TransforMED: End-to-Εnd Transformers for Evidence-Based Medicine and Argument Mining in medical literature.

Argument Mining (AM) refers to the task of automatically identifying arguments in a text and finding their relations. In medical literature this is done by identifying Claims and Premises and classifying their relations as either Support or Attack. Evidence-Based Medicine (EBM) refers to the task of identifying all related evidence in medical literature to allow medical practitioners to make informed choices and form accurate treatment plans. This is achieved through the automatic identification of Population, Intervention, Comparator and Outcome entities (PICO) in the literature to limit the collection to only the most relevant documents. In this work, we combine EBM with AM in medical literature to increase the performance of the individual models and create high quality argument graphs, annotated with PICO entities. To that end, we introduce a state-of-the-art EBM model, used to predict the PICO entities and two novel Argument Identification and Argument Relation classification models that utilize the PICO entities to enhance their performance. Our final system works in a pipeline and is able to identify all PICO entities in a medical publication, the arguments presented in them and their relations.

Integrating multiple immunogenetic data sources for feature extraction and mining somatic hypermutation patterns: the case of "towards analysis" in chronic lymphocytic leukaemia.

BACKGROUND: Somatic Hypermutation (SHM) refers to the introduction of mutations within rearranged V(D)J genes, a process that increases the diversity of Immunoglobulins (IGs). The analysis of SHM has offered critical insight into the physiology and pathology of B cells, leading to strong prognostication markers for clinical outcome in chronic lymphocytic leukaemia (CLL), the most frequent adult B-cell malignancy. In this paper we present a methodology for integrating multiple immunogenetic and clinocobiological data sources in order to extract features and create high quality datasets for SHM analysis in IG receptors of CLL patients. This dataset is used as the basis for a higher level integration procedure, inspired form social choice theory. This is applied in the Towards Analysis, our attempt to investigate the potential ontogenetic transformation of genes belonging to specific stereotyped CLL subsets towards other genes or gene families, through SHM. RESULTS: The data integration process, followed by feature extraction, resulted in the generation of a dataset containing information about mutations occurring through SHM. The Towards analysis performed on the integrated dataset applying voting techniques, revealed the distinct behaviour of subset #201 compared to other subsets, as regards SHM related movements among gene clans, both in allele-conserved and non-conserved gene areas. With respect to movement between genes, a high percentage movement towards pseudo genes was found in all CLL subsets. CONCLUSIONS: This data integration and feature extraction process can set the basis for exploratory analysis or a fully automated computational data mining approach on many as yet unanswered, clinically relevant biological questions.

Immunoglobulin heavy variable (IGHV) genes and alleles: new entities, new names and implications for research and prognostication in chronic lymphocytic leukaemia.

Νext generation sequencing studies in Homo sapiens have identified novel immunoglobulin heavy variable (IGHV) genes and alleles necessitating changes in the international ImMunoGeneTics information system (IMGT) GENE-DB and reference directories of IMGT/V-QUEST. In chronic lymphocytic leukaemia (CLL), the somatic hypermutation (SHM) status of the clonotypic rearranged IGHV gene is strongly associated with patient outcome. Correct determination of this parameter strictly depends on the comparison of the nucleotide sequence of the clonotypic rearranged IGHV gene with that of the closest germline counterpart. Consequently, changes in the reference directories could, in principle, affect the correct interpretation of the IGHV mutational status in CLL. To this end, we analyzed 8066 productive IG heavy chain (IGH) rearrangement sequences from our consortium both before and after the latest update of the IMGT/V-QUEST reference directory. Differences were identified in 405 cases (5 % of the cohort). In 291/405 sequences (71.9 %), changes concerned only the IGHV gene or allele name, whereas a change in the percent germline identity (%GI) was noted in 114/405 (28.1 %) sequences; in 50/114 (43.8 %) sequences, changes in the %GI led to a change in the mutational set. In conclusion, recent changes in the IMGT reference directories affected the interpretation of SHM in a sizeable number of IGH rearrangement sequences from CLL patients. This indicates that both physicians and researchers should consider a re-evaluation of IG sequence data, especially for those IGH rearrangement sequences that, up to date, have a GI close to 98 %, where caution is warranted.

