DNA-diffusion team & contributions

	A	B	C	D	E	F	G	H	I
1		Discord Username on OpenBioML	STILL INTERESTED IN CONTRIBUTIING	Short intro	Skills	Active contribution or observer?	Tasks I am working on or I could contribute, The list of all the tasks and active tasks is available here: https://github.com/orgs/pinellolab/projects/3/views/1	GITHUB USERNAME	Added

2	Luca Pinello	Luca Pinello	yes	I am an Associate Professor at Harvard Medical School and MGH in Boston, USA	Gene regulation, genomics data analyses, genome editing, single-cell omics, machine learning, visualization, web development	Very active! I started the project and I am planning to spend substaintal time on it	1) Define internal metrics to evaluate the quality of the produced sequences 2) Curate datasets that can be used to define conditioning 3) Define plan for experimental validation	lucapinello	x
3	Lucas Ferreira	Lucas Ferreira	yes	I'm a Posdoc Research Fellow at Luca Pinello lab (Harvard Medical School and MGH Boston, USA)	Bioinformatics, Gene regulation, Epigenetics, single-cell omics, DL, ML	Very active, I prototyped and adapted the initial DNA bitdiffusion model. Currently implementing model evaluation metrics and adapting conditional generation	1) Prototyping the first model; Exploring architectures; 2) Creating and testing internal metrics (Ex: motifs distance, FID); 3) Developing and implementing new conditioning variables (ex: motifs); 4) Benchmarking againts other models 5)Define internal metrics to evaluate the quality of the produced sequences	LucasSilvaFerreira	x
4	Wouter Meuleman	meuleman	yes	Investigator at Altius Institute for Biomedical Sciences and Affiliate Associate Professor at the University of Washington, Seattle WA U.S.A.	Genome organization, gene regulation, data visualization, large-scale genomic data analyses, machine learning	Very active, provided initial datasets and annotations, co-drafted proposal. This work is essentially a continuation of work in my own group	1) Define the base dataset to use for building predictive and generative models. 2) Curate these datasets into higher-confidence subsets to decrease label noise. 3) Provide guidance and education on the source and experimental assays related to the datasets, the Biological background as it relates to gene regulation, and assumptions regarding behavior/distribution of the data. 4) Evaluate models and their results in the context of existing work, and in silico vs. in vitro experimental validation assays. 5) Formulate testable hypotheses and their evaluations. 6) Capture insights and conclusions into widely accessible scientific writing.	meuleman	x
5	Zach Nussbaum	nussy	yes	ML Engineer @ Deep Genomics, Previously at Amazon	Machine Learning, Deep Learning, NLP/Transformers, DL applied to Genomics	Very active, helping augment the current training code to allow for conditioning	Adding classifier free conditiong for training, augmenting UNet code + verifying implementation is correct, training on motif dataset + cell type	zanussbaum	x
6	Niccolo' Zanichelli	Niccolo' Zanichelli
7	César Miguel Valdez Córdova	César Miguel (semibah#0612)	yes	Master's student @ JKU Linz	DL, ML, Life sciences data (protein/genomics), Causality, Generative Models, Scientific Writing	Very active. I want to see the project get completed and will contribute substantially, timewise, to it.	Benchmarking, Model exploration, extension and interpretation. General project writing, communicating.	cmvcordova	x
8	Matei Bejan	Matei Bejan (Vrööm)	yes	PhD Student in AI, Deep Learning Research Scientist	ML, DL, PyTorch, Attention, Diffusion.	Very active	VQ-VAE model trianing, UNet refactorization & optimization. Can offer guidance on other tasks (e.g. sampling, scalability). If there are enough people involved and I have the time, I can get involved in these "other tasks" as well.	mateibejan1	x
