Spaces:
Sleeping
Sleeping
Upload 6 files
Browse files- about.md +110 -0
- experience_detailed.md +141 -0
- publications_detailed.md +82 -0
- research_details.md +45 -0
- skills_expertise.md +142 -0
about.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# [Raktim Mondol](https://mondol.me)
|
2 |
+
NSW, Australia | [email protected]
|
3 |
+
|
4 |
+
---
|
5 |
+
|
6 |
+
## SUMMARY & RESEARCH INTEREST
|
7 |
+
|
8 |
+
I am an experienced data scientist and programmer with deep expertise in artificial intelligence, generative AI (GenAI) techniques and large language models (LLMs), bioinformatics, computer vision, and high-performance computing. My research and professional background is centered on analyzing large-scale image and biomedical datasets, developing novel deep learning models, and conducting advanced statistical analyses. I am a dedicated and committed individual with a strong team-oriented spirit, a positive attitude, and exceptional interpersonal skills.
|
9 |
+
|
10 |
+
---
|
11 |
+
|
12 |
+
## EDUCATION
|
13 |
+
|
14 |
+
🎓 **PhD, Computer Science & Engineering** | 2021 - 2025
|
15 |
+
<br>UNSW, Sydney, Australia
|
16 |
+
<br>**Research Topic:** *Deep Learning For Breast Cancer Prognosis & Explainability*
|
17 |
+
<br>**◇ Thesis Submitted**
|
18 |
+
|
19 |
+
🎓 **Masters by Research, Computer Science & Bioinformatics** | 2017 - 2019
|
20 |
+
<br>RMIT University, Melbourne, Australia
|
21 |
+
<br>[High Distinction (85%)](https://www.myequals.net/sharelink/78e7c7d7-5a73-4e7c-9711-f163f5dd1604/af0d807a-8392-45be-9104-d26b95f5aa7a)
|
22 |
+
<br>**Research Thesis:** *[Deep learning in classifying cancer subtypes, extracting relevant genes and identifying novel mutations](https://research-repository.rmit.edu.au/articles/thesis/Deep_learning_in_classifying_cancer_subtypes_extracting_relevant_genes_and_identifying_novel_mutations/27589272?file=50759199)*
|
23 |
+
|
24 |
+
---
|
25 |
+
|
26 |
+
## WORK EXPERIENCE
|
27 |
+
|
28 |
+
🧑🏫 **Casual Academic** | July 2021 - Continuing
|
29 |
+
<br>Dept. of Computer Science & Engineering
|
30 |
+
<br>[UNSW](https://www.unsw.edu.au/), Sydney, NSW
|
31 |
+
<br>**Duties/Responsibilities:**
|
32 |
+
* Conduct Laboratory and Consultation Classes: Computer Vision, Neural Networks and Deep Learning, Artificial Intelligence
|
33 |
+
|
34 |
+
🧑🏫 **Teaching Assistant (Casual)** | July 2017 - Oct 2019
|
35 |
+
<br>Dept. of Electrical and Biomedical Engineering
|
36 |
+
<br>[RMIT University](https://www.rmit.edu.au/), Melbourne, VIC
|
37 |
+
<br>**Duties/Responsibilities:**
|
38 |
+
* Conducted Laboratory Classes: Electronics (EEET2255), Software Engineering Design (EEET2250), Engineering Computing I (EEET2246), Introduction to Embedded Systems (EEET2256).
|
39 |
+
|
40 |
+
🧑🏫 **Lecturer (Full-Time)** | September 2013 - December 2016
|
41 |
+
<br>Dept. of Electrical and Electronic Engineering
|
42 |
+
<br>[World University of Bangladesh (WUB)](https://wub.edu.bd/), Dhaka, Bangladesh
|
43 |
+
<br>**Duties/Responsibilities:**
|
44 |
+
* Courses Instructed (Theory): Electrical Circuit I, Electrical Circuit II, Engineering Materials, Electronics I, Electronics II, Digital Logic Design and Digital Electronics
|
45 |
+
* Courses Instructed (Laboratory): Microprocessor & Interfacing, Digital Electronics and Digital Signal Processing
|
46 |
+
* Supervised Students for Projects and Thesis
|
47 |
+
|
48 |
+
---
|
49 |
+
|
50 |
+
## RESEARCH EXPERIENCE
|
51 |
+
|
52 |
+
🔬 **Doctoral Researcher (Sydney, NSW, Australia)** | March 2021 – Jan 2025
|
53 |
+
<br>**[Biomedical Image Computing Research Group](https://imagescience.org/meijering/group/)**
|
54 |
+
* Developed AI models to assist pathologists in breast cancer identification and treatment recommendation.
