LIVIVO - Suchergebnisse -

Suchergebnis

Treffer 1 - 10 von insgesamt 255

Suchoptionen

Artikel ; Online: ADMET-PrInt: Evaluation of ADMET Properties: Prediction and Interpretation.

Jamrozik, Ewelina / Śmieja, Marek / Podlewska, Sabina

Journal of chemical information and modeling

2024 Band 64, Heft 5, Seite(n) 1425–1432

Abstract: Great progress in the development of computational strategies for drug design applications has revolutionized the process of searching for new drugs. Although the focus ... ...

Abstract	Great progress in the development of computational strategies for drug design applications has revolutionized the process of searching for new drugs. Although the focus of
Mesh-Begriff(e)	Drug Design ; Solubility
Sprache	Englisch
Erscheinungsdatum	2024-02-19
Erscheinungsland	United States
Dokumenttyp	Journal Article
ZDB-ID	190019-5
ISSN	1549-960X ; 0095-2338
ISSN (online)	1549-960X
ISSN	0095-2338
DOI	10.1021/acs.jcim.3c02038
Datenquelle	MEDical Literature Analysis and Retrieval System OnLINE

Zusatzmaterialien

Verfügbar in ZB MED Köln/Königswinter

Zs.A 1230: Hefte anzeigen

Standort:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Über subito bestellen

Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.

Details ▾
- Im ZB MED-Bestand
- Kostenpflichtig bestellen

Artikel ; Online: Multi-Label Conditional Generation From Pre-Trained Models.

Proszewska, Magdalena / Wolczyk, Maciej / Zieba, Maciej / Wielopolski, Patryk / Maziarka, Lukasz / Smieja, Marek

IEEE transactions on pattern analysis and machine intelligence

2024 Band PP

Abstract: Although modern generative models achieve excellent quality in a variety of tasks, they often lack the essential ability to generate examples with requested properties, such as the age of the person in the photo or the weight of the generated molecule. ... ...

Abstract	Although modern generative models achieve excellent quality in a variety of tasks, they often lack the essential ability to generate examples with requested properties, such as the age of the person in the photo or the weight of the generated molecule. To overcome these limitations we propose PluGeN (Plugin Generative Network), a simple yet effective generative technique that can be used as a plugin for pre-trained generative models. The idea behind our approach is to transform the entangled latent representation using a flow-based module into a multi-dimensional space where the values of each attribute are modeled as an independent one-dimensional distribution. In consequence, PluGeN can generate new samples with desired attributes as well as manipulate labeled attributes of existing examples. Due to the disentangling of the latent representation, we are even able to generate samples with rare or unseen combinations of attributes in the dataset, such as a young person with gray hair, men with make-up, or women with beards. In contrast to competitive approaches, PluGeN can be trained on partially labeled data. We combined PluGeN with GAN and VAE models and applied it to conditional generation and manipulation of images, chemical molecule modeling and 3D point clouds generation.
Sprache	Englisch
Erscheinungsdatum	2024-03-26
Erscheinungsland	United States
Dokumenttyp	Journal Article
ISSN	1939-3539
ISSN (online)	1939-3539
DOI	10.1109/TPAMI.2024.3382008
Datenquelle	MEDical Literature Analysis and Retrieval System OnLINE

Zusatzmaterialien

Über subito bestellen

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Details ▾
- Kostenpflichtig bestellen

Buch ; Online: HyperTab

Wydmański, Witold / Bulenok, Oleksii / Śmieja, Marek

Hypernetwork Approach for Deep Learning on Small Tabular Datasets

2023

Abstract: Deep learning has achieved impressive performance in many domains, such as computer vision and natural language processing, but its advantage over classical shallow methods on tabular datasets remains questionable. It is especially challenging to surpass ...

