---

My research largely centers around the question:

how can AI, computing, and algorithmic thinking improve science, society, and democracy?

My work is both constructive and critical for drug discovery, ranging from identifying an inhibitor of the 3CL-main-protease of SARS-CoV-2 (see PDB: 7LTJ) to novel applications of language models for navigating chemical space formulated as a lattice. I am passionate about translating computing developments to novel scientific approaches (and vice-versa) to better science (and produce tangible scientific results).

Recently, as an outgrowth of AI ethics, my work has asked the more powerful interpretive question:

how do we know when models are improving X, and how can we interpret them as decision-makers?

In science, for example, my work has pointed out that this question is more complicated than many treat it. And in terms of algorithmic justice, we ought to turn towards political theory rather than single notions of ethics. I ask how democratic institutions can channel algorithmic developments through the public? Social integration, deliberation, and, more generally, feeling at home in the world are decreasing under the current regime of AI thought. I’m currently a vising fellow at the Harvard Kennedy School’s Science and Technology Program, working on these new questions.

---

Selected Publications and Talks

Please see my CV for the most up to date listing, thanks!

• MANCEPT Workshop Austin Clyde, “Created in our Likeness: Is Open-Source AI at Odds with Animal Rights?” MANCEPT Workshop “Politics, Animals, and Technology” organized by the Manchester Centre for Political Theory, September 2021. (accepted for talk)
• CAFCW20 @ SC'20 Scaffold-Induced Molecular Subgraphs (SIMSG): Effective Graph Sampling Methods for High-Throughput Computational Drug Discovery. Clyde, A., Shah, Ashka, Zvyagin, M., Ramanathan, A., Stevens, R., Virtual 13 November 2020. (accepted for talk)
• Preprint COVID Moonshot: Open Science Discovery of SARS-CoV-2 Main Protease Inhibitors by Combining Crowdsourcing, High-Throughput Experiments, Computational Simulations, and Machine Learning" The COVID Moonshot Consortium (authors here: https://tinyurl.com/y3r7redd ) 30 October 2020.
• Preprint Scalable HPC and AI Infrastructure for COVID-19 Therapeutics" Hyungro Lee, Andre Merzky, Li Tan, Mikhail Titov, Matteo Turilli, Dario Alfe, Agastya Bhati, Alex Brace, Austin Clyde, Peter Coveney, Heng Ma, Arvind Ramanathan, Rick Stevens, Anda Trifan, Hubertus Van Dam, Shunzhou Wan, Sean Wilkinson, Shantenu Jha. 20 October 2020.
• Preprint IMPECCABLE: Integrated Modeling PipelinE for COVID Cure by Assessing Better LEads" Aymen Al Saadi, Dario Alfe, Yadu Babuji, Agastya Bhati, Ben Blaiszik, Thomas Brettin, Kyle Chard, Ryan Chard, Peter Coveney, Anda Trifan, Alex Brace, Austin Clyde, Ian Foster, Tom Gibbs, Shantenu Jha, Kristopher Keipert, Thorsten Kurth, Dieter Kranzlmüller, Hyungro Lee, Zhuozhao Li, Heng Ma, Andre Merzky, Gerald Mathias, Alexander Partin, Junqi Yin, Arvind Ramanathan, Ashka Shah, Abraham Stern, Rick Stevens, Li Tan, Mikhail Titov, Aristeidis Tsaris, Matteo Turilli, Huub Van Dam, Shunzhou Wan, David Wifling. 13 October 2020.
• Preprint Babuji, Yadu, Ben Blaiszik, Tom Brettin, Kyle Chard, Ryan Chard, Clyde, Austin, Ian Foster et al. "Targeting SARS-CoV-2 with AI-and HPC-enabled Lead Generation: A First Data Release." arXiv preprint arXiv:2006.02431 (2020).
• Preprint Clyde, Austin, Xiaotian Duan, and Rick Stevens. "Regression Enrichment Surfaces: a Simple Analysis Technique for Virtual Drug Screening Models." arXiv preprint arXiv:2006.01171 (2020).
• Preprint Clyde, Austin, Tom Brettin, Alexander Partin, Maulik Shaulik, Hyunseung Yoo, Yvonne Evrard, Yitan Zhu, Fangfang Xia, and Rick Stevens. "A Systematic Approach to Featurization for Cancer Drug Sensitivity Predictions with Deep Learning." arXiv preprint arXiv:2005.00095 (2020).
• CompBioMed EU Integrating High-Performance Simulations and Learning toward Improved Cancer Therapy." Clyde, Austin, online. 30 March 2020. (Webinar Series)
• CompBioMed EU "Tiered BFE Estimation Workflow: What’s working and what’s not with the COVID-19 Effort." Clyde, Austin 15 March 2020. (invited talk)
• MLSys'20 "Benchmarking Machine Learning Workloads in Structural Bioinformatics Applications." Heng Ma, Clyde, Austin, Venkatram Vishwanath, Debsindhu Bhowmik, Arvind Ramanathan, Shantenu Jha. 4 March 2020.
• AACR "Virtual Screening with Deep Learning using Cancer Cell Line Dose Response Data", Austin Clyde, Arvind Ramanathan, Rick Stevens. Advancing Precision Medicine Drug Development: Incorporation of Real-World Data and Other Novel Strategies, San Deigo CA. 10 January 2020. (poster)
• Janssen Pharmaceutica "Accelerating Virtual Docking Screens with Deep Learning", Austin Clyde. 5 December 2019. (talk)
• CAFCW19 @ SC'19 "Integrating High-Performance Simulations and Learning toward Improved Cancer Therapy", Clyde, Austin, Dave Wright, Katya Ahmed, John D. Chodera, John Karanicolas, Palani Kirubakaran, Hyungro Lee, Matteo Turilli, Shunzhou Wan, Peter Coveney, Shantenu Jha, Rick Stevens, Denver, CO, 17 November 2019. (accepted for talk)
• NIH.AI ML for NGS Seminar "Virtual Drug Screening with Deep Learning" , Clyde, Austin, NIH.AI Workshop on Applications of Machine Learning for Next Generation Sequencing & Drug Data, Bethesdia, MD, 23 October 2019 (tutorial)
• CompBioMed2 Kick-Off "Computational Drug Discovery at Scale" , Clyde, Austin, CompBioMed2 Kick-Off, Garching, DE, 21 October 2019 (talk)
• ATOM Technical Meeting "Molecule Generation, Search, and Optimization" , Clyde, Austin, Atom 2019 Technical Meeting, Livermore, CA, 11 April 2019 (talk)

---

Teaching

• UChicago Instructor Instructor for Introduction to Computer Science II (CMSC 152), Department of Computer Science, Univeristy of Chicago (Summer '21)
• CAAP Lecturer Instructor for University of Chicago, Chicago Academic Achievement Program Computer Science Course (Summer '20, '21)
• MPCS Practicum Instructor RL for COVID-19 (Spring '20)
• CMSC 254 TA for Machine Learning in Medicine (Fall '19)

---

Current Projects More »

(In progress)

• Regression Enrichment Surfaces RES Python package and new methodology for analyzing deep learning models' performance in regards to virtual screening tasks.
• RLMM RLDock OpenAI Gym environment for virtual structural docking using reinforcement learning. RLDock allows for docking flexible targets and combination with simulation workflows.
• CANDLE CANDLE I worked on the NCI/DOE Pilot-1 cancer dose response prediction models.