MOTIVATION: Accurate prediction of protein function is essential for elucidating molecular mechanisms and advancing biological and therapeutic discovery. Yet experimental annotation lags far behind the rapid growth of protein sequence data. Computational approaches address this gap by associating proteins with Gene Ontology (GO) terms, which encode functional knowledge through hierarchical relations and textual definitions. However, existing models often emphasize one modality over the other, limiting their ability to generalize, particularly to unseen or newly introduced GO terms that frequently arise as the ontology evolves, and making the previously trained models outdated. RESULTS: We present STAR-GO, a Transformer-based framework that jointly models the semantic and structural characteristics of GO terms to enhance zero-shot protein function prediction. STAR-GO integrates textual definitions with ontology graph structure to learn unified GO representations, which are processed in hierarchical order to propagate information from general to specific terms. These representations are then aligned with protein sequence embeddings to capture sequence-function relationships. STAR-GO achieves state-of-the-art performance and superior zero-shot generalization, demonstrating the utility of integrating semantics and structure for robust and adaptable protein function prediction. AVAILABILITY: Code and pre-trained models are available at https://github.com/boun-tabi-lifelu/stargo, https://doi.org/10.5281/zenodo.18643082.

BACKGROUND: When genes are translated into proteins, mutations in the gene sequence can lead to changes in protein structure and function as well as in the interactions between proteins. These changes can disrupt cell function and contribute to the development of tumors. In this study, we introduce a novel approach based on graph neural networks that jointly considers genetic mutations and protein interactions for cancer prediction. We use DNA mutations in whole exome sequencing data and construct a heterogeneous graph in which patients and proteins are represented as nodes and protein-protein interactions as edges. Furthermore, patient nodes are connected to protein nodes based on mutations in the patient's DNA. Each patient node is represented by a feature vector derived from the mutations in specific genes. The feature values are calculated using a weighting scheme inspired by information retrieval, where whole genomes are treated as documents and mutations as words within these documents. The weighting of each gene, determined by its mutations, reflects its contribution to disease development. The patient nodes are updated by both mutations and protein interactions within our noval heterogeneous graph structure. Since the effects of each mutation on disease development are different, we processed the input graph with attention-based graph neural networks. RESULTS: We compiled a dataset from the UKBiobank consisting of patients with a cancer diagnosis as the case group and those without a cancer diagnosis as the control group. We evaluated our approach for the four most common cancer types, which are breast, prostate, lung and colon cancer, and showed that the proposed framework effectively discriminates between case and control groups. CONCLUSIONS: The results indicate that our proposed graph structure and node updating strategy improve cancer classification performance. Additionally, we extended our system with an explainer that identifies a list of causal genes which are effective in the model's cancer diagnosis predictions. Notably, some of these genes have already been studied in cancer research, demonstrating the system's ability to recognize causal genes for the selected cancer types and make predictions based on them.

Tokenization is a crucial step in processing protein sequences for machine learning models, as proteins are complex sequences of amino acids that require meaningful segmentation to capture their functional and structural properties. However, existing subword tokenization methods, developed primarily for human language, may be inadequate for protein sequences, which have unique patterns and constraints. This study evaluates three prominent tokenization approaches, Byte-Pair Encoding (BPE), WordPiece, and SentencePiece, across varying vocabulary sizes (400–6400), analyzing their effectiveness in protein sequence representation, domain boundary preservation, and adherence to established linguistic laws. Our comprehensive analysis reveals distinct behavioral patterns among these tokenizers, with vocabulary size significantly influencing their performance. BPE demonstrates better contextual specialization and marginally better domain boundary preservation at smaller vocabularies, while SentencePiece achieves better encoding efficiency, leading to lower fertility scores. WordPiece offers a balanced compromise between these characteristics. However, all tokenizers show limitations in maintaining protein domain integrity, particularly as vocabulary size increases. Analysis of linguistic law adherence shows partial compliance with Zipf’s and Brevity laws but notable deviations from Menzerath’s law, suggesting that protein sequences may follow distinct organizational principles from natural languages. These findings highlight the limitations of applying traditional NLP tokenization methods to protein sequences and emphasize the need for developing specialized tokenization strategies that better account for the unique characteristics of proteins. Our work contributes to the ongoing dialogue between bioinformatics and natural language processing, offering insights for future development of protein-specific tokenization approaches.

