1. A machine learning-based approach to determine infection status in recipients of BBV152 whole virion inactivated SARS-CoV-2 vaccine for serological surveys
- Author
-
Prateek Singh, Rajat Ujjainiya, Satyartha Prakash, Salwa Naushin, Viren Sardana, Nitin Bhatheja, Ajay Pratap Singh, Joydeb Barman, Kartik Kumar, Raju Khan, Karthik Bharadwaj Tallapaka, Mahesh Anumalla, Amit Lahiri, Susanta Kar, Vivek Bhosale, Mrigank Srivastava, Madhav Nilakanth Mugale, C.P Pandey, Shaziya Khan, Shivani Katiyar, Desh Raj, Sharmeen Ishteyaque, Sonu Khanka, Ankita Rani, null Promila, Jyotsna Sharma, Anuradha Seth, Mukul Dutta, Nishant Saurabh, Murugan Veerapandian, Ganesh Venkatachalam, Deepak Bansal, Dinesh Gupta, Prakash M Halami, Muthukumar Serva Peddha, Gopinath M Sundaram, Ravindra P Veeranna, Anirban Pal, Ranvijay Kumar Singh, Suresh Kumar Anandasadagopan, Parimala Karuppanan, Syed Nasar Rahman, Gopika Selvakumar, Subramanian Venkatesan, MalayKumar Karmakar, Harish Kumar Sardana, Animika Kothari, DevendraSingh Parihar, Anupma Thakur, Anas Saifi, Naman Gupta, Yogita Singh, Ritu Reddu, Rizul Gautam, Anuj Mishra, Avinash Mishra, Iranna Gogeri, Geethavani Rayasam, Yogendra Padwad, Vikram Patial, Vipin Hallan, Damanpreet Singh, Narendra Tirpude, Partha Chakrabarti, Sujay Krishna Maity, Dipyaman Ganguly, Ramakrishna Sistla, Narender Kumar Balthu, A Kiran Kumar, Siva Ranjith, B Vijay Kumar, Piyush Singh Jamwal, Anshu Wali, Sajad Ahmed, Rekha Chouhan, Sumit G Gandhi, Nancy Sharma, Garima Rai, Faisal Irshad, Vijay Lakshmi Jamwal, MasroorAhmad Paddar, Sameer Ullah Khan, Fayaz Malik, Debashish Ghosh, Ghanshyam Thakkar, S K Barik, Prabhanshu Tripathi, Yatendra Kumar Satija, Sneha Mohanty, Md. Tauseef Khan, Umakanta Subudhi, Pradip Sen, Rashmi Kumar, Anshu Bhardwaj, Pawan Gupta, Deepak Sharma, Amit Tuli, Saumya Ray chaudhuri, Srinivasan Krishnamurthi, L Prakash, Ch V Rao, B N Singh, Arvindkumar Chaurasiya, Meera Chaurasiyar, Mayuri Bhadange, Bhagyashree Likhitkar, Sharada Mohite, Yogita Patil, Mahesh Kulkarni, Rakesh Joshi, Vaibhav Pandya, Sachin Mahajan, Amita Patil, Rachel Samson, Tejas Vare, Mahesh Dharne, Ashok Giri, Shilpa Paranjape, G. Narahari Sastry, Jatin Kalita, Tridip Phukan, Prasenjit Manna, Wahengbam Romi, Pankaj Bharali, Dibyajyoti Ozah, Ravi Kumar Sahu, Prachurjya Dutta, Moirangthem Goutam Singh, Gayatri Gogoi, Yasmin BegamTapadar, Elapavalooru VSSK Babu, Rajeev K Sukumaran, Aishwarya R Nair, Anoop Puthiyamadam, PrajeeshKooloth Valappil, Adrash Velayudhan Pillai Prasannakumari, Kalpana Chodankar, Samir Damare, Ved Varun Agrawal, Kumardeep Chaudhary, Anurag Agrawal, Shantanu Sengupta, and Debasis Dash
- Abstract
Data science has been an invaluable part of the COVID-19 pandemic response with multiple applications, ranging from tracking viral evolution to understanding the effectiveness of interventions. Asymptomatic breakthrough infections have been a major problem during the ongoing surge of Delta variant globally. Serological discrimination of vaccine response from infection has so far been limited to Spike protein vaccines used in the higher-income regions. Here, we show for the first time how statistical and machine learning (ML) approaches can discriminate SARS-CoV-2 infection from immune response to an inactivated whole virion vaccine (BBV152, Covaxin, India), thereby permitting real-world vaccine effectiveness assessments from cohort-based serosurveys in Asia and Africa where such vaccines are commonly used. Briefly, we accessed serial data on Anti-S and Anti-NC antibody concentration values, along with age, sex, number of doses, and number of days since the last vaccine dose for 1823 Covaxin recipients. An ensemble ML model, incorporating a consensus clustering approach alongside the support vector machine (SVM) model, was built on 1063 samples where reliable qualifying data existed, and then applied to the entire dataset. Of 1448 self-reported negative subjects, 724 were classified as infected. Since the vaccine contains wild-type virus and the antibodies induced will neutralize wild type much better than Delta variant, we determined the relative ability of a random subset of such samples to neutralize Delta versus wild type strain. In 100 of 156 samples, where ML prediction differed from self-reported uninfected status, Delta variant, was neutralized more effectively than the wild type, which cannot happen without infection. The fraction rose to 71.8% (28 of 39) in subjects predicted to be infected during the surge, which is concordant with the percentage of sequences classified as Delta (75.6%-80.2%) over the same period.
- Published
- 2021
- Full Text
- View/download PDF