This Summer we have four projects assigned to 3 Summer Interns
PERSONAL PAGES FOR 2021 Summer Interns
- Ethan Coomber, Research Assistant III, Data Science and Podcast Library Development
- Srinivas Sriram, Research Assistant I
- Abhisar Anand, Research Assistant I
Project #1: Development of a Podcast Library for +280 Interviews with Scientific Leaders
Skills to be acquired:
- Conversion of Text to Audio
- Classification of +280 domains of knowledge
Project #2: Updates to Twitter Analytics for two Twitter handles:
@pharma_BI – The official Twitter account of LPBI Group
@AVIVA1950 – The Twitter handle of LPBI Group’s Founder
Skills to be acquired:
- Writing Python code for data extraction from Twitter Analytics records
- Statistical modeling of extracted data on +1,000 Twitter followers
- Generation of visualization for the Twitter Analytics data
These two projects are assigned to:
Ethan Coomber, Research Assistant III, Data Science and Podcast Library Development
Project #3: Extraction of ~2MM views of +6,000 scientific journal articles, 4/2012 to Present per article per Years since publication date
Skills to be acquired:
- Writing Python code for data extraction from WordPress.com records
- Data segmentation by time intervals
- Data export to Excel File with N sheets, one per time interval
Project #4: Selection of five Themes for a new website under WordPress.com for the BioMed e-Series translated into Spanish
Skills to be acquired:
- Website Theme selection of five out of 40
- Development of recommendation criteria for final selection of one out of five Website Themes
- Customize all the features offered under WoedPress.com
- Migrate the site structure of https://pharmaceuticalintelligence.com/biomed-e-books/
- To the New Website following customization of all features
- Develop a Content Promotion campaign for Twitter, Facebook and LinkedIn
These two Projects are assigned to:
Abhisar Anand, Research Assistant I
https://pharmaceuticalintelligence.com/contributors-biographies/research-assistants/abhisar-anand-research-assistant-i/
and
Srinivas Sriram, Research Assistant I
https://pharmaceuticalintelligence.com/contributors-biographies/research-assistants/srinivas-sriram-research-assistant-i/
For Future Summers you wish to consider the following two. I have written Letter of Recommendation to both to one of our INTERNS pursuing with us a One year Program in NLP applied to Medical Text Analysis
The Anson L. Clark Scholars Program
- Applicants must be 17 years of age by the program start date, and should graduate in 2021 or 2022.
- NO EXCEPTIONS – Emails requesting exceptions will not be answered.
https://www.depts.ttu.edu/honors/academicsandenrichment/affiliatedandhighschool/clarks/
RSI Research
when it will open again for The RSI 2022 or 2023 applications
https://www.cee.org/programs/apply-rsi
@@@@@@@@@@
2020
2020 Summer Internship on Data Curation and Data Annotation for Text Analysis by
NLP, ML, AI Algorithms
This is LPBI’s PORTAL for 2020 SUMMER INTERNSHIP
Program on
Data Curation and Data Annotation for
Text Analysis by NLP, ML, AI Algorithms
ZOOM for LPBI’s 2020 Summer Internship
EVERY WEEK Tuesday 6/23 to 8/11/2020
FIRST Presentation by Aviva Lev-Ari on 6/23/2020
Please click this URL to start your Zoom meeting
https://us02web.zoom.us/j/83920004499?pwd=Slk3ZExiT3FKNk90M0pSK1lYYVcxZz09
2020 LPBI Summer Interns
June 16, 2020 to August 11, 2020
Team Captain:
Team Captain Corner – Updates and Instructions for 2020 Summer Interns
7/29/2020
For 8/4/2020 meeting:
In the words of Dr. Ofer:
I suggest you interns will do a short review of all new platforms in AI and data science to figure out our position in the developing AI world pyramide.
