A lot of my ideas about Machine Learning come from Quantum Mechanical Perturbation Theory. To provide some context, we need to step back and understand that the familiar techniques of Machine Lear…
a big chance for dry labs
You are into tumor evolution? And got a fancy model? Want to battle with the best?
These are the days of Big Science, my friend. You can’t just have a short name …
View original post 286 more words
Quick recap: Last time we talked about tumor evolution and I presented a toy example to introduce key concepts. I also introduced the intra-tumor phylogeny problem: Given a sample of the genomes of clones in a tumour, reconstruct its `life history’. This problem consists of two sub-problems: (1)identification of clones, and (2) inferring evolutionary relationships between clones.
This problem falls into the general area of reconstructing phylogenetic trees — so how does inferring clonal trees compare to classical phylogenetic methods?
View original post 777 more words
“Cancer evolves dynamically as clonal expansions supersede one another driven by shifting selective pressures, mutational processes, and disrupted cancer genes. These processes mark the genome, such that a cancer’s life history is encrypted in the somatic mutations present,”
write Nik-Zainal et al in the abstract of their 2012 Cell paper `The life history of 21 breast cancers‘. The key figure of their paper shows a phylogenetic tree of tumor development in a patient. The paper contains lots of computational work on analyzing and interpreting mutations based on deep-sequencing data, but –a big surprised but— the very last step of putting together the tree was done manually. Half the paper is describing the reasoning that Peter Campbell and his group used to condense all the evidence they had gathered from genomic data into the tree – but there is no algorithm.
View original post 951 more words
The importance of writing well can never be overstated for a successful professional career, and the ability to write solid papers is an essential trait of a productive researcher. Writing and publishing a paper has its own life cycle; properly following a course of action and avoiding missteps can be vital to the overall success not only of a paper but of the underlying research as well. Here, we offer ten simple rules for writing and publishing research papers.
As a caveat, this essay is not about the mechanics of composing a paper, much of which has been covered elsewhere, e.g., , . Rather, it is about the principles and attitude that can help guide the process of writing in particular and research in general. In this regard, some of the discussion will complement, extend, and refine some advice given in early articles of this Ten Simple Rules series of PLOS Computational Biology –.
A new R package, netClass, has been release. netClass integrate network information, such as protein-protein interaction network or KEGG, to mRNA classification, but also incorporate miRNA to mRNA with mi-mRNA interaction network for biomarker discovery. This methods we called stSVM and already published in PloS ONE (Cun et al 2013). Apart from stSVM, we also implement the flowing methods in netClass:
- AEP (average gene expression of pathway), Guo et al., BMC Bioinformatics 2005, 6:58.
- PAC (pathway activitive classification), Lee E, et al., PLoS Comput Biol 4(11): e1000217.
- hubc (Hub nodes classification), Taylor et al.(2009) Nat. Biotech.: doi: 10.1038/nbt.152
- frSVM (filter via top ranked genes), Cun et al. arXiv:1212.3214 ; Winter etal., PLoS Comput Biol 8(5): e1002511.
- stSVM (network smoothed t-statistic) , Cun et al., PloS One,.
NetClass can be download from souceforg ( http://sourceforge.net/projects/netclassr/) or , CRAN (http://cran.r-project.org/web/packages/netClass/ ). For more detail of netClass, you can refer these four papers:
- Yupeng Cun, Holger Fröhlich (2014) netClass: An R-package for network based, integrative biomarker signature discovery. Bioinformatics; doi: 10.1093/bioinformatics/btu025
- Yupeng Cun, Holger Fröhlich (2013) Network and Data Integration for Biomarker Signature Discovery via Network Smoothed T-Statistics, PLoS ONE 8(9): e73074. doi:10.1371/journal.pone.0073074.