|
55 |
+
|
56 |
+
🔬 **Master's Researcher (Melbourne, VIC, Australia)** | March 2017 – April 2019
|
57 |
+
<br>**[NeuroSyd Research Laboratory](https://sites.google.com/view/neurosyd/home)**
|
58 |
+
* Worked on developing a deep learning model and bio-informatics pipeline to extract bio-marker from high-throughput biological data.
|
59 |
+
|
60 |
+
---
|
61 |
+
|
62 |
+
## TECHNICAL SKILLS
|
63 |
+
|
64 |
+
* **Languages:** Python, R, SQL, LaTeX
|
65 |
+
* **Software:** MATLAB, STATA, SPSS, SAS, NCSS
|
66 |
+
* **Deep Learning Framework:** Tensorflow, Pytorch
|
67 |
+
* **Distributed & Cloud Computing:** AWS, GCP, GALAXY
|
68 |
+
* **Operating Systems:** Windows, Linux
|
69 |
+
* **IDE:** Spyder, Jupyter Notebook, VS Code, Rstudio
|
70 |
+
|
71 |
+
---
|
72 |
+
|
73 |
+
## AWARDS & RECOGNITION
|
74 |
+
|
75 |
+
* **2021:** Awarded PhD Scholarship (Tuition Fee and Stipend)
|
76 |
+
* **2019:** Completed Masters by Research with [High Distinction](https://drive.google.com/file/d/19ItaTbByg686UpoBMB7LcmWT8kfE1-fR/view?usp=sharing)
|
77 |
+
* **2017:** RMIT Research Stipend Scholarship
|
78 |
+
* **2017:** RMIT Research International Tuition Fee Scholarship
|
79 |
+
* **2013:** B.Sc. in Electrical and Electronic Engineering with High Distinction
|
80 |
+
* **2013:** [Vice Chancellor Award Spring 2013](https://drive.google.com/file/d/1VgqAWfSlHtm5OEepYtlB32kxdlV72W1g/view?usp=sharing), BRAC University
|
81 |
+
* **2010:** [Dean Award Fall 2010](https://drive.google.com/file/d/15G0CGXYdDrMdB93LKB90uICPeJMYoLub/view?usp=sharing), [Fall 2011](https://drive.google.com/file/d/1xawevXKfahsE2LUrLAoUTn5PLjDIjyHr/view?usp=sharing), BRAC University
|
82 |
+
|
83 |
+
---
|
84 |
+
|
85 |
+
## PARTICIPATED EVENTS
|
86 |
+
|
87 |
+
* **2019:** Received Training on [NGS RNA Seq. & DNA Seq.](https://drive.google.com/file/d/1kHxtVXS1oD8BjrSqP8lM9koNA4PsT8WB/view?usp=sharing) Data Analysis organized by ArrayGen
|
88 |
+
* **2017:** Presented [Poster](https://drive.google.com/file/d/1K64iv74oatvbMmQYNHpyJgoGDvqRoW_V/view?usp=sharing) in [AMSI BioinfoSummer](https://drive.google.com/file/d/12Y2haYCtShJuEV0lsqeAiJgKtuRKGo_c/view?usp=sharing) at Monash University
|
89 |
+
* **2017:** Presented Thesis in [3 Minute Thesis (3MT)](https://drive.google.com/file/d/1AYj6Yox5GH285b4M7hh7rTxn4OyiPwMm/view?usp=sharing) competition at RMIT University
|
90 |
+
* **2017:** Received Training on High Performance Computing (HPC) at Monash University
|
91 |
+
* **2017:** Symposium on Big Data in Infectious Diseases at University of Melbourne
|
92 |
+
* **2016:** Received Training on Research Methodology at World University
|
93 |
+
* **2013:** Presented Undergraduate Thesis in a Workshop Organized by [IEEE Bangladesh](https://drive.google.com/file/d/1PPs1qlOjDDSZIXmaXWAL66q-WBBlz4i6/view?usp=sharing)
|
94 |
+
|
95 |
+
---
|
96 |
+
|
97 |
+
## PUBLICATIONS
|
98 |
+
|
99 |
+
### JOURNAL PAPERS
|
100 |
+
* 📓 R. K. Mondol, E. K. A. Millar, P. H. Graham, L. Browne, A. Sowmya, and E. Meijering, ["GRAPHITE: Graph-Based Interpretable Tissue Examination for Enhanced Explainability in Breast Cancer Histopathology,"](https://arxiv.org/abs/2501.04206) (Submitted, Under Review), 2024.