TRES: Identification of Discriminatory and Informative SNPs from Population Genomic Data.

The advent of high-throughput genomic technologies is enabling analyses on thousands or even millions of single-nucleotide polymorphisms (SNPs). At the same time, the selection of a minimum number of SNPs with the maximum information content is becoming increasingly problematic. Available locus ranking programs have been accused of providing upwardly biased results (concerning the predicted accuracy of the chosen set of markers for population assignment), cannot handle high-dimensional datasets, and some of them are computationally intensive. The toolbox for ranking and evaluation of SNPs (TRES) is a collection of algorithms built in a user-friendly and computationally efficient software that can manipulate and analyze datasets even in the order of millions of genotypes in a matter of seconds. It offers a variety of established methods for evaluating and ranking SNPs on user defined groups of populations and produces a set of predefined number of top ranked loci. Moreover, dataset manipulation algorithms enable users to convert datasets in different file formats, split the initial datasets into train and test sets, and finally create datasets containing only selected SNPs occurring from the SNP selection analysis for later on evaluation in dedicated software such as GENECLASS. This application can aid biologists to select loci with maximum power for optimization of cost-effective panels with applications related to e.g. species identification, wildlife management, and forensic problems. TRES is available for all operating systems at http://mlkd.csd.auth.gr/bio/tres.

Information System for Symptom Diagnosis and Improvement of Attention Deficit Hyperactivity Disorder: Protocol for a Nonrandomized Controlled Pilot Study.

BACKGROUND: Attention deficit hyperactivity disorder (ADHD) is one of the most common neurodevelopmental disorders during childhood; however, the diagnosis procedure remains challenging, as it is nonstandardized, multiparametric, and highly dependent on subjective evaluation of the perceived behavior. OBJECTIVE: To address the challenges of existing procedures for ADHD diagnosis, the ADHD360 project aims to develop a platform for (1) early detection of ADHD by assessing the user's likelihood of having ADHD characteristics and (2) providing complementary training for ADHD management. METHODS: A 2-phase nonrandomized controlled pilot study was designed to evaluate the ADHD360 platform, including ADHD and non-ADHD participants aged 7 to 16 years. At the first stage, an initial neuropsychological evaluation along with an interaction with the serious game developed ("Pizza on Time") for approximately 30-45 minutes is performed. Subsequently, a 2-week behavior monitoring of the participants through the mADHD360 app is planned after a telephone conversation between the participants' parents and the psychologist, where the existence of any behaviors characteristic of ADHD that affect daily functioning is assessed. Once behavior monitoring is complete, the research team invites the participants to the second stage, where they play the game for a mean duration of 10 weeks (2 times per week). Once the serious game is finished, a second round of behavior monitoring is performed following the same procedures as the initial one. During the study, gameplay data were collected and preprocessed. The protocol of the pilot trials was initially designed for in-person participation, but after the COVID-19 outbreak, it was adjusted for remote participation. State-of-the-art machine learning (ML) algorithms were used to analyze labeled gameplay data aiming to detect discriminative gameplay patterns among the 2 groups (ADHD and non-ADHD) and estimate a player's likelihood of having ADHD characteristics. A schema including a train-test splitting with a 75:25 split ratio, k-fold cross-validation with k=3, an ML pipeline, and data evaluation were designed. RESULTS: A total of 43 participants were recruited for this study, where 18 were diagnosed with ADHD and the remaining 25 were controls. Initial neuropsychological assessment confirmed that the participants in the ADHD group showed a deviation from the participants without ADHD characteristics. A preliminary analysis of collected data consisting of 30 gameplay sessions showed that the trained ML models achieve high performance (ie, accuracy up to 0.85) in correctly predicting the users' labels (ADHD or non-ADHD) from their gameplay session on the ADHD360 platform. CONCLUSIONS: ADHD360 is characterized by its notable capacity to discriminate player gameplay behavior as either ADHD or non-ADHD. Therefore, the ADHD360 platform could be a valuable complementary tool for early ADHD detection. TRIAL REGISTRATION: ClinicalTrials.gov NCT04362982; https://clinicaltrials.gov/ct2/show/NCT04362982. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR1-10.2196/40189.

TP-DDI: Transformer-based pipeline for the extraction of Drug-Drug Interactions.

