Artemy Kolchinsky

Extraction of pharmacokinetic evidence of drug-drug interactions from the literature.

Drug-drug interaction (DDI) is a major cause of morbidity and mortality and a subject of intense scientific interest. Biomedical literature mining can aid DDI research by extracting evidence for large numbers of potential interactions from published literature and clinical databases. Though DDI is investigated in domains ranging in scale from intracellular biochemistry to human populations, literature mining has not been used to extract specific types of experimental evidence, which are reported differently for distinct experimental goals. We focus on pharmacokinetic evidence for DDI, essential for identifying causal mechanisms of putative interactions and as input for further pharmacological and pharmacoepidemiology investigations. We used manually curated corpora of PubMed abstracts and annotated sentences to evaluate the efficacy of literature mining on two tasks: first, identifying PubMed abstracts containing pharmacokinetic evidence of DDIs; second, extracting sentences containing such evidence from abstracts. We implemented a text mining pipeline and evaluated it using several linear classifiers and a variety of feature transforms. The most important textual features in the abstract and sentence classification tasks were analyzed. We also investigated the performance benefits of using features derived from PubMed metadata fields, various publicly available named entity recognizers, and pharmacokinetic dictionaries. Several classifiers performed very well in distinguishing relevant and irrelevant abstracts (reaching F1≈0.93, MCC≈0.74, iAUC≈0.99) and sentences (F1≈0.76, MCC≈0.65, iAUC≈0.83). We found that word bigram features were important for achieving optimal classifier performance and that features derived from Medical Subject Headings (MeSH) terms significantly improved abstract classification. We also found that some drug-related named entity recognition tools and dictionaries led to slight but significant improvements, especially in classification of evidence sentences. Based on our thorough analysis of classifiers and feature transforms and the high classification performance achieved, we demonstrate that literature mining can aid DDI discovery by supporting automatic extraction of specific types of experimental evidence.

Classification of Protein-Protein Interaction Full-Text Documents Using Text and Citation Network Features

We participated (as Team 9) in the Article Classification Task of the Biocreative II.5 Challenge: binary classification of full-text documents relevant for protein-protein interaction. We used two distinct classifiers for the online and offline challenges: 1) the lightweight Variable Trigonometric Threshold (VTT) linear classifier we successfully introduced in BioCreative 2 for binary classification of abstracts and 2) a novel Naive Bayes classifier using features from the citation network of the relevant literature. We supplemented the supplied training data with full-text documents from the MIPS database. The lightweight VTT classifier was very competitive in this new full-text scenario: it was a top-performing submission in this task, taking into account the rank product of the Area Under the interpolated precision and recall Curve, Accuracy, Balanced F-Score, and Matthews Correlation Coefficient performance measures. The novel citation network classifier for the biomedical text mining domain, while not a top performing classifier in the challenge, performed above the central tendency of all submissions, and therefore indicates a promising new avenue to investigate further in bibliome informatics.

Neural correlates of apparent motion perception of impoverished facial stimuli: A comparison of ERP and ERSP activity

Our brains readily decode human movements, as shown by neural responses to face and body motion. N170 event-related potentials (ERPs) are earlier and larger to mouth opening movements relative to closing in both line-drawn and natural faces, and gaze aversions relative to direct gaze in natural faces (Puce and Perrett, 2003; Puce et al., 2000). Here we extended this work by recording both ERP and oscillatory EEG activity (event-related spectral perturbations, ERSPs) to line-drawn faces depicting eye and mouth movements (Eyes: Direct vs Away; Mouth: Closed vs Open) and non-face motion controls. Neural activity was measured in 2 occipito-temporal clusters of 9 electrodes, one in each hemisphere. Mouth opening generated larger N170s than mouth closing, replicating earlier work. Eye motion elicited robust N170s that did not differ between gaze conditions. Control condition differences were seen, and generated the largest N170. ERSP difference plots across conditions in the occipito-temporal electrode clusters (Eyes: Direct vs Away; Mouth: Closed vs Open) showed statistically significant differences in beta and gamma bands for gaze direction changes and mouth opening at similar post-stimulus times and frequencies. In contrast, control stimuli showed activity in the gamma band with a completely different time profile and hemispheric distribution to facial stimuli. ERSP plots were generated in two 9 electrode clusters centered on central sites, C3 and C4. In the left cluster for all stimulus conditions, broadband beta suppression persisted from about 250ms post-motion onset. In the right cluster, beta suppression was seen for control conditions only. Statistically significant differences between conditions were confined between 4 and 15Hz, unlike the occipito-temporal sites where differences occurred at much higher frequencies (high beta/gamma). Our data indicate that N170 amplitude is sensitive to the amount of movement in the visual field, independent of stimulus type. In contrast, occipito-temporal beta and gamma activity differentiates between facial and non-facial motion. Context and stimulus configuration likely plays a role in shaping neural responses, based on comparisons of the current data to previously reported studies. Broadband suppression of central beta activity, and significant low frequency differences were likely stimulus driven and not contingent on behavioral responses.