9	Sameer Gabbita	sameer1	yes	AI student researcher @ MGH	ML/DL, PyTorch, Generative Modeling	Active - currently developing autoencoder models to potentially diffuse in latent space	Training a VQ-VAE for DNA-sequences for stable diffusion; Core model, benchmarking, model exploration	sg134	x
10	Aaron Wenteler	aaron_w	yes	PhD student @ Queen Mary University of London	ML, DL, Bioinformatics, Genomics, Drug Discovery, Interpretability	Very interested in actively contributing wherever I can.	1) Currently thinking about downstream applications of generative DNA models for drug discovery. Have some ideas about this which I'll put in proper writing. 2) Benchmarking and evaluation 3) Optimizing and refactoring UNET (want to be involved with model engineering and training, but more from the sidelines to learn and help out where I can)	aaronwtr	x
11	Hassan Ahmed			Data Scientist/ML Engineer at EoN Next	ML engineering, DL, Experimentation/ Experiment design	Very interested in actively contributing wherever I can	Implement a sequence quality metric based on k-mer composition	hssn-20
12	Mihir Tripathy	Mihir	yes	Computer Science Undergrad, DL Researcher in Computational Biology and SLAM.	ML, DL, Pytorch, Tensorflow, Keras, Computer Vision and Data Engineering	Actively contributing.	Refactoring and optimizing the UNET diffusion code	mihirneal	x
13	Moughees Ahmed	ghees	yes	engineer at startup in toronto, research in comp bio/genomics @ Emory, bioninformatics, software engineer, NLP and speech research	BioML, anything software	Active	Data building, modelling	codeghees	x
14	Ihab Bendidi	Ihab	yes	PhD candidate at ENS-PSL Paris	Deep Learning, bioml, self supervised learning	actuve contributor	Distributed training on pytorch lightning	IhabBendidi	x
15	Simon Senan	ssenan	yes	MSc Data Science	ML, DL, Computer vision relating to medical imaging	Active contributer where needed	Refactoring and optimizing the UNET diffusion code, implementing dataloader	ssenan	x
16	Saurav Maheshkar	psych0man#4316	yes	Machine Learning Engineer, Open Source Contributor, Ex: @Weights & Biases	Deep Learning (Google Developer Expert in ML), Natural Language Processing, Computer Vision	Would love to be a active contributor	Refactoring the UNET bit diffusion code, Benchmarking against other tools (GAN paper, Transformer implementation), Explore othe architetures for denoising	SauravMaheshkar	x
17	Jan Sobotka	jan_s	yes	Bachelor student of Computer Science @ CTU Prague, ML Engineer @ Generali	ML, DL, reinforcement learning, computer vision, full-stack web development, competitive programming	Would love to actively contribute wherever needed!	0) Currently exploring the notebook and data 1) Training a VQ-VAE for DNA-sequences for stable diffusion; 2) Explore othe architetures for denoising; 3) Benchmarking against other tools	Johnny1188	x
18	Ethan Cohen	ethan_cohen	Yes	Phd student @ENS Paris	ML, DL, Computer vision, DL applied to Bioimages	Would love to actively contribute wherever needed and as much as I can		ethancohen123	x
19	Abraham Owodunni		Yes	Researcher at Sisonke Biotik	DL, ML, and a bit of XAI	Really want to be active	to be decided	owos
20	Jon Chen	Jon Chen	yes	I'm a postdoc in the Collins lab at MIT/Broad studing RNA-small molecule interactions, PhD with David Liu where I built VAEs for generating DNA sequences with small molecule binding capabilities	ML, DL, Pytorch, oligonucleotide folding and binding, VAEs for sequence generation	Contribution	Create function motif_count Input, general model development	joncchen
21	Shashank Yadav	xinfy	yes	1st year PhD student in Biomedical Engineering at UArizona.	ML DL	Observer and Learner		xinformatics
22	Martino Mansoldo	mm65	yes	Machine Learning Engineer, Master in AI @ U of Edinburgh	Python, PyTorch, Deep Learning, Transformers, GNNs, software engineering	Would like to contribute	Getting up to speed	mansoldm	x