Drug-Drug Interaction (DDI) extraction is the task of identifying drug entities and the potential interactions between drug pairs from biomedical literature. Computer-aided extraction of DDIs is vital for drug discovery, as this process remains extremely expensive and time consuming. Therefore, Machine Learning-based approaches can reduce the laborious task during the drug development cycle. Numerous traditional and Neural Network-based approaches for Drug Named Entity Recognition (DNER) and the classification of DDIs have been proposed over the years. However, despite the development of many effective methods, achieving good prediction accuracy is an area where significant improvement can be made. In this article, we present a novel end-to-end approach that tackles the overall DDI extraction task as a pipelined method via the Transformer model architecture and biomedical domain pre-trained weights. In our approach, the tasks of DNER and DDI classification are executed successively to extract the drug entities and to classify their relationship respectively. The proposed approach, TP-DDI, integrates prior knowledge by using pre-trained weights from BioBERT and improves in both the Drug Named Entity Recognition and the overall DDI extraction task over the current state-of-the-art approaches on the DDI Extraction 2013 corpus.

EBM+: Advancing Evidence-Based Medicine via two level automatic identification of Populations, Interventions, Outcomes in medical literature.

Evidence-Based Medicine (EBM) has been an important practice for medical practitioners. However, as the number of medical publications increases dramatically, it is becoming extremely difficult for medical experts to review all the contents available and make an informative treatment plan for their patients. A variety of frameworks, including the PICO framework which is named after its elements (Population, Intervention, Comparison, Outcome), have been developed to enable fine-grained searches, as the first step to faster decision making. In this work, we propose a novel entity recognition system that identifies PICO entities within medical publications and achieves state-of-the-art performance in the task. This is achieved by the combination of four 2D Convolutional Neural Networks (CNNs) for character feature extraction, and a Highway Residual connection to facilitate deep Neural Network architectures. We further introduce a PICO Statement classifier, that identifies sentences that not only contain all PICO entities but also answer questions stated in PICO. To facilitate this task we also introduce a high quality dataset, manually annotated by medical practitioners. With the combination of our proposed PICO Entity Recognizer and PICO Statement classifier we aim to advance EBM and enable its faster and more accurate practice.

FIFS: A data mining method for informative marker selection in high dimensional population genomic data.

BACKGROUND AND OBJECTIVE: Single Nucleotide Polymorphism (SNPs) are, nowadays, becoming the marker of choice for biological analyses involving a wide range of applications with great medical, biological, economic and environmental interest. Classification tasks i.e. the assignment of individuals to groups of origin based on their (multi-locus) genotypes, are performed in many fields such as forensic investigations, discrimination between wild and/or farmed populations and others. Τhese tasks, should be performed with a small number of loci, for computational as well as biological reasons. Thus, feature selection should precede classification tasks, especially for Single Nucleotide Polymorphism (SNP) datasets, where the number of features can amount to hundreds of thousands or millions. METHODS: In this paper, we present a novel data mining approach, called FIFS - Frequent Item Feature Selection, based on the use of frequent items for selection of the most informative markers from population genomic data. It is a modular method, consisting of two main components. The first one identifies the most frequent and unique genotypes for each sampled population. The second one selects the most appropriate among them, in order to create the informative SNP subsets to be returned. RESULTS: The proposed method (FIFS) was tested on a real dataset, which comprised of a comprehensive coverage of pig breed types present in Britain. This dataset consisted of 446 individuals divided in 14 sub-populations, genotyped at 59,436 SNPs. Our method outperforms the state-of-the-art and baseline methods in every case. More specifically, our method surpassed the assignment accuracy threshold of 95% needing only half the number of SNPs selected by other methods (FIFS: 28 SNPs, Delta: 70 SNPs Pairwise FST: 70 SNPs, In: 100 SNPs.) CONCLUSION: Our approach successfully deals with the problem of informative marker selection in high dimensional genomic datasets. It offers better results compared to existing approaches and can aid biologists in selecting the most informative markers with maximum discrimination power for optimization of cost-effective panels with applications related to e.g. species identification, wildlife management, and forensics.

Machine Learning and Data Mining Methods in Diabetes Research.