Pretrained language models and large language models are increasingly used to assist in a great variety of natural language tasks. In this work, we explore their use in evaluating the quality of alternative corpus annotation schemes. For this purpose, we analyze two alternative annotations of the Turkish BOUN treebank, versions 2.8 and 2.11, in the Universal Dependencies framework using large language models. Using a suitable prompt generated using treebank annotations, large language models are used to recover the surface forms of sentences. Based on the idea that the large language models capture the characteristics of the languages, we expect that the better annotation scheme would yield the sentences with higher success. The experiments conducted on a subset of the treebank show that the new annotation scheme (2.11) results in a successful recovery percentage of about 2 points higher. All the code developed for this work is available at https://github.com/boun-tabi/eval-ud .

This paper focuses on dealing with data scarcity in spoken question answering (QA) using automatic question-answer generation and a carefully selected fine-tuning strategy that leverages limited annotated data (paragraphs and question-answer pairs). Spoken QA is a challenging task due to using spoken documents, i.e., erroneous automatic speech recognition (ASR) transcriptions, and the scarcity of spoken QA data. We propose a framework for utilizing limited annotated data effectively to improve spoken QA performance. To deal with data scarcity, we train a question-answer generation model with annotated data and then produce large amounts of question-answer pairs from unannotated data (paragraphs). Our experiments demonstrate that incorporating limited annotated data and the automatically generated data through a carefully selected fine-tuning strategy leads to 5.5% relative F1 gain over the model trained only with annotated data. Moreover, the proposed framework is also effective in high ASR errors.

MOTIVATION: Technical errors in sequencing or bioinformatics steps and difficulties in alignment at some genomic sites result in false positive (FP) variants. Filtering based on quality metrics is a common method for detecting FP variants, but setting thresholds to reduce FP rates may reduce the number of true positive variants by overlooking the more complex relationships between features. The goal of this study is to develop a machine learning-based model for identifying FPs that integrates quality metrics with genomic features and with the feature interpretability property to provide insights into model results. RESULTS: We propose a random forest-based model that utilizes genomic features to improve identification of FPs. Further examination of the features shows that the newly introduced features have an important impact on the prediction of variants misclassified by VEF, GATK-CNN, and GARFIELD, recently introduced FP detection systems. We applied cost-sensitive training to avoid errors in misclassification of true variants and developed a model that provides a robust mechanism against misclassification of true variants while increasing the prediction rate of FP variants. This model can be easily re-trained when factors such as experimental protocols might alter the FP distribution. In addition, it has an interpretability mechanism that allows users to understand the impact of features on the model's predictions. AVAILABILITY AND IMPLEMENTATION: The software implementation can be found at https://github.com/ideateknoloji/FPDetect.

Many software systems, such as online social networks, enable users to share information about themselves. Although the action of sharing is simple, it requires an elaborate thought process on privacy: what to share, with whom to share, and for what purposes. Thinking about these for each piece of content to be shared is tedious. Recent approaches to tackle this problem build personal assistants that can help users by learning what is private over time and recommending privacy labels such as private or public to individual content that a user considers sharing. However, privacy is inherently ambiguous and highly personal . Existing approaches to recommend privacy decisions do not address these aspects of privacy sufficiently. Ideally, a personal assistant should be able to adjust its recommendation based on a given user, considering that user’s privacy understanding. Moreover, the personal assistant should be able to assess when its recommendation would be uncertain and let the user make the decision on her own. Accordingly, this article proposes a personal assistant that uses evidential deep learning to classify content based on its privacy label. An important characteristic of the personal assistant is that it can model its uncertainty in its decisions explicitly, determine that it does not know the answer, and delegate from making a recommendation when its uncertainty is high. By factoring in the user’s own understanding of privacy, such as risk factors or own labels, the personal assistant can personalize its recommendations per user. We evaluate our proposed personal assistant using a well-known dataset. Our results show that our personal assistant can accurately identify uncertain cases, personalize them to its user’s needs, and thus helps users preserve their privacy well.