eghttps://www.predictiveanalyticstoday.com/artificial-intelligence-platforms/the assignment is searching tool and packages
Meeting Outline
- Panel
- Higher level understanding in the service of meaning:
- Glossaries
- Dictionaries
- Relatedness tables/matrices
- ‘Chains of relatedness’
- Company/Manufacturers: Teva, BMS, GSK
- Enzyme – enzymatic – enzymology – enzyme-related – substrate
- Other topics:
- Other directions for word clouds
- Field – topic – area – #word tags
- Word-relatedness, repeats, word orders, distances of important words
- Classifications: sci units, proverbs
- For academic papers:
- Text mining references vs. abstracts
- Introduction/references/methods vs. conclusions, results
- Higher level understanding in the service of meaning:
7/21/2020
Hi All,
Here are instructions from Dr. Ofer for Assignment 5. Please complete this assignment following our meeting today.
1. prepare a story board of TP and LPBI relations. the story board should include:
a. idea of how the collaboration will work.
b. What would each bring and do
c. what benefit would it bring the world?
d. what benefit would it bring our clients (different?)
e. Examples (one to three)
remmember story board not presentation, be bold
you can use other peoples visuals using a link or putting in a visual
you are only given 250 words to explain your story board.
prepare your best word cloud out of it and attach to your storyboard
2. Write on two Ideas you decided not to pursue one you still think may be interesting and one that you thought and decided its not as good and why?
prepare a good word cloud out of them
7/1/2020
Hi everyone,
Here are instructions for Assignment 2.
NEW DUE DATE for ASSIGNMENT 2 Submission is July 10, 2020
The goal of this assignment is to compile a list of mutations which lead to the development of cancer, and cause it to progress further. I would like you to first review this Zoom tutorial before moving any further.
https://drive.google.com/file/d/1fdU-B7YuOFsMg3INoQBGKAgzR8FRmKv5/view?usp=sharing
- The filter function is to be used to find all articles related to your cancer type which have information about genetic mutations. In the Zoom tutorial, I have shown you how to use this tool. Here is an example.
- Say our topic includes blood cancers. There are four keywords we would like to use: mutation, change, alteration, and transformation. First we open the filter tool and we do a search for all titles containing “mutation” and “leukemia.”
- Now we copy the names of these articles and paste them into a new Excel spreadsheet (be sure to highlight the appropriate region for you to be able to paste the article info).
- Now we do the same thing for “mutation” and “lymphoma,” and repeat point 2.
- Repeat this process for change, alteration, and transformation (if you only have one single cancer keyword then you will only need to do 4 searches).
- Once you have compiled a list of articles please use the Ctrl+F function to search for relevant keywords including ALL of the ones above. Gene names will pop out at you. They will consist of a seemingly random string of letters and numbers, sometimes including Greek letters. In the Excel document, next to the article name, write a comma separated list of genetic mutations. PLEASE REMEMBER: We are only looking for mutations associated with the development and progression of cancer.
- Lastly, please elaborate on 3 of the mutations you have found and write a 1/2 page summary of each.
- Note: Please review all articles with row numbers highlighted in blue. Copy enough words from the beginning of each title to ensure that you will get meaningful search results. If you don’t get any search hits, then use less words. Please do not hesitate to contact me if you have any questions.
For those with issues using this method:
- If you do not find any articles then please go to Google and then use this template to conduct a search, “my cancer type” + “gene mutations.” For example – “lung cancer gene mutations.”
- Now go back to our journal and do this for each individual gene ID. Add all of the names of articles that contain this word (in the search results) to the Excel list, and in the column next to it list the gene ID.
- If an article name appears multiple times in your Excel sheet then combine all the mutations using commas in one cell and get rid of the extra instances of the article name on the spreadsheet.