|
101 |
+
* 📓 R. K. Mondol, E. K. A. Millar, and A. Sowmya, and E. Meijering, ["BioFusionNet: Deep Learning-Based Survival Risk Stratification in ER+ Breast Cancer Through Multifeature and Multimodal Data Fusion,"](https://ieeexplore.ieee.org/document/10568932) in *IEEE Journal of Biomedical and Health Informatics*, 2024.
|
102 |
+
* 📓 R. K. Mondol, E. K. A. Millar, P. H. Graham, L. Browne, A. Sowmya, and E. Meijering, ["hist2RNA: An Efficient Deep Learning Architecture to Predict Gene Expression from Breast Cancer Histopathology Images,"](https://www.mdpi.com/2072-6694/15/9/2569) in *Cancers*, 2023.
|
103 |
+
* 📓 R. K. Mondol, N. D. Truong, M. Reza, S. Ippolito, E. Ebrahimie, and O. Kavehei, ["AFExNet: An Adversarial Autoencoder for Differentiating Breast Cancer Sub-types and Extracting Biologically Relevant Genes,"](https://ieeexplore.ieee.org/document/9378938) in *IEEE/ACM Transactions on Computational Biology and Bioinformatics*, 2021.
|
104 |
+
|
105 |
+
### CONFERENCE PROCEEDINGS
|
106 |
+
* 📄 R. K. Mondol, E. K. A. Millar, A. Sowmya, and E. Meijering, ["MM-Survnet: Deep Learning-Based Survival Risk Stratification in Breast Cancer Through Multimodal Data Fusion,"](https://doi.org/10.1109/ISBI56570.2024.10635810) in *2024 IEEE International Symposium on Biomedical Imaging (ISBI),* Athens, Greece, 2024, pp. 1-5.
|
107 |
+
* 📄 M.I. Khan, R. K. Mondol, M.A. Zamee, and T.A. Tarique, ["Hardware architecture design of anemia detecting regression model based on FPGA,"](http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=6850814&isnumber=6850678) in *International Conference on Informatics, Electronics Vision (ICIEV),* May 2014, pp. 1-5.
|
108 |
+
* 📄 Imran Khan, and R. K. Mondol, ["FPGA based leaf chlorophyll estimating regression model,"](http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7083557&isnumber=7083385) in *International Conference on Software, Knowledge, Information Management and Applications (SKIMA),* December 2014, pp. 1-6.
|
109 |
+
* 📄 R. K. Mondol, Imran Khan, Md. A.K. Mahbubul Hye, and Asif Hassan, ["Hardware architecture design of face recognition system based on FPGA,"](http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7193228&isnumber=7192777) in *International Conference on Innovations in Information Embedded and Communication Systems (ICIIECS),* March 2015, pp. 1-5.
|
110 |
+
* 📄 A. Hassan, R. K. Mondol, and M. R. Hasan, ["Computer network design of a company — A simplistic way,"](https://doi.org/10.1109/ICACCS.2015.7324121) in *2015 International Conference on Advanced Computing and Communication Systems (ICACCS),* Coimbatore, India, March 2015, pp. 1-4.
|
experience_detailed.md
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Detailed Professional Experience
|
2 |
+
|
3 |
+
## Current Position: Casual Academic at UNSW Sydney (July 2021 - Present)
|
4 |
+
|
5 |
+
### Role and Responsibilities
|
6 |
+
As a Casual Academic in the School of Computer Science and Engineering, Raktim contributes to undergraduate and postgraduate education while pursuing his PhD research.
|
7 |
+
|
8 |
+
**Teaching Duties**:
|
9 |
+
- Conduct laboratory sessions for computer science courses
|
10 |
+
- Lead tutorial classes on programming and algorithms
|
11 |
+
- Provide one-on-one mentoring to students
|
12 |
+
- Assist in course material development and updates
|
13 |
+
- Grade assignments and provide constructive feedback
|
14 |
+
|
15 |
+
**Courses Taught**:
|
16 |
+
- COMP1511: Programming Fundamentals
|
17 |
+
- COMP2521: Data Structures and Algorithms
|
18 |
+
- COMP3311: Database Systems
|
19 |
+
- COMP9417: Machine Learning and Data Mining
|
20 |
+
|
21 |
+
**Student Impact**:
|
22 |
+
- Mentored over 200 students across various courses
|
23 |
+
- Developed innovative teaching materials for complex concepts
|
24 |
+
- Received positive feedback for clear explanations and patient guidance
|
25 |
+
- Helped students transition from theoretical concepts to practical implementation
|
26 |
+
|
27 |
+
### Research Integration
|
28 |
+
- Incorporates current research findings into teaching materials
|
29 |
+
- Supervises undergraduate research projects
|
30 |
+
- Collaborates with faculty on curriculum development
|
31 |
+
- Organizes workshops on AI and machine learning topics
|
32 |
+
|
33 |
+
## Previous Role: Teaching Assistant at RMIT University (July 2017 - October 2019)
|
34 |
+
|
35 |
+
### Academic Responsibilities
|
36 |
+
During his Master's program, Raktim served as a Teaching Assistant, gaining valuable experience in higher education.
