Feeds:
Posts
Comments

Archive for the ‘Innovations in Neurophysiology & Neuropsychology’ Category

AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class X: +300 Audio Podcasts Library: Interviews with Scientific Leaders

AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class X: +300 Audio Podcasts Library: Interviews with Scientific Leaders

Curator: Aviva Lev-Ari, PhD, RN

We had researched the topic of AI Initiatives in Big Pharma in the following article:

  • Authentic Relevance of LPBI Group’s Portfolio of IP as Proprietary Training Data Corpus for AI Initiatives at Big Pharma

https://pharmaceuticalintelligence.com/2025/11/15/authentic-relevance-of-lpbi-groups-portfolio-of-ip-as-proprietary-training-data-corpus-for-ai-initiatives-at-big-pharma/

 

We are publishing a Series of Five articles that demonstrate the Authentic Relevance of Five of the Ten Digital IP Asset Classes in LPBI Group’s Portfolio of IP for AI Initiatives at Big Pharma.

  • For the Ten IP Asset Classes in LPBI Group’s Portfolio, See

https://pharmaceuticalintelligence.com/portfolio-of-ip-assets/

The following Five Digital IP Asset classes are positioned as Proprietary Training Data and Inference for Foundation Models in Health care.
This Corpus comprises of Live Repository of Domain Knowledge Expert-Written Clinical Interpretations of Scientific Findings codified in the following five Digital IP ASSETS CLASSES:
 IP Asset Class I: Journal: PharmaceuticalIntelligence.com
6,250 scientific articles (70% curations, creative expert opinions.  30% scientific reports).
2.4MM Views, equivalent of $50MM if downloading an article is paid market rate of $30.

https://pharmaceuticalintelligence.com/vision/pharmaceuticalintelligence-com-journal-projecting-the-annual-rate-of-article-views/

 

 

• IP Asset Class II: 48 e-Books: English Edition & Spanish Edition.
152,000 pages downloaded under pay-per-view. The largest number of downloads for one e-Publisher (LPBI)
• IP Asset Class III: 100 e-Proceedings and 50 Tweet Collections of Top Biotech and Medical Global Conferences, 2013-2025

• IP Asset Class V: 7,500 Biological Images in our Digital Art Media Gallery, as prior art. The Media Gallery resides in WordPress.com Cloud of LPBI Group’s Web site

• IP Asset Class X: +300 Audio Podcasts: Interviews with Scientific Leaders
BECAUSE THE ABOVE ASSETS ARE DIGITAL ASSETS they are ready for use as Proprietary TRAINING DATA and INFERENCE for AI Foundation Models in HealthCare.
Expert‑curated healthcare corpus mapped to a living ontology, already packaged for immediate model ingestion and suitable for safe pre-training, evals, fine‑tuning and inference. If healthcare domain data is on your roadmap, this is a rare, defensible asset.
The article TITLE of each of the five Digital IP Asset Classes matched to AI Initiatives in Big Pharma, an article per IP Asset Class are:
  • AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class I: PharmaceuticalIntelligence.com Journal, 2.5MM Views, 6,250 Scientific articles and Live Ontology

https://pharmaceuticalintelligence.com/2025/11/22/ai-initiatives-in-big-pharma-grog-prompt-proprietary-data-training-and-inference-by-lpbi-groups-ip-asset-class-i-pharmaceuticalintelligence-com-journal-2-5mm-views-6250-scientific-article/

 

  • AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class II: 48 e-Books: English Edition & Spanish Edition. 152,000 pages downloaded under pay-per-view

https://pharmaceuticalintelligence.com/2025/11/22/ai-initiatives-in-big-pharma-grog-prompt-proprietary-training-data-and-inference-by-lpbi-groups-ip-asset-class-ii-48-e-books-english-edition-spanish-edition-152000/

 

  • AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class III: 100 e-Proceedings and 50 Tweet Collections of Top Biotech and Medical Global Conferences, 2013-2025

https://pharmaceuticalintelligence.com/2025/11/22/ai-initiatives-in-big-pharma-grog-prompt-proprietary-training-data-and-inference-by-lpbi-groups-ip-asset-class-iii-100-e-proceedings-and-50-tweet-collections-of-top-biotech/

 

  • AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class V: 7,500 Biological Images in LPBI Group’s Digital Art Media Gallery, as prior art

https://pharmaceuticalintelligence.com/2025/11/22/ai-initiatives-in-big-pharma-grog-prompt-proprietary-training-data-and-inference-by-lpbi-groups-ip-asset-class-v-7500-biological-images-in-lpbi-groups-digital-art/

 

  • AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class X: +300 Audio Podcasts Library: Interviews with Scientific Leaders

https://pharmaceuticalintelligence.com/2025/11/22/ai-initiatives-in-big-pharma-grog-prompt-proprietary-training-data-and-inference-by-lpbi-groups-ip-asset-class-x-300-audio-podcasts-library-interviews-with-scientific-leaders/

Conclusions by @Grok
Conclusions and Implications
LPBI Group’s IP Asset Class X: A Library of Podcasts are a “live repository” primed for Big Pharma AI, fueling from R&D reviews to global equity. Technical Implications: Enables auditory-multimodal models for diagnostics/education. Business Implications: Accelerates $500M ROI; licensing for partnerships. Unique Insight: As unscripted leader interviews, they provide a “verbal moat” in AI—completing series’ holistic pharma data ecosystem.Promotional with links to podcast library/IP portfolio. Synthesizes series by emphasizing auditory human-AI synergy.

In the series of five articles, as above, we are presenting the key AI Initiatives in Big Pharma as it was created by our prompt to @Grok on 11/18/2025:

  • What are PFIZER’s AI INITIATIVES?

@Grok Response:

x.com/i/grok/share/0ol5VOJsEYs11baXq4xkzNb0h

Generative AI tools that save scientists up to 16,000 hours annually in literature searches and data analysis.
Drug Discovery and Development Acceleration Pfizer uses AI, supercomputing, and ML to streamline R&D timelines
Clinical Trials and Regulatory Efficiency AI:

-Predictive Regulatory Tools

-Decentralize Trials

-inventory management

Disease Detection and Diagnostics:

–       ATTR-CM Initiative

–       Rare diseases

Generative AI and Operational Tools:

–       Charlie Platform

–       Scientific Data Cloud AWS powered ML on centralized data

–       Amazon’s SageMaker /Bedrock for Manufacturing efficiency

–       Global Health Grants:

Pfizer Foundation’s AI Learning Lab for equitable access to care and tools for community care

Partnerships and Education

–       Collaborations: IMI Big Picture for 3M – sample disease database

–       AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine

–       Webinars of AI for biomedical data integration

–       Webinar on AI in Manufacturing

Strategic Focus:

–       $500M R&D reinvestment by 2026 targets AI for Productivity

–       Part of $7.7B cost savings

–       Ethical AI, diverse DBs

–       Global biotech advances: China’s AI in CRISPR

 

  • AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class X: +300 Audio Podcasts Library: Interviews with Scientific Leaders

The Left Column was written @Grok

The Right Column was written by Aviva Lev-Ari, PhD, RN

 

AI Initiative at Big Pharma

i.e., Pfizer

Library of Audio and Video Podcasts

N = +300

Generative AI tools that save scientists up to 16,000 hours annually in literature searches and data analysis.
Drug Discovery and Development Acceleration Pfizer uses AI, supercomputing, and ML to streamline R&D timelines Review ALL SCIENTIFIC BREAKTHROUGHS
Clinical Trials and Regulatory Efficiency AI:

