Search Results for "classification"

...ITI extracts regions in the interactome with differentiating expression over two conditions. These subnetworks can that be used to build a generalizable and stable genomic signature for genomic/cancer classification.

A set of java programs that extract coordinate and chemical information from PDB files. The binding site regions are extracted using grid based scheme. For binding site, spatio-chemical descriptor is generated based on PocketMatch algorithm of Dr. Kalidas (author of this project too).

Kinannote identifies and classifies protein kinases in a user-provided fasta file using an HMM derived from serine/threonine protein kinases, a position specific scoring matrix derived from the HMM, and comparison with a local version of the curated kinase database from kinase.com. If the user inputs a complete proteome, additional modules evaluate the completeness of the kinome and place it in context with reference kinomes. Kinannote runs on a unix command line and depends on local hmmer 2...

This advanced machine learning algorithm is a Michigan-style learning classifier system (LCS) developed to specialize in classification, prediction, data mining, and knowledge discovery tasks. Michigan-style LCS algorithms constitute a unique class of algorithms that distribute learned patterns over a collaborative population of of individually interpretable IF:THEN rules, allowing them to flexibly and effectively describe complex and diverse problem spaces.

Java Machine Learning Library is a library of machine learning algorithms and related datasets. Machine learning techniques include: clustering, classification, feature selection, regression, data pre-processing, ensemble learning, voting, ...

ConoSorter is a high-throughput standalone program that implements regular expressions and profile Hidden Markov Models (pHMMs) for large-scale identification and classification of precursor conopeptides into gene superfamilies and classes based on the ER signal, pro-, and mature conopeptide regions generated from raw next-generation transcriptomic or proteomic data. ConoSorter also generates a set of relevant additional information (frequency of protein sequences, length, number of cysteine residues, hydrophobicity rate of N-terminal region) and automatically searches ConoServer database to allow the user to assess the reliability and relevance of the results and to aid the identification of new conopeptide superfamilies and classes.

The package provides SVM models to be used with SVMlight (http://svmlight.joachims.org/) for drawing a consensus out of individual 3rd-party predictions about the effect of mutations. The 3rd party tools are SIFT, Polyphen2, SNPs&GO and Mutation Assessor. The package also provides a series of Perl modules and scripts to assist in the preparation of data. The modules can be used to build custom tools and pipelines, whereas the scripts provide basic executable implementations based on the...

...These primers generate a fingerprint-pyrogram which is constituted by the sum of all individual pyrograms originating from each primer used. MultiPSQ allows the analysis and classification of multiplex-pyrograms originating from various pyrosequencing primers.

This is a c-library that provides tools for advanced analysis of electrophysiological data. It features denoising, unsupervised classification, time-frequency analysis, phase-space analysis, neural networks, time-warping and more.

RepMiner takes a graph theory approach to the classification and assembly of the repetitive fraction of genomic sequence data. Sequence lengths analyzed by RepMiner can range from full length transposable elements to low coverage sample sequence data.

An R package implementation of a consensus clustering methodology. This package allows users to perform re-sampling statistics based clustering using multiple clustering algorithms to assess the robustness of both clusters and members of clusters.

Quantitative Evalution of Blush: a program to assess myocardial reperfusion on coronary angiograms. This program calculates a value that can be used for risk classification of STEMI patients or as a surrogate endpoint in clinical trials.

Thea, Tools for High-throughput Experiment Analysis, is an integrated information processing system dedicated to the annotation of data issued from classification systems with biological information coming from a knowledge base.