Machine learning-based text classification models require labeled data for training. However, manual labeling is a costly and time-consuming process. This task is particularly difficult in domains such as banking, where outsourcing data labeling is generally not allowed due to privacy laws. We propose a novel active learning-based approach in which the most difficult instances in the pool of unlabeled data are selected based on the Shapley Additive Explanations (SHAP) values of the words in the texts to be classified and passed to human annotators for labeling. At each iteration of this human-in-the-loop strategy, newly labeled instances are added to the training set. We demonstrate the effectiveness of this approach in classifying customer comments in the banking domain surveys. Our experiments indicate that better results are achieved when the proposed approach is used to expand the training set, compared to a baseline strategy of expanding the training set with randomly selected instances. Further analysis shows that the difference in performance between the two approaches becomes more pronounced as class imbalance increases. This study suggests that human-in-the-loop based active learning is a powerful strategy for creating high-quality training datasets by effectively leveraging human annotation effort.

MOTIVATION: The development of novel compounds targeting proteins of interest is one of the most important tasks in the pharmaceutical industry. Deep generative models have been applied to targeted molecular design and have shown promising results. Recently, target-specific molecule generation has been viewed as a translation between the protein language and the chemical language. However, such a model is limited by the availability of interacting protein-ligand pairs. On the other hand, large amounts of unlabelled protein sequences and chemical compounds are available and have been used to train language models that learn useful representations. In this study, we propose exploiting pretrained biochemical language models to initialize (i.e. warm start) targeted molecule generation models. We investigate two warm start strategies: (i) a one-stage strategy where the initialized model is trained on targeted molecule generation and (ii) a two-stage strategy containing a pre-finetuning on molecular generation followed by target-specific training. We also compare two decoding strategies to generate compounds: beam search and sampling. RESULTS: The results show that the warm-started models perform better than a baseline model trained from scratch. The two proposed warm-start strategies achieve similar results to each other with respect to widely used metrics from benchmarks. However, docking evaluation of the generated compounds for a number of novel proteins suggests that the one-stage strategy generalizes better than the two-stage strategy. Additionally, we observe that beam search outperforms sampling in both docking evaluation and benchmark metrics for assessing compound quality. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/boun-tabi/biochemical-lms-for-drug-design and the materials (i.e., data, models, and outputs) are archived in Zenodo at https://doi.org/10.5281/zenodo.6832145. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Abstract An entity mention in text such as “Washington” may correspond to many different named entities such as the city “Washington D.C.” or the newspaper “Washington Post.” The goal of named entity disambiguation (NED) is to identify the mentioned named entity correctly among all possible candidates. If the type (e.g., location or person) of a mentioned entity can be correctly predicted from the context, it may increase the chance of selecting the right candidate by assigning low probability to the unlikely ones. This paper proposes cluster-based mention typing for NED. The aim of mention typing is to predict the type of a given mention based on its context. Generally, manually curated type taxonomies such as Wikipedia categories are used. We introduce cluster-based mention typing, where named entities are clustered based on their contextual similarities and the cluster ids are assigned as types. The hyperlinked mentions and their context in Wikipedia are used in order to obtain these cluster-based types. Then, mention typing models are trained on these mentions, which have been labeled with their cluster-based types through distant supervision. At the NED phase, first the cluster-based types of a given mention are predicted and then, these types are used as features in a ranking model to select the best entity among the candidates. We represent entities at multiple contextual levels and obtain different clusterings (and thus typing models) based on each level. As each clustering breaks the entity space differently, mention typing based on each clustering discriminates the mention differently. When predictions from all typing models are used together, our system achieves better or comparable results based on randomization tests with respect to the state-of-the-art levels on four defacto test sets.