Abstract	Deep learning has achieved impressive performance in many domains, such as computer vision and natural language processing, but its advantage over classical shallow methods on tabular datasets remains questionable. It is especially challenging to surpass the performance of tree-like ensembles, such as XGBoost or Random Forests, on small-sized datasets (less than 1k samples). To tackle this challenge, we introduce HyperTab, a hypernetwork-based approach to solving small sample problems on tabular datasets. By combining the advantages of Random Forests and neural networks, HyperTab generates an ensemble of neural networks, where each target model is specialized to process a specific lower-dimensional view of the data. Since each view plays the role of data augmentation, we virtually increase the number of training samples while keeping the number of trainable parameters unchanged, which prevents model overfitting. We evaluated HyperTab on more than 40 tabular datasets of a varying number of samples and domains of origin, and compared its performance with shallow and deep learning models representing the current state-of-the-art. We show that HyperTab consistently outranks other methods on small data (with a statistically significant difference) and scores comparable to them on larger datasets. We make a python package with the code available to download at https://pypi.org/project/hypertab/
Schlagwörter	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
Thema/Rubrik (Code)	006
Erscheinungsdatum	2023-04-07
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Buch ; Online: r-softmax

Bałazy, Klaudia / Struski, Łukasz / Śmieja, Marek / Tabor, Jacek

Generalized Softmax with Controllable Sparsity Rate

2023

Abstract: Nowadays artificial neural network models achieve remarkable results in many disciplines. Functions mapping the representation provided by the model to the probability distribution are the inseparable aspect of deep learning solutions. Although softmax ... ...

Abstract	Nowadays artificial neural network models achieve remarkable results in many disciplines. Functions mapping the representation provided by the model to the probability distribution are the inseparable aspect of deep learning solutions. Although softmax is a commonly accepted probability mapping function in the machine learning community, it cannot return sparse outputs and always spreads the positive probability to all positions. In this paper, we propose r-softmax, a modification of the softmax, outputting sparse probability distribution with controllable sparsity rate. In contrast to the existing sparse probability mapping functions, we provide an intuitive mechanism for controlling the output sparsity level. We show on several multi-label datasets that r-softmax outperforms other sparse alternatives to softmax and is highly competitive with the original softmax. We also apply r-softmax to the self-attention module of a pre-trained transformer language model and demonstrate that it leads to improved performance when fine-tuning the model on different natural language processing tasks.
Schlagwörter	Computer Science - Machine Learning
Thema/Rubrik (Code)	519
Erscheinungsdatum	2023-04-11
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Buch ; Online: ChiENN

Gaiński, Piotr / Koziarski, Michał / Tabor, Jacek / Śmieja, Marek

Embracing Molecular Chirality with Graph Neural Networks

2023

Abstract: Graph Neural Networks (GNNs) play a fundamental role in many deep learning problems, in particular in cheminformatics. However, typical GNNs cannot capture the concept of chirality, which means they do not distinguish between the 3D graph of a chemical ... ...

Abstract	Graph Neural Networks (GNNs) play a fundamental role in many deep learning problems, in particular in cheminformatics. However, typical GNNs cannot capture the concept of chirality, which means they do not distinguish between the 3D graph of a chemical compound and its mirror image (enantiomer). The ability to distinguish between enantiomers is important especially in drug discovery because enantiomers can have very distinct biochemical properties. In this paper, we propose a theoretically justified message-passing scheme, which makes GNNs sensitive to the order of node neighbors. We apply that general concept in the context of molecular chirality to construct Chiral Edge Neural Network (ChiENN) layer which can be appended to any GNN model to enable chirality-awareness. Our experiments show that adding ChiENN layers to a GNN outperforms current state-of-the-art methods in chiral-sensitive molecular property prediction tasks.
Schlagwörter	Computer Science - Machine Learning ; Quantitative Biology - Quantitative Methods
Thema/Rubrik (Code)	006
Erscheinungsdatum	2023-07-05
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Artikel ; Online: Chronic COVID-19 infection in an immunosuppressed patient shows changes in lineage over time: a case report.

Baker, Sheridan J C / Nfonsam, Landry E / Leto, Daniela / Rutherford, Candy / Smieja, Marek / McArthur, Andrew G

Virology journal

2024 Band 21, Heft 1, Seite(n) 8

Abstract: Background: The COVID-19 pandemic, caused by the Severe Acute Respiratory Syndrome Coronavirus 2 virus, emerged in late 2019 and spready globally. Many effects of infection with this pathogen are still unknown, with both chronic and repeated COVID-19 ... ...

