diff --git a/configs/dmmm copy.yaml b/configs/dmmm copy.yaml new file mode 100644 index 00000000..b4d28ff1 --- /dev/null +++ b/configs/dmmm copy.yaml @@ -0,0 +1,106 @@ +hash_length: 7 + +containers: + registry: + base_url: docker.io + owner: reedcompbio + framework: docker + unpack_singularity: false + +reconstruction_settings: + locations: + reconstruction_dir: "output" + +analysis: + summary: + include: true + cytoscape: + include: false + ml: + # TODO: we either need at least one non-empty pathway in all algorithm runs, + # or we need to get rid of validate_df hard-erroring. The latter seems better. + include: false + aggregate_per_algorithm: false + evaluation: + include: false + +# Custom settings +algorithms: + - name: "omicsintegrator1" + include: true + runs: + run1: + b: 2 + w: .5 + d: 10 + mu: 2 + + - name: "omicsintegrator2" + include: true + runs: + run1: + b: 4 + g: 0 + + - name: "pathlinker" + include: true + runs: + run1: + k: 100 + + #- name: "meo" + # include: true + # runs: + # run1: + # max_path_length: 3 + # local_search: true + # rand_restarts: 10 + + - name: "allpairs" + include: true + + - name: "domino" + include: true + runs: + run1: + slice_threshold: 0.3 + module_threshold: 0.05 + + - name: "rwr" + include: true + runs: + run1: + alpha: 0.85 + threshold: 100 + + - name: "diamond" + include: true + runs: + run1: + n: 1 +datasets: + - label: dmmmegfr_string + data_dir: datasets/egfr + edge_files: ["processed/interactome.tsv"] + node_files: ["processed/prizes.txt"] + other_files: [] + - label: dmmmegfr_irefindex + data_dir: datasets/egfr + edge_files: ["processed/phosphosite-irefindex13.0-uniprot.txt"] + node_files: ["processed/prizes-uniprot.txt"] + other_files: [] + # Yeast: https://github.com/tristan-f-r/spras-benchmarking/blob/9477d85871024a5e3a4b0b8b9be7e78c0d0ee961/yeast_osmotic_stress/config.yaml + - label: dmmmyeast + node_files: ["prizes1_dummies.txt"] + edge_files: ["network1.txt"] + other_files: [] + data_dir: "datasets/yeast_osmotic_stress/processed" +gold_standards: + - label: gs_egfr_string + node_files: ["processed/gold-standard-nodes.txt"] + data_dir: datasets/egfr + dataset_labels: ["dmmmegfr_string"] + - label: gs_egfr_irefindex + node_files: ["processed/gold-standard-nodes-uniprot.txt"] + data_dir: datasets/egfr + dataset_labels: ["dmmmegfr_irefindex"] diff --git a/configs/dmmm.yaml b/configs/dmmm.yaml index 6fddc62c..bf6c577b 100644 --- a/configs/dmmm.yaml +++ b/configs/dmmm.yaml @@ -13,14 +13,14 @@ reconstruction_settings: analysis: summary: - include: false + include: true cytoscape: include: false ml: # TODO: we either need at least one non-empty pathway in all algorithm runs, # or we need to get rid of validate_df hard-erroring. The latter seems better. include: false - aggregate_per_algorithm: true + aggregate_per_algorithm: false evaluation: include: false @@ -34,7 +34,7 @@ algorithms: w: .5 d: 10 mu: 2 - # TODO: egfr prefers dummy_mode: ["file"] since we manually specify EGF_HUMAN as one. + - name: "omicsintegrator2" include: true runs: @@ -42,6 +42,20 @@ algorithms: b: 4 g: 0 + # domino requires too much memory for dmmmegfr_string (Docker OOM). Disabled. + - name: "domino" + include: false + runs: + run1: + slice_threshold: 0.3 + module_threshold: 0.05 + + # diamond requires 'active' column, which yeast dataset lacks. Disabled. + - name: "diamond" + include: false + runs: + run1: + n: 1 datasets: - label: dmmmegfr_string data_dir: datasets/egfr diff --git "a/t-datasetgit checkout yeast-dataset\357\200\232q" "b/t-datasetgit checkout yeast-dataset\357\200\232q" new file mode 100644 index 00000000..74570f66 --- /dev/null +++ "b/t-datasetgit checkout yeast-dataset\357\200\232q" @@ -0,0 +1,324 @@ + + SSUUMMMMAARRYY OOFF LLEESSSS CCOOMMMMAANNDDSS + + Commands marked with * may be preceded by a number, _N. + Notes in parentheses indicate the behavior if _N is given. + A key preceded by a caret indicates the Ctrl key; thus ^K is ctrl-K. + + h H Display this help. + q :q Q :Q ZZ Exit. + --------------------------------------------------------------------------- + + MMOOVVIINNGG + + e ^E j ^N CR * Forward one line (or _N lines). + y ^Y k ^K ^P * Backward one line (or _N lines). + ESC-j * Forward one file line (or _N file lines). + ESC-k * Backward one file line (or _N file lines). + f ^F ^V SPACE * Forward one window (or _N lines). + b ^B ESC-v * Backward one window (or _N lines). + z * Forward one window (and set window to _N). + w * Backward one window (and set window to _N). + ESC-SPACE * Forward one window, but don't stop at end-of-file. + ESC-b * Backward one window, but don't stop at beginning-of-file. + d ^D * Forward one half-window (and set half-window to _N). + u ^U * Backward one half-window (and set half-window to _N). + ESC-) RightArrow * Right one half screen width (or _N positions). + ESC-( LeftArrow * Left one half screen width (or _N positions). + ESC-} ^RightArrow Right to last column displayed. + ESC-{ ^LeftArrow Left to first column. + F Forward forever; like "tail -f". + ESC-F Like F but stop when search pattern is found. + r ^R ^L Repaint screen. + R Repaint screen, discarding buffered input. + --------------------------------------------------- + Default "window" is the screen height. + Default "half-window" is half of the screen height. + --------------------------------------------------------------------------- + + SSEEAARRCCHHIINNGG + + /_p_a_t_t_e_r_n * Search forward for (_N-th) matching line. + ?_p_a_t_t_e_r_n * Search backward for (_N-th) matching line. + n * Repeat previous search (for _N-th occurrence). + N * Repeat previous search in reverse direction. + ESC-n * Repeat previous search, spanning files. + ESC-N * Repeat previous search, reverse dir. & spanning files. + ^O^N ^On * Search forward for (_N-th) OSC8 hyperlink. + ^O^P ^Op * Search backward for (_N-th) OSC8 hyperlink. + ^O^L ^Ol Jump to the currently selected OSC8 hyperlink. + ESC-u Undo (toggle) search highlighting. + ESC-U Clear search highlighting. + &_p_a_t_t_e_r_n * Display only matching lines. + --------------------------------------------------- + Search is case-sensitive unless changed with -i or -I. + A search pattern may begin with one or more of: + ^N or ! Search for NON-matching lines. + ^E or * Search multiple files (pass thru END OF FILE). + ^F or @ Start search at FIRST file (for /) or last file (for ?). + ^K Highlight matches, but don't move (KEEP position). + ^R Don't use REGULAR EXPRESSIONS. + ^S _n Search for match in _n-th parenthesized subpattern. + ^W WRAP search if no match found. + ^L Enter next character literally into pattern. + --------------------------------------------------------------------------- + + JJUUMMPPIINNGG + + g < ESC-< * Go to first line in file (or line _N). + G > ESC-> * Go to last line in file (or line _N). + p % * Go to beginning of file (or _N percent into file). + t * Go to the (_N-th) next tag. + T * Go to the (_N-th) previous tag. + { ( [ * Find close bracket } ) ]. + } ) ] * Find open bracket { ( [. + ESC-^F _<_c_1_> _<_c_2_> * Find close bracket _<_c_2_>. + ESC-^B _<_c_1_> _<_c_2_> * Find open bracket _<_c_1_>. + --------------------------------------------------- + Each "find close bracket" command goes forward to the close bracket + matching the (_N-th) open bracket in the top line. + Each "find open bracket" command goes backward to the open bracket + matching the (_N-th) close bracket in the bottom line. + + m_<_l_e_t_t_e_r_> Mark the current top line with . + M_<_l_e_t_t_e_r_> Mark the current bottom line with . + '_<_l_e_t_t_e_r_> Go to a previously marked position. + '' Go to the previous position. + ^X^X Same as '. + ESC-m_<_l_e_t_t_e_r_> Clear a mark. + --------------------------------------------------- + A