Deep-Learning-in-Bioinformatics-Papers-Reading-Roadmap

If you are a newcomer to apply the the Deep Learning in bioinformatics area, the first question you may have is "What is the profile of deep learning in bioinformatics at present?"

Here is a reading roadmap of papers applying Deep Learning in bioinformatics!

Those papers are mainly published in Nature, Nature Methods, Nature protocols, NAR, Briefings in Bioinformatics, Bioinformatics, Drug Discovery Today, Genome Research, Genome Biology, PLoS computational biology, JCIM, JPR, Distill Pub, CACM, JACM, JMLR, and NIPS.

The recently added journals are AC, Nature Chemistry, Nature Reviews Chemistry, and Nature structural & molecular biology.

I would continue adding papers to this roadmap.

-2. LCMS-based proteomics

[0] Zhifei Zhang. "pDeep: Predicting MS/MS Spectra of Peptides with Deep Learning." AC. (November 10, 2017).

[0] Naohiro Kobayashi. "Noise peak filtering in multi-dimensional NMR spectra using convolutional neural networks." Bioinformatics. (09 July 2018).

[1] Ming Li. "De novo peptide sequencing by deep learning." PNAS. (July 18, 2017).

-1. GCMS-based metabolomics

[0] SKARYSZ, A. ... et al, . "Convolutional neural networks for automated targeted analysis of raw gas chromatography–mass spectrometry data." IJCNN 2018. (2018).

0. Drug discovery

[0] Hongmei Lu. "Deep-Learning-Based Drug–Target Interaction Prediction." JPR. (March 6, 2017)

[1] Jianyang Zeng. "NeoDTI: Neural integration of neighbor information from a heterogeneous network for discovering new drug-target interactions." Bioinformatics. (02 July 2018)

[0] Pierre Baldi. "Deep Learning in Biomedical Data Science." Annual Review of Biomedical Data Science. (2018).

1. Biomacromolecular structure prediction

[0] Yaoqi Zhou. "Accurate Prediction of Protein Contact Maps by Coupling Residual Two-Dimensional Bidirectional Long Short-Term Memory with Convolutional Neural Networks." Bioinformatics. (19 June 2018).

[1] Jinbo Xu. "ComplexContact: a web server for inter-protein contact prediction using deep learning." NAR. (22 May 2018).

[2] Jinbo Xu. "Protein threading using residue co-variation and deep learning." Bioinformatics. (1 July 2018).

2. Cell

[0] Jianzhu Ma. "Using deep learning to model the hierarchical structure and function of a cell." Nature Methods. (2018-04). (ps) ⭐⭐⭐⭐⭐

3. Transcription factor-DNA binding

[0] Abdullah M Khamis. "DeFine: deep convolutional neural networks accurately quantify intensities of transcription factor-DNA binding and facilitate evaluation of functional non-coding variants." NAR. (02 April 2018). (ps) ⭐⭐⭐⭐⭐

4. lncRNAs related

[0] Sungroh Yoon. "lncRNAnet: Long Non-coding RNA Identification using Deep Learning." Bioinformatics. (29 May 2018).

[1] Huaiqiu Zhu. "LncADeep: An ab initio lncRNA identification and functional annotation tool based on deep learning." Bioinformatics. (29 May 2018).

5. Gene expression related

[0] Tianwei Yu. "A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data." Bioinformatics. (29 May 2018).

[1] Wesley De Neve. "SpliceRover: Interpretable Convolutional Neural: Networks for Improved Splice Site Prediction." Bioinformatics. (21 June 2018).

[2] David A Hendrix. "A deep recurrent neural network discovers complex biological rules to decipher RNA protein-coding potential." NAR. (09 July 2018)

^Before September 2017 (only a few widely influential papers were selected)

[0] LuZhang, JianjunTan, DanHan, HaoZhu. "From machine learning to deep learning: progress in machine intelligence for rational drug discovery." Drug Discovery Today.

[1] Dapeng Xiong, Jianyang Zeng, and Haipeng Gong. "A deep learning framework for improving long-range residue–residue contact prediction using a hierarchical strategy." Bioinformatics.

[2] Yeeleng S. Vang, Xiaohui Xie. "HLA class I binding prediction via convolutional neural networks." Bioinformatics.

