AB

Bibliografia publikacji pracowników
Państwowej Szkoły Wyższej w Białej Podlaskiej

Baza tworzona przez Bibliotekę Akademii Bialskiej im. Jana Pawła II.


Zapytanie: AI
Liczba odnalezionych rekordów: 3



Przejście do opcji zmiany formatu | Wyświetl/ukryj etykiety | Wyświetlenie wyników w wersji do druku | Pobranie pliku do edytora | Nowe wyszukiwanie
1/3
Nr opisu: cek^sTomas^u^t^qVanecek T^w^x0000036941^zVanecek Tomas^aPaszkiewicz
Autorzy: , , , Justyna Mariusz Piotr Oryginalny artykuł naukowy publikacja bezkosztowa 99929970.0000070.000PUNKTACJA KBNPUNKTACJA MINISTERSTWALISTA FILADELFIJSKAIMPACT FACTOR70.000PUNKTACJA UWM 009929.000 Q 003 Vol. 46 CC-BY PaszkiewiczSacharczukReligaoriginal-articleF000.00996100009996.2001467-3037003Using Copy Number Variation Data and Neural Networks to Predict Cancer Metastasis Origin Achieves High Area under the Curve Value with a Trade-Off in PrecisionCurrent Issues in Molecular Biology20241467-30452023/2024https://doi.org/10.3390/cimb46080490Paszkiewicz, JustynaaiFINAL_PUBLISHEDThe accurate identification of the primary tumor origin in metastatic cancer cases is crucial for guiding treatment decisions and improving patient outcomes. Copy number alterations (CNAs) and copy number variation (CNV) have emerged as valuable genomic markers for predicting the origin of metastases. However, current models that predict cancer type based on CNV or CNA suffer from low AUC values. To address this challenge, we employed a cutting-edge neural network approach utilizing a dataset comprising CNA profiles from twenty different cancer types. We developed two workflows: the first evaluated the performance of two deep neural networks-one ReLU-based and the other a 2D convolutional network. In the second workflow, we stratified cancer types based on anatomical and physiological classifications, constructing shallow neural networks to differentiate between cancer types within the same cluster. Both approaches demonstrated high AUC values, with deep neural networks achieving a precision of 60%, suggesting a mathematical relationship between CNV type, location, and cancer type. Our findings highlight the potential of using CNA/CNV to aid pathologists in accurately identifying cancer origins with accessible clinical tests.cancerclinical testcopy number variantgenomic markersmetastasisneural network, Justyna Mariusz Piotr Oryginalny artykuł naukowy publikacja bezkosztowa 99929970.0000070.000PUNKTACJA KBNPUNKTACJA MINISTERSTWALISTA FILADELFIJSKAIMPACT FACTOR70.000PUNKTACJA UWM 009929.000 Q 003 Vol. 46 CC-BY PaszkiewiczSacharczukReligaoriginal-articleF000.00996100009996.2001467-3037003Using Copy Number Variation Data and Neural Networks to Predict Cancer Metastasis Origin Achieves High Area under the Curve Value with a Trade-Off in PrecisionCurrent Issues in Molecular Biology20241467-30452023/2024https://doi.org/10.3390/cimb46080490Paszkiewicz, JustynaaiFINAL_PUBLISHEDThe accurate identification of the primary tumor origin in metastatic cancer cases is crucial for guiding treatment decisions and improving patient outcomes. Copy number alterations (CNAs) and copy number variation (CNV) have emerged as valuable genomic markers for predicting the origin of metastases. However, current models that predict cancer type based on CNV or CNA suffer from low AUC values. To address this challenge, we employed a cutting-edge neural network approach utilizing a dataset comprising CNA profiles from twenty different cancer types. We developed two workflows: the first evaluated the performance of two deep neural networks-one ReLU-based and the other a 2D convolutional network. In the second workflow, we stratified cancer types based on anatomical and physiological classifications, constructing shallow neural networks to differentiate between cancer types within the same cluster. Both approaches demonstrated high AUC values, with deep neural networks achieving a precision of 60%, suggesting a mathematical relationship between CNV type, location, and cancer type. Our findings highlight the potential of using CNA/CNV to aid pathologists in accurately identifying cancer origins with accessible clinical tests.cancerclinical testcopy number variantgenomic markersmetastasisneural network.