|
37 |
+
|
38 |
+
**Key Contributions**:
|
39 |
+
- Conducted weekly laboratory sessions for 50+ students
|
40 |
+
- Assisted in course delivery for computer science subjects
|
41 |
+
- Developed supplementary learning materials
|
42 |
+
- Provided technical support for programming assignments
|
43 |
+
|
44 |
+
**Courses Supported**:
|
45 |
+
- Introduction to Programming (Java, Python)
|
46 |
+
- Data Structures and Algorithms
|
47 |
+
- Database Systems
|
48 |
+
- Software Engineering Fundamentals
|
49 |
+
|
50 |
+
**Skills Developed**:
|
51 |
+
- Effective communication of complex technical concepts
|
52 |
+
- Patience and adaptability in teaching diverse student groups
|
53 |
+
- Time management and organizational skills
|
54 |
+
- Collaborative work with academic staff
|
55 |
+
|
56 |
+
### Research Activities
|
57 |
+
- Conducted literature reviews for research projects
|
58 |
+
- Participated in research group meetings
|
59 |
+
- Presented findings at internal seminars
|
60 |
+
- Collaborated on data collection and analysis
|
61 |
+
|
62 |
+
## Early Career: Lecturer at World University of Bangladesh (September 2013 - December 2016)
|
63 |
+
|
64 |
+
### Full-Time Academic Position
|
65 |
+
After completing his Bachelor's degree, Raktim joined as a full-time Lecturer in the Department of Computer Science and Engineering.
|
66 |
+
|
67 |
+
**Teaching Portfolio**:
|
68 |
+
- **Programming Courses**: C, C++, Java, Python programming
|
69 |
+
- **Core CS Subjects**: Data Structures, Algorithms, Database Systems
|
70 |
+
- **Mathematics**: Discrete Mathematics, Statistics for CS
|
71 |
+
- **Specialized Topics**: Computer Networks, Operating Systems
|
72 |
+
|
73 |
+
**Administrative Duties**:
|
74 |
+
- Course coordinator for multiple subjects
|
75 |
+
- Examination committee member
|
76 |
+
- Student advisor and mentor
|
77 |
+
- Curriculum development participant
|
78 |
+
|
79 |
+
### Student Supervision
|
80 |
+
- **Thesis Supervision**: Guided 15+ undergraduate thesis projects
|
81 |
+
- **Project Mentoring**: Supervised capstone projects in software development
|
82 |
+
- **Research Guidance**: Introduced students to research methodologies
|
83 |
+
- **Career Counseling**: Provided guidance on academic and career paths
|
84 |
+
|
85 |
+
**Notable Projects Supervised**:
|
86 |
+
- Web-based student management systems
|
87 |
+
- Mobile applications for local businesses
|
88 |
+
- Data analysis projects for social impact
|
89 |
+
- Machine learning applications in healthcare
|
90 |
+
|
91 |
+
### Professional Development
|
92 |
+
- Attended faculty development programs
|
93 |
+
- Participated in curriculum review committees
|
94 |
+
- Engaged in continuous learning through online courses
|
95 |
+
- Built networks with industry professionals
|
96 |
+
|
97 |
+
### Impact and Recognition
|
98 |
+
- Consistently received high student evaluation scores
|
99 |
+
- Recognized for innovative teaching methods
|
100 |
+
- Contributed to department's accreditation process
|
101 |
+
- Helped establish computer lab facilities
|
102 |
+
|
103 |
+
## Skills Developed Through Experience
|
104 |
+
|
105 |
+
### Teaching and Communication
|
106 |
+
- **Pedagogical Skills**: Developed effective teaching strategies for diverse learning styles
|
107 |
+
- **Public Speaking**: Comfortable presenting to large audiences
|
108 |
+
- **Technical Communication**: Ability to explain complex concepts simply
|
109 |
+
- **Cross-cultural Communication**: Experience with international student populations
|
110 |
+
|
111 |
+
### Leadership and Management
|
112 |
+
- **Team Coordination**: Led teaching teams and research groups
|
113 |
+
- **Project Management**: Managed multiple courses and research projects simultaneously
|
114 |
+
