Antonio Jovanović

1. A. Jovanović, I. Alqassem, N. Chappell, S. Canzar, D. Matijević, Predicting RNA splicing branchpoints, 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO), Opatija, 2022, 383-388
   Abstract

   RNA splicing is a process where introns are removed from pre-mRNA, resulting in mature mRNA. It requires three main signals, a donor splice site (5’ss), an acceptor splice site (3’ss) and a branchpoint (BP). Splice site prediction is a well-studied problem with several reliable prediction tools. However, branchpoint prediction is a harder problem, mainly due to varying nucleotide motifs in the branchpoint area and the existence of multiple branch-points in a single intron. An RNN based approach called LaBranchoR was introduced as the state-of-the-art method for predicting a single BP for each 3’ss. In this work, we explore the fact that previous research reported that 95% of introns have multiple BPs with an estimated average of 5 to 6 BPs per intron. To that end, we extend the existing encoder in the LaBranchoR network with a PointerNetwork decoder. We train our new encoder-decoder model, named RNA PtrNets, on 70-nucleotide-long annotated sequences taken from three publicly available datasets. We evaluate its accuracy and demonstrate how well the predictor can generate multiple branchpoints on the given datasets.

1. T. Prusina, D. Matijević, L. Borozan, J. Maltar, A. Jovanović, Compressing Sentence Representation with maximum Coding Rate Reduction (2023)
   Abstract

   In most natural language inference problems, sentence representation is needed for semantic retrieval tasks. In recent years, pre-trained large language models have been quite effective for computing such representations. These models produce high-dimensional sentence embeddings. An evident performance gap between large and small models exists in practice. Hence, due to space and time hardware limitations, there is a need to attain comparable results when using the smaller model, which is usually a distilled version of the large language model. In this paper, we assess the model distillation of the sentence representation model Sentence-BERT by augmenting the pre-trained distilled model with a projection layer additionally learned on the Maximum Coding Rate Reduction (MCR2)objective, a novel approach developed for general-purpose manifold clustering. We demonstrate that the new language model with reduced complexity and sentence embedding size can achieve comparable results on semantic retrieval benchmarks.

Teaching

Konzultacije (Office Hours): Četvrtak (Thu) 12:00-14:00.  Konzultacije su moguće i po dogovoru.

Nastava

 Zimski semestar ak.god. 21./22.

• Strukture podataka i algoritmi I

 Ljetni semestar ak.god. 21./22.

• Strojno učenje
• Obrada prirodnog jezika tehnikama dubinskog učenja

 Ljetni semestar ak.god. 22./23.

• Strojno učenje
• Obrada prirodnog jezika tehnikama dubinskog učenja
• Nelinearna optimizacija

Personal

• Birthplace: Osijek