LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Erweiterte Suche

Suchergebnis

Treffer 1 - 10 von insgesamt 122

Suchoptionen

  1. Buch ; Online: AI Maintenance

    Chen, Pin-Yu / Das, Payel

    A Robustness Perspective

    2023  

    Abstract: With the advancements in machine learning (ML) methods and compute resources, artificial intelligence (AI) empowered systems are becoming a prevailing technology. However, current AI technology such as deep learning is not flawless. The significantly ... ...

    Abstract With the advancements in machine learning (ML) methods and compute resources, artificial intelligence (AI) empowered systems are becoming a prevailing technology. However, current AI technology such as deep learning is not flawless. The significantly increased model complexity and data scale incur intensified challenges when lacking trustworthiness and transparency, which could create new risks and negative impacts. In this paper, we carve out AI maintenance from the robustness perspective. We start by introducing some highlighted robustness challenges in the AI lifecycle and motivating AI maintenance by making analogies to car maintenance. We then propose an AI model inspection framework to detect and mitigate robustness risks. We also draw inspiration from vehicle autonomy to define the levels of AI robustness automation. Our proposal for AI maintenance facilitates robustness assessment, status tracking, risk scanning, model hardening, and regulation throughout the AI lifecycle, which is an essential milestone toward building sustainable and trustworthy AI ecosystems.

    Comment: Accepted to IEEE Computer Magazine. To be published in 2023
    Schlagwörter Computer Science - Machine Learning ; Computer Science - Artificial Intelligence ; Computer Science - Computers and Society
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2023-01-08
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    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.

  2. Buch ; Online ; Dissertation / Habilitation: Establishment of non-centrosomal microtubule organizing centers in skeletal muscle cells

    Das, Payel [Verfasser] / Engel, Felix [Akademischer Betreuer] / Frasch, Manfred [Gutachter]

    2024  

    Verfasserangabe Payel Das ; Gutachter:  Manfred Frasch ; Betreuer:  Felix Engel
    Schlagwörter Biowissenschaften, Biologie ; Life Science, Biology
    Thema/Rubrik (Code) sg570
    Sprache Englisch
    Verlag Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU)
    Erscheinungsort Erlangen
    Dokumenttyp Buch ; Online ; Dissertation / Habilitation
    Datenquelle Digitale Dissertationen im Internet

    Volltext online

    Zusatzmaterialien

    Kategorien

    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.

  3. Artikel ; Online: ChatGPT: Literate or intelligent about UN sustainable development goals?

    Raman, Raghu / Lathabai, Hiran H / Mandal, Santanu / Das, Payel / Kaur, Tavleen / Nedungadi, Prema

    PloS one

    2024  Band 19, Heft 4, Seite(n) e0297521

    Abstract: Generative AI tools, such as ChatGPT, are progressively transforming numerous sectors, demonstrating a capacity to impact human life dramatically. This research seeks to evaluate the UN Sustainable Development Goals (SDGs) literacy of ChatGPT, which is ... ...

