Nuclear architecture dictates HIV-1 integration site selection
- B. Marini, Attila Kertész-Farkas, M. Lusic
- 2 March 2015
It is shown that HIV-1 integration occurs in the outer shell of the nucleus in close correspondence with the nuclear pore, indicating that nuclear topography is an essential determinant of the HIV- 1 life cycle.
A Protein Classification Benchmark collection for machine learning
- P. Sonego, Mircea Pacurar, S. Pongor
- Computer ScienceNucleic Acids Res.
- 16 November 2006
The Protein Classification Benchmark collection was created in order to provide standard datasets on which the performance of machine learning methods can be compared, and is primarily meant for method developers and users interested in comparing methods under standardized conditions.
Crux: Rapid Open Source Protein Tandem Mass Spectrometry Analysis
- S. McIlwain, Kaipo Tamura, William Stafford Noble
- Chemistry, Computer ScienceJournal of Proteome Research
- 3 September 2014
The Crux mass spectrometry analysis software toolkit is an open source project that aims to provide users with a cross-platform suite of analysis tools for interpreting protein mass Spectrometry data.
Toward an automatic method for extracting cancer- and other disease-related point mutations from the biomedical literature
- E. Doughty, Attila Kertész-Farkas, M. Kann
- Biology, Computer ScienceBioinform.
- 1 February 2011
This work introduces a high-throughput computational method for the identification of relevant disease mutations in PubMed abstracts applied to prostate (PCa) and breast cancer (BCa) mutations by significantly increasing the number of annotated mutations.
HuGaDB: Human Gait Database for Activity Recognition from Wearable Inertial Sensor Networks
- Roman Chereshnev, Attila Kertész-Farkas
- Computer ScienceInternational Joint Conference on the Analysis of…
- 10 May 2017
This dataset is the first of its kind which provides data about human gait in great detail and can be used to perform health-care-related studies, in virtual reality and gaming for simulating humanoid motion, or for humanoid robotics to model humanoid walking.
Author Correction: Test-time augmentation for deep learning-based cell segmentation on microscopy images
- Nikita Moshkov, Botond Mathe, Attila Kertész-Farkas, R. Hollandi, P. Horváth
- Computer ScienceScientific Reports
- 23 October 2019
This paper describes how the test-time argumentation prediction method is incorporated into two major segmentation approaches utilized in the single-cell analysis of microscopy images, and shows that even if only simple test- time augmentations are applied, TTA can significantly improve prediction accuracy.
Application of compression-based distance measures to protein sequence classification: a methodological study
- A. Kocsor, Attila Kertész-Farkas, L. Kaján, S. Pongor
- Computer ScienceBioinform.
- 15 February 2006
Compression-based distance measures performed especially well on distantly related proteins where the performance of a combined measure, constructed from a CBM and a BLAST score, approached or even slightly exceeded that of the Smith-Waterman algorithm and two hidden Markov model-based algorithms.
Improved False Discovery Rate Estimation Procedure for Shotgun Proteomics
- U. Keich, Attila Kertész-Farkas, William Stafford Noble
- BiologyJournal of Proteome Research
- 8 July 2015
This work evaluates four previously proposed protocols for estimating the false discovery rate (FDR) associated with a set of identified tandem mass spectra and proposes the mix-max procedure, which avoids biases associated with the two separate target-decoy search protocols and also avoids the propensity for target- decoy competition to discard a random subset of high-scoring target identifications.
Application of a simple likelihood ratio approximant to protein sequence classification
- L. Kaján, Attila Kertész-Farkas, Dino Franklin, Neli Ivanova, A. Kocsor, S. Pongor
- Computer ScienceBioinform.
- 10 November 2006
It was found that LRA-based scoring can significantly outperform simple scoring methods and be used as a scoring function in the classification of protein sequences.
Benchmarking protein classification algorithms via supervised cross-validation.
- Attila Kertész-Farkas, Somdutta Dhir, S. Pongor
- Computer ScienceJournal of Biochemical and Biophysical Methods
- 24 April 2008