- **Mentoring**: Guided students and junior colleagues
|
115 |
+
- **Conflict Resolution**: Handled academic disputes and student concerns
|
116 |
+
|
117 |
+
### Technical and Research
|
118 |
+
- **Curriculum Development**: Designed course content aligned with industry needs
|
119 |
+
- **Assessment Design**: Created fair and comprehensive evaluation methods
|
120 |
+
- **Research Methodology**: Applied rigorous research practices
|
121 |
+
- **Technology Integration**: Incorporated new technologies into teaching
|
122 |
+
|
123 |
+
## Professional Networks and Collaborations
|
124 |
+
|
125 |
+
### Academic Collaborations
|
126 |
+
- **UNSW Research Groups**: Active member of multiple research teams
|
127 |
+
- **International Collaborations**: Partnerships with researchers globally
|
128 |
+
- **Industry Connections**: Collaborations with healthcare institutions
|
129 |
+
- **Conference Networks**: Regular participant in academic conferences
|
130 |
+
|
131 |
+
### Professional Memberships
|
132 |
+
- IEEE Computer Society member
|
133 |
+
- ACM member
|
134 |
+
- Australian Computer Society (ACS) member
|
135 |
+
- Bioinformatics Australia member
|
136 |
+
|
137 |
+
### Community Engagement
|
138 |
+
- **Peer Review**: Regular reviewer for academic journals
|
139 |
+
- **Conference Organization**: Committee member for academic conferences
|
140 |
+
- **Outreach Programs**: Participant in STEM education initiatives
|
141 |
+
- **Open Source Contributions**: Active contributor to research software projects
|
publications_detailed.md
ADDED
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Detailed Publications and Research Contributions
|
2 |
+
|
3 |
+
## BioFusionNet (2024)
|
4 |
+
**Full Title**: "BioFusionNet: Deep Learning-Based Survival Risk Stratification in ER+ Breast Cancer Through Multifeature and Multimodal Data Fusion"
|
5 |
+
|
6 |
+
**Journal**: IEEE Journal of Biomedical and Health Informatics
|
7 |
+
|
8 |
+
**Key Contributions**:
|
9 |
+
- Novel multimodal fusion architecture combining histopathology, genomics, and clinical data
|
10 |
+
- Attention-based feature selection for interpretability
|
11 |
+
- Superior performance compared to existing methods
|
12 |
+
- Clinical validation on large patient cohorts
|
13 |
+
|
14 |
+
**Technical Details**:
|
15 |
+
- Uses ResNet-based feature extraction for histopathology images
|
16 |
+
- Implements cross-attention mechanisms for data fusion
|
17 |
+
- Employs survival analysis with Cox proportional hazards
|
18 |
+
- Achieves C-index of 0.78 on validation datasets
|
19 |
+
|
20 |
+
**Impact**: This work provides clinicians with a comprehensive tool for patient risk assessment, enabling personalized treatment planning.
|
21 |
+
<!-- This is code for this paper -->
|
22 |
+
**GitHub**: [raktim-mondol/BioFusionNet](https://github.com/raktim-mondol/BioFusionNet)
|
23 |
+
|
24 |
+
## hist2RNA (2023)
|
25 |
+
**Full Title**: "hist2RNA: An Efficient Deep Learning Architecture to Predict Gene Expression from Breast Cancer Histopathology Images"
|
26 |
+
|
27 |
+
**Journal**: Cancers
|
28 |
+
|
29 |
+
**Key Contributions**:
|
30 |
+
- Direct prediction of gene expression from tissue images
|
31 |
+
- Efficient architecture suitable for clinical deployment
|
32 |
+
- Identification of morphology-gene expression relationships
|
33 |
+
- Validation across multiple cancer datasets
|
34 |
+
|
35 |
+
**Technical Details**:
|
36 |
+
- Custom CNN architecture optimized for gene expression prediction
|
37 |
+
- Multi-task learning framework
|
38 |
+
- Attention mechanisms for spatial feature importance
|
39 |
+
- Correlation analysis with known biological pathways
|
40 |
+
|
41 |
+
**Impact**: Enables gene expression profiling without expensive molecular assays, making personalized medicine more accessible.