    Abstract Generative AI tools, such as ChatGPT, are progressively transforming numerous sectors, demonstrating a capacity to impact human life dramatically. This research seeks to evaluate the UN Sustainable Development Goals (SDGs) literacy of ChatGPT, which is crucial for diverse stakeholders involved in SDG-related policies. Experimental outcomes from two widely used Sustainability Assessment tests-the UN SDG Fitness Test and Sustainability Literacy Test (SULITEST) - suggest that ChatGPT exhibits high SDG literacy, yet its comprehensive SDG intelligence needs further exploration. The Fitness Test gauges eight vital competencies across introductory, intermediate, and advanced levels. Accurate mapping of these to the test questions is essential for partial evaluation of SDG intelligence. To assess SDG intelligence, the questions from both tests were mapped to 17 SDGs and eight cross-cutting SDG core competencies, but both test questionnaires were found to be insufficient. SULITEST could satisfactorily map only 5 out of 8 competencies, whereas the Fitness Test managed to map 6 out of 8. Regarding the coverage of the Fitness Test and SULITEST, their mapping to the 17 SDGs, both tests fell short. Most SDGs were underrepresented in both instruments, with certain SDGs not represented at all. Consequently, both tools proved ineffective in assessing SDG intelligence through SDG coverage. The study recommends future versions of ChatGPT to enhance competencies such as collaboration, critical thinking, systems thinking, and others to achieve the SDGs. It concludes that while AI models like ChatGPT hold considerable potential in sustainable development, their usage must be approached carefully, considering current limitations and ethical implications.
    Mesh-Begriff(e) Sustainable Development ; Humans ; Artificial Intelligence ; United Nations ; Goals ; Surveys and Questionnaires ; Literacy ; Intelligence
    Sprache Englisch
    Erscheinungsdatum 2024-04-24
    Erscheinungsland United States
    Dokumenttyp Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 2267670-3
    ISSN 1932-6203 ; 1932-6203
    ISSN (online) 1932-6203
    ISSN 1932-6203
    DOI 10.1371/journal.pone.0297521
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    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.

  4. Artikel ; Online: An end-to-end deep learning framework for translating mass spectra to de-novo molecules.

    Litsa, Eleni E / Chenthamarakshan, Vijil / Das, Payel / Kavraki, Lydia E

    Communications chemistry

    2023  Band 6, Heft 1, Seite(n) 132

    Abstract: Elucidating the structure of a chemical compound is a fundamental task in chemistry with applications in multiple domains including drug discovery, precision medicine, and biomarker discovery. The common practice for elucidating the structure of a ... ...

    Abstract Elucidating the structure of a chemical compound is a fundamental task in chemistry with applications in multiple domains including drug discovery, precision medicine, and biomarker discovery. The common practice for elucidating the structure of a compound is to obtain a mass spectrum and subsequently retrieve its structure from spectral databases. However, these methods fail for novel molecules that are not present in the reference database. We propose Spec2Mol, a deep learning architecture for molecular structure recommendation given mass spectra alone. Spec2Mol is inspired by the Speech2Text deep learning architectures for translating audio signals into text. Our approach is based on an encoder-decoder architecture. The encoder learns the spectra embeddings, while the decoder, pre-trained on a massive dataset of chemical structures for translating between different molecular representations, reconstructs SMILES sequences of the recommended chemical structures. We have evaluated Spec2Mol by assessing the molecular similarity between the recommended structures and the original structure. Our analysis showed that Spec2Mol is able to identify the presence of key molecular substructures from its mass spectrum, and shows on par performance, when compared to existing fragmentation tree methods particularly when test structure information is not available during training or present in the reference database.
    Sprache Englisch
    Erscheinungsdatum 2023-06-23
    Erscheinungsland England
    Dokumenttyp Journal Article
    ZDB-ID 2929562-2
    ISSN 2399-3669 ; 2399-3669
    ISSN (online) 2399-3669
    ISSN 2399-3669
    DOI 10.1038/s42004-023-00932-3
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    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.

  5. Buch ; Online: Reprogramming Pretrained Language Models for Protein Sequence Representation Learning

    Vinod, Ria / Chen, Pin-Yu / Das, Payel

    2023  

    Abstract: Machine Learning-guided solutions for protein learning tasks have made significant headway in recent years. However, success in scientific discovery tasks is limited by the accessibility of well-defined and labeled in-domain data. To tackle the low-data ... ...