-Predictive Regulatory Tools

-Decentralize Trials

-inventory management

Disease Detection and Diagnostics:

–       ATTR-CM Initiative

–       Rare diseases

Generative AI and Operational Tools:

–       Charlie Platform

–       Scientific Data Cloud AWS powered ML on centralized data

–       Amazon’s SageMaker/Bedrock for Manufacturing efficiency

–       Global Health Grants:

Pfizer Foundation’s AI Learning Lab for equitable  access to care and tools for community care

Ingest to Charlie Platform all +300 Podcasts
Partnerships and Education

–       Collaborations: IMI Big Picture for 3M – sample disease database

–       AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine

–       Webinars of AI for biomedical data integration

–       Webinard on Ai in Manufacturing

Use Podcast for Education

Use Podcast as Hybrid: Start presentation with a Podcast continue with a life interview

Strategic Focus:

–       $500M R&D reinvestment by 2026 targets AI for Productivity

–       Part of $7.7B cost savings

–       Ethical AI, diverse DBs

–       Global biotech advances: China’s AI in CRISPR

 

CONCLUSIONS: The Voice of Dr. Stephen J. Williams PhD

PENDING

Article Summary by @Grok of the ArticleTitle:

AI Initiatives in Big Pharma @Grok prompt & Proprietary Training Data and Inference by LPBI Group’s IP Asset Class X: +300 Audio Podcasts Library: Interviews with Scientific Leaders

Publication Date: November 22, 2025

Author/Curator: Aviva Lev-Ari, PhD, RN
(Curator; Posted by 2012pharmaceutical)
@Grok SOURCE:

Overview: Final (fifth) in LPBI Group’s five-article series on AI-ready digital IP assets for pharma. This installment highlights IP Asset Class X—+300 audio podcasts of interviews with scientific leaders—as a proprietary, expert-curated auditory corpus for training and inference in healthcare AI models. Using a November 18, 2025, Grok prompt on Pfizer’s AI efforts, it maps the library to pharma applications, emphasizing audio ingestion for breakthroughs review, education, and platform integration. Unlike visual/text prior classes, this focuses on verbal expert insights for multimodal/hybrid AI, positioning them as a “rare, defensible” resource for ethical, diverse foundation models.
Main Thesis and Key Arguments

  • Core Idea: LPBI’s +300 podcasts capture unscripted scientific discourse from leaders, forming a live repository of domain knowledge ideal for AI ingestion—enhancing Big Pharma’s shift from generic to human-curated models for R&D acceleration and equitable care.
  • Value Proposition: Part of ten IP classes (five AI-ready: I, II, III, V, X); podcasts equivalent to $50MM value in series benchmarks, with living ontology for semantic mapping. Unique for hybrid uses (e.g., education starters) and safe pre-training/fine-tuning, contrasting open-source data with proprietary, ethical inputs.
  • Broader Context: Caps series by adding auditory depth to text/visual assets; supports Pfizer’s $500M AI reinvestment via productivity gains (e.g., 16,000 hours saved).

AI Initiatives in Big Pharma (Focus on Pfizer) Reuses Grok prompt highlights, presented in an integrated mapping table (verbatim):

AI Initiative at Big Pharma i.e., Pfizer
Description
Generative AI tools
Save scientists up to 16,000 hours annually in literature searches and data analysis.
Drug Discovery and Development Acceleration
Pfizer uses AI, supercomputing, and ML to streamline R&D timelines.
Clinical Trials and Regulatory Efficiency AI
Predictive Regulatory Tools; Decentralize Trials; Inventory management.
Disease Detection and Diagnostics
ATTR-CM Initiative; Rare diseases.
Generative AI and Operational Tools
Charlie Platform; Scientific Data Cloud AWS powered ML on centralized data; Amazon’s SageMaker/Bedrock for Manufacturing efficiency; Global Health Grants: Pfizer Foundation’s AI Learning Lab for equitable access to care and tools for community care.
Partnerships and Education
Collaborations: IMI Big Picture for 3M-sample disease database; AI in Pharma AIPM Symposium: Drug discovery and Precision Medicine; Webinars of AI for biomedical data integration; Webinar on AI in Manufacturing.
Strategic Focus
$500M R&D reinvestment by 2026 targets AI for Productivity; Part of $7.7B cost savings; Ethical AI, diverse DBs; Global biotech advances: China’s AI in CRISPR.
Mapping to LPBI’s Proprietary DataCore alignment table (verbatim extraction, linking Pfizer initiatives to Class X podcasts):
AI Initiative at Big Pharma i.e., Pfizer
Library of Audio and Video Podcasts N = +300
Generative AI tools (16,000 hours saved)
(No specific mapping provided.)
Drug Discovery and Development Acceleration
Review ALL SCIENTIFIC BREAKTHROUGHS.
Clinical Trials and Regulatory Efficiency
(No specific mapping provided.)
Disease Detection and Diagnostics (ATTR-CM, rare diseases)
(No specific mapping provided.)
Generative AI and Operational Tools (Charlie, AWS, etc.)
Ingest to Charlie Platform all +300 Podcasts.
Partnerships and Education (IMI, AIPM, webinars)
Use Podcast for Education; Use Podcast as Hybrid: Start presentation with a Podcast continue with a life interview.
Strategic Focus ($500M reinvestment, ethics)
(No specific mapping provided.)

Methodologies and Frameworks

  • AI Training Pipeline: Ingest audio into Charlie/AWS for pre-training (expert discourse corpus), fine-tuning (e.g., breakthrough reviews), and inference (e.g., educational hybrids). Use ontology for thematic mapping; Grok prompt for sourcing initiatives.
  • Productivity Model: Boosts Pfizer’s $7.7B savings via auditory data for diverse, ethical AI (e.g., Learning Lab grants); hybrid formats for webinars/symposia.
  • Insights: Quote from Dr. Stephen J. Williams, PhD: Assets as “codified digital treasures” for safe healthcare AI. Predicts revolution in verbal inference for precision medicine.

Conclusions and Implications

LPBI Group’s IP Asset Class X:
A Library of Podcasts are a “live repository” primed for Big Pharma AI, fueling from R&D reviews to global equity. Technical Implications: Enables auditory-multimodal models for diagnostics/education. Business Implications: Accelerates $500M ROI; licensing for partnerships. Unique Insight: As unscripted leader interviews, they provide a “verbal moat” in AI—completing series’ holistic pharma data ecosystem.Promotional with links to podcast library/IP portfolio. Synthesizes series by emphasizing auditory human-AI synergy.
@Grok was prompted to summarize the Table of Contents of the e-Book that present the Library of Podcast INDEX.