23	Dev Vidhani	DevV		Full time ML Practitioner in industry for last 4 years - originally focussed on NLP; Currently learning theories to understand DL	ML, DL, NLP, Multimodal (Vision, NLP) Diffusion models, VAE models Optimizers, Loss landscape, bayesian ML Theoretical understanding of DL PyTorch	Active		devvidhani	x
24	Patrick Bryant			Mixed background, PhD in protein structure prediction, Postdoc in Berlin	Various biological problems, Deep Learning; https://patrickbryant1.github.io/research.html	Active		patrickbryant1	x
25	PeePa			1 year experience as a Cloud Engineer, new to ML. Given a failed attempt to recreate brainport in uni. New to learn ML, interest in learning epigenetics with technology that has been used to create brainport (hardware side).	Terraform, Python	Observing, really want to be active, and mostly wanting to learn	Tasks I am working on: Creating a dataloader and unit test. End goals: Learn how this model is built, and get a headstart in creating epigenetics projects	JhonSummer	x
26	Jae Shin			PhD Student, Computational biology	bioinformatics	Would like to contribute		jaewshin	x
27	Marla	ceznaka301#0779		Machine Learning Engineer, Master in CS @ TUM	Machine Learning, deep Learning, Medical Imaging, PyTorch	Interested in actively contributing but still trying to understand many things around the project		nagam11	x
28	Stuti	kingstut		ML engineer contractor	ML	Would like to contribute	Embedding so that stable diffusion can be used for this project	kingstut	x
29	Afshan	afshan22		ML engineer	ML, bioinformatics, bio sequence models	Interested in active contribution	Getting up to speed with project so far. Taking notes.	nabiafshan	x
30	Omar Ayyub	tent		PhD Bioengineering, Biochemical Genetic Disorders, Diagnostics	Genetics, python, pytorch, web development	Will observe for now until I can contribute in a meaningful manner.		obayyub	x
31	Giulio Tosato	artificial.giulio		bachelor student in artificial intelligence & cognitive science, university background in math	Pytorch,Keras, Medical imagining (nn-unet), brain computer interface, fast learning and creative mind	actively contribuiting wherever my help could me useful	getting familiar with all this	artificialgiulio	x
32	Dashiell Stander			ML Scientist @ Eleuther AI & Stability	Jax & Pytorch, ML Engineering, Diffusion & Score Matching	Interested in actively contributing.
33	Michael Pieler			OpenBioML and Eleuther AI	DL, multimodal CLIP setup, contrastive learning, biotech		multi-GPU training, HPC setup, CLIP setups (if needed)
34	MIhai Todor			Software Engineer / Tech Lead working on Data Streaming, Scalability and Open Source software	No specific background in the field, trying to learn and looking to work on computational biology in the future (epigenomics, immunotherapy for cancer, ageing). I spent many years working with Go, C++, all things Kubernetes etc. Details here: https://www.linkedin.com/in/mtodor	Mostly observing, would be curious to hear if there's any interest to collaborate on training models and running them at scale
35	Harsha			Master's in CS @ IIITH	ML, DL, Knowledge graphs, Data Driven Drug Discovery	Oberving right now, would love to contribute once i was free
36	David Laub			PhD student @ UC San Diego	ML/DL for genomics	Mostly observing
37	Arsenii Zinkevich			PhD student, Bioinformatics, Drug Target Discovery	ML, Bioinformatics, Genomics, Data research, Docker
38	Daniel Maturana			PhD in Biochemistry, experience annotating genomes and regulatory in bacteria. Working with NanoTemper	DL learner, python programming, genomic, proteins and interactions studies	Mostly observing, but interesting to give feedback, learn and collaborate as much as possible
39	Elizaveta Noskova			Master's student, bioinformatician	Machine learning, deep learning, Pytorch
40	Matt Fisher			Founding Engineer @ Vizcom.ai - Generative 3D AI; Eleuther contributor; CRISPR Cas9 Hobbyist	PyTorch script writing; training	Active; Genome Auto-encoder (?)