    Abstract Machine Learning-guided solutions for protein learning tasks have made significant headway in recent years. However, success in scientific discovery tasks is limited by the accessibility of well-defined and labeled in-domain data. To tackle the low-data constraint, recent adaptions of deep learning models pretrained on millions of protein sequences have shown promise; however, the construction of such domain-specific large-scale model is computationally expensive. Here, we propose Representation Learning via Dictionary Learning (R2DL), an end-to-end representation learning framework in which we reprogram deep models for alternate-domain tasks that can perform well on protein property prediction with significantly fewer training samples. R2DL reprograms a pretrained English language model to learn the embeddings of protein sequences, by learning a sparse linear mapping between English and protein sequence vocabulary embeddings. Our model can attain better accuracy and significantly improve the data efficiency by up to $10^5$ times over the baselines set by pretrained and standard supervised methods. To this end, we reprogram an off-the-shelf pre-trained English language transformer and benchmark it on a set of protein physicochemical prediction tasks (secondary structure, stability, homology, stability) as well as on a biomedically relevant set of protein function prediction tasks (antimicrobial, toxicity, antibody affinity).

    Comment: 11 pages, 5 figures
    Schlagwörter Computer Science - Machine Learning ; Computer Science - Computation and Language ; Quantitative Biology - Biomolecules
    Thema/Rubrik (Code) 006
    Erscheinungsdatum 2023-01-05
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    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.

  6. Artikel: Enhanced sono-assisted adsorptive uptake of malachite green dye onto magnesium ferrite nanoparticles: Kinetic, isotherm and cost analysis

    Das, Payel / Debnath, Parmita / Debnath, Animesh

    Environmental nanotechnology, monitoring & management. 2021 Dec., v. 16

    2021  

    Abstract: In this study, the performance of magnesium ferrite nanoparticles (MgF-NPs) as adsorbent was assessed for removal of toxic malachite green (MG) dye from aqueous solution under ultrasonic irradiation. The MgF-NPs exhibited specific surface area of 70.266 ... ...

    Abstract In this study, the performance of magnesium ferrite nanoparticles (MgF-NPs) as adsorbent was assessed for removal of toxic malachite green (MG) dye from aqueous solution under ultrasonic irradiation. The MgF-NPs exhibited specific surface area of 70.266 m²/g and pore volume of 0.311 cc/g with an average pore diameter of 7.354 nm. Optimum solution pH was found to be 8.0 for sono-assisted MG dye adsorption, which is favourable for large scale field application of the proposed method. The adsorption reaction aided by ultrasonication could yield more than 90% MG dye removal within 15 min of reaction due to enhancement of mass transfer. However, instead of ultrasonication when overhead stirring and shaking was used as mixing methods then the MG dye removal efficacy was dropped to 70% and 65%, respectively. The adsorption kinetic strictly followed the pseudo-second-order model and equilibrium isotherm analysis followed the Langmuir isotherm model with maximum monolayer adsorption capacity of 487.60 mg/g. The presence of chloride ion hindered the MG dye removal efficiency from 91% to 67%, whereas the presence of nitrate, sulfate and phosphate ions in the dye solution could not affect the dye removal efficacy significantly. The cost analysis for synthesis of MgF-NPs revealed that the cost involvement of 50.88 USD/Kg of adsorbent which may be considered as economical for large scale industrial application.
    Schlagwörter administrative management ; adsorbents ; adsorption ; aqueous solutions ; chlorides ; cost analysis ; ferrimagnetic materials ; industrial applications ; magnesium ; malachite green ; mass transfer ; models ; nitrates ; pH ; phosphates ; sorption isotherms ; sulfates ; surface area ; toxicity ; ultrasonic treatment
    Sprache Englisch
    Erscheinungsverlauf 2021-12
    Erscheinungsort Elsevier B.V.
    Dokumenttyp Artikel
    ZDB-ID 2821777-9
    ISSN 2215-1532
    ISSN 2215-1532
    DOI 10.1016/j.enmm.2021.100506
    Datenquelle NAL Katalog (AGRICOLA)

    Volltext online

    Zusatzmaterialien

    Kategorien

    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.

  7. Artikel ; Online: The ultimate fate determinants of drug induced cell-death mechanisms in Trypanosomatids.

    Das, Payel / Saha, Saradindu / BoseDasgupta, Somdeb

    International journal for parasitology. Drugs and drug resistance

    2021  Band 15, Seite(n) 81–91

    Abstract: Chemotherapy constitutes a major part of modern-day therapy for infectious and chronic diseases. A drug is said to be effective if it can inhibit its target, induce stress, and thereby trigger an array of cell death pathways in the form of programmed ... ...