Multi-scale integration and predictability in resting state brain activity

The human brain displays heterogeneous organization in both structure and function. Here we develop a method to characterize brain regions and networks in terms of information-theoretic measures. We look at how these measures scale when larger spatial regions as well as larger connectome sub-networks are considered. This framework is applied to human brain fMRI recordings of resting-state activity and DSI-inferred structural connectivity. We find that strong functional coupling across large spatial distances distinguishes functional hubs from unimodal low-level areas, and that this long-range functional coupling correlates with structural long-range efficiency on the connectome. We also find a set of connectome regions that are both internally integrated and coupled to the rest of the brain, and which resemble previously reported resting-state networks. Finally, we argue that information-theoretic measures are useful for characterizing the functional organization of the brain at multiple scales.

Evaluation of linear classifiers on articles containing pharmacokinetic evidence of drug-drug interactions.

BACKGROUND Drug-drug interaction (DDI) is a major cause of morbidity and mortality. DDI research includes the study of different aspects of drug interactions, from in vitro pharmacology, which deals with drug interaction mechanisms, to pharmaco-epidemiology, which investigates the effects of DDI on drug efficacy and adverse drug reactions. Biomedical literature mining can aid both kinds of approaches by extracting relevant DDI signals from either the published literature or large clinical databases. However, though drug interaction is an ideal area for translational research, the inclusion of literature mining methodologies in DDI workflows is still very preliminary. One area that can benefit from literature mining is the automatic identification of a large number of potential DDIs, whose pharmacological mechanisms and clinical significance can then be studied via in vitro pharmacology and in populo pharmaco-epidemiology. EXPERIMENTS We implemented a set of classifiers for identifying published articles relevant to experimental pharmacokinetic DDI evidence. These documents are important for identifying causal mechanisms behind putative drug-drug interactions, an important step in the extraction of large numbers of potential DDIs. We evaluate performance of several linear classifiers on PubMed abstracts, under different feature transformation and dimensionality reduction methods. In addition, we investigate the performance benefits of including various publicly-available named entity recognition features, as well as a set of internally-developed pharmacokinetic dictionaries. RESULTS We found that several classifiers performed well in distinguishing relevant and irrelevant abstracts. We found that the combination of unigram and bigram textual features gave better performance than unigram features alone, and also that normalization transforms that adjusted for feature frequency and document length improved classification. For some classifiers, such as linear discriminant analysis (LDA), proper dimensionality reduction had a large impact on performance. Finally, the inclusion of NER features and dictionaries was found not to help classification.

Estimating Mixture Entropy with Pairwise Distances

Mixture distributions arise in many parametric and non-parametric settings—for example, in Gaussian mixture models and in non-parametric estimation. It is often necessary to compute the entropy of a mixture, but, in most cases, this quantity has no closed-form expression, making some form of approximation necessary. We propose a family of estimators based on a pairwise distance function between mixture components, and show that this estimator class has many attractive properties. For many distributions of interest, the proposed estimators are efficient to compute, differentiable in the mixture parameters, and become exact when the mixture components are clustered. We prove this family includes lower and upper bounds on the mixture entropy. The Chernoff α -divergence gives a lower bound when chosen as the distance function, with the Bhattacharyaa distance providing the tightest lower bound for components that are symmetric and members of a location family. The Kullback–Leibler divergence gives an upper bound when used as the distance function. We provide closed-form expressions of these bounds for mixtures of Gaussians, and discuss their applications to the estimation of mutual information. We then demonstrate that our bounds are significantly tighter than well-known existing bounds using numeric simulations. This estimator class is very useful in optimization problems involving maximization/minimization of entropy and mutual information, such as MaxEnt and rate distortion problems.

The Minor fall, the Major lift: inferring emotional valence of musical chords through lyrics

We investigate the association between musical chords and lyrics by analysing a large dataset of user-contributed guitar tablatures. Motivated by the idea that the emotional content of chords is reflected in the words used in corresponding lyrics, we analyse associations between lyrics and chord categories. We also examine the usage patterns of chords and lyrics in different musical genres, historical eras and geographical regions. Our overall results confirm a previously known association between Major chords and positive valence. We also report a wide variation in this association across regions, genres and eras. Our results suggest possible existence of different emotional associations for other types of chords.

Correction: Kolchinsky, A. and Tracey, B.D. Estimating Mixture Entropy with Pairwise Distances. Entropy 2017, 19, 361

Following the publication of our paper [1], we uncovered a mistake in the derivation of two formulas in the manuscript.[...]