Thank you,
Daniel Menzin
ROSTER for 2020 Summer Internship on Data Curation and Data Annotation
for application of NLP, ML, AI on Genomics and on Cancer TEXT subjected to
Computerized Text Analysis
Date | Presenter(s) | Content |
Assignment Due |
6/16/2020 | Kick-Off – LPBI Team & Summer Interns | ||
Session #1: 6/23/2020 | Aviva | Mini Curation | 6/23/20202
SEE DETAILS https://pharmaceuticalintelligence.com/2020-summer-internship/ |
Session #2
6/30/2020 | Dr. Williams and Dr. Irina | Three Types of Cancer
______________ | Prepare and present ONE assignment that each Student will apply on HIS CANCER TYPE OF CHOICE
NEW DUE DATE for ASSIGNMENT 2 Submission is July 10, 2020 |
Session #3:
7/7/2020 | Ofer Markman, PhD | · words
· Text processing · Meaning · Text as strings · Punctuation · Thesaurus how its translated to computer language. · Dictionary ______________ | https://pharmaceuticalintelligence.com/2020-summer-internship/
SEE DETAILS Assignment #3 is DUE on week after July 10, 2020 which is the DUE date for Assignment #2 |
Session #4:
7/14/2020 | Ofer Markman, PhD | Meaning: top down
workshop | within the workshop and through the week
slide 12-14 |
Session #5:
7/21/2020 | Ofer Markman, PhD |
SEE AGENDA HERE
|
Assignment will be posted here by Daniel, it was sent to Aviva and Daniel on 7/18 Assignment #5 is due on 7/28/2020 SEE 12 articles for WordClouds, below |
Session #6:
7/28/2020 | Dr. Williams and Dr. Irina | Dr. Williams will present DNA, RNA, PROTEIN and OMICS and overview of BioInformatic Tools and your Weekly assignment | |
Session #7:
8/4/2020 | Ofer Markman, PhD | TBD | |
Session #8:
8/11/2020 LAST Session Part 1: | Dr. Irina, Presenter
Summary by Dr. Ofer, Aviva | TBD | FINAL ASSIGMENTS DUE
For Aviva: Apply ML on the articles in your Assignment for 6/23/2020 |
Session #8:
8/11/2020 LAST Session Part 2: | Interns & Aviva | on JOINTLY composing paragraph for your Resume and uploading final version | |
Session #8:
8/11/2020 LAST Session Part 3: | Interns & Aviva | On RELATIONS beyond 8/11/2020 | ALL ASSIGNMENTS MUST BE COMPLETED on 8/11/2020 |
BIOs of 2020 LPBI Summer Interns
Daniel Menzin, BSc BioMedical Engineering, expected, May 2021, Research Assistant 4, Core Applications Developer and Acting CTO
Noam Steiner Tomer, Summer Internship, Research Assistant 1
Zachary Day, Research Assistant 2, Exploration in Marketing Communications
for
Assignments and DELIVERABLES to be published on
Intern’s Personal Page
This is the only place to store your work as digital recordings of all the assignments for LPBI’s 2020 Summer Internship by each Intern on each INTERN’s Named Page on the Portal
attn ZACH: MONDAYS and WEDs – ZACH & Aviva Lev-Ari’s Zoom Meeting – PLEASE PLACE ZOOM LINK on the calendar. This is a recurring meeting till 8/12/2020, Join Zoom Meeting
https://us02web.zoom.us/j/83151582410?pwd=RnVOSjZTMFVNeG1GcVZxSlBoVEhUZz09
UPDATED on 7/14/2020
NLP Resources
- University of New South Wales NLP Dictionary:https://www.cse.unsw.edu.au/~billw/nlpdict.html
- Princeton WordNet 3.1: (Thesaurus/Dictionary)
http://wordnetweb.princeton.edu/perl/webwn|https://wordnet.princeton.edu/download/current-version
- Natural Language Toolkit: (NLP Python Library) https://www.nltk.org/
UPDATED on 7/8/2020
How Fierce are you about applying AI to your business?
Have you considered this question? As machine learning is on its way to becoming a 96.7B$ market by 2025, Covid-19 accelerates the robotics takeover of factory floors, drug delivery and testing advances and your smart phone gets “smarter,” maybe the time is now? As companies move through their digital transformation and infrastructure gets more agile, the prospect of leveraging artificial intelligence (AI) and machine learning to create business, customer and process value has never been more promising.
We have moved from AI being a “bleeding edge” premise to affordable applications that can automate customer and patient engagement through chat bots that learn — which is why we have created Fierce AI Week.
