In a global pandemic such as COVID-19, technology, artificial intelligence, and data science have become critical to helping societies effectively deal with the outbreak. In this talk, I will discuss three case studies of how AI is being used in Corona Virus research. The first part of the talk will discuss about how deep learning model detected COVID-19 caused pneumonia from computed tomography (CT) scans with comparable performance to expert radiologists. To be more specific, I will discuss about UNet++ architecture that was implemented by researchers for evaluating lung infection in COVID-19 CT images. The second part of the talk will be devoted to recent attempts in natural language processing to generate new insights in support of the ongoing fight against this infectious disease. There is a growing urgency for these approaches because of the rapid acceleration in new coronavirus literature, making it difficult for the medical research community to keep up. To be precise, BERT literature search engine for COVID-19 literature.will be discussed .

The third part of the talk deals with deep learning based generative modeling framework to design drug candidates specific to a given target protein sequence. One of the most important COVID-19 protein targets is the 3C-like protease for which the crystal structure is known. We present different deep learning models designed for generating novel drug molecules with multiple desirable properties. The deep learning framework involves Variational Autoencoder, Generative Adversarial Networks, Reinforcement Learning, and Transfer Learning. The generated molecules might serve as a blueprint for creating drugs that can potentially bind to the viral protein with high target affinity, as well as high drug-likeliness. Last but not the least, this talk will also touch upon how the world community responded by making the data available to the researchers which enabled the data scientists to explore and support the scientific community.

 
 

Outline/Structure of the Talk

1. AI for COVID-19: Promises and Challenges (2 min)

2. COVID-19 imaging and Object segmentation using U-net++ architecture (4 min)

3.Natural Language Processing using BERT to generate new insights in support of the fight against COVID19 (4 min)

4. Molecular machine learning approaches to tackle the corona crisis at molecular scale (9 min)

- Variational Autoencoder and Generative Adversarial Networks for Generative Chemistry

- Representation of small molecules suitable for Neural networks

- Drug-target prediction from ML perspective

5. Summary (1 min)

Learning Outcome

  • After attending this session, the attendees will ...
    • understand U-net++ and its applications in analyzing biomedical images
    • understand how BERT algorithm is used in analyzing scientific documents
    • be familiar with in machino drug design using Generative Adversarial Networks

Target Audience

Beginners who wants to learn how AI is being applied in Corona pandemic. Intermediates who wants to learn the basics of computer vision, NLP and molecular machine learning.

Prerequisites for Attendees

Basics of Deep Learning and Big Data

schedule Submitted 6 months ago

Public Feedback

comment Suggest improvements to the Author
  • Kuldeep Jiwani
    By Kuldeep Jiwani  ~  5 months ago
    reply Reply

    Hi Parthiban,

    For the program committee to get a better understanding, can you please tell us will you be talking about various techniques used by people to detect COVID-19. Or you would technically deep dive into one approach and explain it in details with examples and logic on how it works.

    • Parthiban Srinivasan
      By Parthiban Srinivasan  ~  5 months ago
      reply Reply

      Hi Kuldeep

      In each of the three categories, (diagnostics, NLP and drug design) many people are making several attempts with several approaches. I will choose the best possible case study for each one of them and dive deep into it.

      For instance, I will discuss the U-Net++ that was used by Alibaba to get 96% accuracy in diagnostics.

      Likewise, for drug design, I propose to discuss "in silico medicine"' approach on generative chemistry. In silico medicine approach is very well known in this space. As a matter of fact, I have met Alex and discussed his approach while attending some of the meeting in USA and Europe. In a way, I will dive deep into the Generative Adversarial Networks for designing new drugs.

      Last but not the least, I will talk about the NLP for Coronovirus, from the Kaggle competition and AllenNLP, that is the combination of SciSapcy and BERT for Coronavirus literature. I have cherry picked only these three specific approaches for my presentation.

      If you have any further questions, please let me know. Thank you very much for your response. Regards, Parthi 

      • Madalasa Venkataraman
        By Madalasa Venkataraman  ~  5 months ago
        reply Reply

        Thanks Parthiban- the coverage is good. However, we also want the attendees to obtain significant knowledge of any one algorithm/technique, which will be the mainstay of your presentation. I hope you can accommodate that in your talk, and the slides and time spent on the topic reflect that.

        • Parthiban Srinivasan
          By Parthiban Srinivasan  ~  3 months ago
          reply Reply

          Hello Natasha,

          I wish to inform you that we are the national winners in SAMHAR-COVID19 Hackathon. I am sure this credential will increase the chance of getting acceptance for this proposal. Please find the link in https://samhar-covid19hackathon.cdac.in/#Result

          I am CEO of Vingyani and also serving as Adjunct faculty in IISERB teaching AI. Hence we named our team name as IISERB in the Hackathon. Now I am contemplating to speak only about the drug discovery component rather than touching on NLP and Diagnostics for COVID-19. Please let me know your thoughts.