Overview of IP Asset Class X: +300 Audio Podcasts – Interviews with Scientific LeadersThe BioMed Audio Podcast Library from LPBI Group is a valuable intellectual property asset in the biomedical field, featuring over 301 audio podcasts created from interviews, curations, and discussions with prominent scientific leaders. This collection highlights breakthroughs in areas like genomics, cancer research, immunology, precision medicine, and public health policy. Curated by experts such as Aviva Lev-Ari, PhD, RN (197 podcasts), Larry H. Bernstein, MD, FCAP (48 podcasts), and Stephen J. Williams, PhD (38 podcasts), the library is organized into 21 thematic chapters for easy navigation.Key features include:

  • Search and Accessibility: Filter by chapter, curator, subject, or podcast ID. Each entry includes text-to-speech conversion and NLP-generated WordClouds for topic visualization.
  • Content Focus: Emphasizes Nobel laureates, key opinion leaders, and innovators discussing technologies like CRISPR-Cas9, mRNA vaccines, immunotherapy, and biotechnology ventures.
  • Format and Updates: Derived from articles on real-time events (e.g., COVID-19 impacts, award announcements). The library continues to expand, with no direct audio embeds—access via linked articles for full transcripts and playback.
  • Themes Covered: Public health policy, cardiovascular science, neuroscience, academic institutions, and more, with a strong emphasis on translational research and personalized medicine.

This asset represents a rich repository for researchers, students, and professionals seeking insights from leaders like Francis Collins, Jennifer Doudna, and Siddhartha Mukherjee.Selected Highlights by ChapterBelow are curated examples from key chapters, showcasing interviews with scientific leaders. For the full library (301+ entries), visit the source page.

Chapter 1: Public Health
Podcast ID
Curator
Title
Scientific Leader(s)
Brief Description
Link
17
Aviva Lev-Ari
LEADERS in Genome Sequencing of Genetic Mutations for Therapeutic Drug Selection in Cancer Personalized Treatment: Part 2
Leaders in genome sequencing
Explores genetic mutations’ role in personalized cancer therapies.
161
Aviva Lev-Ari
FDA Commissioner, Dr. Margaret A. Hamburg on HealthCare for 310Million Americans and the Role of Personalized Medicine
Dr. Margaret A. Hamburg
Discusses personalized medicine’s impact on U.S. healthcare policy.
273
Aviva Lev-Ari
Live Notes and Conference Coverage in Real Time. COVID19 And The Impact on Cancer Patients Town Hall with Leading Oncologists; April 4, 2020
Leading oncologists
Real-time analysis of COVID-19’s effects on cancer care.
Chapter: Genomics & Genome Biology
Podcast ID
Curator
Title
Scientific Leader(s)
Brief Description
Link
23
Aviva Lev-Ari
2013 Genomics: The Era Beyond the Sequencing of the Human Genome: Francis Collins, Craig Venter, Eric Lander, et al.
Francis Collins, Craig Venter, Eric Lander
Reflections on post-human genome sequencing advancements.
226
Aviva Lev-Ari

Dr. Jennifer Doudna (UC Berkeley): PMWC 2017 Luminary Award, January 22, 2017

@PMWC

2017

Jennifer Doudna (CRISPR pioneer)
Award speech on CRISPR’s applications in biomedicine.
288
Aviva Lev-Ari
Allon Klein, Harvard Medical School, and Aviv Regev, Genentech, Recipients of National Academy of Sciences James Prize…
Allon Klein, Aviv Regev
Integration of science and technology in genomics research.
Chapter: Precision Medicine & Cancer (35+ Entries)
Podcast ID
Curator
Title
Scientific Leader(s)
Brief Description
Link
15
Aviva Lev-Ari
Harnessing Personalized Medicine for Cancer Management, Prospects of Prevention and Cure: Opinions of Cancer Scientific Leaders
Cancer scientific leaders
Expert opinions on preventing and curing cancer via personalization.
12
Aviva Lev-Ari
The “Cancer establishments” examined by James Watson, co-discoverer of DNA w/Crick, 4/1953
James Watson (Nobel laureate)
Critique of cancer research institutions by DNA co-discoverer.
132
Aviva Lev-Ari
Practicing Oncology: Medscape Editor-in-Chief Eric J. Topol, MD interviews Siddhartha Mukherjee, MD, PhD
Siddhartha Mukherjee (interviewed by Eric J. Topol)
Insights into oncology practices and patient care.
102
Aviva Lev-Ari
Reuben Shaw, Ph.D., a geneticist and researcher at the Salk Institute: Metabolism Influences Cancer
Reuben Shaw, Ph.D.
How metabolism drives cancer progression.
209
Aviva Lev-Ari
Pioneers of Cancer Cell Therapy: Turbocharging the Immune System to Battle Cancer Cells…
Immunotherapy pioneers
Advances in CAR-T and immune-based cancer therapies.
This selection captures the library’s depth, blending historical perspectives (e.g., Watson) with cutting-edge topics (e.g., CRISPR, immunotherapy). For deeper dives, use the site’s search tools to explore chapters like Cardiovascular Science (36 podcasts) or Immunology.

Read Full Post »

Immuno-Timebombs: The Hidden Drivers of Age-Related Illness

Curator: Dr. Sudipta Saha, Ph. D.

 

There are two converging biological processes that drive most age-related diseases: immunosenescence and inflammaging. Together, they explain how a deteriorating immune system and chronic low-grade inflammation contribute to neurodegenerative diseases, cancer, cardiovascular disorders, and frailty.

Immunosenescence refers to the waning competence of both innate and adaptive immune systems. With age, T and B cells become less effective, and macrophage function declines. This makes older individuals more susceptible to infections and less efficient at clearing dysfunctional cells.

Inflammaging, on the other hand, is the persistent presence of inflammation without infection. Factors like gut microbiome alterations, senescent cell accumulation, and epigenetic drift contribute to this condition. Over time, this “silent fire” damages tissues and lays the groundwork for disease.

These drivers don’t just correlate with disease—they often precede it. This positions inflammaging and immunosenescence as targets for prevention, not just treatment. Interventions like exercise, caloric modulation, and anti-inflammatory diets may attenuate their effects. Emerging therapies such as senolytics and immune rejuvenation approaches (e.g., thymic regeneration) are showing promise.

This article also calls for a paradigm shift in medical science—from reactive disease management to proactive longevity interventions. As we unravel the biological clocks of aging, strategies targeting immune recalibration may delay or prevent multiple diseases simultaneously.

The future of healthy aging may well depend on how early we can intervene in this immuno-inflammatory loop—before pathology sets in.

References:

https://erictopol.substack.com/p/the-drivers-of-age-related-diseases

https://www.nature.com/articles/s41591-019-0661-0

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7761661

https://www.cell.com/fulltext/S0092-8674(19)30184-4

https://www.frontiersin.org/articles/10.3389/fimmu.2020.579220/full

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9649506

Read Full Post »

Unlocking the Secrets of Longevity: A 117-Year-Old Woman’s Genes Defied Aging

Curator: Dr. Sudipta Saha, Ph.D.

A recent study led by the University of Barcelona has shed light on the genetic factors contributing to exceptional human longevity. The research focused on Maria Branyas Morera, who was recognized as the world’s oldest living person until her passing at age 117 in August 2024. The findings revealed that her unique genetic makeup allowed her cells to function as if they were 17 years younger, and her gut microbiota resembled that of an infant.

Branyas Morera attributed her remarkable lifespan to “luck and good genetics.” Beyond her genetic advantages, she maintained a healthy lifestyle characterized by a Mediterranean diet, regular physical activity, and strong family bonds. These factors likely contributed to her prolonged cognitive clarity and minimal health issues, primarily limited to joint pain and hearing loss.

