Computational Systems Biology Methods and Protocols.7z

Table 2
The bioinformatic tools based on machine learning strategies

Methods Description URL

mlDNA An R package for machine learning-based differential

network analysis [31]

http://www.cmbb.

arizona.edu/mlDNA/

Co-

clustering

A co-clustering formulation to cluster the genes and the

mesh elements, thereby identifying co-expressed

embryonic domains and the associated genes

simultaneously [32]

http://compbio.cs.odu.

edu/fly/

ml2db The software code (ml2db) uses InterPro signatures to

predict enzyme mechanism [33]

http://sourceforge.net/

projects/ml2db/

BetAware Predict beta-barrels (which are poorly represented in the

database of protein structures and difficult to identify with

experimental approaches) in sets of proteins and the

prediction of their topology [34]

http://betaware.

biocomp.unibo.it/

BetAware

PeakError Supervised labeling method for quantitatively training and

testing peak detection algorithms [35]

https://github.com/

tdhock/PeakError

IDEPI A domain-specific and extensible software library for

supervised learning of models that relate genotype to

phenotype for HIV-1 and other organisms [36]

https://github.com/veg/

idepi

INTREPID As an additional option for cases where sequence

homologues are available, users can include evolutionary

information from INTREPID for enhanced accuracy in

site prediction [37]

http://www.pool.neu.edu

CoRAL A machine learning package that can predict the precursor

class of small RNAs present in a high-throughput RNA-

sequencing dataset [38]

http://wanglab.pcbi.

upenn.edu/coral/

SNooPer A machine learning-based method for somatic variant

identification from low-pass next-generation sequencing

[39]

https://sourceforge.net/

projects/snooper/

FingerID A Matlab/Python package uses the predicted properties for

matching against large molecule databases, such as

PubChem, via machine learning [40]

http://www.sourceforge.

net/p/fingerid

MFlux A web-based platform predicts the bacterial central

metabolism via machine learning, leveraging data from

many papers on heterotrophic bacterial metabolisms [41]

http://mflux.org

apLCMS The new peak detection approach based on the knowledge of

known metabolites, as well as robust machine learning

approaches can learn directly from various data features of

the extracted ion chromatograms to differentiate between

true peak regions from noise regions in the LC/MS profile

[42]

http://web1.sph.emory.

edu/apLCMS/

Taxonomic

assignment

A package is implemented for efficient taxonomic assignment

of metagenomic reads, which can be further improved by

increasing the number of fragments sampled from

reference genome or by increasing thek-mer size [43]

http://cbio.ensmp.fr/

largescalemetagenomics

(continued)

188 Xiang-tian Yu et al.