Filters








34 Hits in 2.6 sec

MOLIERE: Automatic Biomedical Hypothesis Generation System [article]

Justin Sybrandt, Michael Shtutman, Ilya Safro
2017 arXiv   pre-print
Hypothesis generation is becoming a crucial time-saving technique which allows biomedical researchers to quickly discover implicit connections between important concepts.  ...  Typically, these systems operate on domain-specific fractions of public medical data. MOLIERE, in contrast, utilizes information from over 24.5 million documents.  ...  Conclusions In this study we describe a deployed biomedical hypothesis generation system, MOLIERE, that can discover relationship hypotheses among biomedical objects.  ... 
arXiv:1702.06176v3 fatcat:552e3hdsq5cl3o4fneaknyf6ye

MOLIERE

Justin Sybrandt, Michael Shtutman, Ilya Safro
2017 Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '17  
Hypothesis generation is becoming a crucial time-saving technique which allows biomedical researchers to quickly discover implicit connections between important concepts.  ...  Typically, these systems operate on domain-specific fractions of public medical data. MOLIERE, in contrast, utilizes information from over 24.5 million documents.  ...  Conclusions In this study we describe a deployed biomedical hypothesis generation system, MOLIERE, that can discover relationship hypotheses among biomedical objects.  ... 
doi:10.1145/3097983.3098057 pmid:29430330 pmcid:PMC5804740 dblp:conf/kdd/SybrandtSS17 fatcat:yt3qqjxpxfdezn3trux5465jtq

AGATHA: Automatic Graph-mining And Transformer based Hypothesis generation Approach [article]

Justin Sybrandt, Ilya Tyagin, Michael Shtutman, Ilya Safro
2020 arXiv   pre-print
We present AGATHA, a deep-learning hypothesis generation system that can introduce data-driven insights earlier in the discovery process.  ...  Hypothesis generation systems address this challenge by mining the wealth of publicly available scientific information to predict plausible research directions.  ...  The first hypothesis generation system, ARROWSMITH, presents the ABC model of automatic discovery [36] .  ... 
arXiv:2002.05635v1 fatcat:t6jbr53fqrhytm2avreoufvs4y

Validation and Topic-driven Ranking for Biomedical Hypothesis Generation Systems [article]

Justin Sybrandt, Ilya Safro
2018 bioRxiv   pre-print
To expedite their searches, some scientists leverage hypothesis generation (HG) systems, which can automatically inspect published papers to uncover novel implicit connections.  ...  We also introduce a number of new metrics to automatically identify plausible generated hypotheses.  ...  Another extremely important use case of ranking is related to massive query runs in hypothesis generation systems.  ... 
doi:10.1101/263897 fatcat:rd3exyewxzd5fnepjjrctzuaxy

Large-Scale Validation of Hypothesis Generation Systems via Candidate Ranking [article]

Justin Sybrandt, Michael Shtutman, Ilya Safro
2018 arXiv   pre-print
In the modern rapidity of scientific progress, some turn to automated hypothesis generation (HG) systems to aid this process.  ...  Finally, we demonstrate that our proposed validation method aligns with real-world research goals by deploying our method within Moliere, our recent topic-driven HG system, in order to automatically generate  ...  The hypothesis, initially generated with MOLIERE, led to the following finding: Treatment with a DDX3-specific inhibitor blocks the enzymatic activity of the DDX3.  ... 
arXiv:1802.03793v4 fatcat:27scdbhytvbc7k232wtmcblpiq

Are Abstracts Enough for Hypothesis Generation? [article]

Justin Sybrandt, Angelo Carrabba, Alexander Herzog, Ilya Safro
2018 arXiv   pre-print
The potential for automatic hypothesis generation (HG) systems to improve research productivity keeps pace with the growing set of publicly available scientific information.  ...  Moliere generalizes main principles of similar knowledge network-based HG systems and reinforces them with topic modeling components.  ...  For these reasons, in [16] , we present a number of metrics that estimate the potential of an automatically generated hypothesis.  ... 
arXiv:1804.05942v3 fatcat:fj3o4bkv3fe3docq5q6hcrlfhi

Interpretable Visualization of Scientific Hypotheses in Literature-based Discovery [article]

Ilya Tyagin, Ilya Safro
2021 bioRxiv   pre-print
To demonstrate the proposed approach in action, we deployed end-to-end hypothesis generation pipeline AGATHA, which was evaluated by BioCreative VII experts with COVID-19-related queries.  ...  We also make use of the Unified Medical Language System metadata by integrating it directly into the resulting topics, and adding the variability into hypotheses resolution.  ...  We note that AGATHA is a general purpose hypothesis generation system not limited by any specific biomedical subdomain.  ... 
doi:10.1101/2021.10.29.466471 fatcat:zja43wwhqradjdtwky6a5h2y3m

Inhibition of the Dead Box RNA Helicase 3 prevents HIV-1 Tat and cocaine-induced neurotoxicity by targeting microglia activation [article]

Marina Aksenova, Justin Sybrandt, Biyun Cui, Vitali Sikirzhytski, Hao Ji, Diana Odhiambo, Mathew D. Lucius, Jill R. Turner, Eugenia Broude, Edsel Peña, Sofia Lizzaraga, Jun Zhu (+3 others)
2019 bioRxiv   pre-print
To uncover potential targets for anti-HAND therapy, we employed a literature mining system, MOLIERE.  ...  To determine genes with unknown implicit connections to HAND, we utilized MOLIERE, a system to automatically generate biomedical hypotheses (23) .  ...  This dataset consists of 26,759,399 documents; however, we found that certain short documents hinder hypothesis generation results.  ... 
doi:10.1101/591438 fatcat:tu2xj4xnqjetlnapxnk3td6t5m

