GENIES: a natural-language processing system for the extraction of molecular pathways from journal articles.

Systems that extract structured information from natural language passages have been highly successful in specialized domains. The time is opportune for developing analogous applications for molecular biology and genomics. We present a system, GENIES, that extracts and structures information about cellular pathways from the biological literature in accordance with a knowledge model that we developed earlier. We implemented GENIES by modifying an existing medical natural language processing system, MedLEE, and performed a preliminary evaluation study. Our results demonstrate the value of the underlying techniques for the purpose of acquiring valuable knowledge from biological journals.

A knowledge model for the interpretation and visualization of NLP-parsed discharged summaries.

At our institution, a Natural Language Processing (NLP) tool called MedLEE is used on a daily basis to parse medical texts including complete discharge summaries. MedLEE transforms written text into a generic structured format, which preserves the richness of the underlying natural language expressions by the use of concept modifiers (like change, certainty, degree and status). As a tradeoff, extraction of application-specific medical information is difficult without a clear understanding of how these modifiers combine. We report on a knowledge model for MedLEE modifiers that is helpful for a high level interpretation of NLP data and is used for the generation of two distinct views on NLP-parsed discharge summaries: A physician view offering a condensed overview of the severity of patient problems and a data mining view featuring binary problem states useful for machine learning.

A knowledge model for analysis and simulation of regulatory networks.

MOTIVATION: In order to aid in hypothesis-driven experimental gene discovery, we are designing a computer application for the automatic retrieval of signal transduction data from electronic versions of scientific publications using natural language processing (NLP) techniques, as well as for visualizing and editing representations of regulatory systems. These systems describe both signal transduction and biochemical pathways within complex multicellular organisms, yeast, and bacteria. This computer application in turn requires the development of a domain-specific ontology, or knowledge model. RESULTS: We introduce an ontological model for the representation of biological knowledge related to regulatory networks in vertebrates. We outline a taxonomy of the concepts, define their 'whole-to-part' relationships, describe the properties of major concepts, and outline a set of the most important axioms. The ontology is partially realized in a computer system designed to aid researchers in biology and medicine in visualizing and editing a representation of a signal transduction system.

Using BLAST for identifying gene and protein names in journal articles.

We describe a system which automatically identifies gene and protein names in journal articles, an important and non-trivial first step in knowledge extraction of protein and gene actions. Our system uses a database of gene and protein names and is based on BLAST [Altschul et al., Nucleic Acids Res. 25 (1997) 3389-3402], a popular tool for DNA and protein sequence comparison. We describe a method that consists of mapping sequences of text characters into sequences of nucleotides that can be processed by BLAST. We demonstrate that this approach is feasible: the system matches gene and protein names with a recall of 78.8% and a precision of 71.7%, which includes names that are not part of the system database. An analysis of the results suggests techniques that can be used to improve performance further.

Serum angiotensin-converting-enzyme in rabbits with and without pulmonary granulomatosis. Granulomatosis induced with complete-Freund's-adjuvant or BCG.

An animal model with pulmonary, non-caseating, granulomatosis was successfully reproduced in rabbits utilizing intravenous injections of complete-Freund's-adjuvant (CFA) or BCG. Granuloma formation from CFA injections was limited to the lungs, but BCG injections caused systemic granulomatosis (lung, liver and spleen) irrespective of whether the BCG was dissolved in saline or in incomplete-Freund's-adjuvant (IFA). Serum angiotensin-converting-enzyme (ACE) levels began to rise approximately 15 days following the intravenous injection of CFA, but similar rises following the injection of IFA without granuloma formation suggest that the ACE rise was not necessarily reflective of granuloma formation in rabbits. BCG in saline caused no rise in serum ACE, but when suspended in IFA the ACE rise was comparable to that resulting from IFA alone. However, the ACE level of broncho-alveolar-lavage cells obtained from rabbits 21 days post-injection of CFA was 7-fold higher than that of lavaged cells obtained 42 days post injection, correlating with an acute alveolitis occurring early during granuloma formation. These studies confirm the usefulness of intravenous injections of CFA or BCG for inducing a granulomatous state, but show that the assay of serum ACE is not useful for reflecting the granulomatous state in rabbits. In addition, serum ACE levels are 2-5 X higher in rabbits than in humans and tend to fluctuate spontaneously following delivery of the animals to the laboratory.

Pseudoclubbing in a patient with sarcoidosis of the phalangeal bones.

We treated a patient who had sarcoidosis with pseudoclubbing. The involvement was asymmetric and involved some fingertips more than others. It did not involve the toes. The pseudoclubbing totally disappeared with effective prednisone therapy. Roentgenograms of the hands showed bone cysts of the distal and middle phalanges, and a gallium citrate Ga 67 scan showed uptake in two of the phalanges. We believe the pseudoclubbing in this patient is a manifestation of phalangeal bone involvement by sarcoidosis with associated dactylitis. A literature review indicates that true clubbing can exist in patients with sarcoidosis, but this case indicates that it must be distinguished from dactylitis.

Accelerated clearance of small solutes from the lungs in interstitial lung disease.

Solutions of 99mTc-diethylenetriaminepenta-acetate (99mTc-DTPA) and 99mTcO-4 were aerosolized and inhaled by subjects seated against a scintillation camera. Initial clearance rates of these radionuclides were determined over 6 posterior lung regions. Clearance of 99mTcO-4 (molecular weight, 163 dalton exceeded that of 99mTc-DTPA (molecular weight, 492 daltons) by an average factor of 3.3. Upper-lobe clearance of both radionuclides was greater than lower-lobe clearance in the normal subjects, but this gradient was abolished when the subjects exhaled against 7 cm of positive end-expiratory pressure. Twenty-one patients with clinical and roentgenographic evidence of interstitial lung disease (ILD) and diminished CO diffusion rates were studied with 99mTc-DTPA. Clearance of 99mTc-DTPA was increased in each of 5 patients with idiopathic pulmonary fibrosis, 4 of 8 with sarcoid, 2 of 5 with pneumoconiosis, and 2 of 3 patients with other forms of ILD. In contrast, the clearance of 99mTcO-4 was decreased in 4 patients with pulmonary alveolar proteinosis. Furthermore, no increase in 99mTc-DTPA clearance was found in 5 patients with chronic obstructive pulmonary disease. These studies suggest that the initial clearance of these aerosolized hydrophilic radionuclides is accomplished in part by diffusion through the epithelium of alveoli and respiratory bronchioles. Whereas radionuclide clearance is impaired by the presence of precipitated protein in these structures in pulmonary alveolar proteinosis, clearance is accelerated in ILD. This may indicate increased epithelial permeability in ILD related to injury and increased retractile forces.

Dynamic imaging of the systemic perfusion of a lung cancer: case report.

Dynamic lung circulation scintigraphy employing intravenously administered 99mTc as pertechnetate was used to visualize the pulmonary arterial and systemic arterial circulations in a patient with bronchogenic carcinoma. Computer-processed dynamic images and region-of-interest data were utilized to demonstrate differences between tumor and normal regions regarding pulmonary and systemic blood supplies.