BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:Asia/Kolkata
X-WR-TIMEZONE:Asia/Kolkata
BEGIN:VEVENT
UID:206@cds.iisc.ac.in
DTSTART;TZID=Asia/Kolkata:20260618T113000
DTEND;TZID=Asia/Kolkata:20260618T123000
DTSTAMP:20260610T073527Z
URL:https://cds.iisc.ac.in/events/seminar-cds-102-june-18th-1130-towards-b
 reakthrough-generative-ai-for-chemistry/
SUMMARY:{Seminar} @ CDS: #102\, June 18th: 11:30: "Towards Breakthrough Gen
 erative AI for Chemistry."
DESCRIPTION:Department of Computational and Data Sciences\nDepartment Semin
 ar\n\n\n\nSpeaker : Dr. Bharath Ramsundar\, CEO\, Deep Forest Sciences\, U
 SA\nTitle : Towards Breakthrough Generative AI for Chemistry.\nDate &amp\;
  Time : June 18th\, 2026 (Thursday)\, 11:30 AM\nVenue : # 102\, CDS Semina
 r Hall\n\n\n\nABSTRACT:\n\nChemistry as a field has yet to benefit from th
 e transformative capabilities of generative AI due to extensive hallucinat
 ions\, lack of common sense\, and cascading errors at longer time scales. 
 I hypothesize that for generative AI to solve problems in chemistry\, it m
 ust be buttressed with domain-specific infrastructure that takes advantage
  of molecular structure and properties. In particular\, I have taken a mul
 ti-pronged approach in three recent papers from my group at Deep Forest Sc
 iences. First\, I have built “chemical foundation models\,” domain-spe
 cific large language models (LLMs) trained on molecular structure data. In
  joint work with Lawrence Livermore National Labs\, I have introduced Chem
 BERTa-3\, a fully-open framework for training and evaluating chemical foun
 dation models along with an open source model\, weights\, and data release
 . Second\, to overcome LLM hallucinations\, I have developed an iterative 
 feedback method to intersperse chemically grounded validation with LLM inv
 ocations. This algorithm\, DeepRetro\, is a state-of-art system for chemic
 al retrosynthesis. DeepRetro’s iterative LLM calls provide pathways and 
 reasonable experimental instructions to synthesize potential therapeutics.
  I have used DeepRetro to find novel synthetic pathways for complex natura
 l products such as Ohuamine-C and erythromycin. Third\, I have introduced 
 a framework\, DeepChem-DEL\, to effectively leverage chemical foundation m
 odels for modeling large DNA-encoded library (DEL) datasets. This framewor
 k enables effectively modeling the underlying chemical biology to facilita
 te effective AI modeling. Together\, these projects provide a framework an
 d roadmap to leverage generative AI technology to enable breakthrough chem
 istry.\n\nReferences:\n\n[1] DeepRetro: Retrosynthetic Pathway Discovery u
 sing Iterative LLM Reasoning\nhttps://www.nature.com/articles/s41598-026-3
 8821-z\n\n[2] ChemBERTa-3: An Open Source Training Framework for Chemical 
 Foundation Models\nhttps://pubs.rsc.org/en/content/articlehtml/2025/dd/d5d
 d00348b\n\n[3] DeepChem-DEL: An Open Source Framework for Reproducible DEL
  Modeling and Benchmarking\,\nhttps://chemrxiv.org/doi/full/10.26434/chemr
 xiv-2025-f11mk\n\nBIOGRAPHY:\n\nBharath is the founder and CEO of Deep For
 est Sciences\, which is building an AI-powered suite for drug and material
 s design and discovery. Bharath received a BA and BS from UC Berkeley in E
 ECS and Mathematics and was valedictorian of his graduating class in mathe
 matics. He did his PhD in computer science at Stanford University where he
  studied the application of deep-learning to problems in drug-discovery. A
 t Stanford\, Bharath created the deepchem.io open-source project to grow t
 he deep drug discovery open source community\, co-created the moleculenet.
 ai benchmark suite to facilitate development of molecular algorithms\, and
  more. Bharath's graduate education was supported by a Hertz Fellowship\, 
 the most selective graduate fellowship in the sciences. Bharath is the lea
 d author of "TensorFlow for Deep Learning: From Linear Regression to Reinf
 orcement Learning"\, a developer's introduction to modern machine learning
 \, with O'Reilly Media\, and "Deep Learning for the Life Sciences". Additi
 onally\, he authored "The DeepChem Book" in collaboration with the DeepChe
 m team\, published in 2024\, and is currently working on "Differentiable P
 hysics: Machine Learning for Physical Systems".\n\nHost Faculty: Dr. Phani
  Motamarri\n\n\n\nALL ARE WELCOME
CATEGORIES:Events,Talks
END:VEVENT
BEGIN:VTIMEZONE
TZID:Asia/Kolkata
X-LIC-LOCATION:Asia/Kolkata
BEGIN:STANDARD
DTSTART:20250618T113000
TZOFFSETFROM:+0530
TZOFFSETTO:+0530
TZNAME:IST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR