Yufan Guo

A comparison and user-based evaluation of models of textual information structure in the context of cancer risk assessment.

BackgroundMany practical tasks in biomedicine require accessing specific types of information in scientific literature; e.g. information about the results or conclusions of the study in question. Several schemes have been developed to characterize such information in scientific journal articles. For example, a simple section-based scheme assigns individual sentences in abstracts under sections such as Objective, Methods, Results and Conclusions. Some schemes of textual information structure have proved useful for biomedical text mining (BIO-TM) tasks (e.g. automatic summarization). However, user-centered evaluation in the context of real-life tasks has been lacking.MethodsWe take three schemes of different type and granularity - those based on section names, Argumentative Zones (AZ) and Core Scientific Concepts (CoreSC) - and evaluate their usefulness for a real-life task which focuses on biomedical abstracts: Cancer Risk Assessment (CRA). We annotate a corpus of CRA abstracts according to each scheme, develop classifiers for automatic identification of the schemes in abstracts, and evaluate both the manual and automatic classifications directly as well as in the context of CRA.ResultsOur results show that for each scheme, the majority of categories appear in abstracts, although two of the schemes (AZ and CoreSC) were developed originally for full journal articles. All the schemes can be identified in abstracts relatively reliably using machine learning. Moreover, when cancer risk assessors are presented with scheme annotated abstracts, they find relevant information significantly faster than when presented with unannotated abstracts, even when the annotations are produced using an automatic classifier. Interestingly, in this user-based evaluation the coarse-grained scheme based on section names proved nearly as useful for CRA as the finest-grained CoreSC scheme.ConclusionsWe have shown that existing schemes aimed at capturing information structure of scientific documents can be applied to biomedical abstracts and can be identified in them automatically with an accuracy which is high enough to benefit a real-life task in biomedicine.

Weakly supervised learning of information structure of scientific abstracts—is it accurate enough to benefit real-world tasks in biomedicine?

MOTIVATION Many practical tasks in biomedicine require accessing specific types of information in scientific literature; e.g. information about the methods, results or conclusions of the study in question. Several approaches have been developed to identify such information in scientific journal articles. The best of these have yielded promising results and proved useful for biomedical text mining tasks. However, relying on fully supervised machine learning (ml) and a large body of annotated data, existing approaches are expensive to develop and port to different tasks. A potential solution to this problem is to employ weakly supervised learning instead. In this article, we investigate a weakly supervised approach to identifying information structure according to a scheme called Argumentative Zoning (az). We apply four weakly supervised classifiers to biomedical abstracts and evaluate their performance both directly and in a real-life scenario in the context of cancer risk assessment. RESULTS Our best weakly supervised classifier (based on the combination of active learning and self-training) performs well on the task, outperforming our best supervised classifier: it yields a high accuracy of 81% when just 10% of the labeled data is used for training. When cancer risk assessors are presented with the resulting annotated abstracts, they find relevant information in them significantly faster than when presented with unannotated abstracts. These results suggest that weakly supervised learning could be used to improve the practical usefulness of information structure for real-life tasks in biomedicine.

Link prediction in drug-target interactions network using similarity indices

BackgroundIn silico drug-target interaction (DTI) prediction plays an integral role in drug repositioning: the discovery of new uses for existing drugs. One popular method of drug repositioning is network-based DTI prediction, which uses complex network theory to predict DTIs from a drug-target network. Currently, most network-based DTI prediction is based on machine learning – methods such as Restricted Boltzmann Machines (RBM) or Support Vector Machines (SVM). These methods require additional information about the characteristics of drugs, targets and DTIs, such as chemical structure, genome sequence, binding types, causes of interactions, etc., and do not perform satisfactorily when such information is unavailable. We propose a new, alternative method for DTI prediction that makes use of only network topology information attempting to solve this problem.ResultsWe compare our method for DTI prediction against the well-known RBM approach. We show that when applied to the MATADOR database, our approach based on node neighborhoods yield higher precision for high-ranking predictions than RBM when no information regarding DTI types is available.ConclusionThis demonstrates that approaches purely based on network topology provide a more suitable approach to DTI prediction in the many real-life situations where little or no prior knowledge is available about the characteristics of drugs, targets, or their interactions.