|
42 |
+
<!-- This is code for this paper -->
|
43 |
+
**GitHub**: [raktim-mondol/hist2RNA](https://github.com/raktim-mondol/hist2RNA)
|
44 |
+
|
45 |
+
## AFExNet (2021)
|
46 |
+
**Full Title**: "AFExNet: An Adversarial Autoencoder for Differentiating Breast Cancer Sub-types and Extracting Biologically Relevant Genes"
|
47 |
+
|
48 |
+
**Journal**: IEEE/ACM Transactions on Computational Biology and Bioinformatics
|
49 |
+
|
50 |
+
**Key Contributions**:
|
51 |
+
- Adversarial training for robust feature learning
|
52 |
+
- Automatic biomarker discovery
|
53 |
+
- Cancer subtype classification
|
54 |
+
- Biologically interpretable features
|
55 |
+
|
56 |
+
**Technical Details**:
|
57 |
+
- Adversarial autoencoder architecture
|
58 |
+
- Gene selection based on reconstruction importance
|
59 |
+
- Validation on TCGA datasets
|
60 |
+
- Pathway enrichment analysis
|
61 |
+
|
62 |
+
**Impact**: Provides insights into cancer biology while achieving high classification accuracy.
|
63 |
+
<!-- This is code for this paper -->
|
64 |
+
**GitHub**: [raktim-mondol/breast-cancer-sub-types](https://github.com/raktim-mondol/breast-cancer-sub-types)
|
65 |
+
|
66 |
+
## Ongoing Research
|
67 |
+
|
68 |
+
### Multimodal Foundation Models
|
69 |
+
- Developing foundation models for medical imaging
|
70 |
+
- Pre-training on large-scale medical datasets
|
71 |
+
- Transfer learning for rare diseases
|
72 |
+
|
73 |
+
### Ongoing Research
|
74 |
+
- Large Language Models (LLMs)
|
75 |
+
- Retrieval-Augmented Generation (RAG)
|
76 |
+
- Fine-tuning and domain adaptation
|
77 |
+
|
78 |
+
|
79 |
+
### AI Ethics in Healthcare
|
80 |
+
- Bias detection and mitigation
|
81 |
+
- Fairness in medical AI
|
82 |
+
- Regulatory compliance frameworks
|
research_details.md
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Detailed Research Information
|
2 |
+
|
3 |
+
## PhD Research: Deep Learning Based Prognosis and Explainability for Breast Cancer
|
4 |
+
|
5 |
+
### Research Objectives
|
6 |
+
1. Develop novel deep learning architectures for breast cancer survival prediction
|
7 |
+
2. Create explainable AI models that clinicians can trust and understand
|
8 |
+
3. Integrate multimodal data (histopathology images, genomics, clinical data)
|
9 |
+
4. Build treatment recommendation systems based on patient-specific factors
|
10 |
+
|
11 |
+
### Key Innovations
|
12 |
+
- **BioFusionNet**: A multimodal fusion network that combines histopathology images with genomic and clinical data for survival risk stratification
|
13 |
+
- **hist2RNA**: An efficient architecture that predicts gene expression directly from histopathology images
|
14 |
+
- **AFExNet**: An adversarial autoencoder for cancer subtype classification and biomarker discovery
|
15 |
+
|
16 |
+
### Technical Approach
|
17 |
+
- Utilizes attention mechanisms for interpretability
|
18 |
+
- Employs transfer learning from pre-trained vision models
|
19 |
+
- Implements novel fusion strategies for multimodal data
|
20 |
+
- Uses adversarial training for robust feature learning
|
21 |
+
|
22 |
+
### Clinical Impact
|
23 |
+
The research aims to provide clinicians with:
|
24 |
+
- More accurate prognosis predictions
|
25 |
+
- Personalized treatment recommendations
|
26 |
+
- Explainable AI decisions for clinical trust
|
27 |
+
- Cost-effective diagnostic tools
|
28 |
+
|
29 |
+
## Current Projects
|
30 |
+
|
31 |
+
### Large Language Models for Healthcare
|
32 |
+
- Fine-tuning LLMs for medical text analysis
|
33 |
+
- Developing RAG systems for clinical decision support
|
34 |
+
- Creating conversational AI for patient education
|
35 |
+
|
36 |
+
### Multimodal AI Systems
|
37 |
+
- Vision-language models for medical imaging
|
38 |
+
- Cross-modal retrieval systems
|
39 |
+
- Multimodal fusion architectures
|
40 |
+
|
41 |
+
### Explainable AI
|
