|
|
Axel Bernal
4th-year PhD Student
Department of Computer and Information
Science
University of Pennsylvania
Email: abernal at seas dot upenn dot edu
My advisor is professor Fernando Pereira
What's new? The source code for ecraig v1.1 has been released. See the software section for more details
I work on applications of machine learning to computational biology, in
particular biological sequence analysis. I have been working on the last few
years on a higher-accuracy genefinder called CRAIG (for Conditional Random
field-based Ab Initio Genefinder). See CRAIG's webpage
for more details. I have also been working on eCRAIG, a CRF framework for integrating multiple sources of evidence for gene prediction which performs considerably better than any other current automated tool for gene prediction. You can download eCRAIG's source code and parameters for A. thaliana, C. elegans and H. sapiens here. You can also download the train and test datasets used for the aforementioned organisms here.
Currently I am working on using RNA-Seq data to predict alternative splicing as an extension to CRAIG, and also gmeCRAIG, a genomic-scale secretome predictor.
Thesis Proposal: Linear Structure Models for Gene Prediction
Axel E. Bernal
thesis proposal. 2011
Discriminative
Models for Comparative Gene Prediction
Axel E. Bernal
WPE-II paper. 2008
Global
Discriminative Training for Higher-Accuracy Computational Gene Prediction
Bernal A, Crammer K, Hatzigeorgiou A, Pereira F.
PLoS Comput Biol 3(3):e54. 2007
Crick's Hypothesis Revisited: The Existence of a Universal Coding Frame
Jean-Louis Lassez and Ryan A. Rossi, Axel E. Bernal
Advanced Information Networking and Applications Workshops, International Conference on (1):745-751. 2007
Similarity Based Classification
Axel E. Bernal, Karen Hospevian, Tayfun Karadeniz, Jean-Louis Lassez.
IDA 2003: 187-197
Draft Sequencing and Comparative Genomics of Xylella fastidiosa Strains Reveal Novel Biological Insights.
Bhattacharyya A, Stilwagen S, Reznik G, Feil H, Feil WS, Anderson I, Bernal A, D'Souza M, Ivanova N, Kapatral V, Larsen N, Los T, Lykidis A, Selkov E Jr, Walunas TL, Purcell A, Edwards RA, Hawkins T, Haselkorn R, Overbeek R, Kyrpides NC, Predki PF.
Genome Res 2002 Oct; 12(10): 1556-63
Whole-genome comparative analysis of three phytopathogenic Xylella fastidiosa strains
Bhattacharyya A, Stilwagen S, Ivanova N, D'Souza M, Bernal A, Lykidis A, Kapatral V, Anderson I, Larsen N, Los T, Reznik G, Selkov E Jr, Walunas TL, Feil H, Feil WS, Purcell A, Lassez JL, Hawkins TL, Haselkorn R, Overbeek R, Predki PF, Kyrpides NC.
Proc Natl Acad Sci USA 2002 Sep; 99(19): 12403-8
From genetic footprinting to antimicrobial drug targets: examples in cofactor biosynthetic pathways
Gerdes SY, Scholle MD, D'Souza M, Bernal A, Baev MV, Farrell M, Kurnasov OV, Daugherty MD, Mseeh F, Polanuyer BM, Campbell JW, Anantha S, Shatalin KY, Chowdhury SA, Fonstein MY, Osterman AL.
J Bacteriol. 2002 Aug; 184(16): 4555-72
Genome Sequence and Analysis of the Oral Bacterium Fusobacterium nucleatum Strain ATCC 25586
Kapatral V, Anderson I, Ivanova N, Reznik G, Los T, Lykidis A, Bhattacharyya A, Bartman A, Gardner W, Grechkin G, Zhu L, Vasieva O, Chu L, Kogan Y, Chaga O, Goltsman E, Bernal A, Larsen N, D'Souza M, Walunas T, Pusch G, Haselkorn R, Fonstein M, Kyrpides N, Overbeek R.
J Bacteriol 2002 Apr; 184(7): 2005-18
The genome sequence of the facultative intracellular pathogen Brucella melitensis
Vito G. DelVecchio, Vinayak Kapatral, Rajendra J. Redkar, Guy Patra, Cesar Mujer, Tamara Los, Natalia Ivanova, Iain Anderson, Anamitra Bhattacharyya, Athanasios Lykidis, Gary Reznik, Lynn Jablonski, Niels Larsen, Mark D'Souza, Axel Bernal, Mikhail Mazur, Eugene Goltsman, Eugene Selkov, Philip H. Elzer, Sue Hagius, David O'Callaghan, Jean-Jacques Letesson, Robert Haselkorn, Nikos Kyrpides, and Ross Overbeek.
Proc. Natl. Acad. Sci. USA, 2002 Jan 8; Vol. 99, Issue 1, 443-8
Genomes OnLine Database (GOLD): a monitor of genome projects world-wide
Bernal A, Ear U, Kyrpides N.
Nucleic Acids Res 2001 Jan 1; 29(1): 126-7
You can download the source code and x86_64 binaries for the latest release of craig and lless, a general library for training and testing linear structure models for sequences (pronounced "l-less"). Provided along with the full source code is also CRAIG's human model parameters. Both components are released under GPL v2.0.
You can also download the source code for eCRAIG (short for ensemble CRAIG), along with a more recent version of lless and gene model parameters for A. thaliana, C. elegans and H. sapiens.
|