Multi-label text classification is a challenging task because it requires capturing label dependencies.It becomes even more challenging when class distribution is long-tailed.Resampling and re-weighting are common approaches used for addressing the class imbalance problem, however, they are not effective when there is label dependency besides class imbalance because they result in oversampling of common labels.Here, we introduce the application of balancing loss functions for multilabel text classification.We perform experiments on a general domain dataset with 90 labels (Reuters-21578) and a domain-specific dataset from PubMed with 18211 labels.We find that a distribution-balanced loss function, which inherently addresses both the class imbalance and label linkage problems, outperforms commonly used loss functions.Distribution balancing methods have been successfully used in the image recognition field.Here, we show their effectiveness in natural language processing.

BACKGROUND: Although there is an enormous number of textual resources in the biomedical domain, currently, manually curated resources cover only a small part of the existing knowledge. The vast majority of these information is in unstructured form which contain nonstandard naming conventions. The task of named entity recognition, which is the identification of entity names from text, is not adequate without a standardization step. Linking each identified entity mention in text to an ontology/dictionary concept is an essential task to make sense of the identified entities. This paper presents an unsupervised approach for the linking of named entities to concepts in an ontology/dictionary. We propose an approach for the normalization of biomedical entities through an ontology/dictionary by using word embeddings to represent semantic spaces, and a syntactic parser to give higher weight to the most informative word in the named entity mentions. RESULTS: We applied the proposed method to two different normalization tasks: the normalization of bacteria biotope entities through the Onto-Biotope ontology and the normalization of adverse drug reaction entities through the Medical Dictionary for Regulatory Activities (MedDRA). The proposed method achieved a precision score of 65.9%, which is 2.9 percentage points above the state-of-the-art result on the BioNLP Shared Task 2016 Bacteria Biotope test data and a macro-averaged precision score of 68.7% on the Text Analysis Conference 2017 Adverse Drug Reaction test data. CONCLUSIONS: The core contribution of this paper is a syntax-based way of combining the individual word vectors to form vectors for the named entity mentions and ontology concepts, which can then be used to measure the similarity between them. The proposed approach is unsupervised and does not require labeled data, making it easily applicable to different domains.

BACKGROUND: As DNA sequencing technologies are improving and getting cheaper, genomic data can be utilized for diagnosis of many diseases such as cancer. Human raw genome data is huge in size for computational systems. Therefore, there is a need for a compact and accurate representation of the valuable information in DNA. The occurrence of complex genetic disorders often results from multiple gene mutations. The effect of each mutation is not equal for the development of a disease. Inspired from the field of information retrieval, we propose using the term frequency (tf) and BM25 term weighting measures with the inverse document frequency (idf) and relevance frequency (rf) measures to weight genes based on their mutations. The underlying assumption is that the more mutations a gene has in patients with a certain disease and the less mutations it has in other patients, the more discriminative that gene is. RESULTS: We evaluated the proposed representations on the task of cancer type classification. We applied various machine learning techniques using the tf-idf and tf-rf schemes and their BM25 versions. Our results show that the BM25-tf-rf representation leads to improved classification accuracy and f-score values compared to the other representations. The highest accuracy (76.44%) and f-score (76.95%) are achieved with the BM25-tf-rf based data representation. CONCLUSIONS: As a result of our experiments, the BM25-tf-rf scheme and the proposed neural network model is shown to be the best performing classification system for our case study of cancer type classification. This system is further utilized for causal gene analysis. Examples from the most effective genes that are used for decision making are found to be in the literature as target or causal genes.

