Results 101 to 110 of about 35,694,464 (306)

A Deep Learning-Based Approach for Part of Speech (PoS) Tagging in the Pashto Language

IEEE Access
A fundamental task in natural language processing (NLP) is part of speech (PoS) tagging. PoS tagging is crucial to many NLP applications, including question answering, machine translation, syntactic parsing, speech recognition, and semantic parsing.
Shaheen Ullah, Riaz Ahmad, Abdallah Namoun, Siraj Muhammad, Khalil Ullah, Ibrar Hussain, Isa Ali Ibrahim   +6 more
doaj   +1 more source

The heterodimeric amino acid transporters (HAT) of the SLC7/SLC3 family: A structure−function relationships and relevance to human pathology

FEBS Letters, EarlyView.
Heterodimeric amino acid transporters consist of SLC7 and SLC3 family proteins arranged in a conserved structural organization. They regulate nutrient transport across cell membranes, supporting essential cellular functions. These transporters also contribute to xenobiotic/drug uptake and distribution.
Mariafrancesca Scalise, Tiziano Mazza, Raffaella Scanga, Lara Console, Michele Galluccio, Cesare Indiveri   +5 more
wiley   +1 more source

PicAxe: Extracting Figures from Structurally and Syntactically Heterogeneous Corpora of PDF Files

Journal of Open Research Software
PicAxe is open-source Python software that researchers can use to extract figures from corpora of PDF files that contain text and images. It is designed to extract figures from corpora that include both scanned and “born-digital” PDF files (structurally ...
Anna C. Guerrero, Krishna Kamath, Qilin Zhou, Bruno Felalaga, Julia Damerow, Aaron R. Dinner   +5 more
doaj   +1 more source

Leucine‐rich glioma inactivated 1 (LGI1) is a ganglioside‐binding protein

FEBS Letters, EarlyView.
Neuronal hyperexcitability associated with a decrease/absence of the extracellular protein LGI1 has been suggested to be primarily due to the downregulation of Kv1 channel expression. The molecular mechanisms underlying this decrease have not yet been elucidated.
Kévin Debreux, Christian Lévêque, Fodil Azzaz, Marion Sangiardi, Sarosh R Irani, Michael Seagar, Jacques Fantini, Oussama El Far   +7 more
wiley   +1 more source

Cluster-based Sample Selection for Document Image Binarization

, 2019
The current state-of-the-art, in terms of performance, for solving document image binarization is training artificial neural networks on pre-labelled ground truth data.
Amandus Krantz, Florian Westphal, Krantz, Amandus, Westphal, Florian, Krantz, Amandus,, Westphal, Florian,   +5 more
core   +1 more source

From Sketch to Structure: Agentic Prompting for Business Process Diagram Understanding With Vision–Language Models

IEEE Access
Converting real-world process diagrams into structured, executable representations remains challenging: systems must detect heterogeneous symbols, read noisy text, and reconstruct flow topology.
Pritam Deka, Barry Devereux
doaj   +1 more source

A context‐dependent modulatory role for eIF6 in acquired resistance to vemurafenib in melanoma

FEBS Letters, EarlyView.
Acquired resistance to vemurafenib upregulates the translation factor eIF6 in melanoma cells. Silencing eIF6 in resistant cells reduces proliferation and partially restores drug sensitivity, whereas its overexpression increases sensitivity across melanoma lines regardless of BRAF status, via modulation of mTOR, S6K, and MAPK signaling.
George Kyriakopoulos, Antonia Petropoulou, Alexandra Anastogianni, Angelina Bania, Vassilis Stamatakis, Argyris Alexiou, Chi‐Ping Day, Glenn Merlino, Katerina Grafanaki, Constantinos Stathopoulos   +9 more
wiley   +1 more source

WrIHAM: A Comprehensive Dataset for Writer Identification in Historical Arabic Manuscripts

IEEE Access
Writer identification in historical Arabic manuscripts supports manuscript authentication, cataloging, and cultural heritage preservation, yet progress is constrained by the scarcity of reliable writer-labeled datasets.
Abdulrahman Saleh, Wasfi G. Al-Khatib, Mohammad Amro, Abdullah Almugren   +3 more
doaj   +1 more source

Effective and fast binarization method for combined degradation on ancient documents

Heliyon, 2019
Document image binarization is a challenging task because of combined degradation in a document. In this study, a new binarization method is proposed for binarizing an ancient document with combined degradation.
Khairun Saddami, Khairul Munadi, Yuwaldi Away, Fitri Arnia   +3 more
doaj   +1 more source

Invisible but not inaccessible—Revealing transient oligomers formed by intrinsically disordered proteins with solution NMR and complementary methods

FEBS Letters, EarlyView.
Transient oligomers formed by intrinsically disordered proteins may be ‘invisible’ to direct detection yet remain accessible to solution NMR through equilibrium‐exchange measurements and pressure‐jump experiments. Complementary methods report on mass, stoichiometry, selected distance distributions, morphology, and internal packing.
Martin D. Gelenter, Ad Bax
wiley   +1 more source