          Also I have made two other proposals. May be, I can withdraw the other two proposals as this Corona proposal has got more likes.

          Best regards,

          Parthiban Srinivasan

          • Natasha Rodrigues
            By Natasha Rodrigues  ~  3 months ago
            reply Reply

            Hi Parthiban,

            Thank you for the update, that is great news, Congratulations on the win! I will surely inform the Program Committee on the same.

            Once the decision is taken, you can discuss your thoughts with the program committee on the parts of the proposal you would like to present. 

             Many Thanks,

            Natasha 

             

        • Parthiban Srinivasan
          By Parthiban Srinivasan  ~  5 months ago
          reply Reply

          Hi Madalasa

          I have given the timeline for my presentation as per your feedback. I hope this is fine with you. Kindly confirm. 

          Regards,

          Parthi

        • Parthiban Srinivasan
          By Parthiban Srinivasan  ~  5 months ago
          reply Reply

          Thanks for your valuable feedback. Based on your comment, I am thinking of 

          Background :2 min , Diagnostics (U-net++) : 4 min , NLP for Corona Literature: 4 min, and finally Deep learning for Corona drug design using GAN approach: 10 minute.. (2+4+4+10). 

          Does this sound good for you. Your advice is appreciated. Many thanks and kind regards, Parthi

  • Dr. Santonu Goswami
    By Dr. Santonu Goswami  ~  5 months ago
    reply Reply

    Hi Parthiban,

    Thank you for submitting the interesting proposal on a timely topic. You provide detailed background information on your previous talks etc which is quite helpful. 

    I completely agree with you on your stand about the importance of technology such as AI to help fight the COVID19 pandemic. Having said that I think your conclusive stand on the success of AI in coronavirus research is a bit pre-mature, in my viewpoint. This is an area which is just getting started and the results that are coming out do not have enough validation to be able to have a conclusive stand on success of AI in this field yet. I would like to hear your view on this aspect.

    Usages of UNet++ architecture in evaluating lung infection in COVID19 CT images and application of BERT in COVID19 literature research are quite interesting. Are you going to present use cases from your research to showcase these ? To my understanding these are work in progress and research has not matured to the level to claim that AI has achieved any significantly useful success in these areas. Would you like to comment on this aspect as well?

    With these considerations, the title of the proposal "Coronavirus: How AI is used to fight the Pandemic" could be a rather tall claim in today's date and might need modifications. 

    Thank you for your cooperation, your inputs would help the program committee to evaluate the proposal better. 

    Regards, 

    Santonu

     

    • Parthiban Srinivasan
      By Parthiban Srinivasan  ~  5 months ago
      reply Reply

      Dear Santonu

      Thank you very much for your feedback.

      I agree with your view that some of the choice of words may give a different perspective to the readers. For instance, when I say "success story", I meant IBM and insilico medicine have successfully able to generate inhibitors through AI. At Vingyani we are working on this area with the use of Chemical Abstracts Service data. The chemical data that they have open sourced it recently. Since we have few more months to the conference, we will have better version for the conference. I agree with you that the abstract  may give an impression that "Drug is discovered and is being in use", which is not the case. I take your feedback and am refining the abstract. 

      In the case of Biomedical images, Alibaba has achieved 96% accuracy in diagnosis using AI. But we do not know, how much medical practitioners are resorting to the current version of the technology. Keeping this in mind, let me refine the abstract without reducing the gist of it.  Given that we have few more months to the conference. I will have better version on all the three areas that I have written in the abstract.

      Thank you once again for your valuable feedback.

      Best regards,

      Parthi

      • Dr. Santonu Goswami
        By Dr. Santonu Goswami  ~  5 months ago
        reply Reply

        Dear Pratibhan, 

        Thank you very much for your consideration to refine the abstract. I understand that there are few months time till the conference and hence there is scope of an initial breakthrough. The abstract should be worded to reflect the efforts initiated for a breakthrough rather than enthuse our confidence in AI to help control COVID19 pandemic. 

        Regards, 

        Santonu

        • Parthiban Srinivasan
          By Parthiban Srinivasan  ~  3 months ago
          reply Reply

          Dear Santonu

          I wish to inform you that we are the national winners in SAMHAR-COVID19 Hackathon. I am sure this credential will increase the chance of getting acceptance for this proposal. Please find the link in https://samhar-covid19hackathon.cdac.in/#Result

          I am CEO of Vingyani and also serving as Adjunct faculty in IISERB teaching AI. Hence we named our team name as IISERB in the Hackathon.

