of cancer cell proliferation through several signaling pathways, which are the apoptosis signaling pathway, IGF signaling pathway, Notch signaling pathway, and P13K signaling pathway. Conclusion: There were significant differences in gene expression levels between NPC patients and normal individuals. Each gene that has changed the expression level plays a role in regulating various pathways that lead to cell proliferation aberration in NPC cases. read more

Selamat kepada Andika William (Alumni International Undergradute Program of Computer Science, UGM) dan Ibu Yunita Sari, Ph.D. yang telah mempublikasikan paper berjudul “CLICK-ID: A Novel Dataset for Indonesian Clickbait Headlines”. Paper dipublikasikan pada international journal Data in Brief (Scopus Q4)

Abstract
News analysis is a popular task in Natural Language Processing (NLP). In particular, the problem of clickbait in news analysis has gained attention in recent years [1, 2]. However, the majority of the tasks has been focused on English news, in which there is already a rich representative resource. For other languages, such as Indonesian, there is still a lack of resource for clickbait tasks. Therefore, we introduce the CLICK-ID dataset of Indonesian news headlines extracted from 12 Indonesian online news publishers. It is comprised of 15,000 annotated headlines with clickbait and non-clickbait labels. Using the CLICK-ID dataset, we then developed an Indonesian clickbait classification model achieving favourable performance. We believe that this corpus will be useful for replicable experiments in clickbait detection or other experiments in NLP areas. read more

Selamat kepada Dyah Aruming Tyas (Mahasiswa PMDSU Ilmu Komputer), Prof. Sri Hartati, Ph.D, Bapak Agus Harjoko, Ph.D. dan Dr. dr. Tri Ratnaningsih yang telah mempublikasikan paper berjudul “Morphological, Texture, and Color Feature Analysis for Erythrocyte Classification in Thalassemia Cases”. Paper dipublikasikan pada international journal IEEEAccess (Scopus Q1, Impact Factor : 3,74)

Abstract:

Abnormal erythrocytes have diverse shapes. The appearance of specific erythrocyte shapes in a person’s blood can indicate certain diseases, including thalassemia. We used thalassemia peripheral blood smear images and applied a segmentation process to produce single erythrocyte sub-images. Each erythrocyte has a unique shape. The selection of appropriate features to represent erythrocytes is critical for classification accuracy. We used morphological features such as moment invariants, geometry parameters of the cell and central pallor, and distance angle signature (DAS) morphological features of the cell and central pallor. We combined morphological features with texture and color features to increase the accuracy of erythrocyte classification. In this study, the multi-layer perceptron is used to classify nine shapes of erythrocytes present in thalassemia cases. The experimental results of 7108 erythrocytes indicated an accuracy of 98.11% based on the combination of features. The experimental results also show that the combination of features we proposed produced higher classification accuracy than previous work, which yielded an accuracy of 93.77%. Keywords: Classification, distance angle signature, erythrocytes, morphological feature, thalassemia

Artikel lengkap dapat diakses melalui URL
https://ieeexplore.ieee.org/document/9046795

Selamat kepada Bu Binti Solihah (Mahasiswa S3 Ilmu Komputer), Pak Dr. Azhari dan Bu Aina Musdholifah, Ph.D. yang telah mempublikasikan paper berjudul “Enhancement of conformational B-cell
epitope prediction using CluSMOTE”. Paper dipublikasikan pada international journal PeerJ Computer Science (Scopus Q1).

Enhancement of conformational B-cell epitope prediction using CluSMOTE

Background
A conformational B-cell epitope is one of the main components of vaccine design. It contains separate segments in its sequence, which are spatially close in the antigen chain. The availability of Ag-Ab complex data on the Protein Data Bank allows for the development predictive methods. Several epitope prediction models also have been developed, including learning-based methods. However, the performance of the model is still not optimum. The main problem in learning-based prediction models is class imbalance. read more