This study adds to a growing body of research exploring the genetic foundations of longevity. For instance, the Okinawa Centenarian Study has examined over 600 centenarians from Okinawa, Japan, uncovering genetic markers associated with extended lifespan and reduced incidence of age-related diseases.

Similarly, the New England Centenarian Study has identified specific genetic variations linked to longevity, providing insights into the biological mechanisms that allow some individuals to live significantly longer than average.

Researchers hope that understanding these genetic factors can inform the development of treatments for age-related diseases, challenging the notion that aging and illness are inextricably linked. By studying individuals like Branyas Morera, scientists aim to uncover strategies to promote healthier aging across the broader population.

However, it’s important to note that while genetics play a crucial role in exceptional longevity, lifestyle factors such as diet, exercise, and social connections also significantly impact overall health and lifespan. The interplay between genetic predisposition and environmental influences continues to be a critical area of research in understanding human aging.

References

https://www.theguardian.com/world/2025/mar/13/supercentenarian-aging-genes-study?CMP=oth_b-aplnews_d-1

https://www.theguardian.com/science/2024/oct/13/why-everything-you-think-about-living-to-100-might-be-wrong?utm_source=chatgpt.com

https://www.theguardian.com/commentisfree/2024/oct/13/good-news-everyone-we-appear-to-have-reached-peak-longevity?utm_source=chatgpt.com

Read Full Post »

Bipolar Disorder now understood by Markers Identified of the Gene Expression for this Diagnosis

Reporter: Aviva Lev-Ari, PhD, RN

Published: 

Amygdala and anterior cingulate transcriptomes from individuals with bipolar disorder reveal downregulated neuroimmune and synaptic pathways

Abstract

Recent genetic studies have identified variants associated with bipolar disorder (BD), but it remains unclear how brain gene expression is altered in BD and how genetic risk for BD may contribute to these alterations. Here, we obtained transcriptomes from subgenual anterior cingulate cortex and amygdala samples from post-mortem brains of individuals with BD and neurotypical controls, including 511 total samples from 295 unique donors. We examined differential gene expression between cases and controls and the transcriptional effects of BD-associated genetic variants. We found two coexpressed modules that were associated with transcriptional changes in BD: one enriched for immune and inflammatory genes and the other with genes related to the postsynaptic membrane. Over 50% of BD genome-wide significant loci contained significant expression quantitative trait loci (QTL) (eQTL), and these data converged on several individual genes, including SCN2A and GRIN2A. Thus, these data implicate specific genes and pathways that may contribute to the pathology of BP.

SOURCE

https://www.nature.com/articles/s41593-022-01024-6

Gene Expression Markers for Bipolar Disorder Pinpointed

The work was led by researchers at Johns Hopkins’ Lieber Institute for Brain Development. The findings, published this week in Nature Neuroscience, represent the first time that researchers have been able to apply large-scale genetic research to brain samples from hundreds of patients with bipolar disorder (BD). They used 511 total samples from 295 unique donors.

“This is the first deep dive into the molecular biology of the brain in people who died with bipolar disorder—studying actual genes, not urine, blood or skin samples,” said Thomas Hyde of the Lieber Institute and a lead author of the paper. “If we can figure out the mechanisms behind BD, if we can figure out what’s wrong in the brain, then we can begin to develop new targeted treatments of what has long been a mysterious condition.”

Bipolar disorder is characterized by extreme mood swings, with episodes of mania alternating with episodes of depression. It usually emerges in people in their 20s and 30s and remains with them for life. This condition affects approximately 2.8% of the adult American population, or about 7 million people. Patients face higher rates of suicide, poorer quality of life, and lower productivity than the general population. Some estimates put the annual cost of the condition in the U.S. alone at $219.1 billion.

While drugs can be useful in treating BD, many patients find they have bothersome side effects, and for some patients, current medications don’t work at all.

In this study, researchers measured levels of messenger RNA in the brain samples. They observed almost eight times more differentially expressed gene features in the sACC versus the amygdala, suggesting that the sACC may play an especially prominent role—both in mood regulation in general and BD specifically.

In patients who died with BD, the researchers found abnormalities in two families of genes: one containing genes related to the synapse and the second related to immune and inflammatory function.

“There finally is a study using modern technology and our current understanding of genetics to uncover how the brain is doing,” Hyde said. “We know that BD tends to run in families, and there is strong evidence that there are inherited genetic abnormalities that put an individual at risk for bipolar disorder. Unlike diseases such as sickle-cell anemia, bipolar disorder does not result from a single genetic abnormality. Rather, most patients have inherited a group of variants spread across a number of genes.”

“Bipolar disorder, also known as manic-depressive disorder, is a highly damaging and paradoxical condition,” said Daniel R. Weinberger, chief executive and director of the Lieber Institute and a co-author of the study. “It can make people very productive so they can lead countries and companies, but it can also hurl them into the meat grinder of dysfunction and depression. Patients with BD may live on two hours of sleep a night, saving the world with their abundance of energy, and then become so self-destructive that they spend their family’s fortune in a week and lose all friends as they spiral downward. Bipolar disorder also has some shared genetic links to other psychiatric disorders, such as schizophrenia, and is implicated in overuse of drugs and alcohol.”

Read Full Post »

Developing Deep Learning Models (DL) for the Instant Prediction of Patients with Epilepsy

Reporter: Srinivas Sriram, Research Assistant I
Research Team: Srinivas Sriram, Abhisar Anand

2021 LPBI Summer Intern in Data Science and Website Construction
This article reports on a research study conducted from January 2021 to May 2021.
This Research was completed before the 2021 LPBI Summer Internship that began on 6/15/2021.

The main criterion of this study was to utilize the dataset (shown above) to develop a DL network that could accurately predict new seizures based on incoming data. To begin the study, our research group did some exploratory data analysis on the dataset and we recognized the key defining pattern of the data that allowed for the development of the DL model. This pattern of the data can be represented in the graph above, where the lines representing seizure data had major spikes in extreme hertz values, while the lines representing normal patient data remained stable without any spikes. We utilized this pattern as a baseline for our model. 

Conclusions and Future Improvements:

Through our system, we were able to create a prototype solution that would predict when seizures happened in a potential patient using an accurate LSTM network and a reliable hardware system. This research can be implemented in hospitals with patients suffering from epilepsy in order to help them as soon as they experience a seizure to prevent damage. However, future improvements need to be made to this solution to allow it to be even more viable in the Healthcare Industry, which is listed below.

  • Needs to be implemented on a more reliable EEG headset (covers all neurons of the brain, less prone to electric disruptions shown in the prototype). 
  • Needs to be tested on live patients to deem whether the solution is viable and provides a potential solution to the problem. 
  • The network can always be fine-tuned to maximize performance. 
  • A better alert system can be implemented to provide as much help as possible. 

These improvements, when implemented, can help provide a real solution to one of the most common diseases faced in the world. 

Background Information:

Epilepsy is described as a brain disorder diagnostic category for multiple occurrences of seizures that happen within recurrent and/or a brief timespan. According to the World Health Organization, seizure disorders, including epilepsy, are among the most common neurological diseases. Those who suffer seizures have a 3 times higher risk of premature death. Epilepsy is often treatable, especially when physicians can provide necessary treatment quickly. When untreated, however, seizures can cause physical, psychological, and emotional, including isolation from others. Quick diagnosis and treatment prevent suffering and save lives. The importance of a quick diagnosis of epilepsy has led to our research team developing Deep Learning (DL) algorithms for the sole purpose of detecting epileptic seizures as soon as they occur. 

