Merge pull request #5962 from bebatut/genomics-gai-llm-with-python

Large Langage Model for Genomics using Python

Author: anuprulez

bin/check-url-persistence.sh

@@ -25,6 +25,9 @@ cat /tmp/20*.txt | sort -u | \
 	grep -v '/transcriptomics/tutorials/ref-based/faqs/rnaseq_data.html' | \
 	grep -v '/topics/data-management/' | \
 	grep -v 'training-material/tags/' | grep -v 'data-library'| grep -v '/recordings/index.html' |\
+	grep -v '/topics/statistics/tutorials/gai-llm-with-python/slides.html' | \
+	grep -v '/topics/statistics/tutorials/gai-llm-with-python/slides-plain.html' | \
+	grep -v '/topics/statistics/tutorials/gai-llm-with-python/tutorial.html' | \
 	sed 's|/$|/index.html|'  | grep '.html$' | sort -u | sed 's|https://training.galaxyproject.org|_site|' > /tmp/gtn-files.txt
 
 count=0

learning-pathways/ml-using-python.md

@@ -46,11 +46,23 @@ pathway:
         name: deep-learning-without-gai-with-python
         topic: statistics
 - 
-    section: "Module 4: Generative Artificial Intelligence and Large Langage Model"
-    description: Generative Artificial Intelligence and Large Langage Model using Python
+    section: "Module 4: Generative Artificial Intelligence and Large Langage Model for Genomics using Python"
+    description: This tutorial series provides a comprehensive guide to leveraging large language models for genomics, covering pretraining, fine-tuning, mutation impact prediction, sequence generation, and optimization.
     tutorials:
     - 
-        name: gai-llm-with-python
+        name: genomic-llm-pretraining
+        topic: statistics
+    - 
+        name: genomic-llm-finetuning
+        topic: statistics
+    - 
+        name: genomic-llm-zeroshot-prediction
+        topic: statistics
+    - 
+        name: genomic-llm-sequence-generation
+        topic: statistics
+    - 
+        name: genomic-llm-sequence-optimization
         topic: statistics
 - 
     section: "Module 5: Regulations/standards for AI using DOME"

topics/statistics/metadata.yaml

@@ -7,12 +7,23 @@ summary: "Statistical Analyses for omics data and machine learning using Galaxy
 docker_image: "quay.io/galaxy/statistics-training"
 edam_ontology: ["topic_2269"]
 
-requirements:
-  -
-    type: "internal"
-    topic_name: introduction
+#requirements:
+#  -
+#    type: "internal"
+#    topic_name: introduction
 
 editorial_board:
   - marziacremona
   - cumbof
-  - anuprulez
+  - anuprulez
+
+subtopics:
+#  - id: machine-learning
+#    title: "Machine Learning"
+#    description: "Tutorials introducing fundamental concepts and techniques, guiding learners through data preprocessing, model training, evaluation, and application."
+#  - id: deep-learning
+#    title: "Deep Learning"
+#    description: "In-depth guidance on designing and implementing neural networks, covering topics such as architecture design, training techniques, and applications"
+  - id: gai-llm
+    title: "Generative Artificial Intelligence and Large Langage Model"
+    description: "Tutorials covering the creation, pretraining, and applications of Generative Artificial Intelligence and Large Language Models."

topics/statistics/tutorials/gai-llm-with-python/slides.html

@@ -0,0 +1,9 @@
+@misc{zhou2024dnabert2efficientfoundationmodel,
+      title={DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome}, 
+      author={Zhihan Zhou and Yanrong Ji and Weijian Li and Pratik Dutta and Ramana Davuluri and Han Liu},
+      year={2024},
+      eprint={2306.15006},
+      archivePrefix={arXiv},
+      primaryClass={q-bio.GN},
+      url={https://arxiv.org/abs/2306.15006}, 
+}