41	Rushikesh Zawar			Research Engineer in Computer Vision(Graduated with B.E. Computer Science & Masters in Biological Sciences)	ML/DL, Computer Vision, Reinforcement Learning, Biological Sciences (wet-lab in gen-tech, RDNA and bioinformatics)	Observing right now. Would love to contribute, but after a few weeks, because of some other commits
42	James Hennessy				Ml,Bioinformatics,Chemoinformatics, Computer vision, NLP, Data Engineering	Would love to activley contribute	Web scraping, Data set constirctuion, General Coding, model building, ml ops?
43	Tyler Kolody			I am a Canadian CS MSc student working on materials generation using diffusion and topological data analysis.	Materials Informatics and associated libraries, NLP, generative modeling, Data engineering, web scraping	More interested in observing, but am happy to contribute to the components that overlap with my own research.	General consulting/discussion contribution, web scraping, data representation
44	Wuhao Chen			Master Student in AI at Imperial	ML, DL, PyTorch, Generative models, GNN	Would love to contribute now	Model implementation, training, and experimentation, Exploratory dataset analysis and processing, Refactoring the UNET bit diffusion code, Explore othe architetures for denoising
45	Geo Jolly			Bachelor student of Computer Science, researcher @ucsc and @amrita	DL, RL, Generative Models, PyTorch	would like to contribute	Refactoring the UNET bit diffusion code Training a VQ-VAE for DNA-sequences for stable diffusion
46	Karan Dahele			Soon to be MD. ML engineer/data scientist at drug discovery/genomics start-up. Applying generative models to genotype data	ML/DL (PyTorch), bioinformatics, medicine, writing	Active	Model building, protocols for evaluation/analysis of results, writing with biomedical context
47	Derek Neuland			data scientist, researcher @ Puzzle Labs	Data research, data collection, front-end development, design, project management	Very interested in being active contributor, wherever I can help	Research, data analysis, collecting and organizing data, creating datasets, cleaning datasets, designing visual components, designing internal workflows, project management
48	Dmitry Penzar			phd student, data scientist, bioinformatician	sequence-based expression prediction, SNV effect prediction, classical machine learning and deep learning	Interested in actively contributing.	model training, model architecture modifications, have several datasets for the evaluation
49	Jonas Grabbe	Jonas Grabbe#0649		data scientist, researcher @ Oxcitas	Machine Learning, Deep Learning, Geometric DL, Data Driven Drug Discovery	Observing for now. Interested in contributing once I have a bit more time.		JonasGrabbe	x
50	Eeshit Dhaval Vaishnav	edv	yes	https://www.mit.edu/~edv/	https://www.linkedin.com/in/1edv	Both	Anything necessary for the project.	1edv	x
51	Nwanna Joseph N.	Code.Dev		Data scientist, AI researcher , B.Tech in computer science, Masters in Machine Intelligence. Formerly Senior Android developer, currently Data scientist and Machine Intelligence researcher. Pytorch pro and Contributor to scikit learn	Machine learning, Deep learning, Transformers, Pytorch, Python,	Code Contribution	Implement evaluation metrics	Nwanna-Joseph	x
52	Phung Cheng Fei	buttercutter#1033		Data engineer	Pytorch	Would love to actively contribute wherever needed!	Anything necessary for the project.	buttercutter	x
53	Ifty Mohammad Rezwan	Ifty#5354		Machine Learning Engineer @ Neovotech, Research Assistant @ NSU	Deep Learning (General CV and NLP), Python Scripting, Basic API design	Active contribution	Modelling, Data Gathering and DataLoaders and Scripting if necessary. For now I can try the task (Integrate Maximal Update Parametrization (MuP) for hyperparameter tuning). Seems to be the one open on the board. Can Also Work on upgrading core models a bit	imr555