Sign up today for the only virtual event focused on the application of AI to drive business, customer and process value through a discuss, debate and define format. Experience three days of keynotes, vertical industry sessions, a “pitch tank” of new ideas and more!
SIGN UP TODAY
Learn what it means to #BeFierce in the application of AI in these markets
Life Sciences
Healthcare
Telecom
Engineering AI
INTERESTED IN SPEAKING OR SPONSORING?
Contact us for more information on speaking or sponsoring Fierce AI Week or other future virtual events.
CONTACT US
SOURCE
From: Fierce Healthcare <editors@FierceHealthcare.com>
Reply-To: <qx_fiercehealthcare@inbound.bamboocricket.com>
Date: Wednesday, July 8, 2020 at 10:09 AM
To: Aviva Lev-Ari <AvivaLev-Ari@alum.berkeley.edu>
Subject: Announcing Fierce AI Week — August 10–12 | Free Virtual Event
UPDATED on 6/26, 2020
Part of your LPBI 2020 Summer Internship
-
You are advised to register online for one or more of the Lectures, below.
-
On 8/11/2020 – Each Intern will give a Presentation that will include a Summary of one of the Lectures, below.
Marine Biological Laboratory
June 16, 2020 – Kick Off Zoom Meeting
Introduction of Interns to the Team and LPBI’s Team to the Interns
In attendance were
- LPBI’s External Scientific Relations,
- LPBI’s External Business Relations,
- LPBI’s FIT Members: among them – The Team Leaders for 2020 Internship: Dr. Ofer, Dr. Williams, Dr. Irina and Aviva
- The INTERNS
Data Curation on LinkedIn.com Online Course
https://www.linkedin.com/learning/data-curation-foundations/data-curation-in-data-science
Course details
Data curation is quickly evolving as a required skill and job function in data teams and organizations. Creating and sharing data curation files can help you more efficiently and effectively manage the work of teams, and leverage their data for analytics and decision-making. In this course, Monika Wahi demonstrates how to develop curation files to document information about datasets and related business processes. Monika provides an overview of five categories of data curation files: files for back-end curation, different files for front-end curation, survey curation files, flow diagrams, and text-based curation files. She goes over a variety of curation files from each category, providing guidance as to how to develop them using Microsoft Word, Excel, or PowerPoint.
Learning objectives
- How curation files function as part of data management
- Back-end curation
- Front-end curation
- Steps for dashboard design
- Designing surveys
- Creating warehouse, analytic, and application flow diagrams
- Text-based curation files
Skills covered in this course
Data Curation and Data Annotation
We got the book as PDF for our Students & NLP TEAM
https://www.oreilly.com/library/view/natural-language-annotation/9781449332693
Curriculum and Assignments for LPBI’s 2020 Summer Interns
WEEKLY MEETING on TUE at 11AM EST – 2PM EST
SUMMER FIRST SESSION on June 23
June 23, 11AM EST – 2PM EST
SUMMER LAST SESSION on August 11
August 11, 11AM EST – 2PM EST
SUMMER FIRST SESSION on June 23
Session 1:
June 23, 11AM EST – 2PM EST
In attendance:
INTERNS and Aviva
Aviva’s presentation on posting on our Platform and Mini Curation for 8 Key Terms from Prof. Yedgar’s Talk on 6/16
First assignment Due on your PERSONAL Page on June 23, 2020 at 11AM ON LPBI’s
PORTAL for 2020 SUMMER INTERNSHIP
This is LPBI’s PORTAL for 2020 SUMMER INTERNSHIP on
Data Curation and Data Annotation for
Text Analysis by NLP, ML, AI Algorithms
https://pharmaceuticalintelligence.com/2020-summer-internship/
ALL INTERNS
Bookmark this Link
- Please review above link for Internship Curriculum and Schedule
- Please Go to your Page and Add your First assignment Due on your Page on June 23, 2020 at 11AM
- For June 23, 2020 Please Provide 1/2 Page definition and the SOURCE(S) for the following Key Words mentioned in Prof. Yedgar’s Talk on June 16, 2020
- PGE2
- TXA2