The remarkable advances in biotechnology and health sciences have led to a significant production of data, such as high throughput genetic data and clinical information, generated from large Electronic Health Records (EHRs). To this end, application of machine learning and data mining methods in biosciences is presently, more than ever before, vital and indispensable in efforts to transform intelligently all available information into valuable knowledge. Diabetes mellitus (DM) is defined as a group of metabolic disorders exerting significant pressure on human health worldwide. Extensive research in all aspects of diabetes (diagnosis, etiopathophysiology, therapy, etc.) has led to the generation of huge amounts of data. The aim of the present study is to conduct a systematic review of the applications of machine learning, data mining techniques and tools in the field of diabetes research with respect to a) Prediction and Diagnosis, b) Diabetic Complications, c) Genetic Background and Environment, and e) Health Care and Management with the first category appearing to be the most popular. A wide range of machine learning algorithms were employed. In general, 85% of those used were characterized by supervised learning approaches and 15% by unsupervised ones, and more specifically, association rules. Support vector machines (SVM) arise as the most successful and widely used algorithm. Concerning the type of data, clinical datasets were mainly used. The title applications in the selected articles project the usefulness of extracting valuable knowledge leading to new hypotheses targeting deeper understanding and further investigation in DM.

Large-scale online semantic indexing of biomedical articles via an ensemble of multi-label classification models.

BACKGROUND: In this paper we present the approach that we employed to deal with large scale multi-label semantic indexing of biomedical papers. This work was mainly implemented within the context of the BioASQ challenge (2013-2017), a challenge concerned with biomedical semantic indexing and question answering. METHODS: Our main contribution is a MUlti-Label Ensemble method (MULE) that incorporates a McNemar statistical significance test in order to validate the combination of the constituent machine learning algorithms. Some secondary contributions include a study on the temporal aspects of the BioASQ corpus (observations apply also to the BioASQ's super-set, the PubMed articles collection) and the proper parametrization of the algorithms used to deal with this challenging classification task. RESULTS: The ensemble method that we developed is compared to other approaches in experimental scenarios with subsets of the BioASQ corpus giving positive results. In our participation in the BioASQ challenge we obtained the first place in 2013 and the second place in the four following years, steadily outperforming MTI, the indexing system of the National Library of Medicine (NLM). CONCLUSIONS: The results of our experimental comparisons, suggest that employing a statistical significance test to validate the ensemble method's choices, is the optimal approach for ensembling multi-label classifiers, especially in contexts with many rare labels.

Chronic Lymphocytic Leukemia with Mutated IGHV4-34 Receptors: Shared and Distinct Immunogenetic Features and Clinical Outcomes.

Purpose: We sought to investigate whether B cell receptor immunoglobulin (BcR IG) stereotypy is associated with particular clinicobiological features among chronic lymphocytic leukemia (CLL) patients expressing mutated BcR IG (M-CLL) encoded by the IGHV4-34 gene, and also ascertain whether these associations could refine prognostication.Experimental Design: In a series of 19,907 CLL cases with available immunogenetic information, we identified 339 IGHV4-34-expressing cases assigned to one of the four largest stereotyped M-CLL subsets, namely subsets #4, #16, #29 and #201, and investigated in detail their clinicobiological characteristics and disease outcomes.Results: We identified shared and subset-specific patterns of somatic hypermutation (SHM) among patients assigned to these subsets. The greatest similarity was observed between subsets #4 and #16, both including IgG-switched cases (IgG-CLL). In contrast, the least similarity was detected between subsets #16 and #201, the latter concerning IgM/D-expressing CLL. Significant differences between subsets also involved disease stage at diagnosis and the presence of specific genomic aberrations. IgG subsets #4 and #16 emerged as particularly indolent with a significantly (P < 0.05) longer time-to-first-treatment (TTFT; median TTFT: not yet reached) compared with the IgM/D subsets #29 and #201 (median TTFT: 11 and 12 years, respectively).Conclusions: Our findings support the notion that BcR IG stereotypy further refines prognostication in CLL, superseding the immunogenetic distinction based solely on SHM load. In addition, the observed distinct genetic aberration landscapes and clinical heterogeneity suggest that not all M-CLL cases are equal, prompting further research into the underlying biological background with the ultimate aim of tailored patient management. Clin Cancer Res; 23(17); 5292-301. ©2017 AACR.