54	Francesco Sacco	AScaccoLad		Just graduated masters is physics	Physics, BioML, Pytorch	I wish to be an Active contributor	Modelling	Francesco215	x
55	Apoorva Srinivasan	Apoorva	yes	Data scientist, MS in biostats @Columbia University	ML, GANS, statistics, proteomics	Active contributor		apoorvasrinivasan26
56	Noah Weber	noahweber	yes	CTO @ CelerisTx	All things ML & Data	Active	Codebase; development and the Algo research	noahweber1
57	Szilard Polgar	Szilard#9346	yes	data engineer in finance - biochemistry/ML enthusiast	data pipelines, ML	Active from December		szilapo
58	Cheyenne Ziegler	cheyziggy	yes	Phd candidate in comp bio @ UTD, ML/AI Engineer @ EMD Serono	BioML, anything software	Active	Currently working on unit test, really can contribute to anything	ceziegler
59	Oliver Nash	orinoco	Yes	PhD Candidate @ UCL in Engineering	ML, Data, Genomics, Product Management, Policy, Safety	Both		olivernash
60	Peter Clarke	resurgo#1669	Yes	AI/genomics startup CEO/researcher >15 years bioinformatics @sanger, Cambridge Uni, Caltech	PyTorch, Bioinformatics, RNA, Chromatin	Previos observer, now wanting to contribute		fourpartswater
61	Albert Wang	bertie	Yes	Currently building with EF, undergrad at McMaster University (biomedical engineering, health sciences, math)	Beginner, self-taught ML / AI. Python, MATLAB.	Active observor - would love to build skills to a level that I can contribute.	Perhaps I can help review papers and apply product management skills while learning technical skills?	albertyqw
62	Kieran Didi	Kieran Didi	Yes			Active contributor		kierandidi
63
64	Gabriel Dolsten	gaeb	Yes	PhD Student at Princeton	Genomics/ML	Active contributor
65	Younwoo (Ethan) Choi	fdejong	Yes	CS undergrad @ University of Toronto, student researcher @ Vector Institute	ML, NLP, PyTorch	Active contributor		younwoochoi	x
66	Zelun Li	l-z-l.m	YES	Bioinformatics Honours student @ UNSW @ Wong lab(victor chang)	PyTorch, Bioinformatics, epigenetics	Active contributor		l-z-l
67	Aneeqa Fatima	daisies	Yes	CS @ University of Michigan, Master in Applied Math @ University of Washington, Senior SWE @ MSFT on high performance model optimization and kernel development for ASICs	ML, PyTorch, C++, HPC	Observer for now
68	Arnab Bhattacharya	Arnab	Yes	Software Developer (Frontend, Backend microservices, DL, ML)	Pytorch, Tensorflow, React, Node.js, Rust, Go	Active contributor	DNA Embedding, API and User facing apps	arnab28122000
69	Tian-Lai (Leo) Zang	TZ	Yes	BME @ Duke, working on diffusion model before	Pytorch, DL, NLP, Protein Design, Microbiology	Wish to be a active contributor	DNA Embedding, Guided Diffusion
70	Xuan He	chord233		bachelor student in CS，Interested in AI4Science	Pytorch,Tensorflow,AI4Science	Observer for now，would like to contribute		chord233
71	Shaishav Jain	dragonSlayer01#6399	Yes	Associate Data Science Consultant @ ZS Associates	ML/AI, Pytorch, NLP, Transformers, Stable Diffusion, Bioinformatics	Wish to be a Active contributor	Would love to work on the following tasks: Consider DNA embedding models to transition to use stable diffusion, Implement a sequence quality metric based on existing neural networks that can predict enhancer activity (Bert based), expression (Enformer) or chromatin accessibility (BPnet)	dragonslayer01
72	Talha Khan	talk24#4274	Yes		ML/AL,Pytorch,Tensorflow,AWS,Web	active contributor		talkhanz
73	Michael Leone	mjleone#1505	Yes	MD/PhD Student at Carnegie Mellon in Andreas Pfenning Lab	ML, Tensorflow, Epigenomics, snATAC-seq analysis	observer, want to contribute
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100