BNFO 602: Foundations of bioinformatics II
Spring 2016

Instructor:
Usman Roshan, GITC 3802
Ph: 973-596-2872
Office hours: Tue and Thu 2:30 to 5 and by appointment
Email: usman@cs.njit.edu

Course overview: We will cover genome-wide association studies, phylogenetics, basic sequence alignment, short read mapping, and machine learning algorithms.

Grading:

• Several short quizzes spread through the semester and completed before presentation of course projects. Quizzes are worth 50% and project 50%.
• Course project: This will be a programming/research project. The project can be an implementation of a newly published algorithm or experimental study of new and existing software. You are free to select on your own or from this list. Select a project by February 23rd and make sure to have it approved by your professor.

Recommended texts:

• Introduction to Bioinformatics Algorithms by Neil C. Jones and Pavel A. Pevzner
• Introduction to Bioinformatics by Arthur Lesk
• Biological Sequence Analysis by Durbin et. al.
• Algorithms on strings, trees, and sequences: computer science and computational biology by Dan Gusfield
• Introduction to Machine Learning by Ethem Alpaydin

Bioinformatics journals:

• Bioinformatics (Oxford press)
• BMC Bioinformatics (Biomed central; open access)
• PLoS Computational Biology (ISCB official journal; open access)
• More journals here

Bioinformatics conferences:

• Intelligent Systems for Molecular Biology (ISMB)
• Research in Computational Biology (RECOMB)
• Computational Systems Bioinformatics (CSB)
• Workshop on Algorithms in Bioinformatics (WABI)
• International Conference on Bioinformatics and Bioengineering (BIBE)

Course plan:
   

Topic	Date	Lectures
Introduction and GWAS	01/19/16	Basic bio background Projects Programming and system Perl Basic Unix command sheet Instructions for AFS login GWAS
Phylogenetics and quiz 1	01/26/16	Phylogenetics I Phylogenetics II Phylogenetics (ML)
Sequence alignment	02/02/16	Pairwise sequence alignment Multiple sequence alignment
Basic classification	02/09/15	Linear algebra and probability background Bayesian learning Model trees for students with projects in phylogenetics African Eve tree from Maddison et. al. Systematic Zoology, 41:111-124, 1992 Chloroplast rbcL gene tree from Rice et. al., Systematic Biology, 1997
Quiz 2	02/16/16	Logistic regression Balanced error Software Logistic regression program Logistic regression source code (uses GNU Scientific Library) How to run the logistic regression program Predict labels with logistic regression Projects
Logistic regression	02/23/16	Data Training (labels) Validation (labels)
Support vector machines	03/01/16	Hyperplanes as linear classifiers Support vector machines Perl script for balanced error SVM light software (SVMlight code) Perl script to obtain top k SNPs Perl script to convert to SVM light format Risk prediction results
Feature selection	03/08/16	Feature selection A comparison of univariate and multivariate gene selection techniques for classification of cancer datasets Feature selection with SVMs and F-score Ranking genomic causal variants with chi-square and SVM
Perceptrons, neural networks, and regularized risk minimization	03/22/16	Perceptrons and neural networks perceptron.pl Regularized risk minimization bmrm.pl BMRM training config file BMRM test config file
Class cancelled	03/29/16
Quiz3 and tree-based methods for classification	04/05/16	Decision trees, bagging, and boosting Gradient boosting tutorial by Tianqi Chen (XGBoost author)
Quiz 4 and dimensionality reduction and clustering	04/12/16	Dimensionality reduction Dimensionality reduction II Clustering
Quiz 5 and kernel methods for non-linear classification	04/19/16	Kernels Kernel nearest means
Student projects	04/26/16
Final due date for projects	05/10/16