- PLA2
- Receptor
- Agonist/Antigonist in Pharmacology
- Cell signaling PATHWAY
- Inflammation
- Sepsis
- Go to Search Box on the Home Page – type in ANY 4 terms from the list of 8
- From the articles from the archive Presented to you as SEARCH RESULTS
- REVIEW the first 20 titles and choose 5 to list as follows
Article title
Author, Curator Name, Titles
URL
- Of the 5 that you list – choose one that you will read
- Write 1/2 what did you learn new by reading this article
DELIVERABLES for June 23, 11AM EST – saved on your Personal Page
- type in ANY 4 terms from the list of 8
- REVIEW the first 20 titlesand choose 5to list as follows
- List for each one of the 4 Keywords
Article title
Author, Curator Name, Titles
URL
- List the ONE that you had read
- Write Four different 1/2 reports on the Journal Article you read– One for each of the 4 Key words you provided a a definition for
- Type 1/2 page and all the tasks above ON YOUR ON PERSONAL PAGE: DATE, Assignment #1 – Type save publish
Assignment #1: Goals
- TEACH YOU definition of 4 CARDINAL terms in Biological Sciences – you are welcome to research all the 8
- TEACH YOU the ART of selection: 4 out of 8
- TEACH YOU Search Function on our Journal Archive
- TEACH YOU to read 20 titles and Select 5 article
- TEACH YOU How to record a SOURCE retrieved from our Journal Archive [different than a reference you cite in your Academic work]
- TEACH YOU to elect form a List of 5 Article the need to select ONLY one to read
- TEACH YOU to Write 1/2 a page a report – WHAT DID YOU LEARN NEW – EXPANSION OF YOUR UNIVERSE OF KNOWLEDGE IN BIOLOGICAL SCIENCES
GOALS 1 TO 7 – ARE A MUST HAVE FOR CURATION OF MINI CORATIONS AND FOR TEXT ANALYSIS – COMPREHENSION LEVEL
All Instructors need to Specify that section for ALL assignments to 2020 Summer Interns: Assignment # x: Goals
- We need to use INTERNS assignments to create a PROOF OF CONCEPT for the client in UT
- All goals need to be BASIC Research SKILLS and
- Specific Skills for Data Curation and Data Annotation for Text Analysis by NLP, ML, AI Algorithms
2020 LPBI Summer Interns
Personal Page for
Assignment and DELIVERABLES
You access ONLY your Personal Page to WRITE
You access All the Website to READ, copy, paste for your assignments with proper LINK cited
- Daniel Menzin, BSc BioMedical Engineering, expected, May 2021
Daniel, Bookmark this Link - Sonam Sherpa, BSc Computer Science, expected, May 2021
Sonam,Bookmark this Link - Noam Steiner Tomer, Summer Internship, Research Assistant 1
Noam, Bookmark this Link - Doha Akad, BA, 2020 – Research Assistant 5: Statistical Analysis and AI
E-MAIL ME ANY ISSUE
Session 2:
June 30, 11AM EST – 2PM EST
July 10, 2020 DUE date for Assignment #2
In attendance:
INTERNS and Dr. Ofer, Dr. Williams, Dr. Irina
Dr. Williams and Dr. Irina will present:
Dr. Williams will present a Cancer Biology Overview and
- Cancer Type Women’s Cancers (Breast and Ovarian)
- Cancer Type Blood Cancers (Leukemias and Lymphomas)
- Cancer Type Lung Cancer
selected by
- Daniel – Cancer Type x
- Sonam- Cancer Type y
- Noam – Cancer Type z
Dr. Williams and Dr. Irina
Prepare and present ONE assignment that each Student will apply on HIS CANCER TYPE OF CHOICE
Interns: Please see lesson plan here: What is Cancer An Introduction for Curators
Interns: Please curate from our Journal articles on either Breast, Ovarian, Lung Cancer or Blood Cancers
Session 3:
July 7, 11AM EST – 2PM EST
In attendance:
INTERNS and Dr. Ofer
Dr. Ofer LEADS the course on Data Curation and Data Annotation for Text Analysis by NLP, ML, AI Algorithms
Session 3:
Data Preparation Project
• Please list here topic to be covered in 3 hours by you and your Weekly assignment
Topics July 7 and assignments
Assignment #3 is DUE on week after July 10, 2020 which is the DUE date for Assignment #2
Topics:
- words
- Text processing
- Meaning
- Text as strings
- Punctuation
- Thesaurus how its translated to computer language.