Accelerating COVID-19 research with graph mining and transformer-based learning [article]

Ilya Tyagin and Ankit Kulshrestha and Justin Sybrandt and Krish Matta and Michael Shtutman and Ilya Safro
2021 arXiv   pre-print
To expedite their investigations, scientists leverage hypothesis generation systems, which can automatically inspect published papers to discover novel implicit connections.  ...  We present an automated general purpose hypothesis generation systems AGATHA-C and AGATHA-GP for COVID-19 research. The systems are based on graph-mining and the transformer model.  ...  It is not easy to define a perfectly correct result in biomedical hypothesis generation domain.  ... 
arXiv:2102.07631v2 fatcat:7jjv6jcsm5cx5gx6lo4be347yy

Accelerating COVID-19 research with graph mining and transformer-based learning [article]

Ilya Tyagin, Ankit Kulshrestha, Justin Sybrandt, Krish Matta, Michael Shtutman, Ilya Safro
2021 bioRxiv   pre-print
To expedite their investigations, scientists leverage hypothesis generation systems, which can automatically inspect published papers to discover novel implicit connections.  ...  We present an automated general purpose hypothesis generation systems AGATHA-C and AGATHA-GP for COVID-19 research. The systems are based on graph-mining and the transformer model.  ...  MEDLINE is one of the largest and well-known resources for biomedical text mining. Hypothesis Generation Systems. The HG field has been present in information sciences for several decades.  ... 
doi:10.1101/2021.02.11.430789 fatcat:fjso2ettw5by7iailutqjsqrpu

Semantic text mining in early drug discovery for type 2 diabetes

Lena K Hansson, Rasmus Borup Hansen, Sune Pletscher-Frankild, Rudolfs Berzins, Daniel Hvidberg Hansen, Dennis Madsen, Sten B Christensen, Malene Revsbech Christiansen, Ulrika Boulund, Xenia Asbæk Wolf, Sonny Kim Kjærulff, Martijn van de Bunt (+4 others)
2020 PLoS ONE  
Surveying the scientific literature is an important part of early drug discovery; and with the ever-increasing amount of biomedical publications it is imperative to focus on the most interesting articles  ...  To date, most text mining tools in the biomedical field are specialised to specific tasks [10] [11] [12] [13] . Some systems, e.g.  ...  As a curiosity we noted that the semantic concept with the 4th highest weight contained the n-gram 'aims hypothesis' because abstracts from the journal Diabetologia all have the heading 'aims/hypothesis  ... 
doi:10.1371/journal.pone.0233956 pmid:32542027 pmcid:PMC7295186 fatcat:sftzxqxnjratpexcl2rtrzacya

Heavy charged particles in radiation biology and biophysics

H Nikjoo, S Uehara, D Emfietzoglou, A Brahme
2008 New Journal of Physics  
In general, tracks are divided into two classes of sparsely ionizing ones such as electron tracks and densely ionizing tracks such as heavy ions.  ...  Ab initio calculations, due to their complexity, are generally limited to atomic systems [60] .  ...  A popular hypothesis in the field is the concept of clustered DNA damage.  ... 
doi:10.1088/1367-2630/10/7/075006 fatcat:py3e56pahvhtfjvnqhbfydrohq

Named Entity Recognition and Classification on Historical Documents: A Survey [article]

Maud Ehrmann, Ahmed Hamdi, Elvys Linhares Pontes, Matteo Romanello, Antoine Doucet
2021 arXiv   pre-print
Yet, named entity recognition (NER) systems are heavily challenged with diverse, historical and noisy inputs.  ...  Stemming from the distributional hypothesis, they are part of the representation learning paradigm where the objective is to equip machine learning algorithms with generic and efficient data representations  ...  In this regard, we outline a set of key priorities for the next generation of historical NER systems: (1) Transferability.  ... 
arXiv:2109.11406v1 fatcat:zbwoybklk5bjrlf2b67qm6t7e4

Quantitative assessment of spatial sound distortion by the semi-ideal recording point of a hear-through device

Pablo Hoffmann, Flemming Christensen, Dorte Hammersho/i
2013 Journal of the Acoustical Society of America  
A dynamic automatic noisy speech recognition system for a single-channel hybrid noisy industrial environment.  ...  Performance of the system is a serious concern for ASR in general, not just the LENA system.  ...  search systems.  ... 
doi:10.1121/1.4805375 fatcat:u4bvxh6karet3avpjdhpfwqpf4

FastSV: A Distributed-Memory Connected Component Algorithm with Fast Convergence [article]

Yongzhe Zhang, Ariful Azad, Zhenjiang Hu
2020 arXiv   pre-print
2016 30.22M 3.34B 4457 automatic biomedical hypothesis generation system [13] Metaclust50 282.20M 37.28B 15982994 similarities of proteins in Metaclust50 [7] Hyperlink 3.27B 124.90B 29360027  ...  For other software architectures, there are Hash-Min [21] for MapReduce systems and S-V PPA [27] for vertex-centric message passing systems [17] .  ... 
arXiv:1910.05971v2 fatcat:bvon3tci5vdfvnuy5miimuhbpm
« Previous Showing results 1 — 15 out of 34 results