Chenxi Whitehouse, Clara Vania, Alham Fikri Aji, Christos Christodoulopoulos, Andrea Pierleoni. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Recent work in entity disambiguation (ED) has typically neglected structured knowledge base (KB) facts, and instead relied on a limited subset of KB information, such as entity descriptions or types.This limits the range of contexts in which entities can be disambiguated.To allow the use of all KB facts, as well as descriptions and types, we introduce an ED model which links entities by reasoning over a symbolic knowledge base in a fully differentiable fashion.Our model surpasses state-of-the-art baselines on six well-established ED datasets by 1.3 F1 on average.By allowing access to all KB information, our model is less reliant on popularity-based entity priors, and improves performance on the challenging ShadowLink dataset (which emphasises infrequent and ambiguous entities) by 12.7 F1.

MOTIVATION: Subcellular localization is a key feature in the process of functional annotation of both globular and membrane proteins. In the absence of experimental data, protein localization is inferred on the basis of annotation transfer upon sequence similarity search. However, predictive tools are necessary when the localization of homologs is not known. This is so particularly for membrane proteins. Furthermore, most of the available predictors of subcellular localization are specifically trained on globular proteins and poorly perform on membrane proteins. RESULTS: Here we develop MemLoci, a new support vector machine-based tool that discriminates three membrane protein localizations: plasma, internal and organelle membrane. When tested on an independent set, MemLoci outperforms existing methods, reaching an overall accuracy of 70% on predicting the location in the three membrane types, with a generalized correlation coefficient as high as 0.50. AVAILABILITY: The MemLoci server is freely available on the web at: http://mu2py.biocomp.unibo.it/memloci. Datasets described in the article can be downloaded at the same site.

MOTIVATION: Disulfide bonds stabilize protein structures and play relevant roles in their functions. Their formation requires an oxidizing environment and their stability is consequently depending on the redox ambient potential, which may differ according to the subcellular compartment. Several methods are available to predict cysteine-bonding state and connectivity patterns. However, none of them takes into consideration the relevance of protein subcellular localization. RESULTS: Here we develop DISLOCATE, a two-step method based on machine learning models for predicting both the bonding state and the connectivity patterns of cysteine residues in a protein chain. We find that the inclusion of protein subcellular localization improves the performance of these predictive steps by 3 and 2 percentage points, respectively. When compared with previously developed methods for predicting disulfide bonds from sequence, DISLOCATE improves the overall performance by more than 10 percentage points. AVAILABILITY: The method and the dataset are available at the Web page http://www.biocomp.unibo.it/savojard/Dislocate.html. GRHCRF code is available at http://www.biocomp.unibo.it/savojard/biocrf.html. CONTACT: [email protected].

BACKGROUND: Several eukaryotic proteins associated to the extracellular leaflet of the plasma membrane carry a Glycosylphosphatidylinositol (GPI) anchor, which is linked to the C-terminal residue after a proteolytic cleavage occurring at the so called omega-site. Computational methods were developed to discriminate proteins that undergo this post-translational modification starting from their aminoacidic sequences. However more accurate methods are needed for a reliable annotation of whole proteomes. RESULTS: Here we present PredGPI, a prediction method that, by coupling a Hidden Markov Model (HMM) and a Support Vector Machine (SVM), is able to efficiently predict both the presence of the GPI-anchor and the position of the omega-site. PredGPI is trained on a non-redundant dataset of experimentally characterized GPI-anchored proteins whose annotation was carefully checked in the literature. CONCLUSION: PredGPI outperforms all the other previously described methods and is able to correctly replicate the results of previously published high-throughput experiments. PredGPI reaches a lower rate of false positive predictions with respect to other available methods and it is therefore a costless, rapid and accurate method for screening whole proteomes.