BACKGROUND: Use of medication can cause adverse drug reactions (ADRs), unwanted or unexpected events, which are a major safety concern. Drug labels, or prescribing information or package inserts, describe ADRs. Therefore, systematically identifying ADR information from drug labels is critical in multiple aspects; however, this task is challenging due to the nature of the natural language of drug labels. RESULTS: In this paper, we present a machine learning- and rule-based system for the identification of ADR entity mentions in the text of drug labels and their normalization through the Medical Dictionary for Regulatory Activities (MedDRA) dictionary. The machine learning approach is based on a recently proposed deep learning architecture, which integrates bi-directional Long Short-Term Memory (Bi-LSTM), Convolutional Neural Network (CNN), and Conditional Random Fields (CRF) for entity recognition. The rule-based approach, used for normalizing the identified ADR mentions to MedDRA terms, is based on an extension of our in-house text-mining system, SciMiner. We evaluated our system on the Text Analysis Conference (TAC) Adverse Drug Reaction 2017 challenge test data set, consisting of 200 manually curated US FDA drug labels. Our ML-based system achieved 77.0% F1 score on the task of ADR mention recognition and 82.6% micro-averaged F1 score on the task of ADR normalization, while rule-based system achieved 67.4 and 77.6% F1 scores, respectively. CONCLUSION: Our study demonstrates that a system composed of a deep learning architecture for entity recognition and a rule-based model for entity normalization is a promising approach for ADR extraction from drug labels.

Motivation: The effective representation of proteins is a crucial task that directly affects the performance of many bioinformatics problems. Related proteins usually bind to similar ligands. Chemical characteristics of ligands are known to capture the functional and mechanistic properties of proteins suggesting that a ligand-based approach can be utilized in protein representation. In this study, we propose SMILESVec, a Simplified molecular input line entry system (SMILES)-based method to represent ligands and a novel method to compute similarity of proteins by describing them based on their ligands. The proteins are defined utilizing the word-embeddings of the SMILES strings of their ligands. The performance of the proposed protein description method is evaluated in protein clustering task using TransClust and MCL algorithms. Two other protein representation methods that utilize protein sequence, Basic local alignment tool and ProtVec, and two compound fingerprint-based protein representation methods are compared. Results: We showed that ligand-based protein representation, which uses only SMILES strings of the ligands that proteins bind to, performs as well as protein sequence-based representation methods in protein clustering. The results suggest that ligand-based protein description can be an alternative to the traditional sequence or structure-based representation of proteins and this novel approach can be applied to different bioinformatics problems such as prediction of new protein-ligand interactions and protein function annotation. Availability and implementation: https://github.com/hkmztrk/SMILESVecProteinRepresentation. Supplementary information: Supplementary data are available at Bioinformatics online.

Motivation: The identification of novel drug-target (DT) interactions is a substantial part of the drug discovery process. Most of the computational methods that have been proposed to predict DT interactions have focused on binary classification, where the goal is to determine whether a DT pair interacts or not. However, protein-ligand interactions assume a continuum of binding strength values, also called binding affinity and predicting this value still remains a challenge. The increase in the affinity data available in DT knowledge-bases allows the use of advanced learning techniques such as deep learning architectures in the prediction of binding affinities. In this study, we propose a deep-learning based model that uses only sequence information of both targets and drugs to predict DT interaction binding affinities. The few studies that focus on DT binding affinity prediction use either 3D structures of protein-ligand complexes or 2D features of compounds. One novel approach used in this work is the modeling of protein sequences and compound 1D representations with convolutional neural networks (CNNs). Results: The results show that the proposed deep learning based model that uses the 1D representations of targets and drugs is an effective approach for drug target binding affinity prediction. The model in which high-level representations of a drug and a target are constructed via CNNs achieved the best Concordance Index (CI) performance in one of our larger benchmark datasets, outperforming the KronRLS algorithm and SimBoost, a state-of-the-art method for DT binding affinity prediction. Availability and implementation: https://github.com/hkmztrk/DeepDTA. Supplementary information: Supplementary data are available at Bioinformatics online.