42 |
+
- Attention visualization techniques
|
43 |
+
- Counterfactual explanations
|
44 |
+
- Feature importance analysis
|
45 |
+
- Clinical decision support systems
|
skills_expertise.md
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Technical Skills and Expertise
|
2 |
+
|
3 |
+
## Deep Learning and Machine Learning
|
4 |
+
|
5 |
+
### Core Frameworks
|
6 |
+
- **PyTorch**: Advanced proficiency in model development, custom layers, and distributed training
|
7 |
+
- **TensorFlow**: Experience with TensorFlow 2.x, Keras, and TensorFlow Serving
|
8 |
+
- **Hugging Face Transformers**: Fine-tuning, model deployment, and custom tokenizers
|
9 |
+
- **scikit-learn**: Classical ML algorithms, preprocessing, and model evaluation
|
10 |
+
|
11 |
+
### Specialized Techniques
|
12 |
+
- **Transfer Learning**: Pre-trained model adaptation, domain adaptation
|
13 |
+
- **Attention Mechanisms**: Self-attention, cross-attention, multi-head attention
|
14 |
+
- **Adversarial Training**: GANs, adversarial autoencoders, robust training
|
15 |
+
- **Multi-task Learning**: Joint optimization, task balancing, shared representations
|
16 |
+
- **Meta-Learning**: Few-shot learning, model-agnostic meta-learning
|
17 |
+
|
18 |
+
## Large Language Models and NLP
|
19 |
+
|
20 |
+
### LLM Technologies
|
21 |
+
- **Parameter-Efficient Fine-tuning**: LoRA, QLoRA, AdaLoRA, Prefix tuning
|
22 |
+
- **Quantization**: GPTQ, GGUF, 8-bit and 4-bit quantization
|
23 |
+
- **Model Optimization**: Pruning, distillation, efficient architectures
|
24 |
+
- **Prompt Engineering**: Chain-of-thought, few-shot prompting, instruction tuning
|
25 |
+
|
26 |
+
### NLP Applications
|
27 |
+
- **Text Generation**: Controlled generation, style transfer, summarization
|
28 |
+
- **Information Extraction**: Named entity recognition, relation extraction
|
29 |
+
- **Question Answering**: Reading comprehension, open-domain QA
|
30 |
+
- **Sentiment Analysis**: Aspect-based sentiment, emotion detection
|
31 |
+
|
32 |
+
## Computer Vision and Medical Imaging
|
33 |
+
|
34 |
+
### Vision Architectures
|
35 |
+
- **Convolutional Networks**: ResNet, DenseNet, EfficientNet, Vision Transformers
|
36 |
+
- **Object Detection**: YOLO, R-CNN family, DETR
|
37 |
+
- **Segmentation**: U-Net, Mask R-CNN, Segment Anything Model (SAM)
|
38 |
+
- **Medical Imaging**: Specialized architectures for histopathology, radiology
|
39 |
+
|
40 |
+
### Image Processing
|
41 |
+
- **Preprocessing**: Normalization, augmentation, color space conversion
|
42 |
+
- **Feature Extraction**: SIFT, HOG, deep features
|
43 |
+
- **Registration**: Image alignment, geometric transformations
|
44 |
+
- **Quality Assessment**: Blur detection, artifact identification
|
45 |
+
|
46 |
+
## Multimodal AI and Fusion
|
47 |
+
|
48 |
+
### Multimodal Architectures
|
49 |
+
- **Vision-Language Models**: CLIP, BLIP, LLaVA, DALL-E
|
50 |
+
- **Fusion Strategies**: Early fusion, late fusion, attention-based fusion
|
51 |
+
- **Cross-modal Retrieval**: Image-text matching, semantic search
|
52 |
+
- **Multimodal Generation**: Text-to-image, image captioning
|
53 |
+
|
54 |
+
### Data Integration
|
55 |
+
- **Heterogeneous Data**: Combining images, text, tabular data
|
56 |
+
- **Temporal Fusion**: Time-series integration, sequential modeling
|
57 |
+
- **Graph Neural Networks**: Relational data modeling, knowledge graphs
|
58 |
+
|
59 |
+
## Retrieval-Augmented Generation (RAG)
|
60 |
+
|
61 |
+
### Vector Databases
|
62 |
+
- **FAISS**: Efficient similarity search, index optimization
|
63 |
+
- **ChromaDB**: Document storage and retrieval
|
64 |
+
- **Weaviate**: Vector search with filtering
|
65 |
+
- **Milvus**: Scalable vector database management
|
66 |
+
|
67 |
+
### Retrieval Techniques
|
68 |
+
- **Dense Retrieval**: Bi-encoder architectures, contrastive learning