mark is any upper-case or lower-case letter. + Certain marks are predefined: + ^ means beginning of the file + $ means end of the file + --------------------------------------------------------------------------- + + CCHHAANNGGIINNGG FFIILLEESS + + :e [_f_i_l_e] Examine a new file. + ^X^V Same as :e. + :n * Examine the (_N-th) next file from the command line. + :p * Examine the (_N-th) previous file from the command line. + :x * Examine the first (or _N-th) file from the command line. + ^O^O Open the currently selected OSC8 hyperlink. + :d Delete the current file from the command line list. + = ^G :f Print current file name. + --------------------------------------------------------------------------- + + MMIISSCCEELLLLAANNEEOOUUSS CCOOMMMMAANNDDSS + + -_<_f_l_a_g_> Toggle a command line option [see OPTIONS below]. + --_<_n_a_m_e_> Toggle a command line option, by name. + __<_f_l_a_g_> Display the setting of a command line option. + ___<_n_a_m_e_> Display the setting of an option, by name. + +_c_m_d Execute the less cmd each time a new file is examined. + + !_c_o_m_m_a_n_d Execute the shell command with $SHELL. + #_c_o_m_m_a_n_d Execute the shell command, expanded like a prompt. + |XX_c_o_m_m_a_n_d Pipe file between current pos & mark XX to shell command. + s _f_i_l_e Save input to a file. + v Edit the current file with $VISUAL or $EDITOR. + V Print version number of "less". + --------------------------------------------------------------------------- + + OOPPTTIIOONNSS + + Most options may be changed either on the command line, + or from within less by using the - or -- command. + Options may be given in one of two forms: either a single + character preceded by a -, or a name preceded by --. + + -? ........ --help + Display help (from command line). + -a ........ --search-skip-screen + Search skips current screen. + -A ........ --SEARCH-SKIP-SCREEN + Search starts just after target line. + -b [_N] .... --buffers=[_N] + Number of buffers. + -B ........ --auto-buffers + Don't automatically allocate buffers for pipes. + -c ........ --clear-screen + Repaint by clearing rather than scrolling. + -d ........ --dumb + Dumb terminal. + -D xx_c_o_l_o_r . --color=xx_c_o_l_o_r + Set screen colors. + -e -E .... --quit-at-eof --QUIT-AT-EOF + Quit at end of file. + -f ........ --force + Force open non-regular files. + -F ........ --quit-if-one-screen + Quit if entire file fits on first screen. + -g ........ --hilite-search + Highlight only last match for searches. + -G ........ --HILITE-SEARCH + Don't highlight any matches for searches. + -h [_N] .... --max-back-scroll=[_N] + Backward scroll limit. + -i ........ --ignore-case + Ignore case in searches that do not contain uppercase. + -I ........ --IGNORE-CASE + Ignore case in all searches. + -j [_N] .... --jump-target=[_N] + Screen position of target lines. + -J ........ --status-column + Display a status column at left edge of screen. + -k _f_i_l_e ... --lesskey-file=_f_i_l_e + Use a compiled lesskey file. + -K ........ --quit-on-intr + Exit less in response to ctrl-C. + -L ........ --no-lessopen + Ignore the LESSOPEN environment variable. + -m -M .... --long-prompt --LONG-PROMPT + Set prompt style. + -n ......... --line-numbers + Suppress line numbers in prompts and messages. + -N ......... --LINE-NUMBERS + Display line number at start of each line. + -o [_f_i_l_e] .. --log-file=[_f_i_l_e] + Copy to log file (standard input only). + -O [_f_i_l_e] .. --LOG-FILE=[_f_i_l_e] + Copy to log file (unconditionally overwrite). + -p _p_a_t_t_e_r_n . --pattern=[_p_a_t_t_e_r_n] + Start at pattern (from command line). + -P [_p_r_o_m_p_t] --prompt=[_p_r_o_m_p_t] + Define new prompt. + -q -Q .... --quiet --QUIET --silent --SILENT + Quiet the terminal bell. + -r -R .... --raw-control-chars --RAW-CONTROL-CHARS + Output "raw" control characters. + -s ........ --squeeze-blank-lines + Squeeze multiple blank lines. + -S ........ --chop-long-lines + Chop (truncate) long lines rather than wrapping. + -t _t_a_g .... --tag=[_t_a_g] + Find a tag. + -T [_t_a_g_s_f_i_l_e] --tag-file=[_t_a_g_s_f_i_l_e] + Use an alternate tags file. + -u -U .... --underline-special --UNDERLINE-SPECIAL + Change handling of backspaces, tabs and carriage returns. + -V ........ --version + Display the version number of "less". + -w ........ --hilite-unread + Highlight first new line after forward-screen. + -W ........ --HILITE-UNREAD + Highlight first new line after any forward movement. + -x [_N[,...]] --tabs=[_N[,...]] + Set tab stops. + -X ........ --no-init + Don't use termcap init/deinit strings. + -y [_N] .... --max-forw-scroll=[_N] + Forward scroll limit. + -z [_N] .... --window=[_N] + Set size of window. + -" [_c[_c]] . --quotes=[_c[_c]] + Set shell quote characters. + -~ ........ --tilde + Don't display tildes after end of file. + -# [_N] .... --shift=[_N] + Set horizontal scroll amount (0 = one half screen width). + + --exit-follow-on-close + Exit F command on a pipe when writer closes pipe. + --file-size + Automatically determine the size of the input file. + --follow-name + The F command changes files if the input file is renamed. + --form-feed + Stop scrolling when a form feed character is reached. + --header=[_L[,_C[,_N]]] + Use _L lines (starting at line _N) and _C columns as headers. + --incsearch + Search file as each pattern character is typed in. + --intr=[_C] + Use _C instead of ^X to interrupt a read. + --lesskey-context=_t_e_x_t + Use lesskey source file contents. + --lesskey-src=_f_i_l_e + Use a lesskey source file. + --line-num-width=[_N] + Set the width of the -N line number field to _N characters. + --match-shift=[_N] + Show at least _N characters to the left of a search match. + --modelines=[_N] + Read _N lines from the input file and look for vim modelines. + --mouse + Enable mouse input. + --no-edit-warn + Don't warn when using v command on a file opened via LESSOPEN. + --no-keypad + Don't send termcap keypad init/deinit strings. + --no-histdups + Remove duplicates from command history. + --no-number-headers + Don't give line numbers to header lines. + --no-paste + Ignore pasted input. + --no-search-header-lines + Searches do not include header lines. + --no-search-header-columns + Searches do not include header columns. + --no-search-headers + Searches do not include header lines or columns. + --no-vbell + Disable the terminal's visual bell. + --redraw-on-quit + Redraw final screen when quitting. + --rscroll=[_C] + Set the character used to mark truncated lines. + --save-marks + Retain marks across invocations of less. + --search-options=[EFKNRW-] + Set default options for every search. + --show-preproc-errors + Display a message if preprocessor exits with an error status. + --proc-backspace + Process backspaces for bold/underline. + --PROC-BACKSPACE + Treat backspaces as control characters. + --proc-return + Delete carriage returns before newline. + --PROC-RETURN + Treat carriage returns as control characters. + --proc-tab + Expand tabs to spaces. + --PROC-TAB + Treat tabs as control characters. + --status-col-width=[_N] + Set the width of the -J status column to _N characters. + --status-line + Highlight or color the entire line containing a mark. + --use-backslash + Subsequent options use backslash as escape char. + --use-color + Enables colored text. + --wheel-lines=[_N] + Each click of the mouse wheel moves _N lines. + --wordwrap + Wrap lines at spaces. + + + --------------------------------------------------------------------------- + + LLIINNEE EEDDIITTIINNGG + + These keys can be used to edit text being entered + on the "command line" at the bottom of the screen. + + RightArrow ..................... ESC-l ... Move cursor right one character. + LeftArrow ...................... ESC-h ... Move cursor left one character. + ctrl-RightArrow ESC-RightArrow ESC-w ... Move cursor right one word. + ctrl-LeftArrow ESC-LeftArrow ESC-b ... Move cursor left one word. + HOME ........................... ESC-0 ... Move cursor to start of line. + END ............................ ESC-$ ... Move cursor to end of line. + BACKSPACE ................................ Delete char to left of cursor. + DELETE ......................... ESC-x ... Delete char under cursor. + ctrl-BACKSPACE ESC-BACKSPACE ........... Delete word to left of cursor. + ctrl-DELETE .... ESC-DELETE .... ESC-X ... Delete word under cursor. + ctrl-U ......... ESC (MS-DOS only) ....... Delete entire line. + UpArrow ........................ ESC-k ... Retrieve previous command line. + DownArrow ...................... ESC-j ... Retrieve next command line. + TAB ...................................... Complete filename & cycle. + SHIFT-TAB ...................... ESC-TAB Complete filename & reverse cycle. + ctrl-L ................................... Complete filename, list all. diff --git a/web/AKNIYET_README b/web/AKNIYET_README new file mode 100644 index 00000000..ae3c56f6 --- /dev/null +++ b/web/AKNIYET_README @@ -0,0 +1,25 @@ +Running web +#Possible error: + +1) npm command not found. + * try deactivating conda with "conda deactivate" + * You should make sure that you are downloading the file from the git hub link (the.exe file) + * make sure you are in spras-benchmarking-web/web + +2) When cloning from git, only the main branch shows up. First run "git branch -a", if the branches show up then it is there, but hidden. If this happens try to run "git checkout yeast-dataset". + +3) Sometimes an error occurs when building the website when certain methods arent being used, so use this command "rm -rf /c/Users/HP/spras-benchmarking/web/public/data/output/dmmmegfr_string-omicsintegrator2-params-7SW4MFI" -if not using omicsintegrator2 + need to create the commands for all of the algorithms + +The omicsdata1 ran and showed up on the website. I changed the uid/index.astro file and the paths.ts, no more universal, becasue it was uding dataSync, whcih shoul dmake it work for all types of OS's. , so the issue was in fact in the url. + +------------------------------------------------------------------------------------------------------------------------------------ +Instructions for loading the website +------------------------------------------------------------------------------------------------------------------------------------ + +Make a local copy of the the file and all the branches it contains (if other branches dont appear and you only have main then wirte command: ----) +Make sure you are in web directory (----) +Download all the necessary packages through the link (----) +Type command: "conda activate spras". Then type pnpm run build. If you are running only one + + diff --git a/web/pnpm-workspace.yaml b/web/pnpm-workspace.yaml new file mode 100644 index 00000000..f9a5b4c5 --- /dev/null +++ b/web/pnpm-workspace.yaml @@ -0,0 +1,4 @@ +allowBuilds: + '@parcel/watcher': true + esbuild: false + sharp: false diff --git a/web/src/lib/paths.ts b/web/src/lib/paths.ts index 9048e8e4..36787e36 100644 --- a/web/src/lib/paths.ts +++ b/web/src/lib/paths.ts @@ -1,19 +1,31 @@ import { extractDatasetCategory, extractDatasetType } from "./outputStyle"; import { globSync } from 'glob' +import path from 'path'; export function getDataFiles(): string[] { // We prefer this over import.meta.glob, as import.meta.glob currently // leads to OOM for large raw imports, and OOM is especially plausible on CD. - const dataFiles = globSync("public/data/output/**"); - return dataFiles.map((path) => path.substring("public/data/output/".length)); + //(1)const dataFiles = globSync("public/data/output/**", { windowsPathsNoEscape: true }); + const dataFiles = globSync("public/data/output/**", { windowsPathsNoEscape: true }); + return dataFiles + .map((path) => path.replace(/\\/g, "/")) + .map((path) => path.substring("public/data/output/".length)); } + export function getDatasets() { + const prefix=["logs", "datasets-"].join("/"); const files = getDataFiles(); + //console.log("hello"); + //console.log(files); + //(3)const universal= files.map((file) => file.replaceAll("\\", "/")); + //console.log(universal); + //console.log("bye"); + //(4)return universal return files - .filter((file) => file.startsWith("logs/datasets-")) - .map((file) => file.substring("logs/datasets-".length)) - .map((file) => file.slice(0, -".yaml".length)) - .map((file) => extractDatasetType(file)) - .map(({ type, name }) => ({ type, ...extractDatasetCategory(name) })); + .filter((file) => file.startsWith("logs/datasets-")) //just saves the logs\\datasets- files + .map((file) => file.substring("logs/datasets-".length)) //[ 'dmmmyeast.yaml', 'dmmmegfr_string.yaml', 'dmmmegfr_irefindex.yaml' ] + .map((file) => file.slice(0, -".yaml".length)) //[ 'dmmmyeast', 'dmmmegfr_string', 'dmmmegfr_irefindex' ] + .map((file) => extractDatasetType(file)) ////[{ type: 'dmmm', name: 'yeast' },{ type: 'dmmm', name: 'egfr_string' },{ type: 'dmmm', name: 'egfr_irefindex' }] + .map(({ type, name }) => ({ type, ...extractDatasetCategory(name) })); //[{ type: 'dmmm', category: 'yeast', name: '' },{ type: 'dmmm', category: 'egfr', name: 'string' },{ type: 'dmmm', category: 'egfr', name: 'irefindex' }] } diff --git a/web/src/pages/[uid]/index.astro b/web/src/pages/[uid]/index.astro index 9037417c..13a2f60e 100644 --- a/web/src/pages/[uid]/index.astro +++ b/web/src/pages/[uid]/index.astro @@ -12,6 +12,23 @@ import { getDataFiles } from "../../lib/paths"; import { Code } from "astro:components"; export function getStaticPaths() { + //const filteredPaths = new Set( + //console.log("uid filesssss") + //console.log(getDataFiles() + // .filter((path) => !path.startsWith("prepared")) + // .filter((path) => !path.startsWith("logs")) + // .filter((path) => path.includes("/")) + // .map((path) => path.split("/")[0]) + // .filter((path) => path.split("-").length === 4) + // .map((path) => path.replace("-params", "")), + //) + // Build a set of known log files so we can skip runs with no matching parameters file + const logFiles = new Set( + getDataFiles() + .filter((path) => path.startsWith("logs/parameters-")) + .map((path) => path.replace("logs/parameters-", "").replace(".yaml", "")) + ); + const filteredPaths = new Set( getDataFiles() // We can safely filter for these prefixes, as datasets start with their type. @@ -25,7 +42,14 @@ export function getStaticPaths() { // And we want to only have the dataset a-b-c-d params, not analysis ones .filter((path) => path.split("-").length === 4) // Then, we exclude -params- - .map((path) => path.replace("-params", "")), + .map((path) => path.replace("-params", "")) + // Skip any run that has no matching parameters log file or no pathway.txt (e.g. stale/failed/incomplete folders) + .filter((path) => { + const output = parseOutputString(path); + const hasLog = logFiles.has(`${output.algorithm}-params-${output.paramsHash}`); + const hasPathway = getDataFiles().some(f => f === `${asFolderName(output)}/pathway.txt`); + return hasLog && hasPathway; + }), ); return [...filteredPaths].map((path) => ({ params: { uid: styleOutput(parseOutputString(path)) } })); diff --git a/web/src/pages/index.astro b/web/src/pages/index.astro index 35a8be75..04d5e969 100644 --- a/web/src/pages/index.astro +++ b/web/src/pages/index.astro @@ -5,6 +5,8 @@ import { parseOutputString } from "../lib/outputStyle"; import { getStaticPaths } from "./[uid]/index.astro"; import Description from "./description.md"; +//console.log("labubu"); +//console.log(getStaticPaths()); //returns empty ---