Abstract	Background: The COVID-19 pandemic, caused by the Severe Acute Respiratory Syndrome Coronavirus 2 virus, emerged in late 2019 and spready globally. Many effects of infection with this pathogen are still unknown, with both chronic and repeated COVID-19 infection producing novel pathologies. Case presentation: An immunocompromised patient presented with chronic COVID-19 infection. The patient had history of Hodgkin's lymphoma, treated with chemotherapy and stem cell transplant. During the course of their treatment, eleven respiratory samples from the patient were analyzed by whole-genome sequencing followed by lineage identification. Whole-genome sequencing of the virus present in the patient over time revealed that the patient at various timepoints harboured three different lineages of the virus. The patient was initially infected with the B.1.1.176 lineage before coinfection with BA.1. When the patient was coinfected with both B.1.1.176 and BA.1, the viral populations were found in approximately equal proportions within the patient based on sequencing read abundance. Upon further sampling, the lineage present within the patient during the final two timepoints was found to be BA.2.9. The patient eventually developed respiratory failure and died. Conclusions: This case study shows an example of the changes that can happen within an immunocompromised patient who is infected with COVID-19 multiple times. Furthermore, this case demonstrates how simultaneous coinfection with two lineages of COVID-19 can lead to unclear lineage assignment by standard methods, which are resolved by further investigation. When analyzing chronic COVID-19 infection and reinfection cases, care must be taken to properly identify the lineages of the virus present.
Mesh-Begriff(e)	Humans ; COVID-19/complications ; Coinfection ; Pandemics ; SARS-CoV-2 ; Immunocompromised Host
Sprache	Englisch
Erscheinungsdatum	2024-01-04
Erscheinungsland	England
Dokumenttyp	Case Reports ; Journal Article
ZDB-ID	2160640-7
ISSN	1743-422X ; 1743-422X
ISSN (online)	1743-422X
ISSN	1743-422X
DOI	10.1186/s12985-023-02278-7
Datenquelle	MEDical Literature Analysis and Retrieval System OnLINE

Zusatzmaterialien

Über subito bestellen

Details ▾
- Kostenpflichtig bestellen

Artikel ; Online: Initial vancomycin versus metronidazole for the treatment of first-episode non-severe

Zhang, Kevin / Beckett, Patricia / Abouanaser, Salaheddin / Smieja, Marek

Antimicrobial stewardship & healthcare epidemiology : ASHE

2021 Band 1, Heft 1, Seite(n) e27

Abstract: Objective: Clostridioides difficile: Methods: We conducted a retrospective cohort study of all adult inpatients with first-episode CDI at our institution from January 2013 to May 2018. The initial vancomycin versus initial metronidazole cohorts were ... ...

Abstract	Objective: Clostridioides difficile Methods: We conducted a retrospective cohort study of all adult inpatients with first-episode CDI at our institution from January 2013 to May 2018. The initial vancomycin versus initial metronidazole cohorts were examined using a multivariate logistic regression model. Results: The study cohort of 737 patients had a median age of 72.3 years, and 357 of these patients (48.4%) had hospital-acquired infection. Among 326 patients with non-severe CDI, recurrence, new incident infection, and 30-day mortality rates were 16.2%, 10.9%, and 5.3%, respectively, when treated with initial metronidazole, compared to 20.0%, 1.4%, and 10.0%, respectively, when treated with initial vancomycin. In an adjusted multivariable analysis, the use of initial vancomycin for the treatment of non-severe CDI was associated with a reduction in new incident infection (adjusted odds ratio [OR Conclusions: Initial vancomycin was associated with a reduced rate of new incident infection in the treatment of adult inpatients with first-episode non-severe CDI. These findings support the use of initial vancomycin for all inpatients with CDI, when fidaxomicin is unavailable.
Sprache	Englisch
Erscheinungsdatum	2021-09-30
Erscheinungsland	England
Dokumenttyp	Journal Article
ISSN	2732-494X
ISSN (online)	2732-494X
DOI	10.1017/ash.2021.194
Datenquelle	MEDical Literature Analysis and Retrieval System OnLINE

Zusatzmaterialien

Über subito bestellen

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Details ▾
- Kostenpflichtig bestellen

Buch ; Online: Contrastive Hierarchical Clustering

Znaleźniak, Michał / Rola, Przemysław / Kaszuba, Patryk / Tabor, Jacek / Śmieja, Marek

2023

Abstract: Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the ground truth on popular benchmarks, the information contained in the flat ... ...