Throughout the years, one common means of detecting Epilepsy has emerged in the form of an electroencephalogram (EEG). EEGs can detect and compile “normal” and “abnormal “brain wave activity” and “indicate brain activity or inactivity that correlates with physical, emotional, and intellectual activities”. EEG waves are classified mainly by brain wave frequencies (EEG, 2020). The most commonly studied are delta, theta, alpha, sigma, and beta waves. Alpha waves, 8 to 12 hertz, are the key wave that occurs in normal awake people. They are the defining factor for the everyday function of the adult brain. Beta waves, 13 to 30 hertz, are the most common type of wave in both children and adults. They are found in the frontal and central areas of the brain and occur at a certain frequency which, if slow, is likely to cause dysfunction. Theta waves, 4 to 7 hertz, are also found in the front of the brain, but they slowly move backward as drowsiness increases and the brain enters the early stages of sleep. Theta waves are known as active during focal seizures. Delta waves, 0.5 to 4 hertz, are found in the frontal areas of the brain during deep sleep. Sigma waves, 12-16 hertz, are very slow frequency waves that occur during sleep. EEG detection of electrical brain wave frequencies can be used to detect and diagnose seizures based on their deviation from usual brain wave patterns.

In this particular research project, our research group hoped to develop a DL algorithm that when implemented on a live, portable EEG brain wave capturing device, could accurately predict when a particular patient was suffering from Epilepsy as soon as it occurred. This would be accomplished by creating a network that could detect when the brain frequencies deviated from the normal frequency ranges. 

The Study:

Line Graph representing EEG Brain Waves from a Seizure versus EEG Brain Waves from a normal individual. 

Source Dataset: https://archive.ics.uci.edu/ml/datasets/Epileptic+Seizure+Recognition

To expand more on the dataset, it is an EEG data set compiled by Qiuyi Wu and Ernest Fokoue (2021) from the work of medical researchers R.Andrzejak, M.D. et al. (2001) which had been made public domain through the UCI Machine Learning Repository We also confirmed fair use permission with UCI. The dataset had been gathered by Andrzejak during examinations of 500 patients with a chronic seizure disorder. R.G.Andrzejak, et al. (2001) recorded each entry in the EEG dataset used for this project within 23.6 seconds in a time-series data structure. Each row in the dataset represented a patient recorded. The continuous variables in the dataset were single EEG data points at that specific point in time during the measuring period. At the end of the dataset, was a y-variable that indicated whether or not the patient had a seizure during the period the data was recorded. The continuous variables, or the EEG data, for each patient, varied widely based on whether the patient was experiencing a seizure at that time. The Wu & Fokoue Dataset (2021) consists of one file of 11,500 rows, each with 178 sequential data points concatenated from the original dataset of 5 data folders, each including 100 files of EEG recordings of 23.6 seconds and containing 4097 data points. Each folder contained a single, original subset. Subset A contained EEG data gathering during epileptic seizure…. Subset B contained EEG data from brain tumor sites. Subset 3, from a healthy site where tumors had been located. Subsets 4 and 5 from non-seizure patients at rest with eyes open and closed, respectively. 

Based on the described data, our team recognized that a Recurrent Neural Network (RNN) was needed to input the sequential data and return an output of whether the sequential data was a seizure or not. However, we realized that RNN models are known to get substantially large over time, reducing computation speeds. To help provide a solution to this issue, our group decided to implement a long-short-term memory (LSTM) model. After deciding our model’s architecture, we proceeded to train our model in two different DL frameworks inside Python, TensorFlow, and PyTorch. Through various rounds of retesting and redesigning, we were able to train and develop two accurate models in each of the models that not only performed well while learning the data while training, but also could accurately predict new data in the testing set (98 percent accuracy on the unseen data). These LSTM networks could classify normal EEG data when the brain waves are normal, and then immediately predict the seizure data based on if a dramatic spike occurred in the data. 

After training our model, we had to implement our model in a real-life prototype scenario in which we utilized a Single Board Computer (SBC) in the Raspberry Pi 4 and a live capturing EEG headset in the Muse 2 Headband. The two hardware components would sync up through Bluetooth and the headband would return EEG data to the Raspberry Pi, which would process the data. Through the Muselsl API in Python, we were able to retrieve this EEG data in a format similar to the manner implemented during training. This new input data would be fed into our LSTM network (TensorFlow was chosen for the prototype due to its better performance than the PyTorch network), which would then output the result of the live captured EEG data in small intervals. This constant cycle would be able to accurately predict a seizure as soon as it occurs through batches of EEG data being fed into the LSTM network. Part of the reason why our research group chose the Muse Headband, in particular, was not only due to its compatibility with Python but also due to the fact that it was able to represent seizure data. Because none of our members had epilepsy, we had to find a reliable way of testing our model to make sure it worked on the new data. Through electrical disruptions in the wearable Muse Headband, we were able to simulate these seizures that worked with our network’s predictions. In our program, we implemented an alert system that would email the patient’s doctor as soon as a seizure was detected.

Individual wearing the Muse 2 Headband

Image Source: https://www.techguide.com.au/reviews/gadgets-reviews/muse-2-review-device-help-achieve-calm-meditation/

Sources Cited:

Wu, Q. & Fokoue, E. (2021).  Epileptic seizure recognition data set: Data folder & Data set description. UCI Machine Learning Repository: Epileptic Seizure Recognition. Jan. 30. Center for Machine Learning and Intelligent Systems, University of California Irvine.

Nayak, C. S. (2020). EEG normal waveforms.” StatPearls [Internet]. U.S. National Library of Medicine, 31 Jul. 2020, www.ncbi.nlm.nih.gov/books/NBK539805/#.

Epilepsy. (2019). World Health Organization Fact Sheet. Jun. https://www.who.int/ news-room/fact-sheet s/detail/epilepsy

Other Related Articles published in this Open Access Online Scientific Journal include the following:

Developing Deep Learning Models (DL) for Classifying Emotions through Brainwaves

Reporter: Abhisar Anand, Research Assistant I

https://pharmaceuticalintelligence.com/2021/06/22/developing-deep-learning-models-dl-for-classifying-emotions-through-brainwaves/

Machine Learning (ML) in cancer prognosis prediction helps the researcher to identify multiple known as well as candidate cancer diver genes

Curator and Reporter: Dr. Premalata Pati, Ph.D., Postdoc

https://pharmaceuticalintelligence.com/2021/05/04/machine-learning-ml-in-cancer-prognosis-prediction-helps-the-researcher-to-identify-multiple-known-as-well-as-candidate-cancer-diver-genes/

Deep Learning-Assisted Diagnosis of Cerebral Aneurysms

Reporter: Dror Nir, PhD

https://pharmaceuticalintelligence.com/2019/06/09/deep-learning-assisted-diagnosis-of-cerebral-aneurysms/

Developing Machine Learning Models for Prediction of Onset of Type-2 Diabetes

Reporter: Amandeep Kaur, B.Sc., M.Sc.

https://pharmaceuticalintelligence.com/2021/05/29/developing-machine-learning-models-for-prediction-of-onset-of-type-2-diabetes/

Deep Learning extracts Histopathological Patterns and accurately discriminates 28 Cancer and 14 Normal Tissue Types: Pan-cancer Computational Histopathology Analysis

