Swarit Jasial

Having a background in Bioinformatics, Swarit Jasial did his Masters in Life Science Informatics and PhD in Computational Life Sciences from University of Bonn, Germany. During his studies, Swarit was involved in several projects concerning data mining and machine learning. He worked in the research area of computer aided drug design or Chemoinformatics. His PhD work focused on analysis of multitarget activities and assay interference characteristics of pharmaceutically relevant compounds. He studied promiscuity of compounds present in publicly available databases and his data analysis revealed interesting results for state-of-the-art PAINS filters, which are generally used to flag assay interference compounds. The machine learning models built in this project further extended the capacity of PAINS filters as they also took structural context into account. He published his studies in several journals mostly belonging to American Chemical Society (ACS).

Swarit Jasial did his post doctoral studies (2019-2024) in Data-Driven Chemistry lab, Data Science Center, Nara Institute of Science and Technology, Japan where he also worked as a specially appointed assistant professor. He worked on projects such as predicting antiviral activity of odorants with Kao corporation and monomer concentration prediction of polymerization reactions from infra-red spectra in collaboration with JSR corporation. He also supervised students in their research focusing on Chemoinformatics.

• Ph.D. in Computational Life Sciences, Bonn-Aachen International Center for Information Technology (B-IT), Rheinische Friedrich-Wilhelms-Universität Bonn, Germany (2015-2019)
• M.Sc. in Life Science Informatics, Bonn-Aachen International Center for Information Technology (B-IT), Rheinische Friedrich-Wilhelms-Universität Bonn, Germany (2012-2014)
• B.Tech. in Bioinformatics, Jaypee University of Information Technology, Waknaghat, India (2007-2011)

• Riadhi Syahdhi, R.; Jasial, S.; Maeda, I.; Miyao, T. Bridging Structure-and Ligand-Based Virtual Screening through Fragmented Interaction Fingerprint. ACS Omega 2024, 9, 38957-38969.
• Wakiuchi, A.; Jasial, S.; Asano, S.; Hashizume, R.; Hatanaka, M.; Ohnishi, Y.; Matsubara, T.; Ajiro, H.; Sugawara, T.; Fujii, M.; Miyao, T. Multiple comonomer concentrations prediction from FTIR spectra with quantum chemistry-based interpretation. MRS Comm 2024, 14, 439-444.
• Wakiuchi, A.; Jasial, S.; Asano, S.; Hashizume, R.; Hatanaka, M.; Ohnishi, Y.; Matsubara, T.; Ajiro, H.; Sugawara, T.; Fujii, M.; Miyao, T. Chemometrics Approach Based on Wavelet Transforms for the Estimation of Monomer Concentrations from FTIR Spectra. ACS Omega 2023, 8, 19781-19788.

• Jasial, S.; Hu, J.; Miyao, T.; Hirama, Y.; Onishi, S.; Matsui, R.; Osaki, K.; Funatsu, K. Screening and Validation of Odorants against Influenza A Virus Using Interpretable Regression Models. ACS Pharmacol. Transl. Sci. 2022, 6, 139-150.

• Tamura, S.; Jasial, S.; Miyao, T.; Funatsu, K. Interpretation of Ligand-Based Activity Cliff Prediction Models Using the Matched Molecular Pair Kernel. Molecules 2021, 39, 2000103.

• Miyao, T.; Jasial, S.; Bajorath, J.; Funatsu, K. Evaluation of Different Virtual Screening Strategies on the Basis of Compound Sets with Characteristic Core Distributions and Dissimilarity Relationships. J. Comput. Aided Mol. Des. 2019, 33, 729-743.

• Jasial, S.; Gilberg, E.; Blaschke, T.; Bajorath, J. Machine Learning Distinguishes with High Accuracy between Pan-Assay Interference Compounds That Are Promiscuous or Represent Dark Chemical Matter. J. Med. Chem. 2018, 61, 10255-10264.
• Vogt, M.; Jasial, S.; Bajorath, J. Extracting Compound Profiling Matrices from Screening Data. ACS Omega 2018, 3, 4706-4712.

• Jasial, S.; Bajorath, J. Dark Chemical Matter in Public Screening Assays and Derivation of Target Hypotheses. Med. Chem. Commun. 2017, 8, 2100–2104.
• Jasial, S.; Hu, Y.; Bajorath, J. How Frequently Are Pan-Assay Interference Compounds Active? Large-Scale Analysis of Screening Data Reveals Diverse Activity Profiles, Low Global Hit Frequency, and Many Consistently Inactive Compounds. J. Med. Chem. 2017, 60, 3879-3886.

• Jasial, S.; Hu, Y.; Vogt, M.; Bajorath, J. Activity-Relevant Similarity Values for Fingerprints and Implications for Similarity Searching. F1000Research 2016, 5 (Chem. Inf. Sci.): 591.
• Jasial, S.; Hu, Y.; Bajorath, J. Determining the Degree of Promiscuity of Extensively Assayed Compounds. PLoS One 2016, 11, e0153873.
• Jasial, S.; Hu, Y.; Bajorath, J. Assessing the Growth of Bioactive Compounds and Scaffolds over Time: Implications for Lead Discovery and Scaffold Hopping. J. Chem. Inf. Model. 2016, 56, 300-307.
• Jasial, S.; Balfer, J.; Vogt, M.; Bajorath, J. Determination of Meta-Parameters for Support Vector Machine Linear Combinations. Mol. Inf. 2015, 34, 127-133.

Google Scholar Profile: https://scholar.google.com/citations?user=EM_ZtG6p8LYC&hl=en_

• 2024 – Present Assistant Professor Center for Life Sciences Mahindra University.
• Specially Appointed Assistant Professor, Data-Driven Chemistry Laboratory,Data Science Center, Division of Materials Science, Nara Institute of Science and Technology (NAIST), Nara, Japan (2019-2024)

• The main theme of Swarit Jasial’s research is Computer-Aided Drug Design and Chemoinformatics. His work focuses on the application of informatics in chemistry, where data related to chemical compounds and approved drugs is utilized to study diseases and identify potential therapeutic candidates. He aims to develop computational techniques and predictive models that can analyze the activity of compounds against different biological targets, thereby assisting drug discovery programs through the identification of promising drug candidates for further validation.
• His research primarily involves data mining and machine learning using biological and chemical datasets. By applying machine learning algorithms, he studies how computers can recognize hidden structural patterns and molecular features responsible for the biological activity of compounds. He is particularly interested in understanding how algorithms learn from complex data and how machine learning models can be tailored to solve specific scientific problems. Therefore, his work emphasizes both the developmental aspects of computational models and their interpretability.
• His current research interests include the integration of knowledge from multiple domains for improved prediction and rationalization, the use of generative AI for de novo molecular design, and the identification of targets and pathways associated with natural products.