Tytuł równoległy: SacharczukReligaoriginal-articleF000.00996100009996.2001467-3037003Using Copy Number Variation Data and Neural Networks to Predict Cancer Metastasis Origin Achieves High Area under the Curve Value with a Trade-Off in PrecisionCurrent Issues in Molecular Biology20241467-30452023/2024https://doi.org/10.3390/cimb46080490Paszkiewicz, JustynaaiFINAL_PUBLISHEDThe accurate identification of the primary tumor origin in metastatic cancer cases is crucial for guiding treatment decisions and improving patient outcomes. Copy number alterations (CNAs) and copy number variation (CNV) have emerged as valuable genomic markers for predicting the origin of metastases. However, current models that predict cancer type based on CNV or CNA suffer from low AUC values. To address this challenge, we employed a cutting-edge neural network approach utilizing a dataset comprising CNA profiles from twenty different cancer types. We developed two workflows: the first evaluated the performance of two deep neural networks-one ReLU-based and the other a 2D convolutional network. In the second workflow, we stratified cancer types based on anatomical and physiological classifications, constructing shallow neural networks to differentiate between cancer types within the same cluster. Both approaches demonstrated high AUC values, with deep neural networks achieving a precision of 60%, suggesting a mathematical relationship between CNV type, location, and cancer type. Our findings highlight the potential of using CNA/CNV to aid pathologists in accurately identifying cancer origins with accessible clinical tests.cancerclinical testcopy number variantgenomic markersmetastasisneural network : Justyna : Mariusz : Piotr : Oryginalny artykuł naukowy : publikacja bezkosztowa : 99929970.0000070.000PUNKTACJA KBNPUNKTACJA MINISTERSTWALISTA FILADELFIJSKAIMPACT FACTOR70.000PUNKTACJA UWM : 009929.000 : Q : 003 : Vol. 46 : CC-BY
Tytuł czasopisma:
Charakterystyka merytoryczna:
Język publikacji:
Wskaźnik Impact Factor ISI:
Punktacja ministerstwa:
Praca recenzowana
Słowa kluczowe ang.: TACJA UWM^a009996.200^b009929.000^c009999.000^d009929.000202420242024Using Copy Number Variation Data and Neural Networks to Predict Cancer Metastasis Origin Achieves00000481150000000208AOartykuł oryginalny naukowyPUBLIKACJAPEŁNA PUBLIKACJAAAartykuł w czasopiśmie z IF (wykaz MNiSW)AFILIACJA PODANAENGhttps://www.mdpi.com/1467-3045/46/8/490100^a1467-3037^bQ^e1467-3045^iX^jXY^kQ004712^a003^b003^c2024-10-02, 10:59^d2024-11-22, 14:12^e3021029180^f3019828827^aUsing Copy Number Variation Data and Neural Networks to Predict Cancer Metastasis Origin Achieves High Area under the Curve Value with a Trade-Off in Precision^aCurrent Issues in Molecular Biology^a2024^bVol. 46^cissue 8^dp. 8301--8319^a1467-3045^a2023/2024^ahttps://doi.org/10.3390/cimb46080490^aPaszkiewicz, Justyna^cy^aai^aFINAL_PUBLISHED^bCC-BY^cAT_PUBLICATION^eOPEN_JOURNAL^aThe accurate identification of the primary tumor origin in metastatic cancer cases is crucial for guiding treatment decisions and improving patient outcomes. Copy number alterations (CNAs) and copy number variation (CNV) have emerged as valuable genomic markers for predicting the origin of metastases. However, current models that predict cancer type based on CNV or CNA suffer from low AUC values. To address this challenge, we employed a cutting-edge neural network approach utilizing a dataset comprising CNA profiles from twenty different cancer types. We developed two workflows: the first evaluated the performance of two deep neural networks-one ReLU-based and the other a 2D convolutional network. In the second workflow, we stratified cancer types based on anatomical and physiological classifications, constructing shallow neural networks to differentiate between cancer types within the same cluster. Both approaches demonstrated high AUC values, with deep neural networks achieving a precision of 60%, suggesting a mathematical relationship between CNV type, location, and cancer type. Our findings highlight the potential of using CNA/CNV to aid pathologists in accurately identifying cancer origins with accessible clinical tests.^acancer^aclinical test^acopy number variant^agenomic markers^ametastasis^aneural network
Słowa kluczowe ang.: ; ;