Abstract	Deep clustering has been dominated by flat models, which split a dataset into a predefined number of groups. Although recent methods achieve an extremely high similarity with the ground truth on popular benchmarks, the information contained in the flat partition is limited. In this paper, we introduce CoHiClust, a Contrastive Hierarchical Clustering model based on deep neural networks, which can be applied to typical image data. By employing a self-supervised learning approach, CoHiClust distills the base network into a binary tree without access to any labeled data. The hierarchical clustering structure can be used to analyze the relationship between clusters, as well as to measure the similarity between data points. Experiments demonstrate that CoHiClust generates a reasonable structure of clusters, which is consistent with our intuition and image semantics. Moreover, it obtains superior clustering accuracy on most of the image datasets compared to the state-of-the-art flat clustering models.
Schlagwörter	Computer Science - Machine Learning ; Computer Science - Artificial Intelligence
Thema/Rubrik (Code)	006
Erscheinungsdatum	2023-03-03
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Artikel ; Online: ACP Journal Club. Review: oseltamivir relieves symptoms but does not reduce hospitalizations in influenza.

Smieja, Marek

Annals of internal medicine

2012 Band 157, Heft 6, Seite(n) JC3–5

Sprache	Englisch
Erscheinungsdatum	2012-09-18
Erscheinungsland	United States
Dokumenttyp	Comment ; Journal Article
ZDB-ID	336-0
ISSN	1539-3704 ; 0003-4819
ISSN (online)	1539-3704
ISSN	0003-4819
DOI	10.7326/0003-4819-157-6-201209180-02005
Datenquelle	MEDical Literature Analysis and Retrieval System OnLINE

Zusatzmaterialien

Verfügbar in ZB MED Köln/Königswinter

Ua VI Zs.178/2: Hefte anzeigen

Standort:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Über subito bestellen

Details ▾
- Im ZB MED-Bestand
- Kostenpflichtig bestellen

Buch ; Online: Hebbian Continual Representation Learning

Morawiecki, Paweł / Krutsylo, Andrii / Wołczyk, Maciej / Śmieja, Marek

2022

Abstract: Continual Learning aims to bring machine learning into a more realistic scenario, where tasks are learned sequentially and the i.i.d. assumption is not preserved. Although this setting is natural for biological systems, it proves very difficult for ... ...

Abstract	Continual Learning aims to bring machine learning into a more realistic scenario, where tasks are learned sequentially and the i.i.d. assumption is not preserved. Although this setting is natural for biological systems, it proves very difficult for machine learning models such as artificial neural networks. To reduce this performance gap, we investigate the question whether biologically inspired Hebbian learning is useful for tackling continual challenges. In particular, we highlight a realistic and often overlooked unsupervised setting, where the learner has to build representations without any supervision. By combining sparse neural networks with Hebbian learning principle, we build a simple yet effective alternative (HebbCL) to typical neural network models trained via the gradient descent. Due to Hebbian learning, the network have easily interpretable weights, which might be essential in critical application such as security or healthcare. We demonstrate the efficacy of HebbCL in an unsupervised learning setting applied to MNIST and Omniglot datasets. We also adapt the algorithm to the supervised scenario and obtain promising results in the class-incremental learning.
Schlagwörter	Computer Science - Neural and Evolutionary Computing ; Computer Science - Machine Learning
Thema/Rubrik (Code)	006
Erscheinungsdatum	2022-06-28
Erscheinungsland	us
Dokumenttyp	Buch ; Online
Datenquelle	BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

Volltext online

Volltext online

Zusatzmaterialien

Fernleihe an ZB MED

Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.

Zum Seitenanfang

Zusatzmaterialien

Kategorien

Verfügbar in ZB MED Köln/Königswinter

Über subito bestellen

Zusatzmaterialien

Kategorien

Über subito bestellen

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Zusatzmaterialien

Kategorien

Über subito bestellen

Zusatzmaterialien

Kategorien

Über subito bestellen

Fernleihe an ZB MED

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED

Zusatzmaterialien

Kategorien

Verfügbar in ZB MED Köln/Königswinter

Über subito bestellen

Volltext online

Zusatzmaterialien

Kategorien

Fernleihe an ZB MED