Reporter: Aviva Lev-Ari, PhD, RN

https://pharmaceuticalintelligence.com/2019/10/28/deep-learning-extracts-histopathological-patterns-and-accurately-discriminates-28-cancer-and-14-normal-tissue-types-pan-cancer-computational-histopathology-analysis/

A new treatment for depression and epilepsy – Approval of external Trigeminal Nerve Stimulation (eTNS) in Europe

Reporter: Howard Donohue, PhD (EAW)

https://pharmaceuticalintelligence.com/2012/10/07/a-new-treatment-for-depression-and-epilepsy-approval-of-external-trigeminal-nerve-stimulation-etns-in-europe/

Mutations in a Sodium-gated Potassium Channel Subunit Gene related to a subset of severe Nocturnal Frontal Lobe Epilepsy

Reporter: Aviva Lev-Ari, PhD, RN

https://pharmaceuticalintelligence.com/2012/10/22/mutations-in-a-sodium-gated-potassium-channel-subunit-gene-to-a-subset-of-severe-nocturnal-frontal-lobe-epilepsy/

Read Full Post »

Developing Deep Learning Models (DL) for Classifying Emotions through Brainwaves

Reporter: Abhisar Anand, Research Assistant I
Research Team: Abhisar Anand, Srinivas Sriram

2021 LPBI Summer Internship in Data Science and Website construction.
This article reports on a research study conducted till December 2020.
Research completed before the 2021 LPBI Summer Internship began in 6/15/2021.

As the field of Artificial Intelligence progresses, various algorithms have been implemented by researchers to classify emotions from EEG signals. Few researchers from China and Singapore released a paper (“An Investigation of Deep Learning Models from EEG-Based Emotion Recognition”) analyzing different types of DL model architectures such as deep neural networks (DNN), convolutional neural networks (CNN), long short-term memory (LSTM), and a hybrid of CNN and LSTM (CNN-LSTM). The dataset used in this investigation was the DEAP Dataset which consisted of EEG signals of patients that watched 40 one-minute long music videos and then rated them in terms of the levels of arousal, valence, like/dislike, dominance and familiarity. The result of the investigation presented that CNN (90.12%) and CNN-LSTM (94.7%) models had the highest performance out of the batch of DL models. On the other hand, the DNN model had a very fast training speed but was not able to perform as accurately as other other models. The LSTM model was also not able to perform accurately and the training speed was much slower as it was difficult to achieve convergence.

This research in the various model architectures provides a sense of what the future of Emotion Classification with AI holds. These Deep Learning models can be implemented in a variety of different scenarios across the world, all to help with detecting emotions in scenarios where it may be difficult to do so. However, there needs to be more research implemented in the model training aspect to ensure the accuracy of the classification is top-notch. Along with that, newer and more reliable hardware can be implemented in society to provide an easy-to-access and portable EEG collection device that can be used in any different scenario across the world. Overall, although future improvements need to be implemented, the future of making sure that emotions are accurately detected in all people is starting to look a lot brighter thanks to the innovation of AI in the neuroscience field.

Emotions are a key factor in any person’s day to day life. Most of the time, we as humans can detect these emotions through physical cues such as movements, facial expressions, and tone of voice. However, in certain individuals, it can be hard to identify their emotions through their visible physical cues. Recent studies in the Machine Learning and AI field provide a particular development in the ability to detect emotions through brainwaves, more specifically EEG brainwaves. These researchers from across the world utilize the same concept of EEG implemented in AI to help predict the state an individual is in at any given moment.

Emotion classification based on brain wave: a survey (Figure 4)

Image Source: https://hcis-journal.springeropen.com/articles/10.1186/s13673-019-0201-x

EEGs can detect and compile normal and abnormal brain wave activity and indicate brain activity or inactivity that correlates with physical, emotional, and intellectual activities. EEG signals are classified mainly by brain wave frequencies. The most commonly studied are delta, theta, alpha, sigma, and beta waves. Alpha waves, 8 to 12 hertz, are the key wave that occurs in normal awake people. They are the defining factor for the everyday function of the adult brain. Beta waves, 13 to 30 hertz, are the most common type of wave in both children and adults. They are found in the frontal and central areas of the brain and occur at a certain frequency which, if slowed, is likely to cause dysfunction. Theta waves, 4 to 7 hertz, are also found in the front of the brain, but they slowly move backward as drowsiness increases and the brain enters the early stages of sleep. Theta waves are known as active during focal seizures. Delta waves, 0.5 to 4 hertz, are found in the frontal areas of the brain during deep sleep. Sigma waves, 12-16 hertz, are very slow frequency waves that occur during sleep. These EEG signals can help for the detection of emotions based on the frequencies that the signals happen in and the activity of the signals (whether they are active or relatively calm). 

Sources:

Zhang, Yaqing, et al. “An Investigation of Deep Learning Models for EEG-Based Emotion Recognition.” Frontiers in Neuroscience, vol. 14, 2020. Crossref, doi:10.3389/fnins.2020.622759.

Nayak, Anilkumar, Chetan, Arayamparambil. “EEG Normal Waveforms.” National Center for Biotechnology Information, StatPearls Publishing LLC., 4 May 2021, http://www.ncbi.nlm.nih.gov/books/NBK539805.

Other related articles published in this Open Access Online Scientific Journal include the Following:

Supporting the elderly: A caring robot with ‘emotions’ and memory
Reporter: Aviva Lev-Ari, PhD, RN
https://pharmaceuticalintelligence.com/2015/02/10/supporting-the-elderly-a-caring-robot-with-emotions-and-memory/

Developing Deep Learning Models (DL) for the Instant Prediction of Patients with Epilepsy
Reporter: Srinivas Sriram, Research Assistant I
https://pharmaceuticalintelligence.com/2021/06/22/developing-deep-learning-models-dl-for-the-instant-prediction-of-patients-with-epilepsy/

Prediction of Cardiovascular Risk by Machine Learning (ML) Algorithm: Best performing algorithm by predictive capacity had area under the ROC curve (AUC) scores: 1st, quadratic discriminant analysis; 2nd, NaiveBayes and 3rd, neural networks, far exceeding the conventional risk-scaling methods in Clinical Use
Curator: Aviva Lev-Ari, PhD, RN
https://pharmaceuticalintelligence.com/2019/07/04/prediction-of-cardiovascular-risk-by-machine-learning-ml-algorithm-best-performing-algorithm-by-predictive-capacity-had-area-under-the-roc-curve-auc-scores-1st-quadratic-discriminant-analysis/

Developing Machine Learning Models for Prediction of Onset of Type-2 Diabetes
Reporter: Amandeep Kaur, B.Sc., M.Sc.
https://pharmaceuticalintelligence.com/2021/05/29/developing-machine-learning-models-for-prediction-of-onset-of-type-2-diabetes/

Deep Learning-Assisted Diagnosis of Cerebral Aneurysms
Reporter: Dror Nir, PhD
https://pharmaceuticalintelligence.com/2019/06/09/deep-learning-assisted-diagnosis-of-cerebral-aneurysms/

Mutations in a Sodium-gated Potassium Channel Subunit Gene related to a subset of severe Nocturnal Frontal Lobe Epilepsy
Reporter: Aviva Lev-Ari, PhD, RN
https://pharmaceuticalintelligence.com/2012/10/22/mutations-in-a-sodium-gated-potassium-channel-subunit-gene-to-a-subset-of-severe-nocturnal-frontal-lobe-epilepsy/

