Search

Encouraged by recent efforts to map responses of SARS-CoV-2 mutations to various antibody treatments with deep mutational scanning, we explored the possibility of tying measurable structural contact information from the binding complexes of antibodies and their targets to experimentally determined viral escape responses. With just a single crystal structure for each binding complex, we find that the average correlation coefficient R is surprisingly high at 0.76. Our two methods for calculating contact information use binary contacts measured between all residues of two proteins. By varying the parameters to obtain binary contacts, we find that 3.6 Å and 7 Å are pivotal distances to toggle the binary step function when tallying the contacts for each method. The correlations are improved by short simulations (∼25 ns), which increase average R to 0.78. With blind tests using the random forest model, we can further improve average R to 0.84. These easy-to-implement measurements can be utilized in computational screening of viral mutations that escape antibody treatments and potentially other protein-protein interaction problems.

An unsolved challenge in the development of antigen-specific immunotherapies is determining the optimal antigens to target. Comprehension of antigen-major histocompatibility complex (MHC) binding is paramount toward achieving this goal. Here, we apply CASTELO, a combined machine learning-molecular dynamics (ML-MD) approach, to identify per-residue antigen binding contributions and then design novel antigens of increased MHC-II binding affinity for a type 1 diabetes-implicated system. We build upon a small-molecule lead optimization algorithm by training a convolutional variational autoencoder (CVAE) on MD trajectories of 48 different systems across four antigens and four HLA serotypes. We develop several new machine learning metrics including a structure-based anchor residue classification model as well as cluster comparison scores. ML-MD predictions agree well with experimental binding results and free energy perturbation-predicted binding affinities. Moreover, ML-MD metrics are independent of traditional MD stability metrics such as contact area and root-mean-square fluctuations (RMSF), which do not reflect binding affinity data. Our work supports the role of structure-based deep learning techniques in antigen-specific immunotherapy design.

In text analysis tasks like text classification and sentiment analysis, the careful choice of term weighting schemes can have an important impact on the effectiveness. Classic unsupervised schemes are based solely on the distribution of terms across documents, while newer supervised ones leverage the knowledge of membership of training documents to categories; these latter ones are often specifically tailored for either topic or sentiment classification. We propose here a supervised variant of the well-known tf.idf scheme, where the idf factor is computed without considering documents within the category under analysis, so that terms frequently appearing only within it are not penalized. The importance of these terms is further boosted in a second variant inspired by relevance frequency. We performed extensive experiments to compare these novel schemes to known ones, observing top performances in text categorization by topic and satisfactory results in sentiment classification.

Background Functional annotation of genes and gene products is a major challenge in the post-genomic era. Nowadays, gene function curation is largely based on manual assignment of Gene Ontology (GO) annotations to genes by using published literature. The annotation task is extremely time-consuming, therefore there is an increasing interest in automated tools that can assist human experts. Results Here we introduce GOTA, a GO term annotator for biomedical literature. The proposed approach makes use only of information that is readily available from public repositories and it is easily expandable to handle novel sources of information. We assess the classification capabilities of GOTA on a large benchmark set of publications. The overall performances are encouraging in comparison to the state of the art in multi-label classification over large taxonomies. Furthermore, the experimental tests provide some interesting insights into the potential improvement of automated annotation tools. Conclusions GOTA implements a flexible and expandable model for GO annotation of biomedical literature. The current version of the GOTA tool is freely available at http://gota.apice.unibo.it. Electronic supplementary material The online version of this article (doi:10.1186/s12859-015-0777-8) contains supplementary material, which is available to authorized users.

In cross-domain text classification, topic labels for documents of a target domain are predicted by leveraging knowledge of labeled documents of a source domain, having equal or similar topics with possibly different words. Existing methods either adapt documents of the source domain to the target or represent both domains in a common space. These methods are mostly based on advanced statistical techniques and often require tuning of parameters in order to obtain optimal performances. We propose a more straightforward approach based on nearest centroid classification: profiles of topic categories are extracted from the source domain and are then adapted by iterative refining steps using most similar documents in the target domain. Experiments on common benchmark datasets show that this approach, despite its simplicity, obtains accuracy measures better or comparable to other methods, obtained with fixed empirical values for its few parameters.

Computational analyses for biomedical knowledge discovery greatly benefit from the availability of the description of gene and protein functional features expressed through controlled terminologies and ontologies, i.e. of their controlled annotations. In the last years, several databases of such annotations have become available; yet, these annotations are incomplete and only some of them represent highly reliable human curated information. To predict and discover unknown or missing annotations existing approaches use unsupervised learning algorithms. We propose a new learning method that allows applying supervised algorithms to unsupervised problems, achieving much better annotation predictions. This method, which we also extend from our preceding work with data weighting techniques, is based on the generation of artificial labeled training sets through random perturbations of original data. We tested it on nine Gene Ontology annotation datasets; obtained results demonstrate that our approach achieves good effectiveness in novel annotation prediction, outperforming state of the art unsupervised methods.