          Also I have made two other proposals. May be, I can withdraw the other two proposals as this Corona proposal has got more likes. Please let me know your thoughts.

          Best regards,

          Parthiban Srinivasan

        • Parthiban Srinivasan
          By Parthiban Srinivasan  ~  5 months ago
          reply Reply

          Dear Santonu

          I hope the revised proposal is fine with you.

          Many thanks and kind regards,

          Parthi

  • Natasha Rodrigues
    By Natasha Rodrigues  ~  6 months ago
    reply Reply

    Hi Parthiban,

    Thanks for your proposal! Requesting you to update the Outline/Structure section of your proposal with a time-wise breakup of how you plan to use 20 mins for the topics you've highlighted?

    To help the program committee understand your presentation style, can you add the slides for your proposal and provide a link to your past recording or record a small 1-2 mins trailer of your talk and share the link to the same?

    Also, in order to ensure the completeness of your proposal, we suggest you go through the review process requirements.

    Thanks,

    Natasha

    • Parthiban Srinivasan
      By Parthiban Srinivasan  ~  5 months ago
      reply Reply

      Could you please have look at my talk in this you tube video... just for a sample, i have put a sample of one and half minutes to give you a flavor of my style of presenting.

      https://www.youtube.com/watch?v=brzyaKk2Fko

      You can find some of my slides in this page (i am a regular speaker in Europe)

      https://haxel.com/ii-sdv/2019/speaker/p_srinivasan-parthiban

      To know more about me, please see the photo gallery in this page

      https://vingyani.com/about-us

      To see some of my video blogs, please have a look at this page

      https://vingyani.com/blog

      • Natasha Rodrigues
        By Natasha Rodrigues  ~  5 months ago
        reply Reply

        Many thanks for the videos Parthiban.

        • Parthiban Srinivasan
          By Parthiban Srinivasan  ~  3 months ago
          reply Reply

          Hello Natasha,

          I wish to inform you that we are the national winners in SAMHAR-COVID19 Hackathon. I am sure this credential will increase the chance of getting acceptance for this proposal. Please find the link in https://samhar-covid19hackathon.cdac.in/#Result

          I am CEO of Vingyani and also serving as Adjunct faculty in IISERB teaching AI. Hence we named our team name as IISERB in the Hackathon.

          Also I have made two other proposals. May be, I can withdraw the other two proposals as this Corona proposal has got more likes. Please let me know your thoughts.

          Best regards,

          Parthiban Srinivasan

           

           


  • Parthiban Srinivasan
    keyboard_arrow_down

    Parthiban Srinivasan - AI meets IP: There is Nothing Artificial about it

    Parthiban Srinivasan
    Parthiban Srinivasan
    CEO
    Vingyani
    schedule 6 months ago
    Sold Out!
    20 Mins
    Demonstration
    Beginner

    Artificial intelligence is a global phenomenon, a technology that has arrived. No industry will be untouched by the changes and disruption these technologies bring. With the rapidly changing innovation landscape, patent offices are discussing the interplay between AI and patents. Patent analysts will have to respond to this changing environment by being more global in their perspective.

    The machine learning techniques revolutionizing AI are deep learning and neural networks, and these are the fastest growing AI techniques in terms of patent filings: deep learning showed an impressive average annual growth rate of 175 percent from 2013 to 2016, reaching 2,399 patent filings in 2016; and neural networks grew at a rate of 46 percent over the same period, with 6,506 patent filings in 2016.

    The three AI functional applications with the highest number of patent families are computer vision, natural language processing and speech processing. These represent 49 percent, 14 percent and 13 percent of all patent families related to AI, respectively. This underlines the importance of these three functional applications to the field of AI.

    The presentation will focus on these aspects and will highlight recent developments in AI methods and the breadth of AI applications that are of importance to patent searchers, analysts, and decision-makers.

  • Parthiban Srinivasan
    keyboard_arrow_down

    Parthiban Srinivasan - The Global AI Strategy Landscape

    Parthiban Srinivasan
    Parthiban Srinivasan
    CEO
    Vingyani
    schedule 6 months ago
    Sold Out!
    20 Mins
    Demonstration
    Beginner

    AI has the potential to deliver additional global economic activity of around $13 trillion by 2030, or about 16% higher cumulative GDP compared with today. Securing this economic growth, combined with the soft power an AI leadership role will bring any nation, makes it a major social and economic policy priority. In the last couple of years, many countries released strategies to promote the use and development of AI. No two strategies are alike, with each focusing on different aspects of AI policy: scientific research, talent development, skills and education, public and private sector adoption, ethics and inclusion, standards and regulations, and data and digital infrastructure. This talk will discuss the key policies and goals of each nation' strategy, as well as related policies and initiatives that have announced since the release of the initial strategies. The race to become the global leader in AI has officially begun!