|
69 |
+
- **Sparse Retrieval**: BM25, TF-IDF, keyword matching
|
70 |
+
- **Hybrid Search**: Combining dense and sparse methods
|
71 |
+
- **Re-ranking**: Cross-encoder models, relevance scoring
|
72 |
+
|
73 |
+
### RAG Optimization
|
74 |
+
- **Chunk Strategies**: Document segmentation, overlap handling
|
75 |
+
- **Embedding Models**: Sentence transformers, domain-specific embeddings
|
76 |
+
- **Query Enhancement**: Query expansion, reformulation
|
77 |
+
- **Context Management**: Relevance filtering, context compression
|
78 |
+
|
79 |
+
## Bioinformatics and Computational Biology
|
80 |
+
|
81 |
+
### Genomics
|
82 |
+
- **Sequence Analysis**: Alignment algorithms, variant calling
|
83 |
+
- **Gene Expression**: RNA-seq analysis, differential expression
|
84 |
+
- **Pathway Analysis**: Enrichment analysis, network biology
|
85 |
+
- **Population Genetics**: GWAS, linkage analysis
|
86 |
+
|
87 |
+
### Proteomics
|
88 |
+
- **Protein Structure**: Structure prediction, folding analysis
|
89 |
+
- **Mass Spectrometry**: Data processing, protein identification
|
90 |
+
- **Protein-Protein Interactions**: Network analysis, functional prediction
|
91 |
+
|
92 |
+
### Systems Biology
|
93 |
+
- **Network Analysis**: Graph theory, centrality measures
|
94 |
+
- **Mathematical Modeling**: Differential equations, stochastic models
|
95 |
+
- **Multi-omics Integration**: Data fusion, pathway reconstruction
|
96 |
+
|
97 |
+
## Cloud Computing and MLOps
|
98 |
+
|
99 |
+
### Cloud Platforms
|
100 |
+
- **AWS**: EC2, S3, SageMaker, Lambda, ECS
|
101 |
+
- **Google Cloud**: Compute Engine, Cloud Storage, Vertex AI
|
102 |
+
- **Azure**: Virtual Machines, Blob Storage, Machine Learning Studio
|
103 |
+
|
104 |
+
### MLOps Tools
|
105 |
+
- **Model Versioning**: MLflow, DVC, Weights & Biases
|
106 |
+
- **Containerization**: Docker, Kubernetes, container orchestration
|
107 |
+
- **CI/CD**: GitHub Actions, Jenkins, automated testing
|
108 |
+
- **Monitoring**: Model drift detection, performance monitoring
|
109 |
+
|
110 |
+
### Distributed Computing
|
111 |
+
- **Parallel Processing**: Multi-GPU training, data parallelism
|
112 |
+
- **Cluster Computing**: Spark, Dask, distributed training
|
113 |
+
- **Resource Management**: SLURM, job scheduling, resource optimization
|
114 |
+
|
115 |
+
## Programming and Software Development
|
116 |
+
|
117 |
+
### Programming Languages
|
118 |
+
- **Python**: Advanced proficiency, scientific computing, web development
|
119 |
+
- **R**: Statistical analysis, bioinformatics packages, visualization
|
120 |
+
- **SQL**: Database design, query optimization, data warehousing
|
121 |
+
- **JavaScript/TypeScript**: Web development, Node.js, React
|
122 |
+
- **Bash/Shell**: System administration, automation scripts
|
123 |
+
|
124 |
+
### Development Tools
|
125 |
+
- **Version Control**: Git, GitHub, collaborative development
|
126 |
+
- **IDEs**: VS Code, PyCharm, Jupyter notebooks
|
127 |
+
- **Documentation**: Sphinx, MkDocs, technical writing
|
128 |
+
- **Testing**: Unit testing, integration testing, test-driven development
|
129 |
+
|
130 |
+
## Research and Academic Skills
|
131 |
+
|
132 |
+
### Research Methodology
|
133 |
+
- **Experimental Design**: Hypothesis testing, statistical power analysis
|
134 |
+
- **Literature Review**: Systematic reviews, meta-analysis
|
135 |
+
- **Peer Review**: Journal reviewing, conference reviewing
|
136 |
+
- **Grant Writing**: Research proposals, funding applications
|
137 |
+
|
138 |
+
### Communication
|
139 |
+
- **Technical Writing**: Research papers, documentation, tutorials
|
140 |
+
- **Presentations**: Conference talks, poster presentations
|
141 |
+
- **Teaching**: Course development, student mentoring
|
142 |
+
- **Collaboration**: Interdisciplinary research, team leadership
|