Originated as a label to mark specific tweets, hashtags are increasingly used to convey messages that people like to see in the trending hashtags list. Complex noun phrases and even sentences can be turned into a hashtag. Breaking hashtags into their words is a challenging task due to the irregular and compact nature of the language used in Twitter. In this study, we investigate feature‐based machine learning and language model (LM)‐based approaches for hashtag segmentation. Our results show that LM alone is not successful at segmenting nontrivial hashtags. However, when the N‐best LM‐based segmentations are incorporated as features into the feature‐based approach, along with context‐based features proposed in this study, state‐of‐the‐art results in hashtag segmentation are achieved. In addition, we provide an analysis of over two million distinct hashtags, autosegmented by using our best configuration. The analysis reveals that half of all 60 million hashtag occurrences contain multiple words and 80% of sentiment is trapped inside multiword hashtags, justifying the need for hashtag segmentation. Furthermore, we analyze the grammatical structure of hashtags by parsing them and observe that 77% of the hashtags are noun‐based, whereas 11.9% are verb‐based.

MOTIVATION: The amount of information available in textual format is rapidly increasing in the biomedical domain. Therefore, natural language processing (NLP) applications are becoming increasingly important to facilitate the retrieval and analysis of these data. Computing the semantic similarity between sentences is an important component in many NLP tasks including text retrieval and summarization. A number of approaches have been proposed for semantic sentence similarity estimation for generic English. However, our experiments showed that such approaches do not effectively cover biomedical knowledge and produce poor results for biomedical text. METHODS: We propose several approaches for sentence-level semantic similarity computation in the biomedical domain, including string similarity measures and measures based on the distributed vector representations of sentences learned in an unsupervised manner from a large biomedical corpus. In addition, ontology-based approaches are presented that utilize general and domain-specific ontologies. Finally, a supervised regression based model is developed that effectively combines the different similarity computation metrics. A benchmark data set consisting of 100 sentence pairs from the biomedical literature is manually annotated by five human experts and used for evaluating the proposed methods. RESULTS: The experiments showed that the supervised semantic sentence similarity computation approach obtained the best performance (0.836 correlation with gold standard human annotations) and improved over the state-of-the-art domain-independent systems up to 42.6% in terms of the Pearson correlation metric. AVAILABILITY AND IMPLEMENTATION: A web-based system for biomedical semantic sentence similarity computation, the source code, and the annotated benchmark data set are available at: http://tabilab.cmpe.boun.edu.tr/BIOSSES/ . CONTACT: [email protected] or [email protected].

BACKGROUND: Molecular structures can be represented as strings of special characters using SMILES. Since each molecule is represented as a string, the similarity between compounds can be computed using SMILES-based string similarity functions. Most previous studies on drug-target interaction prediction use 2D-based compound similarity kernels such as SIMCOMP. To the best of our knowledge, using SMILES-based similarity functions, which are computationally more efficient than the 2D-based kernels, has not been investigated for this task before. RESULTS: In this study, we adapt and evaluate various SMILES-based similarity methods for drug-target interaction prediction. In addition, inspired by the vector space model of Information Retrieval we propose cosine similarity based SMILES kernels that make use of the Term Frequency (TF) and Term Frequency-Inverse Document Frequency (TF-IDF) weighting approaches. We also investigate generating composite kernels by combining our best SMILES-based similarity functions with the SIMCOMP kernel. With this study, we provided a comparison of 13 different ligand similarity functions, each of which utilizes the SMILES string of molecule representation. Additionally, TF and TF-IDF based cosine similarity kernels are proposed. CONCLUSION: The more efficient SMILES-based similarity functions performed similarly to the more complex 2D-based SIMCOMP kernel in terms of AUC-ROC scores. The TF-IDF based cosine similarity obtained a better AUC-PR score than the SIMCOMP kernel on the GPCR benchmark data set. The composite kernel of TF-IDF based cosine similarity and SIMCOMP achieved the best AUC-PR scores for all data sets.