A new treatment for depression and epilepsy – Approval of external Trigeminal Nerve Stimulation (eTNS) in Europe
Reporter: Howard Donohue, PhD (EAW)
https://pharmaceuticalintelligence.com/2012/10/07/a-new-treatment-for-depression-and-epilepsy-approval-of-external-trigeminal-nerve-stimulation-etns-in-europe/

Read Full Post »

Contribution of Nervous System Functional Deterioration to late-life Mortality: The Role Neurofilament light chain (NfL) a Blood Biomarker for the Progression of Neurological Diseases and its Correlation to Age and Life Expectancy

 

Reporter: Aviva Lev-Ati, PhD, RN

 

A neuronal blood marker is associated with mortality in old age

Abstract

Neurofilament light chain (NfL) has emerged as a promising blood biomarker for the progression of various neurological diseases. NfL is a structural protein of nerve cells, and elevated NfL levels in blood are thought to mirror damage to the nervous system. We find that plasma NfL levels increase in humans with age (n = 122; 21–107 years of age) and correlate with changes in other plasma proteins linked to neural pathways. In centenarians (n = 135), plasma NfL levels are associated with mortality equally or better than previously described multi-item scales of cognitive or physical functioning, and this observation was replicated in an independent cohort of nonagenarians (n = 180). Plasma NfL levels also increase in aging mice (n = 114; 2–30 months of age), and dietary restriction, a paradigm that extends lifespan in mice, attenuates the age-related increase in plasma NfL levels. These observations suggest a contribution of nervous system functional deterioration to late-life mortality.

SOURCE

How long will a healthy older person live? A substance in blood may provide a clue

Levels of a substance in nonagenerians’ and centenarians’ blood accurately predict how much longer they’re going to live. The substance comes from the brain.

The findings, in a study published in Nature Aging, could prove useful in developing life-extending drugs. They also raise questions about the brain’s role in aging and longevity.

The study, conducted by Stanford investigators including neuroscientist Tony Wyss-Coray, PhD, in collaboration with researchers in Denmark and Germany, zeroed in on a substance whose technical name is neurofilament light chain (abbreviated NfL). A structural protein produced in the brain, NfL is found in trace amounts in cerebrospinal fluids and blood, where it’s an indicator of damage to long extensions of nerve cells called axons.

Axons convey signals from one nerve cell to the next and are critical to all brain function. You’d rather they remain intact.

Too much NfL (different from the NFL)

High NfL levels in the blood have previously been associated with Alzheimer’s disease, multiple sclerosis, Huntington’s disease, amyotrophic lateral sclerosis (Lou Gehrig’s disease) and other neurological disorders. But the people monitored in the new study were generally pretty healthy for their age.

The researchers first looked at 122 people whose ages ranged from 21 to 107, and found increasing blood levels of NfL — as well as increasing variation among individuals — with increasing age.

Next, the scientists followed the fates of 135 people age 100 or over for a four-year period. Most of those centenarians were in good shape to begin with, as shown by their performance on standard tests of mental ability and by a measure of their capacity to meet the routine demands of daily living.

Not unexpectedly, those whose mental tests indicated impairment had more NfL in their blood than those with the sharpest minds did. And those with low levels were substantially likelier to live longer than those with high levels.

A look at people in their 90s confirmed the findings in the over-100 group. Blood NfL levels among 180 93-year-olds not only predicted the duration of these folks’ survival, but did so better than mental or daily-coping test scores did.

The investigators showed that mice’s blood NfL levels, too, increase with age. But cutting their caloric intake, beginning in young adulthood — already known to prolong the lives of mice and numerous other species — chopped the little creatures’ blood levels of this substance in half in old age. (This new finding doesn’t prove that lowering NfL blood levels causes increased longevity, but it’s consistent with it.)

Tie to life expectancy?

At a minimum, NfL appears to accurately flag mortality’s approach. That means it might be possible to monitor it as a surrogate marker for remaining life expectancy, much as blood cholesterol levels are used as proxies for cardiovascular health. If so, it could someday help drug developers assess life-extending interventions’ efficacy.

Clinical trials of interventions believed to enhance longevity have been impractical, because it would almost certainly take so long to get a statistically significant result that such trials would be hugely expensive — a major hang-up for pharmas considering investment in longevity drugs. But monitoring a proxy such as NfL could cut years off of such trials’ duration, perhaps encouraging drug developers to dive into the clinical arena with life-prolonging pharmacological candidates.

Possibly most intriguing of all: The new findings hint that maintaining a healthy brain in old age is the best route to a long life.

“It will be interesting to see how and why the brain might be so important in counting down our final years and months,” Wyss-Coray told me.

Photo by Pablo Bendandi

Read Full Post »

Reporter: Adina Hazan, PhD

Elizabeth Unger from the Tian group at UC Davis, Jacob Keller from the Looger lab from HHMI, Michael Altermatt from the Gradinaru group at California Institute of Technology, and colleagues did just this, by redesigned the binding pocket of periplasmic binding proteins (PBPs) using artificial intelligence, such that it became a fluorescent sensor specific for serotonin. Not only this, the group showed that it could express and use this molecule to detect serotonin on the cell, tissue, and whole animal level.

By starting with a microbial PBP and early version of an acetyl choline sensor (iAChSnFR), the scientists used machine learning and modeling to redesign the binding site to exhibit a higher affinity and specificity to serotonin. After three repeats of mutagenesis, modeling, and library readouts, they produced iSeroSnFR. This version harbors 19 mutations compared to iAChSnFR0.6 and a Kd of 310 µM. This results in an increase in fluorescence in HEK293T cells expressing the serotonin receptor of 800%. Of over 40 neurotransmitters, amino acids, and small molecules screened, only two endogenous molecules evoked some fluorescence, but at significantly higher concentrations.

To acutely test the ability of the sensor to detect rapid changes of serotonin in the environment, the researchers used caged serotonin, a technique in which the serotonin is rapidly released into the environment with light pulses, and showed that iSeroSnFR accurately and robustly produced a signal with each flash of light. With this tool, it was then possible to move to ex-vivo mouse brain slices and detect endogenous serotonin release patterns across the brain. Three weeks after targeted injection of iSeroSnFR to specifically deliver the receptor into the prefrontal cortex and dorsal striatum, strong fluorescent signal could be detected during perfusion of serotonin or electrical stimulation.

Most significantly, this molecule was also shown to be detected in freely moving mice, a tool which could offer critical insight into the acute role of serotonin regulation during important functions such as mood and alertness. Through optical fiber placements in the basolateral amygdala and prefrontal cortex, the team measured dynamic and real-time changes in serotonin release in fear-trained mice, social interactions, and sleep wake cycles. For example, while both areas of the brain have been established as relevant to the fear response, they reliably tracked that the PFC response was immediate, while the BSA displayed a delayed response. This additional temporal resolution of neuromodulation may have important implications in neurotransmitter pharmacology of the central nervous system.

This study provided the scientific community with several insights and tools. The serotonin sensor itself will be a critical tool in the study of the central nervous system and possibly beyond. Additionally, an AI approach to mutagenesis in order to redesign a binding pocket of a receptor opens new avenues to the development of pharmacological tools and may lead to many new designs in therapeutics and research.