- Dictionary
finding 3 relevant ones for their summer project
Glossary of terms
finding 3 good ones for their summer projects
- Synonyms
- advance synonyms
- letters and misspelling matrices – how when why.
finding good ones
- Unifying and loss of fine meaning
finding 3 examples.
Trade-offs in text processing
finding 3 examples
Dr. Ofer Markman
Mobile: +972-52-3275720
E-mail:oferm2020@gmail.com ofer.markman@gmce-inc.com
f +972-153-4-8104230
T-+972-4-8104230
Your assignment is a search assignment and requires you find examples and resources as indicated in blue above… (do 4 out of 5) also find a good application or tool for word clouds and please demonstrate using 3 abtract word clouds
Session 4:
July 14, 11AM EST – 2PM EST
In attendance:
INTERNS and Dr. Ofer
Dr. Ofer LEADS
Session 4: Same as Session 3
– meaning: top down – rational for quality improving text prep.
- Please list here topic to be covered in 3 hours by you and your Weekly assignment
in the workshop and in email
Session 5:
July 21, 11AM EST – 2PM EST
In attendance:
INTERNS and Dr. Ofer
Dr. Ofer Leads
Session 5: Same as Session 4
– different content
- Please list here topic to be covered in 3 hours by you and your Weekly assignment
SPECIFY
Session 6:
July 28, 11AM EST – 2PM EST
Subject matter experts present
In attendance
The INTERNS with Dr. Williams, Dr. Irina, Dr. Ofer, Aviva
Presentations by Dr. Williams and Dr. Irina
- Dr. Williams will present DNA, RNA, PROTEIN and OMICS and overview of BioInformatic Tools and your Weekly assignment
SPECIFY TOPIC
Session 7:
August 4, 11AM EST – 2PM EST
In attendance:
INTERNS and Dr. Ofer
Dr. Ofer LEADS
Session 6: Same as Session 5
– different content
- Please list here topic to be covered in 3 hours by you and your Weekly assignment
SPECIFY
Session 8:
August 11, 11AM EST – 2PM EST
Session 8: LAST SESSION
In attendance:
The INTERNS with Dr. Irina, Dr. Ofer, Aviva
Presentations by Dr. Irina, Dr. Ofer, Aviva
All DELIVERABLES DUE for
• Cancer Type 1, 2, 3 submitted electronically on each Student Page on 2020 Summer Internship Portal
Dr. Irina, Dr. Ofer, Aviva will present
SUMMARY for
- What were the goals
- What was accomplished in 8 weeks
- Farwell to Students
RELATIONS beyond August 2020
- LPBI will offer to continue during Academic year – 5 hours per week
- LPBI will offer to continue Summer 2021 till students get into NEXT steps of their career: School or Job
- LPBI’s Affiliation is very important
- LPBI’s recommendation letters are very important
- LPBI offers 2020 Summer INTERNS
- TRAINING in Life Sciences Domains and Technical Knowledge in Data Science
- Affiliation
- Recommendation
- One paragraph to include in Resume on your personal accomplishments during the Internship
This page has the following sub pages.
- Daniel Menzin, BSc Biomedical Engineering, expected, May 2021
- Noam Steiner Tomer, Summer Internship, Research Assistant 1
- Doha Akad, BA, 2020 – Research Assistant 5: Statistical Analysis and AI
- Zachary Day, Research Assistant 2, Exploration in Marketing Communications
- Ethan Coomber, Research Assistant III, Data Science and Podcast Library Development
- Srinivas Sriram, Research Assistant I
- Abhisar Anand, Research Assistant I