MOTIVATION: G protein-coupled receptors (GPCRs) are probably the most attractive drug target membrane proteins, which constitute nearly half of drug targets in the contemporary drug discovery industry. While the majority of drug discovery studies employ existing GPCR and ligand interactions to identify new compounds, there remains a shortage of specific databases with precisely annotated GPCR-ligand associations. RESULTS: We have developed a new database, GLASS, which aims to provide a comprehensive, manually curated resource for experimentally validated GPCR-ligand associations. A new text-mining algorithm was proposed to collect GPCR-ligand interactions from the biomedical literature, which is then crosschecked with five primary pharmacological datasets, to enhance the coverage and accuracy of GPCR-ligand association data identifications. A special architecture has been designed to allow users for making homologous ligand search with flexible bioactivity parameters. The current database contains ∼500 000 unique entries, of which the vast majority stems from ligand associations with rhodopsin- and secretin-like receptors. The GLASS database should find its most useful application in various in silico GPCR screening and functional annotation studies. AVAILABILITY AND IMPLEMENTATION: The website of GLASS database is freely available at http://zhanglab.ccmb.med.umich.edu/GLASS/. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Information regarding bacteria biotopes is important for several research areas including health sciences, microbiology, and food processing and preservation. One of the challenges for scientists in these domains is the huge amount of information buried in the text of electronic resources. Developing methods to automatically extract bacteria habitat relations from the text of these electronic resources is crucial for facilitating research in these areas. METHODS: We introduce a linguistically motivated rule-based approach for recognizing and normalizing names of bacteria habitats in biomedical text by using an ontology. Our approach is based on the shallow syntactic analysis of the text that include sentence segmentation, part-of-speech (POS) tagging, partial parsing, and lemmatization. In addition, we propose two methods for identifying bacteria habitat localization relations. The underlying assumption for the first method is that discourse changes with a new paragraph. Therefore, it operates on a paragraph-basis. The second method performs a more fine-grained analysis of the text and operates on a sentence-basis. We also develop a novel anaphora resolution method for bacteria coreferences and incorporate it with the sentence-based relation extraction approach. RESULTS: We participated in the Bacteria Biotope (BB) Task of the BioNLP Shared Task 2013. Our system (Boun) achieved the second best performance with 68% Slot Error Rate (SER) in Sub-task 1 (Entity Detection and Categorization), and ranked third with an F-score of 27% in Sub-task 2 (Localization Event Extraction). This paper reports the system that is implemented for the shared task, including the novel methods developed and the improvements obtained after the official evaluation. The extensions include the expansion of the OntoBiotope ontology using the training set for Sub-task 1, and the novel sentence-based relation extraction method incorporated with anaphora resolution for Sub-task 2. These extensions resulted in promising results for Sub-task 1 with a SER of 68%, and state-of-the-art performance for Sub-task 2 with an F-score of 53%. CONCLUSIONS: Our results show that a linguistically-oriented approach based on the shallow syntactic analysis of the text is as effective as machine learning approaches for the detection and ontology-based normalization of habitat entities. Furthermore, the newly developed sentence-based relation extraction system with the anaphora resolution module significantly outperforms the paragraph-based one, as well as the other systems that participated in the BB Shared Task 2013.

In this study, we analyzed the effects of ap-plying different levels of stemming approaches such as fixed-length word truncation and mor-phological analysis for multi-document sum-marization (MDS) on Turkish, which is an ag-glutinative and morphologically rich language. We constructed a manually annotated MDS data set, and to our best knowledge, reported the first results on Turkish MDS. Our results show that a simple fixed-length word trun-cation approach performs slightly better than no stemming, whereas applying complex mor-phological analysis does not improve Turkish MDS. 1