Automatic semantic classification of scientific literature according to the hallmarks of cancer

MOTIVATION The hallmarks of cancer have become highly influential in cancer research. They reduce the complexity of cancer into 10 principles (e.g. resisting cell death and sustaining proliferative signaling) that explain the biological capabilities acquired during the development of human tumors. Since new research depends crucially on existing knowledge, technology for semantic classification of scientific literature according to the hallmarks of cancer could greatly support literature review, knowledge discovery and applications in cancer research. RESULTS We present the first step toward the development of such technology. We introduce a corpus of 1499 PubMed abstracts annotated according to the scientific evidence they provide for the 10 currently known hallmarks of cancer. We use this corpus to train a system that classifies PubMed literature according to the hallmarks. The system uses supervised machine learning and rich features largely based on biomedical text mining. We report good performance in both intrinsic and extrinsic evaluations, demonstrating both the accuracy of the methodology and its potential in supporting practical cancer research. We discuss how this approach could be developed and applied further in the future. AVAILABILITY AND IMPLEMENTATION The corpus of hallmark-annotated PubMed abstracts and the software for classification are available at: http://www.cl.cam.ac.uk/∼sb895/HoC.html. CONTACT simon.baker@cl.cam.ac.uk.

Unsupervised Discovery of Information Structure in Biomedical Documents

MOTIVATION Information structure (IS) analysis is a text mining technique, which classifies text in biomedical articles into categories that capture different types of information, such as objectives, methods, results and conclusions of research. It is a highly useful technique that can support a range of Biomedical Text Mining tasks and can help readers of biomedical literature find information of interest faster, accelerating the highly time-consuming process of literature review. Several approaches to IS analysis have been presented in the past, with promising results in real-world biomedical tasks. However, all existing approaches, even weakly supervised ones, require several hundreds of hand-annotated training sentences specific to the domain in question. Because biomedicine is subject to considerable domain variation, such annotations are expensive to obtain. This makes the application of IS analysis across biomedical domains difficult. In this article, we investigate an unsupervised approach to IS analysis and evaluate the performance of several unsupervised methods on a large corpus of biomedical abstracts collected from PubMed. RESULTS Our best unsupervised algorithm (multilevel-weighted graph clustering algorithm) performs very well on the task, obtaining over 0.70 F scores for most IS categories when applied to well-known IS schemes. This level of performance is close to that of lightly supervised IS methods and has proven sufficient to aid a range of practical tasks. Thus, using an unsupervised approach, IS could be applied to support a wide range of tasks across sub-domains of biomedicine. We also demonstrate that unsupervised learning brings novel insights into IS of biomedical literature and discovers information categories that are not present in any of the existing IS schemes. AVAILABILITY AND IMPLEMENTATION The annotated corpus and software are available at http://www.cl.cam.ac.uk/∼dk427/bio14info.html.

Grouping chemicals for health risk assessment: A text mining-based case study of polychlorinated biphenyls (PCBs).

As many chemicals act as carcinogens, chemical health risk assessment is critically important. A notoriously time consuming process, risk assessment could be greatly supported by classifying chemicals with similar toxicological profiles so that they can be assessed in groups rather than individually. We have previously developed a text mining (TM)-based tool that can automatically identify the mode of action (MOA) of a carcinogen based on the scientific evidence in literature, and it can measure the MOA similarity between chemicals on the basis of their literature profiles (Korhonen et al., 2009, 2012). A new version of the tool (2.0) was recently released and here we apply this tool for the first time to investigate and identify meaningful groups of chemicals for risk assessment. We used published literature on polychlorinated biphenyls (PCBs)-persistent, widely spread toxic organic compounds comprising of 209 different congeners. Although chemically similar, these compounds are heterogeneous in terms of MOA. We show that our TM tool, when applied to 1648 PubMed abstracts, produces a MOA profile for a subgroup of dioxin-like PCBs (DL-PCBs) which differs clearly from that for the rest of PCBs. This suggests that the tool could be used to effectively identify homogenous groups of chemicals and, when integrated in real-life risk assessment, could help and significantly improve the efficiency of the process.