- Yupeng Cun, Holger Fröhlich (2012) Integrating Prior Knowledge Into Prognostic Biomarker Discovery Based on Network Structure. arXiv:1212.3214 ( Link for R codes and Supplemental meterials)
- Yupeng Cun, Holger Fröhlich (2012) Prognostic Gene Signatures for Patient Stratification in Breast Cancer – Accuracy, Stability and Interpretability of Gene Selection Approaches Using Prior Knowledge on Protein-Protein Interactions. BMC Bioinformatics, 13:69
A review collection in current approach in Translational Bioinformatics.
‘Translational Bioinformatics’ is a collection of PLOS Computational Biology Education articles which reads as a “book” to be used as a reference or tutorial for a graduate level introductory course on the science of translational bioinformatics.
Translational bioinformatics is an emerging field that addresses the current challenges of integrating increasingly voluminous amounts of molecular and clinical data. Its aim is to provide a better understanding of the molecular basis of disease, which in turn will inform clinical practice and ultimately improve human health.
The concept of a translational bioinformatics introductory book was originally conceived in 2009 by Jake Chen and Maricel Kann. Each chapter was crafted by leading experts who provide a solid introduction to the topics covered, complete with training exercises and answers. The rapid evolution of this field is expected to lead to updates and new chapters that will be incorporated into this collection.
Collection editors: Maricel Kann, Guest Editor, and Fran Lewitter, PLOS Computational Biology Education Editor.
Download the full Translational Bioinformatics collection here: PDF
Collection URL: www.ploscollections.org/translationalbioinformatics
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002796
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002826
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002816
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002805
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002819
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002820
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002821
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002817
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002858
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002827
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002828
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002822
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002808
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002823
PLOS Computational Biology: published 27 Dec 2012 | info:doi/10.1371/journal.pcbi.1002824
In our recent publication in BMC bioinformatics, we acompared a great deal of feature selection methods to finding prognostic biomakers in 6 breast cancer gene expresion data. No methods show significant performacne in prediction accuracy, feature selection stability and biogical interprety, which against previeous reseach results: current network-based appraoch did not show much benift in our analysis. Meanwhile, A group from NKI also show the simliar results in PloS One. The R codes for these algorithms in our paper is availiable as request.
Welcome back! The last post discussed rules 1-3: the importance to do a postdoc, a concise CV and a unique research statement. Like the last post this one is inspired by a Career Development Workshop at ISMB 2012 that I contributed to (download the slides).
There is still one thing missing from a standard application pack:
4. Pretend you care! The teaching statement
Together with CV and research statement some places ask you to submit a teaching statement. So write one. But don’t be fooled, it’s pretty low on the priority list (for the hiring committee, even if maybe not for you). Academic employers want three things from you: money, papers, and … long time nothing … teaching. I’m not saying they won’t ask you to teach for many hours a week, but when it comes to you being evaluated its money and papers (in that order) which…
View original post 951 more words
达堡是我对Dagstuhl Schloss的简称，是位于德国萨尔兰州的一个小城堡，同时也是德国信息学研究领域的Leibniz Center for Informatics所在地。达堡研讨会（Dagstuhl Seminars）的是信息学领域的顶级研讨会之一，他以Oberwolfach数学研究中心为楷模，努力营造一个为学者提供及交流，启迪智慧的平台。达堡会议的宗旨：
Schloss Dagstuhl – Leibniz Center for Informatics (German: Schloss Dagstuhl – Leibniz-Zentrum für Informatik GmbH) is the world’s premier venue for informatics. World-class scientists, promising young researchers and practioners come together to exchange their knowledge and to discuss their research findings.
在这个日新月异的狂飙运动时代，有时能停下来，去乡间和同行去乡间聊点科学，出点汗，总比打折飞的在各种会场和酒桌上只争朝夕，觥筹交错好一点吧。 希望我们自己也能有Oberwolfach 数学中心，Dagstuhl simenar之类的会，大师和年轻学生, 学者们能做到一起， 分享彼此的发现乐趣。