Cross-domain text classification deals with predicting topic labels for documents in a target domain by leverag- ing knowledge from pre-labeled documents in a source domain, with different terms or different distributions thereof. Methods exist to address this problem by re-weighting documents from the source domain to transfer them to the target one or by finding a common feature space for documents of both domains; they often re- quire the combination of complex techniques, leading to a number of parameters which must be tuned for each dataset to yield optimal performances. We present a simpler method based on creating explicit representations of topic categories, which can be compared for similarity to the ones of documents. Categories representations are initially built from relevant source documents, then are iteratively refined by considering the most similar target documents, with relatedness being measured by a simple regression model based on cosine similarity, built once at the begin. This expectedly leads to obtain accurate representations for categories in the target domain, used to classify documents therein. Experiments on common benchmark text collections show that this approach obtains results better or comparable to other methods, obtained with fixed empirical values for its few parameters.

Genomic annotations describing functional features of genes and proteins through controlled terminologies and ontologies are extremely valuable, especially for computational analyses aimed at inferring new biomedical knowledge. Thanks to the biology revolution led by the introduction of the novel DNA sequencing technologies, several repositories of such annotations have becoming available in the last decade; among them, the ones including Gene Ontology annotations are the most relevant. Nevertheless, the available set of genomic annotations is incomplete, and only some of the available annotations represent highly reliable human curated information. In this paper we propose a novel representation of the annotation discovery problem, so as to enable applying supervised algorithms to predict Gene Ontology annotations of different organism genes. In order to use supervised algorithms despite labeled data to train the prediction model are not available, we propose a random perturbation method of the training set, which creates a new annotation matrix to be used to train the model to recognize new annotations. We tested the effectiveness of our approach on nine Gene Ontology annotation datasets. Obtained results demonstrated that our technique is able to improve novel annotation predictions with respect to state of the art unsupervised methods.

Previous studies claim that financial news influence the movements of stock prices almost instantaneously, however the poor foreseeability of news limits their possibility of predicting the stock price changes and trading actions. Recently complex sentiment analysis techniques have also showed that large amount of social network posts can predict the price movements of the Dow Jones Industrial Average (DJIA) within a less stringent timescale. From the idea that the contents of social posts can forecast the future stock trading actions, in this paper we present a simpler text mining method than the sentiment analysis approaches, which extracts the predictive knowledge of the DJIA movements from a large dataset of tweets, boosting also the prediction accuracy by identifying and filtering out irrelevant/noisy tweets. The noise detection technique we introduced improves the initial effectiveness of more than 10%. We tested our method on 10 millions twitter posts spanning one year, achieving an accuracy of 88.9% in the Dow Jones daily predictions, which, to the best of our knowledge, improves the best literature result based on social networks. Finally we have used the prediction method to drive the DJIA buy/sell actions of a trading protocol; the achieved return on investments (ROI) outperforms the state-of-the-art.

Until recently job seeking has been a tricky, tedious and time consuming process, because people looking for a new position had to collect information from many different sources. Job recommendation systems have been proposed in order to automate and simplify this task, also increasing its effectiveness. However, current approaches rely on scarce manually collected data that often do not completely reveal people skills. Our work aims to find out relationships between jobs and people skills making use of data from LinkedIn usersâ?? public profiles. Semantic associations arise by applying Latent Semantic Analysis (LSA). We use the mined semantics to obtain a hierarchical clustering of job positions and to build a job recommendation system. The outcome proves the effectiveness of our method in recommending job positions. Anyway, we argue that our approach is definitely general, because the extracted semantics could be worthy not only for job recommendation systems but also for recruiting systems. Furthermore, we point out that both the hierarchical clustering and the recommendation system do not require parameters to be tuned.

Within text categorization and other data mining tasks, the use of suitable methods for term weighting can bring a substantial boost in effectiveness. Several term weighting methods have been presented throughout literature, based on assumptions commonly derived from observation of distribution of words in documents. For example, the idf assumption states that words appearing in many documents are usually not as important as less frequent ones. Contrarily to tf.idf and other weighting methods derived from information retrieval, schemes proposed more recently are supervised, i.e. based on knownledge of membership of training documents to categories. We propose here a supervised variant of the tf.idf scheme, based on computing the usual idf factor without considering documents of the category to be recognized, so that importance of terms frequently appearing only within it is not underestimated. A further proposed variant is additionally based on relevance frequency, considering occurrences of words within the category itself. In extensive experiments on two recurring text collections with several unsupervised and supervised weighting schemes, we show that the ones we propose generally perform better than or comparably to other ones in terms of accuracy, using two different learning methods.

Efficiently detecting conversation threads from a pool of messages, such as social network chats, emails, comments to posts, news etc., is relevant for various applications, including Web Marketing, Information Retrieval and Digital Forensics. Existing approaches focus on text similarity using keywords as features that are strongly dependent on the dataset. Therefore, dealing with new corpora requires further costly analyses conducted by experts to find out new relevant features. This paper introduces a novel method to detect threads from any type of conversational texts overcoming the issue of previously determining specific features for each dataset. To automatically determine the relevant features of messages we map each message into a three dimensional representation based on its semantic content, the social interactions in terms of sender/recipients and its timestamp; then clustering is used to detect conversation threads. In addition, we propose a supervised approach to detect conversation threads that builds a classification model which combines the above extracted features for predicting whether a pair of messages belongs to the same thread or not. Our model harnesses the distance measure of a message to a cluster representing a thread to capture the probability that a message is part of that same thread. We present our experimental results on seven datasets, pertaining to different types of messages, and demonstrate the effectiveness of our method in the detection of conversation threads, clearly outperforming the state of the art and yielding an improvement of up to a 19%.