2/3
Nr opisu: na^pPaszkiewicz Justyna^rPASZKIEWICZ^sJUSTYNA^u^tZakład Pielęgniarstwa^qPaszkiewicz J^w930593^x0000013936^zPaszkiewicz Justyna^aTeodorowicz
Autorzy: , , , , Patrycja Tomasz Jarosław Olav Gina Mariusz Michel-Edwar Oryginalny artykuł naukowyACZartykuł w czasopiśmie zagranicznym2.800IF 99929970.0000070.000PUNKTACJA KBNPUNKTACJA MINISTERSTWALISTA FILADELFIJSKAIMPACT FACTOR70.000PUNKTACJA UWM 009929.000 Q 003 Vol. 45 CC-BY TeodorowiczKockiHorbańczukMandaSacharczukMickaeloriginal-article996100009996.2001467-3037003Investigation of the Molecular Evolution of Treg Suppresion Mechanisms Indicates a Covergent OriginCurrent Issues in Molecular Biology20231467-30452022/202310.3390/cimb45010042aiFINAL_PUBLISHEDRegulatory T cell (Treg) suppression of conventional T cells is a central mechanism that ensures immune system homeostasis. The exact time point of Treg emergence is still disputed. Furthermore, the time of Treg-mediated suppression mechanisms' emergence has not been identified. It is not yet known whether Treg suppression mechanisms diverged from a single pathway or converged from several sources. We investigated the evolutionary history of Treg suppression pathways using various phylogenetic analysis tools. To ensure the conservation of function for investigated proteins, we augmented our study using nonhomology-based methods to predict protein functions among various investigated species and mined the literature for experimental evidence of functional convergence. Our results indicate that a minority of Treg suppressor mechanisms could be homologs of ancient conserved pathways. For example, CD73, an enzymatic pathway known to play an essential role in invertebrates, is highly conserved between invertebrates and vertebrates, with no evidence of positive selection (w = 0.48, p-value < 0.00001). Our findings indicate that Tregs utilize homologs of proteins that diverged in early vertebrates. However, our findings do not exclude the possibility of a more evolutionary pattern following the duplication degeneration-complementation (DDC) model. Ancestral sequence reconstruction showed that Treg suppression mechanism proteins do not belong to one family; rather, their emergence seems to follow a convergent evolutionary pattern.evolutionmolecular evolutiontregs, Patrycja Tomasz Jarosław Olav Gina Mariusz Michel-Edwar Oryginalny artykuł naukowyACZartykuł w czasopiśmie zagranicznym2.800IF 99929970.0000070.000PUNKTACJA KBNPUNKTACJA MINISTERSTWALISTA FILADELFIJSKAIMPACT FACTOR70.000PUNKTACJA UWM 009929.000 Q 003 Vol. 45 CC-BY TeodorowiczKockiHorbańczukMandaSacharczukMickaeloriginal-article996100009996.2001467-3037003Investigation of the Molecular Evolution of Treg Suppresion Mechanisms Indicates a Covergent OriginCurrent Issues in Molecular Biology20231467-30452022/202310.3390/cimb45010042aiFINAL_PUBLISHEDRegulatory T cell (Treg) suppression of conventional T cells is a central mechanism that ensures immune system homeostasis. The exact time point of Treg emergence is still disputed. Furthermore, the time of Treg-mediated suppression mechanisms' emergence has not been identified. It is not yet known whether Treg suppression mechanisms diverged from a single pathway or converged from several sources. We investigated the evolutionary history of Treg suppression pathways using various phylogenetic analysis tools. To ensure the conservation of function for investigated proteins, we augmented our study using nonhomology-based methods to predict protein functions among various investigated species and mined the literature for experimental evidence of functional convergence. Our results indicate that a minority of Treg suppressor mechanisms could be homologs of ancient conserved pathways. For example, CD73, an enzymatic pathway known to play an essential role in invertebrates, is highly conserved between invertebrates and vertebrates, with no evidence of positive selection (w = 0.48, p-value < 0.00001). Our findings indicate that Tregs utilize homologs of proteins that diverged in early vertebrates. However, our findings do not exclude the possibility of a more evolutionary pattern following the duplication degeneration-complementation (DDC) model. Ancestral sequence reconstruction showed that Treg suppression mechanism proteins do not belong to one family; rather, their emergence seems to follow a convergent evolutionary pattern.evolutionmolecular evolutiontregs.
Tytuł czasopisma:
Charakterystyka formalna: Mariusz^u^t^qSacharczuk M^w^x0000026532^zSacharczuk Mariusz^aMickael
Charakterystyka merytoryczna:
Język publikacji:
Wskaźnik Impact Factor ISI:
Punktacja ministerstwa:
Praca recenzowana
Słowa kluczowe ang.:

3/3
Nr opisu:
Tytuł czasopisma:
Oznaczenie wydania:
Charakterystyka formalna:
Charakterystyka merytoryczna:
Język publikacji:
Punktacja ministerstwa: potential for generating incorrect answers. Additionally, the article highlights the importance of privacy concerns when using Chat GPT. Ultimately, the analysis of the article focuses on examining both the benefits and potential challenges associated with integrating Chat GPT into people's professional endeavors. The aim of this paper is to present the concept of Chat GPT and its impact on various professions. Design/Methodology/Approach: The article employed the following methods: literature review and analysis of the impact of the Chat GPT tool on the job market. The focus was on examining various perspectives and considering the main concepts related to Chat GPT. Findings: Based on the conducted analyses, it was determined that Chat GPT has assisted professionals in their work, but at this moment, it is not capable of replacing humans in their respective occupa
Słowa kluczowe:
Słowa kluczowe ang.: ; ;

  Wyświetl ponownie stosując format:
Wyświetl/ukryj etykiety | Wyświetlenie wyników w wersji do druku | Pobranie pliku do edytora | Nowe wyszukiwanie | Biblioteka AB