[3] Baoji He, S. M. Mortuza, Yanting Wang, Hong-Bin Shen, Yang Zhang."NeBcon: protein contact map prediction using neural network training coupled with naïve Bayes classifiers." Bioinformatics.

[4] Nansu Zong, Hyeoneui Kim, Victoria Ngo, Olivier Harismendy. "Deep mining heterogeneous networks of biomedical linked data to predict novel drug–target associations." Bioinformatics.

[5] José Juan Almagro Armenteros et al. "DeepLoc: Prediction of protein subcellular localization using deep learning." Bioinformatics.

[6] Bite Yang et al. "BiRen: predicting enhancers with a deep-learning-based model using the DNA sequence alone." Bioinformatics.

[7] William J. Godinez et al. "A multi-scale convolutional neural network for phenotyping high-content cellular images." Bioinformatics.

[8] Xiuquan Du, Yanping Zhang et al. "DeepPPI: Boosting Prediction of Protein–Protein Interactions with Deep Neural Networks." JCIM.

[9] Moritz Hess et al. "Partitioned learning of deep Boltzmann machines for SNP data." Bioinformatics.

[10] Travers Ching et al. "Opportunities and obstacles for deep learning in biology and medicine." bioRxiv.

[11] A Esteva et al. "Dermatologist-level classification of skin cancer with deep neural networks." Nature. (FEB 2 2017).

[12] Seonwoo Min et al. "Deep learning in bioinformatics." Briefings in bioinformatics. (16 June 2016).

contact prediction

The selection of papers in protein residue-residue contact prediction is biased.

The NeBcon paper (Baoji He, S. M. Mortuza, Yanting Wang, Hong-Bin Shen, Yang Zhang."NeBcon: protein contact map prediction using neural network training coupled with naïve Bayes classifiers." Bioinformatics.) does not use deep learning and is therefore irrelevant to this list.
The SPOT-Contact paper (Yaoqi Zhou. "Accurate Prediction of Protein Contact Maps by Coupling Residual Two-Dimensional Bidirectional Long Short-Term Memory with Convolutional Neural Networks." Bioinformatics. (19 June 2018).) and the DeepConPred paper (Dapeng Xiong, Jianyang Zeng, and Haipeng Gong. "A deep learning framework for improving long-range residue–residue contact prediction using a hierarchical strategy." Bioinformatics.) are far less influential than Jinbo Xu's earlier paper

Wang, Sheng, Siqi Sun, Zhen Li, Renyu Zhang, and Jinbo Xu. "Accurate de novo prediction of protein contact map by ultra-deep learning model." PLoS computational biology 13, no. 1 (2017): e1005324.

While this paper is not the first attempt that uses deep learning for protein contact prediction (both DNCON and PConSC2 proceed this work), it is the first work that shows deep learning can obtain significantly higher prediction accuracy in contact prediction than traditional machine learning such as shallow neural network. It is also the first paper to propose formulating contact prediction as pixel level labelling problem instead of image level labelling problem, and to use convolutional neural network (CNN) for this purpose. These ideas are so critical to the performance of contact prediction that almost all recent state-of-the-art deep learning based contact prediction programs, including SPOT-Contact, DNCON2, PConsC4, and DeepCov, follow the CNN based pixel level labelling idea proposed by this paper.

The other two listed paper from the same lab ("ComplexContact: a web server for inter-protein contact prediction using deep learning." and "Protein threading using residue co-variation and deep learning.") are either based on or heavily influenced by the above mentioned earlier work by Wang et al 2017.

bjoux2 / deeplearning-in-bioinformatics Goto Github PK

deeplearning-in-bioinformatics's Introduction

Deep-Learning-in-Bioinformatics-Papers-Reading-Roadmap

-2. LCMS-based proteomics

-1. GCMS-based metabolomics

0. Drug discovery

1. Biomacromolecular structure prediction

2. Cell

3. Transcription factor-DNA binding

4. lncRNAs related

5. Gene expression related

^Before September 2017 (only a few widely influential papers were selected)

deeplearning-in-bioinformatics's People

Stargazers

Watchers

Forkers

deeplearning-in-bioinformatics's Issues

Recommend Projects

Recommend Topics

Recommend Org