Social and Semantic Diversity: Socio-semantic Representation of a Scientific Corpus

We propose a new method to extract key- words from texts and categorize these keywords according to their informational value, derived from the analysis of the ar- gumentative goal of the sentences they ap- pear in. The method is applied to the ACL Anthology corpus, containing papers on the computational linguistic domain pub- lished between 1980 and 2008. We show that our approach allows to highlight inter- esting facts concerning the evolution of the topics and methods used in computational linguistics.

Cancer Hallmarks Analytics Tool (CHAT): a text mining approach to organize and evaluate scientific literature on cancer

Motivation: To understand the molecular mechanisms involved in cancer development, significant efforts are being invested in cancer research. This has resulted in millions of scientific articles. An efficient and thorough review of the existing literature is crucially important to drive new research. This time-demanding task can be supported by emerging computational approaches based on text mining which offer a great opportunity to organise and retrieve the desired information efficiently from sizable databases. One way to organise existing knowledge on cancer is to utilise the widely accepted framework of the Hallmarks of Cancer. These hallmarks refer to the alterations in cell behaviour that characterise the cancer cell. Results: We created an extensive Hallmarks of Cancer taxonomy and developed automatic text mining methodology and a tool (CHAT) capable of retrieving and organising millions of cancer-related references from PubMed into the taxonomy. The efficiency and accuracy of the tool was evaluated intrinsically as well as extrinsically by case studies. The correlations identified by the tool show that it offers a great potential to organise and correctly classify cancer-related literature. Furthermore, the tool can be useful, for example, in identifying hallmarks associated with extrinsic factors, biomarkers and therapeutics targets. Availability: CHAT can be accessed at: http://chat.lionproject.net. The corpus of hallmark-annotated PubMed abstracts and the software are available at: http://chat.lionproject.net/about Contact: simon.baker@cl.cam.ac.uk Supplementary information:

Improving Literature-Based Discovery with Advanced Text Mining

Automated Literature Based Discovery (LBD) generates new knowledge by combining what is already known in literature. Facilitating large-scale hypothesis testing and generation from huge collections of literature, LBD could significantly support research in biomedical sciences. However, the uptake of LBD by the scientific community has been limited. One of the key reasons for this is the limited nature of existing LBD methodology. Based on fairly shallow methods, current LBD captures only some of the information available in literature. We discuss how advanced Text Mining based on Information retrieval, Natural Language Processing and data mining could open the doors to much deeper, wider coverage and dynamic LBD better capable of evolving with science, in particular when combined with sophisticated, state-of-the-art knowledge discovery techniques.

Neural networks for link prediction in realistic biomedical graphs: a multi-dimensional evaluation of graph embedding-based approaches

BackgroundLink prediction in biomedical graphs has several important applications including predicting Drug-Target Interactions (DTI), Protein-Protein Interaction (PPI) prediction and Literature-Based Discovery (LBD). It can be done using a classifier to output the probability of link formation between nodes. Recently several works have used neural networks to create node representations which allow rich inputs to neural classifiers. Preliminary works were done on this and report promising results. However they did not use realistic settings like time-slicing, evaluate performances with comprehensive metrics or explain when or why neural network methods outperform. We investigated how inputs from four node representation algorithms affect performance of a neural link predictor on random- and time-sliced biomedical graphs of real-world sizes (∼ 6 million edges) containing information relevant to DTI, PPI and LBD. We compared the performance of the neural link predictor to those of established baselines and report performance across five metrics.ResultsIn random- and time-sliced experiments when the neural network methods were able to learn good node representations and there was a negligible amount of disconnected nodes, those approaches outperformed the baselines. In the smallest graph (∼ 15,000 edges) and in larger graphs with approximately 14% disconnected nodes, baselines such as Common Neighbours proved a justifiable choice for link prediction. At low recall levels (∼ 0.3) the approaches were mostly equal, but at higher recall levels across all nodes and average performance at individual nodes, neural network approaches were superior. Analysis showed that neural network methods performed well on links between nodes with no previous common neighbours; potentially the most interesting links. Additionally, while neural network methods benefit from large amounts of data, they require considerable amounts of computational resources to utilise them.ConclusionsOur results indicate that when there is enough data for the neural network methods to use and there are a negligible amount of disconnected nodes, those approaches outperform the baselines. At low recall levels the approaches are mostly equal but at higher recall levels and average performance at individual nodes, neural network approaches are superior. Performance at nodes without common neighbours which indicate more unexpected and perhaps more useful links account for this.