E164: Dr. James Lam - novel machine learning algorithm to identify new cancer drug targets

Trigger Warning: This episode discusses cancer.​​​​Episode 164: Part of the education and workforce development series (part 56).Description: In this educational episode, Naman Julka-Anderson and Jo McNamara sit down with Dr. James Lam talking about his career as a medical oncologist and work around developing a novel machine learning algorithm to identify new cancer drug targets.​​​​James studied Medicine at Cambridge and completed his MBBS at UCL, qualifying in 2017 with Distinction. He holds an MA(Cantab) for research in retinal neuroscience and was ranked first among all UK Medical Oncology ST3 applicants in 2021.​​Awarded an NIHR Academic Clinical Fellowship, he has contributed to practice-changing oncology trials and cancer cachexia research with the TRACERx Consortium. Now at BioCorteX, he applies computational metagenomics and AI to shaping future cancer care.​​James remains dedicated to oncology research, with a strong interest in nutrition, fitness, and health optimisation.​​​​CPD Reflection Points:​​Read through the three publications attached to show notes and reflect upon how this research may impact on clinical practice. ​​​​Complete this form for your accredited digital badge: Digital Badge Form.​​​​Links from the Episode:​​https://biocortex.com/​​Research links from the Episode:​​ASCO Conquer Cancer Award - Differential Clinical Trial Outcomes in Japan and the US​​Nature Medicine Publication - Cancer Cachexia in TRACERx ​​Google Cloud Press Release - Bacterial Interactions in ADC Cancer Treatment​​Rad Chat Links:​​Rad Chat Website​​Link Tree​​Facebook​​Instagram​​LinkedIn​​TikTok​​BlueSky​​YouTube​​Credits: Music and jingle credits: Dr. Ben Potts and Adam Cooke.© Rad Chat 2025. All rights reserved.  We (or our licensors) own all intellectual property rights in this podcast and all related content, online and offline.  You may not use, copy, modify, download, archive, reproduce, distribute, display, publish, licence, create derivative works from or commercially exploit any part of our content unless we expressly agree in writing.  You must not use any images, audio, video, graphics or clips separately from their accompanying context.  Please acknowledge Rad Chat (and any identified contributors) clearly whenever referencing or sharing our content.