    Abstract Chemotherapy constitutes a major part of modern-day therapy for infectious and chronic diseases. A drug is said to be effective if it can inhibit its target, induce stress, and thereby trigger an array of cell death pathways in the form of programmed cell death, autophagy, necrosis, etc. Chemotherapy is the only treatment choice against trypanosomatid diseases like Leishmaniasis, Chagas disease, and sleeping sickness. Anti-trypanosomatid drugs can induce various cell death phenotypes depending upon the drug dose and growth stage of the parasites. The mechanisms and pathways triggering cell death in Trypanosomatids serve to help identify potential targets for the development of effective anti-trypanosomatids. Studies show that the key proteins involved in cell death of trypanosomatids are metacaspases, Endonuclease G, Apoptosis-Inducing Factor, cysteine proteases, serine proteases, antioxidant systems, etc. Unlike higher eukaryotes, these organisms either lack the complete set of effectors involved in cell death pathways, or are yet to be deciphered. A detailed summary of the existing knowledge of different drug-induced cell death pathways would help identify the lacuna in each of these pathways and therefore open new avenues for research and thereby new therapeutic targets to explore. The cell death pathway associated complexities in metazoans are absent in trypanosomatids; hence this summary can also help understand the trigger points as well as cross-talk between these pathways. Here we provide an in-depth overview of the existing knowledge of these drug-induced trypanosomatid cell death pathways, describe their associated physiological changes, and suggest potential interconnections amongst them.
    Mesh-Begriff(e) Cell Death ; Chagas Disease ; Humans ; Leishmaniasis ; Pharmaceutical Preparations ; Trypanosoma cruzi
    Chemische Substanzen Pharmaceutical Preparations
    Sprache Englisch
    Erscheinungsdatum 2021-01-25
    Erscheinungsland England
    Dokumenttyp Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 2751132-7
    ISSN 2211-3207 ; 2211-3207
    ISSN (online) 2211-3207
    ISSN 2211-3207
    DOI 10.1016/j.ijpddr.2021.01.003
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    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.

  8. Artikel ; Online: Machine learning models in the prediction of drug metabolism: challenges and future perspectives.

    Litsa, Eleni E / Das, Payel / Kavraki, Lydia E

    Expert opinion on drug metabolism & toxicology

    2021  Band 17, Heft 11, Seite(n) 1245–1247

    Mesh-Begriff(e) Drug Discovery ; Humans ; Machine Learning
    Sprache Englisch
    Erscheinungsdatum 2021-11-02
    Erscheinungsland England
    Dokumenttyp Editorial
    ZDB-ID 2214462-6
    ISSN 1744-7607 ; 1742-5255
    ISSN (online) 1744-7607
    ISSN 1742-5255
    DOI 10.1080/17425255.2021.1998454
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Volltext online

    Zusatzmaterialien

    Kategorien

    Verfügbar in ZB MED Köln/Königswinter

    Zs.A 6264: 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

    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.

  9. Artikel ; Online: Resolving the polycistronic aftermath: Essential role of topoisomerase IA in preventing R-loops in Leishmania.

    Das, Payel / Hazra, Arnab / Saha, Saradindu / Roy, Sadhana / Mukherjee, Mandrita / Hazra, Saugata / Majumdar, Hemanta K / BoseDasgupta, Somdeb

    The Journal of biological chemistry

    2024  Band 300, Heft 4, Seite(n) 107162

    Abstract: Kinetoplastid parasites are "living bridges" in the evolution from prokaryotes to higher eukaryotes. The near-intronless genome of the kinetoplastid Leishmania exhibits polycistronic transcription which can facilitate R-loop formation. Therefore, to ... ...

    Abstract Kinetoplastid parasites are "living bridges" in the evolution from prokaryotes to higher eukaryotes. The near-intronless genome of the kinetoplastid Leishmania exhibits polycistronic transcription which can facilitate R-loop formation. Therefore, to prevent such DNA-RNA hybrids, Leishmania has retained prokaryotic-like DNA Topoisomerase IA (LdTOPIA) in the course of evolution. LdTOPIA is an essential enzyme that is expressed ubiquitously and is adapted for the compartmentalized eukaryotic form in harboring functional bipartite nuclear localization signals. Although exhibiting greater homology to mycobacterial TOPIA, LdTOPIA could functionally complement the growth lethality of Escherichia coli TOPIA null GyrB ts strain at non-permissive temperatures. Purified LdTOPIA exhibits Mg
    Mesh-Begriff(e) Animals ; DNA Topoisomerases, Type I/metabolism ; DNA Topoisomerases, Type I/genetics ; Escherichia coli/genetics ; Escherichia coli/metabolism ; Leishmania/enzymology ; Leishmania/genetics ; Protozoan Proteins/metabolism ; Protozoan Proteins/genetics ; Protozoan Proteins/antagonists & inhibitors ; Protozoan Proteins/chemistry ; R-Loop Structures ; Trypanocidal Agents/chemistry ; Trypanocidal Agents/pharmacology
    Chemische Substanzen DNA Topoisomerases, Type I (EC 5.99.1.2) ; Protozoan Proteins ; Trypanocidal Agents
    Sprache Englisch
    Erscheinungsdatum 2024-03-12
    Erscheinungsland United States
    Dokumenttyp Journal Article ; Research Support, Non-U.S. Gov't
    ZDB-ID 2997-x
    ISSN 1083-351X ; 0021-9258
    ISSN (online) 1083-351X
    ISSN 0021-9258
    DOI 10.1016/j.jbc.2024.107162
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

    Verfügbar in ZB MED Köln/Königswinter

    Uc I Zs.108: 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

    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.

  10. Buch ; Online: Keeping Up with the Language Models

    Baldini, Ioana / Yadav, Chhavi / Das, Payel / Varshney, Kush R.

    Robustness-Bias Interplay in NLI Data and Models

    2023  

    Abstract: Auditing unwanted social bias in language models (LMs) is inherently hard due to the multidisciplinary nature of the work. In addition, the rapid evolution of LMs can make benchmarks irrelevant in no time. Bias auditing is further complicated by LM ... ...

    Abstract Auditing unwanted social bias in language models (LMs) is inherently hard due to the multidisciplinary nature of the work. In addition, the rapid evolution of LMs can make benchmarks irrelevant in no time. Bias auditing is further complicated by LM brittleness: when a presumably biased outcome is observed, is it due to model bias or model brittleness? We propose enlisting the models themselves to help construct bias auditing datasets that remain challenging, and introduce bias measures that distinguish between types of model errors. First, we extend an existing bias benchmark for NLI (BBNLI) using a combination of LM-generated lexical variations, adversarial filtering, and human validation. We demonstrate that the newly created dataset (BBNLInext) is more challenging than BBNLI: on average, BBNLI-next reduces the accuracy of state-of-the-art NLI models from 95.3%, as observed by BBNLI, to 58.6%. Second, we employ BBNLI-next to showcase the interplay between robustness and bias, and the subtlety in differentiating between the two. Third, we point out shortcomings in current bias scores used in the literature and propose bias measures that take into account pro-/anti-stereotype bias and model brittleness. We will publicly release the BBNLI-next dataset to inspire research on rapidly expanding benchmarks to keep up with model evolution, along with research on the robustness-bias interplay in bias auditing. Note: This paper contains offensive text examples.
    Schlagwörter Computer Science - Computation and Language
    Thema/Rubrik (Code) 310
    Erscheinungsdatum 2023-05-21
    Erscheinungsland us
    Dokumenttyp Buch ; Online
    Datenquelle BASE - Bielefeld Academic Search Engine (Lebenswissenschaftliche Auswahl)

    Volltext online

    Zusatzmaterialien

    Kategorien

    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