An Evaluation of Deep Neural Network Performance on Limited Protein Phosphorylation Site Prediction Data

Lumbanraja, Favorisen Rosyking; Mahesworo, Bharuno; Cenggoro, Tjeng Wawan; Budiarto, Arif; Pardamean, Bens

doi:10.1016/j.procs.2019.08.137

Cited by 34 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 5)), and area under curve (AUC) (Bradley, 1997). These metrics were commonly employed in the previous research with a focus on prediction protein phosphorylation site (Lumbanraja et al, 2018;Lumbanraja et al, 2019). The AUC was computed using the scikit-learn library from the receiver operating characteristic (ROC) of the models' performance.…”

Section: Discussionmentioning

confidence: 99%

SSMFN: a fused spatial and sequential deep learning model for methylation site prediction

Lumbanraja

Mahesworo

Cenggoro

et al. 2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

Background Conventional in vivo methods for post-translational modification site prediction such as spectrophotometry, Western blotting, and chromatin immune precipitation can be very expensive and time-consuming. Neural networks (NN) are one of the computational approaches that can predict effectively the post-translational modification site. We developed a neural network model, namely the Sequential and Spatial Methylation Fusion Network (SSMFN), to predict possible methylation sites on protein sequences. Method We designed our model to be able to extract spatial and sequential information from amino acid sequences. Convolutional neural networks (CNN) is applied to harness spatial information, while long short-term memory (LSTM) is applied for sequential data. The latent representation of the CNN and LSTM branch are then fused. Afterwards, we compared the performance of our proposed model to the state-of-the-art methylation site prediction models on the balanced and imbalanced dataset. Results Our model appeared to be better in almost all measurement when trained on the balanced training dataset. On the imbalanced training dataset, all of the models gave better performance since they are trained on more data. In several metrics, our model also surpasses the PRMePred model, which requires a laborious effort for feature extraction and selection. Conclusion Our models achieved the best performance across different environments in almost all measurements. Also, our result suggests that the NN model trained on a balanced training dataset and tested on an imbalanced dataset will offer high specificity and low sensitivity. Thus, the NN model for methylation site prediction should be trained on an imbalanced dataset. Since in the actual application, there are far more negative samples than positive samples.

show abstract

Section: Discussionmentioning

confidence: 99%

SSMFN: a fused spatial and sequential deep learning model for methylation site prediction

Lumbanraja

Mahesworo

Cenggoro

et al. 2021

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…The results of the model evaluation are presented in Table I and also shown by the graphic display in Figure 2. Equation ( 1)-( 3) can be used to calculate the evaluation of model training results [32].…”

Section: E Model Trainingmentioning

confidence: 99%

Sistem Deteksi Masker Berbasis Jetson Nano dengan Deep Learning Framework TensorFlow