Polyadenylation site prediction using PolyA-iEP method.

This chapter presents a method called PolyA-iEP that has been developed for the prediction of polyadenylation sites. More precisely, PolyA-iEP is a method that recognizes mRNA 3'ends which contain polyadenylation sites. It is a modular system which consists of two main components. The first exploits the advantages of emerging patterns and the second is a distance-based scoring method. The outputs of the two components are finally combined by a classifier. The final results reach very high scores of sensitivity and specificity.

Pattern discovery for microsatellite genome analysis.

Microsatellite loci comprise an important part of eukaryotic genomes. Their applications in biology as genetic markers are related to numerous fields ranging from paternity analyses to construction of genetic maps and linkage to human disease. Existing software solutions which offer pattern discovery algorithms for the correct identification and downstream analysis of microsatellites are scarce and are proving to be inefficient to analyze large, exponentially increasing, sequenced genomes. Moreover, such analyses can be very difficult for bioinformatically inexperienced biologists. In this paper we present Microsatellite Genome Analysis (MiGA) software for the detection of all microsatellite loci in genomic data through a user friendly interface. The algorithm searches exhaustively and rapidly for most microsatellites. Contrary to other applications, MiGA takes into consideration the following three most important aspects: the efficiency of the algorithm, the usability of the software and the plethora of offered summary statistics. All of the above, help biologists to obtain basic quantitative and qualitative information regarding the presence of microsatellites in genomic data as well as downstream processes, such as selection of specific microsatellite loci for primer design and comparative genome analysis.

StackTIS: a stacked generalization approach for effective prediction of translation initiation sites.

The prediction of the translation initiation site in an mRNA or cDNA sequence is an essential step in gene prediction and an open research problem in bioinformatics. Although recent approaches perform well, more effective and reliable methodologies are solicited. We developed an adaptable data mining method, called StackTIS, which is modular and consists of three prediction components that are combined into a meta-classification system, using stacked generalization, in a highly effective framework. We performed extensive experiments on sequences of two diverse eukaryotic organisms (Homo sapiens and Oryza sativa), indicating that StackTIS achieves statistically significant improvement in performance.

MANTIS: a data mining methodology for effective translation initiation site prediction.

The prediction of the translation initiation site in a genomic sequence with the highest possible accuracy is an important problem that still has to be investigated by the research community. Current approaches perform quite well, however there is still room for a more general framework for the researchers who want to follow an effective and reliable methodology. We developed a prediction methodology that combines ad hoc as well as discovered knowledge in order to significantly increase the achieved accuracy reliably. Our methodology is modular and consists of three major decision components: a consensus component, a coding region classification component and a novel ATG location-based component that allows for the utilization of the advantages of the popular Ribosome Scanning Model while overcoming its limitations. All three of them are combined into a meta-classification system, using stacked generalization, in a highly effective prediction framework. We performed extensive comparative experiments on four different datasets, showing that the increase in terms of accuracy and adjusted accuracy is not only statistically significant, but also the highest reported.

A novel approach for incremental uncertainty rule generation from databases with missing values handling: application to dynamic medical databases.

Current approaches for mining association rules usually assume that the mining is performed in a static database, where the problem of missing attribute values does not practically exist. However, these assumptions are not preserved in some medical databases, like in a home care system. In this paper, a novel uncertainty rule algorithm is illustrated, namely URG-2 (Uncertainty Rule Generator), which addresses the problem of mining dynamic databases containing missing values. This algorithm requires only one pass from the initial dataset in order to generate the item set, while new metrics corresponding to the notion of Support and Confidence are used. URG-2 was evaluated over two medical databases, introducing randomly multiple missing values for each record's attribute (rate: 5-20% by 5% increments) in the initial dataset. Compared with the classical approach (records with missing values are ignored), the proposed algorithm was more robust in mining rules from datasets containing missing values. In all cases, the difference in preserving the initial rules ranged between 30% and 60% in favour of URG-2. Moreover, due to its incremental nature, URG-2 saved over 90% of the time required for thorough re-mining. Thus, the proposed algorithm can offer a preferable solution for mining in dynamic relational databases.