The informal nature of social media text renders it very difficult to be automatically processed by natural language processing tools.Text normalization, which corresponds to restoring the non-standard words to their canonical forms, provides a solution to this challenge.We introduce an unsupervised text normalization approach that utilizes not only lexical, but also contextual and grammatical features of social text.The contextual and grammatical features are extracted from a word association graph built by using a large unlabeled social media text corpus.The graph encodes the relative positions of the words with respect to each other, as well as their part-ofspeech tags.The lexical features are obtained by using the longest common subsequence ratio and edit distance measures to encode the surface similarity among words, and the double metaphone algorithm to represent the phonetic similarity.Unlike most of the recent approaches that are based on generating normalization dictionaries, the proposed approach performs normalization by considering the context of the non-standard words in the input text.Our results show that it achieves state-ofthe-art F-score performance on standard datasets.In addition, the system can be tuned to achieve very high precision without sacrificing much from recall.

In this paper, we addressed the Named Entity Recognition (NER) problem for morphologically rich languages by employing a semi-supervised learning approach based on neural networks. We adopted a fast unsupervised method for learning continuous vector representations of words, and used these representations along with language independent features to develop a NER system. We evaluated our system for the highly inflectional Turkish and Czech languages. We improved the state-of-the-art F-score obtained for Turkish without using gazetteers by 2.26% and for Czech by 1.53%. Unlike the previous state-of-the-art systems developed for these languages, our system does not make use of any language dependent features. Therefore, we believe it can easily be applied to other morphologically rich languages.

SUMMARY: Knowledge of pathogen-host protein interactions is required to better understand infection mechanisms. The pathogen-host interaction search tool (PHISTO) is a web-accessible platform that provides relevant information about pathogen-host interactions (PHIs). It enables access to the most up-to-date PHI data for all pathogen types for which experimentally verified protein interactions with human are available. The platform also offers integrated tools for visualization of PHI networks, graph-theoretical analysis of targeted human proteins, BLAST search and text mining for detecting missing experimental methods. PHISTO will facilitate PHI studies that provide potential therapeutic targets for infectious diseases. AVAILABILITY: http://www.phisto.org. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Bio-molecular event extraction from literature is recognized as an important task of bio text mining and, as such, many relevant systems have been developed and made available during the last decade. While such systems provide useful services individually, there is a need for a meta-service to enable comparison and ensemble of such services, offering optimal solutions for various purposes. RESULTS: We have integrated nine event extraction systems in the U-Compare framework, making them intercompatible and interoperable with other U-Compare components. The U-Compare event meta-service provides various meta-level features for comparison and ensemble of multiple event extraction systems. Experimental results show that the performance improvements achieved by the ensemble are significant. CONCLUSIONS: While individual event extraction systems themselves provide useful features for bio text mining, the U-Compare meta-service is expected to improve the accessibility to the individual systems, and to enable meta-level uses over multiple event extraction systems such as comparison and ensemble.

MOTIVATION: Understanding the role of genetics in diseases is one of the most important aims of the biological sciences. The completion of the Human Genome Project has led to a rapid increase in the number of publications in this area. However, the coverage of curated databases that provide information manually extracted from the literature is limited. Another challenge is that determining disease-related genes requires laborious experiments. Therefore, predicting good candidate genes before experimental analysis will save time and effort. We introduce an automatic approach based on text mining and network analysis to predict gene-disease associations. We collected an initial set of known disease-related genes and built an interaction network by automatic literature mining based on dependency parsing and support vector machines. Our hypothesis is that the central genes in this disease-specific network are likely to be related to the disease. We used the degree, eigenvector, betweenness and closeness centrality metrics to rank the genes in the network. RESULTS: The proposed approach can be used to extract known and to infer unknown gene-disease associations. We evaluated the approach for prostate cancer. Eigenvector and degree centrality achieved high accuracy. A total of 95% of the top 20 genes ranked by these methods are confirmed to be related to prostate cancer. On the other hand, betweenness and closeness centrality predicted more genes whose relation to the disease is currently unknown and are candidates for experimental study. AVAILABILITY: A web-based system for browsing the disease-specific gene-interaction networks is available at: http://gin.ncibi.org.