Bukhori¹,

Prasetiyo

2023

JNTETI

View full text Add to dashboard Cite

Indonesia merupakan salah satu negara yang mengalami dampak virus COVID-19. Segala upaya dilakukan untuk menanggulangi penyebaran virus ini. Salah satu langkah yang efisien guna menanggulangi dampak ini adalah dengan menerapkan protokol kesehatan yang ketat dan pemakaian masker dengan benar. Pemantauan penggunaan masker terus dilakukan di gedung perkantoran, supermarket, maupun ruang publik lainnya. Peran pengawas sangat diperlukan untuk mengawasi pemakaian masker dengan benar. Namun, seorang pengawas mempunyai keterbatasan dalam melakukan pengawasan, sehingga menimbulkan celah bagi orang-orang untuk tidak mematuhi aturan pemakaian masker dengan benar. Oleh karena itu, perlu adanya sistem yang bekerja secara otomatis untuk membantu pengawas dalam memantau pemakaian masker dengan benar. Tujuan makalah ini adalah merancang sebuah computer vision yang dapat mendeteksi seseorang bermasker atau tidak menggunakan deep learning framework TensorFlow. TensorFlow digunakan karena efisiensinya dalam mengolah data citra digital. Klasifikasi data citra digital pada TensorFlow menggunakan struktur deep learning Keras, sehingga ringan dan mampu digunakan pada perangkat tertanam seperti Jetson Nano untuk mendeteksi penggunaan masker secara real-time. Tahapan sistem pendeteksian masker terdiri atas pengumpulan dataset citra, ekstraksi ciri, pemisahan data, pembuatan model, pelatihan model, dan penerapan model. Deep learning framework TensorFlow memproses data citra secara langsung melalui kamera web (webcam). Ketika kamera menangkap objek orang yang sedang tidak menggunakan masker dengan benar, layar monitor menampilkan kotak merah pada wajah. Tanda ini dapat membantu pengawas saat melakukan pengawasan. Hasil pengujian menunjukkan bahwa sistem berhasil mendeteksi dengan benar orang yang tidak menggunakan masker, dengan akurasi sebesar 99,48%. Selain itu, sistem juga berhasil mendeteksi orang yang memakai masker dengan benar dan mendapatkan rata-rata akurasi sebesar 99,12%. Monitor akan menampikan kotak hijau pada wajah jika orang yang dideteksi memakai masker dengan benar.

show abstract

“…Phosphorylation site prediction has recently emerged as an important problem in the field of bioinformatics. As a result, many phosphorylation site prediction tools have been developed to predict both general and kinase-specific phosphorylation sites ( Lumbanraja et al, 2019 ; Luo et al, 2019 ; Haixia et al, 2020 ; Wang D. et al, 2020 ; Ahmed et al, 2021 ; Guo et al, 2021 ). For instance, to predict general phosphorylation sites based on the primary amino acid sequence of an input protein, Ismail et al developed the Random Forest (RF)-based phosphosite predictor 2.0 (RF-Phos 2.0) ( Ismail et al, 2016 ).…”

Section: Introductionmentioning

confidence: 99%

DTL-DephosSite: Deep Transfer Learning Based Approach to Predict Dephosphorylation Sites

Chaudhari

Thapa

Ismail

et al. 2021

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

Phosphorylation, which is mediated by protein kinases and opposed by protein phosphatases, is an important post-translational modification that regulates many cellular processes, including cellular metabolism, cell migration, and cell division. Due to its essential role in cellular physiology, a great deal of attention has been devoted to identifying sites of phosphorylation on cellular proteins and understanding how modification of these sites affects their cellular functions. This has led to the development of several computational methods designed to predict sites of phosphorylation based on a protein’s primary amino acid sequence. In contrast, much less attention has been paid to dephosphorylation and its role in regulating the phosphorylation status of proteins inside cells. Indeed, to date, dephosphorylation site prediction tools have been restricted to a few tyrosine phosphatases. To fill this knowledge gap, we have employed a transfer learning strategy to develop a deep learning-based model to predict sites that are likely to be dephosphorylated. Based on independent test results, our model, which we termed DTL-DephosSite, achieved efficiency scores for phosphoserine/phosphothreonine residues of 84%, 84% and 0.68 with respect to sensitivity (SN), specificity (SP) and Matthew’s correlation coefficient (MCC). Similarly, DTL-DephosSite exhibited efficiency scores of 75%, 88% and 0.64 for phosphotyrosine residues with respect to SN, SP, and MCC.

show abstract

An Evaluation of Deep Neural Network Performance on Limited Protein Phosphorylation Site Prediction Data

Cited by 34 publications

References 22 publications

SSMFN: a fused spatial and sequential deep learning model for methylation site prediction

SSMFN: a fused spatial and sequential deep learning model for methylation site prediction

Sistem Deteksi Masker Berbasis Jetson Nano dengan Deep Learning Framework TensorFlow

DTL-DephosSite: Deep Transfer Learning Based Approach to Predict Dephosphorylation Sites

Contact Info

Product

Resources

About