SOURCE:

Read Full Post »

Sleep Deprivation Death Linked Causally to the Gut

Reporter : Irina Robu, PhD

Neuroscientists at Harvard Medical School identified an unexpected link between sleep deprivation and premature death. Their findings show that the possibility that animals might be able to survive without sleep, under certain circumstances. Their study with sleep-deprived fruit flies found that death was continuously by the accumulation of reactive oxidative species in the gut. And when the flies were given antioxidant compounds that neutralized and cleared ROS from the gut, the sleep-deprived animals remained active and had normal lifespans. Extra experiments in mice confirmed that ROS accumulated in the gut when they didn’t get enough sleep.

Yet, in spite of decades of study, researchers still haven’t revealed why animals die when they don’t sleep. In attempts to answer how sleep deprivation culminates in death, most research has focused on the brain, where sleep originates. However, studies have yet to yield conclusive results. In addition to impairing cognition, sleep loss leads to dysfunction of the gastrointestinal, immune, metabolic, and circulatory systems.

The Harvard Medical School team carried out a sequence of experiments in fruit flies to search throughout the body for signs of damage caused by sleep deprivation. Fruit flies share many sleep-regulating genes with humans. To screen sleep, the investigators used infrared beams to constantly track the movement of flies housed in individual tubes. Scientist show that flies can sleep through physical shaking, so they genetically manipulated fruit flies to express a heat-sensitive protein in specific neurons, the activity of which are known to suppress sleep. When flies were housed at 29°C the protein induced neurons to remain constantly active, thus preventing the flies from sleeping.

The scientists discovered that fruit fly mortality spiked after 10 days of temperature-induced sleep deprivation and all of the flies died by around day 20 and control flies that had normal sleep lived up to approximately 40 days in the same environmental conditions. Since mortality increased around day 10, the scientists looked for markers of cell damage on that and the preceding days. They noticed that the guts of sleep-deprived flies had a dramatic build-up of ROS. The buildup of ROS in the fruit fly guts peaked around day 10 of sleep deprivation, and when deprivation was stopped, ROS levels decreased.

To find out if ROS in the gut plays a causal role in sleep deprivation-induced death, the researchers next looked at whether preventing ROS accumulation could prolong survival. They tested dozens of compounds with antioxidant properties known to neutralize ROS and identified 11 that, when given as a food supplement, allowed sleep-deprived flies to have a normal or near-normal lifespan. These compounds, such as melatonin, lipoic acid, and NAD, were particularly effective at clearing ROS from the gut. Notably, the supplements did not extend the lifespan of non-sleep-deprived flies.

The role of ROS removal in preventing death was also confirmed by experiments in which flies were genetically manipulated to overproduce antioxidant enzymes in their guts. These flies had normal to near-normal lifespans when sleep deprived, but flies that overproduced antioxidant enzymes in their nervous systems weren’t protected from sleep-deprivation-related death. While the results demonstrated that ROS build up in the gut plays a central role in causing premature death from sleep deprivation, the researchers acknowledged that many questions are still without answers. At the same time, they found that insufficient sleep is identified to restrict with the body’s hunger signaling pathways, which lead to measure the fruit fly food intake to analyze whether there were potential associations between feeding and death. They found that some sleep-deprived flies ate more throughout the day compared with non-deprived controls.

The researchers are now working to identify the biological pathways that lead to ROS accumulation in the gut and subsequent physiological disruptions.

SOURCE

Death Due to Sleep Deprivation Linked Causally to the Gut, and is Preventable in Flies

 

Read Full Post »

Reporter and Curator: Dr. Sudipta Saha, Ph.D.

 

Parkinson’s Disease (PD), characterized by both motor and non-motor system pathology, is a common neurodegenerative disorder affecting about 1% of the population over age 60. Its prevalence presents an increasing social burden as the population ages. Since its introduction in the 1960’s, dopamine (DA)-replacement therapy (e.g., L-DOPA) has remained the gold standard treatment. While improving PD patients’ quality of life, the effects of treatment fade with disease progression and prolonged usage of these medications often (>80%) results in side effects including dyskinesias and motor fluctuations. Since the selective degeneration of A9 mDA neurons (mDANs) in the substantia nigra (SN) is a key pathological feature of the disease and is directly associated with the cardinal motor symptoms, dopaminergic cell transplantation has been proposed as a therapeutic strategy.

 

Researchers showed that mammalian fibroblasts can be converted into embryonic stem cell (ESC)-like induced pluripotent stem cells (iPSCs) by introducing four transcription factors i.e., Oct4, Sox2, Klf4, and c-Myc. This was then accomplished with human somatic cells, reprogramming them into human iPSCs (hiPSCs), offering the possibility of generating patient-specific stem cells. There are several major barriers to implementation of hiPSC-based cell therapy for PD. First, probably due to the limited understanding of the reprogramming process, wide variability exists between the differentiation potential of individual hiPSC lines. Second, the safety of hiPSC-based cell therapy has yet to be fully established. In particular, since any hiPSCs that remain undifferentiated or bear sub-clonal tumorigenic mutations have neoplastic potential, it is critical to eliminate completely such cells from a therapeutic product.

 

In the present study the researchers established human induced pluripotent stem cell (hiPSC)-based autologous cell therapy. Researchers reported a platform of core techniques for the production of mDA progenitors as a safe and effective therapeutic product. First, by combining metabolism-regulating microRNAs with reprogramming factors, a method was developed to more efficiently generate clinical grade iPSCs, as evidenced by genomic integrity and unbiased pluripotent potential. Second, a “spotting”-based in vitro differentiation methodology was established to generate functional and healthy mDA cells in a scalable manner. Third, a chemical method was developed that safely eliminates undifferentiated cells from the final product. Dopaminergic cells thus produced can express high levels of characteristic mDA markers, produce and secrete dopamine, and exhibit electrophysiological features typical of mDA cells. Transplantation of these cells into rodent models of PD robustly restored motor dysfunction and reinnervated host brain, while showing no evidence of tumor formation or redistribution of the implanted cells.

 

Together these results supported the promise of these techniques to provide clinically applicable personalized autologous cell therapy for PD. It was recognized by researchers that this methodology is likely to be more costly in dollars and manpower than techniques using off-the-shelf methods and allogenic cell lines. Nevertheless, the cost for autologous cell therapy may be expected to decrease steadily with technological refinement and automation. Given the significant advantages inherent in a cell source free of ethical concerns and with the potential to obviate the need for immunosuppression, with its attendant costs and dangers, it was proposed that this platform is suitable for the successful implementation of human personalized autologous cell therapy for PD.

 

References:

 

https://www.jci.org/articles/view/130767/pdf?elqTrackId=2fd7d0edee744f9cb6d70a686d7b273b

 

https://www.ncbi.nlm.nih.gov/pubmed/31714896

 

https://www.ncbi.nlm.nih.gov/pubmed/23666606

 

https://www.ncbi.nlm.nih.gov/pubmed/27343168

 

https://www.ncbi.nlm.nih.gov/pubmed/21495962

 

https://www.ncbi.nlm.nih.gov/pubmed/28083784

 

https://www.ncbi.nlm.nih.gov/pubmed/20336395

 

https://www.ncbi.nlm.nih.gov/pubmed/28585381

 

Read Full Post »

Older Posts »